A pre-factory safety ability multi-dimensional evaluation method for contractor personnel

Abstract

This invention relates to the field of data processing technology, and in particular to a multi-dimensional assessment method for the pre-entry safety capabilities of contractor personnel. The method includes the following steps: acquiring project information, the job information of the personnel to be assessed, the historical credit score of the personnel to be assessed, and the assessment data of the personnel to be assessed in each assessment dimension; generating assessment weights corresponding to each assessment dimension based on the project information and the job information of the personnel to be assessed; and calculating the comprehensive safety capability score of the personnel to be assessed based on the assessment data of the personnel to be assessed in each assessment dimension and the corresponding assessment weights. This solution dynamically generates assessment weights for each assessment dimension based on project information and job information, enabling the weight configuration to adaptively adjust according to project risk characteristics and job capability requirements, thereby improving the relevance and accuracy of the comprehensive safety capability score.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a multi-dimensional assessment method for the pre-entry safety capabilities of contractor personnel. Background Technology

[0002] In various projects such as engineering construction, equipment maintenance, and operation and maintenance services, contractor personnel undertake a large number of on-site work tasks. Due to their high mobility, diverse backgrounds, and the difficulty in management, their safety capabilities directly affect the overall safety situation of the project.

[0003] Currently, in the safety management process before contractors enter the factory, a multi-dimensional safety capability assessment mechanism is generally adopted. This mechanism assesses the personnel's theoretical knowledge, safety awareness, practical skills, and emergency response capabilities, and determines whether they are qualified to work in the factory based on the combined results.

[0004] Current assessment methods typically use a weighted summation approach to calculate the overall safety capability score. Specifically, a fixed set of weighting coefficients is preset for each assessment dimension. The personnel's scores in each dimension are then weighted and summed with their corresponding weights to obtain a comprehensive score. If the comprehensive score reaches the set threshold, the personnel are allowed to work in the factory.

[0005] While this method achieves a certain degree of safety assessment of contractor personnel, its fixed weight settings make it difficult to adapt to dynamic changes in project characteristics and job requirements, thus limiting the accuracy and relevance of the assessment results. Summary of the Invention

[0006] This invention provides a multi-dimensional assessment method for the pre-entry safety capabilities of contractor personnel. By dynamically generating assessment weights for each assessment dimension based on project and job information, the weight configuration can be adaptively adjusted according to project risk characteristics and job capability requirements, thereby improving the relevance and accuracy of the comprehensive safety capability score.

[0007] To achieve the above objectives, this application provides the following technical solution:

[0008] A multi-dimensional assessment method for pre-entry safety capabilities of contractor personnel includes the following steps:

[0009] S100: Obtain project information, job information of the personnel to be evaluated, historical credit scores of the personnel to be evaluated, and evaluation data of the personnel to be evaluated in each evaluation dimension;

[0010] S200, Based on the project information and the job information of the personnel to be evaluated, generate the evaluation weights corresponding to each evaluation dimension;

[0011] S300: Calculate the comprehensive security capability score of the person to be evaluated based on the evaluation data of the person to be evaluated in each evaluation dimension and the evaluation weight corresponding to each evaluation dimension.

[0012] Furthermore, the assessment dimensions include knowledge and theory, safety awareness, practical skills, and emergency response capabilities.

[0013] Furthermore, the S200 includes:

[0014] S201, Analyze the hazard level of the project based on the project information;

[0015] S202, Analyze the job risk of the personnel to be evaluated based on their job information;

[0016] S203, based on the project's hazard level and the job risks of the personnel to be assessed, generates the assessment weights for each assessment dimension;

[0017] S204, Adjust the evaluation weights of each evaluation dimension based on the historical credit score of the person to be evaluated.

[0018] Furthermore, the project information includes the project type, project size, and the set of hazardous work types included.

[0019] Furthermore, S201 includes:

[0020] S2011: Convert the project type into the first numerical feature according to the pre-stored project type-risk coefficient mapping table; normalize the project scale into the second numerical feature according to the scale range corresponding to each pre-stored scale level; perform one-hot encoding on the set of hazardous operation types and convert it into a numerical vector as the third numerical feature.

[0021] S2012, Construct a hazard analysis neural network model, using the first numerical feature, the second numerical feature and the third numerical feature as the input of the input layer, and the hazard coefficient of the project as the output of the output layer;

[0022] S2013, input the first numerical feature, the second numerical feature and the third numerical feature into the hazard analysis neural network model, output the hazard coefficient of the project, and generate the hazard level of the project according to the preset hazard level classification rules.

[0023] Furthermore, S203 includes:

[0024] S2031, obtain the benchmark weights for each evaluation dimension;

[0025] S2032, based on the job risk of the personnel to be evaluated, adjust the benchmark weights of each evaluation dimension to generate the job suitability weights corresponding to each evaluation dimension.

[0026] Among them, the job suitability weight of the knowledge theory dimension is inversely proportional to the job risk, while the job suitability weights of the safety awareness dimension, practical skills dimension, and emergency response capability dimension are all directly proportional to the job risk.

[0027] S2033, Based on the project's hazard level, generate risk enhancement coefficients for the safety awareness dimension and emergency response capability dimension; the risk enhancement coefficients are proportional to the hazard level.

[0028] S2034, multiply the job suitability weights of the safety awareness dimension and emergency response capability dimension by their respective risk enhancement coefficients to generate the risk enhancement weights of the safety awareness dimension and emergency response capability dimension.

[0029] S2035 uses the job suitability weights of the knowledge theory dimension and the practical skills dimension as the evaluation weights of the corresponding evaluation dimensions, and uses the risk enhancement weights of the safety awareness dimension and the emergency response capability dimension as the evaluation weights of the corresponding evaluation dimensions.

[0030] Furthermore, S204 includes:

[0031] S2041, Based on the historical credit score of the person to be evaluated, adjust the evaluation weights of the safety awareness dimension and the practical skills dimension; if the historical credit score is higher than a preset first threshold, multiply the evaluation weight of the safety awareness dimension by a first adjustment coefficient. The assessment weight of the practical skills dimension will be multiplied by a second adjustment factor. ,in , If the historical credit score is lower than the preset second threshold, the assessment weight of the security awareness dimension will be multiplied by a third adjustment coefficient. The assessment weight of the practical skills dimension will be multiplied by a fourth adjustment factor. ,in , The first threshold is greater than the second threshold.

[0032] Furthermore, S204 also includes:

[0033] S2042 normalizes the evaluation weights of the knowledge theory dimension, emergency response capability dimension, and the adjusted safety awareness dimension and practical skills dimension, so that the sum of the weights of each evaluation dimension is 1, and generates the final evaluation weights of each evaluation dimension.

[0034] The principles and advantages of this invention are as follows:

[0035] This solution dynamically adjusts the assessment weights of each dimension based on the specific project's hazard level and the job risk of the personnel being assessed. For example, in high-risk projects, it automatically strengthens the weighting of safety awareness and emergency response capabilities, ensuring the assessment standards closely match actual operational risks and enhancing the relevance and effectiveness of the assessment. Simultaneously, it introduces historical credit scores as a feedback mechanism for further refinement of the assessment weights. For personnel with high historical credit scores, indicating that their safety habits are internalized and their credit risk is low, appropriately reducing the weighting of the safety awareness dimension and increasing the weighting of the practical skills dimension helps to more accurately assess their actual operational capabilities. Conversely, for personnel with low historical credit scores, indicating weak safety awareness and high behavioral risk, strengthening the assessment weighting of the safety awareness dimension and appropriately reducing the weighting of the practical skills dimension allows for focused risk screening and prevention of potential hazards. Therefore, by constructing a dynamic weighting allocation mechanism based on project risk, job risk, and historical credit, this solution achieves precision and differentiation in safety capability assessment, enhancing the credibility of the comprehensive safety capability score. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating an embodiment of a multi-dimensional assessment method for pre-entry safety capabilities of contractor personnel according to the present invention. Detailed Implementation

[0037] The following detailed description illustrates the specific implementation method:

[0038] Example 1:

[0039] A multi-dimensional method for assessing the pre-entry safety capabilities of contractor personnel, such as... Figure 1 As shown, it includes the following steps:

[0040] S100 obtains project information, job information of the personnel to be evaluated, historical credit scores of the personnel to be evaluated, and evaluation data of the personnel to be evaluated in each evaluation dimension.

[0041] The project information is read from the project management system and includes the project type, project scale, and set of hazardous operation types. In this embodiment, the project type includes building construction, municipal engineering, chemical projects, and power engineering; the project scale is divided into small, medium, and large based on the investment amount, and in other embodiments of this application, it can also be divided based on the amount of work; the hazardous operation types include hot work, high-altitude work, confined space work, temporary power supply work, lifting work, and blasting work.

[0042] The job information is obtained from the human resources management system and includes the job title and job responsibilities.

[0043] The historical credit score is calculated based on the safety performance data of the person being evaluated in past projects. Specifically, it involves obtaining the number of historical violations by the individual. and historical training assessment pass rate Historical credit scores are calculated using the following formula. :

[0044]

[0045] In the formula, To pre-determine the weight of violations, As a preset pass rate weight, and In this embodiment, we take , ; In this embodiment, the maximum number of violations is set to a preset limit. ;when At that time, take Historical credit score The value range of is [0,1]. A higher number indicates better credit.

[0046] The assessment dimensions include theoretical knowledge, safety awareness, practical skills, and emergency response capabilities. The assessment data for each dimension for the personnel to be assessed are obtained through pre-employment testing, including: Knowledge and Theory score: obtained through an online test, maximum score 100; Safety Awareness score: obtained through a scenario simulation questionnaire, maximum score 100; Practical Skills score: obtained through a practical operation assessment, scored by examiners according to standards, maximum score 100; Emergency Response Capability score: obtained through emergency drills, maximum score 100.

[0047] S200, based on the project information and the job information of the personnel to be evaluated, generates the evaluation weights corresponding to each evaluation dimension. S200 includes:

[0048] S201, Based on the project information, analyze the project's hazard level. S201 includes:

[0049] S2011 performs feature extraction and numerical processing on project information.

[0050] A project type-risk coefficient mapping table is pre-built. Project types are then converted into first numerical features according to this pre-built table. As shown in Table 1, the first numerical feature is obtained by querying the project type-risk coefficient mapping table based on the project type.

[0051] Table 1 Project Type-Risk Coefficient Mapping Table

[0052]

[0053] The project size is normalized into a second numerical feature according to the pre-stored size ranges corresponding to each size level. Specifically, the ranges corresponding to the size levels are pre-defined and normalized to [0,1]. In this embodiment, the project size is divided into small, medium, and large, and the corresponding normalized values ​​are shown in Table 2. The size level is determined based on the actual size of the project to obtain the second numerical feature.

[0054] Table 2 Correspondence Table of Scale Levels

[0055]

[0056] One-hot encoding is performed on the set of hazardous operation types, converting them into numerical vectors as the third numerical feature. Specifically, a list of hazardous operation types is pre-constructed, including... This embodiment describes a common type of hazardous operation. The list includes [hot work, high-altitude work, confined space work, temporary electrical work, lifting work, and blasting work]. The set of hazardous work types for the current project is coded; if a work type is included, the corresponding bit is set to 1; otherwise, it is set to 0, resulting in an M-dimensional binary vector as the third numerical feature. For example, if a project includes working at height and lifting operations, it is coded as [0,1,0,0,1,0].

[0057] S2012, a hazard analysis neural network model is constructed, using the first, second, and third numerical features as inputs to the input layer, and the project's hazard coefficient as the output of the output layer. The hazard analysis neural network model has three layers: an input layer, a hidden layer, and an output layer. The number of nodes in the input layer equals the feature dimension, i.e., the total dimension of the first (1-dimensional), second (1-dimensional), and third (6-dimensional) numerical features; therefore, the number of nodes in the input layer is 1 + 1 + 6 = 8. The output layer has 1 node, and the output value is the project's hazard coefficient, ranging from [0, 1]. The number of nodes in the hidden layer is determined using an empirical formula: ;in The number of nodes in the hidden layer. The number of nodes in the input layer. The number of nodes in the output layer. The adjustment constant is between 1 and 10; in this embodiment, it is set to 5, so the hidden layer has a total of 8 nodes. The hidden layer uses the sigmoid tangent function tansig, and the output layer uses the sigmoid logarithmic function logsig to ensure that the output value is between 0 and 1.

[0058] Collect project information from historical projects and their corresponding actual safety accident data. For each historical project, extract the input feature vector according to the S2011 method, and use the project's accident incidence rate as the label value to form training samples. Input the training samples into a BP neural network for training, and adjust the network weights through the backpropagation algorithm until the model converges. After training, the model can be used to predict the risk coefficient of new projects.

[0059] S2013: Input the first, second, and third numerical features into the hazard analysis neural network model, output the hazard coefficient of the project, and generate the project's hazard level according to the preset hazard level classification rules. Specifically, if the hazard coefficient is less than 0.3, the hazard level is low; if the hazard coefficient is greater than or equal to 0.3 and less than 0.6, the hazard level is medium; and if the hazard coefficient is greater than or equal to 0.6, the hazard level is high.

[0060] S202, Based on the job information of the personnel to be evaluated, analyze the job risk of the personnel to be evaluated. This embodiment uses a lookup table method to determine job risk. Specifically, a job-risk level mapping table is pre-established, as shown in Table 3. The table is queried based on the job name of the personnel to be evaluated to obtain the corresponding job risk. If the job is not listed in the table, it is manually judged based on the job description or defaulted to medium risk.

[0061] Table 3 Job Position-Risk Level Mapping Table

[0062]

[0063] S203 generates assessment weights for each assessment dimension based on the project's hazard level and the job risks of the personnel being assessed; S203 includes:

[0064] S2031, Obtain the benchmark weights for each evaluation dimension; in this embodiment, the benchmark weight vector These correspond to four dimensions: theoretical knowledge, safety awareness, practical skills, and emergency response capabilities. The benchmark weights can be preset based on industry experience or historical data.

[0065] S2032, based on the job risk of the personnel to be evaluated, adjust the benchmark weights of each evaluation dimension to generate the job suitability weights corresponding to each evaluation dimension.

[0066] Specifically, the job suitability weight for the knowledge and theory dimension is inversely proportional to the job risk, while the job suitability weights for the safety awareness, practical skills, and emergency response capabilities dimensions are all directly proportional to the job risk. In particular, job risk is quantified into adjustment coefficients. Adjustment coefficients for each dimension under different job risks are pre-set, as shown in Table 4. The baseline weight of each assessment dimension is multiplied by the corresponding adjustment coefficient to obtain the job suitability weight for each assessment dimension. When the job risk level is low, the weight of the knowledge and theory dimension should be appropriately increased (coefficient > 1), while other dimensions should be appropriately decreased (coefficient < 1); the opposite is true for high levels; and the baseline remains unchanged for medium levels.

[0067] Table 4 Adjustment Coefficient Comparison Table

[0068]

[0069] S2033, Based on the project's hazard level, generate risk enhancement coefficients for the safety awareness dimension and emergency response capability dimension; the risk enhancement coefficients are proportional to the hazard level; in this embodiment, the risk enhancement coefficients for the safety awareness dimension and the emergency response capability dimension have the same value. If the project's hazard level is low, the risk enhancement coefficient is 0.9; if the project's hazard level is medium, the risk enhancement coefficient is 1; if the project's hazard level is high, the risk enhancement coefficient is 1.2; in other embodiments of this application, different values ​​can be taken respectively.

[0070] S2034 multiplies the job suitability weights of the safety awareness dimension and the emergency response capability dimension by their respective risk enhancement coefficients to generate the risk enhancement weights of the safety awareness dimension and the emergency response capability dimension.

[0071] S2035 uses the job suitability weights of the knowledge theory dimension and practical skills dimension as the evaluation weights of the corresponding evaluation dimensions, and the risk enhancement weights of the safety awareness dimension and emergency response capability dimension as the evaluation weights of the corresponding evaluation dimensions. The resulting weight vector is not yet normalized, and the sum of the weights for each dimension may not equal 1.

[0072] This plan first adjusts the four dimensions based on job risks to reflect the core competency requirements of the position; then, it strengthens safety awareness and emergency response capabilities based on project hazards, highlighting the special requirements for these two capabilities in high-risk environments. This ensures that the weighting allocation is both consistent with job characteristics and adaptable to on-site project risks, achieving personalized and precise assessment.

[0073] S204, adjust the evaluation weights of each evaluation dimension based on the historical credit score of the person to be evaluated. S204 includes:

[0074] S2041, based on the historical credit score of the person to be evaluated, adjust the evaluation weights of the safety awareness and practical skills dimensions, while keeping the evaluation weights of the knowledge and theory dimensions and the emergency response capability dimension unchanged. Specifically, a first threshold and a second threshold are preset, wherein the first threshold is greater than the second threshold. In this embodiment, the first threshold is 0.8 and the second threshold is 0.4. The adjustment rules are as follows:

[0075] If the historical credit score is higher than the preset first threshold, the assessment weight of the security awareness dimension will be multiplied by the first adjustment coefficient. The assessment weight of the practical skills dimension will be multiplied by a second adjustment factor. ,in , This embodiment takes , .

[0076] If the historical credit score is lower than the preset second threshold, the assessment weight of the security awareness dimension will be multiplied by a third adjustment factor. The assessment weight of the practical skills dimension will be multiplied by a fourth adjustment factor. ,in , This embodiment takes , .

[0077] If the historical credit score is between the first and second thresholds, the evaluation weights of the safety awareness and practical skills dimensions remain unchanged.

[0078] Therefore, for individuals with good credit, the emphasis is placed on practical skills and less on safety awareness, as their safety awareness is already internalized, and the focus should be on their actual operational capabilities. Conversely, for individuals with poor credit, the emphasis is on whether their basic safety awareness has improved. This mechanism incorporates an individual's historical performance into the current evaluation, incentivizing them to maintain a good safety record while ensuring that the evaluation results better reflect their true competence.

[0079] S2042 normalizes the assessment weights of the knowledge theory dimension, emergency response capability dimension, and the adjusted safety awareness dimension and practical skills dimension, ensuring that the sum of the weights of each assessment dimension is 1, thus generating the final assessment weights for each dimension. This ensures that the sum of the weights of each dimension is 1, making the overall score comparable and facilitating the setting of a unified pass / fail standard.

[0080] S300: Based on the assessment data of the personnel to be assessed in each assessment dimension and the corresponding assessment weights for each dimension, calculate the comprehensive safety capability score of the personnel to be assessed. Let the scores of the personnel to be assessed in the four dimensions of theoretical knowledge, safety awareness, practical skills, and emergency response capability be as follows: , , , (All scores are out of 100), then the overall safety capability score is... The calculation formula is as follows:

[0081]

[0082] In the formula, , , , The final evaluation weights are calculated for four dimensions: theoretical knowledge, safety awareness, practical skills, and emergency response capabilities. In practical applications, an excellent score and a passing score can be set according to project requirements. If the comprehensive safety capability score reaches or exceeds the excellent score, the person is allowed to directly enter the factory for work; if the comprehensive safety capability score reaches or exceeds the passing score, the person is allowed to enter the factory for work after training; if the comprehensive safety capability score does not reach the passing score, the person is directly refused entry to the factory.

[0083] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A multi-dimensional assessment method for the pre-entry safety capabilities of contractor personnel, characterized in that: Includes the following steps: S100: Obtain project information, job information of the personnel to be evaluated, historical credit scores of the personnel to be evaluated, and evaluation data of the personnel to be evaluated in each evaluation dimension; S200, Based on the project information and the job information of the personnel to be evaluated, generate the evaluation weights corresponding to each evaluation dimension; S300: Calculate the comprehensive security capability score of the person to be evaluated based on the evaluation data of the person to be evaluated in each evaluation dimension and the evaluation weight corresponding to each evaluation dimension.

2. The multi-dimensional safety capability assessment method for contractor personnel before entry into the plant as described in claim 1, characterized in that: The assessment dimensions include theoretical knowledge, safety awareness, practical skills, and emergency response capabilities.

3. The multi-dimensional safety capability assessment method for contractor personnel before entry into the plant as described in claim 2, characterized in that: S200 includes: S201, Analyze the hazard level of the project based on the project information; S202, Analyze the job risk of the personnel to be evaluated based on their job information; S203, based on the project's hazard level and the job risks of the personnel to be assessed, generates the assessment weights for each assessment dimension; S204, Adjust the evaluation weights of each evaluation dimension based on the historical credit score of the person to be evaluated.

4. The multi-dimensional safety capability assessment method for contractor personnel before entry into the plant as described in claim 3, characterized in that: The project information includes the project type, project size, and the set of hazardous work types included.

5. The multi-dimensional safety capability assessment method for contractor personnel before entry into the plant as described in claim 4, characterized in that: S201 includes: S2011: Convert the project type into the first numerical feature according to the pre-stored project type-risk coefficient mapping table; normalize the project scale into the second numerical feature according to the scale range corresponding to each pre-stored scale level; perform one-hot encoding on the set of hazardous operation types and convert it into a numerical vector as the third numerical feature. S2012, Construct a hazard analysis neural network model, using the first numerical feature, the second numerical feature and the third numerical feature as the input of the input layer, and the hazard coefficient of the project as the output of the output layer; S2013, input the first numerical feature, the second numerical feature and the third numerical feature into the hazard analysis neural network model, output the hazard coefficient of the project, and generate the hazard level of the project according to the preset hazard level classification rules.

6. The multi-dimensional safety capability assessment method for contractor personnel before entry into the plant as described in claim 3, characterized in that: S203 includes: S2031, Obtain the benchmark weights for each evaluation dimension; S2032, based on the job risk of the personnel to be evaluated, adjust the benchmark weights of each evaluation dimension to generate the job suitability weights corresponding to each evaluation dimension. Among them, the job suitability weight of the knowledge theory dimension is inversely proportional to the job risk, while the job suitability weights of the safety awareness dimension, practical skills dimension, and emergency response capability dimension are all directly proportional to the job risk. S2033, Based on the project's hazard level, generate risk enhancement coefficients for the safety awareness dimension and emergency response capability dimension; the risk enhancement coefficients are proportional to the hazard level. S2034, multiply the job suitability weights of the safety awareness dimension and emergency response capability dimension by their respective risk enhancement coefficients to generate the risk enhancement weights of the safety awareness dimension and emergency response capability dimension. S2035 uses the job suitability weights of the knowledge theory dimension and the practical skills dimension as the evaluation weights of the corresponding evaluation dimensions, and uses the risk enhancement weights of the safety awareness dimension and the emergency response capability dimension as the evaluation weights of the corresponding evaluation dimensions.

7. The multi-dimensional safety capability assessment method for contractor personnel before entry into the plant as described in claim 3, characterized in that: S204 includes: S2041, Based on the historical credit score of the person to be evaluated, adjust the evaluation weights of the safety awareness dimension and the practical skills dimension; if the historical credit score is higher than a preset first threshold, multiply the evaluation weight of the safety awareness dimension by a first adjustment coefficient. The assessment weight of the practical skills dimension will be multiplied by a second adjustment factor. ,in , If the historical credit score is lower than the preset second threshold, the assessment weight of the security awareness dimension will be multiplied by a third adjustment coefficient. The assessment weight of the practical skills dimension will be multiplied by a fourth adjustment factor. ,in , The first threshold is greater than the second threshold.

8. The multi-dimensional safety capability assessment method for contractor personnel before entry into the plant according to claim 7, characterized in that: S204 also includes: S2042 normalizes the evaluation weights of the knowledge theory dimension, emergency response capability dimension, and the adjusted safety awareness dimension and practical skills dimension, so that the sum of the weights of each evaluation dimension is 1, and generates the final evaluation weights of each evaluation dimension.

Images