Multi-algorithm combined optimization of 120 emergency center ambulance task allocation method

Abstract

The application discloses a 120 emergency center ambulance task allocation method based on multi-algorithm combination optimization, and comprises the following steps: S1, acquiring the specific positions of all patients to be treated and their illness conditions, the specific positions of all idle ambulances, the specific positions of all hospitals and the treatment ability for each patient in a current time period; S2, constructing an ambulance task allocation evaluation function and a treatment effect evaluation function obtained by each patient; S3, performing path planning in combination with an A* algorithm to ensure that the ambulance selects an optimal route; and S4, using an Ito algorithm and a Newton-Raphson optimization algorithm to iteratively calculate the optimal allocation result of each patient, so that each patient can obtain emergency treatment. The application is superior to a traditional single-algorithm scheduling scheme in response time, treatment effect and resource utilization rate through multi-algorithm combination optimization, can efficiently perform multi-ambulance task allocation, and ensures that each patient can obtain timely and effective treatment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent scheduling and optimization, and particularly relates to a 120 emergency center ambulance task allocation method based on multi-algorithm combination optimization. BACKGROUND

[0002] The existing ambulance dispatching system mainly relies on manual dispatching or simple rule algorithms, and it is difficult to achieve efficient task allocation and path optimization in a complex dynamic environment. Traditional artificial intelligence algorithms have great limitations in dealing with the randomness and suddenness of emergency tasks, resulting in a longer response time, low resource utilization, and an inability to fully meet actual needs. Therefore, a new algorithm is needed to improve the efficiency and response speed of ambulance dispatching.

[0003] Although artificial intelligence algorithms have achieved remarkable results in other fields, their application in 120 emergency ambulance dispatching systems still faces many challenges. Many existing artificial intelligence-based dispatching algorithms, such as genetic algorithms and ant colony algorithms, although perform outstandingly in solving certain optimization problems, are not fully adapted to the high dynamic, multi-variable, and real-time dispatching environment due to the particularity of ambulance dispatching problems. For example, genetic algorithms are prone to fall into local optima and are difficult to achieve global optimal solutions when dealing with large-scale dispatching problems; ant colony algorithms can quickly find feasible solutions in the early stage, but have defects in real-time path updating and decision optimization. This shows that existing single artificial intelligence algorithms have limitations in the field of ambulance dispatching, especially in dealing with real-time dispatching problems in complex and dynamic environments. SUMMARY

[0004] To solve the problem that existing single artificial intelligence algorithms cannot fully adapt to the complex ambulance dispatching needs in actual situations, the present application proposes a 120 emergency center ambulance task allocation method based on multi-algorithm combination optimization, which solves the above problems.

[0005] The present application discloses a 120 emergency center ambulance task allocation method based on multi-algorithm combination optimization, comprising the following steps:

[0006] S1, obtaining the specific locations of all patients to be treated, their illness conditions, the specific locations of all idle ambulances, the specific locations of all hospitals, and the treatment capabilities of hospitals for each patient in the current time period.

[0007] S2, constructing a task allocation evaluation function for ambulances and a treatment effect evaluation function for each patient.

[0008] S3, combining the A* algorithm for path planning to ensure that the ambulance selects the optimal route.

[0009] S4, using the Ito algorithm and Newton-Raphson optimization algorithm to calculate the optimal allocation of each patient, so that each patient can get first aid.

[0010] Preferably, the S1 comprises the following steps:

[0011] The specific location of all patients to be treated in the current time period is obtained through the emergency call system, which can be obtained through GPS positioning system, emergency call records, and patient mobile phone location services.

[0012] The severity of the patient is obtained through the patient's self-report at the time of emergency call, the preliminary judgment of the emergency personnel, and the patient's historical health records.

[0013] The specific location of all idle ambulances is obtained through the vehicle dispatching system and the GPS positioning system. The real-time location information of each ambulance is obtained through the GPS device installed on the vehicle and transmitted to the dispatching center through the wireless network.

[0014] The specific location of the hospital is obtained through the geographic information system.

[0015] The hospital's treatment capacity for patients is obtained through the number of beds, emergency room capacity, available medical equipment, and the number of medical staff in the hospital's real-time resource management system.

[0016] Preferably, the task allocation evaluation function is:

[0017]

[0018] Where N is the number of patients, q i is the treatment effect of the i-th patient, σ F is the standard deviation of all patient treatment effects, and λ is the adjustment parameter for balancing the total treatment effect and its standard deviation. This formula indicates that in order to make the treatment effect of each patient relatively balanced, there should not be a patient with a significantly poor treatment effect that could endanger his life. Therefore, the standard deviation σ F The task allocation of all ambulances is balanced.

[0019] Preferably, the treatment effect evaluation function is:

[0020]

[0021] Where E ij is the treatment capacity of the j-th hospital for the i-th patient, T i is the time consumption of the ambulance to the i-th patient's location, T ij is the time consumption of the i-th patient from waiting for the ambulance to arriving at the j-th hospital, and W iThe severity coefficient of the i-th patient.

[0022] First, the time consumption T of the ambulance to the patient is obtained according to the specific position of the patient and the specific position of the ambulance i Then, the time consumption T of the patient to the hospital is obtained according to the specific position of the patient and the specific position of the hospital ij The time consumption of the patient from dialing 120 to reaching the hospital is T i +T ij In order to make the patient get better treatment effect, it is necessary to find the allocation result that can make q ij The treatment effect evaluation function is used to evaluate the treatment effect of different hospital and ambulance combinations on the patient, and is used to optimize the allocation result in the subsequent steps.

[0023] Preferably, the S3 comprises the following steps:

[0024] S31, defining a state space, the state space comprising all road network nodes, each node representing a geographical position, such as a street intersection, a hospital, a patient position, etc.

[0025] S32, defining a heuristic function, the heuristic function being used to estimate the shortest path from the current node to the target node, the heuristic function being as follows:

[0026]

[0027] Wherein, (x goal ,y goal ) is the coordinate of the target node, (x n ,y n ) is the coordinate of the current node;

[0028] S33, initialization, initializing the open list and the closed list, adding the starting node to the open list and setting its initial cost to 0.

[0029] S34, node expansion, selecting the node with the minimum cost function from the open list for expansion, the cost function being as follows:

[0030] f(n) = g(n) + h(n);

[0031] Wherein, g(n) is the actual cost from the starting point to the current node.

[0032] S35, path update, for each adjacent node of the current node, calculating the new cost function value f(n), if the adjacent node is not in the open list or the new cost function value is smaller than the existing value of the node, updating the cost value of the node and setting its parent node as the current node.

[0033] S36, repeat iteration, repeat S34 and S35 until the target node is expanded, or the open list is empty (indicating no feasible path).

[0034] S37, path backtracking, starting from the target node, backtracking step by step through the parent node pointer to the starting node to obtain the optimal path.

[0035] Preferably, the S4 comprises the following steps:

[0036] S41, particle fitness calculation, calculate the fitness of all particles according to the task evaluation function formula obtained in S2, and the value of the evaluation function F obtained by calculation is the fitness of the particle.

[0037] S42, sort all particles according to fitness, calculate the radius of each particle according to the fitness of each particle, and the calculation formula is:

[0038]

[0039] Where, r max is the maximum value of the particle radius, r min is the minimum value of the particle radius, p represents the particle ranked in the pth position according to the fitness, and M is the total number of particles.

[0040] S43, calculate the environmental temperature, which is used to simulate the cooling process in the distribution process to avoid local optimal solution, and the calculation formula is:

[0041] τ t =τ0×α t ;

[0042] Where, τ t is the environmental temperature at the tth iteration, τ0 is the initial temperature, and α is the annealing coefficient.

[0043] S44, calculate the motion intensity of the particle, and the calculation formula is:

[0044]

[0045] Where, β is the influence factor of the particle radius.

[0046] S45, execute the drift operator, the purpose of the drift operator is to move the solution to the global optimal solution and reduce the deviation of the solution, and ensure that each patient can obtain the optimal first aid effect, which is represented by the following formula:

[0047] H i (s,j)=H i (s,j)+X(p)σ″,ifE c (s,j)∈σ∪σ′;

[0048] wherein σ is the current particle, σ' is the best particle in this iteration, i.e. the attractor, and σ" represents the ambulance and hospital not assigned to the i-th patient in this iteration, and H i (s,j) represents the ambulance s and hospital j assigned to the i-th patient, E c (s,j) represents the edge of node (s,j) in the c-th iteration. The equation indicates that the selection weight of the same assignment result in the current particle and the best particle is increased, so that the feasible solution of the next iteration drifts towards the optimal solution.

[0049] S46, execute the fluctuation operator, the purpose of the fluctuation operator is to increase the diversity of the solution and prevent falling into local optimum, which is represented by the following equation:

[0050] H i (s,j) = H i (s,j) + X(p), if E c (s,j) ∈ σ" ∪ σ' ∪ σ" ∩ rand(0,1) < P perturb ;

[0051] wherein rand(0,1) represents a random function, which can generate a random number in the interval [0,1], P perturb is the disturbance probability, which is used to control the probability of the particle to perform the fluctuation process. The equation indicates that the selection weight of the ambulance and hospital not assigned to the i-th patient and the selection weight of the random ambulance and hospital are increased, so that the particle of the next iteration is randomly disturbed.

[0052] S47, update the particle to construct a new solution.

[0053] S48, if the new particle after updating is better than the current particle, replace the current particle with the new particle and end the current particle update.

[0054] S49, judge whether the current best particle is better than the historical best particle, if yes, replace the historical best particle with the current best particle and reset the maximum number of non-updating times to 0, if no, increase the maximum number of non-updating times by 1.

[0055] S410, judge whether the maximum number of non-updating times is reached, if yes, output the optimal assignment result, if no, go to S43.

[0056] S411, combine the Newton-Raphson optimization algorithm to further optimize the assignment result of each patient.

[0057] Preferably, the S47 comprises the following steps:

[0058] S471, initialize the tabu list to be empty;

[0059] S472, constructing a new feasible solution for each patient;

[0060] S473, adding an ambulance not in the tabu list to the candidate list;

[0061] S474, calculating the selection probability of the candidate ambulance and all hospitals, the calculation formula is as follows:

[0062]

[0063] Wherein, P i (s,j) represents the selection probability of the ambulance and the hospital (s,j) to which the i-th patient is assigned, tabu represents the tabu list, the tabu list records all the assigned ambulances, η i (j) is the reciprocal of T ij , the parameter Ψ is used to control the weight of pheromone concentration in the calculation of selection probability, and the parameter ω is used to control the weight of time consumption in the calculation of selection probability;

[0064] S475, selecting an ambulance and a hospital to assign to the current patient by using roulette method;

[0065] S476, removing the ambulance from the candidate list and adding it to the tabu list;

[0066] S477, judging whether all patients have been assigned, if yes, outputting a new solution and ending the current cycle, if not, returning to S472.

[0067] Preferably, the S411 comprises the following steps:

[0068] S4111, constructing an objective function so that each patient can obtain the best emergency effect, the calculation formula of the objective function is as follows:

[0069]

[0070] Wherein, x is a vector of all patient allocation schemes;

[0071] S4112, calculating the gradient of the objective function, the calculation formula is as follows:

[0072]

[0073] Wherein, each component x1, x2,…, x N represents a decision variable;

[0074] S4113, calculating the Hessian matrix of the objective function, the calculation formula is as follows:

[0075]

[0076] Wherein, xa and x b is the decision variable in the solution vector, representing different dimensions in the optimization problem. The element of the Hessian matrix represents the second-order partial derivative of the objective function G with respect to the variable x a and x b , which reflects the curvature information of the function in each direction.

[0077] 41114、According to the Newton-Raphson optimization algorithm, the allocation scheme is updated, and the update formula is:

[0078]

[0079] where x k is the allocation scheme of the kth iteration;

[0080] S4115、Set the iteration termination condition, when the norm of the gradient is less than the preset threshold ε, stop the iteration, and output the optimal allocation scheme.

[0081] The beneficial effects of the present application are:

[0082] (1) The present application provides efficient path optimization through the A* algorithm, ensuring that ambulances choose the optimal route and shorten the response time. The Ito algorithm is used to handle the randomness and dynamic changes of emergency tasks, providing robustness and adaptability, ensuring the flexibility of task allocation. The Newton-Raphson optimization algorithm provides fast local optimization capability, combined with the initial solution of the Ito algorithm, further improving the accuracy of the allocation result.

[0083] (2) The present application optimizes through the combination of multiple algorithms, which is superior to the traditional single algorithm scheduling scheme in terms of response time, treatment effect and resource utilization, fully demonstrating the advantages in complex dynamic environment, and can efficiently perform multi-ambulance task allocation, ensuring that every patient can receive timely and effective treatment. BRIEF DESCRIPTION OF DRAWINGS

[0084] Figure 1 is the flow chart of the multi-algorithm combined optimization 120 emergency center ambulance task allocation method of the embodiment of the present application. DETAILED DESCRIPTION

[0085] To make the purpose, technical scheme and advantages of the present application clearer, the following embodiments are described in detail with reference to the accompanying drawings.

[0086] The embodiments of the present application disclose a multi-algorithm combined optimization 120 emergency center ambulance task allocation method, the flow is as shown in Figure 1 , including the following steps:

[0087] S1, obtaining the specific locations of all patients to be treated and their illness conditions, the specific locations of all idle ambulances, the specific locations of all hospitals and the treatment ability of each hospital to each patient in the current time period.

[0088] The specific locations of all patients to be treated in the current time period are obtained through an emergency call system, which can be obtained through a GPS positioning system, emergency call records and location services of patient mobile phones.

[0089] In a specific embodiment, the illness conditions of the patients are obtained through the patient's self-description at the time of the emergency call, the preliminary judgment of the emergency personnel and the patient's historical health records. The specific locations of all idle ambulances are obtained through a vehicle dispatching system and a GPS positioning system. The real-time location information of each ambulance is obtained through a GPS device installed on the vehicle and transmitted to the dispatching center through a wireless network. The specific locations of the hospitals are obtained through a geographic information system. The treatment ability of the hospitals to the patients is obtained through the number of beds, the capacity of emergency rooms, available medical equipment and the number of medical staff in the real-time resource management system of the hospitals.

[0090] S2, constructing a task allocation evaluation function of the ambulances and a treatment effect evaluation function of each patient.

[0091] The calculation formula of the task allocation evaluation function is:

[0092]

[0093] wherein N is the number of patients, q i is the treatment effect of the i-th patient, σ F is the standard deviation of the treatment effects of all patients, and λ is a regulation parameter for balancing the total treatment effect and its standard deviation. The task allocation evaluation function indicates that in order to make the treatment effect of each patient relatively balanced and not to cause the treatment effect of a patient to be too poor to endanger his life, the standard deviation σ F balances the task allocation of all ambulances.

[0094] The calculation formula of the treatment effect evaluation function is:

[0095]

[0096] wherein E ij is the treatment ability of the j-th hospital to the i-th patient, T i is the time consumption of the ambulance to the location of the i-th patient, T ij is the time consumption of the i-th patient from waiting for the ambulance to arriving at the j-th hospital, W i is the illness coefficient of the i-th patient.

[0097] First, the time consumption T of an ambulance to a patient is obtained according to the specific position of the patient and the specific position of the ambulance i Then, the time consumption T of the patient to a hospital is obtained according to the specific position of the patient and the specific position of the hospital ij Therefore, the time consumption of the patient from dialing 120 to reaching a hospital is T i +T ij In order to enable the patient to obtain better treatment effect, it is necessary to find the allocation result that can maximize q ij from all ambulances and hospitals. The treatment effect evaluation function is used to evaluate the treatment effect of different hospital and ambulance combinations on the patient, and is used to optimize the allocation result in subsequent steps.

[0098] S3, path planning is combined with A* algorithm to ensure that the ambulance selects the optimal route.

[0099] S31, define the state space, which includes all road network nodes, each node representing a geographical location, such as street intersections, hospitals, patient positions, etc.

[0100] S32, define the heuristic function, which is used to estimate the shortest path from the current node to the target node, and the heuristic function is as follows:

[0101]

[0102] where (x goal ,y goal ) is the coordinate of the target node, and (x n ,y n ) is the coordinate of the current node.

[0103] S33, initialization, initialize the open list and the closed list, and add the starting node to the open list and set its initial cost to 0.

[0104] S34, node expansion, select the node with the smallest cost function from the open list for expansion, and the cost function is as follows:

[0105] f(n) = g(n) + h(n);

[0106] where g(n) is the actual cost from the starting point to the current node.

[0107] S35, path update, for each adjacent node of the current node, calculate the new cost function value f(n), if the adjacent node is not in the open list, or the new cost function value is smaller than the existing value of the node, update the cost value of the node, and set its parent node as the current node.

[0108] S36, repeat iteration, repeat S34 and S35 until the target node is expanded, or the open list is empty (indicating no feasible path).

[0109] S37, path backtracking, starting from the target node, backtracking step by step through the parent node pointer to the starting node to get the optimal path.

[0110] S4, using the Ito algorithm and Newton-Raphson optimization algorithm to iteratively calculate the optimal allocation result of each patient, so that each patient can receive emergency treatment.

[0111] S41, particle fitness calculation, calculate the fitness of all particles according to the task evaluation function formula obtained in S2, and the value of the evaluation function F calculated is the fitness of the particle.

[0112] S42, sort all particles according to fitness, calculate the radius of each particle according to the fitness of each particle, and the calculation formula is:

[0113]

[0114] Where, r max is the maximum value of the particle radius, which is set to 1 in this embodiment, r min is the minimum value of the particle radius, which is set to 0 in this embodiment, p represents the particle ranked in the pth position according to the fitness, M is the total number of particles.

[0115] S43, calculate the environmental temperature, which is used to simulate the cooling process in the allocation process to avoid local optimal solution, and the calculation formula is:

[0116] τ t = τ0× α t ;

[0117] Where, τ y is the environmental temperature at the tth iteration, τ0is the initial temperature, and α is the annealing coefficient, which is set to 0.9 in this embodiment.

[0118] S44, calculate the motion intensity of the particle, and the calculation formula is:

[0119]

[0120] Where, β is the influence factor of the particle radius, which is set to 2 in this embodiment.

[0121] S45, execute the drift operator, the purpose of the drift operator is to move the solution to the global optimal solution and reduce the deviation of the solution, and ensure that each patient can receive the optimal emergency effect, which is represented by the following formula:

[0122] Hi (s,j) = H i (s,j) + X(p)σ", if E c (s,j) e σ U σ';

[0123] where σ is the current particle, σ ′ is the best particle in this iteration (the particle with the highest fitness is the best particle), i.e. the attractor, σ" represents the ambulance and hospital that the ith patient has not been assigned to in this iteration, H i (s,j) represents the ambulance s and hospital j that the ith patient is assigned to, E c (s,j) represents the edge of node (s,j) in the cth iteration. This formula increases the selection weight of the same assignment result in the current particle and the best particle, so that the feasible solution of the next iteration drifts towards the optimal solution.

[0124] S46, execute the fluctuation operator, the purpose of the fluctuation operator is to increase the diversity of the solution and prevent falling into local optimum, which is represented by the following formula:

[0125] H i (s,j) = H i (s,j) + X(p), if E c (s,j) e σ" U σ' U (σ" rand(0,1) < P perturb ;

[0126] where rand(0,1) represents a random function that can generate a random number in the interval [0,1], P perturb is the disturbance probability, which is used to control the probability of the particle performing the fluctuation process. This formula increases the selection weight of the ambulance and hospital that the patient has not been assigned to, as well as randomly selecting an ambulance and hospital, so that the particle in the next iteration performs random disturbance.

[0127] S47, update the particle to construct a new solution.

[0128] S471, initialize the taboo list to be empty.

[0129] S472, traverse each patient to construct a new feasible solution.

[0130] S473, add the ambulance that is not in the taboo list to the candidate list.

[0131] S474, calculate the selection probability of the candidate ambulance and all hospitals, which is calculated as follows:

[0132]

[0133] where P i(s, j) denotes the selection probability of ambulance and hospital (s, j) assigned to the i-th patient, tabu denotes the tabu list, which records all the assigned ambulances, η i (j) is the inverse of T ij , parameter ψ is used to control the weight of pheromone concentration (selection probability of ambulance and hospital) in the calculation of selection probability, and parameter ω is used to control the weight of time consumption in the calculation of selection probability.

[0134] S475, select an ambulance and a hospital to be assigned to the current patient by using roulette method.

[0135] S476, remove the ambulance from the candidate list and add it to the tabu list.

[0136] S477, judge whether all the patients have been assigned, if yes, output the new solution and end the current cycle, if not, return to S472.

[0137] S48, if the updated new particle is better than the current particle, replace the current particle with the new particle and end the current particle update. The greater the value of fitness function F indicates the better solution, and through the comparison of fitness function, it is ensured that the particles gradually move towards the global optimal solution in each iteration.

[0138] S49, judge whether the contemporary optimal particle is better than the historical optimal particle, if yes, replace the historical optimal particle with the contemporary optimal particle and reset the maximum number of non-updating times to 0, if not, increase the maximum number of non-updating times by 1.

[0139] S410, judge whether the maximum number of non-updating times is reached, in the embodiment, the maximum number of non-updating times is 20, if yes, output the optimal assignment result, if not, turn to S43;

[0140] S411, further optimize the assignment result of each patient by combining Newton-Raphson optimization algorithm.

[0141] S4111, construct the objective function so that each patient can obtain the optimal emergency effect, and the calculation formula of the objective function is as follows:

[0142]

[0143] Wherein, x is the vector of all patient assignment schemes;

[0144] S4112, calculate the gradient of the objective function, and the calculation formula is as follows:

[0145]

[0146] Wherein, each component represents a decision variable in the problem.

[0147] S4113, calculate the Hessian matrix of the objective function, the calculation formula is:

[0148]

[0149] Where x a and x b are decision variables in the solution vector, representing different dimensions in the optimization problem. The elements of the Hessian matrix represent the second-order partial derivatives of the objective function G with respect to the variables x a and x b , which reflect the curvature information of the function in each direction.

[0150] 41114, according to the Newton-Raphson optimization algorithm, update the allocation scheme, the update formula is:

[0151]

[0152] Where x k is the allocation scheme of the kth iteration;

[0153] S4115, set the iteration termination condition, when the norm of the gradient is less than the preset threshold ε, stop iteration and output the optimal allocation scheme, in this embodiment ε = 10 -5 .

[0154] In a specific embodiment, in order to evaluate the effect of the embodiments of the present application in practical application, simulation tests are set up, and are compared with Floyd algorithm, ant colony algorithm and the single algorithm contained in the embodiments of the present application, the specific scheme of simulation is as follows:

[0155] Select historical data of 120 emergency centers in a city, including patient location, ambulance location, hospital location and its rescue capacity.

[0156] Select average response time, average treatment effect and resource utilization rate as evaluation indexes.

[0157] The average response time refers to the average time required from receiving an emergency request to the ambulance reaching the patient's location, and the calculation formula is:

[0158]

[0159] The average treatment effect refers to the average value of the treatment effect of all patients, and the calculation formula is:

[0160]

[0161] The resource utilization rate refers to the use efficiency of ambulance and hospital resources, which is used to measure the utilization of the dispatch system to resources, and the calculation formula is:

[0162]

[0163] wherein, denotes the number of all used ambulances, i.e. the usage number of the ambulance resource, denotes the number of all used hospitals, i.e. the usage number of the hospital resource, S denotes the total number of ambulances, and J denotes the total number of hospitals.

[0164] The road network model selects actual road network data of a city, including main roads and intersections. The default vehicle driving speed is 60 km / h. Two simulation scenarios are set. In scenario 1, the treatment weights of all called patients are the same, and the simulation test results are shown in Table 1. In scenario 2, different treatment weights are set according to the actual condition, and the simulation test results are shown in Table 2.

[0165] Table 1 Evaluation index results of each method when the treatment weight is the same

[0166]

[0167] Table 2 Evaluation index results of each method when the treatment weight is different

[0168]

[0169]

[0170] Tables 1 and 2 show the experimental results under different simulation scenarios. By comparison with Floyd algorithm and ant colony algorithm, it can be seen that the method of the present application is superior in response time, treatment effect and resource utilization, and this advantage is more obvious in the environment of assigning treatment weights.

[0171] Table 3 shows the comparison of the combined algorithm of the present application and each single algorithm contained therein. The combined optimization algorithm is superior to the single algorithm in terms of average response time, average treatment effect and resource utilization, verifying the superiority of the combined algorithm in improving the overall performance.

[0172] Table 3 Evaluation index results of the combined algorithm of the present application and each single algorithm of the present application

[0173]

[0174] In summary, through the comparison of the comprehensive evaluation index, it can be seen that in the two scenarios, the method of the present application significantly shortens the response time, ensures that the patient can be treated faster; can effectively improve the average treatment effect of the patient, and through the evaluation function σ FThe effect of the treatment is balanced, and the situation of over-treatment is avoided. Meanwhile, the utilization rate of resources is also excellent, and the existing ambulances and medical resources can be used more efficiently while maintaining a certain redundancy. It can be seen that the method of the application is more efficient in ambulance dispatching, especially when considering the treatment weight (patient condition and hospital treatment level), the advantage is more obvious. The advantages of the application in ambulance task allocation are fully demonstrated.

[0175] In summary, the 120 emergency center ambulance task allocation method based on multi-algorithm combination optimization provided by the application can significantly improve the dispatching efficiency and treatment effect in actual application, and realize efficient utilization of resources.

[0176] The basic principles, main features and advantages of the application are shown and described above. Those skilled in the art should understand that the application is not limited by the above examples, and the above examples and descriptions in the specification are only to illustrate the principles of the application. Without departing from the spirit and scope of the application, various changes and improvements can be made to the application, and these changes and improvements all fall within the scope of the claimed application. The scope of protection of the application is defined by the appended claims and their equivalents.

Claims

1. A 120 emergency center ambulance task allocation method using multi-algorithm combination optimization, characterized in that, The method comprises the following steps: S1, obtaining the specific positions of all patients to be treated and their illness conditions, the specific positions of all idle ambulances, the specific positions of all hospitals, and the treatment capacity of each hospital; S2, constructing a task allocation evaluation function of the ambulance and a treatment effect evaluation function of each patient; The task allocation evaluation function is: wherein, is the number of patients, is the treatment effect for the patient, is the standard deviation of the treatment effect for all patients, is the adjustment parameter; The treatment effect evaluation function is: wherein, the rescue ability of the nth hospital, the rescue ability of the nth hospital, the rescue ability of the nth hospital, the time consumption of the ambulance to the location of the nth patient, the time consumption of the ambulance to the location of the nth patient, the time consumption of the ambulance to the location of the nth patient, the time consumption of the ambulance to the location of the nth patient, the time consumption of the ambulance to the location of the nth patient, the time consumption of the ambulance to the location of the nth patient, the time consumption of the ambulance to the location of the nth patient, S3, combining the A* algorithm to plan a path to ensure that the ambulance selects an optimal route; S31, defining a state space, which comprises all road network nodes, each node representing a geographical position; S32, defining a heuristic function, which is used to estimate the shortest path from a current node to a target node, and the heuristic function is as follows: wherein, is the coordinate of the target node, is the coordinate of the current node; S33, initializing, initializing an open list and a closed list, adding a starting node to the open list, and setting an initial cost of the starting node to 0; S34, node expansion, selecting a node with the minimum cost function from the open list for expansion, and the cost function is as follows: wherein, is the actual cost from the start to the current node; S35. Path update, for each neighbor node of the current node, calculate a new cost function value If the neighbor node is not in the open list, or the new cost function value is less than the existing value of the node, update the cost value of the node and set its parent node as the current node. S36, repeating iteration, repeating S34 and S35 until the target node is expanded or the open list is empty; S37, path backtracking, starting from the target node and backtracking to the starting node through parent node pointers to obtain an optimal path; S4, using the Ito algorithm and the Newton-Raphson optimization algorithm to iteratively calculate the optimal allocation result of each patient, so that each patient can receive emergency treatment; S41, particle fitness calculation, the fitness of all particles is calculated according to the task evaluation function formula obtained in S2, and the value of the evaluation function obtained by calculation is the fitness of the particle ; S42, sorting all particles according to the fitness, calculating the radius of each particle according to the fitness of each particle, and the calculation formula is: wherein, is the maximum value of the particle radius, is the minimum value of the particle radius, denotes the particle in the th position ordered by fitness size, is the total number of particles; S43, calculating the environmental temperature, which is used to simulate the cooling process in the allocation process to avoid local optimal solution, and the calculation formula is: wherein, is the first iteration, is the ambient temperature at the nth iteration, is the initial temperature, is the annealing coefficient; S44, calculating the motion intensity of the particle, and the calculation formula is: wherein is an impact factor for the particle radius; S45, executing the drift operator, which aims to move the solution to the global optimal solution to reduce the deviation of the solution and ensure that each patient can receive the optimal emergency treatment effect, and the drift operator is expressed as: wherein, is the current particle, is the best particle in the current iteration, i.e. the attractor, denotes the patient not assigned to an ambulance and hospital, is denotes the patient assigned to an ambulance and hospital , denotes the edge of the node in the iteration; S46, executing the fluctuation operator, which aims to increase the diversity of the solution to prevent falling into a local optimum, and the fluctuation operator is expressed as: wherein, represents a random function that generates a random number in the interval [0, 1], is a disturbance probability; S47, updating the particle to construct a new solution; S48, if the updated new particle is better than the current particle, replacing the current particle with the new particle and ending the update of the current particle; S49, judging whether the current optimal particle is better than the historical optimal particle, if yes, replacing the historical optimal particle with the current optimal particle and resetting the maximum number of non-updating times to 0, and if no, increasing the maximum number of non-updating times by 1; S410, judging whether the maximum number of non-updating times is reached, if yes, outputting the optimal allocation result, and if no, turning to S43; S411, combining the Newton-Raphson optimization algorithm to further optimize the allocation result of each patient; S4111, constructing a target function to make each patient receive the optimal emergency treatment effect, and the calculation formula of the target function is as follows: wherein, a vector of assigned regimens for all patients; S4112, calculating the gradient of the target function, and the calculation formula is: wherein each component represents a decision variable; S4113, calculating the Hessian matrix of the target function, and the calculation formula is: wherein, and are decision variables in a solution vector, representing different dimensions in an optimization problem, elements of the Hessian matrix representing the objective function with respect to the variables and second-order partial derivatives; S4114, updating the allocation scheme according to the Newton-Raphson optimization algorithm, and the update formula is: wherein is the allocation scheme for the th iteration. S4115, set iteration termination condition, when the norm of gradient is less than the preset threshold value , stop iteration, and output the optimal allocation scheme.

2. The multi-algorithm, combined optimization, 120 emergency center ambulance task assignment method of claim 1, wherein, The S1 comprises the following steps: Obtaining the specific locations of all patients to be treated in the current time period through the emergency call system; Obtaining the critical conditions of the patients through the patient's self-description at the time of the emergency call, the preliminary judgment of the emergency personnel and the patient's historical health records; Obtaining the specific locations of all idle ambulances through the vehicle dispatching system and the GPS positioning system; Obtaining the specific locations of the hospitals through the geographic information system; Obtaining the treatment capacity of the hospitals for the patients through the real-time resource management system of the hospitals.

3. The multi-algorithm, combined optimization, 120 emergency center ambulance task assignment method of claim 2, wherein, The S47 comprises the following steps: S471, initializing the tabu list to be empty; S472, traversing each patient to construct a new feasible solution; S473, adding an ambulance not in the tabu list to the candidate list; S474, calculating the selection probability of the candidate ambulances and all hospitals, and the calculation formula is as follows: wherein, denotes the selection probability of an ambulance and a hospital to which a patient is assigned, denotes a taboo list, which records all ambulances that have already been assigned, is the inverse of , the parameter controls the weight of pheromone concentration in the calculation of the selection probability, and the parameter controls the weight of time consumption in the calculation of the selection probability;​​ S475, selecting an ambulance and a hospital to be allocated to the current patient by using the roulette method; S476, removing the ambulance from the candidate list and adding it to the tabu list; S477, judging whether all patients have been allocated, if yes, outputting a new solution and ending the current cycle, if not, returning to S472.

Images