A method for selecting the location of emergency medical sites based on the urgency of emergency medical resource demand

Abstract

The present invention discloses a method for selecting the location of an emergency medical site based on the urgency of the demand for emergency medical resources, comprising the following steps: respectively obtaining the real road distances between different areas and the emergency medical sites closest to them; using a two-step mobile search algorithm to respectively calculate the accessibility of different areas to obtain emergency medical resources, and selecting areas that cannot obtain emergency medical resources; calculating the urgency of the demand for the areas that cannot obtain emergency medical resources U k ; Genetic algorithms are used to comprehensively evaluate the location of emergency medical stations based on the urgency of the needs of areas without access to emergency medical resources and the number of areas without access to emergency medical resources that can be covered by emergency medical stations. The present invention improves the overall resource allocation efficiency, ensuring that the supply of emergency medical resources in remote areas will not be neglected even when population distribution and demand intensity change, thereby improving the overall public health and welfare level.

Description

Technical Field

[0001] The present invention relates to the field of geographic information data processing technology, and more specifically, to a method for selecting a location for an emergency medical site based on the urgency of the demand for emergency medical resources. Background Art

[0002] In the field of emergency resource management and allocation, fast and accurate decision-making is essential to improve response efficiency and resource utilization. Traditional medical resource allocation methods often rely on intuitive judgment or simple distance calculations, without considering the urgency of the demand point and actual geographical obstacles, resulting in medical resources not being allocated to the areas most in need, resulting in prolonged response time and low efficiency of medical resources in emergencies. Summary of the invention

[0003] An object of the present invention is to solve at least the above problems and to provide at least the advantages which will be described hereinafter.

[0004] In order to achieve these purposes and other advantages according to the present invention, a method for selecting an emergency medical site based on the urgency of the demand for emergency medical resources is provided, comprising the following steps:

[0005] Obtain the actual road distance between different areas and the nearest emergency medical stations;

[0006] A two-step moving search algorithm is used to calculate the accessibility of emergency medical resources in different areas and select areas that are unable to obtain emergency medical resources;

[0007] Calculate the urgency of the need for areas without access to emergency medical resources U k :

[0008] U k =d kj •p k / max(d kj •p k )

[0009] Among them, d kj represents the actual road distance between the area without access to emergency medical resources and the nearest emergency medical station, p k represents the population of the area without access to emergency medical resources, j represents the candidate points of emergency medical sites, k represents the area without access to emergency medical resources, max(d kj •p k ) indicates d kj With p k The maximum value of the product;

[0010] A genetic algorithm is used to comprehensively evaluate the location of emergency medical stations based on the urgency of the needs in areas without access to emergency medical resources and the number of areas that can be covered by emergency medical stations without access to emergency medical resources.

[0011] Preferably, the objective function of the genetic algorithm is set to:

[0012] Max(Z)=U te +N te •MU e

[0013] Where e represents the threshold of emergency medical station service coverage, U te The sum of the urgency of the needs of the covered areas that do not have access to emergency medical resources, N te The total number of areas without access to emergency medical resources that are served by at least one emergency medical station, MU e It represents the average of the urgency of need for all covered areas without access to emergency medical resources with a urgency of need greater than 0.

[0014] Preferably, the total urgency of the needs of the covered areas without access to emergency medical resources is U te The calculation formula is:

[0015] U te =∑ k∈Ne U k •y kj ,∀k∈N e , j∈M;

[0016] Among them, N e represents the set of covered areas that are not accessible to emergency medical resources, M represents the set of candidate points for emergency medical sites, and y kj represents the acceptance intention of the area k that cannot obtain emergency medical resources to the emergency medical resources provided by the candidate emergency medical site j, y kj =1 means accept, y kj =0 means not accept.

[0017] Preferably, the total number of covered areas without access to emergency medical resources is N te The calculation formula is:

[0018] N te =∑ k∈Ne δ(y kj >0),∀k∈N e , j∈M;

[0019] .

[0020] Preferably, the calculation formula for the average urgency of the covered areas without access to emergency medical resources is:

[0021] MU e =∑ k∈Ne U k / |N e |

[0022] Among them, |N e |Represents the total number of covered areas with a demand urgency greater than 0 that do not have access to emergency medical resources.

[0023] Preferably, the constraints of the objective function include:

[0024] Constraints on the number of emergency medical sites: ∑ j∈M x j =P, where x j Indicates whether the candidate point j of the emergency medical station is selected, x j =0 means no site is selected, x j =1 indicates the site is selected, and P indicates the upper limit of the number of emergency medical sites allowed to be built.

[0025] Preferably, the selection process of the genetic algorithm adopts a roulette wheel selection mechanism, the crossover process generates offspring by randomly selecting crossover points and exchanging paternal genes to maintain the genetic diversity of the population, and the mutation process randomly mutates individuals and checks whether there are individual duplications. For duplicate individuals, randomly generated new individuals are used to replace them to ensure the uniqueness of each individual.

[0026] Preferably, a geographic information system is used to visualize the coverage of emergency medical station services, wherein different colors are used to represent the urgency of the needs of the areas covered by the emergency medical station services that are unable to obtain emergency medical resources, and circular areas of different radii are used to represent different numbers of coverable areas.

[0027] The present invention has at least the following beneficial effects:

[0028] The present invention selects the actual road distance between the area without emergency medical resources and the nearest emergency medical station as the emergency space resistance, and the result is accurate and consistent with the actual traffic conditions;

[0029] This paper proposes a calculation model based on the urgency of demand, which combines the actual distance between the region and the nearest medical resource site and the population in need, quantifies the urgency of demand, reflects the priority of different regions, and helps to allocate resources more reasonably. The urgency of demand index is incorporated into the optimization target, and the demand coverage and service fairness are comprehensively considered to achieve global optimization of the layout of emergency medical sites, ensuring that the needs of high-priority areas are met first.

[0030] This invention effectively balances the impact of demand urgency and coverage quantity by introducing the mean of demand urgency as the dynamic weight of the increasing emergency resource demand area. The introduction of this strategy improves the overall resource allocation efficiency and the adaptability to changing environmental conditions, ensuring that even when the population distribution and demand intensity change, the supply of emergency medical resources in remote areas will not be neglected, thereby improving the overall public health and welfare level; it also makes the model closer to the needs of actual application scenarios, especially in areas such as disaster response or emergency service allocation.

[0031] The mutation part of the genetic algorithm of the present invention introduces an enhanced mutation strategy (check duplication strategy), which ensures the diversity of individuals in the population and prevents the algorithm from converging to the local optimal solution too early. Individuals will mutate randomly under the premise of ensuring no duplication, which increases the probability of exploring unknown areas and improves the global search capability. In the process of algorithm implementation, dynamic adjustment of the mutation probability is considered to balance the global search and local search capabilities.

[0032] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of a method for selecting a site for an emergency medical station based on the urgency of the demand for emergency medical resources according to an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of calculating the actual road distance based on path planning in an embodiment of the present invention (only four paths are shown);

[0035] Figure 3 A schematic diagram of a map showing how to calculate reachability using a two-step mobile search algorithm in an embodiment of the present invention (the darker the color, the better the reachability);

[0036] Figure 4 A schematic diagram of a map for calculating the urgency of demand in an embodiment of the present invention (the darker the color, the stronger the urgency of demand);

[0037] Figure 5 A graph showing the changing trend of average fitness during the genetic algorithm optimization process in an embodiment of the present invention;

[0038] Figure 6 This is a schematic map showing the urgency of the demand for emergency medical sites and the number of covered demand points selected in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0040] It should be noted that the experimental methods described in the following embodiments are conventional methods unless otherwise specified, and the reagents and materials are commercially available unless otherwise specified; in the description of the present invention, the terms "lateral", "longitudinal", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0041] like Figure 1 As shown, the present invention provides a method for selecting a site for an emergency medical station based on the urgency of the demand for emergency medical resources, comprising the following steps:

[0042] S1. Obtain the actual road distance between different areas and the nearest emergency medical stations;

[0043] Specifically, the actual road distance between different areas and the nearest emergency medical site can be calculated by calling the Amap route planning API interface.

[0044] Taking Shexian County, Handan City as an example, the "Route Planning Interface 2.0" is used for driving route planning, and the fastest driving route calculation strategy with code 38 is used to obtain the actual road distances between different township areas and Shexian County Hospital with emergency medical resources, such as Figure 2 shown.

[0045] S2, using a two-step mobile search algorithm to calculate the accessibility of emergency medical resources in different areas, and select areas that cannot obtain emergency medical resources;

[0046] The two-step mobile search algorithm is a method for evaluating the spatial accessibility of public service facilities. The method calculates the accessibility of demand points through two search processes. First, the supply and demand points within the threshold range are searched with the supply point as the center, and the supply-demand ratio is calculated. Then, the supply points within the threshold range are searched with the demand point as the center, and the supply-demand ratios of all supply points are summed up to obtain the accessibility of the demand point.

[0047] The calculation formula of the two-step mobile search algorithm is as follows:

[0048] ;

[0049] ;

[0050] ;

[0051] Among them, i represents the location of the administrative area (demand point); j represents the medical site of emergency medical resources (supply point); S j represents the medical service capacity at point j; P i represents the population in the administrative division i; R j represents the medical service supply-demand ratio at point j; d0 represents the search threshold; d ij represents the accessibility resistance between points i and j (i.e. Figure 2 The actual distance between the supply point and the demand point shown); A i represents the medical accessibility at location i; G(d ij ,d0) represents the Gaussian function. A i The larger the value, the better the accessibility of demand location i.

[0052] For example, the accessibility of each administrative area in Shexian County is calculated by the above two-step mobile search algorithm. d0 is set to 15 kilometers. The services provided by the emergency medical stations are basically homogeneous, that is, there are no major differences in their hardware facilities and equipment. Therefore, it can be assumed that all emergency medical stations have the same supply capacity. The calculation results are shown in Tables 1 and 2. Figure 3 shown.

[0053] Table 1

[0054] Township <![CDATA[A i ]]> Region 1 0.0383 Area 2 - Area 3 - Region 4 - Area 5 0.0420 Area 6 0.0369 Area 7 - Area 8 - Area 9 - Region 10 - Area 11 - Area 12 0.0140 Area 13 0.0446 Area 14 0.0220 Area 15 0.0120 Area 16 - Area 17 -

[0055] From Table 1 and Figure 3 It can be seen that areas 2~4, 7~11, and 16~17 were unable to obtain emergency medical resources.

[0056] S3. Calculate the urgency of the need for areas without access to emergency medical resources U k :

[0057] U k =d kj •p k / max(d kj •p k )

[0058] Among them, d kj represents the actual road distance between the area without access to emergency medical resources and the nearest emergency medical station, p k represents the population of the area without access to emergency medical resources, j represents the candidate points of emergency medical sites, k represents the area without access to emergency medical resources, max(d kj •p k ) indicates dkj With p k The maximum value of the product.

[0059] Filter out the urgency of demand k Areas with a value greater than 0 identify those areas as resource-poor and in urgent need.

[0060] The coordinates and demand urgency of each demand point are extracted from the filtered geographic data frame. The coordinates are used to calculate the distance between demand point k and supply point j, while the demand urgency is used to evaluate the urgency of coverage in the objective function.

[0061] For example, based on the accessibility calculation of each administrative area in Shexian County, areas 2-4, 7-11, and 16-17 are all unable to obtain emergency medical resources, so the urgency of the demand for these areas is U k The calculation results are shown in Table 2 and Figure 4 shown.

[0062] Table 2

[0063] Township Urgency Region 1 - Area 2 0.4346 Area 3 0.5010 Region 4 0.8968 Area 5 - Area 6 - Area 7 0.5518 Area 8 0.6726 Area 9 0.3991 Region 10 0.7961 Area 11 0.3561 Area 12 - Area 13 - Area 14 - Area 15 - Area 16 0.5109 Area 17 0.3849

[0064] S4. A genetic algorithm is used to comprehensively assess the location of emergency medical stations based on the urgency of the needs in areas without access to emergency medical resources and the number of areas without access to emergency medical resources that can be covered by emergency medical stations.

[0065] Specifically, the core of calculating the fitness of a given supply point configuration is to count the number of demand points covered by the supply point and accumulate the demand urgency value of each covered demand point. Using the Euclidean distance as the criterion for judging whether a demand point is within the coverage radius of the supply point and using the mean of the demand urgency as the incremental value of the number of demand points can effectively balance the contribution of the two in the objective function and avoid the problem that the demand urgency value may be masked by the number of demand points due to the relatively small demand urgency value. If the data set changes over time, this method can dynamically adjust the parameters of the objective function so that the algorithm can adapt to the new data conditions; if the distribution of the urgency data changes significantly (the demand urgency is generally higher or lower in the new data), it is necessary to readjust the objective function or re-evaluate the parameter settings, and use logarithmic transformation or median smoothing to smooth the impact of extreme values.

[0066] The objective function of the genetic algorithm is set as:

[0067] Max(Z)=U te +N te •MU e

[0068] Where e represents the threshold of emergency medical station service coverage, U teThe sum of the urgency of the needs of the covered areas that do not have access to emergency medical resources, N te The total number of areas without access to emergency medical resources that are served by at least one emergency medical station, MU e It represents the average of the urgency of need for all covered areas without access to emergency medical resources with a urgency of need greater than 0.

[0069] The total urgency of the needs of the covered areas without access to emergency medical resources is U te The calculation formula is:

[0070] U te =∑ k∈Ne U k •y kj ,∀k∈N e , j∈M;

[0071] Among them, N e represents the set of covered areas that are not accessible to emergency medical resources, M represents the set of candidate points for emergency medical sites, and y kj represents the acceptance intention of the area k that cannot obtain emergency medical resources to the emergency medical resources provided by the candidate emergency medical site j, y kj =1 means accept, y kj =0 means not accept.

[0072] The total number of covered areas without access to emergency medical resources N te The calculation formula is:

[0073] N te =∑ k∈Ne δ(y kj >0),∀k∈N e , j∈M;

[0074] .

[0075] The mean urgency of the needs of the covered areas without access to emergency medical resources is calculated as:

[0076] MU e =∑ k∈Ne U k / |N e |

[0077] Among them, |N e |Represents the total number of covered areas with a demand urgency greater than 0 that do not have access to emergency medical resources.

[0078] The constraints of the objective function include:

[0079] Constraints on the number of emergency medical sites: ∑ j∈M x j =P, where x j Indicates whether the candidate point j of the emergency medical station is selected, x j =0 means no site is selected, x j =1 indicates the site is selected, and P indicates the upper limit of the number of emergency medical sites allowed to be built.

[0080] The selection process of the genetic algorithm adopts a roulette selection mechanism, the crossover process adopts a mechanism of randomly selecting crossover points and exchanging paternal genes to generate offspring, and the mutation process randomly mutates individuals and checks whether there are repeated individuals. Repeated individuals continue to mutate to ensure the uniqueness of each individual.

[0081] Specifically, the genetic algorithm steps are as follows:

[0082] 1. Initialization population: Randomly generate the initialization population, each individual has a certain number of supply points;

[0083] 2. Calculate fitness

[0084] 3. Selection: Use a roulette wheel method based on the fitness function to select candidate parents for the next generation, and the selection probability of each individual is proportional to its fitness.

[0085] 4. Crossover: Set the crossover probability, randomly select two parents, and perform single-point crossover. If no crossover is performed, the parents are retained directly. In this stage, check whether there are duplicate individuals. The process is as follows:

[0086] (1) Use the collection to record the supply points that have appeared and check each supply point in the individual.

[0087] (2) Randomly select new points to replace duplicate points.

[0088] (3) The core mechanism is to track the points that have appeared through sets and replace the duplicate points with random new points.

[0089] 5. Mutation: Randomly mutate offspring according to the mutation probability, dynamically adjust the mutation probability so that it gradually decreases with the increase of generations, and the high mutation rate in the early stage enhances the exploration ability and prevents falling into the local optimum. The mutation rate is reduced in the later stage to maintain the stability of the solution. The formula is as follows:

[0090] MR = IMR * (1 - Ge / NGe)

[0091] IMR is the initial mutation rate, Ge is the current generation, and NGe is the total number of iterations.

[0092] 6. Elite retention: In each generation, the individuals with the best fitness are selected to directly enter the next generation to ensure that the optimal solution is not destroyed by crossover or mutation (the best individuals are retained in each generation to avoid losing the better solution due to randomness).

[0093] 7. Update the population: elite individuals and offspring after crossover mutation form the next generation population.

[0094] Still taking Shexian in the aforementioned steps as an example, the initial population size of the genetic algorithm is set to 150, indicating that there are 150 different supply point configurations in each generation; the genetic generation number is set to 50 generations, and the genetic algorithm is used for iteration; the crossover probability is set to 0.8; the initial mutation rate is set to 0.001; the genetic algorithm is run 10 times to obtain multiple optimization results to improve the reliability of the solution.

[0095] The genetic algorithm continuously optimizes fitness through iterative evolution. The randomness of the initial population may lead to different starting points, so multiple runs are performed to reduce the impact of randomness on the results, such as Figure 5 As shown, the overall optimization ability of the algorithm is consistent.

[0096] The geographic information system is used to visualize the coverage of emergency medical stations. Different colors are used to represent the urgency of the needs of the areas that are not covered by emergency medical resources. Circular areas with different radius sizes are used to represent different numbers of covered areas. The results are as follows: Figure 6 shown.

[0097] It can be seen from the above embodiments that:

[0098] The present invention selects the actual road distance between the area without emergency medical resources and the nearest emergency medical station as the emergency space resistance, and the result is accurate and consistent with the actual traffic conditions;

[0099] This paper proposes a calculation model based on the urgency of demand, combining the actual distance between the region and the nearest medical resource site and the population in need, quantifying the urgency of demand, reflecting the priority of different regions, and helping to allocate resources more reasonably. The urgency index is incorporated into the optimization target, and the demand coverage and service fairness are comprehensively considered to achieve global optimization of resource site layout, ensuring that the needs of high-priority areas are met first.

[0100] This invention effectively balances the impact of demand urgency and coverage quantity by introducing the mean of demand urgency as the dynamic weight of the increasing emergency resource demand area. The introduction of this strategy improves the overall resource allocation efficiency and the adaptability to changing environmental conditions, ensuring that even when the population distribution and demand intensity change, the supply of emergency medical resources in remote areas will not be neglected, thereby improving the overall public health and welfare level; it also makes the model closer to the needs of actual application scenarios, especially in areas such as disaster response or emergency service allocation.

[0101] The mutation part of the genetic algorithm of the present invention introduces an enhanced mutation strategy (check duplication strategy), which ensures the diversity of individuals in the population and prevents the algorithm from converging to a local optimal solution too early. Individuals will mutate randomly under the premise of ensuring no duplication, which increases the probability of exploring unknown areas and improves the global search capability.

[0102] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A method for selecting the location of an emergency medical site based on the urgency of the demand for emergency medical resources, characterized in that: The following steps are involved: Obtain the actual road distance between different areas and the nearest emergency medical stations; A two-step moving search algorithm is used to calculate the accessibility of emergency medical resources in different areas and select areas that are unable to obtain emergency medical resources; Calculate the urgency of the need for areas without access to emergency medical resources U k : U k =d kj •p k / max(d kj •p k ) Among them, d kj represents the actual road distance between the area without access to emergency medical resources and the nearest emergency medical station, p k represents the population of the area without access to emergency medical resources, j represents the candidate points of emergency medical sites, k represents the area without access to emergency medical resources, max(d kj •p k ) indicates d kj With p k The maximum value of the product; A genetic algorithm is used to comprehensively evaluate the location of emergency medical stations based on the urgency of the needs of areas without access to emergency medical resources and the number of areas without access to emergency medical resources that can be covered by emergency medical stations; The objective function of the genetic algorithm is set as: Max(Z)=U te +N te •MU e Where e represents the threshold of emergency medical station service coverage, U te The sum of the urgency of the needs of the covered areas that do not have access to emergency medical resources, N te The total number of areas without access to emergency medical resources that are served by at least one emergency medical station, MU e It represents the average of the urgency of need for all covered areas without access to emergency medical resources with a urgency of need greater than 0.

2. The method for selecting the location of an emergency medical station based on the urgency of the demand for emergency medical resources according to claim 1, characterized in that: The total urgency of the needs of the covered areas without access to emergency medical resources is U te The calculation formula is: IN te =∑ k∈Ne IN k •y kj ,∀k∈N e ,j∈M; Among them, N e represents the set of covered areas that are not accessible to emergency medical resources, M represents the set of candidate points for emergency medical sites, and y kj represents the acceptance intention of the area k that cannot obtain emergency medical resources to the emergency medical resources provided by the candidate emergency medical site j, y kj =1 means accept, y kj =0 means not accept.

3. The method for selecting the location of an emergency medical station based on the urgency of the demand for emergency medical resources as claimed in claim 2, characterized in that: The total number of covered areas without access to emergency medical resources N te The calculation formula is: N te =∑ k∈Ne δ(y kj >0) ,∀k∈N e ,j∈M; 。 4. The method for selecting the location of an emergency medical station based on the urgency of the demand for emergency medical resources as claimed in claim 3, characterized in that: The mean urgency of the needs of the covered areas without access to emergency medical resources is calculated as: MU e =∑ k∈Ne U k / |N e | Among them, |N e |Represents the total number of covered areas with a demand urgency greater than 0 that do not have access to emergency medical resources.

5. The method for selecting the location of an emergency medical site based on the urgency of the demand for emergency medical resources according to claim 4, characterized in that: The constraints of the objective function include: Constraints on the number of emergency medical sites: ∑ j∈M x j =P, where x j Indicates whether the candidate point j of the emergency medical station is selected, x j =0 means no site is selected, x j =1 indicates the site is selected, and P indicates the upper limit of the number of emergency medical sites allowed to be built.

6. The method for selecting the location of an emergency medical station based on the urgency of the demand for emergency medical resources according to claim 5, characterized in that: The selection process of the genetic algorithm adopts a roulette wheel selection mechanism. The crossover process generates offspring by randomly selecting crossover points and exchanging paternal genes to maintain the genetic diversity of the population. The mutation process randomly mutates individuals and checks whether there are individual duplications. For duplicate individuals, randomly generated new individuals are used to replace them to ensure the uniqueness of each individual.

7. The method for selecting the location of an emergency medical station based on the urgency of the demand for emergency medical resources according to claim 6, characterized in that: The geographic information system is used to visualize the coverage of emergency medical station services. Different colors are used to represent the urgency of the needs of the areas covered by the emergency medical stations that are unable to obtain emergency medical resources, and circular areas of different radius sizes are used to represent different numbers of coverable areas.

Images