Construction worker unsafe behavior evaluation method and system based on genetic algorithm and fuzzy analysis

Abstract

The invention provides a construction worker unsafe behavior evaluation method and system based on a genetic algorithm and fuzzy analysis, and relates to the technical field of safety production of the construction industry. According to the method, primary and secondary indexes under different dimensions are collected, scores are given to the secondary indexes, and an evaluation matrix is constructed; corresponding weights are given to the first-level evaluation indexes and the second-level evaluation indexes through a genetic algorithm; the entropy weight of the first-level index is calculated according to the weight of the second-level index, and a comprehensive weight result is obtained; constructing a fuzzy relation matrix between the comprehensive weight result and the evaluation grade; performing matrix operation on the weight of the secondary evaluation index and the fuzzy relation matrix to obtain a weight vector of the secondary index; and performing matrix operation on the weight vector and the comprehensive weight result to obtain a comprehensive evaluation vector of each building worker, and displaying the comprehensive evaluation vector to a employment unit in a table form. According to the method, the genetic algorithm and the fuzzy analytic hierarchy process are combined to quantitatively analyze the unsafe behaviors of the building workers, and a scientific basis is provided for safety management of the building industry.

Description

Technical Field

[0001] The present invention relates to the technical field of safe production in the construction industry, and in particular to a method and system for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis. Background Art

[0002] There are many types of unsafe behaviors at construction sites, and the strength of each unsafe behavior is different. It is impossible to make quantitative analysis by purely relying on manpower to distinguish various unsafe behaviors, resulting in inaccurate judgment results.

[0003] The key point is how to construct an evaluation model for the unsafe behaviors of construction workers and provide a basis for judging unsafe behaviors for safety management in the construction industry. Summary of the invention

[0004] Purpose of the invention: The present invention aims to develop a method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis, aiming to solve the above-mentioned problems existing in the prior art.

[0005] First, a method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis is proposed, which includes the following steps:

[0006] Collecting evaluation indicators of unsafe behaviors of construction workers in different dimensions; the evaluation indicators include primary indicators, each of which is associated with a number of secondary indicators;

[0007] Assigning scores to the secondary indicators according to their importance, constructing all the scores into an evaluation matrix, and performing a standardization operation on the evaluation matrix;

[0008] Use genetic algorithm to assign corresponding weights to each primary evaluation index and secondary evaluation index;

[0009] The entropy weight of the first-level indicator is calculated based on the weight of the second-level indicator, and the entropy weights of multiple first-level indicators are aggregated to obtain the comprehensive weight result;

[0010] Construct the fuzzy relationship matrix between the comprehensive weight results and the evaluation grades;

[0011] Performing matrix operations on the weights of each secondary evaluation index and the fuzzy relationship matrix to obtain a weight vector of the secondary index;

[0012] The weight vector of the secondary index and the comprehensive weight result are matrix-operated to obtain the comprehensive evaluation vector of each construction worker; and the comprehensive evaluation vector of each construction worker is displayed to the employer in the form of a table.

[0013] In a further embodiment of the first aspect, the primary indicator B i and secondary indicator C ij The relationship is expressed as:

[0014] B i =(C i1 ,C i2 ,…,C ij )

[0015] The first level indicator B i Including physical quality B1, psychological quality B2, safety knowledge and continuous education B3, personal work habits and skills B4, emotional control and behavioral norms B5;

[0016] Among them, the first-level indicator physiological quality B1 includes the following second-level indicators: physical health status C11, physiological rhythm status C12, and fatigue resistance C13;

[0017] The first-level indicator psychological quality B2 includes the following second-level indicators: stress resistance C21, emotional stability C22, and concentration C23;

[0018] The first-level indicator safety knowledge and continuous education B3 includes the following second-level indicators: safety regulations knowledge C31, emergency response capability C32, and education background level C33;

[0019] The first-level indicator, personal work habits and skills B4, includes the following second-level indicators: precise operation skills C41, standardized work habits C42, and continuous learning ability C43;

[0020] The first-level indicator emotional control and behavioral norms B5 includes the following second-level indicators: emotional management skills C51, behavioral self-discipline C52, and conflict handling ability C53.

[0021] In a further embodiment of the first aspect, each secondary indicator is given a score of 1 to 5 according to its importance, and the scores increase in importance from 1 to 5; all the scores are constructed into an evaluation matrix X;

[0022] The evaluation matrix X is standardized as follows:

[0023]

[0024] In the formula, x ij represents the data in the i-th row and j-th column of the evaluation matrix; n represents the number of rows in the evaluation; x i ′ j Represents the normalized data.

[0025] In a further embodiment of the first aspect, a corresponding weight is assigned to each primary evaluation index and secondary evaluation index by a genetic algorithm, specifically including:

[0026] Randomly generate an initial population of size N, each individual is a weight vector w = [w1, w2, ..., w m ], where m is the number of evaluation indicators;

[0027] Define the fitness function and evaluate the fitness value of each individual based on the comprehensive score. The fitness function formula is as follows:

[0028]

[0029] In the formula, X ij The standardized value of the i-th evaluation object on the j-th indicator, n is the number of evaluation objects; w j Represents the normalized weight of the secondary indicator;

[0030] Select parent individuals from the current population according to the fitness value, using a roulette wheel selection strategy to give priority to individuals with high fitness values;

[0031] Perform single-point or multi-point crossover operations on offspring individuals, exchange some genes of parent individuals, and generate new weight combinations;

[0032] Perform weight mutation on some offspring individuals with a small probability;

[0033] Repeat the above operation until the convergence condition or the upper limit of the number of iterations is reached, and finally the optimal weight combination is obtained.

[0034] In a further embodiment of the first aspect, the entropy weight of the primary indicator is calculated according to the weight of the secondary indicator, and the expression is as follows:

[0035]

[0036] Where W i represents the entropy weight of the i-th first-level indicator; w j Represents the normalized weight of the secondary indicator;

[0037] The entropy weights of multiple first-level indicators are aggregated to obtain the comprehensive weight result W = (W1, W2, W3, W4, W5);

[0038] In the formula, W1 represents the entropy weight of the first-level indicator B1; W2 represents the entropy weight of the first-level indicator B2; W3 represents the entropy weight of the first-level indicator B3; W4 represents the entropy weight of the first-level indicator B4; W5 represents the entropy weight of the first-level indicator B5.

[0039] In a further embodiment of the first aspect, a fuzzy relationship matrix R between the comprehensive weight results and the evaluation scores is constructed, and the expression is as follows:

[0040]

[0041] Where a1, b1, a2, b2, a3, b3 represent the specified evaluation levels, corresponding to 0 to 5.

[0042] In a further embodiment of the first aspect, the weight of each secondary evaluation index and the fuzzy relationship matrix R are subjected to matrix operation to obtain the weight vector Z of the secondary index i :

[0043] Z i =[w1w2w3w4w5]·R

[0044] Where R represents the fuzzy relationship matrix between the comprehensive weight result and the evaluation score; w j Represents the normalized weight of the secondary indicator;

[0045] The weight vector Z of the secondary index i Perform matrix operation with the comprehensive weight result W to obtain the comprehensive evaluation vector Y of each construction worker. i =W*Z i .

[0046] The second aspect of the present invention discloses a construction worker unsafe behavior evaluation system, the system comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the processor, the instructions are used to be executed by the processor to implement the construction worker unsafe behavior evaluation method based on genetic algorithm and fuzzy analysis as described in the first aspect.

[0047] Beneficial effects: The method for evaluating unsafe behaviors of construction workers proposed in the present invention adopts a combination of genetic algorithm and fuzzy hierarchical analysis method to judge certain unsafe behaviors of construction workers for quantitative analysis, and obtains a comprehensive evaluation model, which provides a scientific basis for safety management in the construction industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a worker individual factor affiliation diagram of the construction worker unsafe behavior evaluation method in the embodiment.

[0049] Figure 2 It is an evaluation flow chart of the evaluation method for unsafe behavior of construction workers in the embodiment.

[0050] Figure 3 It is a flow chart of the genetic algorithm of the method for evaluating unsafe behaviors of construction workers in the embodiment.

[0051] Figure 4 It is a fitness curve iteration diagram of the construction worker unsafe behavior evaluation method in the embodiment.

[0052] Figure 5 It is the comprehensive evaluation result of the evaluation method for unsafe behavior of construction workers in the embodiment. DETAILED DESCRIPTION

[0053] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features known in the art are not described.

[0054] Reference Figures 1-2 ,The embodiment of the present invention provides a method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis.,Firstly, starting from individual factors of workers, an index system that comprehensively covers various types of unsafe behaviors is established.,Secondly, these behaviors are systematically evaluated by combining genetic algorithm and fuzzy analytic hierarchy method, and an evaluation model for unsafe behaviors of construction workers is,constructed.

[0055] Reference Figures 3 to 5 The specific details of the construction worker unsafe behavior evaluation method using genetic algorithm and fuzzy analysis described in the embodiment of the present invention are as follows:

[0056] Firstly, the evaluation indexes of unsafe behaviors of construction workers in different dimensions are collected. The evaluation indexes include primary indexes, and each primary index is associated with several secondary indexes.

[0057] The first-level indicators include physiological quality B1, psychological quality B2, safety knowledge and continuous education B3, personal work habits and skills B4, and emotional control and behavioral norms B5. The second-level indicators include physical health status C11, physiological rhythm status C12, fatigue resistance C13, stress resistance C21, emotional stability C22, concentration C23, safety regulations knowledge C31, emergency response ability C32, education background level C33, precise operation skills C41, standardized work habits C42, continuous learning ability C43, emotional management skills C51, behavioral self-discipline C52, and conflict handling ability C53.

[0058] Physiological fitness: In the construction industry, workers need to perform long hours and high-intensity physical labor, which places high demands on physical adaptability. Fatigue management is a key safety consideration because fatigue not only reduces workers' reaction speed and judgment, but also increases the risk of accidents. Effective fatigue management strategies include appropriate rest time, shift system, and regular health checks for workers to monitor their physical condition and work ability.

[0059] Psychological quality: Psychological stability is essential for safe work, especially in high-pressure and potentially dangerous work environments. Construction workers face stress from workload, tight deadlines, and physical fatigue. Cultivating workers' stress tolerance through psychological support and coping strategies, such as stress management training and mental preparation for emergencies, can significantly reduce errors and accidents caused by stress.

[0060] Safety knowledge and continuous education: Lack of safety knowledge is a major factor that leads to unsafe behaviors among construction workers. Continuous safety education and training can ensure that workers are aware of the latest safety procedures and operating standards. Education should include accident prevention, proper use of safety equipment, first aid skills, etc. In addition, paying attention to the induction training of new workers and the re-education of experienced workers can effectively improve the safety level of the entire workplace.

[0061] Responsibility and teamwork: On construction sites, workers' individual work habits and skills are crucial to ensuring work efficiency and safety. Good work habits, such as completing tasks on time, strictly following operating procedures, and using tools and equipment correctly, not only help improve productivity, but are also key factors in preventing accidents and improving construction quality. If workers can maintain these habits continuously, the incidence of safety accidents will be significantly reduced. At the same time, the level of professional skills of workers is also directly related to their ability to perform tasks. Highly skilled workers can usually understand and implement technical requirements more accurately, effectively avoiding problems caused by improper operation. A high level of professional skills not only includes proficient operation of tools, but also involves a deep understanding of work processes and the ability to deal with emergencies. Therefore, improving the skill level of workers has a decisive impact on reducing operating errors and improving overall work quality. Responsibility can be achieved through team building activities, safety incentives and a clear responsibility system.

[0062] Emotional control and behavioral regulation: Emotional fluctuations on construction sites can increase the risk of unsafe behavior. When workers are emotionally unstable, they may make impulsive decisions, such as ignoring safety steps or conflicting with co-workers, which can lead to accidents. Through emotion management training, education on conflict resolution techniques, and creating a supportive work environment, workers can be helped to stay calm and focused in stressful situations.

[0063] Next, the importance of each evaluation indicator is scored. Here, the expert scoring method is used to give 1 to 5 points, and the corresponding importance is divided into five levels: unimportant, not very important, general, important, and very important. The score comparison table 1 is shown.

[0064] Table 1 Evaluation index importance score table

[0065] Importance Points unimportant 1 Not very important 2 generally 3 important 4 Very important 5

[0066] All the values ​​are constructed into an evaluation matrix. In this embodiment, a sampling survey is conducted on workers at a construction site, and there are 10 survey subjects in the survey. Each evaluation subject has 15 evaluation indicators, and the evaluation matrix X is obtained as follows:

[0067]

[0068] Perform a standardization operation on the evaluation matrix X, the expression is as follows:

[0069]

[0070] x ij represents the data in the i-th row and j-th column of the evaluation matrix; n represents the number of rows in the evaluation; x i ′ j Represents the normalized data.

[0071] In this embodiment, the above evaluation matrix X is standardized to obtain:

[0072]

[0073] In order to improve the accuracy of the evaluation model, this application uses a genetic algorithm to optimize the weight distribution. The genetic algorithm simulates the natural evolution process and gradually optimizes the weight combination of evaluation indicators, thereby overcoming the limitations of the traditional entropy weight method in processing complex multidimensional data.

[0074] The steps of genetic algorithm weight optimization are as follows:

[0075] Initialize the population: Randomly generate an initial population of size N, each individual is a weight vector w = [w1, w2, ..., w m ], where m is the number of evaluation indicators.

[0076] Fitness calculation: Define the fitness function and evaluate the fitness value of each individual based on the comprehensive score. The fitness function formula is as follows:

[0077] Among them, X ij The standardized value of the i-th evaluation object on the j-th indicator, and n is the number of evaluation objects.

[0078] Selection operation: Select parent individuals from the current population based on their fitness values, using strategies such as roulette wheel selection to give priority to individuals with higher fitness values.

[0079] Crossover operation: Perform single-point or multi-point crossover operations on offspring individuals to exchange some genes of parent individuals and generate new weight combinations.

[0080] Mutation operation: Perform a small probability weight mutation on some offspring individuals to prevent the algorithm from falling into the local optimum and maintain the diversity of the population.

[0081] Iterative optimization: Repeat the selection, crossover and mutation operations until the convergence condition or the upper limit of the number of iterations is reached, and finally the optimal weight combination is obtained.

[0082] The flowchart of the genetic algorithm is as follows Figure 3 shown.

[0083] Through the above genetic algorithm, the fitness curve is obtained as follows Figure 4 As shown in the figure, it can be seen from the fitness curve that with the increase of the number of iterations, the fitness gradually tends to a stable value. Although there will be some fluctuations in the end, the fluctuations are very small and can be ignored. The genetic algorithm can optimize the weights well in this problem.

[0084] The entropy weight of the first-level indicator is calculated according to the weight of the second-level indicator:

[0085]

[0086] W i represents the entropy weight of the i-th first-level indicator; w j Represents the normalized weight of the secondary indicator; the entropy weights of multiple primary indicators are aggregated to obtain the comprehensive weight result W = (W1, W2, W3, W4, W5).

[0087] W1 represents the entropy weight of the first-level indicator B1; W2 represents the entropy weight of the first-level indicator B2; W3 represents the entropy weight of the first-level indicator B3; W4 represents the entropy weight of the first-level indicator B4; W5 represents the entropy weight of the first-level indicator B5.

[0088] In this embodiment, the entropy weight of the secondary indicator is calculated based on the entropy value and entropy weight formula of the secondary indicator:

[0089] w1=(a1,a2,a3)=(0.0599,0.0277,0.0440)

[0090] w2=(a1,a2,a3)=(0.0278,0.0750,0.0505)

[0091] w3=(a1,a2,a3)=(0.1266,0.0242,0.0267)

[0092] w4=(a1,a2,a3)=(0.2098,0.0901,0.0258)

[0093] w5=(a1,a2,a3)=(0.0925,0.0713,0.0480)

[0094] Further normalization:

[0095] w1=(a1,a2,a3)=(0.4553,0.2104,0.3343)

[0096] w2=(a1,a2,a3)=(0.1814.0.4892,0.3294)

[0097] w3=(a1,a2,a3)=(0.7134,0.1364,0.1502)

[0098] w4=(a1,a2,a3)=(0.6441,0.2767,0.0792)

[0099] w5=(a1,a2,a3)=(0.4368,0.3365,0.2267)

[0100] According to the entropy weight formula of the secondary indicator, the entropy weight of the primary indicator is calculated:

[0101] W=(W1,W2,W3,W4,W5)=(0.1316,0.1534,0.1775,0.3256,0.2119)

[0102] Finally, the comprehensive weight results are obtained, as shown in Table 2:

[0103] Table 2 Comprehensive weight results of primary and secondary indicators

[0104]

[0105]

[0106] From the results, we can see that personal work habits and skills account for the highest proportion, which shows that the main factors for unsafe behaviors are still some operational problems and operational norms, which is also in line with the current situation of accidents. Physiological quality accounts for the lowest proportion, because construction workers are generally in good physical condition, so this will not be the main reason for the high incidence of accidents.

[0107] Then, the fuzzy relationship matrix R between the comprehensive weight results and the evaluation scores is constructed:

[0108]

[0109] Where a1, b1, a2, b2, a3, b3 represent the specified evaluation levels, corresponding to 0 to 5.

[0110] In this embodiment, taking worker 1 as an example, the fuzzy relationship of the worker is calculated according to the fuzzy relationship matrix:

[0111]

[0112] Among them, the rest of the personal calculation process is the same.

[0113] By performing matrix operations on the weights of each secondary indicator and the fuzzy relationship matrix of each worker, we can obtain the comprehensive evaluation vector of the five primary indicators of each worker. Here we only show the calculation process for the first worker. The evaluation calculation process for other workers is the same. The calculation process is as follows:

[0114]

[0115] Finally, the comprehensive weight of the first-level index and the weight vector of the second-level index are matrix-operated to obtain the comprehensive evaluation vector of the first worker and normalize the result. The specific process is as follows:

[0116] Y1=W*Z1=(0.2813,0.2568,0.3028,0.1591)

[0117] At the same time, the evaluation results of other workers were also obtained, which are summarized in Table 3 and Figure 3 As shown:

[0118] Table 3 Calculation summary results

[0119]

[0120]

[0121] Through the above calculation steps, we can get the value of each secondary indicator in the evaluation vector of each worker and the evaluation result of each worker, which can fully reflect the specific proportion of unsafe behaviors under various factors. From the results, we can also see that for the overall situation, the evaluation score of workers' unsafe behaviors is relatively low, which means that in practical applications, it is necessary to strengthen the management of workers to reduce the accident rate.

[0122] When applied on site, the entire set of evaluation methods for unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis disclosed in the above embodiment can be written into computer code, and the code can be allowed to execute corresponding instructions. Thus, a construction worker unsafe behavior evaluation system is constructed, which includes at least one processor and a memory connected to the processor in communication. The memory stores instructions that can be executed by the processor.

[0123] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the present invention itself. Various changes may be made to it in form and detail without departing from the spirit and scope of the present invention as defined in the appended claims.

Claims

1. A method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis, characterized in that: The steps include: Collecting evaluation indicators of unsafe behaviors of construction workers in different dimensions; the evaluation indicators include primary indicators, each of which is associated with a number of secondary indicators; Assigning scores to the secondary indicators according to their importance, constructing all the scores into an evaluation matrix, and performing a standardization operation on the evaluation matrix; Use genetic algorithm to assign corresponding weights to each primary evaluation index and secondary evaluation index; The entropy weight of the first-level indicator is calculated based on the weight of the second-level indicator, and the entropy weights of multiple first-level indicators are aggregated to obtain the comprehensive weight result; Construct the fuzzy relationship matrix between the comprehensive weight results and the evaluation grades; Performing matrix operations on the weights of each secondary evaluation index and the fuzzy relationship matrix to obtain a weight vector of the secondary index; The weight vector of the secondary index and the comprehensive weight result are subjected to matrix operation to obtain a comprehensive evaluation vector of each construction worker; and the comprehensive evaluation vector of each construction worker is displayed to the employing unit in the form of a table.

2. According to claim 1, a construction worker unsafe behavior evaluation method based on genetic algorithm and fuzzy analysis is characterized in that: The first level indicator B i and secondary indicator C ij The relationship is expressed as B i =(C i1 ,C i2 ,…,C ij ); The first level indicator B i Including physical quality B1, psychological quality B2, safety knowledge and continuous education B3, personal work habits and skills B4, emotional control and behavioral norms B5; Among them, the first-level indicator physiological quality B1 includes the following second-level indicators: physical health status C11, physiological rhythm status C12, and fatigue resistance C13; The first-level indicator psychological quality B2 includes the following second-level indicators: stress resistance C21, emotional stability C22, and concentration C23; The first-level indicator safety knowledge and continuous education B3 includes the following second-level indicators: safety regulations knowledge C31, emergency response capability C32, and education background level C33; The first-level indicator, personal work habits and skills B4, includes the following second-level indicators: precise operation skills C41, standardized work habits C42, and continuous learning ability C43; The first-level indicator emotional control and behavioral norms B5 includes the following second-level indicators: emotional management skills C51, behavioral self-discipline C52, and conflict handling ability C53.

3. The method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis according to claim 2 is characterized in that: Each secondary indicator is given a score of 1 to 5 according to its importance, and the scores increase in importance from 1 to 5; all the scores are constructed into an evaluation matrix X; The evaluation matrix X is standardized as follows: In the formula, x ij represents the data in the i-th row and j-th column of the evaluation matrix; n represents the number of rows in the evaluation; x i ′ j Represents the normalized data.

4. The method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis according to claim 1 is characterized in that: The method of assigning corresponding weights to each primary evaluation index and secondary evaluation index by genetic algorithm specifically includes: Randomly generate an initial population of size N, each individual is a weight vector w = [w1, w2, ..., w m ], where m is the number of evaluation indicators; Define the fitness function and evaluate the fitness value of each individual based on the comprehensive score. The fitness function formula is as follows: In the formula, X ij The standardized value of the i-th evaluation object on the j-th indicator, n is the number of evaluation objects; w j Represents the normalized weight of the secondary indicator; Select parent individuals from the current population according to the fitness value, using a roulette wheel selection strategy to give priority to individuals with high fitness values; Perform single-point or multi-point crossover operations on offspring individuals, exchange some genes of parent individuals, and generate new weight combinations; Perform weight mutation on some offspring individuals with a small probability; Repeat the above operation until the convergence condition or the upper limit of the number of iterations is reached, and finally the optimal weight combination is obtained.

5. The method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis according to claim 2 is characterized in that: The entropy weight of the first-level indicator is calculated according to the weight of the second-level indicator. The expression is as follows: Where W i represents the entropy weight of the i-th first-level indicator; w j Represents the normalized weight of the secondary indicator; The entropy weights of multiple first-level indicators are aggregated to obtain the comprehensive weight result W = (W1, W2, W3, W4, W5); In the formula, W1 represents the entropy weight of the first-level indicator B1; W2 represents the entropy weight of the first-level indicator B2; W3 represents the entropy weight of the first-level indicator B3; W4 represents the entropy weight of the first-level indicator B4; W5 represents the entropy weight of the first-level indicator B5.

6. The method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis according to claim 5 is characterized in that: The fuzzy relationship matrix R between the comprehensive weight result and the evaluation score is constructed, and the expression is as follows: Where a1, b1, a2, b2, a3, b3 represent the specified evaluation levels, corresponding to 0 to 5.

7. The method for evaluating unsafe behaviors of construction workers based on genetic algorithm and fuzzy analysis according to claim 6 is characterized in that: The weight of each secondary evaluation index and the fuzzy relationship matrix R are matrix operated to obtain the weight vector Z of the secondary index: i : WITH i =[w1w2w3w4w5] R Where R represents the fuzzy relationship matrix between the comprehensive weight result and the evaluation score; w j Represents the normalized weight of the secondary indicator; The weight vector Z of the secondary index i Perform matrix operation with the comprehensive weight result W to obtain the comprehensive evaluation vector Y of each construction worker. i =W*Z i .

8. A construction worker unsafe behavior evaluation system, characterized in that: include: at least one processor; and at least one memory in communication with the processor; wherein: The memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the construction worker unsafe behavior evaluation method based on genetic algorithm and fuzzy analysis as described in any one of claims 1 to 7.

Images