Intelligent HSE management system construction method and system

By building a smart HSE management system, intelligent means are used to acquire and analyze employees' physiological and environmental parameters to generate real-time safety strategies. This solves the problems of low management efficiency and poor safety in existing technologies, and achieves precise safety management and attention to employee health, thereby improving work efficiency and well-being.

CN118982145AInactive Publication Date: 2024-11-19中安健(北京)科技产业有限公司

Patent Information

Application Number
CN202411052719.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing HSE management methods lack intelligent tools, cannot make timely adjustments to safety assurance strategies, and do not pay enough attention to the physical and mental health of employees, resulting in low management efficiency and poor safety.

Method used

To build a smart HSE management system, an intelligent HSE management model is established by acquiring employee health checkup and production environment parameters. Real-time data is collected using work wristbands to generate real-time safety assurance strategies, which are then visualized and used for training prompts. Multiple classifiers, such as Fisher's criterion and SVM model, are employed for accurate classification.

Benefits of technology

This has enabled precise and hierarchical security strategies, improved employee work efficiency and safety, enhanced employee well-being and satisfaction, and reduced management difficulty.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982145A_ABST
    Figure CN118982145A_ABST
Patent Text Reader

Abstract

The invention provides a smart HSE management system construction method and system. The server receives physiological parameters obtained by physical examination of employees within a certain period of time and production environment parameters stored in the server, and constructs an intelligent HSE management model by using the physiological parameters and employee safety guarantee strategies corresponding to the production environment parameters; and the constructed intelligent HSE management model generates a real-time safety guarantee strategy according to the physiological parameters collected by the employee work bracelet and received by the server and the real-time production environment parameters, and carries out real-time intelligent display and training prompt on the safety and health state of the employee. According to the invention, intelligent management of the employee safety guarantee strategy is realized, an intelligent management effect without manual HSE management is realized, the working efficiency, the working comfort and the working safety of the employees are improved, and the employees can obtain happiness and satisfaction during work.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of intelligent management technology, and in particular relates to a method and system for constructing an intelligent HSE management system. Background Art

[0002] Due to the huge assets, diverse professions, complex processes, continuous operations, multiple locations, wide coverage, and long chains, production safety supervision is very difficult and the task of preventing accidents is arduous. How to effectively implement production safety monitoring and accident control, how to implement systematic and standardized HSE management, how to keep the information transmission channels unblocked, and conduct effective statistical analysis of a large amount of HSE information to provide support for management decisions are extremely important for improving the HSE management level of enterprises and ensuring the sustainable development of enterprises.

[0004] Most of the existing HSE management methods lack intelligent means, and cannot make timely adjustments to safety assurance strategies. They also pay little attention to the physical and mental health of employees. Therefore, there is an urgent need for a smart HSE management system construction method and system that can be used to improve employee work efficiency, work comfort and work safety, so that employees can gain a sense of happiness and satisfaction at work. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a method and system for constructing an intelligent HSE management system.

[0006] In a first aspect of the present invention, a method for constructing a smart HSE management system comprises:

[0007] Obtaining the first physiological parameters of the employee obtained during a physical examination within a certain period of time and the production environment parameters stored in the server;

[0008] Obtaining a safety assurance strategy corresponding to the first physiological parameter and the production environment parameter;

[0009] According to the first physiological parameter and the production environment parameter, the safety assurance strategy jointly constructs an intelligent HSE management model;

[0010] Receiving the second real-time physiological parameter and the real-time production environment parameter collected by the employee's work wristband, combining the first physiological parameter to obtain a third real-time physiological parameter, and generating a real-time safety assurance strategy by the intelligent HSE management model according to the third real-time physiological parameter and the real-time production environment parameter;

[0011] The server provides real-time intelligent display and training prompts for the safety and health status of employees based on the real-time safety assurance strategy.

[0012] Furthermore, the first physiological parameter includes: blood pressure, heart rate, body temperature, blood sugar, blood lipids, weight and height;

[0013] The second real-time physiological parameters include: real-time blood pressure, real-time heart rate, and real-time body temperature.

[0014] Furthermore, the third real-time physiological parameter includes: real-time blood pressure, real-time heart rate, real-time body temperature, blood sugar, blood lipids, weight and height;

[0015] The production environment parameters include: ambient temperature, humidity, air quality, and noise.

[0016] Furthermore, the intelligent HSE management model adopts multiple classifiers, including a classifier based on the Fisher criterion or a SVM model.

[0017] Furthermore, before constructing the SVM model, some variables are removed. The steps are as follows:

[0018] Step S1, dividing the data set composed of the variables into a training set X and a test set T;

[0019] Step S2, using the training set X to establish a random forest model;

[0020] Step S3: Using the importance of variables M i To delete some variables, M i The calculation formula is as follows:

[0021]

[0022] The i is the feature variable; m is the number of variables; e1 is the test set T error; e2 is the test set error after adding noise; t-1 is the number of decision trees;

[0023] Step S4: After deleting some variables, a specific training set ST is obtained.

[0024] Furthermore, the intelligent HSE management model is constructed according to the SVM model using the specific training set ST.

[0025] Furthermore, the specific function expression of the SVM model is:

[0026] ω T X i +b≥1

[0027] Where ω, b are the normal vector and intercept of the hyperplane, respectively, X i is the variable in the specific training set ST, and i is the number of samples.

[0028] A smart HSE management system construction system is also provided, the system includes a data acquisition module, a data storage module, a model construction module, a safety assurance module, and a visualization module, and is characterized in that:

[0029] The data acquisition module: is connected to the physical examination hospital, and is used to collect the first physiological parameters obtained by the employee during the physical examination within a certain period of time, and the production environment parameters stored in the server for a period of time before the physical examination period; it is also connected to the employee's work wristband to receive the second real-time physiological parameter collected by the employee's work wristband, and the second real-time physiological parameter is combined with the first physiological parameter to obtain a third real-time physiological parameter; and the safety assurance strategy corresponding to the first physiological parameter and the production environment parameter is collected; it is also used to collect real-time production environment parameters;

[0030] The data storage module is used to store the first physiological parameter, the third real-time physiological parameter, the production environment parameter, and the security strategy;

[0031] The model building module is used to jointly build an intelligent HSE management model according to the first physiological parameter and the safety assurance strategy corresponding to the production environment parameter;

[0032] The safety assurance module is used to receive the third real-time physiological parameter and the real-time production environment parameter, generate a real-time safety assurance strategy using the intelligent HSE management model according to the third real-time physiological parameter and the real-time production environment parameter, and manage employees according to the real-time safety assurance strategy;

[0033] The visualization module is connected to the safety assurance module and is used to realize the visualization display of the safety and health status of employees and training tips.

[0034] Furthermore, the security assurance strategy includes a primary security assurance strategy, a secondary security assurance strategy and a tertiary security assurance strategy.

[0035] Furthermore, before constructing the SVM model, some variables are removed. The steps are as follows:

[0036] Step S1, dividing the data set composed of the variables into a training set X and a test set T;

[0037] Step S2, using the training set X to establish a random forest model;

[0038] Step S3: Using the importance of variables M i To delete some variables, M i The calculation formula is as follows:

[0039]

[0040] The i is the feature variable; m is the number of variables; e1 is the test set T error; e2 is the test set error after adding noise; t-1 is the number of decision trees;

[0041] Step S4: After deleting some variables, a specific training set ST is obtained.

[0042] Beneficial effects of the present invention:

[0043] (1) The intelligent HSE management model constructed by the present invention utilizes multiple features such as environmental information and employees' real-time physiological information. The safety assurance strategy obtained by the constructed model classification is more accurate and the strategy hierarchy is clear.

[0044] (2) Before constructing the SVM model, the present invention deletes some variables according to the importance M of the variables. The constructed SVM model can reduce the imbalance problem of selected data categories that may exist in the present invention, so as to obtain the selection of security measures with higher accuracy.

[0045] (3) The intelligent HSE management model constructed by the present invention is also visualized, which can more clearly implement the HSE management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of a method for constructing a smart HSE management system of the present invention;

[0047] Figure 2 It is a schematic diagram of the structure of a smart HSE management system construction system of the present invention;

[0048] Figure 3 It is a picture of employees’ physical condition and training reminders. DETAILED DESCRIPTION

[0049] The invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0050] The first embodiment of the present invention:

[0051] In a first aspect of the present invention, a method for constructing a smart HSE management system is provided, the method comprising:

[0052] Obtaining the first physiological parameters of the employee obtained during a physical examination within a certain period of time and the production environment parameters stored in the server;

[0053] Acquire a safety assurance strategy corresponding to the first physiological parameter and the production environment parameter;

[0054] According to the first physiological parameter and the production environment parameter, the safety assurance strategy jointly constructs an intelligent HSE management model;

[0055] Receiving the second real-time physiological parameter and the real-time production environment parameter collected by the employee's work wristband, combining the first physiological parameter to obtain a third real-time physiological parameter, and generating a real-time safety assurance strategy by the intelligent HSE management model according to the third real-time physiological parameter and the real-time production environment parameter;

[0056] The server provides real-time intelligent display and training prompts for the safety and health status of employees based on the real-time safety assurance strategy.

[0057] Furthermore, the first physiological parameter includes: blood pressure, heart rate, body temperature, blood sugar, blood lipids, weight and height;

[0058] The second real-time physiological parameters include: real-time blood pressure, real-time heart rate, and real-time body temperature.

[0059] Furthermore, the third real-time physiological parameter includes: real-time blood pressure, real-time heart rate, real-time body temperature, blood sugar, blood lipids, weight and height;

[0060] The production environment parameters include: ambient temperature, humidity, air quality, and noise.

[0061] In this embodiment, the server is connected to the hospital network, and can collect the first physiological parameters obtained by the employee's physical examination within a certain period of time, as well as the production environment parameters stored in the server for a period of time before the physical examination period; it is also connected to the employee's work wristband to receive the second real-time physiological parameter collected by the employee's work wristband, and the second real-time physiological parameter is combined with the first physiological parameter to obtain a third real-time physiological parameter; and the security assurance strategy corresponding to the first physiological parameter and the production environment parameter is collected; it is also used to collect real-time production environment parameters;

[0062] In this embodiment, the first physiological parameter obtained by the employee during a certain period of time refers to the first physiological parameter obtained by the employee during a physical examination in a certain period of time when the enterprise conducts physical examinations on the employee multiple times a year, such as three times a year. In this case, the physical examination parameter T within 4 months is b (100, 80, 36.7, 5.5, 4.8, 75, 180), where T means that the blood pressure, heart rate, body temperature, blood sugar, and blood lipids of a person with a height of 180 cm and a weight of 75 kg are 100 mmHg, 80 times / min, 36.7°C, 5.5 mmol / L, and 4.8 mmol / L respectively. The physical examination parameters here can be the ones for the last 4 months or the average values ​​for the whole year. This is not limited in the present invention. In addition, the humidity in the production environment parameters is expressed as a percentage, and the air quality adopts a 6-level evaluation standard, which is generally known to those skilled in the art and will not be repeated here. In this embodiment, the server stores the production environment parameters T for the last 4 months of the physical examination period. e(25, 50, 58, 40), at this time, it means that the ambient temperature, humidity, air quality, and noise are 25 degrees Celsius, 50%, 58-good, and 40dB respectively. At this time, the collected safety assurance strategy R1 is risk level 0, the employee is healthy, and no training is required, so the label is L t (0). There are many other safety assurance strategies here. For example, if the risk level of safety assurance strategy R2 is level 1 and the employee is healthy and needs training, the label is L t (1) Safety strategy R3 risk level is level 2, the employee is unhealthy and does not need training, so the label is L t (2) Safety strategy R4 risk level is level 3, the employee is unhealthy and needs training, so the label is L t (3) Combine the two parameters. This embodiment only shows the link, and other combinations are possible, which will not be described here.

[0063] Then the security strategy corresponding to a variable T (blood pressure, heart rate, body temperature, blood sugar, blood lipids, weight, height, ambient temperature, humidity, air quality, noise) in the training set is L t (0).

[0064] In addition, height and weight have little to do with the health status of employees and can be removed. In this case, the physical examination parameters are T*(100, 80, 36.7, 5.5, 4.8), and the subsequent data processing classifier training and use are the same as above.

[0065] Using multiple sets of variables T and corresponding security strategies L t (0), L t (1), etc. The safety assurance strategy in the present invention is set by the user himself, and is not limited to the above four types. The SVM model is trained to obtain specific model parameters. When the server receives the transmitted real-time environmental parameters and the second real-time physiological parameters, the second real-time physiological parameters are combined with the first physiological parameters to obtain a third real-time physiological parameter. According to the real-time environmental parameters and the third real-time physiological parameters, the intelligent HSE management model generates a real-time safety assurance strategy;

[0066] If the second real-time physiological parameter of the employee collected is combined with the real-time environmental parameter to be T t (130, 110, 38, 5.5, 4.8, 75, 180, 25, 50, 58, 60). At this time, the safety assurance strategy determined by the trained intelligent HSE management model is that the risk level is level 3, the employee is unhealthy and needs training, and the corresponding label is L t(3) From the second real-time physiological parameter data, it can be known that the employee is in an unhealthy state with a fever. At this time, the employee's safety and health status is visualized and specific safety training reminders are given afterwards, reminding the management staff to comfort and protect the employee. In this embodiment, the employee wristband, such as the built-in Xiaomi wristband function, can obtain basic employee physiological parameter information. The above employee physiological parameters are authorized by the employee's relevant data.

[0067] Furthermore, the intelligent HSE management model adopts multiple classifiers, including a classifier based on the Fisher criterion or a SVM model.

[0068] Furthermore, before constructing the SVM model, some variables are removed. The steps are as follows:

[0069] Step S1, dividing the data set composed of the variables into a training set X and a test set T;

[0070] Step S2, using the training set X to establish a random forest model;

[0071] Step S3: Using the importance of variables M i To delete some variables, M i The calculation formula is as follows:

[0072]

[0073] The i is the feature variable; m is the number of variables; e1 is the test set T error; e2 is the test set error after adding noise; t-1 is the number of decision trees;

[0074] Step S4: After deleting some variables, a specific training set ST is obtained.

[0075] Furthermore, the intelligent HSE management model is constructed according to the SVM model using the specific training set ST.

[0076] Furthermore, the specific function expression of the SVM model is:

[0077] ω T X i +b≥1

[0078] Where ω, b are the normal vector and intercept of the hyperplane, respectively, X i is the variable in the specific training set ST, and i is the number of samples.

[0079] A smart HSE management system construction system is also provided, the system includes a data acquisition module, a data storage module, a model construction module, a safety assurance module, and a visualization module, and is characterized in that:

[0080] The data acquisition module: is connected to the physical examination hospital, and is used to collect the first physiological parameters obtained by the employee during the physical examination within a certain period of time, and the production environment parameters stored in the server for a period of time before the physical examination period; it is also connected to the employee's work wristband to receive the second real-time physiological parameter collected by the employee's work wristband, and the second real-time physiological parameter is combined with the first physiological parameter to obtain a third real-time physiological parameter; and the safety assurance strategy corresponding to the first physiological parameter and the production environment parameter is collected; it is also used to collect real-time production environment parameters;

[0081] The data storage module is used to store the first physiological parameter, the third real-time physiological parameter, the production environment parameter, and the security strategy;

[0082] The model building module is used to jointly build an intelligent HSE management model according to the first physiological parameter and the safety assurance strategy corresponding to the production environment parameter;

[0083] The safety assurance module is used to receive the third real-time physiological parameter and the real-time production environment parameter, generate a real-time safety assurance strategy using the intelligent HSE management model according to the third real-time physiological parameter and the real-time production environment parameter, and manage employees according to the real-time safety assurance strategy;

[0084] The visualization module is connected to the safety assurance module and is used to realize the visualization display of the safety and health status of employees and training tips.

[0085] Furthermore, the security assurance strategy includes a first-level security assurance strategy, a second-level security assurance strategy, and a third-level security assurance strategy, which correspond to L t (0), L t (1) L t (2).

[0086] Furthermore, before constructing the SVM model, some variables are removed. The steps are as follows:

[0087] Step S1, dividing the data set composed of the variables into a training set X and a test set T;

[0088] Step S2, using the training set X to establish a random forest model;

[0089] The random forest model is established as follows:

[0090] (1) Each time, n training samples are taken from the training set X with replacement to form a new training set;

[0091] (2) Using the new training set, train M sub-models;

[0092] (3) Using the voting method, the classification category of the sub-model with the most votes is the final category;

[0093] Step S3: Using the importance of variables M i To delete some variables, M i The calculation formula is as follows:

[0094]

[0095] The i is the feature variable; m is the number of variables; e1 is the test set T error; e2 is the test set error after adding noise; t-1 is the number of decision trees;

[0096] Step S4: After deleting some variables, a specific training set ST is obtained.

[0097] The noise is a randomly generated variable, and the test set error and the test set error after adding noise are calculated based on the error rate of the security assurance strategy obtained by the test and the actual security assurance strategy. This is a conventional error calculation method for those skilled in the art and will not be repeated here.

[0098] Step S4: After deleting some variables, a specific training set ST is obtained.

[0099] Through this method, T i The variables are reduced to T id , where id<i.

[0100] Furthermore, the specific function expression of the SVM model is:

[0101] ω T X i +b≥1

[0102] Where ω, b are the normal vector and intercept of the hyperplane, respectively, X i is the variable in the specific training set ST, and i is the number of samples.

[0103] For multiple security strategy combinations, multiple hyperplanes are constructed. If there are three security strategies, three hyperplanes are specifically constructed to select the security strategy.

[0104] Where ω and b are the security strategies L t (0) and security strategy L t (1) or security strategy L t (0) and security strategy L t (2) or security strategy L t (1) and security strategy L t (2) The normal vectors and intercepts of the three hyperplanes, X iTo obtain the i characteristic variables in the specific training set ST after deleting some variables, the specific security strategy L t (0) and security strategy L t (1) Hyperplane, the normal vector and intercept of the hyperplane function are input using the safety strategy L t (0) and security strategy L t (1) corresponds to C in the specific training set ST 01 feature variables are trained, when the collected data feature variables are T t When substituted into the formula, if the result is greater than or equal to 1, the server adopts the security strategy L t (0) Intelligent HSE management. After the calculation of the three hyperplanes, the safety assurance strategy with the most votes is L t (0), L t (0) The server adopts the security strategy with the most votes. t (0) Carry out intelligent HSE management.

[0105] It can also be set to more hyperplanes for classification of multiple categories, and the corresponding category labels are the corresponding "security strategy is L t (3)” etc., without limitation here.

[0106] If it is divided into 4 strategies, there will be a situation where the votes are equal. If the votes are equal, the corresponding security assurance strategy with the largest sum of the values ​​calculated by the hyperplane function with the same number of votes is adopted, and the server performs intelligent HSE management based on this.

[0107] The voting rules are as follows:

[0108] Similarly, the constructed L t (0)-L t (1) Hyperplane, L t (0)-L t (2) Hyperplane, L t (0)-L t (3) Hyperplane, L t (1)-L t (2) Hyperplane, L t (1)-L t (3) Hyperplane, L t (2)-L t (3) Hyperplanes There are 6 hyperplanes. If the feature variables of the collected data are T t The results obtained by inputting into 6 hyperplanes are shown in Table 1 below:

[0109] Table 1 Classification of hyperplane functions

[0110]

[0111] Table 1 L t (2) With L t (3) The votes are equal, but L t (2) and L t (3) The ratio of the sum of the hyperplane function values ​​is (-12.4+1.25) less than (-2.76-1.45). At this time, according to the output security strategy L t (3) The server performs intelligent HSE management.

[0112] Furthermore, in the second embodiment, the visualization module is used to realize the 3D visualization display of the employee's physical condition and training tips through WebGL technology. In this embodiment, the training can be selected by managers in various modes such as safety training, accident training, and training assessment, and the training arrangements for employees are made, such as Figure 3 As shown, the employee status is green at this time, the employee is in a healthy state and no training is required.

[0113] Of course, it can be understood that each embodiment of the present invention can achieve one of the effects alone, and a combination of multiple embodiments of the present invention can achieve all of the above effects, but it is not required that every embodiment of the present invention achieve all of the above advantages and effects, because each embodiment of the present invention can constitute a separate technical solution and make one or more contributions to the prior art.

[0114] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A method for constructing a smart HSE management system, characterized in that: The method comprises: Obtaining the first physiological parameters of the employee obtained during a physical examination within a certain period of time and the production environment parameters stored in the server; Obtaining a safety assurance strategy corresponding to the first physiological parameter and the production environment parameter; According to the first physiological parameter and the production environment parameter, the safety assurance strategy jointly constructs an intelligent HSE management model; Receiving a second real-time physiological parameter and a real-time production environment parameter collected by the employee's work wristband, combining the first physiological parameter to obtain a third real-time physiological parameter, and generating a real-time safety assurance strategy by the intelligent HSE management model according to the third real-time physiological parameter and the real-time production environment parameter; The server manages employees according to the real-time security assurance strategy, and provides real-time intelligent display and training prompts for the safety and health status of employees.

2. A method for constructing a smart HSE management system according to claim 1, characterized in that: The first physiological parameters include: blood pressure, heart rate, body temperature, blood sugar, blood lipids, weight and height; The second real-time physiological parameters include: real-time blood pressure, real-time heart rate, and real-time body temperature.

3. A method for constructing a smart HSE management system according to claim 2, characterized in that: The third real-time physiological parameter includes: real-time blood pressure, real-time heart rate, real-time body temperature, blood sugar, blood lipids, weight and height; The production environment parameters include: ambient temperature, humidity, air quality, and noise.

4. A method for constructing a smart HSE management system according to claim 3, characterized in that: The intelligent HSE management model adopts multiple classifiers, including a classifier based on the Fisher criterion or a SVM model.

5. A method for constructing a smart HSE management system according to claim 4, characterized in that: Before building the SVM model, some variables are removed. The steps are as follows: Step S1, dividing the data set consisting of the remaining variables into a training set X and a test set T; Step S2, using the training set X to establish a random forest model; Step S3: Using the importance of variables M i To delete some variables, M i The calculation formula is as follows: The i is a characteristic variable; m is the number of variables; e1 is the error of the test set T; e2 is the error of the test set after adding noise; t-1 is the number of decision trees; Step S4: After deleting some variables, a specific training set ST is obtained.

6. A method for constructing a smart HSE management system according to claim 5, characterized in that: The intelligent HSE management model is constructed according to the SVM model using the specific training set ST.

7. A method for constructing a smart HSE management system according to claim 6, characterized in that: The specific function expression of the SVM model is: oh T X i +b≥1 Where ω, b are the normal vector and intercept of the hyperplane, respectively, X i is the variable in the specific training set ST, and i is the number of samples.

8. A smart HSE management system construction system, the system includes a data acquisition module, a data storage module, a model construction module, a safety assurance module, and a visualization module, characterized in that: The data collection module is connected to the physical examination hospital and is used to collect the first physiological parameters of the employees obtained during the physical examination within a certain period of time, as well as the production environment parameters of the period before the physical examination period stored in the server; It is also connected to the employee's work wristband to receive the second real-time physiological parameter collected by the employee's work wristband, and the second real-time physiological parameter is combined with the first physiological parameter to obtain a third real-time physiological parameter; and collecting the safety assurance strategy corresponding to the first physiological parameter and the production environment parameter; It is also used to collect real-time production environment parameters; The data storage module is used to store the first physiological parameter, the third real-time physiological parameter, the production environment parameter, and the security strategy; The model building module is used to jointly build an intelligent HSE management model according to the first physiological parameter and the safety assurance strategy corresponding to the production environment parameter; The safety assurance module is used to receive the third real-time physiological parameter and the real-time production environment parameter, generate a real-time safety assurance strategy using the intelligent HSE management model according to the third real-time physiological parameter and the real-time production environment parameter, and manage employees according to the real-time safety assurance strategy; The visualization module is connected to the safety assurance module and is used to realize the visualization display of the safety and health status of employees and training tips.

9. The intelligent HSE management system construction system according to claim 8, characterized in that: The security assurance strategy includes a primary security assurance strategy, a secondary security assurance strategy and a tertiary security assurance strategy.

10. The intelligent HSE management system construction system according to claim 8, characterized in that: Before building the SVM model, some variables are removed. The steps are as follows: Step S1, dividing the data set composed of the variables into a training set X and a test set T; Step S2, using the training set X to establish a random forest model; Step S3: Using the importance of variables M i To delete some variables, M i The calculation formula is as follows: The i is a characteristic variable; m is the number of variables; e1 is the error of the test set T; e2 is the error of the test set after adding noise; t-1 is the number of decision trees; Step S4: After deleting some variables, a specific training set ST is obtained.

Citation Information

Patent Citations

  • Building indoor environment adjusting device and method based on thermal health and physiological rhythm

    CN116661528A

  • Wardrobe light color temperature control system and method

    CN117336930A

  • Tunnel constructor thermal risk monitoring and early warning system and method

    CN117877735A

  • Intelligent medical equipment integrated health diagnosis system

    CN118230936A

Cited By

  • Psychophysiological state monitoring system and implementation method thereof

    TWI928921B