An urban emergency management simulation method and device, an electronic device, and a storage medium

Abstract

The application discloses a kind of city emergency management simulation method, device, electronic equipment and storage medium.The present application includes: obtaining the emergency knowledge and emergency data corresponding to emergency task;According to the emergency knowledge and the emergency data determine emergency role;The nested execution pair of the emergency role is constructed;According to the nested execution pair, the system requirement of the emergency role is extracted, and the emergency system analysis template is generated according to the system requirement;Task decomposition is carried out on the emergency task using the emergency system analysis template, and the task decomposition result is obtained;Interactive logic modeling is carried out using the task decomposition result, and the logic flow is formed;The logic flow is used to generate Agent execution graph;Executable simulation model of the Agent execution graph is generated, and the executable simulation model is combined with cloud simulation model.

Description

Technical Field

[0001] This invention relates to the field of emergency management technology, and in particular to a method, device, electronic equipment and storage medium for urban emergency management simulation. Background Technology

[0002] In modern society, urban emergency response faces numerous challenges. Real-world emergency drills and simulations are often costly, risky, and difficult to organize and implement. Traditional map-based operations and sand table exercises struggle to accurately capture the details of emergency actions; relying solely on mathematical analysis is insufficient to comprehensively describe the intelligent behavior of emergency systems and their components. While human-in-the-loop and device-in-the-loop simulations can achieve emergency simulations for single devices and small teams, the complex model systems make it difficult to extend to higher-level urban emergency response simulations. Computer simulation utilizes computers and specialized equipment to simulate real-world emergency response processes through simulation models. In actual emergency response, various emergency activities can be represented by specific models. By studying these models, computer simulation, as a means of emergency response simulation, can reveal the fundamental laws governing emergency response processes. In the information age, computer emergency simulation, as a fundamental method for studying emergency issues, has become a core approach to assessing emergency response capabilities and is receiving increasing attention.

[0003] However, computer simulation is currently not used in urban emergency response. This is because real-world factors are numerous and complex, making it difficult for general simulation models to fully describe them. Each city has unique characteristics in terms of geography, population density, infrastructure, and climate, and existing simulation models lack sufficient adaptability, making it difficult to effectively adjust and apply them to specific urban characteristics. The unique features of each city make it difficult to directly apply simulation models. Furthermore, urban emergency response requires real-time data support, such as traffic flow, weather conditions, and the status of public resources. However, current simulation models struggle to integrate and process this dynamic data in real time, affecting the accuracy and practicality of the simulations. Urban emergency response involves collaboration among multiple departments, such as fire services, medical services, and traffic management. Existing simulation systems struggle to effectively simulate and coordinate the interactions between these departments, limiting the credibility and application effectiveness of the simulation results. Currently, there is a lack of stable and reliable methods for simulating urban emergency response that can accurately describe and comprehensively reflect urban emergency response. Summary of the Invention

[0004] This invention provides a method, device, electronic device, and storage medium for urban emergency management simulation, which addresses the technical problem that existing simulation systems are unable to effectively simulate and coordinate interactions between various departments, thus limiting the credibility and application effectiveness of simulation results.

[0005] This invention provides a simulation method for urban emergency management, comprising:

[0006] Acquire emergency knowledge and data corresponding to emergency tasks;

[0007] Emergency roles are determined based on the aforementioned emergency knowledge and emergency data;

[0008] Construct nested execution pairs for the aforementioned emergency roles;

[0009] Based on the nested execution, extract the system requirements of the emergency role, and generate an emergency system analysis template based on the system requirements;

[0010] The emergency task is decomposed using the aforementioned emergency system analysis template to obtain the task decomposition results.

[0011] The task decomposition results are used to model the interaction logic and form a logical flow.

[0012] The Agent execution graph is generated using the aforementioned logical flow;

[0013] Generate an executable simulation model of the Agent execution graph, and combine the executable simulation model with the cloud simulation model.

[0014] Optionally, the step of determining the emergency role based on the emergency knowledge and the emergency data includes:

[0015] The emergency knowledge and emergency data are analyzed using natural language processing algorithms to obtain the analyzed data;

[0016] The parsed data is then converted into structured data;

[0017] Cluster analysis was performed on the structured data, and the emergency response roles corresponding to each cluster result were determined.

[0018] Optionally, the emergency knowledge includes emergency command logic, emergency command rules, and emergency response experience; the emergency data includes historical emergency data, constraint rule data, and emergency simulation data.

[0019] Optionally, the step of extracting system requirements for the emergency role based on the nested execution and generating an emergency system analysis template based on the system requirements includes:

[0020] Based on the interaction relationships between the emergency roles in the nested execution pair, extract the system requirements of each emergency role;

[0021] Obtain the task breakdown information corresponding to the emergency task;

[0022] An emergency system analysis template is generated using the emergency roles, system requirements, and task breakdown information.

[0023] Optionally, the step of using the emergency system analysis template to decompose the emergency task and obtain the task decomposition result includes:

[0024] The emergency task is spatially decomposed using the task decomposition information to obtain the regional scheduling decomposition result;

[0025] The emergency task is decomposed in the time domain using the task decomposition information to obtain the time scheduling task decomposition result.

[0026] Optionally, the step of using the task decomposition results to model the interaction logic and form a logical flow includes:

[0027] The emergency entities are determined based on the task decomposition results;

[0028] Determine the interaction relationships between various emergency entities;

[0029] Based on the interaction relationships, interaction logic modeling is performed to form a logical flow.

[0030] Optionally, the step of generating the Agent execution graph using the logical flow includes:

[0031] The aforementioned logical flow is used to obtain the action and interaction information of each emergency response role;

[0032] The aforementioned action and interaction information is used to generate a single-agent execution graph for each emergency role;

[0033] A multi-agent execution graph is generated by using the action and interaction information of multiple emergency roles.

[0034] The present invention also provides an urban emergency management simulation device, comprising:

[0035] The emergency knowledge and emergency data acquisition module is used to acquire emergency knowledge and emergency data corresponding to emergency tasks.

[0036] An emergency role determination module is used to determine emergency roles based on the emergency knowledge and the emergency data.

[0037] Nested execution pair building module, used to construct the nested execution pairs of the emergency roles;

[0038] An emergency system analysis template generation module is used to extract the system requirements of the emergency role based on the nested execution, and generate an emergency system analysis template based on the system requirements;

[0039] The task decomposition module is used to decompose the emergency task using the emergency system analysis template to obtain the task decomposition result.

[0040] The logic flow generation module is used to model the interactive logic using the task decomposition results to form a logic flow.

[0041] The Agent execution graph generation module is used to generate an Agent execution graph using the aforementioned logical flow.

[0042] The module is used to generate an executable simulation model of the Agent execution graph and combine the executable simulation model with the cloud simulation model.

[0043] The present invention also provides an electronic device, the device comprising a processor and a memory:

[0044] The memory is used to store program code and transmit the program code to the processor;

[0045] The processor is used to execute the urban emergency management simulation method as described above, according to the instructions in the program code.

[0046] The present invention also provides a computer-readable storage medium for storing program code for executing the urban emergency management simulation method as described in any of the preceding claims.

[0047] As can be seen from the above technical solutions, the present invention has the following advantages: Firstly, by proposing emergency roles and nested execution pairs to construct an emergency system, the present invention can accurately identify and define key roles and behaviors in emergency scenarios, improving the accuracy and adaptability of the emergency system model, enabling it to better reflect the complex situations and role interactions in actual emergency handling; secondly, based on the extraction of system requirements from nested execution pairs and the generation of emergency system analysis templates, it helps to systematically and structurally analyze emergency requirements, ensuring the comprehensiveness and accuracy of emergency system requirements, and increasing the planning and design capabilities of the emergency simulation system; finally, by decomposing emergency tasks, it can refine and clarify each task. The system defines the specific content and execution sequence of emergency tasks, improving their operability and efficiency. Next, based on the task decomposition results, interactive logic modeling is performed to form a logical flow. An Agent execution diagram is then generated based on this flow, visually displaying the execution process and interaction relationships of each Agent. This enhances the model's visualization and usability, facilitating model verification and optimization. Finally, the Agent is compiled into an executable simulation model, dynamically combined with a cloud-based simulation model, enabling automated generation and deployment of the simulation model. This strengthens the system's flexibility and scalability, improves the development efficiency and performance of the simulation model, and allows for faster response to actual emergency needs. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating the steps of an urban emergency management simulation method provided in this embodiment of the invention;

[0050] Figure 2 This is a structural block diagram of an urban emergency management simulation device provided in an embodiment of the present invention. Detailed Implementation

[0051] This invention provides a method, device, electronic device, and storage medium for urban emergency management simulation, which addresses the technical problem that existing simulation systems are unable to effectively simulate and coordinate interactions between various departments, thus limiting the credibility and application effectiveness of simulation results.

[0052] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0053] Please see Figure 1 , Figure 1 A flowchart illustrating the steps of an urban emergency management simulation method provided in this embodiment of the invention.

[0054] The present invention provides a simulation method for urban emergency management, which may specifically include the following steps:

[0055] Step 101: Obtain emergency knowledge and data corresponding to the emergency task;

[0056] In this embodiment of the invention, emergency knowledge and emergency data can be extracted from an emergency management database. Emergency knowledge may include emergency command logic, emergency command rules, and emergency response experience; emergency data may include historical emergency data, constraint rule data, and emergency simulation data.

[0057] Step 102: Determine emergency roles based on emergency knowledge and data;

[0058] After acquiring emergency knowledge and data, emergency roles can be determined based on this knowledge and data.

[0059] In one example, step 102 may include the following sub-steps:

[0060] S21, uses natural language processing algorithms to parse emergency knowledge and emergency data to obtain parsed data;

[0061] S22, convert the parsed data into structured data;

[0062] S23, perform cluster analysis on the structured data and determine the emergency response role corresponding to each cluster result.

[0063] In practical implementation, Natural Language Processing (NLP) algorithms can be used to automatically parse emergency knowledge (such as fire suppression strategies, emergency command rules, and emergency response experience) and transform it into structured data. Based on machine learning models, historical emergency data is clustered to automatically identify and define emergency roles. Taking fire suppression events as an example, clustering analysis algorithms are used to automatically define the roles of fire brigades, medical teams, and traffic management departments based on historical data.

[0064] Step 103: Construct nested execution pairs for emergency roles;

[0065] In this embodiment of the invention, the nested execution of emergency roles includes the emergency role and its corresponding responsibilities. For example:

[0066] Emergency roles: Fire department, responsible for firefighting; Medical team, responsible for treating the injured; Traffic management department, responsible for traffic control.

[0067] Step 104: Extract the system requirements for emergency roles based on nested execution, and generate an emergency system analysis template based on the system requirements;

[0068] After obtaining the nested execution pairs, the system requirements of emergency roles can be extracted based on the nested execution pairs, and an emergency system analysis template can be generated based on the system requirements.

[0069] In one example, step 104 may include the following sub-steps:

[0070] S41, extract the system requirements of each emergency role based on the interaction relationship between each emergency role in the nested execution pair;

[0071] S42, Obtain task breakdown information corresponding to the emergency task;

[0072] S43 uses emergency roles, system requirements, and task breakdown information to generate an emergency system analysis template.

[0073] In this embodiment of the invention, the role relationships and interaction logic within nested execution pairs can be analyzed to extract the specific needs of each role, such as fire truck dispatching needs, medical resource allocation needs, and traffic management needs. Then, an emergency system analysis template containing task decomposition information and the information required for interaction logic modeling is generated.

[0074] In practice, data mining techniques can be used to extract system requirements from emergency roles and nested execution pairs, and then deep learning algorithms can be applied to predict and optimize the requirement data to generate an emergency system analysis template.

[0075] Step 105: Use the emergency system analysis template to decompose the emergency tasks and obtain the task decomposition results;

[0076] In this embodiment of the invention, the emergency task is decomposed, which can refine and clarify the specific content and execution order of each emergency task, thereby improving the operability and execution efficiency of the emergency task.

[0077] In one example, step 105 may include the following sub-steps:

[0078] S51, use task decomposition information to perform spatial domain task decomposition on emergency tasks to obtain regional scheduling decomposition results;

[0079] S52 uses task decomposition information to perform time-domain task decomposition on emergency tasks, and obtains time-scheduled task decomposition results.

[0080] In practical implementation, task decomposition can include spatial domain task decomposition and temporal domain task decomposition. Spatial domain task decomposition can be based on strategic game theory methods to ensure the integrity of tasks in each region. Temporal domain task decomposition is based on a task hierarchy network to ensure the timeliness and priority of tasks. Finally, the results of spatial and temporal domain task decomposition are integrated to form a complete task decomposition result.

[0081] In another embodiment, optimization algorithms such as genetic algorithms and ant colony algorithms can also be used to decompose tasks in the spatial and temporal domains to ensure the completeness and timeliness of the tasks.

[0082] Step 106: Use the task decomposition results to model the interaction logic and form a logical flow;

[0083] In this embodiment of the invention, the task decomposition results can be used to model the interaction logic to establish the interaction relationship between each emergency role and form a logical flow, which can be used to generate the Agent execution graph conceptual model in the future to ensure the effectiveness of the interaction between each emergency role.

[0084] In one example, step 106 may include the following sub-steps:

[0085] S61, Determine emergency entities based on task decomposition results;

[0086] S62, determine the interaction relationships between various emergency entities;

[0087] S63, model the interaction logic based on the interaction relationship to form a logical flow.

[0088] In practical implementation, key variables and relationships in task execution can be identified based on statistical analysis. Then, Bayesian networks and Markov Decision Processes (MDPs) can be applied. Based on the key variables and relationships, a distributed computing platform can be used to model the interaction logic of large-scale emergency entities. Finally, based on a custom symbol rule system, a semantic representation can be constructed to form the logical flow of emergency event management.

[0089] Step 107: Generate the Agent execution graph using a logical flow;

[0090] After obtaining the logical flow, an Agent execution graph can be generated from the logical flow. This Agent execution graph includes single-Agent execution graphs and multi-Agent execution graphs. Specific steps may include:

[0091] S71 uses a logical flow to obtain the action and interaction information of each emergency role;

[0092] S72 uses action and interaction information to generate single-agent execution diagrams for each emergency role;

[0093] S73 uses the action and interaction information of multiple emergency roles to generate a multi-agent execution graph.

[0094] In practical implementations, a single-agent execution graph is used to describe the actions and interactions of a single emergency response entity. A multi-agent execution graph is used to describe the coordinated actions and interactions of multiple emergency response entities.

[0095] The Agent execution diagram comprises a property diagram and a process diagram. The property diagram describes the static attributes of emergency entities, such as roles and resources. The process diagram describes the dynamic behaviors of emergency entities, such as actions and decisions.

[0096] In one example, the Agent attribute graph can be set up based on psychological attributes, cognitive attributes, and emergency command and dispatch algorithms. The diagram illustrates the action optimization strategy design process based on generative adversarial networks (GANs), including behavioral modeling, reasoning and planning mechanisms, dynamic policy optimization, and deep reinforcement learning.

[0097] Furthermore, the design of the multi-Agent execution graph algorithm requires two aspects: the design of an intelligent generation algorithm for multi-Agent execution behavior rules and the design of an interaction protocol algorithm for multi-Agent execution behavior. The former is the foundation for the latter. Through these two aspects, a multi-Agent execution process graph interaction mechanism is realized, which is used to express the interactive actions of multiple emergency entities in performing emergency tasks.

[0098] The intelligent generation algorithm for multi-agent execution behavior rules includes: multi-agent execution behavior prediction and classification based on convolutional neural networks; multi-agent execution behavior rule selection based on deep reinforcement learning; generation of optimal behavior rules and reward / penalty feedback. Behavior prediction and classification: using convolutional neural networks to predict and classify multi-agent execution behaviors. Behavior rule selection: selecting multi-agent execution behavior rules based on DRL. Reward / penalty feedback: generating optimal behavior rules and optimizing them through a reward / penalty mechanism.

[0099] Furthermore, the design of the multi-agent execution behavior interaction and cooperation algorithm includes: multi-agent execution interaction protocol modeling based on an improved contract network; interaction behavior modeling based on Markov processes; and task sequence and interaction task processing by extending communication primitives and communication mechanisms. Specifically, multi-agent execution interaction protocol modeling is performed based on an improved contract network, interaction behavior modeling is performed based on Markov processes, and task sequence and interaction task processing is performed by extending communication primitives and communication mechanisms.

[0100] Step 108: Generate an executable simulation model of the Agent execution graph and combine the executable simulation model with the cloud simulation model.

[0101] After the Agent execution graph is constructed, its logic and behavioral logic can be dynamically verified to generate an executable simulation model.

[0102] Among these measures, dynamic verification of the logic and behavioral logic of the Agent execution graph is performed to ensure its correctness.

[0103] The executable simulation model can run on the simulation platform, and in actual emergency management, the simulation results can be used to optimize emergency strategies.

[0104] This invention first constructs an emergency system by identifying emergency roles and nested execution pairs. This accurately identifies and defines key roles and behaviors in emergency scenarios, improving the accuracy and adaptability of the emergency system model and enabling it to better reflect the complex situations and role interactions in actual emergency handling. Then, based on the extraction of system requirements from nested execution pairs and the generation of emergency system analysis templates, it facilitates a systematic and structured analysis of emergency needs, ensuring the comprehensiveness and accuracy of emergency system requirements and increasing the planning and design capabilities of the emergency simulation system. Next, it decomposes emergency tasks, refining and clarifying the specific content and execution sequence of each emergency task, improving the operability and execution efficiency of emergency tasks. Then, based on the task decomposition results, it models interactive logic to form a logical flow and generates an Agent execution diagram based on the logical flow. This diagram visually displays the execution process and interaction relationships of each Agent, improving the model's visualization and usability, and facilitating model verification and optimization. Finally, the Agents are compiled into an executable simulation model, dynamically combined with a cloud-based simulation model, achieving automated generation and deployment of the simulation model. This enhances the system's flexibility and scalability, improves the development efficiency and operational performance of the simulation model, and enables it to respond more quickly to actual emergency needs.

[0105] To facilitate understanding, the following example illustrates the need for emergency management in a city experiencing a large-scale fire:

[0106] 1. Define the emergency problem: Identify emergency roles such as fire brigades, medical teams, and traffic management departments, and analyze historical fire data, firefighting strategies, and rescue rules.

[0107] Data reception and processing: Extracting emergency knowledge and data from the emergency management database. Emergency knowledge includes fire suppression strategies, emergency command rules, and emergency response experience. Emergency data includes historical fire data, traffic rule data, and emergency simulation data.

[0108] Data Processing: Emergency Knowledge Analysis: Transforming fire suppression strategies, emergency command rules, and emergency response experience into structured data. Emergency Data Analysis: Analyzing historical fire data to determine the frequency, causes, and handling methods of fires. Role Determination: Determining emergency roles based on data, including fire brigades, medical teams, and traffic management departments.

[0109] Emergency roles: Fire department, responsible for firefighting; Medical team, responsible for treating the injured; Traffic management department, responsible for traffic control.

[0110] 2. Define emergency system requirements: Generate an emergency system analysis template, including requirements for fire truck dispatch, medical resource allocation, and traffic management.

[0111] Requirements Extraction: Analyze the role relationships and interaction logic within nested execution pairs. Extract the specific requirements for each role: Fire Brigade: Requires 10 fire trucks and high-pressure water cannons. Medical Team: Requires 20 emergency medical personnel, first-aid supplies, and stretchers. Traffic Management Department: Requires closing roads around the fire scene and setting up evacuation routes.

[0112] Generate analysis template: Based on the above requirements, generate an emergency system analysis template.

[0113] 3. Task decomposition: Using an emergency system analysis template, regional scheduling tasks are decomposed based on strategic game theory, and time scheduling tasks are decomposed based on a task hierarchy network.

[0114] Spatial Domain Task Breakdown: Fire Brigade: Assigned to different areas for firefighting, ensuring coverage of the entire fire zone. Medical Team: Assigned to areas with concentrated casualties, ensuring rapid treatment. Traffic Management Department: Plans the closure and diversion of different roads to ensure smooth traffic flow.

[0115] Task breakdown by time domain: Fire department: First control the spread of the fire, then gradually extinguish it. Medical team: First rescue the seriously injured, then treat the lightly injured. Traffic management department: First close the main roads, then set up evacuation routes.

[0116] For example: Fire department: First control the spread of fire in area A, then gradually extinguish fire in area B. Medical team: First treat the seriously injured in area A, then treat the lightly injured in area B. Traffic management department: First close the main road X, then set up diversion routes Y.

[0117] 4. Interaction logic modeling:

[0118] Variable and relation judgment:

[0119] Fire department and command center: vehicle location, firefighting progress.

[0120] Medical teams and hospitals: number of wounded and allocation of medical resources.

[0121] Traffic management departments and citizens: traffic conditions and traffic diversion routes.

[0122] Emergency entity interaction logic modeling:

[0123] Firefighters and medical teams: The progress of firefighting is affecting the treatment of the injured.

[0124] Traffic management department and fire brigade: Traffic control affects the passage of fire trucks.

[0125] Constructing semantic representation: Based on a custom symbol rule system, a logical flow is formed.

[0126] For example: Fire departments and command centers: After fire trucks arrive at the fire scene, they report the progress of firefighting in real time. Medical teams and hospitals: They report the condition of the injured in real time and dispatch emergency resources. Traffic management departments and citizens: They release real-time traffic information and guide citizens to avoid the fire area.

[0127] 5. Generate execution diagrams for fire brigades, medical teams, and traffic management departments, including attribute diagrams and process diagrams.

[0128] Based on the logical flow, single-agent execution graphs and multi-agent execution graphs are generated.

[0129] Single Agent Execution Graph: Describes the actions and interactions of a single emergency response entity.

[0130] Multi-Agent Execution Graph: Describes the coordinated actions and interactions of multiple emergency entities.

[0131] For example: Single Agent Execution Graph: Describes the path planning and firefighting actions of fire truck A.

[0132] Multi-Agent Execution Graph: Describes the coordinated actions of fire truck A and medical team B to ensure coordination between firefighting and casualty treatment.

[0133] Attribute and process diagram generation: Extract basic information about emergency entities and their actions and interactions to generate attribute and process diagrams.

[0134] Attribute graph: Describes the static attributes of emergency entities, such as roles and resources.

[0135] Process diagram: Describes the dynamic behavior of emergency entities, such as actions and decisions.

[0136] Design the Agent execution attribute graph: based on psychological attributes, cognitive attributes, and emergency command and dispatch algorithm modules. Design the Agent execution process graph: based on generative adversarial networks for behavioral modeling, reasoning and planning mechanisms, dynamic policy optimization, and deep reinforcement learning for action optimization strategies.

[0137] Implementation details: Generative Adversarial Networks (GANs) and Deep Reinforcement Learning (DRL) algorithms are used to generate agent execution graphs, including attribute graphs and process graphs. A cloud computing platform is used for the generation and optimization of the execution graphs. In this embodiment, GAN and DRL algorithms are used to generate single-agent execution graphs for fire truck path planning and firefighting operations.

[0138] 6. Dynamically verify and compile the execution graph, generate an executable simulation model, and integrate it with the cloud-based simulation model set.

[0139] Dynamic verification: The logic and behavioral logic of the Agent execution graph are dynamically verified to ensure its correctness.

[0140] Load model code embedding: The load model code of the Agent's general structure is embedded into the Agent execution graph.

[0141] Code compilation: Compiles the Agent code to generate an executable simulation model. Simulation model ensemble: Dynamically assembles the executable simulation model with the cloud-based simulation model to achieve distributed simulation.

[0142] For example: Fire truck simulation model: simulates the movement path and firefighting process of fire trucks. Medical team simulation model: simulates the treatment of the wounded and resource allocation of medical teams. Traffic management simulation model: simulates traffic control and citizen evacuation processes.

[0143] Specific implementation:

[0144] Automatic code generation and model validation algorithms are applied to convert and dynamically validate the agent execution graph. A cloud-based simulation platform is used for distributed simulation to ensure real-time performance and efficiency. The automatic code generation algorithm converts the agent execution graph into an executable simulation model, which is then run on the cloud simulation platform to simulate coordinated emergency response by fire brigades, medical teams, and traffic management departments.

[0145] The above steps complete the fire emergency management simulation. The simulation model is run on the simulation platform to simulate the actual emergency process. Based on the simulation results, emergency strategies are optimized to improve emergency response efficiency and accuracy.

[0146] Please see Figure 2 , Figure 2 This is a structural block diagram of an urban emergency management simulation device provided in an embodiment of the present invention.

[0147] This invention provides an urban emergency management simulation device, comprising:

[0148] Emergency knowledge and emergency data acquisition module 201 is used to acquire emergency knowledge and emergency data corresponding to emergency tasks;

[0149] Emergency Role Determination Module 202 is used to determine emergency roles based on emergency knowledge and emergency data;

[0150] Nested execution pair building module 203 is used to build nested execution pairs for emergency roles;

[0151] The emergency system analysis template generation module 204 is used to extract the system requirements of emergency roles based on nested execution and generate an emergency system analysis template based on the system requirements.

[0152] Task decomposition module 205 is used to decompose emergency tasks using an emergency system analysis template to obtain task decomposition results.

[0153] The logic flow generation module 206 is used to model interactive logic using the task decomposition results to form a logic flow.

[0154] Agent execution graph generation module 207 is used to generate Agent execution graphs using logical flow;

[0155] Module 208 is used to generate an executable simulation model of the Agent execution graph and combine the executable simulation model with the cloud simulation model.

[0156] In this embodiment of the invention, the emergency role determination module 202 includes:

[0157] The parsing submodule is used to parse emergency knowledge and emergency data using natural language processing algorithms to obtain parsed data.

[0158] The structured data transformation submodule is used to transform parsed data into structured data;

[0159] The Emergency Role Determination Submodule is used to perform cluster analysis on structured data and determine the emergency role corresponding to each cluster result.

[0160] In this embodiment of the invention, emergency knowledge includes emergency command logic, emergency command rules, and emergency response experience; emergency data includes emergency historical data, constraint rule data, and emergency simulation data.

[0161] In this embodiment of the invention, the emergency system analysis template generation module 204 includes:

[0162] The system requirements extraction submodule is used to extract the system requirements of each emergency role based on the interaction relationship between the emergency roles in the nested execution pair.

[0163] The task breakdown information acquisition submodule is used to acquire task breakdown information corresponding to emergency tasks;

[0164] The emergency system analysis module generates a sub-module, which uses emergency roles, system requirements, and task breakdown information to generate emergency system analysis templates.

[0165] In this embodiment of the invention, the task decomposition module 205 includes:

[0166] The spatial domain task decomposition submodule is used to decompose emergency tasks in the spatial domain using task decomposition information to obtain regional scheduling decomposition results.

[0167] The time-domain task decomposition submodule is used to decompose emergency tasks in the time domain using task decomposition information to obtain time-scheduled task decomposition results.

[0168] In this embodiment of the invention, the logic flow generation module 206 includes:

[0169] The emergency entity determination submodule is used to determine emergency entities based on the task decomposition results;

[0170] The interaction relationship determination submodule is used to determine the interaction relationships between various emergency entities;

[0171] The logic flow forms a sub-module, which is used to model the interaction logic based on the interaction relationship and form the logic flow.

[0172] In this embodiment of the invention, the Agent execution graph generation module 207 includes:

[0173] The Action and Interaction Information Acquisition Submodule is used to acquire the action and interaction information of each emergency role using a logical flow.

[0174] The Single Agent Execution Graph Generation Submodule is used to generate single agent execution graphs for each emergency role using action and interaction information;

[0175] The multi-agent execution graph generation submodule is used to generate a multi-agent execution graph using the action and interaction information of multiple emergency roles.

[0176] This invention also provides an electronic device, characterized in that the device includes a processor and a memory:

[0177] The memory is used to store program code and transfer the program code to the processor;

[0178] The processor is used to execute the urban emergency management simulation method of this invention according to the instructions in the program code.

[0179] This invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program code, which is used to execute the urban emergency management simulation method of this invention.

[0180] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0181] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0182] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0183] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0184] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0185] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0186] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0187] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0188] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some 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 the present invention.

Claims

1. A simulation method for urban emergency management, characterized in that, include: Acquire emergency knowledge and data corresponding to emergency tasks; The emergency knowledge and emergency data are analyzed using natural language processing algorithms to obtain the analyzed data; The parsed data is then converted into structured data; Cluster analysis was performed on the structured data, and the emergency response roles corresponding to each cluster result were determined. Construct nested execution pairs of the emergency roles; the nested execution pairs of the emergency roles include the emergency roles and their corresponding responsibilities; Based on the nested execution, extract the system requirements of the emergency role, and generate an emergency system analysis template based on the system requirements; The emergency system analysis template is used to perform spatial domain task decomposition based on strategic game theory, and the emergency task is also decomposed in the time domain based on the task hierarchy network to obtain task decomposition results. The task decomposition results are used to refine and clarify the specific content and execution order of each emergency task. In the task decomposition results, the regional scheduling decomposition results are used to indicate the task area, and the time scheduling task decomposition results are used to indicate the timeliness and priority of the task. The task decomposition results are used to model the interaction logic and form a logical flow. The aforementioned logical flow generates an Agent execution graph, which includes an attribute graph describing the static attributes of emergency entities and a process graph describing the dynamic behavior of emergency entities. The process graph is designed based on behavioral modeling of generative adversarial networks and action optimization strategies of deep reinforcement learning, and the interaction between multiple emergency entities is modeled based on an improved contract network protocol. The Agent execution graph includes single-Agent execution graphs and multi-Agent execution graphs. The single-Agent execution graph is used to describe the actions and interactions of a single emergency entity, and the multi-Agent execution graph is used to describe the collaborative actions and interactions of multiple emergency entities. The algorithm design for the multi-Agent execution graph includes the design of an intelligent generation algorithm for multi-Agent execution behavior rules and the design of an algorithm for multi-Agent execution behavior interaction protocols. Generate an executable simulation model of the Agent execution graph, and combine the executable simulation model with the cloud simulation model; The step of extracting the system requirements for the emergency role based on the nested execution and generating an emergency system analysis template based on the system requirements includes: Based on the interaction relationships between the emergency roles in the nested execution pair, the system requirements of each emergency role are extracted; the task decomposition information corresponding to the emergency task is obtained; and an emergency system analysis template is generated using the emergency roles, the system requirements, and the task decomposition information.

2. The method according to claim 1, characterized in that, The emergency knowledge includes emergency command logic, emergency command rules, and emergency response experience; the emergency data includes historical emergency data, constraint rule data, and emergency simulation data.

3. The method according to claim 1, characterized in that, The step of using the task decomposition results to model the interaction logic and form a logical flow includes: The emergency entities are determined based on the task decomposition results; Determine the interaction relationships between various emergency entities; Based on the interaction relationships, interaction logic modeling is performed to form a logical flow.

4. The method according to claim 1, characterized in that, The step of generating the Agent execution graph using the aforementioned logical flow includes: The aforementioned logical flow is used to obtain the action and interaction information of each emergency response role; The aforementioned action and interaction information is used to generate a single-agent execution graph for each emergency role; A multi-agent execution graph is generated by using the action and interaction information of multiple emergency roles.

5. A city emergency management simulation device, characterized in that, include: The emergency knowledge and emergency data acquisition module is used to acquire emergency knowledge and emergency data corresponding to emergency tasks. An emergency role determination module is used to determine emergency roles based on the emergency knowledge and the emergency data. The nested execution pair building module is used to construct the nested execution pairs of the emergency roles; the nested execution pairs of the emergency roles include the emergency roles and their corresponding responsibilities; An emergency system analysis template generation module is used to extract the system requirements of the emergency role based on the nested execution, and generate an emergency system analysis template based on the system requirements; The task decomposition module is used to perform spatial domain task decomposition of the emergency tasks based on the strategic game method using the emergency system analysis template, and to perform temporal domain task decomposition of the emergency tasks based on the task hierarchy network, to obtain task decomposition results. The task decomposition results are used to refine and clarify the specific content and execution order of each emergency task. In the task decomposition results, the regional scheduling decomposition results are used to indicate the task region, and the time scheduling task decomposition results are used to indicate the timeliness and priority of the task. The logic flow generation module is used to model the interactive logic using the task decomposition results to form a logic flow. The Agent Execution Graph Generation Module is used to generate Agent Execution Graphs using the aforementioned logical flow. The Agent Execution Graphs include attribute graphs describing the static attributes of emergency entities and process graphs describing the dynamic behaviors of emergency entities. The process graphs are designed based on generative adversarial networks (GANs) for behavior modeling and deep reinforcement learning for action optimization strategies. Furthermore, the interactions between multiple emergency entities are modeled based on an improved contract network protocol. The Agent Execution Graphs include single-Agent Execution Graphs and multi-Agent Execution Graphs. The single-Agent Execution Graph describes the actions and interactions of a single emergency entity, while the multi-Agent Execution Graph describes the collaborative actions and interactions of multiple emergency entities. The algorithm design for the multi-Agent Execution Graphs includes an intelligent generation algorithm for multi-Agent execution behavior rules and an algorithm design for multi-Agent execution behavior interaction protocols. The module is used to generate an executable simulation model of the Agent execution graph and combine the executable simulation model with the cloud simulation model; The emergency system analysis template generation module includes: The system requirements extraction submodule is used to extract the system requirements of each emergency role based on the interaction relationship between the emergency roles in the nested execution pair. The task breakdown information acquisition submodule is used to acquire task breakdown information corresponding to emergency tasks; The emergency system analysis module generates a sub-module, which uses emergency roles, system requirements, and task breakdown information to generate emergency system analysis templates. The emergency role determination module includes: The parsing submodule is used to parse emergency knowledge and emergency data using natural language processing algorithms to obtain parsed data. The structured data transformation submodule is used to transform parsed data into structured data; The Emergency Role Determination Submodule is used to perform cluster analysis on structured data and determine the emergency role corresponding to each cluster result.

6. An electronic device, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the urban emergency management simulation method according to any one of claims 1-4 according to the instructions in the program code.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the urban emergency management simulation method according to any one of claims 1-4.

Images