Regional natural disaster emergency response scheduling processing method

Abstract

The invention provides a regional natural disaster emergency response scheduling processing method, which comprises the following steps that: an emergency response system receives disaster early warning information as event trigger, automatically starts a risk area division process and generates risk area data; the emergency response system automatically triggers a scheduling scheme generation process according to the risk area data, and after the scheduling scheme is generated, an instruction issuing process is automatically triggered and a real-time tracking process is started; the emergency response system automatically triggers a post-disaster data entry process after rescue is finished, and automatically starts a loss statistics and planning process after entry is finished, so that full-process automatic propulsion is realized; the emergency response system establishes a process data link, and automatically transmits result data of a previous link to a next link to realize seamless circulation of the data; according to the emergency response system, a multi-agent collaboration platform is built, each agent obtains process data in real time through a terminal and feeds back an execution state, and collaboration linkage is achieved; according to the emergency response system, a differentiated risk assessment model and a resource matching algorithm are designed for different disaster types, and real-time dynamic adjustment is supported.

Description

Technical Field

[0001] This invention relates to the field of information technology, and in particular to a method for regional natural disaster emergency response scheduling and processing. Background Technology

[0002] Disaster emergency management is a crucial area for ensuring social security and public welfare, directly impacting the protection of life and property and the efficiency of post-disaster recovery. In emergencies such as floods, earthquakes, and forest fires, rapid response and efficient coordination are key to minimizing losses and improving rescue effectiveness. However, the current emergency management system faces numerous challenges in practice, particularly in scenarios involving multiple stakeholders and complex process connections, making it difficult to achieve efficient and precise resource allocation and response.

[0003] Existing emergency management methods typically rely on manual coordination and decentralized system support, leading to information delays and uneven resource allocation. For example, in floods, rescue teams may be unable to reach affected areas quickly due to a lack of real-time information, or supply depots may be unable to replenish urgently needed materials in a timely manner due to information asymmetry. This information silo phenomenon results in significant deficiencies in the time sensitivity and resource matching accuracy of emergency responses. Furthermore, the response needs of different disaster types vary considerably, and existing methods struggle to dynamically adjust dispatch plans according to specific disaster characteristics, often leading to resource waste or the omission of critical needs.

[0004] The core technical challenge lies in achieving real-time interaction and dynamic coordination across multiple stakeholders throughout the entire process. Emergency management involves various stakeholders, including government departments, rescue teams, material reserve points, and affected communities, each with different information needs and response capabilities. For example, in forest fire rescue, the command center needs to monitor the fire's spread, the location of rescue teams, and the availability of supplies in real time. However, current systems often fail to efficiently integrate and synchronize this information. This leads to dispatch instructions potentially being based on outdated data, suboptimal rescue route planning, and even situations where multiple stakeholders compete for limited resources simultaneously. The lack of dynamic coordination makes the entire emergency process prone to disruption at critical moments, impacting rescue efficiency.

[0005] Therefore, ensuring real-time information exchange, dynamic adjustment of instructions, and seamless connection of early warning, dispatch, execution, and feedback in complex scenarios involving multiple stakeholders has become a key issue in disaster emergency management. Summary of the Invention

[0006] This invention provides a regional natural disaster emergency response dispatching and processing method, comprising the following steps: The emergency response system receives disaster early warning information as an event trigger, automatically initiates the risk area delineation process, and generates risk area data. The emergency response system automatically triggers a scheduling scheme to generate a target scheduling process based on the risk area data. After the scheduling scheme is generated, it automatically triggers an instruction issuance process and starts a real-time tracking process. The emergency response system automatically triggers the post-disaster data entry process after the rescue is completed. After the data entry process is completed, the loss statistics and target scheduling process is automatically started, realizing the full-process automation. The target scheduling process includes multiple emergency task operations arranged in sequence, with each step corresponding to a branch emergency task operation. The emergency response system establishes a process data chain, automatically transmitting the results data of the previous stage to the next stage, achieving seamless data flow. The emergency response system establishes a multi-entity collaborative platform. Each of the entity collaborative platforms acquires process data in real time through terminals and reports the execution status to achieve collaborative linkage. The entity collaborative platform consists of emergency management departments, rescue team departments, material reserve point departments, and people in disaster-stricken areas. The emergency response system designs and runs differentiated risk assessment models and resource matching algorithms for different types of disasters.

[0007] Furthermore, the fully automated process includes: The emergency response system automatically associates software function modules after receiving the disaster early warning information; The emergency response system directly converts disaster early warning information into risk classification input through an event triggering mechanism, and immediately transmits the risk area data to the scheduling module to generate a plan. The emergency response system activates the tracking module to monitor the rescue progress simultaneously after the command is issued. The emergency response system automatically switches to the post-disaster data entry module when the rescue operation is completed, and calculates the total loss statistics from the entered post-disaster loss statistics.

[0008] Furthermore, the seamless data flow includes: The emergency response system automatically transmits the risk area data to the scheduling module as a basis for resource matching. The emergency response system automatically transmits the dispatch instruction information as a monitoring target to the tracking module; The emergency response system automatically transmits location and progress data during the rescue process to the post-disaster processing module as a statistical reference. The emergency response system ensures that the output of the previous stage directly becomes the input of the next stage through the process data chain; If the emergency response system detects a data transmission interruption, it will automatically retry the transmission to maintain the continuity of the flow. The emergency response system updates the status of each module in real time based on the transmitted data.

[0009] Furthermore, the main collaborative platform also includes performing the following operational steps: The main collaborative platform integrates the terminal access of emergency management departments, rescue teams, material reserve points and disaster-stricken people through terminals; After receiving the dispatch instruction, the rescue team reports the execution status and synchronizes it to the management department's interface; The affected people can obtain information on the rescue progress and provide feedback on their needs through mobile devices; The demand information is automatically transmitted to the scheduling module to support supplementary scheduling. The material reserve points obtain real-time demand data from the disaster-stricken areas in preparation for allocation. The emergency response system adjusts its collaborative interaction based on feedback status to achieve real-time linkage.

[0010] Furthermore, the emergency response system is designed with differentiated risk assessment models and resource matching algorithms for different disaster types, and supports real-time dynamic adjustments, specifically including: The risk assessment model calculates specific core factors and weights for disasters such as floods, earthquakes, and forest fires, and supports custom weight adjustments.

[0011] The resource matching algorithm performs bidirectional matching based on demand classification and resource attributes, and sorts by priority to ensure that high-priority demands are matched with professional resources.

[0012] Real-time acquisition of traffic or emergency data, and sending traffic alerts. Furthermore, when implementing the differentiated risk assessment model, the system also includes: the emergency response system automatically switching the assessment model according to the type of disaster; For flood disasters, the model calculates risk using rainfall, elevation, drainage capacity, population density, and infrastructure importance as core factors; For earthquake disasters, the model uses magnitude, epicentral distance, geological structure, seismic resistance level of buildings, and population density as core factors to calculate risk; For forest fires, the model uses fire weather level, forest flammability, combustible load, distance from settlements and wind force and direction as core factors to calculate risk; The emergency response system supports user-defined factor weights to adapt to local conditions. The differentiated risk assessment model outputs risk area data for subsequent process triggering.

[0013] Furthermore, the differentiated risk assessment model outputs risk area data, including: The emergency response system generates a risk score by weighted calculation of core factors; The emergency response system divides high-risk areas based on risk scores; The emergency response system will store the classification results in association with the disaster type; If the emergency response system receives a custom weight adjustment, it will recalculate the model output. The output data automatically triggers the downstream scheduling process.

[0014] Furthermore, this also includes transporting emergency supplies through dynamic route planning; The method of transporting emergency supplies through dynamic path planning includes: acquiring basic road network data and transportation task information. The basic road network data includes information on nodes and edges. Each edge includes length, basic speed, and real-time status. The transportation task includes start point, destination, and priority. The weight of each edge is updated according to the real-time state. The weight is calculated based on the real-time speed and a priority adjustment coefficient. The real-time speed is determined according to the real-time state. An initial optimal path is generated using a path search algorithm. The initial optimal path is calculated based on the minimum weight objective and the path redundancy is evaluated. If the path redundancy exceeds a threshold, alternative paths are generated. If a change in road conditions is detected, an optimization algorithm is triggered to replan the path. The optimization algorithm uses path encoding to initialize the population, calculates the fitness function, and iteratively generates a new path through genetic operations. Output a dynamic path scheme, which includes a node sequence, estimated time, and alternative paths, and notify relevant devices to update the path information.

[0015] Furthermore, the acquisition of basic road network data and transportation task information includes: The basic road network data is obtained, wherein the nodes represent intersections or bridges, the edges represent roads, and each edge includes a length in kilometers, a basic traffic speed in kilometers per hour, and a real-time traffic status, which indicates whether the traffic is smooth, congested, or damaged, and is obtained from traffic interfaces or on-site reports. The transportation task information is obtained, wherein the starting point represents the material point, the destination represents the disaster point, and the priority is divided into multiple levels; Apply real-time constraints, wherein if the real-time traffic status is damaged, the edge is marked as unusable, and if the real-time traffic status is congested, the real-time speed is adjusted to a preset ratio of the base speed. Based on the real-time constraints, unusable edges in the basic road network data are filtered to obtain the usable road network structure, which is used for subsequent weight updates and path generation.

[0016] Furthermore, updating the weight of each edge based on the real-time state includes: The real-time speed is determined, wherein if the real-time status is unobstructed, the real-time speed is equal to the base speed, and if the real-time status is congested, the real-time speed is equal to the base speed multiplied by a preset coefficient. Calculate the priority adjustment coefficient, wherein the priority adjustment coefficient is determined according to the priority level, with higher priority corresponding to a larger adjustment value; The weight is calculated as an expression consisting of the length divided by the real-time speed and multiplied by a priority adjustment factor, wherein the weight represents the estimated travel time; The weights of all edges are updated to form a real-time weighted road network, which is used as input to the path search algorithm. Furthermore, the step of generating the initial optimal path using a path search algorithm includes: The shortest path algorithm is used to search for a path from the starting point to the ending point. The shortest path algorithm aims to minimize the total weight and obtain the initial optimal path. The path redundancy is calculated as the proportion of congested edges in the initial optimal path; If the path redundancy exceeds a preset threshold, a suboptimal path is generated, wherein the difference between the total weight of the suboptimal path and the weight of the initial optimal path is less than a preset percentage. The initial optimal path and the second-best path are stored as candidate paths for population initialization in subsequent optimization algorithms.

[0017] Furthermore, the step of triggering an optimization algorithm to replan the route if a change in road conditions is detected includes: Monitor the edges in the initial optimal path, and trigger the optimization algorithm if the real-time state becomes corrupted. The path is encoded using a node sequence to represent the node order from the starting point to the ending point; the population is initialized, including generating multiple feasible paths and including the alternative paths; The fitness function is defined as the sum of the total weight of the path plus the risk coefficient multiplied by the number of risky edges in the path, wherein the total weight is the sum of the weights of all edges in the path, the number of risky edges is the number of edges with potential damage risk, and the risk coefficient is a preset parameter. Genetic operations are performed, including selection based on the fitness function, crossover at nodes with the same path, and random replacement of nodes in the path, to ensure that the path is feasible after replacement; After iterating through a preset number of algebras, the path with the highest fitness is output as the new path.

[0018] Furthermore, the output dynamic path scheme includes: Generate the dynamic path scheme, wherein the node sequence represents the node order of the path, and each edge contains the real-time speed and the estimated travel time; The dynamic path scheme includes multiple alternative paths; The application pushes the new route to the device, marking the location of congested or damaged road sections and detour information; The estimated arrival time is calculated based on the total weight of the dynamic path scheme, and the estimated arrival time is synchronized to the management interface.

[0019] Furthermore, the genetic operation includes: selecting a high-fitness path using a roulette wheel algorithm based on the fitness function; performing crossover on the two selected paths at the same node to generate a new path; mutating the path by randomly replacing a node and verifying the feasibility of the path; repeating the genetic operation until the iteration terminates, and updating the population to optimize path selection.

[0020] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This invention discloses a fully automated and multi-entity collaborative system for disaster emergency management. Addressing the problems of fragmented processes, delayed data transmission, low collaborative efficiency, and diverse disaster-type requirements in traditional emergency response, it proposes an integrated solution. This invention constructs a process data chain to seamlessly connect risk area delineation triggered by disaster warnings, dispatch plan generation, instruction issuance, real-time tracking, and post-disaster handling, achieving automatic data flow and fully automated process advancement. For different disaster types, this invention designs differentiated risk assessment models, using specific factors such as floods, earthquakes, and forest fires as core elements, combined with dynamic adjustment algorithms to optimize resource matching and route planning in real time, ensuring that high-priority needs are prioritized for professional resources. Simultaneously, this invention establishes a multi-entity collaborative platform, enabling real-time interaction between emergency management departments, rescue teams, material reserve points, and affected populations through terminals. Demands and execution status are automatically fed back to the dispatch module, supporting supplementary dispatch. This invention significantly improves emergency response efficiency, resource utilization, and multi-entity collaborative capabilities, ensuring efficient operation of the entire disaster management chain. Attached Figure Description

[0021] Figure 1 This is a flowchart of a regional natural disaster emergency response dispatching and processing method according to the present invention. Detailed Implementation

[0022] To further understand the content of this invention, a detailed description of the invention is provided in conjunction with the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] like Figure 1 The regional natural disaster emergency response dispatching and processing method of this invention may specifically include: S1, The emergency response system receives disaster early warning information as an event trigger. Based on the event trigger, the emergency response system automatically starts the risk area division process and generates risk area data.

[0025] S2, the emergency response system automatically triggers the dispatch plan generation process based on the generated risk area data. After the dispatch plan is generated, the system automatically triggers the instruction issuance process and starts the real-time tracking process.

[0026] S3, the emergency response system automatically triggers the post-disaster data entry process after the rescue is completed, and automatically starts the loss statistics and planning process after the entry is completed, so as to realize the full-process automation.

[0027] S4, The emergency response system establishes a process data chain, automatically transmitting the result data of the previous stage to the next stage, achieving seamless data flow.

[0028] S5, the emergency response system establishes a multi-entity collaborative platform, in which each entity obtains process data in real time through the terminal and reports the execution status, thereby achieving collaborative linkage.

[0029] S6, the emergency response system designs differentiated risk assessment models and resource matching algorithms for different disaster types, and supports real-time dynamic adjustments.

[0030] In the above technical solution, S1 mentions "automatically initiating the risk area delineation process and generating risk area data based on event triggering." "Event triggering" specifically refers to the emergency response system receiving disaster early warning information and then initiating the program. S4 mentions "establishing a process data chain to automatically transfer the result data of the previous stage to the next stage." It is necessary to explain the specific method of data transfer (such as API calls) to ensure data consistency between multiple stages.

[0031] In the specific technical solution, the aforementioned emergency response system automatically triggers a dispatch plan generation process based on the generated risk area data. After the dispatch plan is generated, it automatically triggers an instruction issuance process and initiates a real-time tracking process, specifically including: S21, the risk area data is automatically transmitted to the scheduling module as a basis for resource matching, the scheduling instruction information is automatically transmitted to the tracking module as a monitoring target, and the rescue progress data is automatically transmitted to the post-disaster processing module as a statistical reference.

[0032] S22, the multiple entities include emergency management departments, rescue teams, material reserve points and disaster-stricken people. The rescue teams report their execution status and synchronize it to the management department's interface. The disaster-stricken people report their needs and automatically transmit them to the dispatch module to support supplementary dispatch.

[0033] In the above technical solution, S22 mentions that "the feedback needs of the disaster-stricken people are automatically transmitted to the scheduling module to support supplementary scheduling". The feedback channel (such as APP) communicates remotely with the scheduling module to receive feedback from the disaster-stricken people and filter duplicate feedback. The scheduling module is used to perform supplementary scheduling processing operations.

[0034] In the specific technical solution, the emergency response system designs differentiated risk assessment models and resource matching algorithms for different disaster types, and supports real-time dynamic adjustments, specifically including: S61, the risk assessment model calculates specific core factors and weights for disasters such as floods, earthquakes, and forest fires, and supports custom weight adjustments.

[0035] S62, the resource matching algorithm performs bidirectional matching based on demand classification and resource attributes, and sorts by priority to ensure that high-priority demands are matched with professional resources.

[0036] S63 can acquire real-time traffic or emergency data and send traffic alerts.

[0037] During the execution of S61, a differentiated risk assessment model is constructed and applied. The emergency response system incorporates dedicated risk assessment models for major disaster types such as floods, earthquakes, and forest fires. Each model selects a set of quantifiable core factors based on its disaster mechanism and assigns initial weights, generating a regional risk value through weighted calculation.

[0038] S611: Definition of core model factors and risk calculation. The system automatically loads the corresponding assessment model and core factor set based on the disaster type.

[0039] For flood disasters, the core factor set of the model includes: cumulative rainfall (mm), regional average elevation (m), surface drainage capacity (level), population density (people / km²), and critical infrastructure density (sites / km²). Its risk value R_flood is calculated using the following formula: R_flood = w1*F(rainfall) + w2*F(altitude) + w3*F(drainage capacity) + w4*F(population density) + w5*F(infrastructure density); where F() is a function that normalizes the original data of each factor in the interval [0,1], w1 to w5 are the weight coefficients of each factor, and ∑w = 1.

[0040] For earthquake disasters, the core factor set of the model includes: earthquake magnitude (M), epicentral distance (km), site soil type (category), average seismic fortification level of buildings (level), and nighttime population density (people / km²). Its risk value R_quake is calculated using the same principle as the flood model.

[0041] For forest fires, the core factor set of the model includes: forest fire weather index (level), vegetation flammability type (category), combustible material load (t / ha), distance to the nearest settlement (km), and real-time wind speed (m / s). Its risk value R_fire is calculated using the same principle as the flood model. The system allows authorized users to customize the weights w of each model's core factors through a management interface to adapt to local geographical and socio-economic conditions. The adjusted model takes effect immediately and recalculates the risk value.

[0042] In summary, the aforementioned differentiated risk assessment models calculate risk based on the following factors: for floods, rainfall, elevation, drainage capacity, population density, and infrastructure importance; for earthquakes, magnitude, epicenter distance, geological structure, building seismic resistance level, and population density; and for forest fires, fire weather risk level, forest flammability, combustible material load, distance from settlements, and wind direction and force. The emergency response system supports user-defined factor weights to adapt to local conditions, and the model outputs risk area data for subsequent process triggering.

[0043] S612: Perform risk area division and output operations. The system compares the calculated risk value R with a preset threshold and automatically divides the area into "extremely high risk area", "high risk area", "medium risk area" and "low risk area". The division results (i.e., risk area data, including area boundaries, risk level and dominant risk factor) are used as key outputs, automatically associated and stored, and trigger downstream scheduling processes.

[0044] Furthermore, the assessment model outputs risk area data, including: the emergency response system generating a risk score (i.e., risk value R) by weighting core factors; the emergency response system classifying high-risk areas based on the risk score; the emergency response system storing the classification results in association with disaster types; the emergency response system recalculating the model output if it receives a custom weight adjustment; the output data automatically triggering downstream scheduling processes; and the emergency response system integrating multi-source data to improve model accuracy.

[0045] In the specific technical solution, during the execution of S62, the resource matching algorithm performs bidirectional matching based on demand classification and resource attributes, prioritizing requests to ensure that high-priority demands are matched with specialized resources. The scheduling module of the emergency response system receives specific rescue demands transformed from data from the risk area and executes the intelligent resource matching algorithm.

[0046] S621: The system uniformly classifies rescue needs into three categories: Category I - Life Rescue (e.g., trapped personnel, transfer of critically injured patients), Category II - Emergency Material Supply (e.g., food, medicine, temporary shelter supply), and Category III - Infrastructure Repair (e.g., road, communication, power restoration). Category I needs have the highest priority. The system also categorizes dispatchable professional resources into: professional rescue forces (e.g., fire brigades, medical teams, engineering repair teams, with professional capability tags), general rescue forces (e.g., volunteer teams, militia), and material reserves (e.g., medicine, food, engineering machinery, with type, quantity, and location attributes).

[0047] S622: Perform multi-objective optimization matching logic processing. The matching algorithm aims to maximize the demand satisfaction rate and minimize the overall response time, and operates according to the following steps: Priority sorting: Sort all pending requests in the order of Category I > Category II > Category III into a queue.

[0048] Professional resource matching: For each need, a set of candidate resources that match the professional capability tags of the need type are selected from the resource pool.

[0049] Multi-constraint filtering: Within the candidate set, further filter resources that simultaneously meet the following conditions: The first constraint is a distance constraint: the road distance between the resource location and the demand point is less than the maximum response distance threshold D_max set by the system. The second constraint is a capacity constraint: the available resource quantity (such as personnel, materials, and machinery) is greater than or equal to the minimum quantity required by the demand. The third constraint is optimal selection: among the filtered resources, the resource with the shortest "estimated arrival time = road distance / estimated travel speed" is selected, forming a <demand, matching resource, estimated arrival time> matching pair.

[0050] If there are no resources in the current resource pool that meet all the conditions, then: check the current execution conditions, relax the professional matching requirements, and consider general rescue forces; if it still cannot be met, then generate an external resource support request and submit it to the superior system.

[0051] S63: Acquire real-time traffic or emergency data and send road condition alerts.

[0052] S631: Real-time Data Monitoring and Triggering. The system monitors multi-source data streams in real time, including: real-time road conditions (congestion, interruptions) from the transportation department, emergencies reported by on-site teams (such as secondary disasters, resource depletion), and updated inventory data from supply points. When a severe congestion or interruption is detected on the path from a supply point to the target point, the above message is pushed to the terminal of the corresponding rescue team.

[0053] Furthermore, the fully automated process includes: The emergency response system automatically associates software function modules after receiving the disaster early warning information; The emergency response system directly converts disaster early warning information into risk classification input through an event triggering mechanism, and immediately transmits the risk area data to the scheduling module to generate a plan. The emergency response system activates the tracking module to monitor the rescue progress simultaneously after the command is issued. The emergency response system automatically switches to the post-disaster data entry module when the rescue operation is completed, and calculates the total loss statistics from the entered post-disaster loss statistics.

[0054] It should be noted that the aforementioned fully automated process involves the system automatically triggering and linking all subsequent processes (risk area delineation, dispatch plan generation, instruction issuance, real-time tracking, and post-disaster data entry) upon receiving disaster early warning information, forming an automated chain that requires no manual intervention. Simultaneously, it achieves high efficiency and immediacy throughout the entire emergency response process, significantly shortening response initiation time.

[0055] Furthermore, the seamless data flow includes: The emergency response system automatically transmits the risk area data to the scheduling module as a basis for resource matching. The emergency response system automatically transmits the dispatch instruction information as a monitoring target to the tracking module; The emergency response system automatically transmits location and progress data during the rescue process to the post-disaster processing module as a statistical reference. The emergency response system ensures that the output of the previous stage directly becomes the input of the next stage through the process data chain; If the emergency response system detects a data transmission interruption, it will automatically retry the transmission to maintain the continuity of the flow. The emergency response system updates the status of each module in real time based on the transmitted data.

[0056] It's important to note that the specific steps for seamless data flow involve establishing a "process data chain" to ensure that the output data of the previous step automatically becomes the input data of the next step. If the transmission is interrupted, the system will automatically retry to maintain continuity. Ultimately, this guarantees the integrity and consistency of data flow, improving the accuracy of decision-making.

[0057] Furthermore, the main collaborative platform also includes performing the following operational steps: The main collaborative platform integrates the terminal access of emergency management departments, rescue teams, material reserve points and disaster-stricken people through terminals; After receiving the dispatch instruction, the rescue team reports the execution status and synchronizes it to the management department's interface; The affected people can obtain information on the rescue progress and provide feedback on their needs through mobile devices; The demand information is automatically transmitted to the scheduling module to support supplementary scheduling. The material reserve points obtain real-time demand data from the disaster-stricken areas in preparation for allocation. The emergency response system adjusts its collaborative interaction based on feedback status to achieve real-time linkage.

[0058] It's important to note the collaborative platform, which integrates multiple stakeholders (management departments, rescue teams, supply depots, and affected residents). All parties share data, status updates, and needs in real time through their terminals. This achieves the desired technical effect: building cross-departmental and cross-role collaborative capabilities, and enabling precise dispatch and transparent management of rescue forces.

[0059] Furthermore, this also includes transporting emergency supplies through dynamic route planning; The method of transporting emergency supplies through dynamic path planning includes: acquiring basic road network data and transportation task information. The basic road network data includes information on nodes and edges. Each edge includes length, basic speed, and real-time status. The transportation task includes start point, destination, and priority. The weight of each edge is updated according to the real-time state. The weight is calculated based on the real-time speed and a priority adjustment coefficient. The real-time speed is determined according to the real-time state. An initial optimal path is generated using a path search algorithm. The initial optimal path is calculated based on the minimum weight objective and the path redundancy is evaluated. If the path redundancy exceeds a threshold, alternative paths are generated. If a change in road conditions is detected, an optimization algorithm is triggered to replan the path. The optimization algorithm uses path encoding to initialize the population, calculates the fitness function, and iteratively generates a new path through genetic operations. Output a dynamic path scheme, which includes a node sequence, estimated time, and alternative paths, and notify relevant devices to update the path information.

[0060] In specific technical solutions, disasters are often accompanied by road damage or congestion. Traditional static route planning can lead vehicles into dead ends. This solution, through real-time perception and dynamic replanning, can proactively avoid dangerous or congested road sections, selecting the fastest route for rescue supplies and teams under current conditions, directly translating into savings in transportation time and increased rescue success rates. The specific operations of dynamic route planning involve acquiring real-time road conditions, dynamically calculating and updating transportation routes, and using algorithms (such as genetic algorithms) to replan the optimal or suboptimal route when road conditions change. The specific technical effects include effectively avoiding traffic obstacles, significantly shortening emergency supply transportation time, and improving supply reliability.

[0061] Furthermore, the acquisition of basic road network data and transportation task information includes: The basic road network data is obtained, wherein the nodes represent intersections or bridges, the edges represent roads, and each edge includes a length in kilometers, a basic traffic speed in kilometers per hour, and a real-time traffic status, which indicates whether the traffic is smooth, congested, or damaged, and is obtained from traffic interfaces or on-site reports. The transportation task information is obtained, wherein the starting point represents the material point, the destination represents the disaster point, and the priority is divided into multiple levels; Apply real-time constraints, wherein if the real-time traffic status is damaged, the edge is marked as unusable, and if the real-time traffic status is congested, the real-time speed is adjusted to a preset ratio of the base speed. Based on the real-time constraints, unusable edges in the basic road network data are filtered to obtain the usable road network structure, which is used for subsequent weight updates and path generation.

[0062] Furthermore, updating the weight of each edge based on the real-time state includes: The real-time speed is determined, wherein if the real-time status is unobstructed, the real-time speed is equal to the base speed, and if the real-time status is congested, the real-time speed is equal to the base speed multiplied by a preset coefficient. Calculate the priority adjustment coefficient, wherein the priority adjustment coefficient is determined according to the priority level, with higher priority corresponding to a larger adjustment value; The weight is calculated as an expression consisting of the length divided by the real-time speed and multiplied by a priority adjustment factor, wherein the weight represents the estimated travel time; The weights of all edges are updated to form a real-time weighted road network, which is used as input to the path search algorithm. Furthermore, the step of generating the initial optimal path using a path search algorithm includes: The shortest path algorithm is used to search for a path from the starting point to the ending point. The shortest path algorithm aims to minimize the total weight and obtain the initial optimal path. The path redundancy is calculated as the proportion of congested edges in the initial optimal path; If the path redundancy exceeds a preset threshold, a suboptimal path is generated, wherein the difference between the total weight of the suboptimal path and the weight of the initial optimal path is less than a preset percentage. The initial optimal path and the second-best path are stored as candidate paths for population initialization in subsequent optimization algorithms.

[0063] Furthermore, the step of triggering an optimization algorithm to replan the route if a change in road conditions is detected includes: Monitor the edges in the initial optimal path, and trigger the optimization algorithm if the real-time state becomes corrupted. The path is encoded using a node sequence to represent the node order from the starting point to the ending point; the population is initialized, including generating multiple feasible paths and including the alternative paths; The fitness function is defined as the sum of the total weight of the path plus the risk coefficient multiplied by the number of risky edges in the path, wherein the total weight is the sum of the weights of all edges in the path, the number of risky edges is the number of edges with potential damage risk, and the risk coefficient is a preset parameter. Genetic operations are performed, including selection based on the fitness function, crossover at nodes with the same path, and random replacement of nodes in the path, to ensure that the path is feasible after replacement; After iterating through a preset number of algebras, the path with the highest fitness is output as the new path.

[0064] Furthermore, the output dynamic path scheme includes: Generate the dynamic path scheme, wherein the node sequence represents the node order of the path, and each edge contains the real-time speed and the estimated travel time; The dynamic path scheme includes multiple alternative paths; The application pushes the new route to the device, marking the location of congested or damaged road sections and detour information; The estimated arrival time is calculated based on the total weight of the dynamic path scheme, and the estimated arrival time is synchronized to the management interface.

[0065] Furthermore, the genetic operation includes: selecting a high-fitness path using a roulette wheel algorithm based on the fitness function; performing crossover on the two selected paths at the same node to generate a new path; mutating the path by randomly replacing a node and verifying the feasibility of the path; repeating the genetic operation until the iteration terminates, and updating the population to optimize path selection.

[0066] The aforementioned technical solution continuously acquires the "real-time traffic status" (smooth, congested, damaged) of roads through traffic interfaces or on-site reporting, and dynamically updates the traffic speed and weight (estimated travel time) of edges accordingly. When a change in road conditions is detected (such as becoming damaged), an optimization algorithm is triggered to replan the route. This continuous perception and response mechanism for road conditions ensures that the route recommended by the system for transportation tasks is always based on the latest and most accurate road information. This avoids guiding vehicles to impassable or severely congested road sections, thereby directly reducing uncertainty and delays in the transportation process and ensuring the timeliness of relief supplies delivery.

[0067] The aforementioned execution process encompasses a shift from "multi-objective optimization" to "improving path reliability (robustness)." This approach not only considers the shortest time (minimizing total weight) but also introduces "path redundancy" checks, generates "suboptimal paths" as alternatives, and defines a fitness function in the optimization algorithm that includes a "risk coefficient" and "number of risk edges." By checking and avoiding paths with high congestion rates while preparing alternative routes with similar total durations, a backup plan is provided for potential unforeseen circumstances on a single path, enhancing the overall resilience of the solution.

[0068] In the fitness function of the genetic algorithm, edges with potential damage risks are actively penalized, guiding the search process to choose safer and more stable paths. This comprehensive consideration of multiple factors (time, risk) ensures that the final output path is not only theoretically the shortest in time, but also more reliable in reality, reducing the risk of interruption due to road damage during transportation.

[0069] During the execution of the above functions, the task classification includes: Through the priority mechanism, the system can prioritize the allocation of better road resources (faster and more reliable routes) to more urgent transportation tasks, realizing precise scheduling and efficient allocation under limited rescue resources.

[0070] The aforementioned functions include search efficiency: combining the efficiency of algorithms such as Dijkstra's algorithm with the global search capability of genetic algorithms, it ensures the feasibility of the initial solution and can escape local optima through iterative evolution, quickly finding high-quality comprehensive optimal paths in complex road networks, thus improving the efficiency and effectiveness of overall planning. This scheme achieves dynamic response through real-time data-driven approaches, ensuring the timeliness of paths; enhances the robustness of paths through multi-objective (time, risk) and alternative path strategies; and achieves efficient scheduling of rescue missions and high-quality path generation through priority mechanisms and intelligent optimization algorithms. These three aspects work together to ultimately achieve the core technical effect of ensuring "fast and stable" material transportation in post-disaster emergency scenarios.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for dispatching and handling regional natural disaster emergency response, characterized in that, include: The emergency response system receives disaster early warning information as an event trigger, automatically initiates the risk area delineation process, and generates risk area data. The emergency response system automatically triggers a scheduling scheme to generate a target scheduling process based on the risk area data. After the scheduling scheme is generated, it automatically triggers an instruction issuance process and starts a real-time tracking process. The emergency response system automatically triggers the post-disaster data entry process after the rescue is completed. After the data entry process is completed, the loss statistics and target scheduling process is automatically started, realizing the full-process automation. The target scheduling process includes multiple emergency task operations arranged in sequence, with each step corresponding to a branch emergency task operation. The emergency response system establishes a process data chain, automatically transmitting the results data of the previous stage to the next stage, achieving seamless data flow. The emergency response system establishes a multi-entity collaborative platform. Each of the entity collaborative platforms acquires process data in real time through terminals and reports the execution status to achieve collaborative linkage. The entity collaborative platform consists of emergency management departments, rescue team departments, material reserve point departments, and people in disaster-stricken areas. The emergency response system designs and runs differentiated risk assessment models and resource matching algorithms for different types of disasters.

2. The method as described in claim 1, characterized in that, The fully automated process includes: The emergency response system automatically associates software function modules after receiving the disaster early warning information; The emergency response system directly converts disaster early warning information into risk classification input through an event triggering mechanism, and immediately transmits the risk area data to the scheduling module to generate a plan. The emergency response system activates the tracking module to monitor the rescue progress simultaneously after the command is issued. The emergency response system automatically switches to the post-disaster data entry module when the rescue operation is completed, and calculates the total loss statistics from the entered post-disaster loss statistics.

3. The method as described in claim 2, characterized in that, The seamless data flow includes: The emergency response system automatically transmits the risk area data to the scheduling module as a basis for resource matching. The emergency response system automatically transmits the dispatch instruction information as a monitoring target to the tracking module; The emergency response system automatically transmits location and progress data during the rescue process to the post-disaster processing module as a statistical reference. The emergency response system ensures that the output of the previous stage directly becomes the input of the next stage through the process data chain; If the emergency response system detects a data transmission interruption, it will automatically retry the transmission to maintain the continuity of the flow. The emergency response system updates the status of each module in real time based on the transmitted data.

4. The method as described in claim 3, characterized in that, The main collaborative platform also includes the following operational steps: The main collaborative platform integrates the terminal access of emergency management departments, rescue teams, material reserve points and disaster-stricken people through terminals; After receiving the dispatch instruction, the rescue team reports the execution status and synchronizes it to the management department's interface; The affected people can obtain information on the rescue progress and provide feedback on their needs through mobile devices; The demand information is automatically transmitted to the scheduling module to support supplementary scheduling. The material reserve points obtain real-time demand data from the disaster-stricken areas in preparation for allocation. The emergency response system adjusts its collaborative interaction based on feedback status to achieve real-time linkage.

5. The method as described in claim 4, characterized in that, The emergency response system is designed with differentiated risk assessment models and resource matching algorithms for different disaster types, and supports real-time dynamic adjustments, specifically including: The risk assessment model calculates risks for disasters such as floods, earthquakes, and forest fires using specific core factors and weights, and supports custom weight adjustments. The resource matching algorithm is based on a two-way matching process using demand classification and resource attributes, and prioritizes requests to ensure that high-priority demands are matched with specialized resources. It can acquire real-time traffic or emergency data and send traffic alerts.

6. The method as described in claim 4, characterized in that, When implementing the differentiated risk assessment model, the system also includes: the emergency response system automatically switches the assessment model according to the type of disaster; For flood disasters, the model calculates risk using rainfall, elevation, drainage capacity, population density, and infrastructure importance as core factors; For earthquake disasters, the model uses magnitude, epicentral distance, geological structure, seismic resistance level of buildings, and population density as core factors to calculate risk; For forest fires, the model uses fire weather level, forest flammability, combustible load, distance from settlements and wind force and direction as core factors to calculate risk; The emergency response system supports user-defined factor weights to adapt to local conditions. The differentiated risk assessment model outputs risk area data for subsequent process triggering.

7. The method as described in claim 5, characterized in that, The differentiated risk assessment model outputs risk area data, including: The emergency response system generates a risk score by weighted calculation of core factors; The emergency response system divides high-risk areas based on risk scores; The emergency response system will store the classification results in association with the disaster type; If the emergency response system receives a custom weight adjustment, it will recalculate the model output. The output data automatically triggers the downstream scheduling process.

8. The method as described in claim 5, characterized in that, This also includes transporting emergency supplies using dynamic route planning; The method of transporting emergency supplies through dynamic path planning includes: acquiring basic road network data and transportation task information. The basic road network data includes information on nodes and edges. Each edge includes length, basic speed, and real-time status. The transportation task includes start point, destination, and priority. The weight of each edge is updated according to the real-time state. The weight is calculated based on the real-time speed and a priority adjustment coefficient. The real-time speed is determined according to the real-time state. An initial optimal path is generated using a path search algorithm. The initial optimal path is calculated based on the minimum weight objective and the path redundancy is evaluated. If the path redundancy exceeds a threshold, alternative paths are generated. If a change in road conditions is detected, an optimization algorithm is triggered to replan the path. The optimization algorithm uses path encoding to initialize the population, calculates the fitness function, and iteratively generates a new path through genetic operations. Output a dynamic path scheme, which includes a node sequence, estimated time, and alternative paths, and notify relevant devices to update the path information.

9. The method as described in claim 8, characterized in that, The acquisition of basic road network data and transportation task information includes: The basic road network data is obtained, wherein the nodes represent intersections or bridges, the edges represent roads, and each edge includes a length in kilometers, a basic traffic speed in kilometers per hour, and a real-time traffic status, which indicates whether the traffic is smooth, congested, or damaged, and is obtained from traffic interfaces or on-site reports. The transportation task information is obtained, wherein the starting point represents the material point, the destination represents the disaster point, and the priority is divided into multiple levels; Apply real-time constraints, wherein if the real-time traffic status is damaged, the edge is marked as unusable, and if the real-time traffic status is congested, the real-time speed is adjusted to a preset ratio of the base speed. Based on the real-time constraints, unusable edges in the basic road network data are filtered to obtain the usable road network structure, which is used for subsequent weight updates and path generation.

10. The method as described in claim 9, characterized in that, The step of updating the weight of each edge according to the real-time state includes: The real-time speed is determined, wherein if the real-time status is unobstructed, the real-time speed is equal to the base speed, and if the real-time status is congested, the real-time speed is equal to the base speed multiplied by a preset coefficient. Calculate the priority adjustment coefficient, wherein the priority adjustment coefficient is determined according to the priority level, with higher priority corresponding to a larger adjustment value; The weight is calculated as an expression consisting of the length divided by the real-time speed and multiplied by a priority adjustment factor, wherein the weight represents the estimated travel time; The weights of all edges are updated to form a real-time weighted road network, which is then used as input to the path search algorithm. The process of generating the initial optimal path using a path search algorithm includes: The shortest path algorithm is used to search for a path from the starting point to the ending point. The shortest path algorithm aims to minimize the total weight and obtain the initial optimal path. The path redundancy is calculated as the proportion of congested edges in the initial optimal path; If the path redundancy exceeds a preset threshold, a suboptimal path is generated, wherein the difference between the total weight of the suboptimal path and the weight of the initial optimal path is less than a preset percentage. The initial optimal path and the second-best path are stored as candidate paths for population initialization in subsequent optimization algorithms.

Images