Urban rainstorm waterlogging emergency department site selection optimization method, medium and terminal

Abstract

The invention is suitable for the technical field of urban disaster prevention, and relates to an urban rainstorm waterlogging emergency department site selection optimization method, a medium and a terminal, and the method comprises the steps: S10, determining a target function and a corresponding constraint condition, and constructing an emergency response capability optimization model; s20, the rescue speed of the emergency department in the rainstorm waterlogging scene is calculated, the emergency department selects a plurality of candidate addressing sites on the basis of the original addressing site, and the original addressing site and the newly added candidate addressing sites are combined into alternative emergency departments; s30, drawing a first-round iterative site selection distribution diagram of the emergency department; and S40, removing consistent alternative emergency departments and key facility points served by the alternative emergency departments in the output result of the first round of iteration in the step S30, and substituting the remaining alternative emergency departments and key facility points into the algorithm again for iteration until the site selection result output by each emergency department is consistent. The method is simple in process and convenient to operate, and the emergency resource utilization rate and the emergency department site selection accuracy are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban disaster prevention, and particularly relates to an optimization method, medium and terminal for the location selection of urban rainstorm waterlogging emergency departments. Background Technique

[0002] Urban rainstorm waterlogging disasters are characterized by suddenness, frequency, danger, etc. Moreover, with global warming, urban extreme rainfall events show an increasing trend. For densely populated cities, the direct and indirect losses caused by urban waterlogging disasters are becoming more and more serious. It is imperative to effectively respond to the increasingly serious urban waterlogging disasters. By optimizing the location selection of emergency departments and enhancing the emergency response ability, it can ensure the full utilization of emergency response resources, enabling emergencies to be responded to more quickly and efficiently. In addition, the cooperation between different departments is smoother, improving the overall response efficiency, minimizing losses to the greatest extent, and providing strong support for the sustainable development of the city, building a safer, more resilient and vibrant urban environment. At present, in the research on the optimization of emergency response ability, there are mainly the following two limitations: there is still an uneven distribution of emergency resources in the emergency service system, and emergency resources cannot be reasonably utilized, resulting in insufficient coverage and low utilization efficiency of emergency service centers, and low accuracy in the location selection of emergency departments; there is a lack of key analysis of key facility points in the central urban area.

[0003] The patent with the publication number CN106373070B provides a four-prevention method for dealing with urban rainstorm waterlogging. Step 1: Use statistical downscaling to process different Global Climate Model (GCM) data in the area where the city is located for urban rainstorm waterlogging prediction to obtain the predicted daily rainfall; determine whether extreme precipitation occurs based on the predicted daily rainfall: if extreme precipitation occurs, proceed to Step 2 for urban rainstorm waterlogging prediction, otherwise, continue with urban rainstorm waterlogging prediction; Step 2: Based on the predicted daily rainfall obtained in Step 1, further predict whether the city will experience rainstorm waterlogging: if it is predicted that rainstorm waterlogging will occur, proceed to Step 3 for urban rainstorm waterlogging warning; otherwise, return to Step 1 to continue with urban rainstorm waterlogging prediction; Step 3: Process according to the prediction result in Step 2: Integrate and fuse the urban rainstorm waterlogging data resources through fusion, and use the established "entity-relationship" deduction model to deduce the rainstorm waterlogging information in key urban areas, including areas along urban river channels, low-lying areas, key industrial parks, and flood-prone points, to obtain urban rainstorm waterlogging warning information, and then enter Step 4 for further processing of the urban rainstorm waterlogging plan; otherwise, return to Step 2 to continue with urban rainstorm waterlogging prediction; Step 4: Judge according to the urban rainstorm waterlogging warning information obtained in Step 3: If the urban rainstorm waterlogging warning information reaches the level that requires response, digitize the traditional paper and graphic plans, establish a scenario plan, and conduct qualitative and quantitative analysis of the scenario plan based on a visualization platform to finally form an urban rainstorm waterlogging response plan; otherwise, return to Step 3 to continue with rainstorm waterlogging warning. In this patent, only the prediction of urban rainstorm waterlogging and the generation of the plan are realized, and no relevant technical solutions are given on how the emergency department selects the location.

[0004] Therefore, how to optimize the method for selecting the location of the urban rainstorm waterlogging emergency department to improve the accuracy of the emergency department's location selection and the resource utilization efficiency is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the purpose of the present invention is to provide an optimization method for selecting the location of the urban rainstorm waterlogging emergency department to solve the problems in the prior art that emergency resources cannot be reasonably utilized, resulting in low utilization efficiency and low accuracy of the emergency department's location selection; in addition, the present invention also provides an optimization medium and a terminal for selecting the location of the urban rainstorm waterlogging emergency department.

[0006] To solve the above technical problems, the present invention adopts the following technical solutions:

[0007] In the first aspect, the present invention provides an optimization method for selecting the location of the urban rainstorm waterlogging emergency department, including the following steps:

[0008] S10. Take the shortest distance between the emergency department and the critical facility points and the largest number of critical facility points covered within the rescue time threshold of the emergency department as the objective function, determine the corresponding constraints, and construct an emergency response capacity optimization model;

[0009] S20. Calculate the rescue vehicle speed of the emergency department in the rainstorm and waterlogging scenario. On the basis of the original site selection of the emergency department, select several alternative sites, and combine the original site and the newly added alternative sites into alternative emergency departments;

[0010] S30. Based on the tabu search algorithm, use Python software to solve the model, select the emergency departments with the number of original sites among the alternative emergency departments, and draw the first-round iterative site selection distribution map of the emergency departments;

[0011] S40. Remove the alternative emergency departments and the critical facility points served by them that are consistent in the output results of the first-round iteration in step S30, and substitute the remaining alternative emergency departments and critical facility points into the algorithm for iteration again until the site selection results of the emergency departments are consistent each time.

[0012] Further, the specific steps of step S10 are as follows:

[0013] S101. When constructing the emergency response capacity optimization model, preset the following conditions:

[0014] Regard the emergency department as the emergency response resource supplier; regard the critical facility points as the emergency response resource demanders, and use the corresponding population estimation value in the critical facility points as the demand of the demanders; the service quality provided by the emergency departments is the same, and there are no differences in hardware facilities and equipment; one critical facility point is only served by one emergency department; the coordinate information of the emergency department and the critical facility points represents their spatial positions;

[0015] S102. Set the symbolic meanings in the emergency response capacity optimization model as follows:

[0016] ReqPt=(1, 2, 3......, m) is the set of critical facility points i, i∈R; FacPt=(1, 2, 3......, n) is the set of alternative emergency departments j, j∈F; w i is the emergency service demand of critical facility point i, represented by the population estimation value in critical facility point i; d ij is the distance between critical facility point i and the nearest alternative emergency department j; s is the maximum distance between the emergency department and critical facility point i within its supply range; A i is the set of alternative emergency departments whose distance from critical facility point i is less than s; P is the actual number of established emergency departments; v ijLet \(v\) be a variable for assignment, indicating whether the critical facility point \(i\) receives emergency services from the alternative emergency department \(j\). If it does, \(v_{ij}=1\); otherwise, \(v_{ij}=0\). ij Let ij \(c_j\) j be a site - selection variable, indicating whether to establish an emergency department at the alternative emergency department \(j\). If it is established, \(c_j = 1\); otherwise, \(c_j = 0\). \(C\) is the service capacity of the alternative emergency department, represented by the maximum number of people that the emergency department can serve. j Let j \(C\)

[0017] S103. Based on the above - mentioned steps S101 and S102, set the objective function of the emergency response capacity optimization model as follows:

[0018]

[0019] S104. Based on the above - mentioned step S103, set the constraint conditions of the emergency response capacity optimization model as follows:

[0020]

[0021] \(v_{ij}\) ij \(\leq c_j\), \(i\in R\), \(j\in A\) j ; i ;

[0022] \(v_{ij}\), \(c_j\) ij \(\in\{0,1\}\), \(i\in R\), \(j\in A\) j ; i ;

[0023] \(d_{ij}\) ij \(\leq s\);

[0024]

[0025] Furthermore, the specific steps of the above - mentioned step S20 are as follows:

[0026] S201. Based on the hyperbolic - tangent function attenuation model formula, calculate the influence of different waterlogging depths on the driving speed, and take the average vehicle speed of different types of roads in the rainstorm and waterlogging scenario as the rescue vehicle speed of the emergency department.

[0027] S202. The emergency department selects ten alternative sites on the basis of the original site. The original site and the alternative sites are collectively referred to as alternative emergency departments and are used as the input of the emergency response capacity optimization model.

[0028] Furthermore, the specific steps of the above - mentioned step S30 are as follows:

[0029] S301. Initialization: Set the tabu length to 100, the number of iterations to 100, clear the tabu list, import the set of alternative emergency departments and the set of key facility points into the tabu search algorithm. Set the service range of the emergency department as a circle with the emergency department as the center and the product of the rescue vehicle speed and the rescue time threshold as the radius. Calculate the distance between the alternative emergency departments and the key facility points using the Euclidean distance to generate the initial solution;

[0030] S302. Neighborhood search to generate candidate solutions: Through neighborhood random traversal search, store the solutions generated by local search, which also serves as a local tabu list, store the path distances corresponding to the local solutions, copy the current path, and exchange to generate a new path. If the newly generated path is not in the global tabu list and the local tabu list, it is a valid search; otherwise, continue the search. When detecting, check if it meets the service radius constraint. If not, there is no need to check, so that the alternative emergency departments cover the largest area with the shortest distance, and calculate the path distance corresponding to the candidate solution;

[0031] S303. Select the optimal candidate solution: Compare the solution with the smallest path distance among the candidate solutions with the current best solution. If it is better than the best solution, update the current best solution and update the tabu list; if it is not better than the current best solution, select the solution with the smallest path distance that is not tabu among the candidate solutions as the new current solution, and then add the corresponding solution to the tabu list;

[0032] S304. Determine the termination condition: If the specified number of iterations is reached, stop and output the current best solution, and draw the distribution map of the first-round iterative site selection of the emergency department. Otherwise, go back to step S302 to continue the search.

[0033] Furthermore, the specific steps of step S40 are as follows:

[0034] S401. Analyze the distribution map of the first-round iterative site selection of the emergency department, and determine the site selections of the alternative emergency departments that are consistent and inconsistent in several output results of the first-round iteration;

[0035] S402. In the second-round iteration, remove the alternative emergency departments that are consistent in multiple output results and the key facility points they can serve. Substitute the remaining alternative emergency departments and key facility points into the algorithm for iteration again, and draw the distribution map of the second-round iterative site selection of the emergency department;

[0036] S403. Analyze the distribution map of the second-round iterative site selection of the emergency department. If the several output results of the second-round iteration are all consistent, stop the iteration and determine the final site selection; if there are still inconsistent site selection situations, continue the third-round iteration until each output result is consistent.

[0037] Furthermore, the average vehicle speed in step S201 is expressed as:

[0038]

[0039] Among them, V1 is the vehicle speed on sunny days, which is exported from the traffic travel big data platform, V2 is the vehicle speed on rainy days, w is the water depth of the road section, a is the median value of the water depth at which vehicles are prohibited from passing, and b is the precipitation attenuation coefficient, taking 3.5.

[0040] Furthermore, in the step S202, the selection principle is that there is less water accumulation near the selected site, the road network facilities are perfect, and the emergency demand near the selected site is large.

[0041] Furthermore, in the step S301, the time threshold is 10 minutes.

[0042] In a second aspect, the present invention also provides a computer-readable storage medium, where the storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0043] In a third aspect, the present invention also provides an electronic terminal, including: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the terminal executes the method described above.

[0044] Compared with the prior art, the method, medium and terminal for optimizing the location selection of urban rainstorm and waterlogging emergency departments provided by the present invention have at least the following beneficial effects:

[0045] In the prior art, emergency resources cannot be reasonably utilized, resulting in insufficient coverage rate of emergency service centers and low utilization efficiency, and low accuracy of the location selection of emergency departments; there is a lack of key analysis of key facility points in the central urban area. The process of the present invention is simple and easy to operate. Based on the scenario of rainstorm and waterlogging, taking the people in key facility points as the emergency demand side, an emergency response capacity optimization model is constructed, and the tabu search algorithm is used to solve the model. On the premise that the total number of emergency departments remains unchanged, the layout of emergency departments is reorganized, thereby improving the emergency response capacity, effectively improving the utilization efficiency of emergency resources, and also greatly improving the accuracy of the location selection of emergency departments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the solution of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is a flowchart of a method for optimizing the location selection of urban rainstorm and waterlogging emergency departments provided by an embodiment of the present invention;

[0048] Figure 2Schematic diagram of the location selection of the emergency department and key facility points in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0049] Figure 3 Schematic diagram of the alternative location selection of the medical emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0050] Figure 4 Schematic diagram of the alternative location selection of the police emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0051] Figure 5 Schematic diagram of the alternative location selection of the fire emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0052] Figure 6 Schematic diagram of the first-round iterative location selection distribution of the medical emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0053] Figure 7 Schematic diagram of the first-round iterative location selection distribution of the police emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0054] Figure 8 Schematic diagram of the first-round iterative location selection distribution of the fire emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0055] Figure 9 Schematic diagram of the first-round iterative uncertain location selection distribution of the medical emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0056] Figure 10 Schematic diagram of the first-round iterative uncertain location selection distribution of the police emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0057] Figure 11 Schematic diagram of the first-round iterative uncertain location selection distribution of the fire emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0058] Figure 12 Schematic diagram of the first and second-round iterative location selection distribution of the medical emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0059] Figure 13 Schematic diagram of the first and second-round iterative location selection distribution of the police emergency department in a certain city in the urban rainstorm and waterlogging emergency department location selection method provided by the embodiment of the present invention;

[0060] Figure 14 Schematic diagram of the first and second round iterative site selections of a certain city's fire emergency department in a method for selecting sites for urban rainstorm waterlogging emergency departments provided by an embodiment of the present invention;

[0061] Figure 15 Schematic diagram of the optimized final site selection of a certain city's medical emergency department in a method for selecting sites for urban rainstorm waterlogging emergency departments provided by an embodiment of the present invention;

[0062] Figure 16 Schematic diagram of the optimized final site selection of a certain city's police emergency department in a method for selecting sites for urban rainstorm waterlogging emergency departments provided by an embodiment of the present invention;

[0063] Figure 17 Schematic diagram of the optimized final site selection of a certain city's fire emergency department in a method for selecting sites for urban rainstorm waterlogging emergency departments provided by an embodiment of the present invention. Detailed implementation manners

[0064] For ease of understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Preferred embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided so that the understanding of the disclosure of the present invention is more thorough and comprehensive.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0066] The present invention provides a method for optimizing the site selection of urban rainstorm waterlogging emergency departments, which is applied to the optimization process of the layout of emergency departments in the scenario of urban rainstorm waterlogging. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments includes the following steps:

[0067] S10. Taking the shortest distance between the emergency department and the key facility points and the largest number of key facility points covered within the rescue time threshold (10 minutes) of the emergency department as the objective function, determining the corresponding constraint conditions, and constructing an emergency response capacity optimization model; S20. Calculating the rescue vehicle speed of the emergency department in the rainstorm and waterlogging scenario, selecting several alternative locations on the basis of the original location of the emergency department, and combining the original location with the newly added alternative locations into alternative emergency departments; S30. Based on the tabu search algorithm, using Python software to solve the model, selecting the same number of emergency departments as the original location from the alternative emergency departments, and drawing the first-round iterative location distribution map of the emergency department; S40. Removing the alternative emergency departments and the key facility points served by them that are consistent in the output results of the first-round iteration in step S30, and substituting the remaining alternative emergency departments and key facility points into the algorithm for iteration again until the location selection results of the emergency department are consistent each time.

[0068] The process of the present invention is simple and convenient to operate, improving the utilization rate of emergency resources and the accuracy of the location selection of the emergency department.

[0069] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0070] The present invention provides an optimization method for the location selection of the emergency department in urban rainstorm and waterlogging, which is applied to the optimization process of the layout of the emergency department in the urban rainstorm and waterlogging scenario, and combines Figures 1 to 17 In this embodiment, the optimization method for the location selection of the emergency department in a certain city in the urban rainstorm and waterlogging includes the following steps:

[0071] S10. Taking the shortest distance between the emergency department and the key facility points and the largest number of key facility points covered within the rescue time threshold (10 minutes) of the emergency department as the objective function, determining the corresponding constraint conditions, and constructing an emergency response capacity optimization model for a certain city.

[0072] Specifically, in this embodiment, the specific steps of step S10 are as follows:

[0073] S101. Make the following assumptions about the constructed emergency response capacity optimization model: ① Regarding 17 medical institutions, 21 police stations, and 8 fire departments in a certain city as the suppliers of emergency response resources, as Figure 2 shown; ② Regarding 33 key facility points in a certain city as the demanders of emergency response resources, as Figure 2 shown, and using the corresponding population estimation value in the key facility point as the demand of the demander; ③ The service quality provided by the emergency department is the same, and there are no differences in hardware facilities and equipment; ④ One key facility point is only served by one emergency department; ⑤ The coordinate information of the emergency department and the key facility point represents their spatial positions.

[0074] S102. Set the symbolic meanings of the emergency response capacity optimization model as follows:

[0075] ReqPt = (1, 2, 3......, m) is the set of critical facility points i, where i ∈ R; FacPt = (1, 2, 3......, n) is the set of alternative emergency departments j, where j ∈ F; w i is the emergency service demand of critical facility point i, represented by the estimated population value within critical facility point i; d ij is the distance between critical facility point i and the nearest alternative emergency department j; s is the maximum distance between an emergency department and the critical facility points i within its supply range; A i is the set of alternative emergency departments whose distance from critical facility point i is less than s; P is the actual number of established emergency departments (where P is equal to the original site selection number and P ≤ n); v ij is an allocation variable, indicating whether critical facility point i receives the emergency service of alternative emergency department j. If it does, v ij = 1, otherwise v ij = 0; c j is a site selection variable, indicating whether to establish an emergency department at alternative emergency department j. If it is established, c j = 1, otherwise c j = 0; C is the service capacity of the alternative emergency department, represented by the maximum number of people that the emergency department can serve.

[0076] S103. Based on the model assumptions and symbolic meanings, set the objective function of the emergency response capacity optimization model as follows:

[0077]

[0078] Among them, F1 ensures that the total distance between the emergency departments and critical facility points in a certain city is the smallest; F2 ensures that the number of people within the critical facility points covered by the emergency departments in a certain city within the rescue time threshold (10 min) is the largest (for symbolic meanings, see step S102).

[0079] S104. Based on the constructed objective function, set the constraint conditions of the emergency response capacity optimization model as follows:

[0080]

[0081] V ij ≤ c j , i ∈ R, j ∈ A i ;

[0082] V ij , c j ∈ {0, 1}, i ∈ R, j ∈ A i ;

[0083] d ij ≤ s;

[0084]

[0085] wherein, ensure that each critical facility point can only be provided with emergency services by one emergency department; stipulate that the total number of selected emergency departments is the original site selection quantity p; V ij ≤ c j , i ∈ R, j ∈ A i means that the emergency services of critical facility points can only be provided by the points selected as emergency departments; represents V ij and c j are both 0-1 variables; d ij ≤ s ensures that the critical facility points are within the range that can be covered by the rescue time threshold of the emergency department; limits the number of people served by the emergency department to be less than or equal to its service capacity (for the symbol meanings, see step S102).

[0086] S20. Calculate the rescue vehicle speed of the emergency department in a certain city under the scenario of rainstorm and waterlogging. On the basis of the original site selection, ten alternative site selections are selected, and the original site selection and the newly added alternative site selections are combined into alternative emergency departments.

[0087] Specifically, in this embodiment, the specific steps of step S20 are as follows:

[0088] S201. Select the design rainfall scenario with a return period of 20 years in a certain city as an example for optimization. Based on the hyperbolic tangent function attenuation model formula, calculate that the average vehicle speed of different types of roads under the design rainfall scenario with a return period of 20 years in a certain city is 10 km / h, and set this vehicle speed as the rescue speed of the emergency vehicle. The formula is as follows:

[0089]

[0090] wherein, V1 is the vehicle speed on sunny days, which is exported from the Baidu Map traffic travel big data platform; V2 is the vehicle speed on rainy days, w is the water depth of the road section, a is the median value of the water depth at which vehicles are prohibited from passing; b is the rainfall attenuation coefficient, taking 3.5.

[0091] S202. In a certain city, the medical, police, and fire departments respectively select 10 alternative site selections on the basis of 17, 21, and 8 original site selections, as Figure 3 , Figure 4 , Figure 5 shown. The selection principles are: ① less water accumulation near the site selection; ② perfect road network facilities for easy travel; ③ large emergency demand near the site selection. The original site selections and alternative site selections in a certain city are collectively referred to as alternative emergency departments and used as the input side of the emergency response capacity optimization model.

[0092] S30. Based on the tabu search algorithm, use Python software to solve the model, select the emergency departments with the original number of selected sites from the alternative emergency departments, and draw the distribution map of the first-round iterative site selection of the emergency departments in a certain city.

[0093] Specifically, in this embodiment, the specific steps of step S30 are as follows:

[0094] S301. Initialization. Set the tabu length to 100, the number of iterations to 100, and clear the tabu list. Import the set of alternative emergency departments (FacPt set) and the set of key facility points (ReqPt set) into the tabu search algorithm. Set the service range of the emergency departments in a certain city as a circle with the emergency department as the center and the product of the rescue vehicle speed (10 km / h) and the rescue time threshold (10 min) as the radius. Use the Euclidean distance to calculate the distance between the alternative emergency departments and the key facility points, and generate the initial solution.

[0095] S302. Neighborhood search to generate candidate solutions. Through neighborhood random traversal search, store the solutions generated by local search, which also serves as a local tabu list, store the path distances corresponding to the local solutions, copy the current path, and exchange to generate a new path. If the newly generated path is not in the global tabu list and the local tabu list, it is an effective search, otherwise continue the search. Detect whether the service radius constraint is met. If not, there is no need to detect, so that the alternative emergency departments have the shortest distance under the condition of covering the largest area. Calculate the path distance corresponding to the candidate solution.

[0096] S303. Select the best candidate solution. Compare the solution with the smallest path distance in the candidate solutions with the current best solution. If it is better than the best solution, update the current best solution and update the tabu list. If it is not better than the current best solution, select the solution with the smallest path distance that is not tabu in the candidate solutions as the new current solution, and then add the corresponding solution to the tabu list.

[0097] S304. Judge the termination condition. If the specified number of iterations is reached, stop immediately and output the current best solution, and draw the distribution map of the first-round iterative site selection of the emergency departments in a certain city, as Figure 6 、 Figure 7 、 Figure 8 shown; otherwise, return to step S302 to continue the search.

[0098] S40. Remove the alternative emergency departments and the key facility points they serve that are the same in the output results of the first-round iteration in step S30, and substitute the remaining alternative emergency departments and key facility points into the algorithm for iteration until the site selection results of the emergency departments are the same each time.

[0099] Specifically, in this embodiment, the specific steps of step S40 are as follows:

[0100] S401. Analyze the first-round iterative site selection distribution map of the emergency department in a certain city. For medical, police, and fire departments, 11, 14, and 5 site selections are determined (outside the boxes), and 6, 7, and 3 site selections are undetermined (inside the boxes), as Figure 9 , Figure 10 , Figure 11 shown.

[0101] S402. In the second-round iteration, the medical, police, and fire departments respectively remove the 11, 14, and 5 alternative emergency departments and the key facility points they can serve that are consistent in the first-round output results. Then, the remaining 6, 7, and 3 alternative emergency departments and key facility points are substituted into the algorithm for iteration again, and a second-round iterative site selection distribution map of the emergency department in the city is drawn, as Figure 12 , Figure 13 , Figure 14 shown.

[0102] S403. Analyze the second-round iterative site selection distribution map of the emergency department in a certain city. The several output results of the second-round iteration of the medical, police, and fire departments are all consistent. Therefore, in the second-round iteration, the medical, police, and fire departments determine the 6, 7, and 3 site selections that were undetermined in the first-round iteration. The finally optimized site selections of the medical, police, and fire departments are as Figure 15 , Figure 16 , Figure 17 shown. Thus, the site selection optimization of the emergency department in the scenario of urban rainstorm and waterlogging is completed.

[0103] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements any one of the methods in this embodiment.

[0104] The embodiment of the present invention also provides an electronic terminal, including: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the terminal executes any one of the methods in this embodiment.

[0105] For the computer-readable storage medium in this embodiment, those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to the computer program. The foregoing computer program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disk, or optical disc that can store program codes.

[0106] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver, and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used for communication, and the processor and the transceiver are used to run the computer programs so that the electronic terminal executes each step of the above method.

[0107] Compared with the prior art, for the method, medium, and terminal for optimizing the location selection of urban rainstorm and waterlogging emergency departments described in the above embodiments, in the prior art, emergency resources cannot be reasonably utilized, resulting in insufficient coverage rate and low utilization efficiency of emergency service centers, and low accuracy of the location selection of emergency departments; there is a lack of key analysis of key facility points in the urban central area. The process of the present invention is simple and convenient to operate. Based on the scenario of rainstorm and waterlogging, with the people in key facility points as the emergency demand side, an optimization model for emergency response capabilities is constructed, and the taboo search algorithm is used to solve the model. On the premise that the total number of emergency departments remains unchanged, the layout of emergency departments is reorganized, thereby improving the emergency response capabilities, effectively improving the utilization efficiency of emergency resources, and greatly improving the accuracy of the location selection of emergency departments.

[0108] Obviously, the embodiments described above are only the preferred embodiments of the present invention, rather than all the embodiments. The preferred embodiments of the present invention are given in the drawings, but they do not limit the patent scope of the present invention. The present invention can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present invention more thorough and comprehensive. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements for some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present invention in other related technical fields shall be similarly within the scope of the patent protection of the present invention.

Claims

1. A method for optimizing the site selection of urban rainstorm waterlogging emergency departments, characterized in that: The following steps are involved: S10. Taking the shortest distance between the emergency department and key facilities and the maximum number of people covering the key facilities within the emergency department rescue time threshold as the objective function, determine the corresponding constraints and build an emergency response capability optimization model; S20. Calculate the rescue vehicle speed of the emergency department in the case of heavy rain and waterlogging. The emergency department selects several alternative sites based on the original site, and merges the original site and the newly added alternative site into an alternative emergency department; S30, based on the taboo search algorithm, using Python software to solve the model, selecting the emergency departments with the original number of sites from the candidate emergency departments, and drawing a first-round iterative site selection distribution map of the emergency departments; S40, removing the candidate emergency departments and the key facilities they serve that are consistent in the first round of iteration output results in step S30, and substituting the remaining candidate emergency departments and key facilities into the algorithm iteration again until the site selection results output by each emergency department are consistent.

2. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments according to claim 1, characterized in that: The specific steps of step S10 are as follows: S101. When constructing the emergency response capability optimization model, the following conditions are preset: The emergency department is regarded as the supplier of emergency response resources; the key facility points are regarded as the demanders of emergency response resources, and the corresponding population estimation value in the key facility points is used as the demand demand of the demand side; the service quality provided by the emergency departments is the same, and there is no difference in hardware facilities and equipment; a key facility point is only served by one emergency department; the coordinate information of the emergency department and the key facility points represents their spatial location; S102. The meanings of the symbols in the emergency response capability optimization model are set as follows: ReqPt=(1, 2, 3..., m) is the set of key facility points i, i∈R; FacPt=(1, 2, 3..., n) is the set of candidate emergency departments j, j∈F; w i is the emergency service demand at key facility point i, expressed by the estimated population value at key facility point i; d ij is the distance between key facility point i and the nearest alternative emergency department j; s is the maximum distance between the emergency department and the key facility point i within its supply range; A i is the set of alternative emergency departments whose distance to key facility point i is less than s; P is the number of emergency departments actually established; v ij is an allocation variable, indicating whether key facility i accepts emergency services from alternative emergency department j. If so, v ij =1, otherwise v ij =0;c j is a location variable, indicating whether an emergency department is established at the j alternative emergency department. If established, c j =1, otherwise c j =0; C is the service capacity of the alternative emergency department, expressed as the maximum number of people that the emergency department can serve; S103: Based on step S101 and step S102, the objective function of the emergency response capability optimization model is set as follows: S104: Based on step S103, set the constraint conditions of the emergency response capability optimization model as follows: In ij ≤c j ,i∈R,j∈A i ; In ij ,c j ∈{0,1}, i∈R, j∈A i ; d ij ≤s; 3. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments according to claim 2, characterized in that: The specific steps of step S20 are as follows: S201. Based on the hyperbolic tangent function attenuation model formula, calculate the impact of different water depths on driving speed, and use the average speed of different types of roads under the rainstorm waterlogging scenario as the rescue speed of emergency department vehicles; S202. The emergency department selects ten alternate sites based on the original site. The original site and the alternate sites are collectively referred to as alternative emergency departments and serve as input to the emergency response capability optimization model.

4. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments according to claim 1, characterized in that: The specific steps of step S30 are as follows: S301, initialization: set the taboo length to 100, the number of iterations to 100, clear the taboo table, import the candidate emergency department set and the key facility point set into the taboo search algorithm, set the service range of the emergency department to a circle with the emergency department as the center and the rescue vehicle speed multiplied by the rescue time threshold as the radius, calculate the distance between the candidate emergency department and the key facility point using the Euclidean distance, and generate an initial solution; S302, domain search generates candidate solutions: through domain random traversal search, the solutions generated by local search are stored, which also acts as a local taboo table, the path distance corresponding to the local solution is stored, the current path is copied, and a new path is generated by exchange. If the newly generated path is not in the global taboo table and the local taboo table, it is a valid search, otherwise the search continues, and the service radius constraint is met during detection. If it is not met, no detection is required, so that the alternative emergency department has the shortest distance under the condition of maximum coverage, and the path distance corresponding to the candidate solution is calculated; S303, select the best candidate solution: compare the solution with the smallest path distance among the candidate solutions with the current best solution. If it is better than the best solution, update the current best solution and the taboo table. If it is not better than the current best solution, select the solution with the smallest path distance that is not tabooed among the candidate solutions as the new current solution, and then add the corresponding solution to the taboo table. S304, determine the termination condition: if the specified number of iterations is reached, stop and output the current best solution, and draw the first round of iterative site selection distribution map of the emergency department, otherwise return to step S302 to continue searching.

5. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments according to claim 1, characterized in that: The specific steps of step S40 are as follows: S401, analyzing the first round of iterative site selection distribution map of the emergency department, and determining the candidate emergency department sites that are consistent and inconsistent in the output results of the first round of iterations; S402. In the second round of iteration, the candidate emergency departments and the key facilities they can serve that are consistent in multiple output results are removed, the remaining candidate emergency departments and key facilities are substituted into the algorithm again for iteration, and a second round of iterative site selection distribution map of the emergency departments is drawn; S403, analyzing the second round of iterative site selection distribution map of the emergency department. If the output results of several times of the second round of iterations are consistent, the iteration is stopped and the final site selection is determined; if there are still inconsistent site selections, the third round of iteration is continued until each output result is consistent.

6. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments according to claim 3, characterized in that: The average vehicle speed in step S201 is expressed as: Among them, V1 is the speed on a sunny day, which is derived from the traffic travel big data platform, V2 is the speed on a rainy day, w is the depth of water accumulation on the road section, a is the median of the water depth where vehicles are prohibited from driving, and b is the precipitation attenuation coefficient, which is 3.

5.

7. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments according to claim 3, characterized in that: In step S202, the selection principle is that there is little water accumulation near the site, the road network facilities are complete, and the emergency demand near the site is large.

8. The method for optimizing the site selection of urban rainstorm waterlogging emergency departments according to claim 6, characterized in that: In step S301, the time threshold is 10 minutes.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

10. An electronic terminal, characterized in that: include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the method according to any one of claims 1 to 8.

Images