Secure area division method and system

Abstract

The invention provides a safety area division method and system. A safety area comprises a plurality of sub-areas. The security region division method comprises the following steps: acquiring risk-related real-time data and corresponding historical data of each sub-region; based on the real-time data and historical data of each sub-region, determining a dynamic risk value of the corresponding sub-region, and establishing a multi-dimensional risk assessment model; generating a multi-dimensional risk dynamic weight matrix based on the dynamic risk values of the plurality of sub-regions; and dynamically optimizing the dynamic weight matrix through a greedy algorithm. According to the safe area division method provided by the invention, based on the dynamic weight matrix, the problems of how to adapt to the rapid change of the construction progress and how to improve the management efficiency and the response speed are solved.

Description

Technical Field

[0001] The present invention relates to a safety management technology for a construction site, and in particular to a safety area division method and system. Background Art

[0002] With the rapid development of urbanization, the construction industry faces increasingly severe safety challenges. Construction sites are complex environments, densely populated with people, and feature a vast array of equipment. Effectively demarcating and adjusting safety zones is crucial for preventing accidents and protecting the lives and property of construction workers. Dynamic safety zone demarcation based on construction progress is a dynamic optimization problem, and similar algorithms are widely used in fields such as logistics, transportation, and urban planning.

[0003] Existing construction site safety management relies on manual inspections and fixed zoning, which is unable to adapt to the rapid changes in construction progress, resulting in low management efficiency and response speed. Therefore, how to provide a safety zoning method and system that can adapt to the rapid changes in construction progress and effectively improve management efficiency and response speed has become an urgent problem in the industry. Summary of the Invention

[0004] In order to adapt the area division to the rapid changes in the construction progress and thereby effectively improve the management efficiency and response speed, the present invention provides a safety area division method and system.

[0005] The technical solutions of the present invention are as follows:

[0006] A method for dividing a security area, wherein the security area includes multiple sub-areas; the method comprises:

[0007] Obtain real-time risk-related data and corresponding historical data for each sub-region;

[0008] Determine the dynamic risk value of the corresponding sub-region based on the real-time data and the historical data of each sub-region, and establish a multi-dimensional risk assessment model;

[0009] generating a dynamic weight matrix based on the dynamic risk values ​​of the plurality of sub-regions;

[0010] The dynamic weight matrix is ​​dynamically optimized by a greedy algorithm.

[0011] Optionally, the step of obtaining real-time risk-related data for each sub-region includes:

[0012] Collect raw data related to risks in each sub-area in real time;

[0013] Preprocessing the raw data; wherein the preprocessing includes cleaning and standardizing the raw data.

[0014] Furthermore, the step of collecting raw data related to risks in each sub-area in real time includes:

[0015] At least one of the following information is collected in real time: personnel location information, equipment status information, environmental parameter information, construction progress information, and equipment operation parameter information of each sub-area.

[0016] Optionally, the step of determining the dynamic risk value of the corresponding sub-region based on the real-time data and the historical data of each sub-region and establishing a multi-dimensional risk assessment model includes:

[0017] determining at least two risk factor parameter values ​​based on the real-time data;

[0018] Determining at least two factor weight coefficients corresponding one-to-one to the at least two risk factor parameter values ​​based on the historical data;

[0019] Determine the sum of the products of the at least two risk factor parameter values ​​and the corresponding factor weight coefficients as the dynamic risk value of each sub-region;

[0020] Minimize the sum of the dynamic risk values ​​of the multiple sub-areas.

[0021] Optionally, the method further includes:

[0022] Determine the security level of each sub-area; and determine the update frequency of the dynamic weight matrix when operating in the corresponding sub-area based on the security level.

[0023] Optionally, the method further includes:

[0024] In response to receiving accident occurrence information, or in response to receiving construction status change information, the dynamic weight matrix update is triggered.

[0025] Optionally, the step of dynamically optimizing the dynamic weight matrix by a greedy algorithm includes:

[0026] The dynamic weight matrix is ​​optimized by a multi-objective function; the multi-objective function is determined according to the following method:

[0027]

[0028] Among them, F tatol is a multi-objective function; R j represents the initial risk value of the jth region; R j ' represents the risk value of the jth region after optimization; w1 is the target weight coefficient of the risk target; C k represents the initial cost of the kth task or resource; C k' represents the cost of the kth task or resource after optimization; w2 is the target weight coefficient of the cost target; E i represents the initial risk value of the jth region; E i ' represents the risk value of the i-th region after optimization; w3 is the target weight coefficient of the efficiency target.

[0029] Furthermore, the method further includes: regularly iterating the multi-objective function; and terminating the iteration by limiting the number of iterations or judging the convergence.

[0030] Optionally, the method further includes: updating the safety area boundary map in real time based on the optimized dynamic weight matrix, and displaying the map.

[0031] The present application also provides a security area division system, wherein the security area includes multiple sub-areas; the system includes:

[0032] Data acquisition module, used to obtain real-time risk-related data and corresponding historical data for each sub-area;

[0033] A multidimensional risk assessment model module, which determines the dynamic risk value of each sub-region based on the real-time data and the historical data, and establishes a multidimensional risk assessment model;

[0034] A dynamic weight matrix module generates a dynamic weight matrix based on the dynamic risk values ​​of the multiple sub-regions;

[0035] The dynamic optimization module is used to dynamically optimize the dynamic weight matrix through a greedy algorithm.

[0036] The beneficial effects of the present invention are as follows:

[0037] By acquiring real-time and historical data related to risks in each sub-area, and determining the dynamic risk value of each sub-area based on these real-time and historical data, a multi-dimensional risk assessment model is established. Furthermore, a dynamic weight matrix is ​​generated based on the dynamic risk values ​​of multiple sub-areas, and the dynamic weight matrix is ​​dynamically optimized using a greedy algorithm. This allows the system to adapt to rapid changes in construction progress, effectively improving management efficiency and response speed.

[0038] Moreover, by comprehensively considering the influence of multi-dimensional factors, the partitioning scheme is ensured to be more scientific and reasonable; and through the improved greedy algorithm of multi-objective optimization, it can effectively balance the relationship between safety, economy and operational efficiency, and achieve the comprehensive optimization goal. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of a method for dividing a security area according to an embodiment of the present invention;

[0040] Figure 2 is an overall flow chart of a security area division method according to another embodiment of the present invention;

[0041] Figure 3 yes Figure 2 Specific implementation flow chart of the security area division method;

[0042] Figure 4 is a structural block diagram of a security area division system according to an embodiment of the present invention;

[0043] Figure 5 It is a structural block diagram of a security area division system according to another embodiment of the present invention. DETAILED DESCRIPTION

[0044] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. The advantages and features of the present invention will become more apparent from the following description and claims. It should be noted that the drawings are greatly simplified and not to exact scale, and are intended solely to facilitate and clearly illustrate the embodiments of the present invention.

[0045] First, it should be noted that the safety zone partitioning method in this application is a dynamic weight matrix-based safety zone partitioning algorithm (DWM-SZPA), particularly for real-time optimization of construction sites. The safety zone can be a construction site, which can be divided into multiple sub-zones.

[0046] Example:

[0047] Figure 1 The following is a flow chart of the method for dividing a security area according to an embodiment of the present application. Figure 1 , the security area division method of this application is described in detail.

[0048] In step 101, real-time risk-related data and corresponding historical data of each sub-region are obtained.

[0049] In one embodiment, step 101 may include the following sub-steps:

[0050] Step 1011: collect raw data related to risks in each sub-area in real time.

[0051] The original data related to the risk may include at least one of personnel location information, equipment status information, environmental parameter information, construction progress information, and equipment operation parameter information of each sub-area.

[0052] In a specific example, sensors and IoT devices can be used to obtain real-time information on construction site personnel location, equipment status, and environmental parameters. Specifically, infrared and RFID positioning devices can be used to obtain real-time personnel location information, equipment operating status information, and construction progress information. IoT technology can also be used to collect equipment operating parameter information in real time. Furthermore, the system can be integrated with an on-site construction progress management system to track construction progress information.

[0053] Step 1012: pre-process the original data.

[0054] Among them, preprocessing includes cleaning and standardizing the original data to ensure the consistency and accuracy of the input data.

[0055] As an optimal solution, the regional adjustment unit can also be used to timely adjust the regional security policy according to the security level change rules. This can further adapt to the rapid changes in construction progress and improve management efficiency and response speed.

[0056] In step 102, based on the real-time data and historical data of each sub-region, the dynamic risk value of the corresponding sub-region is determined, and a multi-dimensional risk assessment model is established.

[0057] In one embodiment, step 102 may include the following sub-steps:

[0058] Step 1021: Determine at least two risk factor parameter values ​​based on real-time data.

[0059] Specifically, the following risk factors can be considered: personnel density, equipment hazard level, construction stage (such as foundation construction, main structure construction), distribution of hazard sources (such as high-altitude work areas, heavy machinery areas), and environmental hazard level (temperature and humidity, etc.).

[0060] Step 1022: Determine at least two factor weight coefficients corresponding to at least two risk factor parameter values ​​based on historical data.

[0061] The sum of the weight coefficients of the factors may be equal to 1.

[0062] Step 1023: Determine the sum of the products of at least two risk factor parameter values ​​and corresponding factor weight coefficients as the dynamic risk value of each sub-region.

[0063] Step 1024: Minimize the sum of the dynamic risk values ​​of the multiple sub-regions.

[0064] In a specific example, assume that the construction site is divided into N grid areas, and the dynamic risk value of each sub-area is: W i =a·D i +b·E i +c·Vi .

[0065] Among them, Di is the personnel density of sub-area i, and the specific unit can be people / square meter; Ei is the equipment density of sub-area i, and the specific size can be 1 to 5. The higher Ei, the more dangerous it is; Vi is the environmental hazard level of the construction site in sub-area i, and specifically can be related to factors such as high temperature, high altitude, and toxic and harmful gases. a, b, and c are the corresponding factor weight coefficients, which are adjusted according to actual conditions. The factor weight coefficients range from [0,1] and satisfy a+b+c=1. Specifically, the factor weight coefficients can be determined by historical data analysis or expert evaluation method. Among them, the historical data analysis method can analyze the historical accident records of the construction site and statistically analyze the relationship between the cause of the accident and each factor. For example, if equipment failure is the main cause of the accident, b is given a larger weight. The expert evaluation method can invite experts in safety management, equipment management, and construction progress management to score the importance of each risk factor, and determine the factor weight coefficient based on expert opinions. Its goal is to minimize the sum of the dynamic risk values ​​of multiple sub-areas, that is,

[0066] In a specific example, the risk factor parameter values ​​and weight coefficients are shown in the following table:

[0067]

[0068] Among them, the dynamic risk value W of sub-area A is A =8*0.4+7*0.35+…; Dynamic risk value W of sub-area B B =6*0.3+8*0.25+…; Dynamic risk value W of sub-area C C =5*0.2+9*0.15+….

[0069] In step 103 , a dynamic weight matrix is ​​generated based on the dynamic risk values ​​of the multiple sub-regions.

[0070] That is to say, based on real-time data and risk assessment results, a multi-dimensional risk dynamic weight matrix is ​​generated to describe the security priority and adjustment strategy of each area.

[0071] Specifically, a dynamic weight matrix is ​​constructed based on the dynamic risk value updated in real time. Where N is the number of sub-areas divided on site, and Wi is the dynamic risk value for each construction area, representing the sub-area's priority. A smaller value indicates a higher safety level and lower risk. The W matrix adjusts the weight coefficients of each sub-area in the global optimization problem to ensure a globally optimal solution that meets priority constraints.

[0072] In one embodiment, the method further includes: determining a safety level for each sub-area; and determining an update frequency of a dynamic weight matrix when operating in the corresponding sub-area according to the safety level.

[0073] Specifically, the update frequency of the dynamic weight matrix can be determined based on the specific conditions and management needs of the construction site. The safety level of each sub-area is determined so that the area can be set as a high-risk area, a medium-risk area, and a low-risk area. In a specific example, when working in a high-risk area, the update frequency of the dynamic weight matrix can be updated every 5 to 10 minutes; when working in a low-risk area, it can be updated every hour or every shift. This can further ensure that both the timeliness and effectiveness of updates are taken into account.

[0074] Furthermore, real-time construction site data and historical data analysis results can be combined, primarily through data collection, data analysis, and weight adjustment. Data collection can include data collection on Di, Ei, and Vi; data analysis can include analyzing the impact of various risk factors; and weight adjustment involves adjusting the weights of a, b, and c.

[0075] In one embodiment, the method further includes triggering a dynamic weight matrix update in response to receiving accident information or receiving construction status change information. In other words, upon receiving accident information or construction status change information, the dynamic weight matrix update is triggered, thereby further ensuring both the timeliness and effectiveness of the update.

[0076] In step 104, the dynamic weight matrix is ​​dynamically optimized using a greedy algorithm.

[0077] In one embodiment, in order to ensure both cost and efficiency while ensuring safety, the original dynamic optimal solution is optimized with multiple objectives, thereby improving the quality and adaptability of the solution.

[0078] Specifically, three objective functions, f1, f2, and f3, are established, corresponding to risk reduction, cost optimization, and efficiency improvement, respectively, to form a multi-objective optimization problem. This improved greedy strategy also requires a weighted approach to balance these three objective functions. Each iteration minimizes the maximum security risk of the current sub-region while simultaneously satisfying the goals of risk reduction, cost optimization, and efficiency improvement.

[0079] The objective function f1 is determined as follows:

[0080]

[0081] The objective function f1 is used to reduce the risk value of each sub-area by optimizing the zoning of the construction site, where Rj represents the initial risk value of the jth area; R j ' represents the risk value of the jth region after optimization. The optimization goal is to maximize f1, that is, to reduce the overall risk.

[0082] The objective function f2 is determined as follows:

[0083]

[0084] The objective function f2 is used to minimize the total cost by partitioning the construction site. k represents the initial cost of the kth task or resource; C k ' represents the cost of the kth task or resource after optimization. The optimization goal is to minimize f2, that is, to reduce the overall cost.

[0085]

[0086] The objective function f3 is used to improve the overall efficiency by optimizing the zoning of the construction site, where Ei represents the initial risk value of the i-th area; E i ' represents the risk value of the i-th region after optimization. The optimization goal is to maximize f3, that is, to improve the overall efficiency.

[0087] Therefore, the dynamic weight matrix can be optimized by a multi-objective function, which is determined as follows: total =w1f1+w2f2+w3f3.

[0088] Right now,

[0089] Among them, F tatol is a multi-objective function; R j represents the initial risk value of the jth region; R j ' represents the risk value of the jth region after optimization; w1 is the target weight coefficient of the risk target; C k represents the initial cost of the kth task or resource; C k ' represents the cost of the kth task or resource after optimization; w2 is the target weight coefficient of the cost target; E i represents the initial risk value of the jth region; E i ' represents the risk value of the i-th region after optimization; w3 is the target weight coefficient of the efficiency target. And w1+w2+w3=1.

[0090] F tatol It can be used for the final comprehensive evaluation to help verify and optimize the final selection. On the one hand, when multiple candidate sub-regions meet the target requirements of the previous layers at the same time, Ftatol On the other hand, it can be used to timely discover whether there are potential adjustment opportunities in each sub-area when the field conditions change.

[0091] The target weight coefficient w1 for the risk objective reflects the importance of risk reduction in the overall optimization problem. A larger weight value prioritizes risk optimization. The target weight coefficient w2 for the cost objective reflects the importance of cost optimization in the overall optimization problem. A larger weight value prioritizes cost reduction. The target weight coefficient w3 for the efficiency objective reflects the importance of efficiency improvement in the overall optimization problem. A larger weight value prioritizes efficiency improvement.

[0092] Furthermore, hierarchical optimization can be performed for the three goals: the first level first satisfies the maximum security guarantee, screens out candidate sub-areas that exceed the preset security standards, and enters the next level of optimization; the second level minimizes costs while meeting the security guarantee, and screens out sub-areas that meet both security requirements and have good cost-effectiveness; the third level maximizes efficiency while ensuring the first two goals, and determines the sub-area that can achieve the highest efficiency as the final optimization result.

[0093] It should be noted that this process can re-execute the hierarchical optimization process regularly or irregularly to adapt to new environments and needs, and then adjust the weight coefficients of risk, cost, and efficiency according to the actual situation of the project to select the optimal solution.

[0094] It is understandable that the above embodiment uses the three-dimensional objective functions of risk, cost, and efficiency to iterate through a multi-objective greedy algorithm, but the present application is not limited to this. For example, in a specific implementation, a traditional greedy algorithm can be used to dynamically optimize the safety risk area division matrix of each stage of the construction site to minimize the overall safety risk of the construction site; it can also be used to use the objective functions of risk and cost to iterate through a multi-objective greedy algorithm to take into account both risk objectives and cost objectives; it can also be used to use the objective functions of risk and efficiency to iterate through a multi-objective greedy algorithm to take into account both risk objectives and efficiency objectives.

[0095] In one embodiment, the above greedy algorithm is iterated to further optimize the partitioning effect. The specific iteration rules can be: in each iteration, based on the dynamic weight matrix and real-time data, the region boundaries or security levels are adjusted to gradually optimize overall security. For example, if the Ei of a sub-region increases, the security measures for that sub-region are increased, and the b-weight value of that region is increased.

[0096] In this specific example, the main process can be as follows: Access the dynamic weight matrix above one by one, use the multidimensional data evaluation model to calculate the probability of assigning the area to different safety levels (such as high risk, medium risk, and low risk), and comprehensively consider the overall safety goals of the entire construction site. Select a safety zoning scheme that not only optimizes the individual area but also achieves the best overall results. This process may involve comparing and screening multiple candidate options. Calculate the comprehensive evaluation value of all candidate options, and select the option with the highest comprehensive evaluation value as the next step.

[0097] Then, the selected optimal division scheme will be applied to the actual construction project, the safety measures and management strategies of each sub-area will be adjusted, the risk weights of each sub-area will be re-evaluated regularly to adapt to the dynamic changes in the construction site, and the next round of optimization will be carried out based on the new evaluation results.

[0098] Repeat the above process until the preset optimization goal is achieved. Collect feedback information during the actual operation process, continuously improve the algorithm and implementation strategy to enhance the overall security management effect.

[0099] Furthermore, the iteration can be terminated by limiting the number of iterations or judging the convergence.

[0100] In other words, there are two types of termination conditions for the iteration. One is to stop the calculation by limiting the number of iterations to Iter_max (e.g., 20). The other is to determine convergence. When the overall improvement is less than a preset threshold ε, that is, |Loss(t+1)-Loss(t)| < ε, the algorithm is considered to have converged and the calculation is stopped. In a specific example, ε can be 2%. After the calculation is terminated, the final safety zone division plan is output and the results are passed to the construction site management system for management personnel to adjust and optimize.

[0101] In one embodiment, the security zone boundary map can be updated and displayed in real time based on the optimized dynamic weight matrix. Specifically, a new security zone boundary map is generated in real time and displayed to relevant personnel via a management platform or mobile terminal. Simultaneously, the system can automatically adjust monitoring strategies and resource allocation plans based on the new division results, ensuring continuous optimization of security management.

[0102] The following is a specific example to further explain and illustrate the security area division method provided by this application.

[0103] Figure 2 FIG. 1 is an overall flow chart of the security area division method of this specific embodiment. Figure 2 As shown, the steps of the overall process include:

[0104] Step 201, start.

[0105] Step 202: real-time data collection and processing.

[0106] Step 203: Determine the dynamic risk value.

[0107] Step 204: Dynamically update the weight parameters.

[0108] Step 205: Multi-objective hierarchical greedy algorithm.

[0109] Step 206: solution screening and iteration.

[0110] Step 207, end.

[0111] Figure 3 FIG. 1 is a flow chart showing the specific implementation of the security area division method of this specific embodiment. Figure 3 As shown, the steps of the specific implementation process include:

[0112] Step 301: collect and integrate real-time data, and then execute step 302.

[0113] Step 302: Data preprocessing, and then executing step 303.

[0114] Step 303: Data warehouse ETL processing, and then execute steps 304 and 305.

[0115] Step 304: output corresponding historical data.

[0116] Step 305 , determining the latest detected dynamic data, and executing step 306 .

[0117] Step 306 , extract and quantitatively analyze risk factors, and then execute step 307 .

[0118] Step 307: Build a risk assessment indicator system and execute step 308.

[0119] Step 308 , based on the risk assessment indicator system, expert assessment data and historical data, factor weight coefficients are allocated, and step 309 is executed.

[0120] Step 309: Build a multi-dimensional risk assessment model, and then execute steps 310 and 311.

[0121] The model integrates multi-dimensional data and weights to calculate the dynamic risk values ​​of all sub-areas and update them according to conditions.

[0122] Step 310 , generate a multi-dimensional risk dynamic weight matrix, and execute step 312 .

[0123] Among them, the multi-dimensional risk dynamic weight matrix is ​​used to generate a multi-safety area division scheme.

[0124] Step 311 , extracting the latest dynamic data according to the conditions, for executing step 306 .

[0125] Specific conditions may include: scheduled updates, updates combined with real-time data analysis, and trigger condition updates.

[0126] Step 312: Establish a multi-objective function and execute steps 313 and 314.

[0127] Specifically, a multi-objective function is established regarding safety goals, cost goals, and efficiency goals, and the multi-objective function value is calculated for the final comprehensive evaluation.

[0128] Step 313: Execute the multi-objective improved greedy strategy.

[0129] Specifically, the three objectives of safety, cost, and efficiency are screened in layers and optimized iteratively.

[0130] In step 314 , the evaluation results are visualized, and step 315 is executed.

[0131] Step 315: Feedback and dynamic adjustment.

[0132] In summary, the safety zone demarcation method provided in the embodiments of this application obtains real-time risk-related data and corresponding historical data for each sub-area; determines the dynamic risk value of each sub-area based on the real-time and historical data, establishes a multidimensional risk assessment model; generates a dynamic weight matrix based on the dynamic risk values ​​of multiple sub-areas; and dynamically optimizes the dynamic weight matrix using a greedy algorithm. This allows the system to adapt to rapid changes in construction progress, effectively improving management efficiency and response speed.

[0133] Moreover, by comprehensively considering the influence of multi-dimensional factors, the partitioning scheme is ensured to be more scientific and reasonable; and through the improved greedy algorithm of multi-objective optimization, the relationship between safety, economy and operational efficiency can be effectively balanced, achieving the comprehensive optimization goal.

[0134] Figure 4 FIG is a structural block diagram of a security area division system according to an embodiment of the present application. Figure 4 As shown, the security area division system 400 includes: a data acquisition module 401, a multi-dimensional risk assessment model module 402, a dynamic weight matrix module 403 and a dynamic optimization module 404.

[0135] The data acquisition module 401 is used to acquire the real-time data and corresponding historical data related to the risk of each sub-region. Figure 5As shown, the data acquisition module 401 may include a data acquisition unit 4011 for collecting real-time data related to personnel, equipment, and environment, and a data preprocessing unit 4012 for performing data cleaning, data standardization, and data verification.

[0136] The multi-dimensional risk assessment model module 402 is used to determine the dynamic risk value of each sub-region based on the real-time data and historical data of each sub-region and establish a multi-dimensional risk assessment model.

[0137] The dynamic weight matrix module 403 is used to generate a dynamic weight matrix based on the dynamic risk values ​​of multiple sub-regions.

[0138] The dynamic optimization module 404 is used to dynamically optimize the dynamic weight matrix through a greedy algorithm.

[0139] In one embodiment, the data acquisition module 401 is specifically used to: collect raw data related to risks in each sub-region in real time; and pre-process the raw data; wherein the pre-processing includes cleaning and standardizing the raw data.

[0140] In one embodiment, the data acquisition module 401 is further specifically used to collect at least one of personnel location information, equipment status information, environmental parameter information, construction progress information, and equipment operation parameter information of each sub-area in real time.

[0141] In one embodiment, the multidimensional risk assessment model module 402 is specifically used to: determine at least two risk factor parameter values ​​based on real-time data; determine at least two factor weight coefficients corresponding to the at least two risk factor parameter values ​​based on historical data; determine the sum of the products of the at least two risk factor parameter values ​​and the corresponding factor weight coefficients as the dynamic risk value of each sub-area; and minimize the sum of the dynamic risk values ​​of multiple sub-areas.

[0142] In one embodiment, the dynamic weight matrix module 403 is further configured to: determine the security level of each sub-area; and determine the update frequency of the dynamic weight matrix when operating in the corresponding sub-area according to the security level.

[0143] In one embodiment, the dynamic weight matrix module 403 is further configured to trigger an update of the dynamic weight matrix in response to receiving accident information or receiving construction status change information.

[0144] In one embodiment, the dynamic optimization module 404 is specifically configured to optimize the dynamic weight matrix using a multi-objective function. The multi-objective function is determined in the following manner:

[0145]

[0146] Among them, F tatolis a multi-objective function; R j represents the initial risk value of the jth region; R j ' represents the risk value of the jth region after optimization; w1 is the target weight coefficient of the risk target; C k represents the initial cost of the kth task or resource; C k ' represents the cost of the kth task or resource after optimization; w2 is the target weight coefficient of the cost target; E i represents the initial risk value of the jth region; E i ' represents the risk value of the i-th region after optimization; w3 is the target weight coefficient of the efficiency target.

[0147] In one embodiment, the dynamic optimization module 404 is further configured to: periodically iterate the multi-objective function; and terminate the iteration based on a limit on the number of iterations or a convergence judgment.

[0148] In one embodiment, the safety area division system 400 further includes a visualization feedback module 405. The visualization feedback module 405 is configured to update the safety area boundary map in real time based on the optimized dynamic weight matrix and display the map.

[0149] The above description is only a description of the preferred embodiments of the present invention and does not limit the scope of the present invention. Any changes and modifications made by ordinary technicians in the field of the present invention based on the above disclosure shall fall within the scope of protection of the claims.

Claims

1. A method for dividing a security area, characterized in that: The security area includes multiple sub-areas; and the method includes: Obtain real-time risk-related data and corresponding historical data for each sub-region; Determine the dynamic risk value of the corresponding sub-region based on the real-time data and the historical data of each sub-region, and establish a multi-dimensional risk assessment model; generating a dynamic weight matrix based on the dynamic risk values ​​of the plurality of sub-regions; The dynamic weight matrix is ​​dynamically optimized by a greedy algorithm.

2. The method for dividing a security area according to claim 1, wherein: The step of obtaining real-time data related to risks in each sub-area includes: Collect raw data related to risks in each sub-area in real time; Preprocessing the raw data; wherein the preprocessing includes cleaning and standardizing the raw data.

3. The method for dividing a security area according to claim 2, wherein: The step of collecting raw data related to risks in each sub-area in real time includes: At least one of the following information is collected in real time: personnel location information, equipment status information, environmental parameter information, construction progress information, and equipment operation parameter information of each sub-area.

4. The method for dividing a security area according to claim 1, wherein: The step of determining the dynamic risk value of the corresponding sub-region based on the real-time data and the historical data of each sub-region and establishing a multi-dimensional risk assessment model includes: determining at least two risk factor parameter values ​​based on the real-time data; Determining at least two factor weight coefficients corresponding one-to-one to the at least two risk factor parameter values ​​based on the historical data; Determine the sum of the products of the at least two risk factor parameter values ​​and the corresponding factor weight coefficients as the dynamic risk value of each sub-region; Minimize the sum of the dynamic risk values ​​of the multiple sub-areas.

5. The method for dividing a security area according to claim 1, wherein: The method further comprises: Determine the security level of each sub-area; and determine the update frequency of the dynamic weight matrix when operating in the corresponding sub-area based on the security level.

6. The method for dividing a security area according to claim 1, wherein: The method further comprises: In response to receiving accident occurrence information, or in response to receiving construction status change information, the dynamic weight matrix update is triggered.

7. The method for dividing a security area according to claim 1, wherein: The step of dynamically optimizing the dynamic weight matrix by a greedy algorithm comprises: The dynamic weight matrix is ​​optimized by a multi-objective function; the multi-objective function is determined according to the following method: Among them, F tatol is a multi-objective function; R j represents the initial risk value of the jth region; R j ' represents the risk value of the jth region after optimization; w1 is the target weight coefficient of the risk target; C k represents the initial cost of the kth task or resource; C k ' represents the cost of the kth task or resource after optimization; w2 is the target weight coefficient of the cost target; E i represents the initial risk value of the jth region; E i ' represents the risk value of the i-th region after optimization; w3 is the target weight coefficient of the efficiency target.

8. The method for dividing a security area according to claim 7, wherein: The method further comprises: regularly iterating the multi-objective function; and terminating the iteration by limiting the number of iterations or judging the convergence.

9. The method for dividing a security area according to claim 1, wherein: The method further includes: updating the safety area boundary map in real time based on the optimized dynamic weight matrix and displaying the map.

10. A security area division system, characterized in that: The security area includes multiple sub-areas; and the system includes: Data acquisition module, used to obtain real-time risk-related data and corresponding historical data for each sub-area; A multidimensional risk assessment model module, which determines the dynamic risk value of each sub-region based on the real-time data and the historical data, and establishes a multidimensional risk assessment model; A dynamic weight matrix module generates a dynamic weight matrix based on the dynamic risk values ​​of the multiple sub-regions; The dynamic optimization module is used to dynamically optimize the dynamic weight matrix through a greedy algorithm.

Images