An emergency rescue method and system based on hybrid ant colony optimization

Abstract

The present invention provides an emergency rescue method and system based on hybrid ant colony optimization, which relates to the field of emergency rescue technology. The method initializes ant colony algorithm parameters, including the number of ants, pheromone matrix, heuristic factor and volatility factor, by collecting key data such as the position of the wounded, the change of survival probability, the location of the rescue vehicle and the hospital. Subsequently, the survival probability function is set based on the real data of the survival probability of the wounded, and the pheromone matrix is ​​constructed to record the path information. During the algorithm iteration process, the rescue target is selected with a certain probability according to the pheromone concentration and heuristic information, the total survival probability of the wounded on the path is calculated, and the pheromone matrix is ​​updated according to the total survival probability. Through continuous iterative optimization, the rescue path with the highest total survival probability is finally output as the optimal rescue order. The method significantly improves the efficiency of emergency response, can quickly respond to emergencies in a complex rescue environment, has strong global optimization ability, and is excellent in adaptability and robustness.

Description

Technical Field

[0001] The present invention relates to the field of emergency rescue technology, and in particular to an emergency rescue method and system based on hybrid ant colony optimization. Background Art

[0002] After emergencies such as natural disasters, rapid and effective emergency rescue has a crucial impact on the survival rate of the wounded. Such emergencies are often accompanied by complex and changing rescue environments, including scattered distribution of the wounded, complex road conditions, limited rescue resources and other multiple challenges.

[0003] Traditional emergency rescue strategies mainly rely on manual experience and preset rules to dispatch rescue vehicles. However, this method often fails to make the best global decision quickly in the face of complex rescue environments, resulting in low rescue efficiency and difficulty in maximizing the survival rate of the wounded.

[0004] In order to improve the effectiveness of emergency rescue, researchers have begun to explore the use of optimization algorithms to assist or replace traditional scheduling methods. Ant colony algorithm, as an optimization algorithm based on bionics, is widely used to solve complex combinatorial optimization problems due to its good robustness and fast convergence speed. In the field of emergency rescue, ant colony algorithm can simulate the pheromone transmission mechanism of ants in the foraging process, and find the optimal rescue path by continuously iterating and updating the pheromone matrix.

[0005] However, the traditional ant colony algorithm also has some shortcomings. First, the algorithm parameter settings, such as the number of ants, pheromone volatilization factors, etc., often rely on manual experience and are difficult to select. Inappropriate parameter settings may lead to poor algorithm performance or even failure to find the optimal solution. Secondly, the global optimization ability of the traditional ant colony algorithm is slightly poor, and it is easy to fall into the local optimal solution, which is extremely disadvantageous in the field of emergency rescue, because missing the best rescue time may lead to a significant decrease in the survival rate of the wounded.

[0006] Therefore, how to improve and optimize the traditional ant colony algorithm in combination with the actual needs of the emergency rescue field has become an urgent problem to be solved. Summary of the invention

[0007] To this end, an embodiment of the present invention provides an emergency rescue method and system based on hybrid ant colony optimization, which is used to solve the problems in the prior art that traditional emergency rescue strategies are difficult to quickly make global optimal decisions when facing complex and changeable rescue environments, the rescue efficiency is low, and the survival rate of the wounded is difficult to maximize.

[0008] In order to solve the above problems, an embodiment of the present invention provides an emergency rescue method based on hybrid ant colony optimization, which includes:

[0009] Step S1: Collect key data, including the location of the injured, the real data of the survival probability of the injured over time, the location of the rescue vehicle and the location of the hospital, and initialize the ant colony according to the collected key data, including setting the number of ants, the initial pheromone matrix, the heuristic factor and the volatility factor;

[0010] Step S2: setting a wounded survival probability function based on real data of the wounded survival probability changing over time, and constructing a pheromone matrix, wherein the pheromone matrix is ​​used to record the pheromone concentration on the path;

[0011] Step S3: Select the next rescue target with a certain probability according to the pheromone concentration and heuristic information;

[0012] Step S4: After each ant completes the path selection, it calculates the total survival probability of all the wounded on the selected path;

[0013] Step S5: Update the pheromone matrix according to the total survival probability of the path;

[0014] Step S6: Return to step S3 until the preset number of iterations is reached or the termination condition is met;

[0015] Step S7: After the iterative optimization is completed, the rescue path with the highest overall survival probability is output as the optimal rescue sequence.

[0016] Preferably, the heuristic information is inversely proportional to the distance between the injured persons, expressed as:

[0017]

[0018] Where η ij represents the heuristic information between injured person i and injured person j, d ij Represents the distance between injured person i and injured person j.

[0019] Preferably, the next rescue target is selected with a certain probability according to the pheromone concentration and the heuristic information, wherein the calculation formula of the selection probability is:

[0020]

[0021] Where P ij represents the probability of selecting injured person j as the next rescue target at the position of injured person i; α and β represent the pheromone importance factor and the heuristic information importance factor respectively; T ij represents the pheromone concentration of the rescue path from injured person i to injured person j, which is a matrix element in the pheromone matrix T; allowed represents the set of rescue targets that the current ant can choose, that is, the set of injured person locations that the ant can choose to go to in the current state; k is an index variable.

[0022] Preferably, the pheromone importance factor α and the heuristic information importance factor β are determined by a particle swarm algorithm, the objective function of the particle swarm algorithm is the total survival rate of the wounded, and the positions of the particles in the particle swarm algorithm are updated according to the following formula:

[0023]

[0024] Wherein, the subscript i represents the i-th particle; the superscript t represents the t-th iteration; X represents the position of the particle, v represents the velocity vector of the particle; c1 is the individual learning factor, which determines the importance of the particle to the individual best solution Pbest when updating its velocity; c2 is the group learning factor, which determines the importance of the particle to the global best solution gbest when updating its velocity; r1 and r2 are random numbers in the interval [0-1].

[0025] Preferably, the method for calculating the total survival probability of all injured persons on the selected path is:

[0026]

[0027] Where S is the overall survival probability, t i represents the time when the injured person i is rescued, that is, the time from the i-th injured person being injured to being rescued; P(t i ) represents the casualty i at time t i The survival probability of being rescued; K represents the total number of injured people on the path, that is, the number of injured people in the path {n1, n2, ..., nk}; It means to sum all the wounded on the path.

[0028] Preferably, the method for updating the pheromone matrix according to the total survival probability of the path includes:

[0029] The pheromone matrix update includes two processes: volatilization and increase. The volatilization process reduces the pheromone concentration according to the preset volatilization factor:

[0030] T ij ′=(1-ρ)T ij ;

[0031] Where, T ij ′ is the updated pheromone concentration, T ij is the pheromone concentration, ρ is the volatility factor;

[0032] The increasing process increases the pheromone concentration according to the total survival probability of the path:

[0033] T ij ′=T ij +ΔT ij ;

[0034] In the formula, ΔT ij It represents the increment of pheromone contributed by ants on the path, which is proportional to the total survival probability of the path.

[0035] Preferably, the method further comprises: during the iterative optimization process, introducing a 3-Opt algorithm to avoid falling into a local optimal solution, wherein the 3-Opt algorithm attempts to form a new path by selecting three edges in the path for reconnection, and calculates the overall survival rate of the wounded on the new path; if the overall survival probability of the wounded on the new path is higher, the new path is accepted as the current optimal path.

[0036] The embodiment of the present invention further provides an emergency rescue system based on hybrid ant colony optimization, which is used to implement the emergency rescue method based on hybrid ant colony optimization described above, and specifically includes:

[0037] The initialization module is used to collect key data, including the location of the injured, the real data of the survival probability of the injured over time, the location of the rescue vehicle and the location of the hospital, and initialize the ant colony based on the collected key data, including setting the number of ants, the initial pheromone matrix, the heuristic factor and the volatility factor;

[0038] A model building module, used to set a wounded survival probability function based on real data of wounded survival probability changing over time, and to build a pheromone matrix, wherein the pheromone matrix is ​​used to record the pheromone concentration on the path;

[0039] The path selection module is used to select the next rescue target with a certain probability based on the pheromone concentration and heuristic information;

[0040] The path evaluation module is used to calculate the total survival probability of all the wounded on the path selected by each ant after it completes the path selection;

[0041] The pheromone update module is used to update the pheromone matrix according to the total survival probability of the path;

[0042] An iterative optimization module is used to return to the path selection module until a preset number of iterations is reached or a termination condition is met;

[0043] The optimal path output module is used to output the rescue path with the highest total survival probability as the optimal rescue sequence after the iterative optimization is completed.

[0044] An embodiment of the present invention also provides an electronic device, which includes a processor, a memory and a bus system, wherein the processor and the memory are connected through the bus system, the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the above-mentioned emergency rescue method based on hybrid ant colony optimization.

[0045] An embodiment of the present invention further provides a computer storage medium storing a computer software product. The computer software product includes a number of instructions for enabling a computer device to execute the above-mentioned emergency rescue method based on hybrid ant colony optimization.

[0046] It can be seen from the above technical solutions that the present invention has the following beneficial effects:

[0047] (1) Improving emergency response efficiency: The present invention automatically and quickly optimizes the rescue strategy through the hybrid ant colony algorithm, which can quickly respond to emergencies and significantly improve rescue efficiency.

[0048] (2) Strong global optimization capability: The present invention can achieve optimal scheduling in complex rescue environments, and has strong global optimization capability, adaptability and robustness, ensuring the effectiveness and reliability of the rescue plan.

[0049] (3) Improving the survival probability of the wounded: By optimizing the rescue vehicle dispatch plan, the present invention can maximize the survival probability of the wounded, effectively reduce casualties, and improve the rescue effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the implementation cases of the present invention or the technical solutions in the prior art, the following is a brief description of the drawings required for use in the embodiments. By referring to the drawings, the features and advantages of the present invention will be more clearly understood. The drawings are schematic and should not be understood as limiting the present invention in any way. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0051] Figure 1 A flowchart of an emergency rescue method based on hybrid ant colony optimization provided in an embodiment;

[0052] Figure 2 It is a schematic diagram of the architecture of the present invention in the embodiment;

[0053] Figure 3 A block diagram of an emergency rescue system based on hybrid ant colony optimization provided in an embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Embodiment 1

[0056] In order to solve the problems in the existing technology that the traditional emergency rescue strategy is difficult to quickly make the best global decision in the face of complex and changing rescue environments, the rescue efficiency is low, and the survival rate of the wounded is difficult to maximize. Figure 1 As shown, an embodiment of the present invention proposes an emergency rescue method based on hybrid ant colony optimization, the method comprising:

[0057] Step S1: Collect key data, including the location of the injured, the real data of the survival probability of the injured over time, the location of the rescue vehicle and the location of the hospital, and initialize the ant colony according to the collected key data, including setting the number of ants, the initial pheromone matrix, the heuristic factor and the volatility factor;

[0058] Step S2: setting a wounded survival probability function based on real data of the wounded survival probability changing over time, and constructing a pheromone matrix, wherein the pheromone matrix is ​​used to record the pheromone concentration on the path;

[0059] Step S3: Select the next rescue target with a certain probability according to the pheromone concentration and heuristic information;

[0060] Step S4: After each ant completes the path selection, it calculates the total survival probability of all the wounded on the selected path;

[0061] Step S5: Update the pheromone matrix according to the total survival probability of the path;

[0062] Step S6: Return to step S3 until the preset number of iterations is reached or the termination condition is met;

[0063] Step S7: After the iterative optimization is completed, the rescue path with the highest overall survival probability is output as the optimal rescue sequence.

[0064] It can be seen from the above technical scheme that the present invention proposes an emergency rescue method based on hybrid ant colony optimization. The method initializes the parameters of the ant colony algorithm, including the number of ants, pheromone matrix, heuristic factor and volatility factor, by collecting key data such as the location of the wounded, the change of survival probability, the location of the rescue vehicle and the hospital. Subsequently, the survival probability function is set based on the real data of the survival probability of the wounded, and the pheromone matrix is ​​constructed to record the path information. During the algorithm iteration process, the rescue target is selected with a certain probability according to the pheromone concentration and heuristic information, the total survival probability of the wounded on the path is calculated, and the pheromone matrix is ​​updated according to the total survival probability. Through continuous iterative optimization, the rescue path with the highest total survival probability is finally output as the optimal rescue order. The method significantly improves the efficiency of emergency response, can quickly respond to emergencies in a complex rescue environment, has strong global optimization ability, and excellent adaptability and robustness. At the same time, by optimizing the rescue vehicle scheduling plan, the survival probability of the wounded is significantly improved, and casualties are effectively reduced, providing an efficient and intelligent solution for emergency rescue.

[0065] Reference Figure 2 The present invention conceives an emergency rescue method based on hybrid ant colony optimization. By comprehensively considering factors such as the location of the injured, the change of survival probability over time, the location of the rescue vehicle and the hospital, the ant colony algorithm is combined with the particle swarm algorithm and the 3-Opt algorithm to optimize the path, so as to quickly respond to emergencies and improve the rescue efficiency and the survival probability of the injured.

[0066] In step S1, the initialization phase: collect key data, including the location of the injured (this usually includes latitude and longitude coordinates or the distance and direction relative to a reference point), real data on the survival probability of the injured over time (data from historical rescue records or medical research results, etc.), the location of the rescue vehicle and the location of the hospital, so that the distance factor can be considered in the subsequent algorithm. Initialize the ant colony based on the collected key data, including setting the number of ants (depending on the scale of the problem and the limitations of computing resources), the initial pheromone matrix (indicating the initial concentration of pheromones on each path), the heuristic factor and the volatility factor (these parameters will affect the preference of ants in choosing paths and the decay rate of pheromones).

[0067] In step S2, a model is constructed: according to the collected data (real data of the survival probability of the wounded over time), a function P(t) of the survival probability of the wounded over time is fitted, i.e., the survival probability function. This function will be used to calculate the total survival probability of the path in the subsequent calculation. At the same time, a pheromone matrix T is constructed, where the matrix element T ij represents the pheromone concentration of the rescue path from injured person i to injured person j. Initially, the values ​​of all elements are set to a constant T0.

[0068] In step S3, path selection: the next rescue target is selected with a certain probability according to the pheromone concentration and heuristic information.

[0069] Specifically, the heuristic information η between the injured is calculated ij , which is usually the distance d between the casualty ij Inversely proportional, that is Heuristic information is used to guide ants to choose shorter paths.

[0070] Furthermore, each ant moves according to the pheromone concentration T at its current location. ij and heuristic information η ij , select the next rescue target with a certain probability. The probability calculation formula takes into account the pheromone importance factor α and the heuristic information importance factor β, as well as the set of rescue targets that the current ant can choose allowed. The calculation formula for the selection probability is:

[0071]

[0072] Where P ij It represents the probability of selecting injured person j as the next rescue target at the position of injured person i; allowed represents the set of rescue targets that the current ant can choose, that is, the set of injured person positions that the ant can choose to go to in the current state; k is an index variable.

[0073] Furthermore, the pheromone importance factor α and the heuristic information importance factor β are determined by the particle swarm algorithm.

[0074] Particle Swarm Optimization (PSO) is a population-based optimization algorithm inspired by the behavior of flocks of birds looking for food. Each individual in the swarm is called a particle and points to a solution in the search space. The dimension of a particle is the same as the number of parameters in the problem whose values ​​are desired. Particles are initially randomly distributed in the search space. Each particle generates a fitness value based on the objective function of the problem. The PSO runs until the specified number of iterations or error value is reached. The position of the particle is updated according to the following formula:

[0075]

[0076] Wherein, the subscript i represents the i-th particle; the superscript t represents the t-th iteration; X represents the position of the particle, v represents the velocity vector of the particle; c1 is the individual learning factor, which determines the importance of the particle to the individual best solution Pbest when updating its velocity; c2 is the group learning factor, which determines the importance of the particle to the global best solution gbest when updating its velocity; r1 and r2 are random numbers in the interval [0-1].

[0077] Furthermore, gbest represents the parameters α and β in the particle swarm algorithm that provide the highest survival rate for each ant. The ant path and parameters that provide the shortest path length are accepted as the solution of the system. According to the above formula, the paths of all ants are used to implement pheromone update until the number of iterations preset for the ant colony algorithm is reached or the termination condition is met (such as the total survival probability is no longer significantly improved).

[0078] In step S4, path evaluation: After each ant completes path selection, it calculates the total survival probability of all the wounded on the selected path. This is achieved by accumulating the survival probability of each wounded when rescued. The calculation formula for the total survival probability is:

[0079]

[0080] Where S is the overall survival probability, t i represents the time when the injured person i is rescued, that is, the time from the i-th injured person being injured to being rescued; P(t i ) represents the casualty i at time t i The survival probability of being rescued; K represents the total number of injured people on the path, that is, the number of injured people in the path {n1, n2, ..., nk}; It means to sum all the wounded on the path.

[0081] In step S5, pheromone update: update the pheromone matrix T according to the total survival probability of the path. First, pheromones evaporate over time, and the update formula is T ij ′=(1-ρ)T ij , where T ij ′ is the updated pheromone concentration, and ρ is the volatility factor. Then, according to the total survival probability of each path, the pheromone matrix is ​​updated, and the update formula is T ij ′=T ij +ΔT ij , where ΔT ij The increment of pheromone contributed by ants on the path is proportional to the total survival probability of the path. This step simulates the behavior of ants leaving pheromones on the path to guide subsequent ants.

[0082] In step S6, the path selection, path evaluation and pheromone update steps are repeated until the preset number of iterations is reached or the termination condition is met (such as the total survival probability is no longer significantly improved). In the iterative process, the optimal solution is gradually approached by continuously optimizing the path selection and pheromone update strategies.

[0083] Initially, all ants only consider the distance to the wounded when completing their first trip. Subsequently, the particle swarm algorithm is used to determine the values ​​of the parameters α and β in the formula to further improve the efficiency of the algorithm. The objective function of the particle swarm algorithm is the total survival rate of the wounded. By continuously optimizing the parameters α and β, the algorithm has a stronger optimization ability in the global scope.

[0084] Furthermore, in order to prevent the ant colony algorithm from falling into a local optimal solution, the 3-Opt algorithm is introduced in the iterative optimization process. The 3-Opt algorithm attempts to form a new path by selecting three edges in the path for reconnection and calculates the overall survival rate of the wounded on the new path. If the overall survival probability of the wounded on the new path is higher, the new path is accepted as the current optimal path.

[0085] In practice, three edges in the path can be randomly disconnected, and then the six nodes can be reconnected to form a new path. This process can be repeated many times until a better path is found or a certain number of iterations is reached.

[0086] In step S7, after the iterative optimization is completed, the rescue path with the highest total survival probability is output as the optimal rescue sequence. This path will guide the rescue vehicle to the location of the injured for rescue in the best way.

[0087] Through the above detailed steps and strategies to avoid local optimality, this method can achieve optimal scheduling in complex rescue environments, quickly respond to emergencies, improve rescue efficiency, and significantly increase the survival probability of the wounded.

[0088] Embodiment 2

[0089] like Figure 3 As shown, the present invention provides an emergency rescue system based on hybrid ant colony optimization, which is used to implement the emergency rescue method based on hybrid ant colony optimization of the above embodiment 1, and specifically includes:

[0090] Initialization module 100 is used to collect key data, including the location of the injured, the real data of the survival probability of the injured over time, the location of the rescue vehicle and the location of the hospital, and initialize the ant colony according to the collected key data, including setting the number of ants, the initial pheromone matrix, the heuristic factor and the volatility factor;

[0091] A model building module 200 is used to set a wounded survival probability function based on real data of wounded survival probability changing over time, and to build a pheromone matrix, wherein the pheromone matrix is ​​used to record the pheromone concentration on the path;

[0092] A path selection module 300 is used to select the next rescue target with a certain probability according to the pheromone concentration and heuristic information;

[0093] The path evaluation module 400 is used to calculate the total survival probability of all the wounded on the path selected by each ant after the ant completes the path selection;

[0094] The pheromone updating module 500 is used to update the pheromone matrix according to the total survival probability of the path;

[0095] Iterative optimization module 600, used to return to the path selection module until a preset number of iterations is reached or a termination condition is met;

[0096] The optimal path output module 700 is used to output the rescue path with the highest total survival probability as the optimal rescue sequence after the iterative optimization is completed.

[0097] An emergency rescue system based on hybrid ant colony optimization in this embodiment is used to implement the aforementioned emergency rescue method based on hybrid ant colony optimization. Therefore, the specific implementation method of the emergency rescue system based on hybrid ant colony optimization can be seen in the embodiment part of the emergency rescue method based on hybrid ant colony optimization in the previous text. For example, the initialization module 100, the model building module 200, the path selection module 300, the path evaluation module 400, the pheromone update module 500, the iterative optimization module 600, and the optimal path output module 700 are respectively used to implement steps S1, S2, S3, S4, S5, S6, and S7 in the above-mentioned emergency rescue method based on hybrid ant colony optimization. Therefore, its specific implementation method can refer to the description of the corresponding embodiments of each part. In order to avoid redundancy, it will not be repeated here.

[0098] Embodiment 3

[0099] An embodiment of the present invention provides an electronic device, which includes a processor, a memory and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the above-mentioned emergency rescue method based on hybrid ant colony optimization.

[0100] Embodiment 4

[0101] An embodiment of the present invention provides a computer storage medium, which stores a computer software product. The computer software product includes a number of instructions for enabling a computer device to execute the above-mentioned emergency rescue method based on hybrid ant colony optimization.

[0102] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0103] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0105] Obviously, the above embodiments are merely examples for clear explanation and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. An emergency rescue method based on hybrid ant colony optimization, characterized in that: include: Step S1: Collect key data, including the location of the injured, the real data of the survival probability of the injured over time, the location of the rescue vehicle and the location of the hospital, and initialize the ant colony according to the collected key data, including setting the number of ants, the initial pheromone matrix, the heuristic factor and the volatility factor; Step S2: setting a wounded survival probability function based on real data of the wounded survival probability changing over time, and constructing a pheromone matrix, wherein the pheromone matrix is ​​used to record the pheromone concentration on the path; Step S3: Select the next rescue target with a certain probability according to the pheromone concentration and heuristic information; Step S4: After each ant completes the path selection, it calculates the total survival probability of all the wounded on the selected path; Step S5: Update the pheromone matrix according to the total survival probability of the path; Step S6: Return to step S3 until the preset number of iterations is reached or the termination condition is met; Step S7: After the iterative optimization is completed, the rescue path with the highest overall survival probability is output as the optimal rescue sequence.

2. The emergency rescue method based on hybrid ant colony optimization according to claim 1, characterized in that: The heuristic information is inversely proportional to the distance between the wounded, expressed as: Where η ij represents the heuristic information between injured person i and injured person j, d ij Represents the distance between injured person i and injured person j.

3. The emergency rescue method based on hybrid ant colony optimization according to claim 1, characterized in that: The next rescue target is selected with a certain probability according to the pheromone concentration and heuristic information, wherein the calculation formula of the selection probability is: Where P ij represents the probability of selecting injured person j as the next rescue target at the position of injured person i; α and β represent the pheromone importance factor and the heuristic information importance factor respectively; T ij represents the pheromone concentration of the rescue path from injured person i to injured person j, which is a matrix element in the pheromone matrix T; allowed represents the set of rescue targets that the current ant can choose, that is, the set of injured person locations that the ant can choose to go to in the current state; k is an index variable.

4. The emergency rescue method based on hybrid ant colony optimization according to claim 3 is characterized in that: The pheromone importance factor α and the heuristic information importance factor β are determined by a particle swarm algorithm. The objective function of the particle swarm algorithm is the total survival rate of the wounded. The positions of the particles in the particle swarm algorithm are updated according to the following formula: Wherein, the subscript i represents the i-th particle; the superscript t represents the t-th iteration; X represents the position of the particle, v represents the velocity vector of the particle; c1 is the individual learning factor, which determines the importance of the particle to the individual best solution Pbest when updating its velocity; c2 is the group learning factor, which determines the importance of the particle to the global best solution gbest when updating its velocity; r1 and r2 are random numbers in the interval [0-1].

5. The emergency rescue method based on hybrid ant colony optimization according to claim 3 is characterized in that: The method for calculating the total survival probability of all the wounded on the selected path is: Where S is the overall survival probability, t i represents the time when the injured person i is rescued, that is, the time from the i-th injured person being injured to being rescued; P(t i ) represents the casualty i at time t i The survival probability of being rescued; K represents the total number of injured persons on the path, that is, the number of injured persons in the path {n1, n2, ..., nk}; It means to sum all the injured persons on the path.

6. The emergency rescue method based on hybrid ant colony optimization according to claim 1, characterized in that: The method for updating the pheromone matrix according to the total survival probability of the path includes: The pheromone matrix update includes two processes: volatilization and increase. The volatilization process reduces the pheromone concentration according to the preset volatilization factor: T ij ′=(1-ρ)T ij ; Where, T ij ′ is the updated pheromone concentration, T ij is the pheromone concentration, ρ is the volatility factor; The increasing process increases the pheromone concentration according to the total survival probability of the path: T ij ′=T ij +ΔT ij ; In the formula, ΔT ij It represents the increment of pheromone contributed by ants on the path, which is proportional to the total survival probability of the path.

7. The emergency rescue method based on hybrid ant colony optimization according to claim 1, characterized in that: The method also includes: during the iterative optimization process, introducing a 3-Opt algorithm to avoid falling into a local optimal solution, wherein the 3-Opt algorithm attempts to form a new path by selecting three edges in the path for reconnection, and calculates the overall survival rate of the wounded on the new path; if the overall survival probability of the wounded on the new path is higher, the new path is accepted as the current optimal path.

8. An emergency rescue system based on hybrid ant colony optimization, characterized in that: The system is used to implement the emergency rescue method based on hybrid ant colony optimization according to any one of claims 1 to 7, specifically comprising: The initialization module is used to collect key data, including the location of the injured, the real data of the survival probability of the injured over time, the location of the rescue vehicle and the location of the hospital, and initialize the ant colony based on the collected key data, including setting the number of ants, the initial pheromone matrix, the heuristic factor and the volatility factor; A model building module, used to set a wounded survival probability function based on real data of wounded survival probability changing over time, and to build a pheromone matrix, wherein the pheromone matrix is ​​used to record the pheromone concentration on the path; The path selection module is used to select the next rescue target with a certain probability based on the pheromone concentration and heuristic information; The path evaluation module is used to calculate the total survival probability of all the wounded on the path selected by each ant after it completes the path selection; The pheromone update module is used to update the pheromone matrix according to the total survival probability of the path; An iterative optimization module is used to return to the path selection module until a preset number of iterations is reached or a termination condition is met; The optimal path output module is used to output the rescue path with the highest total survival probability as the optimal rescue sequence after the iterative optimization is completed.

9. An electronic device, characterized in that: The electronic device includes a processor, a memory and a bus system, the processor and the memory are connected through the bus system, the memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the emergency rescue method based on hybrid ant colony optimization as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer software product, which includes a number of instructions for enabling a computer device to execute the emergency rescue method based on hybrid ant colony optimization as described in any one of claims 1 to 7.

Images