Emergency rescue management optimization method and system based on AI algorithm

Abstract

The invention relates to the technical field of emergency management, in particular to an emergency rescue management optimization method based on an AI algorithm. The method comprises the following steps: obtaining the corresponding number and position of various rescue resources and the corresponding state and performance of various rescue devices through an emergency disaster area, carrying out rescue resource capability evaluation, and predicting the emergency rescue resource demand corresponding to each emergency rescue task; based on the emergency rescue resource demand quantity corresponding to each emergency rescue task, performing emergency priority sorting analysis on each emergency rescue task, and generating a corresponding emergency rescue priority sequence in the current area; and carrying out emergency rescue allocation management optimization on the corresponding emergency rescue priority sequence in the current area by taking the maximum rescue effect as a target and combining the corresponding emergency rescue resource capability in the current area so as to generate a corresponding emergency rescue resource allocation management decision suggestion. According to the invention, the response speed and rescue effect of emergency rescue can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency management, and particularly to an optimization method for emergency rescue management based on AI algorithms. Background Art

[0002] In recent years, with the development of artificial intelligence (AI), big data, and Internet of Things technologies, emergency rescue management methods based on AI algorithms have gradually become a research hotspot in the emergency field. AI technologies, especially machine learning and deep learning algorithms, have significant advantages in large-scale data analysis, pattern recognition, decision-making support, etc. Through the intelligent decision-making of AI algorithms, real-time monitoring of emergencies, intelligent scheduling and optimization of emergency resources can be achieved, greatly improving the response speed and efficiency of emergency rescue. However, most of the existing methods rely on a single data source, such as meteorological data, geographical information, or event monitoring data, and fail to effectively integrate data from multiple channels, resulting in insufficient decision-making support. At the same time, traditional AI algorithms mostly focus on the optimization of a certain aspect, such as resource scheduling or personnel deployment, and lack comprehensive consideration of the complex relationships between multi-dimensional factors (such as resources, time, location, etc.), thus reducing the response speed of emergency rescue. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide an optimization method and system for emergency rescue management based on AI algorithms to solve at least one of the above technical problems.

[0004] To achieve the above object, an optimization method for emergency rescue management based on AI algorithms includes the following steps:

[0005] Step S1: Obtain the quantity and location of various rescue resources and the status and performance of various rescue equipment corresponding to the emergency affected area; based on the quantity and location of various rescue resources, evaluate the status and performance of various rescue equipment to obtain the corresponding emergency rescue resource capabilities in the current area;

[0006] Step S2: Obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area; according to the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task, obtain the corresponding disaster spread speed and the number of affected people, and predict the required emergency rescue resource demand for each emergency rescue task;

[0007] Step S3: Based on the required emergency rescue resource demand for each emergency rescue task and in combination with the disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and the number of affected people, conduct an emergency priority ranking analysis for each emergency rescue task to generate the corresponding emergency rescue priority sequence in the current area;

[0008] Step S4: Optimize the emergency rescue deployment management of the corresponding emergency rescue priority sequence in the current area by aiming to maximize the rescue effect and combining the corresponding emergency rescue resource capabilities in the current area, so as to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue tasks.

[0009] Furthermore, step S1 includes the following steps:

[0010] Step S11: Obtain the quantities and locations of various rescue resources through the emergency affected area;

[0011] Step S12: Obtain the status and performance of various rescue equipment through the emergency affected area;

[0012] Step S13: Conduct a soundness assessment and analysis of the equipment based on the status and performance of various rescue equipment to obtain the soundness probabilities of various rescue equipment;

[0013] Step S14: Conduct a resource reserve statistics on the quantities and locations of various rescue resources based on the soundness probabilities of various rescue equipment to obtain the corresponding rescue resource reserve amounts in the area;

[0014] Step S15: Evaluate the rescue resource capabilities for the emergency affected area based on the corresponding rescue resource reserve amounts in the area to obtain the corresponding emergency rescue resource capabilities in the current area.

[0015] Furthermore, step S13 includes the following steps:

[0016] Step S131: Obtain the corresponding changes in equipment component sizes and surface roughness of the equipment through the status of various rescue equipment;

[0017] Step S132: Conduct an equipment wear assessment calculation based on the corresponding changes in equipment component sizes and surface roughness of various rescue equipment to obtain the wear degrees of various rescue equipment;

[0018] Step S133: Assign corresponding weights to each performance index within the performance of various rescue equipment through the analytic hierarchy process, where each performance index includes an equipment response index, an equipment operation index, and an equipment capacity index, and conduct a weighted calculation of the performance scores based on the weights and the corresponding performance indices to obtain the performance scores of various rescue equipment;

[0019] Step S134: Conduct a ratio calculation between the wear degrees and performance scores of various rescue equipment to obtain the soundness probabilities of various rescue equipment.

[0020] Furthermore, step S14 includes the following steps:

[0021] Step S141: Based on the intact probabilities corresponding to various rescue equipment, conduct an intact correction analysis on the quantities corresponding to various rescue resources. If the corresponding intact probability is less than 50%, subtract one from the quantity corresponding to the corresponding type of rescue resource; otherwise, keep it unchanged, so as to obtain the complete quantities corresponding to various rescue resources through correction and update;

[0022] Step S142: Evaluate the resource convenience based on the locations corresponding to various rescue resources to obtain the location reserve convenience degrees corresponding to various rescue resources;

[0023] Step S143: Determine the resource reserve verification of the complete quantities corresponding to various rescue resources according to the location reserve convenience degrees corresponding to various rescue resources, so as to obtain the corresponding rescue resource reserve quantities within the region.

[0024] Furthermore, Step S142 includes the following steps:

[0025] Precisely determine the corresponding reserve locations within the emergency affected area through the locations corresponding to various rescue resources, so as to obtain the regional reserve locations corresponding to various rescue resources;

[0026] Calculate the rescue transportation distances between the regional reserve locations corresponding to various rescue resources and the corresponding disaster rescue task locations within the emergency affected area, so as to obtain the rescue transportation distances between various rescue reserve resources and the disaster rescue task locations;

[0027] Determine the number of rescue transportation paths and the traffic volume of transportation hubs corresponding to various rescue resources according to the rescue transportation distances between various rescue reserve resources and the disaster rescue task locations;

[0028] Evaluate the resource convenience of the locations corresponding to various rescue resources based on the number of rescue transportation paths and the traffic volume of transportation hubs corresponding to various rescue resources, so as to obtain the location reserve convenience degrees corresponding to various rescue resources.

[0029] Furthermore, Step S2 includes the following steps:

[0030] Step S21: Obtain the disaster types, disaster distribution scales, and the surrounding population distribution scales corresponding to each emergency rescue task through the emergency affected area;

[0031] Step S22: Set the corresponding disaster observation window sizes according to the corresponding disaster types, and conduct a distribution scale time series analysis on the disaster distribution scales and the surrounding population distribution scales corresponding to each emergency rescue task based on the disaster observation window sizes, so as to obtain the disaster distribution area change sequences and the population quantity distribution change sequences corresponding to each emergency rescue task under the corresponding windows;

[0032] Step S23: Estimate the disaster spread speed according to the disaster distribution area change sequences corresponding to each emergency rescue task under the corresponding window, so as to obtain the disaster spread speed corresponding to each emergency rescue task;

[0033] Step S24: Estimate the affected population according to the population quantity distribution change sequences corresponding to each emergency rescue task under the corresponding window, so as to obtain the affected population quantity corresponding to each emergency rescue task;

[0034] Step S25: Based on the disaster spread speed and the affected population quantity corresponding to each emergency rescue task, and combined with the AI algorithm, predict the rescue resource requirements for the corresponding emergency rescue tasks within the emergency affected area, so as to predict the required emergency rescue resource quantities corresponding to each emergency rescue task.

[0035] Further, the emergency rescue resource quantities described in Step S25 include the required quantities corresponding to rescue personnel, rescue equipment, and rescue supplies.

[0036] Further, Step S3 includes the following steps:

[0037] Step S31: Combine the required emergency rescue resource quantities corresponding to each emergency rescue task with the corresponding disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and affected population quantity to form corresponding emergency rescue data vectors, and constitute a corresponding vector matrix, so as to generate an emergency rescue task vector matrix;

[0038] Step S32: Calculate the eigenvalues through each sub-vector within the emergency rescue task vector matrix, so as to obtain the vector eigenvalues corresponding to each emergency rescue task sub-vector;

[0039] Step S33: Based on the vector eigenvalues corresponding to each emergency rescue task sub-vector, perform emergency priority sorting on each emergency rescue task within the emergency affected area from largest to smallest, so as to generate the corresponding emergency rescue priority sequence within the current area.

[0040] Further, Step S4 includes the following steps:

[0041] Step S41: Obtain the corresponding emergency rescue resource transportation and availability constraints through the emergency rescue resource capabilities within the current area;

[0042] Step S42: Optimize the emergency rescue deployment management for each rescue task in the corresponding emergency rescue priority sequence within the current area by aiming to maximize the rescue effect and combining the transportation and availability constraints of the corresponding emergency rescue resources in the current area, so as to reasonably arrange the emergency rescue resources corresponding to each rescue task considering the transportation distance, transportation time, and resource availability factors of the emergency rescue resources, and select the optimal corresponding emergency rescue resource transportation route, thereby generating decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue task.

[0043] Furthermore, the present invention also provides an emergency rescue management optimization system based on an AI algorithm for executing the above-mentioned emergency rescue management optimization method based on an AI algorithm. The emergency rescue management optimization system based on an AI algorithm includes:

[0044] A rescue capacity evaluation module, which is used to obtain the quantity and location of various rescue resources and the status and performance of various rescue equipment through the emergency affected area; evaluate the status and performance of various rescue equipment based on the quantity and location of various rescue resources to obtain the corresponding emergency rescue resource capacity within the current area;

[0045] A resource demand prediction module, which is used to obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area; obtain the corresponding disaster spread speed and the number of affected people according to the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task, and predict the required emergency rescue resource demand corresponding to each emergency rescue task;

[0046] An emergency rescue ranking module, which is used to conduct an emergency priority ranking analysis on each emergency rescue task based on the required emergency rescue resource demand corresponding to each emergency rescue task and combining the disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and the number of affected people, so as to generate the corresponding emergency rescue priority sequence within the current area;

[0047] An emergency rescue management module, which is used to optimize the emergency rescue deployment management for the corresponding emergency rescue priority sequence within the current area by aiming to maximize the rescue effect and combining the corresponding emergency rescue resource capacity within the current area, so as to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue task.

[0048] Advantages of the present invention:

[0049] 1. The emergency rescue management optimization method based on AI algorithm proposed by the present invention, compared with the prior art, the beneficial effects of the present application are as follows: by obtaining the quantity, location of various rescue resources in the emergency disaster area, as well as the status and performance information of various rescue equipment, a comprehensive capacity assessment of the current emergency rescue resources can be carried out, so as to provide data support for subsequent resource allocation and rescue decision-making. For example, if the quantity of medical equipment in a certain area is insufficient or the status is poor, it can be identified early and supplemented or optimized in a timely manner to avoid resource waste or missing the rescue opportunity. In addition, understanding the performance of various rescue equipment can also ensure that resources can maximize their utility during the actual rescue process, avoid the situation of excessive or insufficient concentration of resources, and ensure that the emergency response can cover the disaster area in a timely and comprehensive manner, so as to effectively integrate data from multiple channels. Secondly, by analyzing factors such as the type of disaster, the distribution scale of the disaster, and the distribution scale of the surrounding population, the amount of resources required for each emergency rescue task can be inferred. This analysis helps to accurately predict the needs of various rescue tasks and ensure that all tasks can be fully guaranteed with resources. By predicting variables such as the spread speed of the disaster and the number of affected people, preparations for resource allocation can be made in advance. Through the prediction of these factors, not only can the complexity and resource requirements of the rescue task be accurately evaluated, but also the use strategy of resources can be adjusted according to the particularity of the disaster area to avoid excessive or insufficient resource allocation. At the same time, by analyzing the distribution scale of the surrounding population, potential affected people can also be predicted, so as to targetedly carry out emergency evacuation, material distribution, etc., to ensure the rationality and efficiency of resource use, and thus better support the management decision-making corresponding to the emergency rescue task. Then, by combining factors such as the type of disaster, the distribution scale of the disaster, and the distribution scale of the surrounding population to prioritize emergency rescue tasks, it can be ensured that limited rescue resources can be preferentially invested in the most urgent and critical rescue tasks. The key to this step is that it can optimize the use efficiency of resources to the greatest extent and avoid poor rescue effects caused by uneven resource allocation. For example, certain disasters need to be dealt with immediately, such as chemical leaks or fires, etc. These situations usually pose a direct threat to human life safety and must be given priority. For other disasters, although they are also very serious, they pose a greater threat to the environment and property and can be dealt with after other high-priority tasks are completed. Through reasonable prioritization, it can be ensured that the rescue operation can quickly and accurately respond to the most urgent needs, which can achieve a comprehensive consideration of the complex relationships between multi-dimensional factors (such as resources, time, location, etc.), greatly improve the timeliness and effectiveness of the rescue work, and thus maximize the response speed and rescue effect of the emergency rescue.Finally, by optimizing resource allocation based on the goal of maximizing rescue effects, combining the resource capabilities and priority sequences within the region, it can provide clear decision-making support for emergency management personnel, ensuring that all resources can be most effectively allocated during complex emergency rescue processes. Through this optimization process, the resource allocation can be adjusted in a timely manner according to the actual situation, effectively meeting the resource requirements of each rescue task while avoiding resource waste. In large-scale disaster scenarios, optimized allocation can also ensure resource balance between different regions and tasks, avoiding over-concentration or shortage of resources and ensuring that all tasks can obtain the necessary support on time.

[0050] 2. The emergency rescue management optimization system based on AI algorithms proposed by the present invention is generally composed of a rescue capacity evaluation module, a resource demand prediction module, an emergency rescue ranking module, and an emergency rescue management module, and can implement any of the emergency rescue management optimization methods based on AI algorithms described in the present invention. It is used to realize the emergency rescue management optimization method based on AI algorithms through the operation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient emergency rescue management optimization process based on AI algorithms, thereby simplifying the operation process of the emergency rescue management optimization system based on AI algorithms. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Other features, objects, and advantages of the present invention will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings:

[0052] Figure 1 It is a schematic flowchart of the steps of the emergency rescue management optimization method based on AI algorithms of the present invention;

[0053] Figure 2 For Figure 1 it is a detailed schematic flowchart of step S1 in

[0054] Figure 3 For Figure 2 it is a detailed schematic flowchart of step S13 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The technical methods of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments in the present invention without creative efforts fall within the scope of protection of the present invention.

[0056] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0057] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0058] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides an optimization method for emergency rescue management based on AI algorithms, and the method includes the following steps:

[0059] Step S1: Obtain the quantity and location of various rescue resources and the status and performance of various rescue equipment corresponding to the emergency affected area; based on the quantity and location of various rescue resources, evaluate the status and performance of various rescue equipment to obtain the corresponding emergency rescue resource capabilities in the current area;

[0060] Step S2: Obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area; according to the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task, obtain the corresponding disaster spread speed and the number of affected people, and predict the corresponding emergency rescue resource requirements for each emergency rescue task;

[0061] Step S3: Based on the corresponding emergency rescue resource requirements for each emergency rescue task and in combination with the disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and the number of affected people, conduct an emergency priority ranking analysis for each emergency rescue task to generate the corresponding emergency rescue priority sequence in the current area;

[0062] Step S4: Optimize the emergency rescue deployment management of the corresponding emergency rescue priority sequence in the current area by aiming to maximize the rescue effect and combining the corresponding emergency rescue resource capabilities in the current area, so as to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue tasks.

[0063] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the step flow of the emergency rescue management optimization method based on the AI algorithm of the present invention. In this example, the emergency rescue management optimization method based on the AI algorithm includes the following steps:

[0064] Step S1: Obtain the quantity and location of various rescue resources and the status and performance of various rescue equipment through the emergency affected area; evaluate the status and performance of various rescue equipment based on the quantity and location of various rescue resources to obtain the corresponding emergency rescue resource capabilities in the current area;

[0065] In the embodiment of the present invention, the information of various rescue resources and equipment in the emergency affected area is obtained by using the Global Positioning System (GPS) devices and the sensor network. In terms of rescue resources, each supply box, equipment unit, etc. is equipped with a GPS tag, such as a fire hose box, a fire extinguisher box, etc., to transmit the location information in real time. At the same time, the quantity of various rescue resources is accurately recorded through the inventory management system. For example, there are 500 rolls of fire hoses and 300 fire extinguishers in the fire-fighting material warehouse. For rescue equipment, a variety of sensors are installed on equipment such as fire trucks and cranes. For example, vibration sensors monitor the engine operation status, and pressure sensors monitor the performance of the hydraulic system. Based on these data, the Analytic Hierarchy Process (AHP) is used to evaluate the rescue resource capabilities, and an evaluation model is constructed. The resource quantity, location convenience, equipment integrity rate, etc. are used as evaluation indicators, and emergency rescue experts are invited to score the importance of each indicator to determine the weight. For example, the weight of the resource quantity is 0.4, the weight of the location convenience is 0.3, and the weight of the equipment integrity rate is 0.3. The quantitative evaluation result of the emergency rescue resource capabilities in the current area is calculated, such as a comprehensive score of 80 points (full score of 100 points).

[0066] Step S2: Obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area; obtain the corresponding disaster spread speed and the number of affected people according to the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task, and predict the corresponding emergency rescue resource demand required for each emergency rescue task;

[0067] In the embodiments of the present invention, relevant information of each emergency rescue task within the emergency affected area is obtained by applying satellite remote sensing technology and geographic information system (GIS). Through satellite remote sensing images, image recognition algorithms are used to determine the type of disaster. For example, a fire presents specific high-temperature and smoke image characteristics, and an earthquake can be identified through signs such as ground deformation. In the GIS system, combined with high-precision terrain data and remote sensing images, the scale of the disaster distribution is measured. For example, the burned area of a certain forest fire is 3 square kilometers. Through census data and real-time population monitoring systems, the scale of the surrounding population distribution is determined. For example, the population living within 5 kilometers around the fire is 2,000 people. For the disaster spread speed, a time series analysis method is adopted. By comparing satellite images at different time periods, the disaster expansion speed is estimated. For example, a fire spreads 0.5 square kilometers per day. The number of affected people is estimated by analyzing factors such as population flow trends and the scope of the affected area. Based on this information, a long short-term memory network (LSTM) model based on deep learning is used to predict the demand for emergency rescue resources. The type of disaster, scale, spread speed, population quantity, etc. are used as input features. After training the model, it is predicted that, for example, a certain fire rescue task requires 300 firefighters, 20 fire trucks, 50 tons of fire extinguishing agents, etc. Finally, the demand for corresponding emergency rescue resources required for each emergency rescue task is obtained.

[0068] Step S3: Based on the demand for corresponding emergency rescue resources required for each emergency rescue task and combined with the type of disaster, the scale of disaster distribution, the scale of the surrounding population distribution, the disaster spread speed, and the number of affected people, perform an emergency priority ranking analysis on each emergency rescue task to generate a corresponding emergency rescue priority sequence within the current area;

[0069] In the embodiments of the present invention, by leveraging Python's data analysis libraries (such as NumPy and pandas) and the Analytic Hierarchy Process (AHP), an emergency priority ranking analysis is conducted for each emergency rescue task. By integrating the required emergency rescue resource demand for each emergency rescue task with the disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and the number of affected people into a data set, a hierarchical structure model is constructed. The target layer is the priority ranking of emergency rescue tasks, and the criterion layer includes the degree of resource demand, severity of the disaster, degree of impact on the affected population, etc. Experts in the field of emergency rescue are invited to make pairwise comparisons of the relative importance of each indicator in the criterion layer to construct a judgment matrix. For example, if an expert believes that the degree of resource demand is slightly more important than the severity of the disaster, the corresponding position in the judgment matrix is assigned a value of 3. By calculating the eigenvector of the judgment matrix, the weights of each indicator in the criterion layer are obtained. Then, a quantitative score is given to the data set of each emergency rescue task, and the comprehensive score is calculated in combination with the weights. The tasks are ranked from high to low according to the comprehensive score to generate the emergency rescue priority sequence in the current area. For example, Task A (earthquake rescue) has a comprehensive score of 90 points, and Task B (fire rescue) has a comprehensive score of 85 points, and the priority sequence is [Task A, Task B,...].

[0070] Step S4: Optimize the emergency rescue deployment management for the corresponding emergency rescue priority sequence in the current area by aiming at maximizing the rescue effect and combining the corresponding emergency rescue resource capabilities in the current area, so as to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue tasks.

[0071] In an embodiment of the present invention, by applying a linear programming algorithm, with the goal of maximizing the rescue effect, the emergency rescue deployment management of the emergency rescue priority sequence in the current area is optimized in combination with the emergency rescue resource capabilities in the current area. For example, for a certain fire rescue task in the priority sequence, it is known that the rescue resources required for this task are 250 firefighters, 15 fire trucks, and 40 tons of fire extinguishing agents. There are 3 fire rescue bases in the current area. Base A has 150 firefighters, 10 fire trucks, and 20 tons of fire extinguishing agents, and is 10 kilometers away from the fire scene; Base B has 100 firefighters, 8 fire trucks, and 15 tons of fire extinguishing agents, and is 15 kilometers away from the fire scene; Base C has 80 firefighters, 5 fire trucks, and 10 tons of fire extinguishing agents, and is 8 kilometers away from the fire scene. Taking the rescue effect (such as the fire extinguishing speed, the success rate of rescuing affected people, etc.) as the objective function, and taking the resource quantity, transportation distance, resource availability, etc. of each base as the constraint conditions, and solving through the linear programming algorithm, it is obtained that 150 firefighters, 10 fire trucks, and 20 tons of fire extinguishing agents are allocated from Base A, 100 firefighters, 5 fire trucks, and 15 tons of fire extinguishing agents are allocated from Base B, 0 firefighters, 0 fire trucks, and 5 tons of fire extinguishing agents are allocated from Base C, and the optimal transportation route is determined, such as from Base A to the fire scene via Main Road X and Secondary Road Y, so as to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue task.

[0072] Further, step S1 includes the following steps:

[0073] Step S11: Obtain the quantity and location corresponding to various rescue resources through the emergency affected area;

[0074] Step S12: Obtain the status and performance corresponding to various rescue equipment through the emergency affected area;

[0075] Step S13: Conduct equipment integrity assessment and analysis based on the status and performance corresponding to various rescue equipment to obtain the integrity probability corresponding to various rescue equipment;

[0076] Step S14: Conduct resource reserve statistics on the quantity and location corresponding to various rescue resources based on the integrity probability corresponding to various rescue equipment to obtain the corresponding rescue resource reserve in the area;

[0077] Step S15: Evaluate the rescue resource capabilities for the emergency affected area based on the corresponding rescue resource reserve in the area to obtain the corresponding emergency rescue resource capabilities in the current area.

[0078] As an embodiment of the present invention, referring to Figure 2 shown, for Figure 1 the detailed step flow diagram of step S1, in this embodiment, step S1 includes the following steps:

[0079] Step S11: Obtain the quantity and location of various rescue resources through the emergency disaster area;

[0080] In an embodiment of the present invention, positioning base stations are deployed in emergency disaster areas, and ultra-wideband (UWB) positioning technology is used to accurately locate various types of rescue resources. UWB tags are equipped for each type of rescue resource. For example, special UWB tags are installed on fire hose reels. At the same time, barcode or QR code technology is used to count the number of rescue resources. In a material warehouse, when staff members carry fire hose reels onto vehicles, they scan the QR code on the hoses with a scanning device, and the system automatically records the number. When a vehicle loaded with hoses enters the disaster area, the positioning base station receives the UWB tag signal and accurately obtains the position coordinates of the hose reels in the disaster area. Assuming that 50 fire hoses are deployed for this rescue operation, by scanning the code to count the number, combined with UWB positioning, the specific distribution locations of these 50 hoses in the disaster area can be clearly known, such as 10 hoses stored at a fire rescue point on a certain street.

[0081] Step S12: Obtaining the status and performance of various rescue equipment through the emergency disaster area;

[0082] In an embodiment of the present invention, multiple types of sensors are installed at various locations where firefighting and rescue equipment are stored in emergency disaster areas (such as fire disaster areas). For fire trucks, sensors are installed on key components such as engines, water tanks, and fire pumps. For example, a gas composition sensor is installed on the engine air intake to monitor the intake quality; a liquid level sensor is installed on the water tank to provide real-time feedback on the water level in the water tank; and a speed sensor is installed on the fire pump shaft to monitor the operating speed of the pump. These sensors transmit the collected data to a data aggregation center through low-power wide area network (LPWAN) technology, such as narrowband Internet of Things (NB-IoT). The data aggregation center uses data analysis algorithms to convert the original sensor data into intuitive equipment status and performance parameters. For example, by analyzing the gas composition sensor data, it is possible to determine whether the engine combustion is sufficient, thereby comprehensively obtaining the status and performance of various rescue equipment such as fire trucks.

[0083] Step S13: performing equipment integrity assessment and analysis based on the status and performance of each type of rescue equipment to obtain the integrity probability corresponding to each type of rescue equipment;

[0084] In an embodiment of the present invention, based on the previously obtained status and performance data of rescue equipment, the fault tree analysis method (FTA) is used to conduct a soundness assessment analysis of the equipment. Taking a crane as an example, a fault tree of the crane is constructed. The abnormal operation of the crane is used as the top event, and engine failure, hydraulic system failure, electrical system failure, etc. are used as intermediate events. Each intermediate event is further refined into specific bottom events. For example, engine failure can be refined into spark plug failure, fuel pump failure, etc. According to the data monitored by sensors, it is judged whether the bottom event occurs. If the bottom event occurs, according to the logical relationship of the fault tree, the probabilities of the intermediate event and the top event occurring are gradually deduced upward. Suppose through analysis, the probability of spark plug failure is 0.05, and the probability of fuel pump failure is 0.03. After fault tree operation, the probability of engine failure is obtained as 0.07, and then the overall soundness probability of the crane is 1 - 0.07 = 0.93. Similar fault tree analysis methods are adopted for various types of rescue equipment to obtain their corresponding soundness probabilities.

[0085] Step S14: Based on the soundness probabilities corresponding to various types of rescue equipment, conduct a resource reserve statistics on the quantity and location of various types of rescue resources to obtain the corresponding rescue resource reserve in the region.

[0086] In an embodiment of the present invention, through the soundness probabilities of various types of rescue equipment obtained previously, combined with the quantity and location information of the rescue resources obtained, a resource reserve statistics is carried out. For example, for medical rescue resources, it is known that there are 10 medical aid points, and each aid point has 10 sets of first aid equipment. The soundness probability of each set of first aid equipment is evaluated as 0.9. Then, through calculation, the actual available quantity of these first aid equipment can be obtained as 10×10×0.9 = 90 sets. At the same time, according to the location information of each medical aid point, these available first aid equipment are statistically analyzed according to the geographical location. For example, there are 3 medical aid points in Area A of the disaster area, and the available quantity of first aid equipment in this area is 3×10×0.9 = 27 sets. By analogy, for various types of rescue resources, such as fire rescue resources, living material rescue resources, etc., in this way, based on the equipment soundness probability, their quantity and location are statistically analyzed, and finally the corresponding rescue resource reserve in the entire region is obtained.

[0087] Step S15: Evaluate the rescue resource capacity for the emergency disaster area according to the corresponding rescue resource reserve in the region to obtain the corresponding emergency rescue resource capacity in the current region.

[0088] In the embodiments of the present invention, the analytic hierarchy process (AHP) is adopted to evaluate the rescue resource capabilities in the emergency affected areas. First, an evaluation index system is determined, including the quantity, distribution rationality, intact rate, etc. of rescue resources. A judgment matrix is constructed, and experts in the field of emergency rescue are invited to compare the relative importance of these indicators pairwise. For example, if the expert believes that the quantity of rescue resources is slightly more important than the distribution rationality, a value of 3 is assigned to the corresponding position in the judgment matrix. By calculating the eigenvector of the judgment matrix, the weights of each indicator are obtained. Then, the previously obtained data on the reserve quantity of rescue resources are quantified according to each indicator. For example, for the quantity of rescue resources, different quantification standards are set according to different resource types, and the actual reserve quantity is converted into the corresponding quantification score; the distribution rationality is scored according to the degree of uniform coverage of resources in the affected area. Finally, combining the weights of each indicator and the quantification scores, the comprehensive score of the corresponding emergency rescue resource capabilities in the current area is calculated to evaluate the emergency rescue resource capabilities.

[0089] Further, step S13 includes the following steps:

[0090] Step S131: Obtain the corresponding changes in the sizes of equipment components and the surface roughness of the equipment through the states of various rescue equipment.

[0091] Step S132: Perform equipment wear assessment calculations based on the corresponding changes in the sizes of equipment components and the surface roughness of various rescue equipment to obtain the wear degrees corresponding to various rescue equipment.

[0092] Step S133: Assign corresponding weights to each performance indicator within the performance of various rescue equipment through the analytic hierarchy process. Each performance indicator includes an equipment response indicator, an equipment operation indicator, and an equipment capacity indicator, and perform weighted calculations of performance scores according to the weights and the corresponding performance indicators to obtain the performance scores corresponding to various rescue equipment.

[0093] Step S134: Calculate the ratio between the wear degrees and the performance scores corresponding to various rescue equipment to obtain the intact probabilities corresponding to various rescue equipment.

[0094] As an embodiment of the present invention, referring to Figure 3 shown, it is Figure 2 a detailed step - by - step process schematic diagram of step S13. In this embodiment, step S13 includes the following steps:

[0095] Step S131: Obtain the corresponding changes in the sizes of equipment components and the surface roughness of the equipment through the states of various rescue equipment.

[0096] In the embodiments of the present invention, for various rescue devices, a high-precision laser measuring instrument is used to obtain the dimensional changes of device components. Taking the ladder arm of a fire truck as an example, at the key parts of the ladder arm, such as the connection points of each section of the arm and the telescopic joints, multiple laser measuring instrument measurement points are set. The laser measuring instrument emits a laser beam, and by measuring the time for the laser to reflect back, the distance between the measurement point and the surface of the device component is accurately calculated, so as to obtain the initial dimensional data of the component. Regular measurements (such as weekly) are carried out, and the newly measured data is compared with the initial data to obtain the dimensional changes of the component. At the same time, a profilometer is used to measure the surface roughness of the device. The probe of the profilometer is slowly moved along the surface of the fire truck body, the ladder arm, etc. The sensor of the probe will generate an electrical signal according to the microscopic undulations of the surface. The circuit inside the profilometer converts the electrical signal into a digital signal and calculates the surface roughness parameters according to the standard algorithm, so as to comprehensively obtain the dimensional changes of the device components corresponding to various rescue devices and the surface roughness of the device.

[0097] Step S132: Perform equipment wear assessment calculations based on the dimensional changes of the device components corresponding to various rescue devices and the surface roughness of the device, so as to obtain the wear degrees corresponding to various rescue devices;

[0098] In the embodiments of the present invention, based on the obtained dimensional changes of the device components and the surface roughness data, an empirical formula combined with database comparison is used to perform equipment wear assessment calculations. A rescue equipment wear assessment database is established. The database stores the corresponding relationships between the dimensional change ranges, surface roughness values, and wear degrees of different types of rescue devices under different service years and working conditions. For example, for the impeller of a fire pump, if its dimensional change exceeds 10% of the normal range in the database within a certain period of time and the surface roughness increases by 0.5 μm, by querying the database and combining the pre-set empirical formula: wear degree = dimensional change influence coefficient × dimensional change ratio + surface roughness influence coefficient × surface roughness increase value. Assuming that the dimensional change influence coefficient is 0.6 and the surface roughness influence coefficient is 0.4, the calculated wear degree of the impeller of this fire pump is 0.6×0.1 + 0.4×0.5 = 0.26. By analogy, the wear degrees corresponding to various rescue devices are obtained.

[0099] Step S133: Assign corresponding weights to each performance index within the performance of various rescue devices through the analytic hierarchy process. Each performance index includes an equipment response index, an equipment operation index, and an equipment capacity index, and perform weighted calculations of the performance scores according to the weights and the corresponding performance indexes, so as to obtain the performance scores corresponding to various rescue devices;

[0100] In an embodiment of the present invention, the analytic hierarchy process (AHP) is used to assign corresponding weights to each performance index within the performance corresponding to various rescue devices. Taking a crane as an example, first, a hierarchical structure model is constructed. The target layer is the crane performance evaluation, the criterion layer is the equipment response index, the equipment operation index, and the equipment capacity index, and the index layer is refined into specific indexes such as start response time, operation smoothness, and lifting weight. Experts in the field of emergency rescue are invited to compare the relative importance of each index in the criterion layer pairwise to construct a judgment matrix. For example, if the expert believes that the equipment capacity index is slightly more important than the equipment response index, the corresponding position in the judgment matrix is assigned a value of 3. By calculating the eigenvector of the judgment matrix, the weights of each criterion layer index are obtained. Suppose the weight of the equipment response index is 0.2, the weight of the equipment operation index is 0.3, and the weight of the equipment capacity index is 0.5. Then, the index layer indexes are quantitatively scored. For example, if the start response time is within 1 second, the score is 10 points, if the operation smoothness is good, the score is 8 points, and if the lifting weight reaches the rated value, the score is 10 points. The performance score is calculated by weighting according to the weights: Performance score = Equipment response index weight × Equipment response index score + Equipment operation index weight × Equipment operation index score + Equipment capacity index weight × Equipment capacity index score. That is, the crane performance score = 0.2×10 + 0.3×8 + 0.5×10 = 9.4, so as to obtain the performance scores corresponding to various rescue devices.

[0101] Step S134: Calculate the ratio between the wear degree corresponding to various rescue devices and the performance score to obtain the intact probability corresponding to various rescue devices.

[0102] In an embodiment of the present invention, by calculating the ratio according to the wear degree corresponding to various rescue devices and the performance score, the equipment intact probability is determined. Suppose the wear degree of a certain type of fire rescue equipment is 0.3, the performance score is 8 points, and the reference score is 10 (i.e., full score). The formula for calculating the equipment intact probability is: Intact probability = (Reference performance score - Wear degree × Performance score) / Reference performance score. Substituting the data, the intact probability of this equipment = (10 - 0.3×8) / 10 = 0.76. For all types of rescue devices, calculations are performed according to this formula using the obtained wear degree and performance score, so as to obtain the intact probabilities corresponding to various rescue devices, providing key data support for subsequent rescue resource reserve statistics and emergency rescue resource capacity evaluation.

[0103] Further, step S14 includes the following steps:

[0104] Step S141: Based on the intact probabilities corresponding to various rescue equipment, conduct an intact correction analysis on the quantities corresponding to various rescue resources. If the corresponding intact probability is less than 50%, subtract one from the quantity corresponding to the corresponding type of rescue resource; otherwise, keep it unchanged, so as to obtain the complete quantities corresponding to various rescue resources through correction and update.

[0105] In the embodiment of the present invention, for various rescue resources, an intact correction analysis is conducted on their quantities one by one according to the intact probabilities of the corresponding rescue equipment. Taking fire extinguishers as an example, assume there are 50 fire extinguishers in total. Through the previous status assessment of rescue equipment such as the pressure detection equipment and nozzle unobstructed detection equipment supporting the fire extinguishers, it is obtained that the intact probability of these equipment is 40%, which is less than 50%. At this time, according to the rule, subtract one from the quantity of fire extinguishers, that is, the corrected quantity of fire extinguishers is 49. If the intact probability of the detection equipment associated with a certain type of fire hose is 60%, which is greater than 50%, the quantity of this type of fire hose remains unchanged at the initially counted 30. For each type of rescue resource, such as first aid kits, fire axes, etc., strictly follow this logic to correct the quantity based on the intact probability of the corresponding rescue equipment, so as to obtain the complete quantities corresponding to various rescue resources through correction and update.

[0106] Step S142: Evaluate the resource convenience based on the locations corresponding to various rescue resources, so as to obtain the location reserve convenience degrees corresponding to various rescue resources.

[0107] In the embodiment of the present invention, by using the Geographic Information System (GIS) technology, evaluate the resource convenience based on the locations corresponding to various rescue resources, that is, import the location information of various rescue resources, such as longitude and latitude coordinates, into the GIS system. In the GIS system, analyze by combining the road network data, population distribution data, and building distribution data of the disaster-stricken area. For example, for a medical first aid point located beside the main road in the disaster-stricken area and with a dense population around it, its location reserve convenience degree is relatively high, because rescue personnel can quickly reach this first aid point through the main road to obtain supplies and can quickly provide services to a large number of affected people around. For a rescue supply storage point located in a remote mountainous area with inconvenient transportation and a sparse population around it, its location reserve convenience degree is relatively low. Through the spatial analysis function of the GIS system, quantitatively evaluate the location of each rescue resource. For example, set the convenience degree from 0 - 10 points, and comprehensively score according to factors such as the traffic and population around the location, so as to obtain the location reserve convenience degrees corresponding to various rescue resources.

[0108] Step S143: Determine the resource reserve verification of the complete quantities corresponding to various rescue resources according to the location reserve convenience degrees corresponding to various rescue resources, so as to obtain the corresponding rescue resource reserve quantity in the region.

[0109] In an embodiment of the present invention, the verified quantity after correction is determined by verifying the resource reserve according to the reserve convenience degree corresponding to various types of rescue resources obtained previously. For example, for a certain type of fire sandbag, the verified quantity after correction is 80 bags, and the reserve convenience degree score of the storage location is 8 points (a high score represents a high convenience degree). Considering that the location is convenient, the materials are easy to access and can efficiently serve the disaster-stricken area, it is considered that the reserve quantity of these 80 fire sandbags is reasonable and is included in the statistics of the rescue resource reserve quantity in the area. However, for a type of fireproof clothing with a reserve convenience degree of only 3 points (a low score represents a low convenience degree) at another storage location, even if the verified quantity after correction is 50 sets, due to the inconvenience of access and the difficulty in effectively serving the disaster-stricken area, its reserve quantity will be adjusted according to the actual situation, such as increasing the quantity to ensure that the rescue needs can be met even in an unfavorable location. Finally, considering the situations of various types of rescue resources, the corresponding rescue resource reserve quantity in the area is obtained.

[0110] Further, step S142 includes the following steps:

[0111] Precisely determine the corresponding reserve locations of various types of rescue resources in the emergency disaster-stricken area to obtain the regional reserve locations corresponding to various types of rescue resources;

[0112] In an embodiment of the present invention, by combining the Global Positioning System (GPS) and the Geographic Information System (GIS), the reserve locations of various types of rescue resources in the emergency disaster-stricken area are precisely determined. High-precision GPS positioning devices are equipped for the storage facilities of each type of rescue resource, such as fire-fighting material warehouses, medical rescue points, etc., to obtain their longitude and latitude coordinates in real time. These coordinate information are imported into the GIS system. In the system, by matching with the detailed map data of the disaster-stricken area, the specific locations of various types of rescue resources can be clearly and intuitively marked, thereby obtaining the regional reserve locations corresponding to various types of rescue resources. For example, after obtaining the coordinates of a large emergency material reserve center through GPS positioning, it is clear in the GIS system that it is located in the south-central part of the disaster-stricken area, and the geographical information such as surrounding roads and buildings is clear at a glance, which is convenient for subsequent analysis of its relationship with the disaster rescue task locations.

[0113] Preferably, calculate the rescue transportation distance between the regional reserve locations corresponding to various types of rescue resources and the corresponding disaster rescue task locations in the emergency disaster-stricken area to obtain the rescue transportation distance between various types of rescue reserve resources and the disaster rescue task locations;

[0114] In an embodiment of the present invention, in the GIS system, by using the path analysis function, based on the regional reserve locations corresponding to various rescue resources, the rescue transportation distances are calculated between the corresponding disaster relief task locations in the emergency affected area. Taking a fire rescue task as an example, in the GIS system, the locations of the fire fighting material reserve warehouse and the fire occurrence location are respectively marked. According to the built-in road network data, path search algorithms such as the Dijkstra algorithm or the A* algorithm are used to calculate the shortest path from the fire fighting material reserve warehouse to the fire occurrence location, and the length of this path is the rescue transportation distance. Suppose the shortest rescue transportation distance from Fire Fighting Material Reserve Warehouse A to a certain fire scene is calculated by the system to be 5 kilometers. In this way, the rescue transportation distances between various rescue reserve resources and the disaster relief task locations can be obtained, providing basic data for subsequent analysis.

[0115] Preferably, according to the rescue transportation distances between various rescue reserve resources and the disaster relief task locations, the number of rescue transportation paths corresponding to various rescue resources and the traffic volume of transportation hubs are determined;

[0116] In an embodiment of the present invention, by means of traffic big data analysis technology, according to the rescue transportation distances between various rescue reserve resources and the disaster relief task locations, the number of rescue transportation paths corresponding to various rescue resources and the traffic volume of transportation hubs are determined. The historical traffic flow data, road passing capacity data, etc. in the affected area are collected to construct a traffic model. When the transportation distance of a certain type of rescue resource from the reserve location to the disaster relief task location is known, such as the transportation distance from Medical Rescue Point B to a temporary resettlement point for affected people is 3 kilometers, the traffic model will analyze the possible transportation paths from Medical Rescue Point B to this resettlement point according to the historical traffic data and the current road conditions. Suppose it is analyzed that there are 3 feasible paths. At the same time, by analyzing the historical traffic flow data of the transportation hubs (such as main intersections, bridges, etc.) passed by these paths, the possible traffic volume of each transportation hub during the emergency rescue period is calculated. For example, in previous similar emergencies, the average number of vehicles passing through a certain transportation hub per hour is 200. In this way, the number of rescue transportation paths corresponding to various rescue resources and the traffic volume of transportation hubs are determined.

[0117] Preferably, based on the number of rescue transportation paths corresponding to various rescue resources and the traffic volume of transportation hubs, the resource convenience of the locations corresponding to various rescue resources is evaluated to obtain the location reserve convenience degree corresponding to various rescue resources.

[0118] In the embodiments of the present invention, based on the number of rescue transportation paths corresponding to various rescue resources and the traffic volume of transportation hubs, the analytic hierarchy process (AHP) is used to evaluate the location convenience of various rescue resources, so as to obtain the location reserve convenience degree corresponding to various rescue resources. By constructing a hierarchical structure model, the target layer is the evaluation of the location convenience of rescue resources, and the criterion layer is the number of rescue transportation paths and the traffic volume of transportation hubs. Experts in the field of emergency rescue are invited to compare the relative importance of each indicator in the criterion layer pairwise to construct a judgment matrix. Suppose the expert believes that the number of rescue transportation paths is slightly more important than the traffic volume of transportation hubs, and the corresponding position in the judgment matrix is assigned a value of 3. By calculating the eigenvector of the judgment matrix, the weights of each criterion layer indicator are obtained. For example, the weight of the number of rescue transportation paths is 0.6, and the weight of the traffic volume of transportation hubs is 0.4. For the locations of various rescue resources, quantitative scores are given according to the number of their rescue transportation paths and the traffic volume of transportation hubs. For example, a certain rescue resource location has 5 rescue transportation paths and a small traffic volume of the transportation hub, and the score is 8 points. Calculated according to the weights: the location reserve convenience degree = the weight of the number of rescue transportation paths × the score of the number of rescue transportation paths + the weight of the traffic volume of the transportation hub × the score of the traffic volume of the transportation hub = 0.6×8 + 0.4×6 = 7.2 points. In this way, the location reserve convenience degree corresponding to various rescue resources is obtained.

[0119] Further, step S2 includes the following steps:

[0120] Step S21: Obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area.

[0121] In the embodiments of the present invention, relevant information of the emergency affected area is obtained by using satellite remote sensing technology, geographic information system (GIS), and census data. Through high-resolution satellite remote sensing images, image recognition algorithms are used to process the images to identify different ground object types, so as to determine the disaster type corresponding to each emergency rescue task, such as fire, flood, etc. In the GIS system, high-precision terrain data and satellite images are loaded, combined with the image recognition results, and the disaster distribution scale is accurately measured through an area calculation tool. At the same time, the population distribution data around the affected area is extracted from the latest census database, and the surrounding population distribution scale is screened according to the regional boundary range. For example, in a fire rescue task occurring in a certain city, the satellite remote sensing image identifies the fire area, the GIS system measures the fire distribution scale to be 2 square kilometers, and through the census data, it is known that the population distribution scale within 2 kilometers around is 5000 people.

[0122] Step S22: Set the corresponding disaster observation window size according to the corresponding disaster type, and perform a time-series analysis of the disaster distribution scale and the surrounding population distribution scale corresponding to each emergency rescue task based on the disaster observation window size, so as to obtain the change sequence of the disaster distribution area and the change sequence of the population quantity distribution corresponding to each emergency rescue task under the corresponding window;

[0123] In the embodiment of the present invention, by setting the corresponding disaster observation window size according to the disaster type, for a fire disaster, since its spread speed is relatively fast, the observation window is set to 1 hour; for a flood disaster, since its development is relatively slow, the observation window is set to 6 hours. In the GIS system, using the time-series analysis tool, analyze the disaster distribution scale and the surrounding population distribution scale corresponding to each emergency rescue task with the set observation window. For example, for the above-mentioned fire rescue task, measure the fire distribution scale once per hour for 5 consecutive times, and obtain the change sequence of the fire distribution area as [2.1 square kilometers, 2.3 square kilometers, 2.5 square kilometers, 2.7 square kilometers, 2.9 square kilometers]. At the same time, for the surrounding population distribution scale, at an interval of 1 hour, count the dynamic changes of the population around the disaster area, and obtain the change sequence of the population quantity distribution, such as [4800 people, 4500 people, 4200 people, 3900 people, 3600 people], so as to obtain the change sequence corresponding to each emergency rescue task under the corresponding window.

[0124] Step S23: Estimate the disaster spread speed according to the change sequence of the disaster distribution area corresponding to each emergency rescue task under the corresponding window, so as to obtain the disaster spread speed corresponding to each emergency rescue task;

[0125] In the embodiment of the present invention, by using the linear regression algorithm to estimate the disaster spread speed according to the change sequence of the disaster distribution area corresponding to each emergency rescue task under the corresponding window. Taking the fire rescue task as an example, take the area values in the change sequence of the fire distribution area as the dependent variable, and the time (in units of the observation window) as the independent variable. For the above-mentioned change sequence of the fire distribution area, the corresponding time sequence is [1 hour, 2 hours, 3 hours, 4 hours, 5 hours]. Calculate the linear relationship between the area and time through the linear regression algorithm. Suppose the obtained regression equation is y = 0.2x + 2 (where y is the fire distribution area and x is the time). The slope 0.2 of this equation is the disaster spread speed corresponding to the fire under this observation window, with the unit of square kilometers per hour. In this way, the disaster spread speed corresponding to each emergency rescue task is obtained.

[0126] Step S24: Estimate the affected population according to the change sequence of the population quantity distribution corresponding to each emergency rescue task under the corresponding window, so as to obtain the number of affected people corresponding to each emergency rescue task;

[0127] In the embodiment of the present invention, by using the moving average method to estimate the affected population according to the sequence of changes in the population quantity distribution corresponding to each emergency rescue task under the corresponding window. Continuing with the above example of the fire rescue task, for the sequence of changes in the population quantity distribution [4800 people, 4500 people, 4200 people, 3900 people, 3600 people], set the moving average window to 3. First, calculate the average value of the first three data, that is, (4800 + 4500 + 4200) / 3 = 4500 people; then move one data backward in turn and calculate (4500 + 4200 + 3900) / 3 = 4200 people, and so on. Finally, obtain the estimated value of the affected population quantity. Assume that after moving average calculation, the affected population quantity corresponding to this fire rescue task stabilizes at about 4000 people. In this way, the affected population quantity corresponding to each emergency rescue task is obtained.

[0128] Step S25: Based on the disaster spread speed and the affected population quantity corresponding to each emergency rescue task, and combined with the AI algorithm, predict the rescue resource requirements for the corresponding emergency rescue tasks in the emergency affected area, so as to predict the required corresponding emergency rescue resource quantities for each emergency rescue task.

[0129] In the embodiment of the present invention, by using the long short-term memory network (LSTM) model based on deep learning combined with the AI algorithm to predict the rescue resource requirements for the corresponding emergency rescue tasks in the emergency affected area based on the disaster spread speed and the affected population quantity corresponding to each emergency rescue task. Take the disaster spread speed, the affected population quantity, and other relevant features (such as the one-hot encoding of the disaster type, etc.) as input data to train the LSTM model. For example, for the fire rescue task, input the fire spread speed (such as 0.2 square kilometers per hour), the affected population quantity (4000 people), and the fire type encoding (such as 1 represents forest fire, 2 represents urban fire, etc.) into the trained LSTM model. After learning and calculation by the model, output the required corresponding emergency rescue resource quantities for each emergency rescue task. For example, it is predicted that this fire rescue task requires 300 fire rescue personnel, 20 fire trucks, 50 tons of fire extinguishing agents, etc. In this way, the required corresponding emergency rescue resource quantities for each emergency rescue task are predicted.

[0130] Further, the emergency rescue resource quantities described in step S25 include the required quantities corresponding to rescue personnel, rescue equipment, and rescue supplies.

[0131] Further, step S3 includes the following steps:

[0132] Step S31: Generate an emergency rescue task vector matrix by combining the required amounts of emergency rescue resources corresponding to each emergency rescue task with the corresponding disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and the number of affected people to form corresponding emergency rescue data vectors and constituting corresponding vector matrices.

[0133] In the embodiment of the present invention, an emergency rescue task vector matrix is constructed by using the NumPy library of Python as a tool. First, for each emergency rescue task, the required amounts of emergency rescue resources, such as the number of rescue personnel, the number of rescue equipment, and the amount of rescue supplies, are integrated with the disaster type corresponding to the task (which can be encoded by numbers, for example, 1 represents an earthquake, 2 represents a fire, etc.), the disaster distribution scale (in square kilometers), the surrounding population distribution scale (counting the specific number of people), the disaster spread speed (the area change per unit time, such as square kilometers per hour), and the number of affected people. For example, for a fire rescue task that requires 200 firefighters, 15 fire trucks, and 30 tons of fire extinguishing agents, with a disaster type code of 2, a disaster distribution scale of 1.5 square kilometers, a surrounding population distribution scale of 3000 people, a disaster spread speed of 0.1 square kilometers per hour, and a number of affected people of 1000, these data are combined into a vector [200, 15, 30, 2, 1.5, 3000, 0.1, 1000]. The same operation is performed on all emergency rescue tasks, and these vectors are used as rows to construct a two-dimensional vector matrix, thereby generating an emergency rescue task vector matrix.

[0134] Step S32: Calculate the eigenvalues through the corresponding sub-vectors in the emergency rescue task vector matrix to obtain the vector eigenvalues corresponding to each emergency rescue task sub-vector.

[0135] In an embodiment of the present invention, by also using the NumPy library of Python to calculate the eigenvalues of each sub-vector within the previously generated emergency rescue task vector matrix, the NumPy library provides efficient linear algebra calculation capabilities. For each sub-vector in the matrix (i.e., each row of data), the eigenvalue decomposition algorithm is used. For example, for a certain row vector [200, 15, 30, 2, 1.5, 3000, 0.1, 1000] in the emergency rescue task vector matrix, by calling relevant functions of NumPy, such as the numpy.linalg.eigvals function, to process this vector, this function will calculate the eigenvalues reflecting the characteristics of the vector according to the relationships between the elements of the vector. The calculated eigenvalues can comprehensively reflect the characteristics of the emergency rescue task in terms of resource requirements, disaster conditions, etc. For example, after calculation, the vector eigenvalue corresponding to this sub-vector is 5.67 (the specific value is obtained according to the calculation). In this way, the vector eigenvalues corresponding to each emergency rescue task sub-vector are obtained.

[0136] Step S33: Based on the vector eigenvalues corresponding to each emergency rescue task sub-vector, perform emergency priority sorting on each emergency rescue task within the emergency affected area from largest to smallest to generate the corresponding emergency rescue priority sequence within the current area.

[0137] In an embodiment of the present invention, by using the sorting function of Python based on the vector eigenvalues corresponding to each emergency rescue task sub-vector to process them, thereby performing emergency priority sorting on each emergency rescue task within the emergency affected area from largest to smallest. For example, assume that the vector eigenvalues corresponding to 5 previously obtained emergency rescue task sub-vectors are [8.2, 5.67, 6.5, 4.1, 7.8] respectively. Using the sorted function of Python combined with the reverse=True parameter to sort these eigenvalues, the sorted result is [8.2, 7.8, 6.5, 5.67, 4.1]. At the same time, record the emergency rescue task numbers corresponding to each eigenvalue, and according to the sorting result, arrange the corresponding emergency rescue tasks in descending order of eigenvalues to generate the corresponding emergency rescue priority sequence within the current area. For example, if the eigenvalue 8.2 corresponds to Task A and 7.8 corresponds to Task C, then the emergency rescue priority sequence is [Task A, Task C,...]. In this way, it can be clearly determined which emergency rescue tasks need to be carried out first, providing a basis for reasonably allocating rescue resources.

[0138] Further, step S4 includes the following steps:

[0139] Step S41: Obtain the corresponding emergency rescue resource transportation and availability constraints through the emergency rescue resource capabilities within the current area;

[0140] In the embodiment of the present invention, by means of the Geographic Information System (GIS) and the resource management database, the transportation and availability constraints of the corresponding emergency rescue resources in the current area are obtained. In the GIS system, detailed road network data are stored, including information such as the length, traffic capacity, and congestion condition of the roads. By docking with the resource management database, the inventory quantity, storage location, and available status of various emergency rescue resources (such as whether the equipment is in good condition, whether the materials are sufficient, etc.) can be obtained. For example, there are 3 fire material storage points in a certain area. Through the resource management database, it is known that storage point A has 50 tons of fire extinguishing agents, storage point B has 30 tons, and storage point C has 20 tons. Also, the number of transport vehicles and the deployable situation at each storage point are recorded. At the same time, the GIS system shows that the road length from storage point A to a certain fire rescue mission location is 10 kilometers, the road traffic capacity is 50 vehicles per hour, and the current congestion index is 0.3. Combining these information, the transportation and availability constraints of emergency rescue resources are determined, including the limit of the available quantity of resources, the road traffic restrictions during transportation, etc.

[0141] Step S42: Optimize the emergency rescue deployment management for each rescue mission in the corresponding emergency rescue priority sequence in the current area by aiming at maximizing the rescue effect and combining the transportation and availability constraints of the corresponding emergency rescue resources in the current area, so as to reasonably arrange the emergency rescue resources corresponding to each rescue mission considering the transportation distance, transportation time, and resource availability factors of the emergency rescue resources, and select the optimal corresponding emergency rescue resource transportation route to generate the decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue mission.

[0142] In the embodiment of the present invention, by applying the linear programming algorithm, with the goal of maximizing the rescue effect, combined with the previously obtained constraints on the transportation and availability of emergency rescue resources, the emergency rescue deployment management of each rescue task in the corresponding emergency rescue priority sequence in the current area is optimized. Taking an earthquake rescue task as an example, this task is at the forefront of the priority sequence. It is known that the rescue resources required for this task are: 200 rescue personnel, 5 life detectors, and 300 first-aid kits. According to the constraints on resource transportation and availability, there are multiple resource supply points to choose from. Suppose 200 rescue personnel are transported from the A rescue base, with a distance of 15 kilometers and an estimated transportation time of 2 hours. There are 300 deployable rescue personnel at this base; 5 life detectors are transported from the B warehouse, with a distance of 8 kilometers and a transportation time of 1 hour. There are 8 life detectors in the B warehouse; 300 first-aid kits are transported from the C medical supplies reserve center, with a distance of 12 kilometers and a transportation time of 1.5 hours. There are 400 first-aid kits in the C center. Through the linear programming algorithm, taking the rescue effect (such as the number of successfully rescued people, rescue efficiency, etc.) as the objective function and taking the transportation distance, transportation time, resource availability, etc. as the constraint conditions for solution, it is finally obtained that 200 rescue personnel are deployed from the A rescue base, 5 life detectors are deployed from the B warehouse, and 300 first-aid kits are deployed from the C medical supplies reserve center, and the optimal transportation route is determined. For example, the optimal route from the A rescue base to the earthquake rescue point is through main road A and secondary road B, so as to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue task.

[0143] Furthermore, the present invention also provides an emergency rescue management optimization system based on the AI algorithm for executing the emergency rescue management optimization method based on the AI algorithm as described above. The emergency rescue management optimization system based on the AI algorithm includes:

[0144] A rescue capacity evaluation module, which is used to obtain the quantity and location of various rescue resources corresponding to the emergency affected area and the status and performance of various rescue equipment; evaluate the status and performance of various rescue equipment based on the quantity and location of various rescue resources corresponding to obtain the corresponding emergency rescue resource capacity in the current area;

[0145] A resource demand prediction module, which is used to obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area; obtain the corresponding disaster spread speed and the number of affected people according to the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task, and predict the required emergency rescue resource demand corresponding to each emergency rescue task;

[0146] An emergency rescue prioritization module, which is used to perform emergency priority ranking analysis on each emergency rescue task based on the required emergency rescue resource demand corresponding to each emergency rescue task and in combination with the disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and the number of affected people, so as to generate a corresponding emergency rescue priority sequence within the current area;

[0147] An emergency rescue management module, which is used to optimize the emergency rescue deployment management of the corresponding emergency rescue priority sequence within the current area by aiming at maximizing the rescue effect and in combination with the corresponding emergency rescue resource capacity within the current area, so as to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue task.

[0148] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application document within the present invention.

[0149] The above description is only a specific implementation manner of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An optimization method for emergency rescue management based on AI algorithms, characterized in that, Including the following steps: Step S1: Obtain the quantity and location of various rescue resources and the status and performance of various rescue equipment through the emergency affected area; based on the quantity and location of various rescue resources, evaluate the status and performance of various rescue equipment to obtain the corresponding emergency rescue resource capabilities in the current area; Step S2: Obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area; based on the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task, obtain the corresponding disaster spread speed and the number of affected people, and predict the corresponding emergency rescue resource requirements for each emergency rescue task; Step S3: Based on the corresponding emergency rescue resource requirements for each emergency rescue task and combined with the disaster type, disaster distribution scale, surrounding population distribution scale, disaster spread speed, and the number of affected people, conduct an emergency priority ranking analysis for each emergency rescue task to generate the corresponding emergency rescue priority sequence in the current area; Step S4: Optimize the emergency rescue deployment management of the corresponding emergency rescue priority sequence in the current area with the goal of maximizing the rescue effect and combined with the corresponding emergency rescue resource capabilities in the current area to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue tasks.

2. The emergency rescue management optimization method based on the AI algorithm according to claim 1, characterized in that Step S1 includes the following steps: Step S11: Obtain the quantity and location of various rescue resources through the emergency affected area; Step S12: Obtain the status and performance of various rescue equipment through the emergency affected area; Step S13: Conduct an equipment integrity assessment analysis based on the status and performance of various rescue equipment to obtain the integrity probability of various rescue equipment; Step S14: Based on the integrity probability of various rescue equipment, conduct a resource reserve statistics on the quantity and location of various rescue resources to obtain the corresponding rescue resource reserve in the area; Step S15: Based on the corresponding rescue resource reserve in the area, evaluate the rescue resource capabilities of the emergency affected area to obtain the corresponding emergency rescue resource capabilities in the current area.

3. The emergency rescue management optimization method based on the AI algorithm according to claim 2, wherein, Step S13 includes the following steps: Step S131: Obtain the corresponding equipment component size change and equipment surface roughness through the status of various rescue equipment; Step S132: Conduct an equipment wear assessment calculation based on the equipment component size change and equipment surface roughness of various rescue equipment to obtain the wear degree of various rescue equipment; Step S133: Assign corresponding weights to each performance index within the performance of various rescue equipment through the analytic hierarchy process, where each performance index includes an equipment response index, an equipment operation index, and an equipment capacity index, and conduct a weighted calculation of the performance scores based on the weights and the corresponding performance indexes to obtain the performance scores of various rescue equipment; Step S134: Conduct a ratio calculation between the wear degree and the performance score of various rescue equipment to obtain the integrity probability of various rescue equipment.

4. The emergency rescue management optimization method based on the AI algorithm according to claim 2, characterized in that, Step S14 includes the following steps: Step S141: Based on the intact probabilities corresponding to various rescue equipment, conduct an intact correction analysis on the quantities corresponding to various rescue resources. If the corresponding intact probability is less than 50%, subtract one from the quantity corresponding to the corresponding type of rescue resource; otherwise, keep it unchanged, so as to correct and update to obtain the complete quantities corresponding to various rescue resources; Step S142: Evaluate the resource convenience based on the locations corresponding to various rescue resources to obtain the location reserve convenience levels corresponding to various rescue resources; Step S143: Determine the resource reserve verification of the complete quantities corresponding to various rescue resources according to the location reserve convenience levels corresponding to various rescue resources, so as to obtain the corresponding rescue resource reserve quantities within the region.

5. The emergency rescue management optimization method based on the AI algorithm according to claim 4, characterized in that, Step S142 includes the following steps: Precisely determine the corresponding reserve locations within the emergency disaster-affected area through the locations corresponding to various rescue resources, so as to obtain the regional reserve locations corresponding to various rescue resources; Calculate the rescue transportation distances between the regional reserve locations corresponding to various rescue resources and the corresponding disaster rescue task locations within the emergency disaster-affected area, so as to obtain the rescue transportation distances between various rescue reserve resources and the disaster rescue task locations; Determine the number of rescue transportation paths and the traffic volume of transportation hubs corresponding to various rescue resources according to the rescue transportation distances between various rescue reserve resources and the disaster rescue task locations; Evaluate the resource convenience of the locations corresponding to various rescue resources based on the number of rescue transportation paths and the traffic volume of transportation hubs corresponding to various rescue resources, so as to obtain the location reserve convenience levels corresponding to various rescue resources.

6. The emergency rescue management optimization method based on the AI algorithm according to claim 1, characterized in that Step S2 includes the following steps: Step S21: Obtain the disaster types, disaster distribution scales, and surrounding population distribution scales corresponding to each emergency rescue task through the emergency disaster-affected area; Step S22: Set the corresponding disaster observation window sizes according to the corresponding disaster types, and conduct a distribution scale time series analysis on the disaster distribution scales and surrounding population distribution scales corresponding to each emergency rescue task based on the disaster observation window sizes, so as to obtain the disaster distribution area change sequences and population quantity distribution change sequences corresponding to each emergency rescue task under the corresponding windows; Step S23: Estimate the disaster spread speed according to the disaster distribution area change sequences corresponding to each emergency rescue task under the corresponding windows, so as to obtain the disaster spread speeds corresponding to each emergency rescue task; Step S24: Estimate the affected population according to the population quantity distribution change sequences corresponding to each emergency rescue task under the corresponding windows, so as to obtain the affected population quantities corresponding to each emergency rescue task; Step S25: Based on the disaster spread speeds and affected population quantities corresponding to each emergency rescue task and combined with the AI algorithm, predict the rescue resource requirements for the corresponding emergency rescue tasks within the emergency disaster-affected area, so as to predict the required quantities of corresponding emergency rescue resources for each emergency rescue task.

7. The emergency rescue management optimization method based on the AI algorithm according to claim 6, wherein The required quantities of emergency rescue resources in Step S25 include the required quantities corresponding to rescue personnel, rescue equipment, and rescue supplies.

8. The emergency rescue management optimization method based on the AI algorithm according to claim 1, wherein, Step S3 includes the following steps: Step S31: Generate an emergency rescue task vector matrix by combining the required emergency rescue resource demands corresponding to each emergency rescue task with the corresponding disaster type, disaster distribution scale, surrounding population distribution scale, disaster spreading speed, and the number of affected people, and forming a corresponding vector matrix. Step S32: Calculate the eigenvalues through the corresponding sub-vectors within the emergency rescue task vector matrix to obtain the vector eigenvalues corresponding to each emergency rescue task sub-vector. Step S33: Based on the vector eigenvalues corresponding to each emergency rescue task sub-vector, perform emergency priority sorting on each emergency rescue task within the emergency affected area from largest to smallest to generate the corresponding emergency rescue priority sequence within the current area.

9. The emergency rescue management optimization method based on the AI algorithm according to claim 1, characterized in that Step S4 includes the following steps: Step S41: Obtain the corresponding emergency rescue resource transportation and availability constraints through the emergency rescue resource capabilities within the current area. Step S42: Optimize the emergency rescue deployment management for each rescue task within the corresponding emergency rescue priority sequence within the current area by aiming to maximize the rescue effect and combining the corresponding emergency rescue resource transportation and availability constraints within the current area. Reasonably arrange the emergency rescue resources corresponding to each rescue task considering the transportation distance, transportation time, and resource availability factors of the emergency rescue resources, and select the optimal corresponding emergency rescue resource transportation route to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue task.

10. An emergency rescue management optimization system based on AI algorithms, characterized in that, For implementing the emergency rescue management optimization method based on the AI algorithm as described in Claim 1, the emergency rescue management optimization system based on the AI algorithm includes: A rescue capacity assessment module, which is used to obtain the quantity and location of various rescue resources and the status and performance of various rescue equipment through the emergency affected area; evaluate the rescue resource capabilities based on the quantity and location of various rescue resources to obtain the corresponding emergency rescue resource capabilities within the current area. A resource demand prediction module, which is used to obtain the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task through the emergency affected area; obtain the corresponding disaster spreading speed and the number of affected people based on the disaster type, disaster distribution scale, and surrounding population distribution scale corresponding to each emergency rescue task, and predict the required emergency rescue resource demands corresponding to each emergency rescue task. An emergency rescue sorting module, which is used to perform emergency priority sorting analysis on each emergency rescue task based on the required emergency rescue resource demands corresponding to each emergency rescue task and in combination with the disaster type, disaster distribution scale, surrounding population distribution scale, disaster spreading speed, and the number of affected people to generate the corresponding emergency rescue priority sequence within the current area. An emergency rescue management module, which is used to optimize the emergency rescue deployment management for the corresponding emergency rescue priority sequence within the current area by aiming to maximize the rescue effect and combining the corresponding emergency rescue resource capabilities within the current area to generate decision-making suggestions for the emergency rescue resource deployment management corresponding to the emergency rescue task.

Images