A method and system for optimizing emergency resource scheduling based on resource scheduling graph

Abstract

The present application provides an emergency resource scheduling optimization method and system based on a resource scheduling graph, which converts the emergency resource scheduling problem into a graph model for deduction, and combines the optimization method of an enhanced rolling horizon evolutionary algorithm to generate an emergency resource scheduling plan; realizes online deduction of key elements of emergency resource scheduling through a resource scheduling graph model, and realizes partial visualization functions; uses a rolling horizon evolutionary algorithm for deduction to ensure the diversity of the population, enhance the accuracy of the evolutionary algorithm's individual evaluation, and expand the search space and accuracy of the optimization method.

Description

Technical Field

[0001] The present application relates to the technical field of emergency resource scheduling, and specifically to an emergency resource scheduling optimization method and system based on a resource scheduling map. Background Art

[0002] Emergency resource dispatch is an important part of emergency management, especially after a public emergency occurs. It is a key step in realizing the value of rescue, and is a special logistics activity that aims to ensure the rational and efficient use of emergency resources to meet the needs of materials and personnel, so as to respond quickly and effectively to various emergencies and provide emergency support, which is characterized by complex situations and high timeliness.

[0003] Emergency resource dispatch usually includes several material points and accident points, vehicles, personnel units and other elements. The supply of materials to the accident point can be one-way supply, that is, only one accident point is supplied at a time, or it can be non-one-way supply, that is, multiple accident points are supplied at a time. The real-time road and other road restrictions must also be considered when transporting people and materials by vehicles.

[0004] Existing emergency resource scheduling optimization methods mostly use traditional mathematical methods or single-objective evolutionary algorithms, but they have the disadvantage of poor solution results when dealing with problems with large data volumes, high computational complexity, and diverse objectives. Although some advanced algorithms use evolutionary algorithms, they may have problems such as incomplete coverage of resource scheduling elements and inaccurate algorithm deduction. Summary of the invention

[0005] In view of this, in order to solve the above-mentioned problems in the prior art, the present application proposes an emergency resource scheduling optimization method based on a resource scheduling graph.

[0006] This application solves the above problems through the following technical means:

[0007] The first aspect of the present application provides an emergency resource scheduling optimization method based on a resource scheduling map.

[0008] The steps include:

[0009] Step S100: Acquire emergency resource scheduling data and determine resource scheduling targets;

[0010] Step S200: construct an emergency resource scheduling graph model using knowledge graph technology, and set initialization conditions for the emergency resource scheduling graph model according to the emergency resource scheduling data;

[0011] Step S300: The emergency resource scheduling graph model is used as a forward model and integrated into the rolling horizon evolutionary algorithm to solve the resource scheduling target, continuously iterate and optimize, and generate the optimal emergency resource scheduling solution for a specific scenario.

[0012] Preferably, the emergency resource dispatch data obtained includes operation unit data and map unit data, and both the operation unit data and the map unit data include data resource type, data resource quantity, and data resource location; wherein the operation unit data includes vehicle data and personnel data, and the map unit data includes material data, accident point data, gas station data, material data, road node data, and road data.

[0013] Preferably, the method of using the emergency resource scheduling graph model as a forward model of a rolling horizon evolutionary algorithm comprises:

[0014] The initialization parameters of the rolling horizon evolutionary algorithm include the number of iterations, the number of individuals in the population, PopSize, and the forward model time T. forward , the number of individual actions L;

[0015] The objective function of the forward model is set to

[0016] s t represents the current state of the forward model, and A represents each operating unit in the current state s t The action performed, k represents k operable units, each of which performs its own action a, s t+1 Represents the forward model prediction at the current state s t Each operation unit performs action A for a period of time T forward After the status.

[0017] Preferably, the method of using the emergency resource scheduling graph model as a forward model of a rolling horizon evolutionary algorithm to solve the resource scheduling target and generate an optimal resource scheduling solution comprises the following steps:

[0018] Step S301, initialization process: using random methods and specific rules to initialize individuals Ind, and thus forming an initial population Pop;

[0019] Step S302, fitness evaluation: calculate the fitness value J(θ) of each individual Ind in the population Pop;

[0020] Step S303, individual sorting: sorting the individuals Ind in the population Pop from high to low according to the fitness value J(θ);

[0021] Step S304, genetic operation: performing genetic operations such as selection, crossover and mutation on the population Pop to generate a descendant population Pop′;

[0022] Step S305, population merging and updating: merging the parent population Pop and the child population Pop′ to form a new population Pop, the size of the new population is consistent with the parent population Pop;

[0023] Step S306, iteration judgment: check whether the number of optimization iterations currently executed is equal to or greater than the preset number of iterations, if so, go to step S307; if not, return to step S302 to continue the optimization process;

[0024] Step S307, executing the first action: in the current population Pop, identifying the individual Ind with the highest fitness value as the best individual, analyzing the scheduling sequence of the best individual Ind, finding the first scheduling action that has not been executed and executing it;

[0025] Step S308, target satisfaction judgment: judge whether the resource scheduling target has been achieved, if it has been met, output the emergency resource scheduling plan; if not, go to step S309;

[0026] Step S309, waiting time judgment: check whether the waiting time is equal to or greater than the forward model time T forward If yes, go to step S310; if no, return to step S307 to continue to execute the scheduling action;

[0027] Step S310, model update: update the emergency resource scheduling graph model, retain the elite individuals of the population, and return to step S301 to start the next round of optimization cycle.

[0028] Preferably, the method of initializing the individual Ind using a random method and a specific rule to form an initial population Pop comprises the following steps:

[0029] Determine whether this initialization is the first initialization, if yes, proceed to step S3011, otherwise jump to step S3012;

[0030] Step S3011, based on the NSGA-II algorithm, a random method is used to initialize random individuals Ind, accounting for 80% of the total number of the population; combined with the existing plan model, the plan-generated individuals Ind are initialized, accounting for 10% of the total number of the population; the remaining artificial individuals Ind are initialized by artificial means, accounting for 10% of the total number of the population; the random individuals Ind, the plan-generated individuals Ind and the artificial individuals Ind are merged to form a final population Pop, in which the individual ratio complies with the ratio rule of 8:1:1, and the initialization is completed;

[0031] Step S3012, determine the number of elite individuals Ind to be retained, calculate the number of remaining individuals Ind that need to be initialized based on the difference between the number of elite individuals Ind and the total number of individuals in the preset population PopSize, initialize the remaining individuals Ind using a random method, merge the retained elite individuals Ind with the newly initialized remaining individuals Ind to form the final population Pop.

[0032] Preferably, the step of calculating the fitness value J(θ) of each individual Ind in the population Pop comprises:

[0033] Use the emergency resource scheduling graph model as the forward model for individual evaluation to deduce the final state s of individual Ind t ′, the final state s t ′ means that all accident point requirements have been met or all actions have been completed; T(s t ′-s t ) represents the starting state s t To the final state s t 'The time required;

[0034] Fitness value

[0035] Preferably, performing genetic operations such as selection, crossover and mutation on the population Pop to generate a progeny population Pop′ comprises:

[0036] Selection operation: Use elite selection and index sorting selection strategies to select the population Pop. The top three best individuals Ind are copied to the next generation intact, and the remaining individuals are selected by index sorting to assign survival probabilities to the sorted individuals.

[0037] P(i) represents the survival probability of the i-th individual, c is a constant greater than 1, N is the size of the current population, and i is the sequence number of the individual currently considered after sorting;

[0038] Crossover and mutation operations: Use the adaptive adjustment strategy of the Chaos Gray Wolf Optimization Algorithm to dynamically change the crossover rate and mutation rate, and determine the control parameter value by calculating and comparing the individual fitness value J(θ) and the average fitness value of the population;

[0039]

[0040] a i is the current control parameter value of the individual, a max is the maximum value of the control parameter, a min is the minimum value of the control parameter, J i represents the current fitness value of the individual, J avgRepresents the average fitness value of the current group, J min Indicates the minimum fitness value of the current population.

[0041] The second aspect of the present application provides an emergency resource scheduling optimization system based on a resource scheduling map, including:

[0042] Determine the module, used to obtain emergency resource scheduling data and determine resource scheduling targets;

[0043] A modeling module, which uses knowledge graph technology to build an emergency resource scheduling graph model, and sets initialization conditions for the emergency resource scheduling graph model according to the emergency resource scheduling data;

[0044] The optimization module is used to integrate the emergency resource scheduling graph model as a forward model into the rolling horizon evolutionary algorithm, perform solution operations on the resource scheduling target, continuously iterate and optimize, and generate the optimal emergency resource scheduling solution for a specific scenario.

[0045] A third aspect of the present application provides a computer device, comprising a processor and a memory, wherein the memory is used to store executable instructions, and the instructions are used to control the processor to execute any method described in any one of the first aspects of the present application.

[0046] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the methods described in the first aspect of the present application.

[0047] Compared with the prior art, the beneficial effects of this application include at least:

[0048] The present application provides an emergency resource scheduling optimization method based on a resource scheduling graph, which converts the emergency resource scheduling problem into a graph model for deduction, and combines the optimization method of an enhanced rolling horizon evolutionary algorithm to generate an emergency resource scheduling plan; realizes online deduction of key elements of emergency resource scheduling through a resource scheduling graph model, and realizes partial visualization functions; uses a rolling horizon evolutionary algorithm for deduction to ensure the diversity of the population, enhance the accuracy of the evolutionary algorithm's individual evaluation, and expand the search space and accuracy of the optimization method. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1It is a schematic diagram of an emergency resource scheduling process based on a resource scheduling map provided in an embodiment of the present application;

[0051] Figure 2 This is a flow chart of a rolling horizon evolutionary algorithm generating an optimal resource scheduling solution provided by an embodiment of the present application;

[0052] Figure 3 It is a schematic diagram of a forward model flow provided in an embodiment of the present application;

[0053] Figure 4 It is a schematic diagram of an emergency resource scheduling graph model provided in an embodiment of the present application;

[0054] Figure 5 This is an individual Ind deduction final state s provided in the embodiment of the present application t 'flow chart;

[0055] Figure 6 This is a schematic diagram of a visual display of an optimal resource scheduling solution provided in an embodiment of the present application;

[0056] Figure 7 It is a structural diagram of an emergency resource scheduling optimization system based on a resource scheduling map provided in an embodiment of the present application;

[0057] Figure 8 It is a structural diagram of an emergency resource scheduling optimization computer device based on a resource scheduling map provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be pointed out that the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0059] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0060] Technical terms involved in this application:

[0061] The Rolling Horizon Evolutionary Algorithm (RHEA) is an evolutionary algorithm specifically designed to handle time series data and dynamic optimization problems. It is able to make decisions based on the latest information and environmental status in each time step, so as to better adapt to changing situations. RHEA adopts a rolling planning strategy to decompose long-term planning problems into a series of short-term sub-problems. This approach allows the algorithm to re-optimize future plans in each time step to cope with emerging information and changing environmental conditions. RHEA can take advantage of parallel computing because the population evaluation and selection operations in its evolutionary process can be performed independently. This makes the algorithm have the potential for efficient execution in high-performance computing environments. As an evolutionary algorithm, RHEA is based on swarm intelligence and genetic operations, and is able to explore multiple solutions in the search space and gradually approach the global optimal solution through operations such as selection, crossover, and mutation. RHEA can be combined with various models and applications, including simulators, predictive models, and actual systems to solve optimization problems in various fields, such as emergency resource scheduling, path planning, energy management, etc. RHEA gradually improves the solution in each time step instead of seeking the global optimal solution at one time. This incremental approach can provide feasible and continuously optimized decisions within limited computing time.

[0062] Embodiment 1

[0063] The present application provides an emergency resource scheduling optimization method based on a resource scheduling map, comprising the following steps:

[0064] Step S100: Acquire emergency resource scheduling data and determine resource scheduling targets;

[0065] Step S200: construct an emergency resource scheduling graph model using knowledge graph technology, and set initialization conditions for the emergency resource scheduling graph model according to the emergency resource scheduling data;

[0066] Step S300: The emergency resource scheduling graph model is used as a forward model and integrated into the rolling horizon evolutionary algorithm to solve the resource scheduling target, continuously iterate and optimize, and generate the optimal emergency resource scheduling solution for a specific scenario.

[0067] Preferably, the emergency resource dispatch data obtained includes operation unit data and map unit data, and both the operation unit data and the map unit data include data resource type, data resource quantity, and data resource location; wherein the operation unit data includes vehicle data and personnel data, and the map unit data includes material data, accident point data, gas station data, material data, road node data, and road data.

[0068] Specifically, the operation unit data includes:

[0069] Vehicle unit, representing V1, V2, ..., V x1 , x1 is the total number of vehicle units, for each vehicle unit V = (c, f, m), c represents the vehicle type, f represents the real-time remaining fuel, and m represents the real-time total weight.

[0070] Personnel units are represented by P1, P2, ..., P x2 , x2 is the total number of personnel units, for each personnel unit P = (c, n), c represents the personnel type, and n represents the number.

[0071] Materials can overlap with vehicle units, which means the vehicle unit is loaded with the materials; personnel units can overlap with vehicles, which means the personnel units are riding in the vehicle unit.

[0072] Executable actions

[0073] V represents the number of vehicle units, P represents the number of personnel units, and a 1V ,......,a kV is the executable action of the Vth vehicle unit, a 1P ,......,a zP is the executable action of the Pth personnel unit, a is the potential executable action of the operation unit, and if the vehicle unit V is a car, there is no loading and unloading action.

[0074] Specifically, map unit data includes:

[0075] A single accident point can be expressed as: accident point E = (n1, n2, ..., nz , m1, m2, ..., m p ), n1, n2, ..., n z Represents the quantity of z kinds of materials required, m1, m2, ..., m p represents the number of p types of personnel required; if there are multiple accident points, they are represented as E1, E2, ..., E x3 , x3 is the total number of accident points.

[0076] Gas stations are represented by F1, F2, ..., F x4 , x4 is the total number of gas stations, and for each gas station F = (f), f represents the remaining fuel inventory.

[0077] Materials are represented by S1, S2, ..., S x5 , x5 is the total number of materials, for each material S = (c, n, t), c represents the material type, n represents the quantity, and t represents the time required for loading and unloading. Materials can exist in multiple locations at the same time, indicating that there are different types of materials at the location.

[0078] Road nodes are represented by N1, N2, ..., N x6 , x6 is the total number of accident points, for each road node N = (x, y), x, y represent the coordinate axes of the road node on the emergency resource scheduling map.

[0079] Roads are represented by R1, R2, ..., R x7 , x7 is the total number of accident points, for each road R = (d, v, r h , r m , Info), d represents the road travel length, v represents the real-time average speed of vehicles on the road, r h Represents height limit, r m represents weight limit, Info represents multiple information points info1, info2, .... info = (d, V / P / E / S ...), d represents the distance from the information point to the previous road node, V / P / E / S ... represent specific information points, such as vehicle units, personnel units, etc.

[0080] Preferably, the method of using the emergency resource scheduling graph model as a forward model of a rolling horizon evolutionary algorithm comprises:

[0081] The initialization parameters of the rolling horizon evolutionary algorithm include the number of iterations, the number of individuals in the population, PopSize, and the forward model time T. forward , the number of individual actions L;

[0082] The objective function of the forward model is set to

[0083] s t represents the current state of the forward model, and A represents each operating unit in the current state s t The action performed, k represents k operable units, each of which performs its own action a, s t+1 Represents the forward model prediction at the current state s t Each operation unit performs action A for a period of time T forward After the status.

[0084] Specifically, the forward model time T forward , represents the previous state s in the forward model t With the next state s t The time interval between ′, such as Figure 3 As shown. The number of iterations, the number of individuals in the population PopSize, and the forward model time T forward , the number of individual actions L is pre-set according to the map size and task complexity. Forward model time T forward The default setting is 20 minutes, and the default setting for the population PopSize is 100.

[0085] Preferably, the method of using the emergency resource scheduling graph model as a forward model of a rolling horizon evolutionary algorithm to solve the resource scheduling target and generate an optimal resource scheduling solution comprises the following steps:

[0086] Step S301, initialization process: using random methods and specific rules to initialize individuals Ind, and thus forming an initial population Pop;

[0087] Step S302, fitness evaluation: calculate the fitness value J(θ) of each individual Ind in the population Pop;

[0088] Step S303, individual sorting: sorting the individuals Ind in the population Pop from high to low according to the fitness value J(θ);

[0089] Step S304, genetic operation: performing genetic operations such as selection, crossover and mutation on the population Pop to generate a descendant population Pop′;

[0090] Step S305, population merging and updating: merging the parent population Pop and the child population Pop′ to form a new population Pop, the size of the new population is consistent with the parent population Pop;

[0091] Step S306, iteration judgment: check whether the number of optimization iterations currently executed is equal to or greater than the preset number of iterations, if so, go to step S307; if not, return to step S302 to continue the optimization process;

[0092] Step S307, executing the first action: in the current population Pop, identifying the individual Ind with the highest fitness value as the best individual, analyzing the scheduling sequence of the best individual Ind, finding the first scheduling action that has not been executed and executing it;

[0093] Step S308, target satisfaction judgment: judge whether the resource scheduling target has been achieved, if it has been met, output the emergency resource scheduling plan; if not, go to step S309;

[0094] Step S309, waiting time judgment: check whether the waiting time is equal to or greater than the forward model time T forward If yes, go to step S310; if no, return to step S307 to continue to execute the scheduling action;

[0095] Step S310, model update: update the emergency resource scheduling graph model, retain the elite individuals of the population, and return to step S301 to start the next round of optimization cycle.

[0096] Preferably, the method of initializing the individual Ind using a random method and a specific rule to form an initial population Pop comprises the following steps:

[0097] Determine whether this initialization is the first initialization, if yes, proceed to step S3011, otherwise jump to step S3012;

[0098] Step S3011, based on the NSGA-II algorithm, a random method is used to initialize random individuals Ind, accounting for 80% of the total number of the population; combined with the existing plan model, the plan-generated individuals Ind are initialized, accounting for 10% of the total number of the population; the remaining artificial individuals Ind are initialized by artificial means, accounting for 10% of the total number of the population; the random individuals Ind, the plan-generated individuals Ind and the artificial individuals Ind are merged to form a final population Pop, in which the individual ratio complies with the ratio rule of 8:1:1, and the initialization is completed;

[0099] Step S3012, determine the number of elite individuals Ind to be retained, calculate the number of remaining individuals Ind that need to be initialized based on the difference between the number of elite individuals Ind and the total number of individuals in the preset population PopSize, initialize the remaining individuals Ind using a random method, merge the retained elite individuals Ind with the newly initialized remaining individuals Ind to form the final population Pop.

[0100] Specifically, in the process of initializing individual Ind, the following logic is adopted:

[0101] Random individual generation: Random individuals are generated from the current population by randomly combining the genes of parent individuals. Although the performance of these individuals may be relatively poor, their large number can provide rich diversity and help avoid the algorithm from falling into a local optimal solution. Therefore, the proportion of random individuals in the population is set to 80% to make full use of their exploration capabilities.

[0102] Plan generation individuals are generated according to preset rules or conditions, with specific attributes or constraints. Such individuals are created using existing emergency plan generation models, aiming to guide the algorithm to explore specific areas in the problem space more effectively.

[0103] Elite individual generation: Elite individuals are individuals that show the best fitness in the current population and represent a higher solution quality. Since the number of elite individuals is small, they can provide the necessary stability and convergence to help the algorithm move towards the global optimal solution. In this application, elite individuals are generated manually during the first initialization to ensure that the solution has a good performance foundation in the initial stage.

[0104] Through the above logic, the initialized individual Ind set includes characteristics such as random exploration, directed search and excellent inheritance, thus taking into account diversity, convergence and performance guarantee in the optimization process.

[0105] Specifically, the individual Ind is initialized using a random method and a specific rule, and the initial population Pop is formed therefrom, which also includes the following steps:

[0106] The population is represented as Pop = Ind1, Ind2, Ind3, ..., Ind popSize , PopSize is the number of individuals in the population.

[0107] Individual Ind includes a series of action groups of operable units according to time series, which are expressed as

[0108]

[0109] A represents the actions that all operable units choose to execute at the same time, A1, A2, ..., A L It represents that all operable units have executed L steps together. represents the action a selected by each of k operable units, including vehicle unit and personnel unit (k = x1 + x2, operable unit parameter), and the action of the operating unit is a from A 可执行 Select in.

[0110] Preferably, the step of calculating the fitness value J(θ) of each individual Ind in the population Pop comprises:

[0111] Use the emergency resource scheduling graph model as the forward model for individual evaluation to deduce the final state s of individual Ind t ′, the final state s t ′ means that all accident point requirements have been met or all actions have been completed; T(s t ′-s t ) represents the starting state s t To the final state s t 'The time required;

[0112] Fitness value

[0113] Preferably, performing genetic operations such as selection, crossover and mutation on the population Pop to generate a progeny population Pop′ comprises:

[0114] Selection operation: Use elite selection and index sorting selection strategies to select the population Pop. The top three best individuals Ind are copied to the next generation intact, and the remaining individuals are selected by index sorting to assign survival probabilities to the sorted individuals.

[0115] P(i) represents the survival probability of the i-th individual, c is a constant greater than 1, N is the size of the current population, and i is the sequence number of the individual currently considered after sorting;

[0116] Crossover and mutation operations: Use the adaptive adjustment strategy of the Chaos Gray Wolf Optimization Algorithm to dynamically change the crossover rate and mutation rate, and determine the control parameter value by calculating and comparing the individual fitness value J(θ) and the average fitness value of the population;

[0117]

[0118] a i is the current control parameter value of the individual, a max is the maximum value of the control parameter, a min is the minimum value of the control parameter, J i represents the current fitness value of the individual, J avg Represents the average fitness value of the current group, J min Indicates the minimum fitness value of the current population.

[0119] Preferably, the updating of the emergency resource scheduling graph model and retaining elite individuals in the population further includes: sorting according to the fitness values ​​of the individuals Ind, selecting several individuals with the highest fitness values ​​as elite individuals, and configuring the number of elite individuals according to pre-set parameters.

[0120] The selected elite individuals are retained in the emergency resource scheduling graph model to maintain the convergence and stability of the algorithm and provide an excellent genetic basis for subsequent optimization iterations.

[0121] After the emergency resource scheduling graph model is used as a forward model and integrated into the rolling horizon evolutionary algorithm, a solution operation is performed on the resource scheduling target, and finally an optimal emergency resource scheduling plan for a specific scenario is generated, the optimal emergency resource scheduling plan is displayed in a visual manner.

[0122] refer to Figure 6 ,In a possible implementation method, the emergency resource scheduling graph model is ,integrated into the navigation map to generate a state map ,and display the key elements; the states of the best individuals ,derived by the emergency resource scheduling graph model are ,combined to generate the corresponding state map and form a short ,video

[0123] Embodiment 2

[0124] The second aspect of the present application provides an emergency resource scheduling optimization system based on a resource scheduling map, including:

[0125] Determine the module, used to obtain emergency resource scheduling data and determine resource scheduling targets;

[0126] A modeling module, which uses knowledge graph technology to build an emergency resource scheduling graph model, and sets initialization conditions for the emergency resource scheduling graph model according to the emergency resource scheduling data;

[0127] The optimization module is used to integrate the emergency resource scheduling graph model as a forward model into the rolling horizon evolutionary algorithm, perform solution operations on the resource scheduling target, continuously iterate and optimize, and generate the optimal emergency resource scheduling solution for a specific scenario.

[0128] Embodiment 3

[0129] The embodiment of the present application further provides a computer device for optimizing emergency resource scheduling based on a resource scheduling map, the device comprising:

[0130] at least one processor;

[0131] at least one memory for storing at least one program;

[0132] When the at least one program is executed by the at least one processor, the at least one processor implements the emergency resource scheduling optimization method based on the resource scheduling map described in any of the above embodiments.

[0133] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0134] Embodiment 4

[0135] The present application also provides a computer-readable storage medium, on which is stored an emergency resource scheduling optimization processing program based on a resource scheduling map. When the emergency resource scheduling optimization processing program based on the resource scheduling map is executed by a processor, the steps of the emergency resource scheduling optimization method based on the resource scheduling map as described in any of the above embodiments are implemented.

[0136] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the emergency resource scheduling optimization system based on the resource scheduling map, and uses various interfaces and lines to connect the various parts of the entire emergency resource scheduling optimization processing executable device based on the resource scheduling map.

[0137] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the emergency resource scheduling optimization processing system based on the resource scheduling map by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0138] Although the description of the present application has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims by reference to the attached claims, taking into account the prior art, so as to effectively cover the intended scope of the present application. In addition, the above description of the present application is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present application that have not yet been foreseen may still represent equivalent changes to the present application.

[0139] Compared with the prior art, the beneficial effects of this application include at least:

[0140] The present application provides an emergency resource scheduling optimization method based on a resource scheduling graph, which converts the emergency resource scheduling problem into a graph model for deduction, and combines the optimization method of an enhanced rolling horizon evolutionary algorithm to generate an emergency resource scheduling plan; realizes online deduction of key elements of emergency resource scheduling through a resource scheduling graph model, and realizes partial visualization functions; uses a rolling horizon evolutionary algorithm for deduction to ensure the diversity of the population, enhance the accuracy of the evolutionary algorithm's individual evaluation, and expand the search space and accuracy of the optimization method.

[0141] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An emergency resource scheduling optimization method based on resource scheduling graph, characterized in that: The steps include: Step S100: Acquire emergency resource scheduling data and determine resource scheduling targets; Step S200: construct an emergency resource scheduling graph model using knowledge graph technology, and set initialization conditions for the emergency resource scheduling graph model according to the emergency resource scheduling data; Step S300: Integrate the emergency resource scheduling graph model as a forward model into the rolling horizon evolutionary algorithm, perform solution calculations for the resource scheduling target, continuously iterate and optimize, and generate an optimal emergency resource scheduling solution for a preset scenario; The emergency resource scheduling graph model is used as a forward model of the rolling horizon evolutionary algorithm, including: The initialization parameters of the rolling horizon evolutionary algorithm include the number of iterations, the number of individuals in the population, PopSize, and the forward model time T. forward , the number of individual actions L; The objective function of the forward model is set to s t represents the current state of the forward model, and A represents each operating unit in the current state s t The action performed, k represents k operable units, each of which performs its own action a, s t+1 Represents the forward model prediction at the current state s t Each operation unit performs action A for a period of time T forward After the status.

2. The method for optimizing emergency resource scheduling based on resource scheduling graph according to claim 1 is characterized in that: The emergency resource dispatch data obtained includes operation unit data and map unit data, and both the operation unit data and the map unit data include data resource type, data resource quantity, and data resource location; wherein the operation unit data includes vehicle data and personnel data, and the map unit data includes material data, accident point data, gas station data, material data, road node data, and road data.

3. The method for optimizing emergency resource scheduling based on resource scheduling graph according to claim 1, characterized in that: The method uses the emergency resource scheduling graph model as a forward model of the rolling horizon evolutionary algorithm to solve the resource scheduling target and generate the optimal resource scheduling solution, including the following steps: Step S301, initialization process: using random methods and specific rules to initialize individuals Ind, and thus forming an initial population Pop; Step S302, fitness evaluation: calculate the fitness value J(θ) of each individual Ind in the population Pop; Step S303, individual sorting: sorting the individuals Ind in the population Pop from high to low according to the fitness value J(θ); Step S304: Genetic operation: Perform genetic operations of selection, crossover and mutation on the population Pop to generate the offspring population Pop. ′ ; Step S305: Population merging and updating: merge the parent population Pop and the child population Pop ′ Merge to form a new population Pop, the size of the new population is consistent with the parent population Pop; Step S306, iteration judgment: check whether the number of optimization iterations currently executed is equal to or greater than the preset number of iterations, if so, go to step S307; if not, return to step S302 to continue the optimization process; Step S307, executing the first action: in the current population Pop, identifying the individual Ind with the highest fitness value as the best individual, analyzing the scheduling sequence of the best individual Ind, finding the first scheduling action that has not been executed and executing it; Step S308, target satisfaction judgment: judge whether the resource scheduling target has been achieved, if it has been met, output the emergency resource scheduling plan; if not, go to step S309; Step S309, waiting time judgment: check whether the waiting time is equal to or greater than the forward model time T forward , if yes, go to step S310; If not, return to step S307 to continue executing the scheduling action; Step S310, model update: update the emergency resource scheduling graph model, retain the elite individuals of the population, and return to step S301 to start the next round of optimization cycle.

4. The method for optimizing emergency resource scheduling based on resource scheduling graph according to claim 3 is characterized in that: The method of using a random method and a specific rule to initialize the individual Ind and thereby form an initial population Pop includes the following steps: Determine whether this initialization is the first initialization, if yes, proceed to step S3011, otherwise jump to step S3012; Step S3011, based on the NSGA-II algorithm, a random method is used to initialize random individuals Ind, accounting for 80% of the total number of the population; combined with the existing plan model, the plan-generated individuals Ind are initialized, accounting for 10% of the total number of the population; the remaining artificial individuals Ind are initialized by artificial means, accounting for 10% of the total number of the population; the random individuals Ind, the plan-generated individuals Ind and the artificial individuals Ind are merged to form a final population Pop, in which the individual ratio complies with the ratio rule of 8:1:1, and the initialization is completed; Step S3012, determine the number of elite individuals Ind to be retained, calculate the number of remaining individuals Ind that need to be initialized based on the difference between the number of elite individuals Ind and the total number of individuals in the preset population PopSize, initialize the remaining individuals Ind using a random method, merge the retained elite individuals Ind with the newly initialized remaining individuals Ind to form the final population Pop.

5. The method for optimizing emergency resource scheduling based on resource scheduling graph according to claim 3 is characterized in that: The calculation of the fitness value J(θ) of each individual Ind in the population Pop includes: Use the emergency resource scheduling graph model as the forward model for individual evaluation to deduce the final state s of individual Ind t ′ , the final state s t ′ All accident point requirements have been met or all actions have been completed; T(s t ′ -s t ) represents the starting state s t To the final state s t ′ the time required; Fitness value 6. The method for optimizing emergency resource scheduling based on resource scheduling graph according to claim 3 is characterized in that: The genetic operations of selection, crossover and mutation are performed on the population Pop to generate the offspring population Pop ′ ,Include: Selection operation: Use elite selection and index sorting selection strategies to select the population Pop. The top three best individuals Ind are copied to the next generation intact, and the remaining individuals are selected by index sorting to assign survival probabilities to the sorted individuals. P(i) represents the survival probability of the i-th individual, c is a constant greater than 1, N is the size of the current population, and i is the sequence number of the individual currently considered after sorting; Crossover and mutation operations: Use the adaptive adjustment strategy of the Chaos Gray Wolf Optimization Algorithm to dynamically change the crossover rate and mutation rate, and determine the control parameter value by calculating and comparing the individual fitness value J(θ) and the average fitness value of the population; a i is the current control parameter value of the individual, a max is the maximum value of the control parameter, a min is the minimum value of the control parameter, J i represents the current fitness value of the individual, J avg Represents the average fitness value of the current group, J min Indicates the minimum fitness value of the current population.

7. An emergency resource scheduling optimization system based on a resource scheduling map, comprising: Determine the module, used to obtain emergency resource scheduling data and determine resource scheduling targets; A modeling module, which uses knowledge graph technology to build an emergency resource scheduling graph model, and sets initialization conditions for the emergency resource scheduling graph model according to the emergency resource scheduling data; An optimization module, used to integrate the emergency resource scheduling graph model as a forward model into the rolling horizon evolutionary algorithm, perform solution calculations for the resource scheduling target, continuously iterate and optimize, and generate an optimal emergency resource scheduling solution for a specific scenario; The emergency resource scheduling graph model is used as a forward model of the rolling horizon evolutionary algorithm, including: The initialization parameters of the rolling horizon evolutionary algorithm include the number of iterations, the number of individuals in the population, PopSize, and the forward model time T. forward , the number of individual actions L; The objective function of the forward model is set to s t represents the current state of the forward model, and A represents each operating unit in the current state s t The action performed, k represents k operable units, each of which performs its own action a, s t+1 Represents the forward model prediction at the current state s t Each operation unit performs action A for a period of time T forward After the status.

8. A computer device, characterized in that: The invention comprises a processor and a memory, wherein the memory is used to store executable instructions, and the instructions are used to control the processor to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images