An intelligent decision method and system for emergency deployment of first-aid supplies

Abstract

The application provides an intelligent decision-making method and system for emergency allocation of first-aid materials. The method integrates graph neural networks, deep learning, reinforcement learning, Bayesian optimization, and genetic algorithms to efficiently process demand information from multiple emergency response points. By receiving demand information including the number, type, and severity of injuries, the intelligent assessment system dynamically calculates the urgency of demand and generates a preliminary allocation plan. Then, using a traffic prediction model combined with real-time and historical data, the road capacity is estimated, and various logistics distribution strategies are simulated to optimize the preliminary plan and determine the optimal path planning. Subsequently, the AI simulation training system verifies the material allocation effect in different scenarios, adjusts the allocation plan, and finally forms a comprehensive allocation instruction to guide actual operations. The technical solution of the application can realize intelligent decision support for first-aid materials, significantly improving the efficiency and accuracy of first-aid material allocation.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to an intelligent decision-making method and system for emergency allocation of emergency medical supplies. Background Technology

[0002] In emergency rescue scenarios, the rapid and precise allocation of emergency medical supplies is crucial for improving patient survival rates and the quality of rehabilitation.

[0003] Currently, emergency medical supplies allocation mainly relies on manual dispatching or automated systems based on preset rules. These systems typically incorporate geographic information systems to assist decision-making and may integrate basic traffic prediction models to optimize delivery routes.

[0004] However, such methods often lack flexibility and adaptability when dealing with emergencies, and cannot fully take into account the uncertainties in the actual situation, such as traffic accidents or temporary traffic control. Summary of the Invention

[0005] This application provides an intelligent decision-making method and system for emergency allocation of emergency medical supplies, which solves the problems of low efficiency, lack of flexibility and adaptability in the allocation of emergency medical supplies in the prior art.

[0006] In a first aspect, embodiments of this application provide an intelligent decision-making method for the emergency allocation of emergency medical supplies, including:

[0007] Receive demand information from multiple emergency response points, the demand information including at least the number of injured, the type of injury, the severity of injury, the status of on-site medical resources, priority indicators, and geographic spatial distribution;

[0008] Based on the graph neural network intelligent assessment system, the urgency of the needs of each emergency response point is assessed according to the demand information, and a preliminary allocation plan is generated. The preliminary allocation plan is determined according to the urgency of the needs of each emergency response point, and includes the types and quantities of emergency supplies required by each emergency response point, as well as the allocation order of the emergency supplies.

[0009] Using a deep learning prediction model, road capacity predictions are generated based on historical and real-time traffic data from multiple sources. Reinforcement learning algorithms are then combined to simulate various logistics delivery strategies, refining the initial allocation plan and determining the target logistics delivery strategy. The road capacity predictions refer to the deep learning prediction model's estimation of road traffic conditions over a future period using historical traffic data, real-time traffic data, and model algorithms. The logistics delivery strategy is formulated based on the allocation order of emergency supplies in the initial allocation plan. The target logistics delivery strategy avoids predicted congested road sections and ensures timely arrival at designated locations.

[0010] An AI simulation exercise system based on Bayesian optimization and genetic algorithm is launched. According to the target logistics distribution strategy, the system simulates the configuration schemes of the types and quantities of emergency supplies under multiple scenarios. The system then uses a genetic algorithm to iteratively evolve the optimal configuration scheme of the types and quantities of emergency supplies that can adapt to the actual situation from the configuration schemes under multiple scenarios, and generates a comprehensive dispatch instruction. The comprehensive dispatch instruction includes an emergency supplies list, estimated delivery time, and optimal transportation route.

[0011] The comprehensive allocation command is executed to realize the emergency allocation of the emergency medical supplies.

[0012] Optionally, the step of using a deep learning prediction model to generate prediction results of road capacity based on historical traffic data and real-time traffic obtained from multiple sources includes:

[0013] Historical traffic data and real-time traffic data obtained from multiple sources are integrated to obtain a traffic dataset. The historical traffic data includes at least traffic flow, accident records and weather effects in the same time period in the past, and the real-time traffic data includes at least current traffic camera images, vehicle location information and real-time traffic conditions provided by sensors.

[0014] The traffic data in the traffic dataset is analyzed and processed using a deep learning prediction model to generate prediction results of road capacity over a future period. The deep learning prediction model is trained to identify and predict the impact of different factors on road capacity and output the expected traffic efficiency of each road in a specific future time period, thereby generating prediction results of road capacity.

[0015] Optionally, based on the predicted road capacity, various logistics and distribution strategies are simulated using reinforcement learning algorithms to refine and adjust the preliminary allocation plan, and a target logistics and distribution strategy is determined, including:

[0016] Using the predicted road capacity and a reinforcement learning algorithm, the allocation order of emergency supplies in the preliminary allocation plan is simulated to obtain a variety of logistics and distribution strategies aimed at optimizing time cost and transportation efficiency.

[0017] Based on various logistics and distribution strategies, the preliminary allocation plan is refined and adjusted. The process of refining and adjusting includes optimizing the transportation routes of the emergency supplies under different logistics and distribution strategies and adjusting the types and quantities of emergency supplies required for each emergency response point to adapt to the actual situation.

[0018] For each of the aforementioned logistics and delivery strategies, a performance evaluation process is performed to avoid predicted congested road sections and ensure timely arrival at the designated location. The performance evaluation indicators include at least delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, thereby obtaining the evaluation results for each of the aforementioned logistics and delivery strategies.

[0019] Based on the evaluation results of the effectiveness of all logistics and distribution strategies, select the target logistics and distribution strategy that can maximize transportation efficiency and minimize delays;

[0020] The target logistics and distribution strategy is applied to the adjusted preliminary allocation plan for verification and confirmation to ensure that the target logistics and distribution strategy can achieve the expected results in actual operation.

[0021] Optionally, the step of selecting the target logistics and distribution strategy that maximizes transportation efficiency and minimizes delays based on the evaluation results of the effectiveness of all logistics and distribution strategies includes:

[0022] Based on the evaluation results of the effectiveness of all logistics and distribution strategies, qualified logistics and distribution strategies are selected. Based on multi-dimensional evaluation, the selected logistics and distribution strategies are comprehensively scored to obtain a score for each logistics and distribution strategy. The one or more logistics and distribution strategies with the highest scores are selected as candidate logistics and distribution strategies.

[0023] The analysis of route selection, projected traffic conditions, and delay risks in each candidate logistics and delivery strategy is used to determine the target logistics and delivery strategy that maximizes transportation efficiency and minimizes delays.

[0024] Optionally, an AI simulation exercise system based on Bayesian optimization and genetic algorithms is launched. According to the target logistics distribution strategy, the system simulates configuration schemes for the types and quantities of emergency supplies under multiple scenarios. Using a genetic algorithm, iteratively evolves the optimal configuration scheme for the types and quantities of emergency supplies that adapts to the actual situation from the configuration schemes under multiple scenarios, and generates comprehensive allocation instructions, including:

[0025] Start the AI ​​simulation exercise system based on Bayesian optimization and genetic algorithm, load the target logistics distribution strategy as input data, and initialize the simulation environment;

[0026] Bayesian optimization techniques are used to automatically adjust the model parameters of the AI ​​simulation training system to improve simulation accuracy and obtain optimized parameter configuration.

[0027] Based on the optimized parameter configuration, the configuration schemes for the types and quantities of the emergency supplies are simulated in multiple predefined scenarios, and the allocation effect corresponding to the configuration scheme in each predefined scenario is evaluated.

[0028] By using a genetic algorithm, the allocation effect corresponding to the configuration scheme under each predefined scenario is iteratively evolved to determine the optimal configuration scheme for the types and quantities of emergency supplies that can adapt to various actual situations.

[0029] Verify the effectiveness of the optimal configuration scheme and generate a comprehensive dispatch instruction that includes a detailed list of emergency supplies, estimated delivery time, and optimal transportation route.

[0030] Optionally, the step of simulating configuration schemes for the types and quantities of emergency supplies under multiple predefined scenarios based on optimized parameter configurations, and evaluating the allocation effect corresponding to the configuration schemes under each predefined scenario, includes:

[0031] In the AI ​​simulation training system, the optimized parameter configuration is loaded as the initial setting to initialize the simulation environment and ensure that the simulation environment can accurately reflect the actual situation.

[0032] Based on the optimized parameter configuration, the allocation of emergency supplies is simulated in each predefined scenario. The simulation process includes route selection, time arrangement, and allocation of emergency resources to obtain the configuration scheme of the types and quantities of emergency supplies in each predefined scenario.

[0033] Evaluate the allocation schemes for each type and quantity of emergency supplies, with evaluation indicators including at least delivery time, transportation cost, supply utilization efficiency, rescue success rate, and emergency response speed, to obtain the allocation effect corresponding to the allocation schemes.

[0034] Optionally, the graph neural network-based intelligent assessment system assesses the urgency of the demand at each emergency response point based on the demand information and generates a preliminary deployment plan, including:

[0035] Natural language processing algorithms are used to parse and process demand information from multiple emergency response points to obtain specific demand results for each emergency response point.

[0036] Based on the specific requirements, a graph structure data model is constructed, wherein the nodes in the graph structure data model represent various emergency response points, and the edges represent the correlation and influence range between different emergency response points.

[0037] Based on the pre-trained model parameters, the graph neural network intelligent evaluation system is launched to load and process the graph structure data model, ensuring that the graph neural network intelligent evaluation system can identify and process different types of node and edge attributes. The graph neural network intelligent evaluation system is then used to evaluate the urgency of each emergency response point and calculate the urgency score of each node. The urgency score is determined based on the correlation and impact range between different emergency response points.

[0038] Based on the urgency score of the demand, a preliminary allocation plan is generated.

[0039] Optionally, for each of the logistics delivery strategies, a performance evaluation process is performed to avoid predicted congested road sections and ensure timely arrival at the designated location. The performance evaluation indicators include at least delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, resulting in an evaluation result for each of the logistics delivery strategies, including:

[0040] For each of the aforementioned logistics and distribution strategies Performance evaluation processes should be conducted to avoid anticipated congested road sections and ensure timely arrival at designated locations. Performance evaluation metrics should include at least: delivery time. Transportation costs Path reliability Traffic adaptability Resource flexibility ;

[0041] Evaluation results Calculated using the following formula:

[0042]

[0043] in, These are the weighting coefficients for delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, respectively. It is an exponential adjustment factor for delivery time, used to reflect the severity of the delay; These are the maximum values ​​of path reliability, traffic adaptability, and resource flexibility, respectively, used for normalization to ensure that the values ​​of each performance evaluation index are within a certain range. Within the range.

[0044] Optionally, the evaluation of the configuration scheme for each type and quantity of emergency supplies includes evaluation indicators at least including supply utilization efficiency, rescue success rate, and emergency response speed, to obtain the allocation effect corresponding to the configuration scheme, including:

[0045] Based on the optimized parameter configuration In each predefined scenario The following simulation process is performed on the distribution of the emergency supplies, including route selection. Schedule and the allocation of the aforementioned emergency medical resources To obtain a configuration scheme for the types and quantities of emergency supplies in each predefined scenario. ;

[0046] Each allocation scheme Represented as:

[0047]

[0048] Indicates the first One transportation route; Indicates the first The time schedule for each transportation route; Indicates the first The demand for emergency medical supplies;

[0049] Configuration scheme for the type and quantity of each of the aforementioned emergency supplies. An evaluation should be conducted, and the evaluation indicators should include at least the efficiency of material utilization. Rescue success rate Emergency response speed ;

[0050] Distribution effect Calculated using the following formula:

[0051]

[0052] These are the weighting coefficients for resource utilization efficiency, rescue success rate, and emergency response speed, respectively. It is the corresponding index adjustment factor; Indicates the first Allocation of emergency medical resources along the routes The calculated resource utilization efficiency represents the resource utilization efficiency. A specific instance under a specific path and resource allocation; Indicates the first Scheduled for a given time on the path The rescue success rate represents the overall success rate of the rescue. Specific examples under a particular path and time schedule; This represents the shortest delivery time among all routes, used to measure emergency response speed. ; It represents the maximum efficiency of material utilization and is used for normalization.

[0053] Secondly, embodiments of this application provide an intelligent decision-making system for the emergency allocation of emergency medical supplies, including:

[0054] The receiving module is used to receive demand information from multiple emergency response points. The demand information includes at least the number of injured, the type of injury, the severity of injury, the status of on-site medical resources, priority indicators, and geographic spatial distribution.

[0055] The generation module is used to evaluate the urgency of the needs of each emergency response point based on the demand information according to the graph neural network intelligent assessment system, and generate a preliminary allocation plan. The preliminary allocation plan is determined according to the urgency of the needs of each emergency response point, and includes the types and quantities of emergency supplies required by each emergency response point, as well as the allocation order of the emergency supplies.

[0056] The determination module utilizes a deep learning prediction model to generate road capacity predictions based on historical and real-time traffic data from multiple sources. It then combines this with reinforcement learning algorithms to simulate various logistics delivery strategies, refining the initial allocation plan and determining the target logistics delivery strategy. The road capacity predictions refer to the deep learning prediction model's estimation of road traffic conditions over a future period using historical, real-time traffic data and model algorithms. The logistics delivery strategy is formulated based on the allocation order of emergency supplies in the initial allocation plan. The target logistics delivery strategy avoids predicted congested road sections and ensures timely arrival at designated locations.

[0057] The generation module is also used to launch an AI simulation exercise system based on Bayesian optimization and genetic algorithm. According to the target logistics distribution strategy, it simulates the configuration schemes of the types and quantities of emergency supplies under multiple scenarios, and iteratively evolves the optimal configuration scheme of the types and quantities of emergency supplies that can adapt to the actual situation from the configuration schemes under multiple scenarios through genetic algorithm, and generates a comprehensive dispatch instruction. The comprehensive dispatch instruction includes an emergency supplies list, estimated delivery time and optimal transportation route.

[0058] The execution module is used to execute the comprehensive allocation command to realize the emergency allocation of the emergency supplies.

[0059] In this embodiment, demand information from multiple emergency response points is received. This demand information includes at least the number of injured persons, their types, severity, on-site medical resource status, priority indicators, and geographic spatial distribution. Based on a graph neural network intelligent assessment system, the urgency of the demand at each emergency response point is assessed according to the demand information, and a preliminary allocation plan is generated. This preliminary allocation plan is determined based on the urgency of the demand at each emergency response point and includes the types and quantities of emergency supplies required by each emergency response point, as well as the allocation order of the emergency supplies. Using a deep learning prediction model, road capacity predictions are generated based on historical and real-time traffic data from multiple sources. Reinforcement learning algorithms are then used to simulate various logistics delivery strategies, refining the initial allocation plan and determining the target logistics delivery strategy. The predicted road capacity refers to the deep learning prediction model using historical traffic data, real-time traffic data, and model algorithms to estimate road traffic conditions over a future period. The logistics delivery strategy is formulated based on the allocation order of emergency supplies in the initial allocation plan. The target logistics delivery strategy avoids predicted congestion sections and ensures timely arrival at designated locations. An AI simulation exercise system based on Bayesian optimization and genetic algorithms is launched. According to the target logistics delivery strategy, it simulates configuration schemes for the types and quantities of emergency supplies under multiple scenarios. A genetic algorithm iteratively evolves from these configuration schemes to find the optimal configuration scheme for the types and quantities of emergency supplies that adapts to the actual situation, generating a comprehensive allocation instruction. This comprehensive allocation instruction includes an emergency supplies list, estimated delivery time, and optimal transportation route. The comprehensive allocation command is executed to realize the emergency allocation of the emergency medical supplies.

[0060] The technical solution of this application has the following beneficial effects:

[0061] This application utilizes a graph neural network intelligent evaluation system to dynamically assess the urgency of needs at each emergency response point, rapidly generating preliminary allocation plans. This method can determine the optimal resource allocation scheme in the shortest possible time, significantly shortening decision-making time and improving rescue efficiency. Based on demand information and on-site medical resource conditions, it accurately calculates the types and quantities of emergency supplies required for each emergency response point, ensuring that supplies are neither excessively wasted nor insufficiently supplied, maximizing resource utilization efficiency. Bayesian optimization and genetic algorithms are used to iteratively evolve the optimal configuration scheme, further enhancing the scientific and rational nature of resource allocation. A deep learning prediction model, combined with historical and real-time traffic data, accurately predicts road capacity over a future period, providing a reliable basis for logistics and distribution strategies. Reinforcement learning algorithms simulate various logistics and distribution strategies, ensuring that the selected routes not only avoid predicted congested sections but also maximize the saving of transportation time and costs, improving overall distribution efficiency. The AI ​​simulation exercise system automatically adjusts parameters through Bayesian optimization to improve simulation accuracy; the genetic algorithm continuously adjusts and optimizes based on actual conditions, ensuring the high adaptability and flexibility of the scheme. The comprehensive allocation instruction includes a detailed list of emergency supplies, estimated delivery time, and optimal transportation routes, guiding actual operations and reducing uncertainties caused by human factors. The entire system design fully considers uncertainties in emergencies, such as changes in traffic conditions and the condition of the injured, enhancing its ability to cope with complex scenarios. By simulating the allocation of emergency supplies under multiple predefined scenarios, the system comprehensively evaluates the efficiency of supply utilization, rescue success rate, and emergency response speed, ensuring efficient rescue under various circumstances and thus improving the overall rescue success rate.

[0062] Furthermore, this application embodiment also utilizes road capacity prediction and reinforcement learning algorithms to optimize the allocation order of emergency supplies, generating a variety of logistics distribution strategies aimed at reducing time costs and improving transportation efficiency; based on these strategies, transportation routes are further optimized and the types and quantities of supplies required at each emergency response point are adjusted to adapt to the actual situation; performance evaluation is performed on each strategy, with evaluation indicators covering delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, selecting the target logistics distribution strategy that maximizes transportation efficiency and minimizes delays; finally, the target logistics distribution strategy is applied to the adjusted preliminary allocation plan to verify its feasibility in actual operation.

[0063] The above methods not only dynamically adapt to changing road conditions but also continuously optimize logistics and distribution strategies through reinforcement learning algorithms, ensuring optimal material allocation order and transportation routes. The performance evaluation process comprehensively considers multiple key indicators, ensuring that the selected route planning scheme is not only fast and efficient but also highly reliable and adaptable. The final selected target logistics and distribution strategy has been validated and can achieve the expected results in actual operation, significantly improving the scientific nature and accuracy of decision-making, enhancing the ability to respond to emergencies, and ensuring that emergency supplies can be delivered to their destination efficiently in the shortest possible time.

[0064] In summary, this method not only improves the speed and accuracy of emergency supplies allocation, but also optimizes resource allocation through intelligent technology and algorithms, enhancing the system's adaptability and reliability, and effectively improving emergency response capabilities and rescue success rates.

[0065] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0066] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0067] Figure 1 A flowchart illustrating an intelligent decision-making method for the emergency allocation of emergency medical supplies, provided in an embodiment of this application;

[0068] Figure 2 This is a schematic diagram of the structure of an intelligent decision-making system for emergency allocation of emergency medical supplies, provided in an embodiment of this application. Detailed Implementation

[0069] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0070] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0071] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0072] Figure 1 A flowchart of an intelligent decision-making method for emergency allocation of emergency medical supplies is provided in this application embodiment, as shown below. Figure 1 As shown, the method includes:

[0073] 101. Receive request information from multiple emergency response points.

[0074] The required information includes, but is not limited to, the number of injured, the type of injury (e.g., trauma, poisoning), the severity (mild, moderate, severe), the status of on-site medical resources (the quantity and capacity of existing medicines, equipment, and medical personnel), priority indicators (urgent or non-urgent), and geospatial distribution (geographical location, accessibility). This data is used to construct a comprehensive description of the emergency scenario and forms the basis for all subsequent decisions.

[0075] In practice, the system collects the aforementioned requirements information through various channels, such as telephone, mobile applications, and IoT devices. This information is uploaded to a central server in real time for processing and analysis, ensuring the timeliness and accuracy of the data and providing solid data support for subsequent intelligent assessments.

[0076] For example, in a city's emergency medical services system, when a traffic accident occurs, on-site rescue personnel use mobile devices to quickly input accident details, including the number of injured, injury classifications, and currently available medical resources, and upload them to the system. Simultaneously, nearby hospitals and emergency stations also update their resource status. This aggregated information forms a complete description of the entire event, providing a basis for subsequent intelligent assessment.

[0077] 102. Based on the graph neural network intelligent assessment system, the urgency of the demand for each emergency response point is assessed according to the demand information, and a preliminary allocation plan is generated.

[0078] Graph Neural Networks (GNNs) are machine learning models capable of processing complex relational data, suitable for analyzing the correlations and impact ranges between emergency response points. By modeling the relationships between response points, they dynamically assess the urgency of each point's needs, thereby providing scientific guidance for resource allocation.

[0079] The preliminary allocation plan is determined based on the urgency of the needs of each emergency response point, and includes the types and quantities of emergency supplies required by each emergency response point, as well as the allocation order of the emergency supplies.

[0080] Based on the received demand information, GNN considers factors such as distance between different response points, transportation conditions, and sharing of medical resources to calculate the urgency of the demand at each point, and generates a preliminary allocation plan that includes the types, quantities, and allocation order of supplies.

[0081] For example, continuing the previous example, in a traffic accident case, the GNN assessment identified two emergency stations, A and B, closest to the accident scene. Station A had relatively abundant resources, while station B was relatively strained. Therefore, the system decided to first allocate more resources from station A to the accident site and planned to consider mobilizing station C, which was farther away but had more abundant resources, if further support was needed, to ensure that the most urgently needed resources could arrive as quickly as possible.

[0082] 103. Using a deep learning prediction model, based on historical traffic data and real-time traffic data obtained from multiple sources, predict the road capacity and combine it with reinforcement learning algorithms to simulate various logistics and distribution strategies. Then, refine and adjust the preliminary allocation plan and determine the target logistics and distribution strategy.

[0083] Deep learning prediction models combine historical and real-time traffic data to estimate road capacity over a future period, providing accurate road condition forecasts for logistics and delivery. Reinforcement learning algorithms simulate various delivery strategies to find the target logistics delivery strategy, ensuring that goods transportation is both fast and safe.

[0084] The predicted road capacity refers to the deep learning prediction model using historical traffic data, real-time traffic data, and model algorithms to estimate road traffic conditions over a future period. The logistics delivery strategy is formulated based on the allocation order of emergency supplies in the preliminary deployment plan. The target logistics delivery strategy avoids predicted congested road sections and ensures timely arrival at designated locations.

[0085] The model uses various factors such as traffic flow, weather forecasts, and construction information to predict potential traffic bottlenecks and adjusts the delivery routes in the initial dispatch plan accordingly. Through continuous iterative optimization, the optimal route to avoid congested sections is ultimately determined.

[0086] For example, in the aforementioned traffic accident, the system predicted that the main road leading to Station A would be severely congested half an hour later due to another traffic accident. Therefore, the AI ​​suggested taking a longer but expectedly unobstructed side road to ensure that emergency supplies could reach the accident scene smoothly within the stipulated time, avoiding delays in treatment.

[0087] 104. Launch an AI simulation exercise system based on Bayesian optimization and genetic algorithm. According to the target logistics distribution strategy, simulate the configuration schemes of the types and quantities of emergency supplies under multiple scenarios. Through genetic algorithm, iteratively evolve the optimal configuration scheme of the types and quantities of emergency supplies that can adapt to the actual situation from the configuration schemes under multiple scenarios, and generate comprehensive dispatch instructions.

[0088] Bayesian optimization and genetic algorithms work together in an AI simulation system. The former automatically tunes parameters to improve simulation accuracy, while the latter finds the optimal configuration scheme to adapt to the actual situation through iterative evolution. The system aims to verify and optimize the initial deployment plan, ensuring its effective execution under various conditions.

[0089] Based on the target logistics and distribution strategy derived in the previous step, the AI ​​simulation exercise system simulates multiple possible scenarios, such as different time periods, weather changes, and emergencies, to evaluate the efficiency of material utilization, the success rate of rescue, and the speed of emergency response. Finally, it generates a comprehensive dispatch instruction that includes a detailed list, delivery time, and route.

[0090] For example, taking the aforementioned traffic accident as an example, the AI ​​simulation system considered the impact of various scenarios, such as poor visibility at night and slippery roads in rainy weather, and ultimately confirmed the optimal material delivery plan. This plan not only specified a detailed list of materials and the estimated delivery time, but also planned a backup route that could ensure efficient transportation even in adverse weather conditions, ensuring the rescue operation would be foolproof.

[0091] It should be noted that while the target logistics and distribution strategy determines the optimal route for material delivery, it does not fully consider various complex situations that may be encountered during actual delivery, such as resource utilization efficiency in different scenarios, treatment success rates, and the adaptability of material types and quantities. Therefore, after generating the target logistics and distribution strategy, it is necessary to further conduct multi-scenario simulations through an AI simulation system to ensure that the final comprehensive allocation instructions are optimized and best adapted to actual conditions.

[0092] 105. Execute the comprehensive allocation command to realize the emergency allocation of the emergency supplies.

[0093] The comprehensive dispatch instructions, a final decision-making document refined through multiple rounds of evaluation and optimization, include a detailed list of emergency supplies, estimated delivery times, and optimal transportation routes. These instructions directly guide on-site operations, ensuring the efficiency and accuracy of resource allocation.

[0094] Once the comprehensive deployment order is generated, it is immediately communicated to all relevant parties, such as ambulance drivers and logistics managers, to ensure everyone clearly understands the mission details. During execution, the system continuously monitors progress and makes real-time adjustments as necessary to ensure the successful completion of the rescue operation.

[0095] For example, in traffic accident rescue, the overall dispatch order is quickly transmitted to all participating units. Emergency vehicles depart according to the predetermined route, maintaining contact with the command center en route and reporting their location and any problems encountered. Based on the latest feedback, the system dynamically adjusts the allocation of other resources to ensure the entire rescue operation proceeds smoothly until all injured persons receive proper treatment.

[0096] Through the implementation of steps 101 to 105, this intelligent decision-making method for emergency allocation of emergency supplies achieves intelligent management of the entire process, from comprehensive collection of demand information, intelligent assessment and generation of preliminary plans, traffic forecasting and optimization of logistics and distribution strategies, AI simulation exercises, to the final execution of comprehensive allocation instructions. First, the system receives detailed demand information from multiple emergency response points, ensuring data accuracy and real-time performance, laying a solid foundation for subsequent decision-making. Next, based on graph neural networks, the urgency of each response point's needs is dynamically assessed, generating a scientifically sound preliminary allocation plan, improving the targeting and timeliness of resource allocation. Then, a deep learning prediction model combined with historical and real-time traffic data is used to predict road capacity, and a reinforcement learning algorithm is used to simulate various logistics and distribution strategies to determine the target logistics and distribution strategy, ensuring that supplies can be delivered quickly and safely. Further, an AI simulation exercise system based on Bayesian optimization and genetic algorithms is launched to simulate the effects of supply allocation under different scenarios, optimize and verify the preliminary allocation plan, and generate comprehensive allocation instructions containing a detailed list, estimated delivery time, and optimal transportation routes. Finally, these instructions are executed to achieve efficient allocation of emergency supplies. The entire process not only significantly improved the speed and accuracy of emergency response, but also optimized resource allocation efficiency and enhanced the system's adaptability and reliability, thereby greatly improving the success rate of rescue and the overall emergency response capability.

[0097] To address the prediction challenges posed by the diversity and complexity of traffic data, and to further improve the accuracy and real-time performance of road capacity prediction, in some embodiments, step 103 utilizes a deep learning prediction model to generate road capacity prediction results based on historical traffic data and real-time traffic obtained from multiple sources, including:

[0098] Historical and real-time traffic data from multiple sources are integrated to obtain a traffic dataset. The historical traffic data includes at least traffic flow, accident records, and weather impacts from the same time period in the past, while the real-time traffic data includes at least current traffic camera images, vehicle location information, and real-time traffic conditions provided by sensors. A deep learning prediction model is used to analyze and process the traffic data in the traffic dataset to generate predictions of road capacity over a future period. The deep learning prediction model, through training, can identify and predict the impact of different factors on road capacity and output the expected traffic efficiency of each road in a specific future time period, thus generating predictions of road capacity.

[0099] In this embodiment, historical traffic data includes at least information such as traffic flow, accident records, and weather effects from the same time period in the past. This data is used to identify long-term trends and periodic patterns. Real-time traffic data includes at least current traffic camera images, vehicle location information (such as from GPS or onboard sensors), and real-time traffic conditions provided by sensors (such as traffic light status, road surface wetness, etc.) to capture instantaneous changes and emergencies.

[0100] In this embodiment, the system first cleans, aligns, and standardizes data from different sources using multi-source data fusion technology to ensure data consistency and usability. Then, a deep learning prediction model is used to analyze the integrated traffic dataset. This model, through extensive training, can identify and predict the impact of different factors (such as time, location, weather conditions, traffic accidents, and holiday effects) on road capacity, and output the expected traffic efficiency of each road in a specific future time period. The prediction model not only considers static road infrastructure information but also dynamically adjusts to adapt to the constantly changing traffic environment.

[0101] Here is a specific example:

[0102] In a case study of emergency medical supplies allocation in a large city, the system needed to develop a targeted logistics and delivery strategy based on the upcoming weekday evening rush hour. To achieve this, the system collected and integrated traffic flow data, accident records, and weather conditions from the same weekday evening rush hour over the past few months as historical data. Simultaneously, it acquired real-time traffic camera images, vehicle GPS location information, and real-time traffic conditions from roadside sensors. This data was then fed into a well-trained deep learning prediction model.

[0103] Based on historical and real-time data, the model predicts the traffic efficiency of major roads and intersections over the next two hours. For example, the model identifies a major road leading to an emergency station that may experience temporary congestion within the next hour due to school dismissal nearby, but will subsequently return to normal. Therefore, the system suggests that emergency supply transport vehicles choose a slightly longer but expectedly smoother off-road route as an alternative, ensuring that supplies reach their destination in the shortest possible time.

[0104] Furthermore, the model also considers potential unforeseen events, such as temporary traffic control or accidents, automatically adjusting predictions and providing alternative route options. This not only improves the accuracy of road capacity predictions but also enhances the system's flexibility, ensuring optimal logistics and delivery decisions are made under any circumstances.

[0105] To address the static nature of the initial allocation plan and its insufficient adaptability to actual conditions, and to further improve the flexibility and efficiency of logistics distribution strategies, in some embodiments, step 103 involves simulating various logistics distribution strategies based on the predicted road capacity using reinforcement learning algorithms. This refines and adjusts the initial allocation plan, ultimately determining the target logistics distribution strategy, including:

[0106] Using the predicted road capacity and a reinforcement learning algorithm, the allocation order of emergency supplies in the initial deployment plan is simulated to obtain multiple logistics and distribution strategies aimed at optimizing time costs and transportation efficiency. Based on these strategies, the initial deployment plan is refined and adjusted. This refinement includes optimizing the transportation routes of emergency supplies under different strategies and adjusting the types and quantities of emergency supplies required for each emergency response point to adapt to actual conditions. For each logistics and distribution strategy, a performance evaluation is conducted to avoid predicted congestion and ensure timely arrival at designated locations. Performance evaluation indicators include at least delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, resulting in evaluation results for each strategy. Based on the evaluation results of all logistics and distribution strategies, a target strategy that maximizes transportation efficiency and minimizes delays is selected. The target strategy is then applied to the adjusted initial deployment plan for verification and confirmation to ensure that it achieves the expected results in actual operation.

[0107] In this embodiment, the distribution sequence of emergency supplies in the initial allocation plan is simulated using road capacity predictions combined with a reinforcement learning algorithm. Here, the road capacity predictions are generated based on historical and real-time traffic data, providing the projected traffic efficiency of each road over a future period. The reinforcement learning algorithm learns the optimal action sequence through trial and error, evaluating the effectiveness of different delivery strategies in a simulated environment, aiming to optimize time costs and transportation efficiency.

[0108] The detailed adjustment process includes optimizing emergency supplies transportation routes under different logistics and distribution strategies, as well as adjusting the types and quantities of emergency supplies required at each emergency response point. This not only considers route selection but also dynamically adjusts resource allocation based on the latest demand information to ensure efficient operation even in changing environments.

[0109] Performance evaluation metrics include at least delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility. These metrics are used to comprehensively measure the performance of each logistics and delivery strategy, ensuring that the selected solution is not only fast and reliable, but also flexible in responding to unforeseen events.

[0110] In this embodiment, the system first utilizes road capacity prediction results and combines them with reinforcement learning algorithms to simulate various possible logistics delivery strategies. During this process, the algorithm attempts different allocation orders, route selections, and resource adjustments to find the strategy that can complete delivery in the shortest time and at the lowest cost. Subsequently, the system performs a detailed performance evaluation of each strategy, comprehensively considering multiple dimensions such as delivery time, transportation cost, and route reliability, and ultimately determines one or more candidate target logistics delivery strategies.

[0111] To verify the practical feasibility of the selected plan, the system will apply it to the adjusted preliminary deployment plan and confirm its effectiveness through simulation exercises or other means. If the simulation results show that the plan can meet the expected goals, the plan will be officially adopted; otherwise, the system will continue to iterate and optimize until the optimal solution is found.

[0112] Here is a specific example:

[0113] In a case study of urban emergency supplies allocation, suppose the initial allocation plan has specified a route for delivering supplies from three different warehouses to four emergency stations. However, due to changes in traffic conditions (such as temporary congestion on certain roads), the original routes may no longer be the optimal choice.

[0114] At this point, the system activates a reinforcement learning algorithm, combining the latest road capacity predictions to simulate various possible logistics delivery strategies. For example, one strategy might be to prioritize a slightly longer but more easily accessible side road, while another strategy would be to use main roads during off-peak hours. The system also considers whether some delivery tasks can be merged to reduce the total travel distance and time.

[0115] Next, the system conducts a comprehensive evaluation of each strategy. For delivery time, the system checks whether all materials can arrive within the specified time; for transportation costs, it calculates expenses such as fuel consumption and vehicle wear and tear; for route reliability, it assesses potential obstacles or risks along the route; for traffic adaptability, it examines the strategy's ability to adapt to different traffic conditions; and finally, for resource flexibility, it ensures that it can be flexibly adjusted even when demand changes.

[0116] After multiple rounds of simulations and evaluations, the system ultimately selected a strategy that maximizes transportation efficiency while minimizing delays as the target logistics and distribution strategy. This solution not only avoids predicted congested road sections but also reduces total travel time and costs by optimizing the delivery sequence. Furthermore, the system underwent pre-operation validation to ensure the solution achieves the expected results in a real-world environment, thereby significantly improving the efficiency and reliability of the entire emergency supplies allocation process.

[0117] To address the multi-objective optimization problem in logistics distribution strategy selection and further improve the scientific rigor and reliability of route planning, in some embodiments, the step of selecting the target logistics distribution strategy that maximizes transportation efficiency and minimizes delays based on the evaluation results of the effects of all logistics distribution strategies includes:

[0118] Based on the evaluation results of all logistics and distribution strategies, qualified strategies are selected. A comprehensive score is then calculated for each selected strategy based on a multi-dimensional evaluation, and the highest-scoring strategies are selected as candidate strategies. The route selection, expected traffic conditions, and delay risks for each candidate strategy are analyzed to determine the target logistics and distribution strategy that maximizes transportation efficiency and minimizes delays.

[0119] In this embodiment, eligible logistics and delivery strategies refer to those that perform well in terms of delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility. Multi-dimensional evaluation involves multiple key performance indicators (KPIs), each with corresponding weights and scoring criteria, used to comprehensively measure the effectiveness of each strategy.

[0120] The scoring mechanism ensures comparability between different strategies, while selecting multiple high-scoring strategies as candidates provides more flexibility and choice for subsequent analysis.

[0121] The process involves analyzing the route planning information contained in candidate logistics and distribution strategies, including the selection of each route segment, expected traffic conditions, and potential delay risks, and integrating this information into a specific route planning scheme. This step delves into the specific details of each candidate strategy to ensure that the final selected route is not only theoretically excellent but also practically feasible.

[0122] The system selects the route planning scheme that maximizes transportation efficiency and minimizes delays as the target logistics distribution strategy. Through detailed analysis and comparison, the system identifies one or more target logistics distribution strategies that achieve optimal transportation efficiency and minimized delays while satisfying all constraints.

[0123] In this embodiment, the system first performs a preliminary screening of all logistics and delivery strategies based on pre-set multi-dimensional evaluation indicators, removing options that are clearly unsuitable. Then, a weighted scoring model is used to quantitatively evaluate the remaining strategies, where the weight of each indicator reflects its importance in the overall evaluation. The scoring model may consider the following factors:

[0124] Delivery time: The shorter the better, with higher weighting.

[0125] Transportation costs: The lower the cost, the better, but not at the expense of too much timeliness.

[0126] Route reliability: Avoid high-risk routes to ensure the safe arrival of supplies.

[0127] Traffic adaptability: The ability to flexibly respond to different traffic conditions.

[0128] Resource flexibility: It can be quickly adjusted to adapt to changes in demand.

[0129] Next, the system selects several high-scoring strategies as candidate logistics delivery strategies. For each candidate strategy, the system will analyze its path planning information in detail, including but not limited to:

[0130] Route selection for each segment: the selection of specific roads and their characteristics.

[0131] Predicted traffic conditions: Future traffic flow estimates based on predictive models.

[0132] Potential delay risks: Identify potential risk points and assess their impact.

[0133] Finally, the system integrates the above information into a specific route planning scheme and confirms its practical feasibility through simulation exercises or other verification methods. Based on this, the system selects the target logistics and distribution strategy that maximizes transportation efficiency and minimizes delays.

[0134] To address the uncertainties and complexities of the target logistics distribution strategy in actual operation and further improve the adaptability and reliability of emergency supplies allocation, in some embodiments, step 104 initiates an AI simulation exercise system based on Bayesian optimization and genetic algorithms. According to the target logistics distribution strategy, this system simulates configuration schemes for the types and quantities of emergency supplies under multiple scenarios. Using a genetic algorithm, iteratively evolves the optimal configuration scheme for the types and quantities of emergency supplies that adapts to the actual situation from the configuration schemes under multiple scenarios, and generates a comprehensive allocation instruction, including:

[0135] An AI simulation training system based on Bayesian optimization and genetic algorithms is launched, and the target logistics distribution strategy is loaded as input data to initialize the simulation environment. Bayesian optimization technology is used to automatically adjust the model parameters of the AI ​​simulation training system to improve simulation accuracy, resulting in optimized parameter configurations. Based on the optimized parameter configurations, configuration schemes for the types and quantities of emergency supplies are simulated under multiple predefined scenarios, and the allocation effect corresponding to the configuration scheme under each predefined scenario is evaluated. Through a genetic algorithm, the allocation effect corresponding to the configuration scheme under each predefined scenario is iteratively evolved to determine the optimal configuration scheme for the types and quantities of emergency supplies that can adapt to various actual situations. The effectiveness of the optimal configuration scheme is verified, and a comprehensive dispatch instruction containing a detailed emergency supplies list, estimated delivery time, and optimal transportation route is generated.

[0136] In this embodiment, the target logistics delivery strategy is determined in the previous step (such as step 103) and includes detailed transportation routes, estimated delivery times, and material allocation order. The simulation environment is a virtual platform that can reproduce traffic conditions, weather changes, and emergencies under different scenarios to test and verify the actual effectiveness of the target logistics delivery strategy.

[0137] Bayesian optimization is an efficient global optimization method, particularly suitable for parameter tuning problems in high-dimensional spaces. It finds the optimal configuration by constructing a surrogate model to predict the relationship between parameters and performance, and dynamically adjusting the parameters based on historical evaluation results. This helps ensure that the output of the simulated system closely approximates real-world conditions.

[0138] Multiple predefined scenarios can cover different time periods, weather conditions, traffic flow, and possible emergencies, such as road closures or the emergence of new emergencies. Each simulation generates a detailed report on the effectiveness of resource allocation, including key indicators such as resource utilization efficiency, rescue success rate, and emergency response speed.

[0139] Genetic algorithms mimic the process of natural selection, continuously optimizing the solution set through operations such as selection, crossover, and mutation, ultimately evolving into a highly adaptable and robust configuration scheme. This step ensures that the system can quickly adjust and provide optimal resource allocation suggestions regardless of any unforeseen circumstances.

[0140] The system will conduct multiple rounds of verification on the selected optimal configuration scheme to ensure that it can achieve the expected results in various predefined scenarios. Once the verification is successful, the system will generate the final comprehensive allocation instruction to guide the operators in completing the material allocation task.

[0141] In this embodiment, the system first loads the target logistics distribution strategy, initializes the simulation environment, and sets initial parameter values. Then, it automatically adjusts the model parameters using Bayesian optimization techniques to gradually improve simulation accuracy. Next, based on the optimized parameter configuration, the system simulates the allocation process of emergency supplies under multiple predefined scenarios and records the allocation effect in each scenario. Subsequently, a genetic algorithm is used to iteratively evolve these effects to find the optimal configuration scheme. Finally, the system verifies the effectiveness of the optimal configuration scheme and generates a comprehensive dispatch instruction containing a detailed list of emergency supplies, estimated delivery time, and optimal transportation route.

[0142] To address the discrepancy between the simulated environment and actual conditions, and to further improve the accuracy and adaptability of the configuration scheme for the types and quantities of emergency supplies, based on the above embodiments, another embodiment is provided. This embodiment simulates the configuration schemes for the types and quantities of emergency supplies under multiple predefined scenarios based on optimized parameter configurations, and evaluates the allocation effect corresponding to the configuration scheme under each predefined scenario, including:

[0143] In the AI ​​simulation exercise system, optimized parameter configurations are loaded as initial settings to initialize the simulation environment, ensuring that the simulation environment accurately reflects the actual situation. Based on the optimized parameter configurations, the allocation of emergency supplies is simulated in each predefined scenario. The simulation process includes route selection, time scheduling, and the allocation of emergency resources to obtain a configuration scheme for the types and quantities of emergency supplies in each predefined scenario. The configuration scheme for the types and quantities of each emergency supply is evaluated, and the evaluation indicators include at least delivery time, transportation cost, material utilization efficiency, rescue success rate, and emergency response speed to obtain the allocation effect corresponding to the configuration scheme.

[0144] The optimized parameter configuration, obtained through Bayesian optimization techniques, represents the best model parameters used to simulate key factors in the environment, such as vehicle speed, load capacity, and traffic flow. Initializing the simulation environment involves setting the initial state and conditions of the simulation system to closely approximate the actual operating environment. This step is crucial for ensuring the validity and reliability of subsequent simulation results.

[0145] Route selection involves determining the specific routes from the warehouse to each emergency response point; timing takes into account the time required for loading, transporting, and unloading supplies; and the allocation of emergency resources covers the types and quantities of supplies needed at different sites. By simulating these processes in detail, the system can generate specific allocation plans for each predefined scenario.

[0146] The allocation schemes for each type and quantity of emergency supplies are evaluated, with evaluation metrics including at least delivery time, transportation costs, supply utilization efficiency, rescue success rate, and emergency response speed, to determine the corresponding allocation effectiveness. These evaluation metrics are used to comprehensively measure the performance of each allocation scheme, ensuring that the final selected scheme is not only fast but also efficient. For example, delivery time reflects whether supplies can reach their destination on time; transportation costs consider factors such as fuel consumption and vehicle wear and tear; supply utilization efficiency measures whether supplies are fully utilized; rescue success rate assesses the impact of supply allocation on patient treatment; and emergency response speed focuses on the system's ability to respond to emergencies.

[0147] In this embodiment, the system first loads the optimal parameter configuration adjusted using Bayesian optimization techniques and initializes the simulation environment. This step ensures that the basic conditions of the simulation environment (such as traffic conditions and weather forecasts) are as close to the actual situation as possible, thereby improving the reliability of the simulation results. Then, based on the optimized parameter configuration, the system simulates the allocation of emergency supplies under multiple predefined scenarios. Each simulation includes detailed route selection, time scheduling, and allocation of emergency resources to generate a specific and feasible allocation plan.

[0148] Next, the system conducts a comprehensive evaluation of each generated allocation plan. During the evaluation, the system considers multiple key performance indicators, including delivery time, transportation costs, resource utilization efficiency, rescue success rate, and emergency response speed. Each indicator has a corresponding weight and scoring criteria to ensure the objectivity and scientific rigor of the evaluation results. For example, if an allocation plan has the shortest delivery time but excessively high transportation costs or low resource utilization efficiency, its overall score may be affected.

[0149] Finally, the system calculates the effectiveness of emergency supplies allocation for each predefined scenario based on the evaluation results. This process not only helps identify the optimal allocation plan but also provides valuable data support for subsequent decision-making, ensuring that the expected results can be achieved in actual operation.

[0150] Here is a specific example:

[0151] In a case study of urban emergency supplies allocation, it is assumed that the system has adjusted the model parameters through Bayesian optimization techniques and initialized the simulation environment, setting basic conditions such as traffic flow and weather conditions for the current time period.

[0152] The system loads optimized parameter configurations and sets basic parameters for the simulation environment to ensure that the simulation environment accurately reflects the actual situation. For example, considering that the main road is under construction at the current time, the system lowers the traffic efficiency of that road segment to simulate real traffic conditions.

[0153] The system simulates the allocation of emergency medical supplies under multiple predefined scenarios. For example, one scenario simulates traffic congestion during peak daytime hours; another simulates unobstructed roads at night. Each simulation includes detailed route selection (e.g., choosing main roads or side roads), time scheduling (e.g., estimated departure and arrival times), and allocation of emergency medical resources (e.g., the quantity of medicines and equipment required at each station). In this way, the system generates a specific allocation plan for each predefined scenario.

[0154] The system comprehensively evaluates each generated allocation plan. Evaluation metrics include, but are not limited to, delivery time, transportation costs, resource utilization efficiency, rescue success rate, and emergency response speed. For example, in one simulation, the system found that a certain route, although longer, was expected to be more accessible. Therefore, despite the increased total travel distance, the delivery time was significantly reduced, and the transportation cost was lower. Simultaneously, the system also evaluated the resource utilization efficiency and rescue success rate along this route to ensure that the selected plan achieves an optimal balance in all aspects.

[0155] Ultimately, the system calculates the effectiveness of emergency supplies distribution in each predefined scenario based on the evaluation results. For example, in a daytime peak-hour simulation, the system selected a side road that avoided main roads as the delivery route, ensuring that supplies could reach their destination smoothly within the specified time while reducing transportation costs. In a nighttime simulation, the system leveraged the unobstructed access of main roads to further optimize the delivery sequence and improve overall efficiency.

[0156] In this way, the system not only improves the accuracy and reliability of simulation results, but also enhances its adaptability to various real-world situations, ensuring that emergency supplies can be delivered to their destination efficiently in the shortest possible time, and significantly improving the efficiency and reliability of the entire emergency supplies allocation process.

[0157] To address the complexity and diversity of demand information parsing and further improve the accuracy and scientific rigor of emergency response point demand urgency assessment, in some embodiments, the graph neural network-based intelligent assessment system described in step 102 assesses the demand urgency of each emergency response point based on the demand information and generates a preliminary allocation plan, including:

[0158] Natural language processing algorithms are used to parse and process demand information from multiple emergency response points, obtaining specific demand results for each emergency response point. Based on these specific demand results, a graph structure data model is constructed, where nodes in the graph structure data model represent each emergency response point, and edges represent the correlation and influence range between different emergency response points. Based on pre-trained model parameters, a graph neural network intelligent evaluation system is launched to load and process the graph structure data model, ensuring that the graph neural network intelligent evaluation system can identify and process different types of node and edge attributes. Using the graph neural network intelligent evaluation system, the urgency of demand for each emergency response point is evaluated, and a demand urgency score for each node is calculated. The demand urgency score is determined based on the correlation and influence range between different emergency response points. Based on the demand urgency score, a preliminary deployment plan is generated.

[0159] In this embodiment, the demand information can be in the form of a text report, voice recording, or structured data form. NLP algorithms are used to extract and understand key information such as the number, type, severity, on-site medical resource status, priority indicators, and geospatial distribution of the injured. In this way, the system can transform unstructured input into structured, specific demand results, providing a foundation for subsequent assessment.

[0160] Graph-based data models are a mathematical abstraction that represents complex real-world relationships in the form of nodes (emergency response points) and edges (relationships and scope of impact). Node attributes may include location, urgency rating, etc.; edge attributes reflect factors such as distance, transportation conditions, and resource sharing between different response points. This modeling approach helps to intuitively demonstrate the interactions between response points, providing structured data support for intelligent assessment.

[0161] Graph Neural Networks (GNNs) are deep learning models specifically designed for processing graph-structured data. They can capture the complex relationships between nodes, thus more accurately assessing the urgency of needs. Pre-trained model parameters enable the system to generalize well to different types of data, while the urgency score is a result that comprehensively considers factors such as the correlation between different response points, the scope of influence, and priority indicators.

[0162] The initial deployment plan clearly defines the types and quantities of emergency supplies needed at each emergency response point, as well as the priority order for supply allocation. This process considers not only the needs of individual response points but also the optimal allocation of resources across the entire network, ensuring that the most urgently needed resources reach their destinations as quickly as possible.

[0163] Here is a specific example:

[0164] In a case study of urban emergency medical supplies allocation, suppose the system receives demand information from multiple emergency response points. This information includes various formats such as text descriptions, voice recordings, and tabular data. To effectively process this information, the system first uses NLP algorithms for parsing and processing to extract the specific demand results for each emergency response point. For example, at one location, there are 5 seriously injured patients requiring immediate surgery, and at another location, there are 3 slightly injured patients waiting for bandaging.

[0165] The system analyzes the above information using NLP algorithms to identify key elements such as the number, type, and severity of injuries. For example, the text description "5 seriously injured patients" is automatically interpreted as "5 severely injured patients"; the voice recording "more bandages needed" is converted into a demand for bandages.

[0166] Based on the analyzed specific requirements, the system constructs a graph-structured data model. In this model, each emergency response point is represented as a node, with node attributes including location and urgency score. The correlation and impact range between different response points are connected as edges, with edge attributes reflecting factors such as traffic conditions and resource sharing. For example, if there is a fast passage between two adjacent stations, the edge between them will have a higher weight.

[0167] The system loads a pre-trained graph neural network intelligent evaluation system to process the graph structure data model. This system can identify and process different types of node and edge attributes, assess the urgency of each emergency response point, and calculate a urgency score. For example, a response point close to a hospital and with convenient transportation might receive a higher score because it is more likely to receive additional support.

[0168] Based on the urgency score, the system generates a preliminary allocation plan, specifying the types and quantities of emergency supplies needed at each emergency response point, as well as the priority order for resource allocation. For example, the system decides to first allocate more medicines and equipment to the response point with the highest score, ensuring that the most urgently needed resources arrive as quickly as possible.

[0169] In this way, the system not only improves the efficiency and accuracy of demand information analysis, but also enhances the scientific nature and reliability of the assessment of the urgency of emergency response point needs, ensuring that emergency supplies can be efficiently allocated in the shortest possible time, and significantly improving the efficiency and effectiveness of the entire emergency supplies allocation process.

[0170] This application recognizes that evaluating logistics and distribution strategies requires comprehensive consideration of multiple key performance indicators (KPIs) to ensure that the selected route planning scheme not only avoids predicted congested sections and arrives at the designated location on time, but also achieves optimal performance in terms of transportation costs, route reliability, traffic adaptability, and resource flexibility. Traditional single-indicator evaluation methods are insufficient to fully reflect complex and ever-changing actual needs; therefore, a new alternative scheme is proposed, which includes:

[0171] For each of the aforementioned logistics and delivery strategies, a performance evaluation is performed to assess its ability to avoid anticipated congested routes and ensure timely arrival at the designated location. Performance evaluation metrics include at least delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility. The evaluation results for each of the aforementioned logistics and delivery strategies are then obtained, including:

[0172] For each of the aforementioned logistics and distribution strategies Performance evaluation processes should be conducted to avoid anticipated congested road sections and ensure timely arrival at designated locations. Performance evaluation metrics should include at least: delivery time. Transportation costs Path reliability Traffic adaptability Resource flexibility ;

[0173] Evaluation results Calculated using the following formula:

[0174]

[0175] in, These are the weighting coefficients for delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, respectively. It is an exponential adjustment factor for delivery time, used to reflect the severity of the delay; These are the maximum values ​​of path reliability, traffic adaptability, and resource flexibility, respectively, used for normalization to ensure that the values ​​of each performance evaluation index are within a certain range. Within the range.

[0176] The following is a detailed explanation of each parameter:

[0177] : No. The comprehensive evaluation score of a logistics and delivery strategy is used to measure the overall performance of the strategy. It is calculated by comprehensively considering multiple key performance indicators (such as delivery time, transportation cost, route reliability, etc.) and according to preset weighting coefficients and index adjustment factors.

[0178] These are weighting coefficients for delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, respectively. These weights reflect the relative importance of different indicators in the overall evaluation and can be adjusted according to actual circumstances. They are determined through expert systems or historical data analysis. For example, initial weights can be set based on past success stories or expert opinions and dynamically adjusted based on feedback from actual operations.

[0179] An exponential adjustment factor for delivery time, used to reflect the severity of the delay. This is achieved through an exponential function. The impact of prolonged delays on assessment results was emphasized. This was determined through experimental data fitting or simulation. Typically, a suitable exponential adjustment factor value can be found by analyzing the impact of different delay times on rescue effectiveness. The actual travel time for each route was obtained through GPS tracking systems or simulations. Future delivery times can also be predicted by combining real-time traffic data.

[0180] : No. For this logistics and delivery strategy, the shorter the delivery time (in hours), the better. Use an exponential function to amplify the impact of long delays and ensure the importance of fast delivery. Obtain the actual travel time for each route through GPS tracking systems or simulations. Real-time traffic data can also be used to predict future delivery times.

[0181] : No. The transportation cost (in yuan) for each logistics and distribution strategy should be as low as possible. This directly and linearly impacts the evaluation score, ensuring cost-effectiveness. This cost can be obtained through quotations from logistics companies or their internal cost accounting systems. Factors such as fuel consumption and vehicle wear and tear can also be considered for a detailed cost analysis.

[0182] :No. The path reliability of this logistics and distribution strategy, with a value range of [value missing]. The higher the better. After normalization, compare it with the maximum value. The comparison addresses shortcomings in calculating route reliability. This is achieved through historical data statistics and real-time monitoring. For example, the success rate of similar routes in the past can be analyzed, or the reliability of the current route can be assessed using real-time traffic conditions and weather forecasts (the calculation method can be designed according to requirements, such as calculating route reliability by weighted summation of the above information).

[0183] : No. The traffic adaptability of various logistics and distribution strategies, with a value range of [value range missing]. The higher the better. After normalization, compare it with the maximum value. The shortcomings of traffic adaptability are compared and calculated. This is obtained through traffic flow prediction models and real-time traffic data. For example, real-time traffic information provided by traffic cameras, sensor data, or navigation software can be used to evaluate the adaptability of a route to different traffic conditions (the calculation method can be designed according to needs, such as calculating traffic adaptability by weighted summation of various real-time traffic information).

[0184] :No. The resource flexibility of this logistics and distribution strategy, with a value range of [value range missing]. The higher the better. After normalization, compare it with the maximum value. The comparison assesses the shortcomings in resource flexibility. This information is obtained through the materials management system and emergency response database. For example, the types, quantities, and distribution of existing resources can be analyzed to assess the flexibility and response speed of resource allocation (the calculation method can be designed according to needs, such as calculating resource flexibility by weighted summation of the above information).

[0185] The following explains the rationale behind each sub-item design:

[0186] Delivery time is a key factor, especially in the allocation of emergency supplies, where time is of paramount importance. Using an exponential function... This can amplify the impact of long delays, highlighting the importance of ensuring rapid delivery. (Exponential adjustment factor) Used to adjust the sensitivity to time delays.

[0187] Transportation costs directly impact the economics of the entire delivery solution. A linear approach is used to directly incorporate these costs into the evaluation score, ensuring cost-effectiveness. Lower costs contribute to a higher overall score.

[0188] Path reliability reflects the safety and stability of a path. After normalization, any deficiencies in path reliability are calculated to ensure that the selected path is sufficiently safe and reliable. Higher path reliability means less risk and a higher success rate.

[0189] Traffic adaptability considers the ability of a path to adapt to different traffic conditions. After normalization, the shortcomings of traffic adaptability are calculated to ensure that the selected path can flexibly cope with various traffic changes and reduce the occurrence of unexpected situations.

[0190] Resource flexibility reflects the system's flexibility and response speed in resource allocation. After normalization, any deficiencies in resource flexibility are calculated to ensure that resources can be quickly allocated when needed, thereby improving the overall responsiveness of the system.

[0191] The summation of the individual items is done to comprehensively consider multiple Key Performance Indicators (KPIs), ensuring a thorough and scientific evaluation. Each item represents an important evaluation dimension, assigned different weighting coefficients. This allows for the assessment of the importance of different indicators within the overall evaluation. Specifically, by summing up the various sub-items, a comprehensive evaluation can be conducted on the performance of each logistics and distribution strategy in multiple aspects, including delivery time, transportation costs, route reliability, traffic adaptability, and resource flexibility.

[0192] Weighting Adjustment: The weighting coefficients allow you to adjust the importance of different indicators based on actual needs. For example, in emergency situations, delivery time may be more critical, and the weighting can be increased. The value is used to highlight its impact. Final score It comprehensively reflects the performance of all key performance indicators, ensuring that the selected solution is not only excellent in one aspect, but achieves the best balance in multiple aspects.

[0193] This comprehensive evaluation method ensures that the selection of logistics and distribution strategies is more scientific and reasonable, improves the accuracy and reliability of decision-making, and is better able to cope with various challenges, especially in complex and ever-changing real-world environments.

[0194] Here is a specific example:

[0195] In a case study of urban emergency supplies allocation, assume the system generates three different logistics and distribution strategies. The specific data is shown in Table 1 below:

[0196] Table 1

[0197]

[0198] Assume the maximum values ​​of each performance evaluation metric are as follows:

[0199]

[0200]

[0201]

[0202] Furthermore, the weighting coefficients and the exponential adjustment factor are set as follows:

[0203]

[0204]

[0205]

[0206]

[0207]

[0208]

[0209] Calculation process:

[0210] for :

[0211]

[0212] for :

[0213]

[0214] for :

[0215]

[0216] Conclusion Explanation:

[0217] Based on the above calculations, the evaluation results of the three logistics and distribution strategies are as follows:

[0218]

[0219]

[0220]

[0221] The calculation results show that, although It received the highest evaluation score, but due to its high transportation costs (900 yuan) and low resource flexibility (0.65), it may not be suitable for all situations in actual operation. In contrast, and The scores were quite close, but The delivery time is shorter (2.5 hours vs 3.0 hours), and the route reliability and traffic adaptability are both better, therefore... That might be a more ideal choice.

[0222] Ultimately, the system chose As a targeted logistics and distribution strategy, it ensures optimal transportation efficiency and minimized delays while meeting all constraints. This not only improves the scientific rigor and accuracy of decision-making but also enhances adaptability to emergencies, ensuring that emergency supplies can be delivered to their destination efficiently in the shortest possible time.

[0223] This application considers that the evaluation of the configuration scheme for the types and quantities of emergency supplies requires comprehensive consideration of multiple key performance indicators (KPIs) to ensure that the selected route planning scheme not only utilizes resources efficiently and improves the success rate of rescue, but also responds in the shortest possible time. Traditional single-indicator evaluation methods are insufficient to fully reflect the complex and ever-changing actual needs; therefore, a new alternative scheme is proposed, which includes:

[0224] The evaluation of the configuration scheme for each type and quantity of emergency supplies includes evaluation indicators such as supply utilization efficiency, rescue success rate, and emergency response speed, to obtain the allocation effect corresponding to the configuration scheme, including:

[0225] Based on the optimized parameter configuration In each predefined scenario The following simulation process is performed on the distribution of the emergency supplies, including route selection. Schedule and the allocation of the aforementioned emergency medical resources To obtain a configuration scheme for the types and quantities of emergency supplies in each predefined scenario. ;

[0226] Each allocation scheme Represented as:

[0227]

[0228] Indicates the first One transportation route; Indicates the first The time schedule for each transportation route; Indicates the first The demand for emergency medical supplies;

[0229] Configuration scheme for the type and quantity of each of the aforementioned emergency supplies. An evaluation should be conducted, and the evaluation indicators should include at least the efficiency of material utilization. Rescue success rate Emergency response speed ;

[0230] Distribution effect Calculated using the following formula:

[0231]

[0232] These are the weighting coefficients for resource utilization efficiency, rescue success rate, and emergency response speed, respectively. It is the corresponding index adjustment factor; Indicates the first Allocation of emergency medical resources along the routes The calculated resource utilization efficiency represents the resource utilization efficiency. A specific instance under a specific path and resource allocation; Indicates the first Scheduled for a given time on the path The rescue success rate represents the overall success rate of the rescue. Specific examples under a particular path and time schedule; This represents the shortest delivery time among all routes, used to measure emergency response speed. ; It represents the maximum efficiency of material utilization and is used for normalization.

[0233] The following is a detailed explanation of each parameter:

[0234] : No. The comprehensive evaluation score of the configuration scheme of the types and quantities of emergency supplies under a predefined scenario is used to measure the overall effectiveness of the scheme. It is calculated by comprehensively considering multiple key performance indicators (such as material utilization efficiency, rescue success rate, emergency response speed, etc.) and according to preset weighting coefficients and index adjustment factors.

[0235] The optimized parameter configuration includes key parameters such as the speed and loading capacity of the transport vehicles. This is determined through historical data analysis, simulation, and expert systems. For example, initial parameters can be set based on successful past delivery cases or expert opinions, and then dynamically adjusted based on feedback from actual operations.

[0236] :No. It provides predefined scenarios to simulate different emergency response conditions (such as weather, traffic conditions, etc.). These scenarios are generated by analyzing historical emergency response records and real-time environmental data. For example, multiple possible emergency response scenarios can be constructed based on past meteorological data, traffic flow information, and emergency reports.

[0237] Each allocation scheme is represented as ,in : No. One transportation route. : No. The schedule for each transportation route. : No. The demand for emergency medical supplies is generated using route planning algorithms and time scheduling models. For example, shortest path algorithms (such as Dijkstra's algorithm), time window constraint optimization models, and demand forecasting models can be used to generate detailed route selections and time schedules.

[0238] These are weighting coefficients for resource utilization efficiency, rescue success rate, and emergency response speed, respectively. These weights reflect the relative importance of different indicators in the overall assessment and are determined through expert systems or historical data analysis. For example, initial weights can be set based on past successful cases or expert opinions and dynamically adjusted based on feedback from actual operations.

[0239] The corresponding index adjustment factor is used to adjust the degree of influence of each component on the final score. It is determined through experimental data fitting or simulation. Typically, a suitable index adjustment factor value can be found by analyzing the impact of factors such as different delay times and changes in success rate on the rescue effect.

[0240] : in the Allocation of emergency medical resources along the routes The calculated resource utilization efficiency represents the resource utilization efficiency. Specific examples under specific paths and resource allocation. Obtained through materials management systems and emergency response databases. For example, the types, quantities, and distribution of existing resources can be analyzed to assess the flexibility and speed of resource deployment.

[0241] : in the Scheduled for a given time on the path The rescue success rate represents the overall success rate of the rescue operation. Specific examples under specific routes and time schedules. Obtained through historical data statistics and real-time monitoring. For example, the success rate of similar routes in the past can be analyzed, or the reliability of the current route can be assessed through real-time traffic conditions and weather forecasts.

[0242] The shortest delivery time among all routes, used to measure emergency response speed. The actual travel time for each route can be obtained through GPS tracking systems or simulations. Real-time traffic data can also be used to predict future delivery times.

[0243] The maximum value of material utilization efficiency is used for normalization to ensure that the values ​​of each performance indicator are within a certain range. Within a given range. Determined through historical data analysis and best practice case studies. For example, the highest resource utilization efficiency can be identified as a benchmark based on past successful resource allocation cases.

[0244] The following is a brief introduction to the reasons for each sub-item design:

[0245] Resource utilization efficiency It is a key indicator for measuring whether resources are being fully utilized. This is achieved by measuring the efficiency of material use along each pathway. Accumulate and divide by the maximum value. Perform normalization to ensure its value is within Within the range. Exponential adjustment factor. This is used to emphasize the importance of efficiency, ensuring that solutions that make efficient use of resources receive higher scores.

[0246] Rescue success rate This reflects the impact of the delivery plan on the actual rescue effectiveness. It also shows the rescue success rate along each route. Multiply, then apply the logarithmic function This smooths out large-scale variations, ensuring that the score is not unbalanced due to excessively high or low success rates for individual paths. Multiplication ensures that the success rate of all paths is considered, while the logarithmic function prevents excessively large or small values ​​from affecting the overall score. Exponential adjustment factor. Used to adjust the degree of influence on the success rate of rescue.

[0247] Emergency response speed This is a crucial factor in emergency situations. It involves finding the minimum delivery time among all possible routes. And apply the exponential function This can amplify the importance of rapid response. Exponential adjustment factor. This is used to adjust the impact of response speed, ensuring that solutions that reach the destination quickly receive higher scores.

[0248] This formula adds up all the sub-items to comprehensively consider multiple key performance indicators (KPIs), ensuring a comprehensive and scientific evaluation result. Each sub-item represents an important evaluation dimension, assigned different weighting coefficients. This allows for the assessment of the importance of different indicators within the overall evaluation. Specifically, by summing up the various sub-items, a comprehensive evaluation can be conducted on the performance of each type and quantity of emergency supplies in terms of resource utilization efficiency, rescue success rate, and emergency response speed. Weighting coefficients allow for adjustments to the importance of different indicators based on actual needs. For example, in emergency situations, emergency response speed may be more critical, and the importance of these indicators can be increased. The value is used to highlight its impact. Final score It comprehensively reflects the performance of all key performance indicators, ensuring that the selected solution is not only excellent in one aspect, but achieves the best balance in multiple aspects.

[0249] This comprehensive evaluation method ensures that the selection of the types and quantities of emergency supplies is more scientific and reasonable, improving the accuracy and reliability of decision-making. Especially in complex and ever-changing real-world environments, it can better cope with various challenges and achieve the most efficient allocation of supplies.

[0250] Here is a specific example:

[0251] Suppose we have three predefined scenarios And set the following parameters:

[0252] Weighting coefficient:

[0253]

[0254]

[0255]

[0256] Exponential adjustment factor:

[0257]

[0258]

[0259]

[0260] Maximum value:

[0261]

[0262] For each scenario, the specific values ​​are shown in Table 2 below:

[0263] Table 2

[0264]

[0265] Calculation process:

[0266] calculate Distribution effect :

[0267]

[0268] calculate Distribution effect :

[0269]

[0270] calculate Distribution effect :

[0271]

[0272] Based on the above calculations, the evaluation results for the three predefined scenarios are as follows:

[0273]

[0274]

[0275]

[0276] The calculation results show that, although It received the highest evaluation score, but its shortest delivery time of 2.5 hours is relatively long, which may result in a slower response time. In contrast, Although its assessment score was lower, its shortest delivery time was 1.5 hours, enabling a faster response to emergencies, and its resource utilization efficiency and rescue success rate were also higher. Therefore, considering all factors, That is the more ideal choice.

[0277] Ultimately, the system chose As a targeted logistics and distribution strategy, it ensures optimal transportation efficiency and minimized delays while meeting all constraints. This not only improves the scientific rigor and accuracy of decision-making but also enhances adaptability to emergencies, ensuring that emergency supplies can be delivered to their destination efficiently in the shortest possible time.

[0278] This approach not only improves the accuracy of decision-making but also enhances adaptability to unforeseen events, ensuring optimal logistics and distribution decisions can be made in complex and ever-changing real-world environments.

[0279] Figure 2 This application provides a schematic diagram of the structure of an intelligent decision-making system for the emergency allocation of emergency medical supplies, as shown in the embodiments of this application. Figure 2 As shown, the system includes:

[0280] The receiving module 21 is used to receive demand information from multiple emergency response points. The demand information includes at least the number of injured, the type of injury, the severity of injury, the status of on-site medical resources, priority indicators, and geographic spatial distribution.

[0281] The generation module 22 is used to evaluate the urgency of the needs of each emergency response point based on the graph neural network intelligent evaluation system and generate a preliminary allocation plan. The preliminary allocation plan is determined according to the urgency of the needs of each emergency response point and includes the types and quantities of emergency supplies required by each emergency response point, as well as the allocation order of the emergency supplies.

[0282] Module 23 is used to utilize a deep learning prediction model to generate road capacity prediction results based on historical traffic data and real-time traffic data obtained from multiple sources. It also combines this with reinforcement learning algorithms to simulate various logistics delivery strategies, refine the preliminary allocation plan, and determine the target logistics delivery strategy. The road capacity prediction results refer to the deep learning prediction model using historical traffic data, real-time traffic data, and model algorithms to estimate road traffic conditions over a future period. The logistics delivery strategy is formulated based on the allocation order of emergency supplies in the preliminary allocation plan. The target logistics delivery strategy avoids predicted congested road sections and ensures timely arrival at the designated location.

[0283] The generation module 22 is also used to launch an AI simulation exercise system based on Bayesian optimization and genetic algorithm. According to the target logistics distribution strategy, it simulates the configuration schemes of the types and quantities of emergency supplies under multiple scenarios, and iteratively evolves the optimal configuration scheme of the types and quantities of emergency supplies that can adapt to the actual situation from the configuration schemes under multiple scenarios through genetic algorithm, and generates a comprehensive dispatch instruction. The comprehensive dispatch instruction includes an emergency supplies list, estimated delivery time and optimal transportation route.

[0284] The execution module 24 is used to execute the comprehensive allocation command to realize the emergency allocation of the emergency supplies.

[0285] Figure 2 The aforementioned intelligent decision-making system for the emergency allocation of emergency medical supplies can execute... Figure 1 The implementation principle and technical effects of the intelligent decision-making method for emergency allocation of emergency supplies described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit of the intelligent decision-making system for emergency allocation of emergency supplies in the above embodiments are described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0286] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0287] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An intelligent decision-making method for the emergency allocation of emergency medical supplies, characterized in that, include: Receive demand information from multiple emergency response points, the demand information including at least the number of injured, the type of injury, the severity of injury, the status of on-site medical resources, priority indicators, and geographic spatial distribution; Based on the graph neural network intelligent assessment system, the urgency of the needs of each emergency response point is assessed according to the demand information, and a preliminary allocation plan is generated. The preliminary allocation plan is determined according to the urgency of the needs of each emergency response point, and includes the types and quantities of emergency supplies required by each emergency response point, as well as the allocation order of the emergency supplies. Using a deep learning prediction model, road capacity predictions are generated based on historical and real-time traffic data from multiple sources. Reinforcement learning algorithms are then combined to simulate various logistics delivery strategies, refining the initial allocation plan and determining the target logistics delivery strategy. The road capacity predictions refer to the deep learning prediction model's estimation of road traffic conditions over a future period using historical traffic data, real-time traffic data, and model algorithms. The logistics delivery strategy is formulated based on the allocation order of emergency supplies in the initial allocation plan. The target logistics delivery strategy avoids predicted congested road sections and ensures timely arrival at designated locations. An AI simulation exercise system based on Bayesian optimization and genetic algorithm is launched. According to the target logistics distribution strategy, the system simulates the configuration schemes of the types and quantities of emergency supplies under multiple scenarios. The system then uses a genetic algorithm to iteratively evolve the optimal configuration scheme of the types and quantities of emergency supplies that can adapt to the actual situation from the configuration schemes under multiple scenarios, and generates a comprehensive dispatch instruction. The comprehensive dispatch instruction includes an emergency supplies list, estimated delivery time, and optimal transportation route. Execute the comprehensive allocation command to realize the emergency allocation of the emergency medical supplies; An AI simulation exercise system based on Bayesian optimization and genetic algorithms is launched. According to the target logistics distribution strategy, it simulates configuration schemes for the types and quantities of emergency supplies under multiple scenarios. Using a genetic algorithm, it iteratively evolves from these configuration schemes to find the optimal configuration scheme for the types and quantities of emergency supplies that adapts to the actual situation, and generates comprehensive allocation instructions, including: Start the AI ​​simulation training system based on Bayesian optimization and genetic algorithm, load the target logistics distribution strategy as input data, and initialize the simulation environment; Bayesian optimization techniques are used to automatically adjust the model parameters of the AI ​​simulation training system to improve simulation accuracy and obtain optimized parameter configuration. Based on the optimized parameter configuration, the configuration schemes for the types and quantities of the emergency supplies are simulated in multiple predefined scenarios, and the allocation effect corresponding to the configuration scheme in each predefined scenario is evaluated. By using a genetic algorithm, the allocation effect corresponding to the configuration scheme under each predefined scenario is iteratively evolved to determine the optimal configuration scheme for the types and quantities of emergency supplies that can adapt to various actual situations. Verify the effectiveness of the optimal configuration scheme and generate a comprehensive dispatch instruction that includes a detailed list of emergency supplies, estimated delivery time, and optimal transportation route; The process involves simulating configuration schemes for the types and quantities of emergency supplies under multiple predefined scenarios based on optimized parameter configurations, and evaluating the allocation effect of each configuration scheme under each predefined scenario, including: In the AI ​​simulation training system, the optimized parameter configuration is loaded as the initial setting to initialize the simulation environment and ensure that the simulation environment can accurately reflect the actual situation. Based on the optimized parameter configuration, the allocation of emergency supplies is simulated in each predefined scenario. The simulation process includes route selection, time arrangement, and allocation of emergency supplies to obtain the configuration scheme of the types and quantities of emergency supplies in each predefined scenario. Evaluate the allocation schemes for each type and quantity of emergency supplies, with evaluation indicators including at least delivery time, transportation cost, supply utilization efficiency, rescue success rate, and emergency response speed, to obtain the allocation effect corresponding to the allocation schemes; The graph neural network-based intelligent assessment system, based on the demand information, assesses the urgency of the demand at each emergency response point and generates a preliminary allocation plan, including: Natural language processing algorithms are used to parse and process demand information from multiple emergency response points to obtain specific demand results for each emergency response point. Based on the specific requirements, a graph structure data model is constructed, wherein the nodes in the graph structure data model represent various emergency response points, and the edges represent the correlation and influence range between different emergency response points. Based on the pre-trained model parameters, the graph neural network intelligent evaluation system is launched to load and process the graph structure data model, ensuring that the graph neural network intelligent evaluation system can identify and process different types of node and edge attributes. The graph neural network intelligent evaluation system is then used to evaluate the urgency of each emergency response point and calculate the urgency score of each node. The urgency score is determined based on the correlation and impact range between different emergency response points. Based on the urgency score of the demand, a preliminary allocation plan is generated.

2. The method according to claim 1, characterized in that, The method of generating road capacity prediction results using a deep learning prediction model based on historical traffic data and real-time traffic data obtained from multiple sources includes: Historical traffic data and real-time traffic data obtained from multiple sources are integrated to obtain a traffic dataset. The historical traffic data includes at least traffic flow, accident records and weather effects in the same time period in the past, and the real-time traffic data includes at least current traffic camera images, vehicle location information and real-time traffic conditions provided by sensors. The traffic data in the traffic dataset is analyzed and processed using a deep learning prediction model to generate prediction results of road capacity over a future period. The deep learning prediction model is trained to identify and predict the impact of different factors on road capacity and output the expected traffic efficiency of each road in a specific future time period, thereby generating prediction results of road capacity.

3. The method according to claim 2, characterized in that, Based on the predicted road capacity, various logistics and distribution strategies are simulated using reinforcement learning algorithms. The preliminary allocation plan is then refined and adjusted, and a target logistics and distribution strategy is determined, including: Using the predicted road capacity and a reinforcement learning algorithm, the allocation order of emergency supplies in the preliminary allocation plan is simulated to obtain a variety of logistics and distribution strategies aimed at optimizing time cost and transportation efficiency. Based on various logistics and distribution strategies, the preliminary allocation plan is refined and adjusted. The process of refining and adjusting includes optimizing the transportation routes of the emergency supplies under different logistics and distribution strategies and adjusting the types and quantities of emergency supplies required for each emergency response point to adapt to the actual situation. For each of the aforementioned logistics and delivery strategies, a performance evaluation process is performed to avoid predicted congested road sections and ensure timely arrival at the designated location. The performance evaluation indicators include at least delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, thereby obtaining the evaluation results for each of the aforementioned logistics and delivery strategies. Based on the evaluation results of the effectiveness of all logistics and distribution strategies, select the target logistics and distribution strategy that can maximize transportation efficiency and minimize delays; The target logistics and distribution strategy is applied to the adjusted preliminary allocation plan for verification and confirmation to ensure that the target logistics and distribution strategy can achieve the expected results in actual operation.

4. The method according to claim 3, characterized in that, The process of selecting a target logistics and distribution strategy that maximizes transportation efficiency and minimizes delays based on the evaluation results of all logistics and distribution strategies includes: Based on the evaluation results of the effectiveness of all logistics and distribution strategies, qualified logistics and distribution strategies are selected. Based on multi-dimensional evaluation, the selected logistics and distribution strategies are comprehensively scored to obtain a score for each logistics and distribution strategy. The one or more logistics and distribution strategies with the highest scores are selected as candidate logistics and distribution strategies. The selection of each segment of the route, the expected traffic conditions, and the delay risk in each of the candidate logistics and distribution strategies are analyzed to determine the target logistics and distribution strategy that can maximize transportation efficiency and minimize delays.

5. The method according to claim 3, characterized in that, For each of the aforementioned logistics and delivery strategies, a performance evaluation process is performed to ensure timely arrival at the designated location while avoiding anticipated congested road sections. The performance evaluation indicators include at least delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility. The evaluation results for each of the aforementioned logistics and delivery strategies are obtained, including: For each of the aforementioned logistics and distribution strategies Performance evaluation processes should be conducted to avoid anticipated congested road sections and ensure timely arrival at designated locations. Performance evaluation metrics should include at least: delivery time. Transportation costs Path reliability Traffic adaptability Resource flexibility ; Evaluation results Calculated using the following formula: ； in, These are the weighting coefficients for delivery time, transportation cost, route reliability, traffic adaptability, and resource flexibility, respectively. It is an exponential adjustment factor for delivery time, used to reflect the severity of the delay; These are the maximum values ​​of path reliability, traffic adaptability, and resource flexibility, respectively, used for normalization to ensure that the values ​​of each performance evaluation index are within a certain range. Within the range.

6. The method according to claim 1, characterized in that, The evaluation of the configuration scheme for each type and quantity of emergency supplies includes evaluation indicators such as supply utilization efficiency, rescue success rate, and emergency response speed, to obtain the allocation effect corresponding to the configuration scheme, including: Based on the optimized parameter configuration In each predefined scenario The following simulation process is performed on the distribution of the emergency supplies, including route selection. Schedule and the distribution of the aforementioned emergency medical supplies. To obtain a configuration scheme for the types and quantities of emergency supplies in each predefined scenario. ; Each allocation scheme Represented as: Indicates the first One transportation route; Indicates the first The time schedule for each transportation route; Indicates the first The demand for emergency medical supplies; Configuration scheme for the type and quantity of each of the aforementioned emergency supplies. An evaluation should be conducted, and the evaluation indicators should include at least the efficiency of material utilization. Rescue success rate Emergency response speed ; Distribution effect Calculated using the following formula: ； These are the weighting coefficients for resource utilization efficiency, rescue success rate, and emergency response speed, respectively. It is the corresponding index adjustment factor; Indicates the first Allocation of emergency medical resources along the routes The calculated resource utilization efficiency represents the resource utilization efficiency. A specific instance under a specific path and resource allocation; Indicates the first Scheduled for a given time on the path The rescue success rate represents the overall success rate of the rescue. Specific examples under a particular path and time schedule; This represents the shortest delivery time among all routes, used to measure emergency response speed. ; It represents the maximum efficiency of material utilization and is used for normalization.

7. An intelligent decision-making system for the emergency allocation of emergency medical supplies, used to execute the intelligent decision-making method for the emergency allocation of emergency medical supplies as described in any one of claims 1 to 6, characterized in that, include: The receiving module is used to receive demand information from multiple emergency response points. The demand information includes at least the number of injured, the type of injury, the severity of injury, the status of on-site medical resources, priority indicators, and geographic spatial distribution. The generation module is used to evaluate the urgency of the needs of each emergency response point based on the demand information according to the graph neural network intelligent assessment system, and generate a preliminary allocation plan. The preliminary allocation plan is determined according to the urgency of the needs of each emergency response point, and includes the types and quantities of emergency supplies required by each emergency response point, as well as the allocation order of the emergency supplies. The determination module utilizes a deep learning prediction model to generate road capacity predictions based on historical and real-time traffic data from multiple sources. It then combines this with reinforcement learning algorithms to simulate various logistics delivery strategies, refining the initial allocation plan and determining the target logistics delivery strategy. The road capacity predictions refer to the deep learning prediction model's estimation of road traffic conditions over a future period using historical, real-time traffic data and model algorithms. The logistics delivery strategy is formulated based on the allocation order of emergency supplies in the initial allocation plan. The target logistics delivery strategy avoids predicted congested road sections and ensures timely arrival at designated locations. The generation module is also used to launch an AI simulation exercise system based on Bayesian optimization and genetic algorithm. According to the target logistics distribution strategy, it simulates the configuration schemes of the types and quantities of emergency supplies under multiple scenarios, and iteratively evolves the optimal configuration scheme of the types and quantities of emergency supplies that can adapt to the actual situation from the configuration schemes under multiple scenarios through genetic algorithm, and generates a comprehensive dispatch instruction. The comprehensive dispatch instruction includes an emergency supplies list, estimated delivery time and optimal transportation route. The execution module is used to execute the comprehensive allocation command to realize the emergency allocation of the emergency supplies.

Images