Emergency resource optimization scheduling method and system based on event priority evaluation and medium

Abstract

The invention discloses an emergency resource optimization scheduling method based on event priority evaluation, and belongs to the technical field of emergency management, and the method comprises the following steps: S1, obtaining a plurality of pieces of emergency event information; s2, performing priority evaluation on each emergency event based on a preset priority evaluation model, and outputting a priority score, the priority evaluation model being constructed based on historical disaster data and an evolution rule thereof; s3, analyzing required emergency resources according to the priority score and the event information; s4, generating a resource scheduling scheme based on the resource demand, the resource availability and the scheduling constraint by adopting an optimization algorithm; and S5, sending the resource scheduling scheme to an execution unit to schedule emergency resources. According to the method, the hysteresis quality and subjectivity of manual decision making are overcome, resource scheduling is based on the basis, the response time from event occurrence to resource dispatching is greatly shortened through the automatic process, it is ensured that limited emergency resources are used for most needed places, and overall benefit maximization is achieved.

Description

Technical Field

[0001] This invention belongs to the field of emergency management technology, specifically relating to an emergency resource optimization scheduling method and system based on event priority assessment, which is particularly suitable for risk prevention and emergency early warning of urban critical infrastructure (such as water supply and gas supply systems) under extreme weather conditions. Background Technology

[0002] Currently, with the acceleration of urbanization and the frequent occurrence of extreme weather events, emergency management systems face challenges in integrating multi-source heterogeneous data, conducting dynamic risk assessments, and optimizing resource allocation. Traditional emergency resource allocation methods are often based on static rules or single indicators, lacking dynamic assessment of event priorities, leading to uneven resource allocation, response delays, and increased risks of secondary disasters. For example, in rainstorm disasters, existing technologies struggle to assess the risk of disaster chain evolution in real time, making precise resource allocation impossible. While some solutions employ priority assessment, they typically rely on simple rules or historical data, failing to consider the dynamic evolution of disaster chains and the fusion of multi-source data, resulting in low assessment accuracy and insufficient allocation efficiency. Therefore, there is an urgent need for an intelligent allocation method that integrates disaster chain analysis, dynamic trust assessment, and data fusion to improve the accuracy and timeliness of emergency responses. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide an emergency resource optimization scheduling method and system based on event priority assessment. Through dynamic priority assessment and multi-objective optimization, it achieves efficient scheduling of emergency resources, reduces disaster losses, and solves the technical problems mentioned in the background art.

[0004] The objective of this invention is achieved as follows: an emergency resource optimization and scheduling method based on event priority assessment, comprising the following steps: S1, acquiring information on multiple emergency events, wherein the event information includes at least one of event type, event location, and event severity; S2, prioritizing each emergency event based on a preset priority assessment model and outputting a priority score, wherein the priority assessment model is constructed based on historical disaster data and its evolution patterns; S3, analyzing the required emergency resources based on the priority score and the event information, wherein the emergency resources include resource type, resource quantity, and target resource location; S4, employing an optimization algorithm based on resource demand and resource availability... Based on usage and scheduling constraints, a resource scheduling scheme is generated, wherein the optimization algorithm is configured as a multi-objective optimization, and the optimization objective includes at least one of minimizing response time, minimizing scheduling cost, and maximizing resource coverage; S5, the resource scheduling scheme is sent to the execution unit to schedule emergency resources; S6, feedback data is collected, the scheduling execution status is monitored, and the priority evaluation model and resource scheduling scheme are dynamically adjusted based on the feedback data, wherein the feedback data includes at least one of resource deployment status, event processing progress, and user satisfaction; dynamic adjustment includes updating the priority evaluation model using a machine learning algorithm, wherein the machine learning algorithm is a reinforcement learning or deep learning model trained based on historical feedback data.

[0005] By constructing a logic for optimizing emergency resource allocation, the system transforms emergency resource allocation from a traditional static "first-come, first-served" model into a data-driven, intelligently evaluated, and dynamically optimized closed-loop process. By introducing a priority assessment model, the system can intelligently determine the urgency and importance of different emergency events, thus providing a scientific basis for the accurate and efficient allocation of subsequent resources. During implementation, the system collects basic information on sudden emergency events in real-time or near real-time through various data sources such as IoT sensors, reporting systems, and meteorological APIs, and inputs the collected event information into a pre-trained priority assessment model. The model calculates based on historical data and knowledge (such as disaster evolution patterns) and outputs a quantified priority score for each event. This score is the primary basis for resource allocation decisions. Based on the event's priority score and specific information (such as location and type), the system automatically matches and analyzes the types and quantities of resources required to complete the event's handling, as well as the target locations to be delivered. The scheduling optimization algorithm then begins to work, comprehensively considering the current resource demand, the distribution and status of all available resources, and various real-world constraints (such as travel time, cost, and traffic conditions). Through multi-objective optimization calculations, it generates one or more scheduling schemes with the highest overall benefits. The optimal scheduling scheme is automatically distributed to the corresponding execution units, such as the intelligent terminals of rescue teams, drone nests, or material dispatch centers, to initiate the actual resource scheduling process.

[0006] By elevating priority assessment from subjective, static judgment to a model-based, automated process, and linking event information acquisition, intelligent evaluation, resource analysis, optimized scheduling, and execution into a complete, automated closed loop, the overall efficiency of emergency response is significantly improved. This overcomes the lag and subjectivity of human decision-making, ensuring that resource allocation is based on evidence. The automated process greatly shortens the response time from event occurrence to resource deployment, ensuring that limited emergency resources are used where they are most needed, maximizing overall benefits.

[0007] Further, in step S2, the risk evolution law is obtained by analyzing the evolution paths and node relationships of historical disaster events to construct a disaster chain containing primary disasters, secondary disasters, and derivative disasters. This risk evolution law is obtained through complex network analysis, which includes calculating at least one network parameter among node degree, clustering coefficient, and betweenness centrality to identify key disaster nodes and key evolution paths. Through complex network analysis, disaster events are abstracted into network nodes, and the causal and derivative relationships between events are abstracted into edges, thereby quantifying the overall risk of the disaster network and identifying "key node" events that, once they occur, will trigger a series of serious consequences. When evaluating a specific event, the system analyzes the event's position in the disaster chain network and calculates its node network parameters (such as degree and betweenness centrality). A high betweenness centrality for an event indicates that it is a hub for multiple key evolution paths, and its priority score will be correspondingly increased. Applying disaster chain theory and complex network analysis methods to the priority assessment of emergency events not only assesses the events themselves, but also anticipates the secondary and derivative disasters they may trigger. This allows for the priority handling of key events that may cause a "domino effect," thus curbing the expansion of disasters at their source.

[0008] Furthermore, the priority evaluation model in step S2 includes a dynamic trust evaluation component. Dynamic trust evaluation is based on a comprehensive score derived from at least one of device status data, environmental factor data, and user behavior data, implemented through trusted computing. This includes generating a trusted report using a Trusted Platform Module (TPM) or a Trusted Cryptography Module (TCM). Dynamic trust evaluation also includes continuous verification based on a zero-trust architecture, where the identity, device status, and behavioral patterns of emergency equipment and users are monitored and scored in real time. During implementation, the system continuously collects device status data (such as whether the GPS signal is normal) and user operation behavior data (such as whether the login location is abnormal). Trusted reports are generated using trusted computing technology (such as TPM / TCM hardware security chips), and combined with a behavioral analysis model, a dynamic trust score is given to each entity. If the trust score of a data source is too low, the weight of its data in the priority evaluation will be reduced or it will be directly excluded to prevent malicious attacks or faulty equipment from misleading scheduling decisions. Integrating dynamic trust assessment and zero-trust architecture into the field of emergency management ensures the security of the dispatch system, safeguards the root of trust at the hardware level, enhances the immutability of the assessment, effectively defends against internal and external security threats, prevents dispatch errors caused by data contamination or malicious attacks, ensures that emergency response actions are based on trusted data and instructions, and guarantees the effectiveness of rescue operations and the safety of rescue personnel.

[0009] Furthermore, the emergency resources required for analysis in step S3 include the use of a data fusion strategy. This strategy, based on DS evidence theory, integrates multiple data sources, including at least two of meteorological data, geographic information data, real-time sensor data, and historical disaster data, to determine resource requirements. The data fusion strategy also includes privacy-preserving computation-based data processing, using at least one of homomorphic encryption, secure multi-party computation, or a Trusted Execution Environment (TEE) to ensure data privacy and security. Using DS evidence theory, a high-level mathematical tool for handling uncertain information, fuses data from different sources that may conflict or be incomplete, improving the quality of decision-making information. Simultaneously, privacy-preserving computation techniques are used to protect the privacy of the original data during the data fusion process. When analyzing resource requirements, the system acquires data from multiple sources, including meteorological bureaus, geographic information databases, and sensors. This data is first processed for privacy protection using techniques such as homomorphic encryption, and then, under encrypted conditions or in a secure computation environment, DS evidence theory is applied for fusion computation to arrive at a comprehensive and highly reliable judgment on resource requirements. This approach effectively protects the data privacy of different departments or institutions while fully leveraging the value of the data, promoting cross-departmental data collaboration and sharing. By integrating data from multiple sources, the uncertainty of a single data source is reduced, making resource demand analysis closer to reality.

[0010] Furthermore, the optimization algorithm in step S4 includes at least one of linear programming, genetic algorithm, or particle swarm optimization, and the optimization algorithm is configured to consider real-time constraints, including resource location, traffic conditions, and network conditions. The generated resource scheduling scheme simulates the effects of different scheduling strategies through simulation algorithms, and the simulation algorithms are based on discrete event simulation or Monte Carlo simulation. Mature mathematical programming or intelligent optimization algorithms (such as genetic algorithms) are used to search for optimal solutions under complex multi-constraint conditions. Simultaneously, simulation technology is introduced to perform a "sandbox simulation" of the generated scheme, predicting its performance in real complex environments. During implementation, the optimization algorithm (such as genetic algorithm) generates a preliminary optimization scheme. Subsequently, the discrete event simulation model simulates the driving and queuing processes of resource vehicles in a real traffic network, while the Monte Carlo simulation simulates the impact of various random events (such as sudden congestion on a road). Through simulation results, multiple schemes can be compared, and the most robust and reliable scheme can be selected. The solutions generated by the optimization algorithm are then verified and evaluated through simulation, forming a "optimization-simulation-feedback" cycle, which improves the feasibility and robustness of the solutions. Monte Carlo simulation can handle random factors in the real world very well, making the solutions more adaptable.

[0011] Further, the execution unit in step S5 includes a communication platform configured to send dispatch instructions to rescue equipment via at least one of wireless network, satellite communication, or Internet of Things (IoT) protocol, wherein the rescue equipment includes drones, robots, or mobile terminals. The communication platform also includes edge computing nodes configured to support local processing of dispatch instructions to reduce latency, wherein the edge computing nodes use lightweight cryptographic technology for secure communication. The emergency resources include at least one of human resources, material resources, or equipment resources, wherein material resources include medical supplies, rescue tools, or daily necessities, and equipment resources include vehicles, generators, or communication equipment. Utilizing modern communication technologies and edge computing architecture, the real-time and reliable transmission of instructions is ensured, and resources are finely categorized and managed. During implementation, after the optimized scheme is generated, the system sends out instructions through the most reliable communication link (such as satellite communication as a backup). To improve response speed, some computational tasks (such as the final generation and encryption of instructions) can be completed on edge computing nodes close to the execution unit. The edge nodes employ lightweight cryptographic technology to ensure secure communication and low latency. By clearly defining the communication platform's support for multiple communication protocols and edge computing nodes, and adapting to communication needs in complex emergency environments, the emergency resources were classified in detail and at multiple levels. This reflects the refinement of the solution management, ensures the timely and accurate delivery of dispatch instructions, and lays the foundation for precise resource procurement, storage, and dispatch management.

[0012] An emergency resource optimization and scheduling system based on event priority assessment, used to implement the above-mentioned method, includes: a data acquisition module for acquiring information on multiple emergency events, including event type, event location, and event severity; a priority assessment module for prioritizing emergency events based on a preset priority assessment model, wherein the priority assessment module integrates a disaster chain analysis component and a dynamic trust assessment component; a resource analysis module for analyzing the required emergency resources based on the priority scores; a scheduling optimization module for generating resource scheduling schemes using optimization algorithms; and an execution communication module for sending the scheduling schemes to the execution unit.

[0013] An electronic device includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the method described above.

[0014] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0015] The beneficial effects of this invention are as follows: By constructing a logic for optimizing the scheduling of emergency resources, the system transforms emergency resource scheduling from a traditional static "first-come, first-served" model into a data-driven, intelligently evaluated, and dynamically optimized closed-loop process. By introducing a priority evaluation model, the system can intelligently determine the urgency and importance of different emergency events, thus providing a scientific basis for the accurate and efficient scheduling of subsequent resources. During implementation, the system collects basic information on sudden emergency events in real-time or near real-time through various data sources such as IoT sensors, reporting systems, and meteorological APIs, and inputs the collected event information into a pre-trained priority evaluation model. The model calculates based on historical data and knowledge (such as disaster evolution patterns) and outputs a quantified priority score for each event. This score is the primary basis for resource allocation decisions. Based on the event's priority score and specific information (such as location and type), the system automatically matches and analyzes the types and quantities of resources required to complete the event's handling, as well as the target locations to be delivered. The scheduling optimization algorithm then begins to work, comprehensively considering the current resource demand, the distribution and status of all available resources, and various real-world constraints (such as travel time, cost, and traffic conditions). Through multi-objective optimization calculations, it generates one or more scheduling schemes with the highest overall benefits. The optimal scheduling scheme is automatically distributed to the corresponding execution units, such as the intelligent terminals of rescue teams, drone nests, or material dispatch centers, to initiate the actual resource scheduling process.

[0016] By collecting execution feedback data and dynamically adjusting model parameters using machine learning algorithms, the system can adapt to constantly changing environments and event patterns. During resource scheduling execution, the system continuously collects feedback data (such as resource arrival time and event handling progress). This data is used to periodically retrain the priority evaluation model (e.g., using reinforcement learning algorithms), enabling the model to learn new disaster evolution patterns or the effectiveness of scheduling strategies, thus continuously improving in future decisions. It can adapt to new emergencies or environmental changes, maintain the effectiveness of decision-making, and its performance continuously improves over time, becoming increasingly intelligent. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the method flow of the present invention; Figure 2 This is a schematic diagram of the system modules of the present invention. Detailed Implementation

[0018] The present invention will now be described in further detail with reference to the accompanying drawings. It should be noted that this is only for the purpose of more clearly illustrating and explaining the present invention. Example 1

[0019] like Figure 1 and 2 As shown, this embodiment discloses an emergency resource optimization and scheduling method based on event priority assessment, including the following steps: S1, acquiring information on multiple emergency events, wherein the event information includes at least one of event type, event location, and event severity; S2, prioritizing each emergency event based on a preset priority assessment model and outputting a priority score, wherein the priority assessment model is constructed based on historical disaster data and its evolution patterns; S3, analyzing the required emergency resources based on the priority score and the event information, wherein the emergency resources include resource type, resource quantity, and target resource location; S4, employing an optimization algorithm based on resource demand and resource availability. S5. Given scheduling constraints, generate a resource scheduling scheme, wherein the optimization algorithm is configured as multi-objective optimization, and the optimization objective includes at least one of minimizing response time, minimizing scheduling cost, and maximizing resource coverage; S6. Send the resource scheduling scheme to the execution unit to schedule emergency resources; S7. Collect feedback data, monitor the scheduling execution status, and dynamically adjust the priority evaluation model and resource scheduling scheme based on the feedback data, wherein the feedback data includes at least one of resource deployment status, event processing progress, and user satisfaction; dynamic adjustment includes updating the priority evaluation model using a machine learning algorithm, wherein the machine learning algorithm is a reinforcement learning or deep learning model trained based on historical feedback data.

[0020] By constructing a logic for optimizing emergency resource allocation, the system transforms emergency resource allocation from a traditional static "first-come, first-served" model into a data-driven, intelligently evaluated, and dynamically optimized closed-loop process. By introducing a priority assessment model, the system can intelligently determine the urgency and importance of different emergency events, thus providing a scientific basis for the accurate and efficient allocation of subsequent resources. During implementation, the system collects basic information on sudden emergency events in real-time or near real-time through various data sources such as IoT sensors, reporting systems, and meteorological APIs, and inputs the collected event information into a pre-trained priority assessment model. The model calculates based on historical data and knowledge (such as disaster evolution patterns) and outputs a quantified priority score for each event. This score is the primary basis for resource allocation decisions. Based on the event's priority score and specific information (such as location and type), the system automatically matches and analyzes the types and quantities of resources required to complete the event's handling, as well as the target locations to be delivered. The scheduling optimization algorithm then begins to work, comprehensively considering the current resource demand, the distribution and status of all available resources, and various real-world constraints (such as travel time, cost, and traffic conditions). Through multi-objective optimization calculations, it generates one or more scheduling schemes with the highest overall benefits. The optimal scheduling scheme is automatically distributed to the corresponding execution units, such as the intelligent terminals of rescue teams, drone nests, or material dispatch centers, to initiate the actual resource scheduling process.

[0021] By elevating priority assessment from subjective, static judgment to a model-based, automated process, and linking event information acquisition, intelligent evaluation, resource analysis, optimized scheduling, and execution into a complete, automated closed loop, the overall efficiency of emergency response is significantly improved. This overcomes the lag and subjectivity of human decision-making, ensuring that resource allocation is based on evidence. The automated process greatly shortens the response time from event occurrence to resource deployment, ensuring that limited emergency resources are used where they are most needed, maximizing overall benefits. Example 2

[0022] like Figure 1 and 2As shown, this embodiment discloses an emergency resource optimization and scheduling method based on event priority assessment, including the following steps: S1, acquiring information on multiple emergency events, wherein the event information includes at least one of event type, event location, and event severity; S2, prioritizing each emergency event based on a preset priority assessment model and outputting a priority score, wherein the priority assessment model is constructed based on historical disaster data and its evolution patterns; S3, analyzing the required emergency resources based on the priority score and the event information, wherein the emergency resources include resource type, resource quantity, and target resource location; S4, employing an optimization algorithm based on resource demand and resource availability. The system generates a resource scheduling scheme based on scheduling constraints. The optimization algorithm is configured as a multi-objective optimization, with optimization objectives including at least one of minimizing response time, minimizing scheduling cost, and maximizing resource coverage. Step S5 involves sending the resource scheduling scheme to the execution unit to schedule emergency resources. Step S6 involves collecting feedback data, monitoring scheduling execution, and dynamically adjusting the priority evaluation model and resource scheduling scheme based on the feedback data. Feedback data includes at least one of resource deployment status, event processing progress, and user satisfaction. Dynamic adjustment includes updating the priority evaluation model using machine learning algorithms, specifically reinforcement learning or deep learning models trained on historical feedback data. By constructing the logic for optimizing emergency resource scheduling, the system transforms emergency resource scheduling from a traditional static "first-come, first-served" rule model into a data-driven, intelligently evaluated, and dynamically optimized closed-loop process. By introducing a priority evaluation model, the system can intelligently determine the urgency and importance of different emergency events, thus providing a scientific basis for the accurate and efficient scheduling of subsequent resources. During implementation, the system collects basic information about sudden emergency events in real-time or near real-time through various data sources such as IoT sensors, reporting systems, and meteorological APIs, and inputs the collected event information into the pre-trained priority evaluation model. The model calculates based on historical data and knowledge (such as disaster evolution patterns) and outputs a quantified priority score for each event. This score is the primary basis for resource allocation decisions. Based on the event's priority score and specific information (such as location and type), the system automatically matches and analyzes the types and quantities of resources required to complete the event's handling, as well as the target locations to be delivered. The scheduling optimization algorithm then begins to work, comprehensively considering the current resource demand, the distribution and status of all available resources, and various real-world constraints (such as travel time, cost, and traffic conditions). Through multi-objective optimization calculations, it generates one or more scheduling schemes with the highest overall benefits. The optimal scheduling scheme is automatically distributed to the corresponding execution units, such as the intelligent terminals of rescue teams, drone nests, or material dispatch centers, to initiate the actual resource scheduling process.

[0023] For better results, in step S2, the risk evolution law is obtained by analyzing the evolution paths and node relationships of historical disaster events to construct a disaster chain containing primary, secondary, and derivative disasters. Furthermore, the risk evolution law is obtained through complex network analysis, which includes calculating at least one network parameter among node degree, clustering coefficient, and betweenness centrality to identify key disaster nodes and key evolution paths. Through complex network analysis, disaster events are abstracted into network nodes, and the causal and derivative relationships between events are abstracted into edges, thereby quantifying the overall risk of the disaster network and identifying "key node" events that, once they occur, will trigger a series of serious consequences. When evaluating a specific event, the system analyzes the event's position in the disaster chain network and calculates its node network parameters (such as degree and betweenness centrality). A high betweenness centrality for an event indicates that it is a hub for multiple key evolution paths, and its priority score will be correspondingly increased. Applying disaster chain theory and complex network analysis methods to the priority assessment of emergency events not only assesses the events themselves, but also anticipates the secondary and derivative disasters they may trigger. This allows for the priority handling of key events that may cause a "domino effect," thus curbing the expansion of disasters at their source.

[0024] For better results, the priority evaluation model in step S2 includes a dynamic trust evaluation component. Dynamic trust evaluation is based on a comprehensive score derived from at least one of device status data, environmental factor data, and user behavior data, implemented through trusted computing. This includes generating a trusted report using a Trusted Platform Module (TPM) or a Trusted Cryptography Module (TCM). Furthermore, dynamic trust evaluation also includes continuous verification based on a zero-trust architecture, where the identity, device status, and behavioral patterns of emergency equipment and users are monitored and scored in real time. During implementation, the system continuously collects device status data (such as whether GPS signals are normal) and user operation behavior data (such as whether login locations are abnormal). Trusted reports are generated using trusted computing technology (such as TPM / TCM hardware security chips), and combined with a behavioral analysis model, a dynamic trust score is given to each entity. If the trust score of a data source is too low, the weight of its data in the priority evaluation will be reduced or it will be directly excluded to prevent malicious attacks or faulty equipment from misleading scheduling decisions. Integrating dynamic trust assessment and zero-trust architecture into the field of emergency management ensures the security of the dispatch system, safeguards the root of trust at the hardware level, enhances the immutability of the assessment, effectively defends against internal and external security threats, prevents dispatch errors caused by data contamination or malicious attacks, ensures that emergency response actions are based on trusted data and instructions, and guarantees the effectiveness of rescue operations and the safety of rescue personnel.

[0025] To achieve better results, the emergency resource analysis in step S3 includes the use of a data fusion strategy. This strategy, based on DS evidence theory, integrates at least two of multiple data sources, including meteorological data, geographic information data, real-time sensor data, and historical disaster data, to determine resource requirements. The data fusion strategy also includes privacy-preserving computation-based data processing, using at least one of homomorphic encryption, secure multi-party computation, or a Trusted Execution Environment (TEE) to ensure data privacy and security. DS evidence theory, a high-level mathematical tool for handling uncertain information, is used to fuse data from different sources that may be conflicting or incomplete, improving the quality of decision-making information. Simultaneously, privacy-preserving computation techniques are used to protect the privacy of the original data during the data fusion process. When analyzing resource requirements, the system acquires data from multiple sources, including meteorological bureaus, geographic information databases, and sensors. This data is first processed for privacy protection using techniques such as homomorphic encryption, and then, under encrypted conditions or in a secure computation environment, DS evidence theory is applied for fusion computation to arrive at a comprehensive and highly reliable judgment on resource requirements. This approach effectively protects the data privacy of different departments or institutions while fully leveraging the value of the data, promoting cross-departmental data collaboration and sharing. By integrating data from multiple sources, the uncertainty of a single data source is reduced, making resource demand analysis closer to reality.

[0026] For better results, the optimization algorithm in step S4 includes at least one of linear programming, genetic algorithm, or particle swarm optimization, and the optimization algorithm is configured to consider real-time constraints, including resource location, traffic conditions, and network conditions. The generated resource scheduling scheme simulates the effects of different scheduling strategies through simulation algorithms, and the simulation algorithms are based on discrete event simulation or Monte Carlo simulation. Mature mathematical programming or intelligent optimization algorithms (such as genetic algorithms) are used to search for optimal solutions under complex multi-constraint conditions. At the same time, simulation technology is introduced to "scenario-test" the generated scheme and predict its performance in real complex environments. During implementation, the optimization algorithm (such as genetic algorithm) generates an initial optimization scheme. Subsequently, the discrete event simulation model simulates the driving and queuing processes of resource vehicles in the real traffic network, while the Monte Carlo simulation simulates the impact of various random events (such as sudden congestion on a road). Through simulation results, multiple schemes can be compared, and the most robust and reliable scheme can be selected. The solutions generated by the optimization algorithm are then verified and evaluated through simulation, forming a "optimization-simulation-feedback" cycle, which improves the feasibility and robustness of the solutions. Monte Carlo simulation can handle random factors in the real world very well, making the solutions more adaptable.

[0027] For better results, the execution unit in step S5 includes a communication platform configured to send dispatch instructions to rescue equipment via at least one of wireless network, satellite communication, or Internet of Things (IoT) protocols. The rescue equipment includes drones, robots, or mobile terminals. The communication platform also includes edge computing nodes configured to support local processing of dispatch instructions to reduce latency. These edge computing nodes use lightweight cryptographic technology for secure communication. The emergency resources include at least one of human resources, material resources, or equipment resources. Material resources include medical supplies, rescue tools, or daily necessities, while equipment resources include vehicles, generators, or communication equipment. Utilizing modern communication technologies and edge computing architecture ensures the real-time performance and reliability of instruction transmission and allows for refined resource classification and management. During implementation, after the optimized scheme is generated, the system sends out instructions via the most reliable communication link (such as satellite communication as a backup). To improve response speed, some computational tasks (such as the final generation and encryption of instructions) can be completed on edge computing nodes located close to the execution unit. The edge nodes employ lightweight cryptographic technology to ensure secure and low-latency communication. By clearly defining the communication platform's support for multiple communication protocols and edge computing nodes, and adapting to communication needs in complex emergency environments, the emergency resources were classified in detail and at multiple levels. This reflects the refinement of the solution management, ensures the timely and accurate delivery of dispatch instructions, and lays the foundation for precise resource procurement, storage, and dispatch management.

[0028] An emergency resource optimization and scheduling system based on event priority assessment, used to implement the above-mentioned method, includes: a data acquisition module for acquiring information on multiple emergency events, including event type, event location, and event severity; a priority assessment module for prioritizing emergency events based on a preset priority assessment model, wherein the priority assessment module integrates a disaster chain analysis component and a dynamic trust assessment component; a resource analysis module for analyzing the required emergency resources based on the priority scores; a scheduling optimization module for generating resource scheduling schemes using optimization algorithms; and an execution communication module for sending the scheduling schemes to the execution unit.

[0029] An electronic device includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the method described above.

[0030] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0031] In practice, let's take urban water supply systems under extreme rainfall as an example: The system is deployed in a cloud-edge collaborative environment: Data acquisition module: Deployed on the front-end server, integrating IoT sensors and API interfaces to collect data in real time.

[0032] Priority evaluation module: Deployed on the backend server, it runs Python algorithms and calls complex network libraries (such as NetworkX) and the Trusted Computing SDK.

[0033] Scheduling optimization module: Deployed on edge nodes, it uses C++ to implement optimization algorithms and supports low-latency computing.

[0034] The communication module communicates with external devices via a RESTful API and supports the MQTT protocol for IoT devices.

[0035] Deployment architecture: The front-end uses Vue.js, the back-end uses Spring Boot, the database uses MySQL, and the cache uses Redis. The system supports distributed deployment, such as deploying edge nodes in the Beijing demonstration park to process local data.

[0036] The electronic equipment is an industrial-grade server, with the following configuration: Processor: Intel Xeon 8-core CPU. Memory: 32GB RAM, 1TB SSD. Communication Interfaces: Gigabit Ethernet, 5G module.

[0037] Storage medium implementation methods: The computer-readable storage medium, such as DVD-ROM or cloud storage, stores Java or Python code that, when read by the device, implements the method steps. The code includes: a data acquisition class: processing sensor data; an evaluation class: implementing a priority evaluation model; an optimization class: running a genetic algorithm; and a communication class: sending scheduling instructions.

[0038] 1. Data Acquisition: Real-time rainfall data, pipeline pressure data, and historical disaster data are acquired through sensors and APIs. For example, an event is triggered when rainfall exceeds 50 mm / h.

[0039] 2. Priority Assessment: Using a priority assessment model based on disaster chain analysis, a disaster chain network of the water supply system is constructed to identify key nodes (such as pipeline rupture and pump station damage). Parameters such as node degree and betweenness centrality are calculated through complex network analysis.

[0040] Dynamic Trust Assessment: Collects equipment status (such as pump station operation status), environmental factors (such as water depth), and user behavior data, generates a trust report through the Trusted Computing Module (TPM / TCM), and outputs a comprehensive priority score.

[0041] The model outputs a score ranging from 0 to 1, with higher scores indicating higher priority.

[0042] 3. Resource Analysis: Based on the score, determine the resources that need to be dispatched, such as water pumps, rescue teams, and maintenance equipment, and calculate the required quantities and target locations.

[0043] 4. Scheduling Optimization: A genetic algorithm is used for multi-objective optimization. The objective functions include minimizing response time (≤1s), minimizing cost, and maximizing coverage. The optimization results generate a scheduling scheme.

[0044] 5. Execution: The plan is sent to drones and mobile terminals via 5G network to carry out rescue missions.

[0045] In extreme rainfall events, the system successfully reduced response time to within one second, improved resource scheduling accuracy by 30%, and effectively reduced water supply system failures and secondary disasters. By elevating priority assessment from subjective, static judgment to a model-based, automated process, the system integrates event information acquisition, intelligent assessment, resource analysis, optimized scheduling, and execution into a complete, automated closed loop, significantly improving the overall efficiency of emergency response. It overcomes the lag and subjectivity of human decision-making, making resource scheduling data-driven. The automated process greatly shortens the response time from event occurrence to resource deployment, ensuring that limited emergency resources are used where they are most needed, maximizing overall benefits. This invention can be widely applied in smart cities, emergency management, and critical infrastructure protection.

[0046] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An emergency resource optimization scheduling method based on event priority assessment, characterized in that, Includes the following steps: S1. Obtain information on multiple emergency events, wherein the event information includes at least one of event type, event location, and event severity; S2. Based on the preset priority assessment model, prioritize each emergency event and output a priority score. The priority assessment model is constructed based on historical disaster data and its evolution. S3. Analyze the required emergency resources based on the priority score and the event information, wherein the emergency resources include resource type, resource quantity and resource target location; S4. Using an optimization algorithm, a resource scheduling scheme is generated based on resource demand, resource availability, and scheduling constraints. The optimization algorithm is configured as a multi-objective optimization, and the optimization objective includes at least one of minimizing response time, minimizing scheduling cost, and maximizing resource coverage. S5. Send the resource scheduling plan to the execution unit to schedule emergency resources.

2. The emergency resource optimization and scheduling method based on event priority assessment according to claim 1, characterized in that, In step S2, the risk evolution law is obtained by analyzing the evolution path and node relationship of historical disaster events to construct a disaster chain containing a chain relationship of primary disasters, secondary disasters and derivative disasters; and the risk evolution law is obtained through complex network analysis, which includes calculating at least one network parameter among node degree, clustering coefficient and betweenness centrality to identify key disaster nodes and key evolution paths.

3. The emergency resource optimization and scheduling method based on event priority assessment according to claim 1, characterized in that, The priority assessment model in step S2 includes a dynamic trust assessment component. The dynamic trust assessment is based on a comprehensive score of at least one of device status data, environmental factor data, and user behavior data, and is implemented through trusted computing, including generating a trusted report using a Trusted Platform Module (TPM) or a Trusted Cryptography Module (TCM). The dynamic trust assessment also includes continuous verification based on a zero-trust architecture, in which the identity, device status, and behavior patterns of emergency devices and users are monitored and scored in real time.

4. The emergency resource optimization and scheduling method based on event priority assessment according to claim 1, characterized in that, The emergency resources required for analysis in step S3 include the use of a data fusion strategy, which is DS evidence theory fusion, to integrate multiple data sources, including at least two of meteorological data, geographic information data, real-time sensor data, and historical disaster data, to determine resource requirements; and the data fusion strategy includes privacy-based computation-based data processing, using at least one of homomorphic encryption, secure multi-party computation, or trusted execution environment (TEE) to ensure data privacy and security.

5. The emergency resource optimization and scheduling method based on event priority assessment according to claim 1, characterized in that, The optimization algorithm in step S4 includes at least one of linear programming, genetic algorithm or particle swarm optimization, and the optimization algorithm is configured to consider real-time constraints, including resource location, traffic conditions and network conditions; the generated resource scheduling scheme simulates the effects of different scheduling strategies through simulation algorithms, and the simulation algorithms are based on discrete event simulation or Monte Carlo simulation.

6. The emergency resource optimization and scheduling method based on event priority assessment according to claim 1, characterized in that, The execution unit in step S5 includes a communication platform configured to send dispatch instructions to rescue equipment via at least one of wireless network, satellite communication, or Internet of Things (IoT) protocol, wherein the rescue equipment includes drones, robots, or mobile terminals; the communication platform also includes a configuration to support edge computing nodes for processing dispatch instructions locally to reduce latency, wherein the edge computing nodes perform secure communication based on lightweight cryptographic technology; The emergency resources include at least one of human resources, material resources, or equipment resources, wherein material resources include medical supplies, rescue tools, or daily necessities, and equipment resources include vehicles, generators, or communication equipment.

7. The emergency resource optimization and scheduling method based on event priority assessment according to claim 1, characterized in that, Also includes: S6. Collect feedback data, monitor scheduling execution, and dynamically adjust the priority evaluation model and resource scheduling scheme based on the feedback data. The feedback data includes at least one of resource deployment status, event processing progress, and user satisfaction. Dynamic adjustment includes updating the priority evaluation model using machine learning algorithms, where the machine learning algorithm is a reinforcement learning or deep learning model trained based on historical feedback data.

8. An emergency resource optimization and scheduling system based on event priority assessment, used to implement the method as described in any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire information on multiple emergency events, including event type, event location, and event severity. The priority assessment module is used to score the priority of emergency events based on a preset priority assessment model. The priority assessment module integrates a disaster chain analysis component and a dynamic trust assessment component. The resource analysis module is used to analyze the required emergency resources based on priority scoring; The scheduling optimization module is used to generate resource scheduling schemes using optimization algorithms. The execution communication module is used to send the scheduling plan to the execution unit.

9. An electronic device comprising a processor and a memory, the memory storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images