Emergency material dispatching path intelligent optimization method and system and storage medium

Abstract

The invention discloses an emergency material dispatching path intelligent optimization method and system and a storage medium. The method comprises the following steps: acquiring input data, wherein the input data comprises information of each material demand point, transport vehicle information and position information; determining a chromosome coding rule according to the input data; randomly generating chromosome codes according to a chromosome coding rule to obtain an initial matching scheme set; performing constraint processing by using a target function and specifying a fitness function; calculating a fitness score of an individual corresponding to each chromosome code in the set, selecting a dominant individual according to the fitness score, adopting roulette selection, reserving a parent optimal chromosome to replace a filial generation worst chromosome for replication, performing crossover and mutation operation of the chromosome codes, and generating a filial generation individual; and iterating the offspring individuals, and selecting an optimal individual for decoding to obtain a final matching scheme. According to the invention, the optimization of the emergency material dispatching path is realized under the limited hardware condition, the death rate is lowest, and the energy consumption is low.

Description

Technical Field

[0001] The present invention belongs to the field of emergency management, and specifically relates to an intelligent optimization method for emergency material dispatching paths taking into account the random deterioration of injuries, as well as a corresponding system and computer storage medium. Background Art

[0002] Formulating an emergency material dispatch plan plays a vital role in improving the rescue value of emergency materials and reducing the mortality rate.

[0003] The path planning of emergency resource allocation tasks is a complex process. The planning of emergency material transportation routes has a certain impact on the dispatch of emergency materials with high timeliness requirements. When an emergency occurs, transport vehicles are needed to go to the demand points for material distribution. In one mission, a vehicle needs to deliver one or more demand points; when the delivery is completed, the vehicle needs to go to the next demand point or return; a delivery vehicle will be responsible for delivering materials to one or more demand points. The matching between different tasks and vehicles needs to follow the restrictions between them. In the prior art, part of the path planning is matched manually by staff, which is not only inefficient but also prone to errors.

[0004] In view of this, the industry urgently needs an emergency rescue material dispatch path optimization method, system and storage medium that takes into account the random deterioration of injuries. Summary of the invention

[0005] The present invention studies the dispatching problem of emergency materials with the minimum sum of death probabilities in each disaster area as the optimization goal, taking into account the driving range, the limitation of rated load capacity and the deterioration of the condition of the wounded, and introduces the Markov chain to characterize the evolution law of the condition of the wounded, and integrates the relevant quantitative characteristics into the objective function, constructs a mathematical model that conforms to the characteristics of emergency material dispatching, and designs a fast and effective intelligent optimization algorithm. An intelligent optimization method, system and storage medium for emergency material dispatching path considering the random deterioration of the condition of the wounded are proposed, so as to solve the problems raised in the background technology, realize the optimization of the emergency material dispatching path under limited hardware conditions, and minimize the mortality rate and reduce the energy consumption.

[0006] To achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect of the present invention, an intelligent optimization method for emergency material dispatching paths considering random deterioration of injuries is proposed, which specifically comprises the following steps:

[0008] Obtaining input data, wherein the input data includes information of each material demand point, transportation vehicle information, and location information;

[0009] Determine chromosome encoding rules according to the input data;

[0010] According to the chromosome encoding rule, the input data is randomly generated into a plurality of chromosome encodings to obtain an initial matching solution set of vehicles, tasks, and paths;

[0011] Use objective functions to handle constraints and specify fitness functions;

[0012] Calculate the fitness score of each individual corresponding to the chromosome code in the initial matching scheme set, select the dominant individual according to the fitness score to perform the inheritance, crossover and mutation operations of the chromosome code to generate offspring individuals;

[0013] The offspring individuals are iterated, the best individual is selected, and decoding is performed to obtain a final matching solution.

[0014] Specifically, in the step of "obtaining input data", the input data specifically includes the following data: the material demand point information includes a list of the number of wounded persons with different injury levels at each material demand point; the transport vehicle information characteristics include quantity, rated load, average speed, and cruising range; the location information includes a list of latitude and longitude information of material centers, material demand points, and gas stations.

[0015] Specifically, in the step of "determining the chromosome encoding rule according to the input data", the chromosome is simulated by a sequence, and the length of the chromosome sequence is the longitude and latitude of the material center + the longitude and latitude of the required emergency material point + the longitude and latitude of the gas station, that is, m+n+1, where n represents the number of demand points, and m represents the number of gas stations; the corresponding number of the material center is 0, the corresponding number of the emergency material demand point is 1 to n, and the corresponding number of the gas station is n+1 to n+m; the chromosome encoding rule of the number of wounded at different levels at the material demand point specifically includes: the corresponding number of the material center is 0, and the number of wounded at each required emergency material point with moderate and severe injuries is [A 1 , A 2 , A 3 ......A n ] and [B 1 , B 2 , B 3 ......B n ], the number of gas stations is 0.

[0016] Specifically, in the step of "determining the chromosome encoding rule according to the input data", it also includes generating a corresponding Boolean matrix according to the input data according to the cruising range and rated load limit condition rules, including a three-dimensional matrix of material scheduling tasks matching transport vehicles, transport routes and transport costs; this step is subject to the constraints of vehicle cruising range, vehicle rated load, the number of transport vehicles in the emergency material distribution center, and the transport task starting and ending at the material center;

[0017] The vehicle driving range constraint means: ensuring that the remaining fuel volume of the transport vehicle is greater than zero when it reaches each point on its delivery route;

[0018] The vehicle rated load constraint means that each transport vehicle has a maximum load limit, and the total weight of the transported goods arranged by the material center for it shall not exceed its rated load;

[0019] The quantity constraint of the transport vehicles of the emergency material distribution center means that the material center has a certain number of transport vehicles, and the total number of transport vehicles used in the material distribution plan shall not be greater than the total number of transport vehicles owned by the logistics distribution center.

[0020] Specifically, in the step of "using the objective function to perform constraint processing and specify the fitness function", the objective function takes into account the transportation cost and the personal injury cost, namely the mortality cost. The evolution characteristics of the wounded's condition in the mortality cost conform to the Markov process's no aftereffect property, and the injury evolution process is discretized into three finite-state Markov processes: moderate injury, serious injury and death. The evolution process ends when the wounded dies or the emergency supplies are delivered to the wounded. The inverse of the objective function is taken as the fitness function.

[0021] Specifically, in the step of "using the objective function to perform constraint processing and specify the fitness function", it also includes preprocessing the chromosome encoding before calculating the fitness function. The preprocessing process is to adjust the chromosome encoding according to the three-dimensional Boolean matrix so that any chromosome encoding after preprocessing satisfies various constraints.

[0022] Specifically, in the step of "calculating the fitness score of each individual corresponding to the chromosome encoding in the initial matching scheme set, selecting the dominant individual according to the fitness score to perform inheritance, crossover and mutation operations of the chromosome encoding, and generating offspring individuals", roulette wheel selection is adopted to retain the best chromosome of the parent generation and replace the worst chromosome of the offspring to generate offspring individuals.

[0023] Specifically, in order to build a reasonable and effective model, this method is based on the following assumptions: the emergency material distribution center has several transport vehicles of a single type; the material center has a large material storage capacity, and each rescue station can be satisfied with the number of emergency materials; the fuel tank of the transport vehicle is full before departure; the driving speed of the transport vehicle is constant; factors such as bad weather, vehicle breakdown, and road congestion during the distribution process are not considered; the demand for each demand point is constant and known; the demand for emergency materials by the wounded is related to the injury. The more serious the injury, the more materials are needed; when the materials are delivered to the rescue station, the wounded can receive treatment and their injuries will improve; the material flow is one-way, and pure distribution does not bring return materials; the location coordinates of the material center and the demand points are known; each transport vehicle can deliver materials to multiple demand points, but each demand point can only be delivered by a single vehicle; each vehicle departs from the emergency logistics distribution center and returns to the starting point after delivering the materials.

[0024] The second aspect of the present invention proposes an intelligent allocation system for emergency materials taking into account the random deterioration of injuries, comprising a data acquisition module, a rule determination module, a coding module, a fitness score calculation module, and an iteration module connected in sequence; wherein:

[0025] The data acquisition module is used to acquire input data, and the input data includes information of each material demand point, transportation vehicle information, and location information;

[0026] The rule determination module is used to determine the chromosome encoding rule according to the input data;

[0027] The encoding module is used to randomly generate a number of chromosome codes from the input data according to the chromosome encoding rule to obtain an initial matching solution set of tasks, vehicles and paths;

[0028] The fitness score calculation module is used to calculate the fitness score of each individual corresponding to the chromosome code in the initial matching scheme set, and select the dominant individual according to the fitness score to perform the crossover and mutation operations of the chromosome code to generate offspring individuals;

[0029] The iteration module is used to iterate the offspring individuals, select the best individual, and decode to obtain a final matching solution.

[0030] According to a third aspect of the present invention, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned intelligent optimization method for emergency material scheduling paths taking into account random deterioration of injuries are implemented.

[0031] The remarkable effects of the present invention are:

[0032] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method, system and storage medium for intelligent optimization of emergency material dispatch paths that take into account the random deterioration of injuries. Based on the Markov process, the evolution law of the wounded's injuries is characterized, and a method is constructed with the minimum sum of mortality rates as the goal. The rated load and fuel consumption of the vehicle are considered, and a genetic algorithm is used to simulate the genetic evolution process of organisms to find a better path from the material center to each material demand point, that is, to find a relatively excellent dispatching solution. The genetic algorithm is used to solve the matching problem of tasks, vehicles, and paths in the intelligent dispatch of emergency materials. It has been verified that the matching task can be completed in a very short time, which improves the scheduling efficiency and greatly reduces the algorithm running time. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 The figure is a flow chart of the method of the present invention.

[0034] Figure 2 This is a diagram of the random evolution of the injuries of the wounded mentioned in the present invention.

[0035] Figure 3 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention.

[0037] First, an embodiment of the present invention discloses an intelligent optimization method for dispatching emergency materials taking into account the random deterioration of injuries, such as Figure 1 As shown, the specific steps include:

[0038] S1. Obtain input data. The input data includes information about each material demand point, transportation vehicles, and location information. In order to describe the model more clearly and accurately, the symbols used in the model are defined as follows:

[0039] N: The required emergency supplies collection point;

[0040] K: the set of transport vehicles, with the subscript k representing it;

[0041] M: Meet at the gas station;

[0042] O: Material center, subscript is represented by o;

[0043] V: a collection of demand points, gas stations, material centers, etc., with the subscript v, denoted by V = N∪MUO;

[0044] C: Transportation cost per unit distance of transportation vehicle distribution; d ij: The distance from point i to point j on the earth's spherical surface, i, j∈V;

[0045] A i :Demand point i is in neutral (L 2 ) of the injured, i∈N;

[0046] B i :Demand point i is seriously injured (L 1 ) of the injured, i∈N;

[0047] q i : The demand quantity at demand point i, q i =2*A i +3*B i , i∈N;

[0048] Q: Rated load of the transport vehicle;

[0049] P: The cruising range of the transport vehicle when fully fueled;

[0050] speed: the speed of the transport vehicle during the delivery process;

[0051] dpu: the penalty value per unit time for the transport vehicle to cause the injury to worsen;

[0052]

[0053] S2. Determine the chromosome encoding rules based on the input data. In genetic algorithms, chromosomes are usually simulated by a digital sequence. In the actual application of the matching algorithm, the length of the chromosome sequence is: the longitude and latitude of the material center + the longitude and latitude of the required emergency material point + the longitude and latitude of the gas station, that is, m+n+1, where n represents the number of demand points and m represents the number of gas stations. The corresponding number of the material center is 0, the corresponding number of the emergency material demand point is 1 to n, and the corresponding number of the gas station is n+1 to n+m; (2) The chromosome encoding rules for the number of wounded at different levels of material demand points specifically include: the corresponding number of the material center is 0, and the number of wounded at each required emergency material point with moderate and severe injuries is [A 1 , A 2 , A 3 ......A n ] and [B 1 , B 2 , B 3 ......B n ], and the gas station is 0. The coding sample table is as follows:

[0054]

[0055]

[0056] This method is subject to the vehicle's mileage, the vehicle's rated load, the number of transport vehicles in the emergency material distribution center, and the transportation task starting and ending at the material center. The constraints of the chromosome sequence are analyzed as follows:

[0057] (1) Vehicle driving range constraints

[0058] Ensure that the remaining fuel of the transport vehicle is greater than zero when it arrives at each point on its delivery route. The mileage constraint of the transport vehicle can be expressed in mathematical form as:

[0059]

[0060] (2) Rated load capacity constraints of transport vehicles

[0061] Each transport vehicle has a maximum load limit, and the total weight of the transported goods arranged by the material center must not exceed its rated load. The rated load constraint of electric vehicles can be expressed as:

[0062]

[0063] (3) Constraints on the number of vehicles transporting goods to the material center

[0064] The material center has a certain number of transport vehicles, and the total number of transport vehicles used in the material distribution plan must not be greater than the total number of transport vehicles owned by the logistics distribution center. The number constraint of the transport vehicles of the logistics distribution center can be expressed as:

[0065]

[0066] (4) The transportation task is constrained by the material center as the starting point and end point

[0067] The transportation task with the material center as the starting point and end point constraints can be expressed as:

[0068]

[0069] S3. According to the chromosome encoding rules, the input data is randomly generated into several chromosome codes to obtain an initial matching solution set of vehicles, tasks, and paths;

[0070] S4. Use the objective function to perform constraint processing and specify the fitness function.

[0071] The first step is to construct the objective function. The objective function takes into account the transportation cost and personal injury cost (mortality rate), and the material distribution cost is composed of only two aspects: the transportation cost of distribution and the penalty cost.

[0072] (1) Vehicle delivery costs

[0073] The transportation cost of a vehicle increases with the distance it travels. It can be considered that the transportation cost of a vehicle is proportional to the mileage it travels. tr It can be expressed as:

[0074]

[0075] (2) Penalty Cost

[0076] The transport vehicle's mileage, rated load limit and minimum mortality rate are processed in the form of a penalty function, and the resulting objective function is:

[0077]

[0078] The coefficients C and M in the above formula are 1 、M 2 、M 3 They are all positive constants and can be adjusted according to the model.

[0079] Since all three constraints must be satisfied, C, M 1 、M 2 、M 3 Taking a large positive number can maximize the objective function value of the chromosome that does not meet the constraints.

[0080] Among them, the mortality cost of the random evolution process of the wounded's condition is based on the Markov process's lack of aftereffect. Figure 2 As shown:

[0081] In L 1 The wounded in the state may die of P per minute while waiting for emergency supplies to arrive. 1D The probability of death is P 11 The probability of maintaining L 1 state, at this time P 1D +P 11 =1. Similarly, for L 2 The wounded in the state may be P per minute. 21 The probability of evolving to state L 1 , with P 22 The probability is L 2 state, at this time, P 22 +P 21 = 1. Assuming that the degree of deterioration of the injury before the injured person receives treatment is linearly related to time, the initial injury state is L 1 The probability of death of the injured j is expressed as:

[0082]

[0083] in is the time it takes for emergency vehicle k to deliver supplies to demand point i, Z j Indicates the initial injury status of the casualty.

[0084] if When it is greater than 1, the wounded will die while waiting. Therefore, this paper uses the min function to represent the probability that a seriously injured person may die while waiting for supplies, that is,

[0085]

[0086] When Z j =L 2 According to the evolution of the injury, the wounded first 2 Evolved to serious injury L 1 , and finally evolves into state D. Therefore, when calculating the probability of death of the wounded, we first determine whether the wounded is L 2 Completely evolved to L 1 At the moment T. Figure 2 It can be seen that the state L 2 To L 1 The transition probability per unit time is P 21 Let P 21 *T=1, then L 2 Evolved into L 1 The time T = 1 / P 21 When emergency supplies arrive When the wounded person's condition has not evolved to death, the probability of death is 0. When , the probability of death in this state Therefore, the death probability function in this state is a time-division function, that is,

[0087]

[0088] Step 2: The sum of the survival probabilities of all the wounded represents the expected number of survivors. The larger the sum of the probabilities, the more expected survivors. The sum of the death probabilities of all the wounded represents the expected number of deaths. The smaller the sum of the probabilities, the smaller the expected number of deaths. The sum of the death probabilities of all the wounded at demand point i is expressed as:

[0089]

[0090] According to the above analysis, the sum of the death probabilities of the injured at all demand points is expressed as:

[0091]

[0092] in It depends on the initial condition of the casualty and how long the casualty has to wait for emergency supplies.

[0093]

[0094] The function expression of penalty cost is as follows:

[0095] pu=F*dpu

[0096] The third step is to define the fitness function. The larger the fitness function is required to be, the better, so the inverse of the above objective function is taken as the fitness function, that is, the fitness function is: fit(i) = 1 / z.

[0097] Based on the above assumptions and parameter definitions, the established mathematical model is:

[0098]

[0099] T ij =d ij / speed

[0100]

[0101] S5. Calculate the fitness score of each individual corresponding to the chromosome code in the initial matching solution set, use the roulette method to select the dominant individual according to the fitness score to perform crossover and mutation operations on the chromosome code, and replace the worst chromosome of the offspring to generate the offspring individual.

[0102] S6. Iterate the offspring individuals, select the best individual, and decode it to obtain the final matching solution.

[0103] The evolutionary iteration process in this embodiment is as follows: first, according to the established chromosome encoding rules, a certain number of individuals are generated as the initial group, the fitness score of each individual is calculated, and the dominant individual is selected by weight according to the fitness score, and the chromosome encoding is subjected to random crossover and mutation operations to obtain the chromosome encoding of the next generation of individuals; after a certain number of iterations, the chromosome encoding of the optimal individual is decoded and restored to the actual problem parameters, that is, the correspondence between maintenance personnel, maintenance tasks and ships, that is, which teams are on a ship, who are in each team, and which tasks are completed, and output.

[0104] Chromosome crossing over refers to the random fusion process of two chromosomes, and chromosome mutation means that there is a certain probability (usually less than 2%) that part of the digital sequence will be replaced by a random value that complies with the chromosome encoding rules to reduce the possibility of the algorithm falling into a local optimum.

[0105] Then, the embodiment of the present invention also discloses an intelligent allocation system for emergency supplies taking into account the random deterioration of injuries, such as Figure 3As shown, it includes a data acquisition module, a rule determination module, an encoding module, a fitness score calculation module, and an iteration module connected in sequence; wherein:

[0106] A data acquisition module is used to acquire input data, wherein the input data includes information of each material demand point, transportation vehicle information, and location information;

[0107] A rule determination module, used for determining chromosome encoding rules according to input data;

[0108] The encoding module is used to randomly generate a number of chromosome codes from the input data according to the chromosome encoding rules to obtain an initial matching solution set of vehicles, tasks, and paths;

[0109] The fitness score calculation module is used to calculate the fitness score of each individual corresponding to the chromosome code in the initial matching scheme set, select the dominant individual according to the fitness score to perform the crossover and mutation operations of the chromosome code, and generate the offspring individual;

[0110] The iteration module is used to iterate the offspring individuals, select the best individual, and decode it to obtain the final matching solution.

[0111] Finally, an embodiment of the present invention provides a computer storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned intelligent optimization method for emergency material dispatching paths taking into account the random deterioration of injuries are implemented.

[0112] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0113] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent optimization method for emergency material dispatching paths considering random deterioration of injuries, characterized in that: The specific steps include: Obtaining input data, wherein the input data includes information of each material demand point, transportation vehicle information, and location information; Determine chromosome encoding rules according to the input data; According to the chromosome encoding rule, the input data is randomly generated into a plurality of chromosome encodings to obtain an initial matching solution set of vehicles, tasks, and paths; Use objective functions to handle constraints and specify fitness functions; Calculate the fitness score of each individual corresponding to the chromosome code in the initial matching scheme set, select the dominant individual according to the fitness score to perform the inheritance, crossover and mutation operations of the chromosome code to generate offspring individuals; The offspring individuals are iterated, the best individual is selected, and decoding is performed to obtain a final matching solution.

2. According to claim 1, an intelligent optimization method for emergency material dispatching paths considering random deterioration of injuries is characterized in that: In the step of "obtaining input data", the input data specifically includes the following data: the material demand point information includes a list of the number of injured persons at different injury levels at each material demand point; the transport vehicle information characteristics include quantity, rated load, average speed, and cruising range; the location information includes a list of latitude and longitude information of material centers, material demand points, and gas stations.

3. According to claim 1, the intelligent optimization method for emergency material dispatching paths considering the random deterioration of injuries is characterized in that: In the step of "determining the chromosome encoding rule according to the input data", the chromosome is simulated by a sequence, and the length of the chromosome sequence is the longitude and latitude of the material center + the longitude and latitude of the required emergency material point + the longitude and latitude of the gas station, that is, m+n+1, where n represents the number of demand points and m represents the number of gas stations; the material center corresponds to 0, the emergency material demand point corresponds to 1 to n, and the gas station corresponds to n+1 to n+m; The chromosome coding rules for the number of wounded at different levels at the material demand point include: the corresponding number of the material center is 0, and the number of wounded with moderate and severe injuries at each required emergency material point is [A1, A2, A3...A n ] and [B1, B2, B3...B n ], the number of gas stations is 0.

4. According to claim 3, the intelligent optimization method for emergency material dispatching paths considering the random deterioration of injuries is characterized in that: It also includes generating a corresponding Boolean matrix according to the input data according to the mileage and rated load restriction rules, including a three-dimensional matrix of the material dispatch task matching the transport vehicle, the transport route and the transport cost; this step is subject to the constraints of the vehicle's mileage, the vehicle's rated load, the number of transport vehicles in the emergency material distribution center, and the transport task starting and ending at the material center; The vehicle driving range constraint means: ensuring that the remaining fuel volume of the transport vehicle is greater than zero when it reaches each point on its delivery route; The vehicle rated load constraint means that each transport vehicle has a maximum load limit, and the total weight of the transported goods arranged by the material center for it shall not exceed its rated load; The quantity constraint of the transport vehicles of the emergency material distribution center means that the material center has a certain number of transport vehicles, and the total number of transport vehicles used in the material distribution plan shall not be greater than the total number of transport vehicles owned by the logistics distribution center.

5. According to claim 1, the intelligent optimization method for emergency material dispatching paths considering random deterioration of injuries is characterized in that: In the step of "using the objective function to perform constraint processing and specifying the fitness function", the objective function takes into account the transportation cost and the personal injury cost, namely the mortality cost. The characteristics of the evolution of the wounded's condition in the mortality cost conform to the Markov process's no aftereffect property, and the injury evolution process is discretized into three finite-state Markov processes: moderate injury, severe injury and death. When the wounded dies or the emergency supplies are delivered to the wounded, the evolution process ends. The inverse of the objective function is taken as the fitness function.

6. According to claim 5, the intelligent optimization method for emergency material dispatching paths considering the random deterioration of injuries is characterized in that: It also includes preprocessing the chromosome code before calculating the fitness function, wherein the preprocessing process is to adjust the chromosome code according to the three-dimensional Boolean matrix so that any chromosome code after preprocessing satisfies various restriction conditions.

7. According to claim 1, the intelligent optimization method for emergency material dispatching paths considering random deterioration of injuries is characterized in that: In the step of "calculating the fitness score of each individual corresponding to the chromosome code in the initial matching scheme set, selecting the dominant individual according to the fitness score to perform the inheritance, crossover and mutation operations of the chromosome code to generate offspring individuals", the offspring individuals are generated by adopting a roulette wheel selection method to retain the best chromosome of the parent generation and replace the worst chromosome of the offspring.

8. According to claim 1, the intelligent optimization method for emergency material dispatching paths considering the random deterioration of injuries is characterized in that: This method is based on the following assumptions: the emergency material distribution center has several transport vehicles of a single type; the material center has a large material storage capacity, and each rescue station can be satisfied with the number of emergency materials; the fuel tank of the transport vehicle is full before departure; the speed of the transport vehicle is constant; factors such as bad weather, vehicle failure, and road congestion during the distribution process are not considered; the demand for each demand point is constant and known; the demand for emergency materials by the wounded is related to the injury, and the more serious the injury, the more materials are needed; when the materials are delivered to the rescue station, the wounded can be treated and their injuries will improve; the material flow is one-way, and pure distribution does not bring return materials; the location coordinates of the material center and the demand point are known; Each transport vehicle can deliver supplies to multiple demand points, but each demand point can only be delivered by a single vehicle; each vehicle departs from the emergency logistics distribution center and returns to the starting point after delivering the supplies.

9. An intelligent emergency material allocation system that takes into account the random deterioration of injuries, characterized in that: It includes a data acquisition module, a rule determination module, an encoding module, a fitness score calculation module, and an iteration module connected in sequence; wherein: The data acquisition module is used to acquire input data, and the input data includes information of each material demand point, transportation vehicle information, and location information; The rule determination module is used to determine the chromosome encoding rule according to the input data; The encoding module is used to randomly generate a number of chromosome codes from the input data according to the chromosome encoding rule to obtain an initial matching solution set of tasks, vehicles and paths; The fitness score calculation module is used to calculate the fitness score of each individual corresponding to the chromosome code in the initial matching scheme set, and select the dominant individual according to the fitness score to perform the crossover and mutation operations of the chromosome code to generate offspring individuals; The iteration module is used to iterate the offspring individuals, select the best individual, and decode to obtain a final matching solution.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent optimization method for emergency material dispatching paths taking into account random deterioration of injuries as described in any one of claims 1 to 8.

Images