Intelligent road emergency plan deduction method, system, equipment and medium

Abstract

The invention provides an intelligent road emergency plan deduction method, system and device and a medium, and belongs to the technical field of intelligent traffic. The method comprises the following steps: constructing a multi-source heterogeneous emergency database by collecting traffic knowledge, road historical data, real-time data and resources; a rule engine is designed based on the multi-source heterogeneous emergency database, a pre-arranged plan intelligent generation model is built in combination with a recurrent neural network model, and the model receives input event features and outputs an emergency pre-arranged plan; a visual deduction scene is constructed based on a three-dimensional WebGIS engine, and weather special effect simulation is realized by using a GLSL shader technology; performing visual mapping and simulation on the emergency resources and the emergency plan in the visual deduction scene; and event parameters input by a user are received, the intelligent plan generation model is called to obtain an emergency plan, and full-process dynamic deduction from event occurrence to disposal completion is completed in the visual deduction scene.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, and more specifically relates to an intelligent road emergency response plan simulation method, system, equipment and medium. Background Technology

[0002] With the acceleration of urbanization and the continuous growth of motor vehicle ownership, the burden on road transportation is increasing, and various emergencies are characterized by high frequency, diverse types, and wide impact. To reduce accident losses, traffic management departments in various regions have generally developed emergency plans. However, existing plans are mostly based on historical experience or static templates, relying on periodic manual revisions, resulting in long update cycles and difficulty in reflecting real-time dynamic changes in traffic, weather, and resources. This leads to significant discrepancies between the plan content and actual needs.

[0003] In terms of data collection and utilization, traditional methods mainly rely on manual reporting and decentralized information systems. The data formats are inconsistent, the dimensions are limited, and there is a lack of deep integration of multi-source heterogeneous data such as traffic monitoring, weather forecasts, geographic information, and emergency resources. As a result, the resulting contingency plans often fail to accurately depict the accident scene environment and are difficult to predict the evolution trend of the accident, leading to insufficient targeting of subsequent response measures and low efficiency in resource allocation.

[0004] In the simulation and verification phase, existing technologies mostly employ desktop simulations or on-site drills. Desktop simulations are highly abstract and cannot intuitively present road networks, traffic flow changes, and resource scheduling processes; on-site drills are costly, time-consuming, and limited by factors such as venue, weather, and personnel, making large-scale, high-frequency implementation difficult. The lack of effective simulation methods makes it difficult to detect deficiencies in contingency plans in a timely manner, resulting in delayed emergency response when accidents occur, which can easily lead to the spread of traffic congestion and secondary accidents. Summary of the Invention

[0005] To address the above problems, the present invention aims to provide an intelligent road emergency plan simulation method, system, device, and medium. By integrating multi-source data, a joint model of rules and neural networks, and three-dimensional visualization simulation, the generation of road emergency plans is made more accurate, the simulation more intuitive, and the response more rapid.

[0006] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide an intelligent road emergency response plan simulation method, including: By collecting traffic knowledge, historical road data, real-time data, and resources, a multi-source heterogeneous emergency database is constructed, which includes a knowledge base, a historical database, a real-time database, and a resource database. A rule engine is designed based on a multi-source heterogeneous emergency database, and an intelligent emergency plan generation model is constructed by combining a recurrent neural network model. The model receives input event features and outputs emergency plans. A visual simulation scenario is built based on a 3D WebGIS engine, and weather effects simulation is achieved using GLSL shader technology. Emergency resources and emergency plans are visualized and simulated in the visualization simulation scenario; The system receives event parameters input by the user, calls the intelligent generation model of the contingency plan to obtain the emergency plan, and completes a dynamic simulation of the entire process from the occurrence of the event to its resolution in the visualized simulation scenario.

[0007] In one optional implementation, the construction of a multi-source heterogeneous emergency database by collecting traffic knowledge, historical road data, real-time data, and resources includes: Collect traffic-related departmental regulations, industry standards, emergency knowledge, and expert experience to build a structured knowledge base; Collect historical traffic emergency data and their response plans, build a historical database, and extract multi-dimensional feature data including accident type, time, location, response measures, and resource allocation records to generate a historical labeled dataset; Access and integrate real-time traffic flow data, surveillance video data, meteorological data, and geographic information system data to build a real-time database; Acquire and store spatial geographic data, road network data, emergency shelter information, as well as location, status and dispatch attribute information of emergency supplies, emergency teams, emergency experts and emergency personnel, and build a resource database; All data in the multi-source heterogeneous emergency database were cleaned to remove duplicate and erroneous data, and missing values ​​were filled in; historical traffic emergency data were labeled to clearly identify the event type, level, and handling results.

[0008] In an optional implementation, the rule engine based on a multi-source heterogeneous emergency database includes: Based on a knowledge base, a rule engine is designed to transform textual departmental regulations, industry standards, emergency common sense, and expert experience into computer-executable logical rules and generate deterministic response plans.

[0009] In an optional implementation, the step of constructing a contingency plan intelligent generation model by combining a recurrent neural network model includes: extracting features from data in historical databases, real-time databases, and resource databases to generate feature sequences; Construct a recurrent neural network model, input feature sequences into the model to capture the temporal dependencies in emergency events, output the probability distribution of response measures for the current event, and determine the optimization scheme; The recurrent neural network model was trained using a historical labeled dataset. The cross-entropy loss function was used to measure the difference between the predicted values ​​and the true labels. The model parameters were adjusted through backpropagation and optimization algorithms. The model performance was evaluated using cross-validation. The learning rate, number of network layers, and number of neurons of the model were optimized. By integrating the rule engine with the recurrent neural network model, an intelligent emergency plan generation model is constructed. This model integrates deterministic and optimized solutions to generate structured emergency plan templates that include emergency team formation, personnel and vehicle evacuation plans, traffic control measures, and resource allocation lists.

[0010] In an optional implementation, the construction of a visual simulation scene based on a 3D WebGIS engine and the use of GLSL shader technology to simulate weather effects include: Using a Node.js environment, leveraging the Vue 3 framework and the Cesium.js library, we built a 3D WebGIS front-end application, creating [the application] within the page.<divid="cesiumContainer"> The container is instantiated with a Cesium.Viewer object to load the 3D globe and map basemap; Acquire GeoJSON format road network data of the event location and dynamically set the display color and width of the roads based on real-time traffic congestion levels; acquire building outline data of the relevant area and render 3D building models; Based on meteorological data, a custom GLSL shader is invoked in a 3D scene using Cesium's PostProcessStage method to simulate dynamic weather effects such as rain, snow, thunder, and fog.

[0011] In an optional implementation, the step of visually mapping and simulating emergency resources and emergency plans in the visualization simulation scenario includes: The location information of emergency supplies, emergency teams, emergency experts, and emergency personnel is rendered on a 3D map in the form of icons or 3D models; Based on the emergency plan template, the emergency plan determines evacuation routes through personnel and vehicle evacuation schemes, determines the prevention and control scope of relevant areas through traffic control measures, and further determines the prevention and control circle on the 3D map; the movement trajectory and route of emergency resources are determined through the resource scheduling list, and resource scheduling routes are generated; evacuation routes, prevention and control circles, and resource scheduling routes are simulated in the 3D scene.

[0012] In an optional implementation, the step of receiving event parameters input by the user, invoking the intelligent contingency plan generation model to obtain an emergency plan, and completing a dynamic simulation of the entire process from event occurrence to resolution in the visualized simulation scenario includes: Receive event parameters input by the user on the front-end interface, the event parameters including location, accident type, meteorological data and brief description; Input the event parameters into the intelligent emergency plan generation model, and generate a structured emergency plan by matching the corresponding emergency plan template; Based on the emergency plan, visualization mapping and simulation are carried out in the visualization simulation scenario, and the entire process from event occurrence, resource scheduling, traffic management to safe evacuation is dynamically rendered in the three-dimensional scene.

[0013] Secondly, embodiments of this application also provide an intelligent road emergency response plan simulation system, including: The database construction module is used to build a multi-source heterogeneous emergency database by collecting traffic knowledge, historical road data, real-time data and resources. The multi-source heterogeneous emergency database includes a knowledge base, a historical database, a real-time database and a resource database. The model is designed to build a rule engine based on a multi-source heterogeneous emergency database and to build an intelligent emergency plan generation model by combining a recurrent neural network model. The model receives input event features and outputs emergency plans. The scene building module is used to build visual simulation scenes based on the 3D WebGIS engine and to realize weather effect simulation using GLSL shader technology; The visualization mapping module is used to visualize and simulate emergency resources and emergency plans in the visualization simulation scenario; The real-time simulation module is used to receive event parameters input by the user, call the intelligent generation model of the contingency plan to obtain the emergency plan, and complete the dynamic simulation of the entire process from the occurrence of the event to the completion of the handling in the visualized simulation scenario.

[0014] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the intelligent road emergency response plan simulation method described in any of the above descriptions.

[0015] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the intelligent road emergency response plan simulation method described in any of the above.

[0016] As can be seen from the above technical solutions, the present invention has the following advantages: The intelligent road emergency response plan simulation method provided in this application constructs a multi-source heterogeneous emergency database by aggregating regulations, cases, and real-time traffic and resource data. It automatically generates and continuously optimizes emergency plans using a rule engine and recurrent neural network fusion model. Furthermore, it dynamically visualizes events, resources, and the handling process using 3D WebGIS and GLSL real-time simulation. This significantly improves the relevance, real-time nature, and operability of the plans, reduces the workload of manual preparation, shortens emergency response time, and achieves precision, intelligence, and efficiency in handling road emergencies.

[0017] This application unifies and aggregates heterogeneous information from multiple sources, including traffic regulations, historical emergencies, real-time traffic flow, meteorology, GIS, and emergency resources. After cleaning, labeling, and structuring, it forms a high-quality emergency database, completely breaking down information barriers between departments and achieving panoramic data support.

[0018] This application transforms textual regulations and standards, along with expert experience, into an executable rule engine, which is deeply coupled with a recurrent neural network. This ensures that the measures taken are legal and compliant, while also fully exploring historical time-series patterns, performing probabilistic reasoning on the characteristics of current events, and automatically generating accurate and implementable structured emergency plans.

[0019] This application is based on a 3D WebGIS front-end combined with GLSL shaders to render weather effects such as rain, snow, thunder, and fog, as well as road congestion status in real time. It transforms abstract traffic flow and emergency resources into intuitive 3D scenes, enabling commanders to immerse themselves in the observation and interactive adjustment of the entire response process.

[0020] In this application, once the contingency plan is generated, the location and status of emergency supplies, teams, and experts can be synchronously mapped on a 3D map, the optimal evacuation routes and resource scheduling trajectories can be dynamically calculated, and the entire process of vehicle and personnel movement can be simulated in a particle-based manner, significantly improving the timeliness and utilization rate of resource deployment. Attached Figure Description

[0021] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying 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.

[0022] Figure 1 A flowchart illustrating the intelligent road emergency response plan simulation method provided in this application.

[0023] Figure 2 A schematic diagram of the intelligent road emergency response plan simulation system provided in this application.

[0024] Figure 3A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0025] The various embodiments of this disclosure will be described more fully in the detailed steps of the intelligent road emergency response plan simulation method described below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0026] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Please see Figure 1 The diagram shows a flowchart of an intelligent road emergency response plan simulation method in a specific embodiment. The method includes: S1: By collecting traffic knowledge, historical road data, real-time data, and resources, a multi-source heterogeneous emergency database is constructed, which includes a knowledge base, a historical database, a real-time database, and a resource database.

[0029] In a specific implementation, the first step is to build a knowledge base, collecting traffic knowledge from multiple channels, covering traffic regulations, industry standards, emergency preparedness knowledge, and expert experience. The collected regulations, standards, key points of common knowledge, and experience summaries are then systematically categorized and structured to facilitate subsequent queries and access.

[0030] When building the historical database, comprehensive and detailed information on past traffic emergencies is collected, including event type, time and location, response measures taken, and details of resource allocation. This historical data is then analyzed in depth to accurately extract key features, such as the geographical information of the accident location and weather conditions at the time of the incident. The data is then meticulously categorized and labeled according to the severity and scope of the event.

[0031] Building a real-time database requires integrating various real-time data resources. On one hand, it involves accessing traffic flow data to understand changes in vehicle volume and speed on the roads; on the other hand, it integrates surveillance video data to intuitively understand road conditions using traffic cameras. Simultaneously, it integrates meteorological data and Geographic Information System (GIS) data to comprehensively analyze current road traffic conditions and environmental conditions. The construction of a resource database involves collecting and organizing various emergency resource information, including spatial geographic data, road network data, emergency shelter information, and relevant data on emergency supplies, teams, experts, and personnel. This includes clearly defining the types, quantities, and storage locations of emergency supplies; recording the personnel composition and professional skills of emergency teams; compiling the names, professional fields, and contact information of emergency experts; and collecting basic information and job responsibilities of emergency personnel. To ensure the accuracy and timeliness of the data, resource data needs to be updated regularly.

[0032] Finally, the data in the multi-source heterogeneous emergency database was thoroughly cleaned to remove duplicate and obviously erroneous data, and missing values ​​were filled using appropriate methods. Simultaneously, historical traffic emergency data was meticulously annotated to clarify the type, severity, and outcome of each event, laying a solid foundation for subsequent data analysis and model training.

[0033] S2: A rule engine is designed based on a multi-source heterogeneous emergency database, and an intelligent emergency plan generation model is constructed by combining a recurrent neural network model. The model receives input event features and outputs emergency plans.

[0034] In a specific implementation, when constructing the intelligent emergency response model, the first step is to accurately extract rule logic based on resources such as laws, regulations, and industry standards in the knowledge base. For example, in a hazardous chemical spill accident, this involves clarifying the evacuation range for surrounding personnel. Next, these rule logics are converted into a computer-executable format, such as "if a specific situation occurs, execute the corresponding measures," thus establishing the framework of the rule engine. Then, features closely related to the emergency event, such as accident location, weather conditions, and traffic flow, are selected from historical, real-time, and resource databases and arranged chronologically to generate a feature sequence, providing data for model training.

[0035] When constructing the Recurrent Neural Network (RNN) model, considering the gradient vanishing and exploding problems inherent in traditional RNNs, optimized architectures such as Long Short-Term Memory (LSTM) or Gated Recurrent Units (GRUs) are selected. The generated feature sequences are input into the model, which, through the information transmission of hidden states along the time axis, accurately captures the temporal dependencies in emergency events and ultimately outputs the probability distribution of different response measures, thereby determining the optimization scheme. Next, the RNN model is trained using a historical labeled dataset, with the feature sequences of historical events as input and the corresponding response measure labels as output. During training, a cross-entropy loss function is introduced to measure the difference between predictions and reality. Backpropagation and optimization algorithms (such as Adam and SGD) are used to fine-tune the model parameters to reduce the value of the loss function. Simultaneously, cross-validation is used to comprehensively evaluate the model performance, and the model hyperparameters, such as the learning rate, number of network layers, and number of neurons, are optimized based on the evaluation feedback.

[0036] Finally, the rule engine and recurrent neural network model are deeply integrated to construct an intelligent emergency plan generation model. When generating an emergency plan, the rule engine first produces a deterministic response plan, and then the recurrent neural network model generates an optimized plan. After the two are organically integrated, a complete emergency plan template is formed, covering key aspects such as emergency team formation, personnel and vehicle evacuation, traffic control, and resource allocation.

[0037] S3: Constructs a visual simulation scenario based on a 3D WebGIS engine and uses GLSL shader technology to simulate weather effects.

[0038] In this specific implementation, the first step is to build a 3D WebGIS front-end application. First, download and install the VS Code front-end development software, and then deploy the Node.js environment using NVM (Node.js version manager). Next, introduce the Vue.js framework to build the front-end application architecture and integrate the Cesium.js library to achieve 3D geographic information visualization. Then, create [the necessary components] within the page.<divid="cesiumContainer"> The container holds the 3D globe and map content rendered by CesiumViewer. A Cesium.Viewer object is instantiated using the code newCesium.Viewer('cesiumContainer',{...}), which loads the 3D globe and map base and sets parameters such as view extent, layers, and controls as needed.

[0039] Then, GeoJSON format road network data and regional building outline data (e.g., shp format) of the event location are acquired. The road network data is loaded into the Cesium scene, and the road display color and width are dynamically adjusted according to the real-time traffic congestion level, such as using red to widen congested road sections. Simultaneously, the building outline data is converted and rendered in GeoJSON format, and building color and shape attributes are set to realistically present them in the 3D scene, creating a detailed geographical background for emergency simulations. A meteorological data interface is connected to obtain real-time information such as rainfall, snowfall, lightning intensity, and fog concentration. Custom shader code is written using GLSL (OpenGL Shading Language) to simulate weather effects such as rain, snow, thunder, and fog. In the 3D scene, the GLSL shader is called using Cesium's PostProcessStage method to achieve dynamic display of weather effects, such as using specific algorithms to simulate falling raindrops, drifting snowflakes, lightning path generation, and fog changes, creating realistic environmental conditions for emergency simulations.

[0040] S4: Visualize and simulate emergency resources and emergency plans in the visualization simulation scenario.

[0041] In a specific implementation, the location information of emergency supplies, teams, experts, and personnel is first accurately extracted from the resource database, covering key data such as latitude and longitude, affiliated unit, or storage location. For different resource types and attributes, appropriate icons or 3D models are selected to represent them. These icons or models are then rendered on a 3D map based on the acquired location information, achieving an intuitive visualization of the distribution of emergency resources. For example, ambulance icons identify medical rescue teams, and sandbag icons represent flood control supplies.

[0042] Then, the generated emergency response plan template was analyzed in depth to accurately extract core content such as personnel and vehicle evacuation plans, traffic control measures, and resource allocation lists. Combined with map data, evacuation routes were precisely located based on the evacuation plan, such as the optimal path from the accident site to the surrounding safe area; the control scope was clarified with reference to traffic control measures, and control circles were drawn on a 3D map to define the areas requiring control; the movement trajectory and routes of emergency resources were planned according to the resource allocation list, such as the transportation route of supplies from the warehouse to the site, and the travel routes of experts from their units to the site.

[0043] In a 3D scene, the entire emergency response process is dynamically simulated based on the generated evacuation, control, and dispatch routes. With the help of animation effects, the evacuation actions of vehicles and personnel, the allocation and use of emergency resources are vividly displayed, such as the rapid arrival of rescue vehicles at the scene and the orderly unloading and distribution of rescue supplies, helping users to clearly understand the execution details and effectiveness of the emergency plan.

[0044] S5: Receive event parameters input by the user, call the intelligent generation model of the contingency plan to obtain the emergency plan, and complete the dynamic simulation of the entire process from the occurrence of the event to the completion of the handling in the visualized simulation scenario.

[0045] In a specific implementation, the system first obtains key information such as the location, accident type, and weather data input by the user through the user input interface on the front-end page, as well as a brief description of the event, such as "multi-vehicle pileup at a highway intersection, injuries, light rain." Upon receiving the input, the system immediately parses the information, accurately extracting event parameters, including location coordinates (after geocoding), accident type code, and weather data code, to prepare for model processing.

[0046] Then, the extracted event parameters are input into the intelligent emergency plan generation model. The model matches the corresponding template according to the parameters and quickly generates a structured emergency plan by taking into account factors such as event type, location, and weather. Subsequently, the plan content is precisely associated and mapped with the visualized simulation scenario, such as matching evacuation routes with map roads and associating resource scheduling lists with resource icons, providing solid support for dynamic simulation.

[0047] Ultimately, the entire process from the occurrence of an event to its resolution is presented sequentially in a 3D visualization simulation scenario, following the steps of the emergency response plan. The event scene is dynamically rendered in animation, depicting events such as vehicle collisions and crowd gatherings; resources are shown converging on-site in real-time, with personnel evacuation and vehicles leaving the danger zone; traffic control and site cleanup are meticulously depicted until roads are reopened. The entire simulation process is coherent and smooth, helping users comprehensively understand the emergency response plan's execution process and effectiveness, providing strong support for actual emergency response decisions.

[0048] In this embodiment, by constructing a multi-source heterogeneous emergency database, designing an intelligent emergency plan generation model that integrates a rule engine and a recurrent neural network, creating a three-dimensional visualization simulation scenario and simulating weather effects, and simulating the dynamic mapping between emergency resources and plans, this intelligent road emergency plan simulation method achieves dynamic simulation of the entire process from the occurrence of an event to its completion. It achieves significant results in improving the accuracy of plans, optimizing resource allocation, and enhancing emergency response capabilities, effectively contributing to the improvement of traffic emergency management.

[0049] like Figure 2 As shown, the following are embodiments of the intelligent road emergency response plan simulation system provided in this disclosure. This system and the intelligent road emergency response plan simulation method of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the intelligent road emergency response plan simulation system, please refer to the embodiments of the intelligent road emergency response plan simulation method described above.

[0050] An intelligent road emergency response plan simulation system includes: The database construction module is used to build a multi-source heterogeneous emergency database by collecting traffic knowledge, historical road data, real-time data, and resources. The multi-source heterogeneous emergency database includes a knowledge base, a historical database, a real-time database, and a resource database.

[0051] The model construction model is used to design a rule engine based on a multi-source heterogeneous emergency database and to build an intelligent emergency plan generation model in combination with a recurrent neural network model. The model receives input event features and outputs emergency plans.

[0052] The scene building module is used to build visual simulation scenes based on the 3D WebGIS engine and to realize weather effect simulation using GLSL shader technology.

[0053] The visualization mapping module is used to visualize and simulate emergency resources and emergency plans in the visualization simulation scenario.

[0054] The real-time simulation module is used to receive event parameters input by the user, call the intelligent generation model of the contingency plan to obtain the emergency plan, and complete the dynamic simulation of the entire process from the occurrence of the event to the completion of the handling in the visualized simulation scenario.

[0055] The intelligent road emergency response plan simulation system provided in this embodiment constructs a unified emergency database by aggregating heterogeneous data from multiple sources. It achieves automatic generation and optimization of plans through a rule engine and a recurrent neural network fusion model. Relying on 3D WebGIS and GLSL effects, it presents the entire process of weather, road conditions, and resource scheduling in real time, forming a data-driven, visually interactive, and closed-loop evolutionary intelligent simulation system. This significantly improves the response speed, resource utilization efficiency, and scientific decision-making of road emergencies.

[0056] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0057] The intelligent road emergency response plan simulation method provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0058] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0059] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0060] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0061] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0062] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0063] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0064] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0065] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0066] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0067] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0068] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0069] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0070] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0071] The aforementioned electronic equipment realizes the intelligent road emergency plan simulation method of this application by constructing a multi-source heterogeneous emergency database, integrating a rule engine and a recurrent neural network to form an intelligent plan generation model, and relying on 3D WebGIS and GLSL effects to achieve a visual simulation closed loop, thus achieving the beneficial effects of automatic and accurate generation of road emergency plans, efficient resource scheduling, real-time emergency response, and continuous optimization closed loop.

[0072] The storage medium provided in this application stores a program product capable of realizing an intelligent road emergency response plan simulation method.

[0073] Intelligent road emergency response plan simulation methods include: By collecting traffic knowledge, historical road data, real-time data, and resources, a multi-source heterogeneous emergency database is constructed, which includes a knowledge base, a historical database, a real-time database, and a resource database. A rule engine is designed based on a multi-source heterogeneous emergency database, and an intelligent emergency plan generation model is constructed by combining a recurrent neural network model. The model receives input event features and outputs emergency plans. A visual simulation scenario is built based on a 3D WebGIS engine, and weather effects simulation is achieved using GLSL shader technology. Emergency resources and emergency plans are visualized and simulated in the visualization simulation scenario; The system receives event parameters input by the user, calls the intelligent generation model of the contingency plan to obtain the emergency plan, and completes a dynamic simulation of the entire process from the occurrence of the event to its resolution in the visualized simulation scenario. In some possible implementations, the intelligent road emergency response plan simulation method of this disclosure can be implemented as a program product, which includes program code. When the program product is run on a terminal device, the program code is used to cause the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0074] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0075] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent road emergency response plan simulation method, characterized in that, include: By collecting traffic knowledge, historical road data, real-time data, and resources, a multi-source heterogeneous emergency database is constructed, which includes a knowledge base, a historical database, a real-time database, and a resource database. A rule engine is designed based on a multi-source heterogeneous emergency database, and an intelligent emergency plan generation model is constructed by combining a recurrent neural network model. The model receives input event features and outputs emergency plans. A visual simulation scenario is built based on a 3D WebGIS engine, and weather effects simulation is achieved using GLSL shader technology. Emergency resources and emergency plans are visualized and simulated in the visualization simulation scenario; The system receives event parameters input by the user, calls the intelligent generation model of the contingency plan to obtain the emergency plan, and completes a dynamic simulation of the entire process from the occurrence of the event to its resolution in the visualized simulation scenario.

2. The intelligent road emergency response plan simulation method according to claim 1, characterized in that, The aforementioned method involves collecting traffic knowledge, historical road data, real-time data, and resources to construct a multi-source heterogeneous emergency database, including: Collect traffic-related departmental regulations, industry standards, emergency knowledge, and expert experience to build a structured knowledge base; Collect historical traffic emergency data and their response plans, build a historical database, and extract multi-dimensional feature data including accident type, time, location, response measures, and resource allocation records to generate a historical labeled dataset; Access and integrate real-time traffic flow data, surveillance video data, meteorological data, and geographic information system data to build a real-time database; Acquire and store spatial geographic data, road network data, emergency shelter information, as well as location, status and dispatch attribute information of emergency supplies, emergency teams, emergency experts and emergency personnel, and build a resource database; All data in the multi-source heterogeneous emergency database were cleaned to remove duplicate and erroneous data, and missing values ​​were filled in; historical traffic emergency data were labeled to clearly identify the event type, level, and handling results.

3. The intelligent road emergency response plan simulation method according to claim 2, characterized in that, The rule engine designed based on a multi-source heterogeneous emergency database includes: Based on a knowledge base, a rule engine is designed to transform textual departmental regulations, industry standards, emergency common sense, and expert experience into computer-executable logical rules and generate deterministic response plans.

4. The intelligent road emergency response plan simulation method according to claim 3, characterized in that, The construction of the intelligent generation model for the contingency plan by combining the recurrent neural network model includes: extracting features from data in historical databases, real-time databases, and resource databases to generate feature sequences; Construct a recurrent neural network model, input feature sequences into the model to capture the temporal dependencies in emergency events, output the probability distribution of response measures for the current event, and determine the optimization scheme; The recurrent neural network model was trained using a historical labeled dataset. The cross-entropy loss function was used to measure the difference between the predicted values ​​and the true labels. The model parameters were adjusted through backpropagation and optimization algorithms. The model performance was evaluated using cross-validation. The learning rate, number of network layers, and number of neurons of the model were optimized. By integrating the rule engine with the recurrent neural network model, an intelligent emergency plan generation model is constructed. This model integrates deterministic and optimized solutions to generate structured emergency plan templates that include emergency team formation, personnel and vehicle evacuation plans, traffic control measures, and resource allocation lists.

5. The intelligent road emergency response plan simulation method according to claim 4, characterized in that, The construction of a visual simulation scenario based on a 3D WebGIS engine, and the use of GLSL shader technology to simulate weather effects, includes: Using a Node.js environment, leveraging the Vue 3 framework and the Cesium.js library, we built a 3D WebGIS front-end application, creating [the application] within the page.<divid="cesiumContainer"> The container is instantiated with a Cesium.Viewer object to load the 3D globe and map basemap; Acquire GeoJSON format road network data of the event location and dynamically set the display color and width of the roads based on real-time traffic congestion levels; acquire building outline data of the relevant area and render 3D building models; Based on meteorological data, a custom GLSL shader is invoked in a 3D scene using Cesium's PostProcessStage method to simulate dynamic weather effects such as rain, snow, thunder, and fog.

6. The intelligent road emergency response plan simulation method according to claim 5, characterized in that, The process of visually mapping and simulating emergency resources and emergency plans within the visualization simulation scenario includes: The location information of emergency supplies, emergency teams, emergency experts, and emergency personnel is rendered on a 3D map in the form of icons or 3D models; Based on the emergency plan template, the emergency plan determines evacuation routes through personnel and vehicle evacuation schemes, determines the prevention and control scope of relevant areas through traffic control measures, and further determines the prevention and control circle on the 3D map; the movement trajectory and route of emergency resources are determined through the resource scheduling list, and resource scheduling routes are generated; evacuation routes, prevention and control circles, and resource scheduling routes are simulated in the 3D scene.

7. The intelligent road emergency response plan simulation method according to claim 6, characterized in that, The process of receiving event parameters input by the user, calling the intelligent contingency plan generation model to obtain an emergency plan, and performing a dynamic simulation of the entire process from event occurrence to resolution in the visualized simulation scenario includes: Receive event parameters input by the user on the front-end interface, the event parameters including location, accident type, meteorological data and brief description; Input the event parameters into the intelligent emergency plan generation model, and generate a structured emergency plan by matching the corresponding emergency plan template; Based on the emergency plan, visualization mapping and simulation are carried out in the visualization simulation scenario, and the entire process from event occurrence, resource scheduling, traffic diversion to safe evacuation is dynamically rendered in the three-dimensional scene.

8. An intelligent road emergency response plan simulation system, characterized in that, The system employs the intelligent road emergency response plan simulation method as described in any one of claims 1 to 7; The system includes: The database construction module is used to build a multi-source heterogeneous emergency database by collecting traffic knowledge, historical road data, real-time data and resources. The multi-source heterogeneous emergency database includes a knowledge base, a historical database, a real-time database and a resource database. The model building module is used to design a rule engine based on a multi-source heterogeneous emergency database and to build an intelligent emergency plan generation model in combination with a recurrent neural network model. The model receives input event features and outputs emergency plans. The scene building module is used to build visual simulation scenes based on the 3D WebGIS engine and to realize weather effect simulation using GLSL shader technology; The visualization mapping module is used to visualize and simulate emergency resources and emergency plans in the visualization simulation scenario; The real-time simulation module is used to receive event parameters input by the user, call the intelligent generation model of the contingency plan to obtain the emergency plan, and complete the dynamic simulation of the entire process from the occurrence of the event to the completion of the handling in the visualized simulation scenario.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the intelligent road emergency response plan simulation method as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent road emergency response plan simulation method as described in any one of claims 1 to 7.

Images