Occupational health risk prediction method and device and computer equipment

By performing differential processing and quantitative evaluation of enterprise-related data, the problems of inaccurate and complexity of occupational health risk prediction in the existing technology are solved, and more efficient and accurate prediction results are achieved, which are suitable for multi-sample attribute correlation scenarios.

CN119067435APending Publication Date: 2024-12-03DAWNING CLOUD COMPUTING TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410985690.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The prior art has the problem of inaccurate prediction results in the prediction of occupational health risks of enterprises, and the process is complex, making it difficult to reduce the amount of data and improve efficiency.

Method used

By determining the state quantization values ​​of multiple groups of occupational health risk status based on enterprise-related data, performing differential processing to obtain reliability assessment results, and conducting occupational health risk prediction when the reliability assessment is passed, avoiding the participation of complex algorithms and reducing the data sensitivity.

Benefits of technology

It improves the accuracy and efficiency of occupational health risk prediction results, simplifies the prediction process, reduces data volume processing, and is suitable for various sample attribute correlations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067435A_ABST
    Figure CN119067435A_ABST
Patent Text Reader

Abstract

The invention relates to an occupational health risk prediction method and device and computer equipment. The method comprises the steps of determining state quantized values of a plurality of groups of occupational health risk states according to enterprise associated data of a target enterprise, performing difference processing according to each group of state quantized values to obtain a reliability evaluation result corresponding to the enterprise associated data, and when the reliability evaluation result is passed, determining that the target enterprise is in an occupational health risk state. And predicting the occupational health risk of the target enterprise based on the enterprise associated data. According to the method, the enterprise associated data required for predicting the occupational health risk of the target enterprise is subjected to reliability evaluation, so that the occupational health risk is further predicted for the passed enterprise associated data through the reliability evaluation result; according to the process, occupational health risk prediction can be realized through enterprise associated data with relatively high reliability, so that the accuracy of a prediction result is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of occupational health prediction, and in particular to an occupational health risk prediction method, device and computer equipment. Background Art

[0002] As people's material living standards continue to improve, their demand for health is also increasing.

[0003] Take occupational health as an example. Occupational health refers to a state in which people maintain physical and mental health in the working environment. Therefore, it is particularly important to predict the occupational health risks of enterprises.

[0004] However, in the related art, there is a problem of inaccurate prediction results when predicting occupational health risks of enterprises. Summary of the invention

[0005] Based on this, it is necessary to provide an occupational health risk prediction method, device and computer equipment to address the above technical problems, which can improve the accuracy of occupational health risk prediction results.

[0006] In a first aspect, an embodiment of the present application provides a method for predicting occupational health risks, the method comprising:

[0007] Determine the status quantification values ​​of multiple groups of occupational health risk statuses based on the enterprise-related data of the target enterprise;

[0008] Perform difference processing based on the state quantification values ​​of each group to obtain the reliability assessment results corresponding to the enterprise-related data;

[0009] If the reliability assessment result is passed, the occupational health risks of the target enterprise are predicted based on the enterprise-related data.

[0010] The technical solution in the embodiment of the present application determines multiple groups of state quantification values ​​of occupational health risk states according to the enterprise-related data of the target enterprise, performs difference processing according to each group of state quantification values, obtains the reliability evaluation results corresponding to the enterprise-related data, and predicts the occupational health risks of the target enterprise based on the enterprise-related data when the reliability evaluation result is passed; the above method can first perform reliability evaluation on the enterprise-related data required for the occupational health risk prediction of the target enterprise, so that the occupational health risk is further predicted through the enterprise-related data with a reliability evaluation result of passed. This process can ensure that the occupational health risk prediction is achieved through the enterprise-related data with higher reliability, thereby improving the accuracy of the prediction result; at the same time, compared with the traditional technology, the above method does not require the participation of complex algorithms, has a lower implementation difficulty, can reduce the complexity of the occupational health risk prediction process, thereby reducing the amount of data processed in the prediction process, and improving the speed and efficiency of occupational health risk prediction; in addition, the above method is insensitive to the enterprise-related data to be processed, thereby avoiding the process of formatting the enterprise-related data, making the occupational health risk prediction process relatively simple; furthermore, the above method does not require the assumption of independence of sample attributes (i.e., enterprise-related data), so even if the sample attributes are related, the prediction effect of occupational health risk can be improved.

[0011] In one embodiment, performing difference processing according to each group of state quantization values ​​to obtain a reliability evaluation result corresponding to the enterprise-related data includes:

[0012] Perform paired sample difference detection processing according to each group of state quantization values ​​to obtain the reliability effective evaluation index value of each group of state quantization values;

[0013] When the reliability effective evaluation index value is less than the preset threshold, the reliability evaluation result of the enterprise-related data is determined according to the state quantification value of each group.

[0014] The technical solution in the embodiment of the present application performs paired sample difference detection processing according to each group of state quantization values ​​to obtain the reliability effective evaluation index value of each group of state quantization values, and when the reliability effective evaluation index value is less than a preset threshold, the reliability evaluation result of the enterprise-related data is determined according to each group of state quantization values; the above method can first obtain the reliability effective evaluation index value of each group of state quantization values, and only determine the reliability evaluation result of the enterprise-related data according to each group of state quantization values ​​when it is determined that the reliability effective evaluation index value meets the reliability effective evaluation condition, so that the accuracy of the reliability evaluation result of the determined enterprise-related data is higher; the above method can obtain the reliability effective evaluation index value of each group of state quantization values ​​through a mathematical method, that is, paired sample difference detection, and the processing process is relatively simple, which reduces the complexity of the reliability effective evaluation index value acquisition process.

[0015] In one embodiment, paired sample difference detection processing is performed according to each group of state quantization values ​​to obtain the reliability effective evaluation index value of the enterprise association data, including:

[0016] Determine a plurality of first paired data and a plurality of second paired data according to each group of state quantization values;

[0017] Determine a plurality of third pairing data according to each of the first pairing data and each of the second pairing data;

[0018] A paired sample difference test is performed based on each third paired data to determine the reliability validity evaluation index value.

[0019] The technical solution in the embodiment of the present application determines a plurality of first paired data and a plurality of second paired data according to each group of state quantization values, determines a plurality of third paired data according to each first paired data and each second paired data, and performs a paired sample difference test based on each third paired data to determine a reliability effective evaluation index value; the above method does not require the participation of a complex algorithm, and can obtain the reliability effective evaluation index value of the enterprise-related data only through a simple data method (i.e., paired sample difference test), thereby reducing the amount of data required to be processed when obtaining the reliability effective evaluation index value of the enterprise-related data, thereby improving the speed and efficiency of obtaining the reliability effective evaluation index value of the enterprise-related data; at the same time, the above method can perform a paired sample difference test through the third paired data formed by the historical state quantization value and the current state quantization value, so that some data that may affect the reliability effective evaluation index value can be paired, which can eliminate the interference caused by these influencing factors, reduce the error of the obtained reliability effective evaluation index value, thereby improving the accuracy of the obtained reliability effective evaluation index value, and in addition, the paired sample difference is realized through the paired third paired data.

[0020] In one embodiment, the state quantization value includes a historical state quantization value and a current state quantization value; and according to each group of state quantization values, a plurality of first paired data and a plurality of second paired data are determined, including:

[0021] Obtain the historical state mean and historical state standard deviation corresponding to each group of historical state quantization values; and obtain the current state mean and current state standard deviation corresponding to each group of current state quantization values;

[0022] A plurality of first paired data are determined according to each historical state mean value and each historical state standard deviation; and a plurality of second paired data are determined according to each current state mean value and each current state standard deviation.

[0023] The technical solution in the embodiment of the present application obtains the historical state mean and the historical state standard deviation corresponding to each group of historical state quantization values, and obtains the current state mean and the current state standard deviation corresponding to each group of current state quantization values, and determines multiple first paired data based on each historical state mean and each historical state standard deviation, and determines multiple second paired data based on each current state mean and each current state standard deviation; the above method does not require the participation of complex algorithms, and the processing process is relatively simple, thereby improving the speed and efficiency of obtaining the first paired data and the second paired data; in addition, the data relied on by the above method when obtaining the reliability assessment results corresponding to the enterprise-related data include both the historical state quantization values ​​and the current state quantization values, so that the data relied on when obtaining the reliability assessment results corresponding to the enterprise-related data is relatively comprehensive, which can greatly improve the accuracy of the obtained reliability assessment results.

[0024] In one embodiment, the state quantization value includes a historical state quantization value and a current state quantization value; and determining the reliability evaluation result of the enterprise-related data according to each group of state quantization values ​​includes:

[0025] Determine multiple groups of pairing results according to each group of historical state quantization values ​​and each group of current state quantization values;

[0026] Determine the mean of the statistic according to the statistic of each group of paired results; and determine the mean of the significance level according to the significance level of each group of paired results;

[0027] Perform difference analysis based on the statistical mean and significance level to determine the difference analysis results;

[0028] Obtain the reliability assessment results of enterprise-related data based on the difference analysis results.

[0029] The technical solution in the embodiment of the present application determines multiple groups of pairing results according to each group of historical state quantization values ​​and each group of current state quantization values, determines the statistical mean according to the statistics of each group of pairing results, and determines the significance level average according to the significance level of each group of pairing results, performs difference analysis processing according to the statistical mean and the significance level average to determine the difference analysis result, and obtains the reliability evaluation result of the enterprise-related data according to the difference analysis result; the above method does not require the participation of complex algorithms, and the processing process is relatively simple, thereby reducing the amount of data processed for obtaining the reliability evaluation result of the enterprise-related data, and accelerating the speed and efficiency of obtaining the reliability evaluation result of the enterprise-related data; at the same time, the above method does not require human participation, thereby reducing human participation errors and improving the accuracy of the obtained reliability evaluation results.

[0030] In one embodiment, performing difference analysis processing according to the statistical mean and the significance level to determine the difference analysis result includes:

[0031] Determine a first difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the statistic mean; and determine a second difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the significance level mean;

[0032] A difference analysis result is determined according to the first difference result and the second difference result.

[0033] This embodiment does not require the participation of complex algorithms and the processing process is relatively simple, thereby reducing the amount of data processed to determine the difference analysis results and accelerating the speed and efficiency of determining the difference analysis results.

[0034] In one embodiment, predicting occupational health risks of a target enterprise based on enterprise-related data includes:

[0035] Obtain statistical peak values ​​based on multiple groups of pairing results corresponding to enterprise-related data;

[0036] Determine the occupational health risk prediction results of the target enterprise based on statistical peaks and enterprise-related data.

[0037] The technical solution in the embodiment of the present application obtains statistical peaks based on multiple groups of pairing results corresponding to the enterprise-related data, and determines the occupational health risk prediction results of the target enterprise based on the statistical peaks and the enterprise-related data; the above method can predict the occupational health risks of the target enterprise based on the enterprise-related data when the reliability assessment result of the enterprise-related data of the target enterprise is passed, thereby greatly improving the accuracy and reliability of the occupational health risk prediction of the target enterprise.

[0038] In one embodiment, based on the enterprise-related data of the target enterprise, determining the state quantification values ​​of multiple groups of occupational health risk states includes:

[0039] According to the enterprise-related data, multiple groups of health risk status corresponding to different occupational health risk levels of the target enterprise are obtained;

[0040] The occupational health risk status of each group is quantified to obtain the quantitative value of each group of status.

[0041] The technical solution in the embodiment of the present application obtains multiple groups of health risk states corresponding to different occupational health risk levels of the target enterprise based on enterprise-related data, and quantifies each group of occupational health risk states to obtain each group of state quantization values; the above method does not require the participation of complex algorithms, and the processing process is relatively simple, thereby reducing the amount of data processed to obtain the state quantization values ​​and speeding up the acquisition speed and efficiency of the state quantization values; at the same time, the above method does not require human participation, thereby reducing human participation errors and improving the accuracy of the obtained state quantization values.

[0042] In a second aspect, an embodiment of the present application provides an occupational health risk prediction device, the device comprising:

[0043] A quantitative value acquisition module is used to determine the status quantitative values ​​of multiple groups of occupational health risk statuses according to the enterprise-related data of the target enterprise;

[0044] A processing module is used to perform difference processing according to each group of state quantization values ​​to obtain the reliability evaluation results corresponding to the enterprise-related data;

[0045] The prediction module is used to predict the occupational health risks of the target enterprise based on the enterprise-related data when the reliability assessment result is passed.

[0046] In a third aspect, an embodiment of the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of any one of the embodiments of the first aspect when executing the computer program.

[0047] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method of any embodiment in the above-mentioned first aspect are implemented.

[0048] In a fifth aspect, an embodiment of the present application further provides a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method of any embodiment of the first aspect above.

[0049] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is an application environment diagram of an occupational health risk prediction method in an embodiment;

[0051] Figure 2 A flowchart of an occupational health risk prediction method in one embodiment;

[0052] Figure 3 A schematic diagram of a flow chart of an occupational health risk prediction method in another embodiment;

[0053] Figure 4 A schematic diagram of a flow chart of an occupational health risk prediction method in another embodiment;

[0054] Figure 5 A schematic diagram of a flow chart of an occupational health risk prediction method in another embodiment;

[0055] Figure 6 A schematic diagram of a flow chart of an occupational health risk prediction method in another embodiment;

[0056] Figure 7 A schematic diagram of a flow chart of an occupational health risk prediction method in another embodiment;

[0057] Figure 8 A schematic diagram of a flow chart of an occupational health risk prediction method in another embodiment;

[0058] Fig. 9 A schematic diagram of a flow chart of an occupational health risk prediction method in another embodiment;

[0059] Fig.10 is a structural block diagram of an occupational health risk prediction device in one embodiment;

[0060] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] In the field of health, especially occupational health, is closely related to people's daily working environment. Therefore, in order to ensure that people can work in a safe environment, it is particularly important to predict the occupational health risks of an enterprise. In the related art, the Bayesian estimation algorithm is mainly used to predict the occupational health risks of an enterprise. However, the process of predicting the occupational health risks of an enterprise in the related art is relatively complicated, and there may be problems with inaccurate prediction results. Based on this, an embodiment of the present application provides an occupational health risk prediction method that can improve the accuracy of occupational health risk prediction results.

[0063] The occupational health risk prediction method provided in the embodiment of the present application can be applied to Figure 1 The application environment diagram shown. The application environment includes a computer device and a management system for enterprise-related data corresponding to multiple different enterprises. Optionally, the management system may include data centers of multiple different government management departments (such as the Health Commission, the Human Resources and Social Security Bureau, the Market Supervision Bureau, etc.) for supervising enterprise-related data. Optionally, each data center can be a data management device, and can also be a database system, etc., which is not limited to this embodiment of the present application. Among them, the computer device and each data center can be a communication connection, and the communication method can be Wi-Fi, mobile network or Bluetooth connection, etc. Optionally, the above-mentioned computer device and data management device can be, but not limited to, electronic devices with data processing functions such as personal computers, laptops, tablet computers, iPads, etc., and this embodiment does not limit the specific form of the computer device. The following embodiment of the present application uses a computer device as the execution subject of the occupational health risk prediction method to introduce the specific process of the occupational health risk prediction method.

[0064] like Figure 2 FIG. 1 is a flow chart of an occupational health risk prediction method provided in an embodiment of the present application, and the method can be implemented by the following steps:

[0065] S100. Determine, based on the enterprise-related data of the target enterprise, the status quantification values ​​of multiple groups of occupational health risk statuses.

[0066] In practical applications, the target enterprise can be any type of enterprise, such as communications enterprises, transportation enterprises, construction enterprises, medical and health enterprises, wholesale and retail enterprises, etc. Among them, the computer device can obtain valid data required for occupational health risk prediction of the target enterprise within a period of time, that is, enterprise-related data. Optionally, the above period of time can be the time corresponding to the current time and a continuous time period before the current time. Optionally, the above enterprise-related data can be understood as enterprise information related to the target enterprise and employee information of all employees. Optionally, all employees in the above target enterprise can include currently resigned employees and currently serving employees.

[0067] The original data may be obtained from various data centers of the management system. Optionally, the enterprise-related data may include employment registration information and medical insurance treatment information of each employee in the target enterprise, as well as enterprise attribute information and enterprise penalty information of the target enterprise.

[0068] Optionally, the employment registration information of any employee in the above-mentioned target enterprise may include the name, ID number, target enterprise name and unified social credit code of the employee in the target enterprise; the medical insurance treatment information of any employee in the above-mentioned target enterprise may include the name, ID number, insurance information, medical institution, unified social credit code of the medical institution, insurance status, insurance time, etc. of the employee in the target enterprise; the enterprise attribute information of the above-mentioned target enterprise may include the enterprise name, unified social credit code, enterprise type, business scope, whether the target enterprise is an enterprise certified for occupational disease hazards, enterprise recognition scope, etc.; the enterprise penalty information of the above-mentioned target enterprise may include the administrative penalty data of the target enterprise, relevant descriptions of occupational disease risks caused by abnormal production, etc.

[0069] Specifically, the computer device can group the enterprise-related data according to the time period corresponding to the enterprise-related data of the target enterprise to obtain multiple groups of data to be processed, and then determine the state quantification values ​​of multiple groups of occupational health risk states according to each group of data to be processed. It should be noted here that the time periods corresponding to the above different groups of data to be processed are different, and the time periods corresponding to the different groups of data to be processed can be equal or unequal in length.

[0070] In one implementation, a computer device can pre-train an algorithm model, and then for any set of data to be processed, the data to be processed is input into the algorithm model, and the algorithm model outputs a state quantification value corresponding to a set of occupational health risk states.

[0071] In another implementation, for any group of data to be processed, the computer device can search for the data to be processed in the association relationship between different data and different occupational health risk status quantification values, and determine the occupational health risk status quantification value corresponding to the data matching the data to be processed as the status quantification value corresponding to a group of occupational health risk states.

[0072] In addition, there may be multiple levels of occupational health risks; for different occupational health risk levels, the occupational health risk states corresponding to the same set of data to be processed may be the same or different.

[0073] S200, performing difference processing according to each group of state quantization values ​​to obtain reliability assessment results corresponding to the enterprise-related data.

[0074] Specifically, the computer device may use a difference analysis method to perform difference processing on each group of state quantization values ​​to obtain the reliability evaluation result corresponding to the enterprise-related data. Optionally, the difference analysis method may be, but is not limited to, a parameter test method or a non-parameter test method.

[0075] It should be noted here that the reliability evaluation result corresponding to the enterprise-related data can be understood as the result of the reliability evaluation of the enterprise-related data required for predicting the occupational health risks of the target enterprise. Optionally, the reliability evaluation result corresponding to the enterprise-related data can be passed or failed.

[0076] S300: When the reliability assessment result is passed, the occupational health risks of the target enterprise are predicted based on the enterprise-related data.

[0077] In actual applications, when the reliability assessment result corresponding to the enterprise-related data is passed, it indicates that the prediction accuracy of the enterprise-related data application in predicting the occupational health risks of the target enterprise is high; when the reliability assessment result corresponding to the enterprise-related data is failed, it indicates that the prediction accuracy of the enterprise-related data application in predicting the occupational health risks of the target enterprise is low.

[0078] Specifically, the computer device can use a prediction algorithm to predict the occupational health risks of the target enterprise based on the enterprise-related data to obtain the occupational health risk level of the target enterprise.

[0079] Optionally, the above prediction algorithm may be, but is not limited to, a qualitative prediction method, a differential equation model, a grey prediction model, a Markov prediction model or a time series analysis method.

[0080] The technical solution in the embodiment of the present application determines multiple groups of state quantification values ​​of occupational health risk states according to the enterprise-related data of the target enterprise, performs difference processing according to each group of state quantification values, obtains the reliability evaluation results corresponding to the enterprise-related data, and predicts the occupational health risks of the target enterprise based on the enterprise-related data when the reliability evaluation result is passed; the above method can first perform reliability evaluation on the enterprise-related data required for the occupational health risk prediction of the target enterprise, so that the occupational health risk is further predicted through the enterprise-related data with a reliability evaluation result of passed. This process can ensure that the occupational health risk prediction is achieved through the enterprise-related data with higher reliability, thereby improving the accuracy of the prediction result; at the same time, compared with the traditional technology, the above method does not require the participation of complex algorithms, has a lower implementation difficulty, can reduce the complexity of the occupational health risk prediction process, thereby reducing the amount of data processed in the prediction process, and improving the speed and efficiency of occupational health risk prediction; in addition, the above method is insensitive to the enterprise-related data to be processed, thereby avoiding the process of formatting the enterprise-related data, making the occupational health risk prediction process relatively simple; furthermore, the above method does not require the assumption of independence of sample attributes (i.e., enterprise-related data), so even if the sample attributes are related, the prediction effect of occupational health risk can be improved.

[0081] The following is a description of the process of performing difference processing on the state quantization values ​​of each group to obtain the reliability evaluation result corresponding to the enterprise association data. Figure 3 As shown, the steps in S200 above can be implemented in the following manner:

[0082] S210 , performing paired sample difference detection processing according to each group of state quantization values, and obtaining reliability effective evaluation index values ​​of each group of state quantization values.

[0083] In practical applications, a computer device can pre-train a paired sample difference detection model, and then for any group of state quantization values, the current group of state quantization values ​​is input into the paired sample difference detection model, and the paired sample difference detection model performs paired sample difference detection processing and outputs a reliability effectiveness evaluation index value for the group of state quantization values.

[0084] Optionally, the above-mentioned paired sample difference detection model can be implemented by at least one of a convolutional neural network model, a fully connected neural network model, a long short-term memory neural network model, a recurrent neural network model, etc.

[0085] It should be noted here that the reliability effective evaluation index of each group of state quantization values ​​can be understood as a reliability measurement index for subsequently determining the reliability evaluation result of the enterprise-related data through each group of state quantization values.

[0086] S220: When the reliability effective evaluation index value is less than a preset threshold, determine the reliability evaluation result of the enterprise-related data according to each group of state quantization values.

[0087] Optionally, the preset threshold value may be any positive number, may be user-defined, or may be determined based on historical experience, which is not limited in the present embodiment. In the present embodiment, the preset threshold value of 0.05 is taken as an example for explanation.

[0088] In an embodiment of the present application, when it is determined that the reliability effective evaluation index value of each group of state quantization values ​​meets the reliability effective evaluation conditions, that is, when each reliability effective evaluation index value is greater than a preset threshold, it indicates that each group of state quantization values ​​can reliably and effectively determine the reliability evaluation result of the enterprise-related data, and then determine the reliability evaluation result of the enterprise-related data based on each group of state quantization values.

[0089] In practical applications, the computer device can perform statistical and / or arithmetic operations based on each group of state quantization values ​​to determine the reliability assessment results of the enterprise-related data.

[0090] Optionally, the arithmetic operation may include at least one of addition, subtraction, multiplication, division, logarithmic operation, weighted summation, etc.

[0091] The technical solution in the embodiment of the present application performs paired sample difference detection processing according to each group of state quantization values ​​to obtain the reliability effective evaluation index value of each group of state quantization values, and when the reliability effective evaluation index value is less than a preset threshold, the reliability evaluation result of the enterprise-related data is determined according to each group of state quantization values; the above method can first obtain the reliability effective evaluation index value of each group of state quantization values, and only determine the reliability evaluation result of the enterprise-related data according to each group of state quantization values ​​when it is determined that the reliability effective evaluation index value meets the reliability effective evaluation condition, so that the accuracy of the reliability evaluation result of the determined enterprise-related data is higher; the above method can obtain the reliability effective evaluation index value of each group of state quantization values ​​through a mathematical method, that is, paired sample difference detection, and the processing process is relatively simple, which reduces the complexity of the reliability effective evaluation index value acquisition process.

[0092] The following is an explanation of the above paired sample difference detection process. Figure 4 As shown, the step of performing paired sample difference detection processing according to each group of state quantization values ​​in the above S210 to obtain the reliability effective evaluation index value of the enterprise association data can be implemented in the following way:

[0093] S211 . Determine a plurality of first paired data and a plurality of second paired data according to each group of state quantization values.

[0094] In practical applications, for any set of state quantization values, the computer device may perform a first arithmetic operation on the current set of state quantization values ​​to obtain a first pairing data, and perform a second arithmetic operation on the current set of state quantization values ​​to obtain a second pairing data. In the implementation of this application, the first arithmetic operation and the second arithmetic operation may be different.

[0095] S212: Determine a plurality of third pairing data according to each of the first pairing data and each of the second pairing data.

[0096] Furthermore, for the first paired data and the second paired data corresponding to any set of state quantization values, a third arithmetic operation may be performed on the first paired data and the second paired data to obtain corresponding third paired data.

[0097] The third arithmetic operation process may be different from the first arithmetic operation process and the second arithmetic operation process. In the embodiment of the present application, the third arithmetic operation process may be an addition operation or a subtraction operation.

[0098] For example, if the first paired data corresponding to any set of state quantization values ​​is A, and the corresponding second paired data is B, then the corresponding third paired data may be equal to A±B.

[0099] S213: Perform a paired sample difference test based on each third paired data to determine a reliability validity evaluation index value.

[0100] The computer device may perform a paired sample difference test on each third paired data to obtain a reliability effective evaluation index value corresponding to each group of state quantization values.

[0101] Optionally, the paired sample difference test may be a parameter test method, which may be a z test method, a chi-square variance test method, etc. In an embodiment of the present application, the paired sample difference test may be a t test method among the parameter test methods.

[0102] In the embodiment of the present application, the above paired sample difference test process can be described as: calculating the mean m of each third paired data, calculating the standard deviation S of each third paired data, and then calculating the paired sample t test t value n represents the total number of third paired data, wherein the degree of freedom represents df and the test level represents α in the paired sample t test process. Further, the significance level P can be found in the boundary value table (determined by the degree of freedom and the test level). If the t value is less than the significance level P at the α level, it indicates that the significance level P at the t value is greater than α (taking α equal to 0.05 as an example), that is, there is no significance between the third paired data; if the t value is greater than the significance level P at the α level, it indicates that the significance level P at the t value is less than α, that is, there is significance between the third paired data. In this case, it is determined that the reliability effective evaluation index value meets the reliability effective evaluation condition. It should be noted here that the above reliability effective evaluation index value can be represented by the significance level P value.

[0103] The technical solution in the embodiment of the present application determines a plurality of first paired data and a plurality of second paired data according to each group of state quantization values, determines a plurality of third paired data according to each first paired data and each second paired data, and performs a paired sample difference test based on each third paired data to determine the reliability effective evaluation index value; the above method does not require the participation of a complex algorithm, and can obtain the reliability effective evaluation index value of the enterprise-related data only through a simple data method (i.e., paired sample difference test), thereby reducing the amount of data required to be processed when obtaining the reliability effective evaluation index value of the enterprise-related data, thereby improving the speed and efficiency of obtaining the reliability effective evaluation index value of the enterprise-related data; at the same time, the above method can perform a paired sample difference test through the third paired data formed by the historical state quantization value and the current state quantization value, so that some data that may affect the reliability effective evaluation index value can be paired, which can eliminate the interference caused by these influencing factors, reduce the error of the obtained reliability effective evaluation index value, and thus improve the accuracy of the obtained reliability effective evaluation index value. In addition, the paired sample difference test is implemented through the paired third paired data, which can also reduce the large calculation error caused by the independent state quantization value in the case of large data volume.

[0104] In one embodiment, the state quantization value includes a historical state quantization value and a current state quantization value; Figure 5 As shown, the step of determining a plurality of first paired data and a plurality of second paired data according to each group of state quantization values ​​in the above S211 may include:

[0105] S2111. Obtain the historical state mean and the historical state standard deviation corresponding to each group of historical state quantization values; and obtain the current state mean and the current state standard deviation corresponding to each group of current state quantization values.

[0106] In practical applications, each group of state quantization values ​​includes multiple groups of historical state quantization values ​​and multiple groups of current state quantization values. In the embodiment of the present application, the number of groups of historical state quantization values ​​and current state quantization values ​​is the same.

[0107] For example, there are 5 groups of state quantization values, and the time periods corresponding to each group of state quantization values ​​are A1-A2, A2-A3, A3-A4, A4-A5, A5-A6, and A6-A7, respectively. A1, A2, A3, A4, A5, A6, and A7 are all time points arranged in chronological order, and A7 is the current time point. Then the above historical state quantization values ​​may include the state quantization values ​​corresponding to the time periods A1-A2, A2-A3, and A3-A4, and the above current state quantization values ​​may include the state quantization values ​​corresponding to the time periods A4-A5, A5-A6, and A6-A7. That is, the time period corresponding to the historical state quantization values ​​is earlier, and the time period corresponding to the current state quantization values ​​is later.

[0108] Specifically, for any group of historical state quantization values, the group of historical state quantization values ​​can be averaged to obtain the historical state mean corresponding to the group of historical state quantization values; at the same time, the standard deviation of the group of historical state quantization values ​​can be calculated to obtain the historical state standard deviation corresponding to the group of historical state quantization values.

[0109] In addition, for any group of current state quantization values, the group of current state quantization values ​​can be averaged to obtain the current state mean corresponding to the group of current state quantization values; at the same time, the standard deviation of the group of current state quantization values ​​can be calculated to obtain the current state standard deviation corresponding to the group of current state quantization values.

[0110] S2112: Determine a plurality of first paired data according to each historical state mean value and each historical state standard deviation; and determine a plurality of second paired data according to each current state mean value and each current state standard deviation.

[0111] In practical applications, each set of historical state quantization values ​​corresponds to a historical state mean and a historical state standard deviation. Specifically, the computer device can perform arithmetic operation processing on the historical state mean and the historical state standard deviation corresponding to each set of historical state quantization values ​​to obtain a first pairing data. In the embodiment of the present application, the arithmetic operation processing here can be an addition operation processing or a subtraction operation processing.

[0112] For example, if the historical state mean corresponding to any group of historical state quantization values ​​is A1, and the corresponding historical state standard deviation is B1, then the first paired data corresponding to the group of historical state quantization values ​​may be equal to A1±B1.

[0113] At the same time, each group of current state quantization values ​​corresponds to a current state mean and a current state standard deviation. Specifically, the computer device can perform arithmetic operation processing on the current state mean and the current state standard deviation corresponding to each group of current state quantization values ​​to obtain a second pairing data. In the embodiment of the present application, the arithmetic operation processing here can also be an addition operation processing or a subtraction operation processing.

[0114] For example, if the current state mean corresponding to any set of current state quantization values ​​is A2 and the corresponding current state standard deviation is B2, then the second paired data corresponding to the set of current state quantization values ​​may be equal to A2±B2.

[0115] The technical solution in the embodiment of the present application obtains the historical state mean and the historical state standard deviation corresponding to each group of historical state quantization values, and obtains the current state mean and the current state standard deviation corresponding to each group of current state quantization values, and determines multiple first paired data based on each historical state mean and each historical state standard deviation, and determines multiple second paired data based on each current state mean and each current state standard deviation; the above method does not require the participation of complex algorithms, and the processing process is relatively simple, thereby improving the speed and efficiency of obtaining the first paired data and the second paired data; in addition, the data relied on by the above method when obtaining the reliability assessment results corresponding to the enterprise-related data include both the historical state quantization values ​​and the current state quantization values, so that the data relied on when obtaining the reliability assessment results corresponding to the enterprise-related data is relatively comprehensive, which can greatly improve the accuracy of the obtained reliability assessment results.

[0116] The following is an explanation of the process of determining the reliability evaluation results of enterprise-related data based on each group of state quantization values. In one embodiment, the state quantization values ​​include historical state quantization values ​​and current state quantization values; Figure 6 As shown, the step of determining the reliability evaluation result of the enterprise-related data according to each group of state quantization values ​​in the above S220 can be implemented in the following manner:

[0117] S221 . Determine multiple groups of pairing results according to each group of historical state quantization values ​​and each group of current state quantization values.

[0118] In practical applications, for each set of historical state quantization values ​​and the corresponding set of current state quantization values, each quantization value in the set of historical state quantization values ​​can be subtracted from each quantization value in the corresponding set of current state quantization values ​​to obtain the corresponding pairing result of the set.

[0119] S222. Determine a statistical mean according to the statistical quantity of each group of pairing results; and determine a significance level average according to the significance level of each group of pairing results.

[0120] In practical applications, for each group of pairing results, the average value and standard deviation of the pairing results can be calculated to obtain the pairing result mean and the pairing result standard deviation, and then arithmetic operations are performed based on the pairing result mean, the pairing result standard deviation and the number of data in the pairing results to obtain statistics.

[0121] In the embodiment of the present application, the statistic t of the pairing result group can be expressed by the following formula:

[0122]

[0123] in, represents the mean of the pairing results of this group; s drepresents the standard deviation of the pairing results of this group; n represents the number of data in this group of pairing results; μ = μ 0 is true, it obeys the t distribution with (n-1) degrees of freedom. In the embodiment of the present application, μ 0 is equal to 0.

[0124] Furthermore, the statistics corresponding to all group pairing results can be averaged to obtain the statistical mean.

[0125] At the same time, for each set of pairing results, the computer device can perform a normality test on the pairing results to obtain the significance level of the pairing results. Optionally, the normality test method can be, but is not limited to, the Shapiro-Wilk test or the Kolmonov-Smirnov test. In the embodiment of the present application, the type of normality test method can be determined according to the number of each set of pairing results.

[0126] In addition, the significance levels of all group pairing results can be averaged to obtain the average significance level.

[0127] S223. Perform difference analysis processing based on the statistical mean and significance level, and determine the difference analysis result.

[0128] In practical applications, a computer device can pre-train an algorithm model, and then input both the statistical mean and the significance level into the algorithm model. The algorithm model performs difference analysis processing based on the statistical mean and the significance level and outputs the difference analysis result.

[0129] In addition, the computer device can perform arithmetic operations on the statistical mean and the significance level average to complete the difference analysis processing based on the statistical mean and the significance level average to obtain the difference analysis results.

[0130] In one embodiment, if Figure 7 As shown, the step of performing difference analysis processing according to the statistical mean and the significance level mean in the above S223 to determine the difference analysis result can be achieved in the following way:

[0131] S2231. Determine a first difference result based on the absolute value of the difference between the statistic mean and the significance level mean and the statistic mean; and determine a second difference result based on the absolute value of the difference between the statistic mean and the significance level mean and the significance level mean.

[0132] Among them, the absolute value of the difference between the statistical mean and the significance level mean and the statistical mean can be subjected to arithmetic operation to obtain a first difference result; and the absolute value of the difference between the statistical mean and the significance level mean and the significance level mean can be subjected to arithmetic operation to obtain a second difference result.

[0133] In the embodiment of the present application, the absolute value of the difference between the statistic mean and the significance level average can be subtracted from the statistic mean and then the absolute value is taken to obtain the first difference result. 1 It can be expressed as:

[0134]

[0135] Among them, the above Represents the mean significance level.

[0136] At the same time, the absolute value of the difference between the statistical mean and the significance level average can be subtracted from the significance level average to obtain the second difference result. 2 It can be expressed as:

[0137]

[0138] S2232. Determine a difference analysis result according to the first difference result and the second difference result.

[0139] The first difference result and the second difference result may be subjected to arithmetic operation to obtain a difference analysis result.

[0140] In the embodiment of the present application, a weighted sum process may be performed on the first difference result and the second difference result to obtain a difference analysis result.

[0141] This embodiment does not require the participation of complex algorithms and the processing process is relatively simple, thereby reducing the amount of data processed to determine the difference analysis results and accelerating the speed and efficiency of determining the difference analysis results.

[0142] S224. Obtain reliability assessment results of the enterprise-related data based on the difference analysis results.

[0143] Among them, based on the difference analysis results obtained in the previous steps, the difference analysis results can be quantitatively analyzed to determine the reliability assessment results of the enterprise-related data.

[0144] In an embodiment of the present application, the reliability assessment level corresponding to the difference analysis result can be determined according to the reliability assessment level classification information, and then the reliability assessment result of the enterprise-related data can be determined according to the reliability assessment level.

[0145] In the embodiment of the present application, the reliability assessment level division information may include the correspondence between different reliability assessment scores and the reliability assessment levels corresponding to each reliability assessment score. For example, the reliability assessment level division information may include that the reliability assessment level corresponding to scores below 60 is a low level, the reliability assessment level corresponding to scores between 60 and 80 is a medium level, and the reliability assessment level corresponding to scores above 80 is a high level.

[0146] Among them, the above-mentioned difference analysis results can be understood as reliability assessment scores; specifically, the difference analysis results can be found in the reliability assessment grade classification information, and the reliability assessment grade corresponding to the reliability assessment score corresponding to the difference analysis result can be obtained. If the reliability assessment grade is high or medium, the reliability assessment result of the enterprise-related data is determined to be passed.

[0147] In addition, the difference analysis results may be searched in the association relationship between different difference analysis results and different reliability assessment results, and the reliability assessment results corresponding to the found difference analysis results may be determined as the reliability assessment results of the enterprise associated data.

[0148] The technical solution in the embodiment of the present application determines multiple groups of pairing results according to each group of historical state quantization values ​​and each group of current state quantization values, determines the statistical mean according to the statistics of each group of pairing results, and determines the significance level average according to the significance level of each group of pairing results, performs difference analysis processing according to the statistical mean and the significance level average to determine the difference analysis result, and obtains the reliability evaluation result of the enterprise-related data according to the difference analysis result; the above method does not require the participation of complex algorithms, and the processing process is relatively simple, thereby reducing the amount of data processed for obtaining the reliability evaluation result of the enterprise-related data, and accelerating the speed and efficiency of obtaining the reliability evaluation result of the enterprise-related data; at the same time, the above method does not require human participation, thereby reducing human participation errors and improving the accuracy of the obtained reliability evaluation results.

[0149] The following is an explanation of the process of predicting the occupational health risks of a target enterprise based on the enterprise-related data. Figure 8 As shown, the step of predicting the occupational health risks of the target enterprise based on the enterprise-related data in the above S300 can be implemented in the following ways:

[0150] S310: Obtain statistical peak values ​​according to multiple groups of pairing results corresponding to the enterprise-related data.

[0151] In practical applications, multiple groups of state quantization values ​​can be determined based on enterprise-related data, and the multiple groups of state quantization values ​​include multiple groups of historical state quantization values ​​and multiple groups of current state quantization values; wherein the number of groups of historical state quantization values ​​is equal to the number of groups of current state quantization values.

[0152] Optionally, each group of historical state quantization values ​​and each group of current historical state quantization values ​​include multiple state quantization values, and the number of state quantization values ​​in any group of historical state quantization values ​​is the same as the number of state quantization values ​​in the corresponding group of current state quantization values.

[0153] For any group of historical state quantization values ​​and the corresponding group of current state quantization values, each state quantization value in the group of historical state quantization values ​​can be subtracted from the corresponding state quantization value in the corresponding group of current state quantization values ​​to obtain a group of pairing results.

[0154] Furthermore, a histogram statistical method may be used to generate a histogram based on each pairing result, and then determine a statistical peak value based on the histogram. Alternatively, each pairing result may be classified and statistically processed, and a statistical peak value may be determined based on the classified statistical results.

[0155] S320. Determine occupational health risk prediction results for the target enterprise based on statistical peaks and enterprise-related data.

[0156] In one implementation, a computer device can pre-train a prediction model, and then input both the statistical peak value and the enterprise-related data into the prediction model, which outputs the occupational health risk prediction result of the target enterprise. Optionally, the above prediction model can be implemented by at least one of a convolutional neural network model, a fully connected neural network model, a recurrent neural network model, a long short-term memory neural network model, and a residual neural network model.

[0157] In another implementation, the computer device can use a prediction algorithm to perform occupational health risk prediction processing based on statistical peak values ​​and enterprise-related data to obtain occupational health risk prediction results for the target enterprise. Optionally, the above prediction algorithm can be an exponential smoothing method, a linear regression method, a statistical analysis method, etc., which is not limited in the embodiments of the present application.

[0158] The technical solution in the embodiment of the present application obtains statistical peaks based on multiple groups of pairing results corresponding to the enterprise-related data, and determines the occupational health risk prediction results of the target enterprise based on the statistical peaks and the enterprise-related data; the above method can predict the occupational health risks of the target enterprise based on the enterprise-related data when the reliability assessment result of the enterprise-related data of the target enterprise is passed, thereby greatly improving the accuracy and reliability of the occupational health risk prediction of the target enterprise.

[0159] The following is a description of how to determine the status quantification values ​​of multiple groups of occupational health risk statuses through the enterprise-related data of the target enterprise. Fig. 9 As shown, the steps in S100 above can be implemented in the following manner:

[0160] S110. Obtain multiple groups of health risk states corresponding to different occupational health risk levels of the target enterprise according to the enterprise-related data.

[0161] Among them, the above-mentioned different occupational health risk levels comply with the national occupational health standards; the health risk status corresponding to any occupational health risk level can be understood as whether the enterprise-related data has a risk status of the occupational health risk level. In the embodiment of the present application, if the enterprise-related data has a risk of the occupational health risk level, the health risk status corresponding to the occupational health risk level can be yes; if the enterprise-related data has a risk of the occupational health risk level, the health risk status corresponding to the occupational health risk level can be no.

[0162] In the embodiment of the present application, the above-mentioned enterprise association data may include multiple groups of association data corresponding to the target enterprise, and the multiple groups of association data may include multiple groups of historical association data and multiple groups of current association data. Among them, the historical time period corresponding to each group of historical association data is the same as the historical time period corresponding to each group of historical state quantization values; the current time period corresponding to each group of current association data is the same as the current time period corresponding to each group of current state quantization values.

[0163] In one embodiment, for any occupational health risk level, the computer device can detect whether there is standard associated data corresponding to the occupational health risk level in any group of associated data based on the standard associated data corresponding to the occupational health risk level. If so, it is determined that the health risk status of the target enterprise corresponding to the occupational health risk level is yes; otherwise, it is determined that the health risk status of the target enterprise corresponding to the occupational health risk level is no.

[0164] In another embodiment, for any occupational health risk level, the computer device can extract data features from any group of related data. If the extracted data features include data features corresponding to the occupational health risk level, it is determined that the health risk status of the target enterprise corresponding to the occupational health risk level is yes; otherwise, it is determined that the health risk status of the target enterprise corresponding to the occupational health risk level is no.

[0165] Exemplarily, as shown in Table 1, any set of historical associated data and corresponding current associated data in the enterprise associated data of the target enterprise corresponds to the health risk status under 10 different occupational health risk levels.

[0166] Table 1

[0167]

[0168] S120, quantifying the occupational health risk status of each group to obtain a quantified value of each group of status.

[0169] Based on any set of related data obtained in the previous steps, if any occupational health risk status corresponding to the set of related data is yes, then the occupational health risk status can be quantified as 1; if any occupational health risk status corresponding to the set of related data is no, then the occupational health risk status can be quantified as 0.

[0170] Among them, based on Table 1, the corresponding state quantization values ​​are obtained as shown in Table 2.

[0171] Table 2

[0172]

[0173] The technical solution in the embodiment of the present application obtains multiple groups of health risk states corresponding to different occupational health risk levels of the target enterprise based on enterprise-related data, and quantifies each group of occupational health risk states to obtain each group of state quantization values; the above method does not require the participation of complex algorithms, and the processing process is relatively simple, thereby reducing the amount of data processed to obtain the state quantization values ​​and speeding up the acquisition speed and efficiency of the state quantization values; at the same time, the above method does not require human participation, thereby reducing human participation errors and improving the accuracy of the obtained state quantization values.

[0174] In one embodiment, the present application also provides an occupational health risk prediction method, which is applied to a computer device, and the method includes the following process:

[0175] (1) Based on the enterprise-related data of the target enterprise, multiple groups of health risk status corresponding to different occupational health risk levels of the target enterprise are obtained;

[0176] (2) Quantify the occupational health risk status of each group and obtain the quantitative value of each group;

[0177] (3) obtaining a historical state mean and a historical state standard deviation corresponding to each group of historical state quantization values ​​in the multiple groups of state quantization values; and obtaining a current state mean and a current state standard deviation corresponding to each group of current state quantization values ​​in the multiple groups of state quantization values;

[0178] (4) determining a plurality of first paired data according to each historical state mean and each historical state standard deviation; and determining a plurality of second paired data according to each current state mean and each current state standard deviation;

[0179] (5) determining a plurality of third pairing data according to each of the first pairing data and each of the second pairing data;

[0180] (6) performing a paired sample difference test based on each third paired data to determine a reliability effective evaluation index value;

[0181] (7) when the reliability effective evaluation index value is less than a preset threshold, determining multiple groups of pairing results according to the historical state quantization values ​​of each group and the current state quantization values ​​of each group;

[0182] (8) determining a statistical mean according to the statistical quantity of each group of paired results; and determining a significance level mean according to the significance level of each group of paired results;

[0183] (9) determining a first difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the statistic mean; and determining a second difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the significance level mean;

[0184] (10) Determining the statistical mean and significance level of the difference analysis result according to the first difference result and the second difference result, performing difference analysis processing, and determining the difference analysis result;

[0185] (11) Obtaining reliability assessment results of enterprise-related data based on the difference analysis results;

[0186] (12) When the reliability assessment result is passed, obtain the statistical peak value according to the multiple groups of pairing results corresponding to the enterprise-related data;

[0187] (13) Determine the occupational health risk prediction results of the target enterprise based on statistical peaks and enterprise-related data.

[0188] The execution process of the above (1) to (13) can be specifically referred to the description of the above embodiment. The implementation principles and technical effects are similar and will not be repeated here.

[0189] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0190] Based on the same inventive concept, the embodiment of the present application also provides an occupational health risk prediction device for implementing the above-mentioned occupational health risk prediction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the occupational health risk prediction device provided below can refer to the limitations of the occupational health risk prediction method above, and will not be repeated here.

[0191] In one embodiment, Fig.10 This is a schematic diagram of the structure of an occupational health risk prediction device in one embodiment of the present application. The occupational health risk prediction device provided in the embodiment of the present application can be applied to computer equipment. Fig.10 As shown, the occupational health risk prediction device of the embodiment of the present application may include: a quantitative value acquisition module 11, a processing module 12 and a prediction module 13, wherein:

[0192] A quantitative value acquisition module 11 is used to determine the status quantitative values ​​of multiple groups of occupational health risk statuses according to the enterprise-related data of the target enterprise;

[0193] A processing module 12 is used to perform difference processing according to each group of state quantization values ​​to obtain a reliability evaluation result corresponding to the enterprise-related data;

[0194] The prediction module 13 is used to predict the occupational health risks of the target enterprise based on the enterprise-related data when the reliability assessment result is passed.

[0195] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0196] In one embodiment, the processing module 12 includes: a detection processing unit and a first determination unit, wherein:

[0197] A detection processing unit, used to perform paired sample difference detection processing according to each group of state quantization values, and obtain a reliability effective evaluation index value of each group of state quantization values;

[0198] The first determining unit is used to determine the reliability evaluation result of the enterprise-related data according to each group of state quantization values ​​when the reliability effective evaluation index value is less than a preset threshold.

[0199] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0200] In one embodiment, the detection processing unit includes: a first determination subunit, a second determination subunit and a third determination subunit, wherein:

[0201] A first determining subunit, configured to determine a plurality of first paired data and a plurality of second paired data according to each group of state quantization values;

[0202] A second determining subunit, configured to determine a plurality of third pairing data according to each of the first pairing data and each of the second pairing data;

[0203] The third determination subunit is used to perform a paired sample difference test based on each third paired data to determine a reliability validity evaluation index value.

[0204] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0205] In one embodiment, the state quantization value includes a historical state quantization value and a current state quantization value; and the first determining subunit is specifically used for:

[0206] Obtain the historical state mean and historical state standard deviation corresponding to each group of historical state quantization values; and obtain the current state mean and current state standard deviation corresponding to each group of current state quantization values;

[0207] A plurality of first paired data are determined according to each historical state mean value and each historical state standard deviation; and a plurality of second paired data are determined according to each current state mean value and each current state standard deviation.

[0208] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0209] In one embodiment, the state quantization value includes a historical state quantization value and a current state quantization value; the first determination unit includes: a fourth determination subunit, a fifth determination subunit and an analysis and processing subunit; wherein:

[0210] A fourth determination subunit, used to determine multiple groups of pairing results according to each group of historical state quantization values ​​and each group of current state quantization values;

[0211] A fifth determination subunit is used to determine a statistical mean according to the statistical means of each group of pairing results; and to determine a significance level average according to the significance level of each group of pairing results;

[0212] The analysis and processing subunit is used to perform difference analysis and processing according to the statistical mean and the significance level, and determine the difference analysis result;

[0213] Obtain the reliability assessment results of enterprise-related data based on the difference analysis results.

[0214] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0215] In one embodiment, the analysis and processing subunit is specifically used for:

[0216] Determine a first difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the statistic mean; and determine a second difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the significance level mean;

[0217] A difference analysis result is determined according to the first difference result and the second difference result.

[0218] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0219] In one embodiment, the occupational health risk prediction device further includes: a peak acquisition module and a determination module, wherein:

[0220] A peak acquisition module is used to obtain statistical peak values ​​according to multiple groups of pairing results corresponding to enterprise-related data;

[0221] The determination module is used to determine the occupational health risk prediction results of the target enterprise based on the statistical peak value and enterprise-related data.

[0222] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0223] In one embodiment, the quantitative value acquisition module 11 includes: a risk state acquisition unit and a quantitative value acquisition unit, wherein:

[0224] A risk status acquisition unit, used to acquire multiple groups of health risk statuses corresponding to different occupational health risk levels of the target enterprise according to enterprise-related data;

[0225] The quantitative value acquisition unit is used to quantify each group of occupational health risk states and obtain the quantitative value of each group of states.

[0226] The occupational health risk prediction device provided in the embodiment of the present application can be used to implement the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application. Its implementation principle and technical effect are similar and will not be repeated here.

[0227] For the specific definition of the occupational health risk prediction device, please refer to the definition of the occupational health risk prediction method above, which will not be repeated here. Each module in the above-mentioned occupational health risk prediction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0228] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.11 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide processing power. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the enterprise-related data of the target enterprise. The network interface of the computer device is used to communicate with an external endpoint through a network connection. When the computer program is executed by the processor, a method for predicting occupational health risks is implemented.

[0229] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0230] In one embodiment, a computer device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the technical solution in the above-mentioned occupational health risk prediction method embodiment of the present application is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0231] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the technical solution of the above-mentioned occupational health risk prediction method of the present application is implemented. The implementation principle and technical effect are similar and will not be repeated here.

[0232] In one embodiment, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the technical solution of the above-mentioned occupational health risk prediction method of the present application. The implementation principle and technical effect are similar and will not be repeated here.

[0233] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0234] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0235] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for predicting occupational health risks, characterized in that: The method comprises: Determine the status quantification values ​​of multiple groups of occupational health risk statuses based on the enterprise-related data of the target enterprise; Perform difference processing according to the state quantization values ​​of each group to obtain the reliability evaluation result corresponding to the enterprise-related data; When the reliability assessment result is passed, the occupational health risk of the target enterprise is predicted based on the enterprise-related data.

2. The method according to claim 1, characterized in that The performing difference processing according to the state quantization values ​​of each group to obtain the reliability evaluation result corresponding to the enterprise-related data includes: Perform paired sample difference detection processing according to the state quantization values ​​of each group to obtain the reliability effective evaluation index value of the state quantization values ​​of each group; When the reliability effective evaluation index value is less than a preset threshold, the reliability evaluation result of the enterprise-related data is determined according to each group of state quantization values.

3. The method according to claim 2, characterized in that The performing paired sample difference detection processing according to the state quantization values ​​of each group to obtain the reliability effective evaluation index value of the enterprise association data includes: Determine a plurality of first paired data and a plurality of second paired data according to each group of state quantization values; Determine a plurality of third pairing data according to each of the first pairing data and each of the second pairing data; A paired sample difference test is performed based on each of the third paired data to determine the reliability validity evaluation index value.

4. The method according to claim 3, characterized in that The state quantization value includes a historical state quantization value and a current state quantization value; and the determining of a plurality of first paired data and a plurality of second paired data according to each group of the state quantization values ​​includes: Obtaining the historical state mean and the historical state standard deviation corresponding to each group of the historical state quantization values; and obtaining the current state mean and the current state standard deviation corresponding to each group of the current state quantization values; The plurality of first paired data are determined according to each of the historical state mean values ​​and each of the historical state standard deviations; and the plurality of second paired data are determined according to each of the current state mean values ​​and each of the current state standard deviations.

5. The method according to any one of claims 2 to 4, characterized in that: The state quantization value includes a historical state quantization value and a current state quantization value; the reliability evaluation result of the enterprise-related data is determined according to each group of the state quantization values, including: Determine multiple groups of pairing results according to the historical state quantization values ​​of each group and the current state quantization values ​​of each group; Determine the statistical mean according to the statistical quantity of the pairing results of each group; and determine the significance level mean according to the significance level of the pairing results of each group; Performing difference analysis processing according to the statistical mean and the significance level mean to determine the difference analysis result; The reliability evaluation result of the enterprise-related data is obtained according to the difference analysis result.

6. The method according to claim 5, characterized in that The performing difference analysis processing according to the statistical mean and the significance level mean to determine the difference analysis result includes: Determine a first difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the statistic mean; and determine a second difference result according to the absolute value of the difference between the statistic mean and the significance level mean and the significance level mean; The difference analysis result is determined according to the first difference result and the second difference result.

7. The method according to any one of claims 1 to 4, characterized in that The predicting of the occupational health risk of the target enterprise based on the enterprise-related data includes: Obtaining statistical peak values ​​according to multiple groups of pairing results corresponding to the enterprise-related data; The occupational health risk prediction result of the target enterprise is determined according to the statistical peak value and the enterprise-related data.

8. The method according to any one of claims 1 to 4, characterized in that Determining the state quantification values ​​of multiple groups of occupational health risk states according to the enterprise-related data of the target enterprise includes: According to the enterprise-related data, multiple groups of health risk states corresponding to different occupational health risk levels of the target enterprise are obtained; The occupational health risk status of each group is quantified to obtain a quantified value of the status of each group.

9. An occupational health risk prediction device, characterized in that: The device comprises: A quantitative value acquisition module is used to determine the status quantitative values ​​of multiple groups of occupational health risk statuses according to the enterprise-related data of the target enterprise; A processing module, used for performing difference processing according to each group of state quantization values ​​to obtain a reliability evaluation result corresponding to the enterprise-related data; A prediction module is used to predict the occupational health risk of the target enterprise based on the enterprise-related data when the reliability assessment result is passed.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Citation Information

Patent Citations

  • Food safety risk assessment method, device and equipment and storage medium

    CN111738549A

  • Automobile manufacturing industry occupational health risk assessment method and device

    CN117875700A

  • Cross-platform enterprise credit determination method and device, electronic equipment and storage medium

    CN118071366A