Emergency resource intelligent allocation method and equipment based on big data, and medium

Abstract

The invention discloses an emergency resource intelligent allocation method and device based on big data and a medium, and the method comprises the steps: collecting multi-source heterogeneous data, and carrying out the cleaning conversion and fusion processing of the multi-source heterogeneous data, and generating a preprocessing data set in a unified format; the multi-source heterogeneous data comprises disaster situation data, resource data and environment data; based on historical data and real-time data in the preprocessed data set, predicting emergency resource demand gaps of different areas in different time periods through a machine learning algorithm; constructing a multi-objective optimization model, and solving an optimal resource allocation scheme corresponding to the multi-objective optimization model by using an intelligent optimization algorithm; multiple targets in the multi-target optimization model comprise resource supply and demand balance, transportation cost and time efficiency; and issuing the optimal resource allocation scheme to an execution terminal, monitoring a resource transportation state in real time, and dynamically adjusting the optimal resource allocation scheme according to a monitoring result so as to enable the resources to be delivered to a disaster site.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, device and medium for intelligent allocation of emergency resources based on big data. Background Technology

[0002] In recent years, natural disasters and accidents have occurred frequently worldwide, and the timeliness and accuracy of emergency resource allocation directly affect the effectiveness of rescue efforts. Currently, emergency resource allocation mainly relies on human experience-based decision-making, posing serious challenges to allocation efficiency and resource utilization. Traditional methods have significant shortcomings in key areas such as disaster information acquisition, demand forecasting, resource allocation, and dynamic adjustment, making it difficult to meet the real-time and precision requirements of modern emergency rescue.

[0003] In existing technologies, emergency resource allocation decisions are typically based on static reports and historical experience, lacking the ability to collect and integrate multi-source heterogeneous data in real time. Disaster data, resource inventory information, and environmental data are scattered across different systems, with inconsistent formats and delayed updates, resulting in incomplete decision-making basis. Especially in the early stages of a disaster, key information such as the affected area and population distribution, obtained manually, often has a delay of several hours, while dynamic environmental factors such as weather and road conditions cannot be taken into account in a timely manner, causing significant deviations in resource demand forecasts. This decision-making model based on fragmented information leads to a mismatch between emergency material allocation and actual needs, often resulting in a contradictory situation where some areas have resource surpluses while severely affected areas suffer from insufficient supplies. Summary of the Invention

[0004] This application provides a method, device, and medium for intelligent allocation of emergency resources based on big data, in order to solve the above-mentioned technical problems.

[0005] On the one hand, embodiments of this application provide a method for intelligent allocation of emergency resources based on big data, including: Collect multi-source heterogeneous data, and clean, transform, and fuse the multi-source heterogeneous data to generate a preprocessed dataset in a unified format; the multi-source heterogeneous data includes disaster data, resource data, and environmental data; Based on the historical and real-time data in the preprocessed dataset, machine learning algorithms are used to predict the emergency resource demand gap in different regions at different time periods. A multi-objective optimization model is constructed, and an intelligent optimization algorithm is used to solve for the optimal resource allocation scheme corresponding to the multi-objective optimization model; the multi-objectives in the multi-objective optimization model include resource supply and demand balance, transportation cost, and time efficiency. The optimal resource allocation plan is sent to the execution terminal to monitor the resource transportation status in real time, and the optimal resource allocation plan is dynamically adjusted according to the monitoring results so that the resources can be delivered to the disaster site.

[0006] In one implementation of this application, based on historical and real-time data in the preprocessed dataset, a machine learning algorithm is used to predict the emergency resource demand gap in different regions at different time periods, specifically including: Based on the historical and real-time data in the preprocessed dataset, and through machine learning algorithms, emergency resource needs are predicted. Based on the disaster data, determine the real-time resource inventory information, the size of the affected population, and the severity of the disaster at the disaster-stricken location; and based on the environmental data, determine the constraints of traffic conditions and weather conditions. Based on the emergency resource demand, real-time resource inventory information of the disaster-stricken area, the size of the affected population, the severity of the disaster, and constraints such as traffic conditions and weather conditions, calculate the difference between the resources required by the disaster-stricken area and the actual available resources within the target time period. If the difference exceeds a preset safety stock threshold, the difference will be marked as an emergency resource demand gap.

[0007] In one implementation of this application, a multi-objective optimization model is constructed, specifically including: The objective function for transportation cost is defined as the weighted sum of route distance and fuel consumption, and the objective function for time efficiency is defined as the inverse relationship between estimated arrival time and demand urgency. The weighted objective function is solved iteratively using a genetic algorithm or a particle swarm optimization algorithm.

[0008] In one implementation of this application, the optimal resource allocation scheme is sent to the execution terminal, specifically including: The resource type identifier, quantity code, transportation path coordinate sequence, and timestamp instruction in the optimal resource allocation scheme are parsed, and an encrypted transmission data packet carrying a digital signature is generated. The encrypted transmission data packet is encapsulated based on the protocol adapted to the execution terminal type, and the encapsulated encrypted transmission data packet is asynchronously pushed to the material dispatch terminal, the transportation vehicle terminal and the regional coordination terminal through a message queue.

[0009] In one implementation of this application, real-time monitoring of resource transportation status specifically includes: The real-time location information of the transport vehicle terminal is obtained through a preset GPS device, and the speed vector and cargo loading status of the transport vehicle terminal are obtained through a sensor device. By using the meteorological data interface, the weather conditions of the route area are updated, and real-time traffic topology maps and meteorological warning information from environmental data are overlaid to construct a transportation risk heat map. The real-time location information, cargo hold loading status, and weather conditions are compared in real time with the planned routes and time nodes in the optimal resource allocation scheme. If the comparison results determine that the transportation risk heat map triggers an alarm area, a dynamic adjustment command is activated.

[0010] In one implementation of this application, the optimal resource allocation scheme is dynamically adjusted based on monitoring results to ensure that resources are delivered to the disaster-stricken area, specifically including: If a transport vehicle is detected to have deviated from its planned route by more than a threshold distance and / or its estimated arrival time is delayed by more than a threshold duration, the updated real-time traffic topology map and resource inventory data are invoked to generate a differential instruction set; the differential instruction set includes a new transport route coordinate sequence. The optimal resource allocation scheme is dynamically adjusted based on the differential instruction set, and the adjusted optimal resource allocation scheme is pushed to the execution terminal so that the execution terminal can deliver emergency resources to the disaster site according to the adjusted optimal resource allocation scheme.

[0011] In one implementation of this application, the collection of multi-source heterogeneous data specifically includes: Initiate a request to the emergency management platform to call the disaster data interface in order to obtain the GPS coordinates of the disaster-stricken location, the disaster severity classification label, and the population heat map in real time; The database interface of the materials management system is polled to extract the location coordinates of emergency material warehouses, the time-series records of dynamic changes in inventory, and the topology of medical resource distribution; Subscribe to the message queue of the traffic and weather data service to receive incremental updates of real-time traffic topology maps and weather warnings.

[0012] In one implementation of this application, the multi-source heterogeneous data is cleaned, transformed, and fused, specifically including: For the disaster population size field in the disaster data, missing values ​​are filled in according to the average value of adjacent areas, and outliers that exceed the historical statistical range are filtered out. The units of material reserves in the resource data are uniformly converted into standard units of measurement, and redundant records of the same material in different systems are linked together. Traffic condition data and geographic information data are integrated to generate a road network topology; the road network topology includes travel time weights.

[0013] On the other hand, this application also provides an intelligent emergency resource allocation device based on big data, the device comprising: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are then executed by the at least one processor to enable the at least one processor to perform the above-described method for intelligent allocation of emergency resources based on big data.

[0014] On the other hand, this application embodiment also provides a non-volatile computer storage medium storing computer-executable instructions, which, when executed, implement the above-described method for intelligent allocation of emergency resources based on big data.

[0015] This application provides a method, device, and medium for intelligent allocation of emergency resources based on big data, which has at least the following beneficial effects: By collecting and integrating disaster data, resource data, and environmental data in real time, a preprocessed dataset with a unified format is constructed. This solves the problems of traditional methods relying on manual statistics, information lag, and inconsistent data formats and information redundancy between different systems. Combined with machine learning algorithms to predict resource demand gaps, it can dynamically assess the actual needs of different regions and time periods, avoiding insufficient or redundant resource allocation. Based on a multi-objective optimization model and intelligent optimization algorithms, it generates the optimal allocation plan, comprehensively considering resource supply and demand balance, transportation costs, and time efficiency, to ensure that emergency resources are accurately delivered to disaster-stricken areas in the shortest possible time. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating an intelligent emergency resource allocation method based on big data, provided for an embodiment of this application; Figure 2 This is a schematic diagram of the internal structure of an emergency resource intelligent allocation device based on big data, provided as an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0019] Figure 1This is a flowchart illustrating an intelligent emergency resource allocation method based on big data, provided as an embodiment of this application.

[0020] The analysis method involved in the embodiments of this application can be implemented by a terminal device or a server, and this application does not impose any special limitations on it. For ease of understanding and description, the following embodiments are all described in detail using a server as an example.

[0021] It should be noted that the server can be a single device or a system composed of multiple devices, i.e., a distributed server. This application does not make any specific limitations on this.

[0022] like Figure 1 As shown in the figure, an embodiment of this application provides a method for intelligent allocation of emergency resources based on big data, including: Step 101: Collect multi-source heterogeneous data, and clean, transform and fuse the multi-source heterogeneous data to generate a preprocessed dataset in a unified format.

[0023] It should be noted that the multi-source heterogeneous data in the embodiments of this application include disaster data, resource data, and environmental data.

[0024] In this embodiment, data is acquired through three main channels: initiating a disaster data interface call request to the emergency management platform to obtain disaster location information; polling the material management system database to extract resource data; and subscribing to traffic and meteorological data services to receive environmental data. It is understandable that this multi-channel data collection method ensures the comprehensiveness and real-time nature of the data.

[0025] Specifically, disaster data includes, but is not limited to, GPS coordinates of affected locations, disaster severity grading labels, and population heat maps. It should be noted that this data originates from real-time data interfaces provided by government departments and telecommunications operators. Resource data includes the location coordinates of emergency supply warehouses and time-series records of inventory changes; this information is obtained by periodically polling the database interface of the supplies management system. Regarding environmental data, the system continuously receives real-time road condition topology maps and weather radar data from traffic and meteorological services.

[0026] In this embodiment, for the disaster population size field in the disaster data, the system automatically identifies and handles outliers, filling in missing data with the average value of adjacent areas. This approach preserves the data's authenticity while ensuring its integrity. For resource data, the system converts material measurement units from different sources into a standardized unit and eliminates redundant records using data association technology.

[0027] Specifically, the data fusion stage combines traffic condition data with geographic information data to generate a road network topology structure with travel time weights. It should be noted that this fusion process provides fundamental data support for subsequent route optimization. The entire preprocessing process ultimately generates a dataset in a unified format, providing standardized data input for subsequent analysis.

[0028] Step 102: Based on historical and real-time data in the preprocessed dataset, predict the emergency resource demand gap in different regions at different time periods using machine learning algorithms.

[0029] In this embodiment, the system first trains a prediction model using a preprocessed historical dataset. It is understood that this historical data contains key information such as resource consumption records and disaster details from past disaster events.

[0030] Specifically, the prediction process employs multiple machine learning algorithms in parallel. This includes, but is not limited to, linear regression models, support vector machine models, and neural network models. In this embodiment, the system integrates the prediction results from each model with real-time disaster data to generate the final predicted resource demand value.

[0031] For example, the forecasting not only considers historical consumption patterns but also integrates key factors such as the real-time size of the affected population and the severity of the disaster. Understandably, this multi-dimensional forecasting approach significantly improves accuracy. The system also incorporates traffic conditions and weather data from environmental sources to assess the potential impact of these factors on resource transportation.

[0032] It's important to note that the demand gap calculation process is particularly crucial. Specifically, the system compares the predicted demand with the actual inventory, and marks a demand gap when the difference exceeds a safety threshold. It's also worth noting that this dynamic threshold mechanism can automatically adjust based on the type and severity of disasters, ensuring the rationality of resource allocation.

[0033] Step 103: Construct a multi-objective optimization model and use intelligent optimization algorithms to solve for the optimal resource allocation scheme corresponding to the multi-objective optimization model.

[0034] It should be noted that the multi-objective optimization model in this application embodiment includes resource supply and demand balance, transportation cost, and time efficiency.

[0035] In this embodiment, the model construction process first requires defining two core objective functions: a transportation cost objective function and a time efficiency objective function. It is understood that transportation cost comprehensively considers factors such as route distance and fuel consumption, while time efficiency relates to the relationship between arrival time and the urgency of demand.

[0036] Specifically, the optimization model employs a multi-objective programming framework. It should be noted that this framework allows for the simultaneous optimization of multiple mutually constraining objectives. In this embodiment, the system dynamically adjusts the weight coefficients of each objective based on different types of emergency resources. For example, the weight of time efficiency will be appropriately increased for medical emergency supplies.

[0037] Understandably, the solution process employs intelligent optimization algorithms, including genetic algorithms and particle swarm optimization. In this embodiment, the algorithm generates a series of non-dominated solutions, which are then selected by the decision-maker based on the actual situation. It should be noted that each solution contains a complete resource allocation plan, including elements such as type, quantity, transportation route, and timeframe.

[0038] For example, for special materials such as cold-chain pharmaceuticals, the system will add additional constraints such as temperature-controlled transportation to the optimization model. Understandably, this flexible constraint addition mechanism ensures the practical feasibility of the solution. The final allocation plan will comprehensively consider various realistic factors to achieve the overall optimal effect.

[0039] Step 104: Send the optimal resource allocation plan to the execution terminal, monitor the resource transportation status in real time, and dynamically adjust the optimal resource allocation plan based on the monitoring results so that resources can be delivered to the disaster-stricken area.

[0040] In this embodiment, during the issuance of the optimal resource allocation plan, the optimized allocation plan is first subjected to structured parsing, decomposing it into a set of executable operation instructions. It can be understood that these instruction sets contain key elements such as resource type identifiers, quantity codes, transportation path coordinate sequences, and timestamps, forming a complete operational loop.

[0041] Specifically, the resource type identifier adopts the internationally recognized material classification coding system to ensure interoperability between different systems. It should be noted that the quantity code uses a standardized format with check digits, containing both total quantity information and details of repackaging. In this embodiment, the transportation route coordinate sequence not only includes a set of latitude and longitude points but also marks the estimated arrival time and dwell time for each route node. For example, for the transportation of medical supplies, the system will add temperature control check instructions at key nodes.

[0042] Understandably, data transmission security is paramount. Specifically, the system employs an asymmetric encryption algorithm to encrypt the instruction set and attaches a digital signature to ensure data integrity and source credibility. In this embodiment, the encryption process dynamically adjusts the key validity period based on the time-sensitive nature of the instructions. It should be noted that this security mechanism effectively prevents the risk of instructions being tampered with or forged.

[0043] The instruction encapsulation and push process fully considers terminal heterogeneity. For example, for material dispatch terminals, the system uses an HTTP-based RESTful API for encapsulation; for transportation vehicle terminals, lightweight protocols such as MQTT are preferred. This protocol adaptation mechanism ensures that various terminals can efficiently receive instructions. Specifically, the system uses message queues to asynchronously push instructions, supporting high concurrency while ensuring reliability. In this embodiment, critical instructions are configured with a multi-level retry mechanism to ensure delivery rates even in extreme conditions.

[0044] In this embodiment, a multi-source sensor network is used to collect real-time data on all elements of the transportation process, providing a basis for dynamic adjustments. It is understood that this monitoring not only focuses on vehicle location but also covers key dimensions such as cargo status and environmental changes.

[0045] Specifically, vehicle positioning data is acquired through high-precision GPS devices and combined with inertial navigation technology to improve positioning continuity in blind areas such as tunnels. It should be noted that the system calculates velocity vectors in real time, including parameters such as speed, heading, and acceleration, to predict trajectory deviations. In this embodiment, the cargo hold loading status is monitored using multimodal sensing technologies such as weight sensors and image recognition, enabling timely detection of abnormal reductions or damage to supplies. For example, for temperature-sensitive materials such as vaccines, the system continuously monitors the operating status of cold chain equipment.

[0046] Environmental risk monitoring employs data fusion technology. Understandably, the system obtains real-time weather conditions for the areas it traverses through a meteorological data interface, including key indicators such as precipitation intensity and wind speed. Specifically, this data is spatially overlaid with a real-time traffic topology map to identify high-risk areas such as road flooding and landslides. In this embodiment, the system integrates historical accident data and real-time monitoring information to construct a dynamically updated transportation risk heat map. It should be noted that this heat map uses a three-color (red, yellow, green) tiered warning system to visually display the risk level of different areas.

[0047] The intelligent comparison and early warning mechanism enables proactive risk prevention and control. For example, the system compares real-time collected transportation status data with the original plan at millisecond levels, calculating the time deviation rate and route deviation. Understandably, when a red warning area appears on the risk heatmap, and a vehicle is expected to pass through that area, the system automatically triggers a dynamic adjustment command. Specifically, the warning threshold is dynamically adjusted according to the urgency of the supplies, with stricter monitoring standards set for critical supplies such as emergency medicines. In this embodiment, the system anticipates risks in advance, gaining valuable time for adjustment decisions.

[0048] In this embodiment, when the monitoring system detects a transportation anomaly, it immediately initiates a plan adjustment process to ensure that resources are ultimately delivered to the target location. It is understood that this adjustment is not a simple route replanning, but rather a global optimization that comprehensively considers the latest situation.

[0049] Specifically, the threshold determination employs multi-dimensional composite logic. It should be noted that the path deviation threshold considers not only the straight-line distance but also the additional time cost caused by detours. In this embodiment, the time delay threshold is dynamically calculated based on medical indicators such as the expiration date of supplies and the survival rate of the injured. For example, for the transportation of blood products, the system calculates the latest acceptable arrival time by combining the remaining valid time and the number of injured.

[0050] The differential instruction generation process embodies intelligent optimization. Understandably, when the system retrieves the latest traffic data, it prioritizes data freshness and reliability. Specifically, resource inventory data queries lock the current transaction state, ensuring that adjustment plans are based on a consistent data snapshot. In this embodiment, the differential instruction set employs an incremental update strategy, containing only the changed path coordinate sequence and adjusted time points, significantly reducing data transmission volume. It should be noted that this design is particularly suitable for disaster-prone environments with unstable mobile networks.

[0051] The system's solution delivery and execution emphasize timeliness and reliability. For example, the system assesses the quality of each communication channel and selects the optimal path to deliver adjustment instructions. Understandably, for critical instructions, the system employs a multi-channel parallel transmission mechanism to ensure that at least one channel successfully delivers the message. Specifically, upon receiving the instruction, the executing terminal immediately sends back confirmation information; instructions without confirmation automatically enter the retransmission queue. In this embodiment, the system continuously tracks the execution effect after adjustments, forming a closed-loop optimization mechanism. This design ensures that emergency resources can always maintain optimal allocation in a constantly changing environment.

[0052] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide an intelligent emergency resource allocation device based on big data, the structure of which is as follows: Figure 2 As shown.

[0053] Figure 2 This is a schematic diagram of the internal structure of an emergency resource intelligent allocation device based on big data, provided as an embodiment of this application. Figure 2 As shown, the device includes: At least one processor; And, a memory that is communicatively connected to at least one processor; The memory stores instructions that can be executed by at least one processor, and the instructions, when executed by at least one processor, enable at least one processor to: Collect multi-source heterogeneous data, and clean, transform, and fuse the multi-source heterogeneous data to generate a preprocessed dataset in a unified format; the multi-source heterogeneous data includes disaster data, resource data, and environmental data; Based on historical and real-time data in the preprocessed dataset, machine learning algorithms are used to predict the emergency resource demand gap in different regions at different time periods. A multi-objective optimization model is constructed, and an intelligent optimization algorithm is used to solve for the optimal resource allocation scheme corresponding to the multi-objective optimization model. The multi-objectives in the multi-objective optimization model include resource supply and demand balance, transportation cost, and time efficiency. The optimal resource allocation plan is sent to the execution terminal to monitor the resource transportation status in real time, and the optimal resource allocation plan is dynamically adjusted based on the monitoring results to ensure that resources are delivered to the disaster-stricken area.

[0054] This application also provides a non-volatile computer storage medium storing computer-executable instructions, which, when executed, can: Collect multi-source heterogeneous data, and clean, transform, and fuse the multi-source heterogeneous data to generate a preprocessed dataset in a unified format; the multi-source heterogeneous data includes disaster data, resource data, and environmental data; Based on historical and real-time data in the preprocessed dataset, machine learning algorithms are used to predict the emergency resource demand gap in different regions at different time periods. A multi-objective optimization model is constructed, and an intelligent optimization algorithm is used to solve for the optimal resource allocation scheme corresponding to the multi-objective optimization model. The multi-objectives in the multi-objective optimization model include resource supply and demand balance, transportation cost, and time efficiency. The optimal resource allocation plan is sent to the execution terminal to monitor the resource transportation status in real time, and the optimal resource allocation plan is dynamically adjusted based on the monitoring results to ensure that resources are delivered to the disaster-stricken area.

[0055] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0056] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0057] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0062] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0063] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0064] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0065] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for intelligent allocation of emergency resources based on big data, characterized in that, The method includes: Collect multi-source heterogeneous data, and clean, transform, and fuse the multi-source heterogeneous data to generate a preprocessed dataset in a unified format; the multi-source heterogeneous data includes disaster data, resource data, and environmental data; Based on the historical and real-time data in the preprocessed dataset, machine learning algorithms are used to predict the emergency resource demand gap in different regions at different time periods. A multi-objective optimization model is constructed, and an intelligent optimization algorithm is used to solve for the optimal resource allocation scheme corresponding to the multi-objective optimization model; the multi-objectives in the multi-objective optimization model include resource supply and demand balance, transportation cost, and time efficiency. The optimal resource allocation plan is sent to the execution terminal to monitor the resource transportation status in real time, and the optimal resource allocation plan is dynamically adjusted according to the monitoring results so that the resources can be delivered to the disaster site.

2. The method for intelligent allocation of emergency resources based on big data according to claim 1, characterized in that, Based on historical and real-time data in the preprocessed dataset, machine learning algorithms are used to predict the emergency resource demand gaps in different regions at different time periods, specifically including: Based on the historical and real-time data in the preprocessed dataset, and through machine learning algorithms, emergency resource needs are predicted. Based on the disaster data, determine the real-time resource inventory information, the size of the affected population, and the severity of the disaster at the disaster-stricken location; and based on the environmental data, determine the constraints of traffic conditions and weather conditions. Based on the emergency resource demand, real-time resource inventory information of the disaster-stricken area, the size of the affected population, the severity of the disaster, and constraints such as traffic conditions and weather conditions, calculate the difference between the resources required by the disaster-stricken area and the actual available resources within the target time period. If the difference exceeds a preset safety stock threshold, the difference will be marked as an emergency resource demand gap.

3. The method for intelligent allocation of emergency resources based on big data according to claim 1, characterized in that, Constructing a multi-objective optimization model specifically includes: The objective function for transportation cost is defined as the weighted sum of route distance and fuel consumption, and the objective function for time efficiency is defined as the inverse relationship between estimated arrival time and demand urgency. The weighted objective function is solved iteratively using a genetic algorithm or a particle swarm optimization algorithm.

4. The method for intelligent allocation of emergency resources based on big data according to claim 1, characterized in that, Sending the optimal resource allocation plan to the execution terminal specifically includes: The resource type identifier, quantity code, transportation path coordinate sequence, and timestamp instruction in the optimal resource allocation scheme are parsed, and an encrypted transmission data packet carrying a digital signature is generated. The encrypted transmission data packet is encapsulated based on the protocol adapted to the execution terminal type, and the encapsulated encrypted transmission data packet is asynchronously pushed to the material dispatch terminal, the transportation vehicle terminal and the regional coordination terminal through a message queue.

5. The method for intelligent allocation of emergency resources based on big data according to claim 1, characterized in that, Real-time monitoring of resource transportation status, specifically including: The real-time location information of the transport vehicle terminal is obtained through a preset GPS device, and the speed vector and cargo loading status of the transport vehicle terminal are obtained through a sensor device. By using the meteorological data interface, the weather conditions of the route area are updated, and real-time traffic topology maps and meteorological warning information from environmental data are overlaid to construct a transportation risk heat map. The real-time location information, cargo hold loading status, and weather conditions are compared in real time with the planned routes and time nodes in the optimal resource allocation scheme. If the comparison results determine that the transportation risk heat map triggers an alarm area, a dynamic adjustment command is activated.

6. The method for intelligent allocation of emergency resources based on big data according to claim 1, characterized in that, The optimal resource allocation plan is dynamically adjusted based on monitoring results to ensure resources reach the disaster-stricken areas. Specifically, this includes: If a transport vehicle is detected to have deviated from its planned route by more than a threshold distance and / or its estimated arrival time is delayed by more than a threshold duration, the updated real-time traffic topology map and resource inventory data are invoked to generate a differential instruction set; the differential instruction set includes a new transport route coordinate sequence. The optimal resource allocation scheme is dynamically adjusted based on the differential instruction set, and the adjusted optimal resource allocation scheme is pushed to the execution terminal so that the execution terminal can deliver emergency resources to the disaster site according to the adjusted optimal resource allocation scheme.

7. The method for intelligent allocation of emergency resources based on big data according to claim 1, characterized in that, Collecting multi-source heterogeneous data, specifically including: Initiate a request to the emergency management platform to call the disaster data interface in order to obtain the GPS coordinates of the disaster-stricken location, the disaster severity classification label, and the population heat map in real time; The database interface of the materials management system is polled to extract the location coordinates of emergency material warehouses, the time-series records of dynamic changes in inventory, and the topology of medical resource distribution; Subscribe to the message queue of the traffic and weather data service to receive incremental updates of real-time traffic topology maps and weather warnings.

8. The method for intelligent allocation of emergency resources based on big data according to claim 1, characterized in that, The process of cleaning, transforming, and fusing the multi-source heterogeneous data specifically includes: For the disaster population size field in the disaster data, missing values ​​are filled in according to the average value of adjacent areas, and outliers that exceed the historical statistical range are filtered out. The units of material reserves in the resource data are uniformly converted into standard units of measurement, and redundant records of the same material in different systems are linked together. Traffic condition data and geographic information data are integrated to generate a road network topology; the road network topology includes travel time weights.

9. An intelligent emergency resource allocation device based on big data, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform a big data-based intelligent allocation method for emergency resources as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, they implement the big data-based intelligent allocation method for emergency resources as described in any one of claims 1-8.

Images