Emergency plan management method for emergency events, and emergency linkage control method and system

Abstract

Provided in the present application are an emergency plan management method for emergency events, and an emergency linkage control method and system. The emergency plan management method for emergency events comprises the steps of: acquiring on-site monitoring data of historical emergency events and corresponding emergency plans thereof; performing structured processing on the emergency plans, decomposing the emergency plans into a plurality of minimum executable units having a clear sequential execution order, and according to the types, severities and impact scopes of the emergency events, classifying the emergency plans into different levels, so as to establish an emergency plan database; and each time an emergency event occurs, recording on-site monitoring data, an executed final emergency plan and actual rescue decision-making data, and by means of a machine learning algorithm, learning the on-site monitoring data and the actual rescue decision-making data of the emergency event, so as to update and optimize the emergency plan database.

Description

Emergency response plan management methods, emergency response control methods and systems

[0001] This application claims priority to Chinese Patent Application No. 202411505208.9, filed with the Chinese Patent Office on October 28, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application belongs to the field of data processing technology, and relates to emergency response plan processing technology for sudden events, and in particular to an emergency response plan management method, emergency linkage control method and system. Background Technology

[0003] During the operation of highway tunnels, in the event of emergencies (such as fires, accidents, or congestion during periods of heavy traffic or inclement weather), secondary accidents are highly likely to occur if emergency plans are not activated promptly. The consequences of secondary accidents are far more severe than those of the primary accident. Emergency plans, as pre-established action plans, aim to ensure a rapid and effective response when emergencies occur. The advantage of emergency plans lies in their clear definition of the responsibilities and response procedures of all parties involved, and the preparation of emergency resources. This guides rapid, efficient, and orderly emergency rescue operations, minimizing personal injury, property damage, and environmental impact. Therefore, emergency plans play a crucial role in the operation of highway tunnels.

[0004] However, fixed emergency plans also have some limitations in practical application. Emergencies are highly unpredictable and constantly changing; the specific circumstances and changing factors of each event may differ. Therefore, fixed emergency plans often cannot be updated and adjusted in a timely manner when faced with real-time changes in emergencies, resulting in a lag in content.

[0005] In summary, while existing emergency plans play an important guiding role in emergency management, they are clearly insufficient in terms of flexibility and real-time response to emergencies. Summary of the Invention

[0006] To address at least one deficiency in the existing technology, this application provides a method for managing emergency response plans, an emergency linkage control method, and a system for handling sudden events.

[0007] The first aspect of this application provides a method for managing emergency response plans for sudden events, including the following steps:

[0008] Data acquisition steps: Acquire historical on-site monitoring data of emergencies and their corresponding emergency response plans;

[0009] Data processing steps: The emergency plan is structured and decomposed into multiple smallest executable units with a clear execution order. Different levels of emergency plans are classified according to the type, severity, and scope of impact of the emergency, forming an emergency plan database.

[0010] Update steps: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and the actual rescue decision data to update and optimize the emergency plan database.

[0011] In some embodiments of the first aspect, during the data processing step, the emergency response plan is divided into four categories based on the type of emergency: fire, earthquake, chemical leak, and traffic accident.

[0012] In some embodiments of the first aspect, in the data processing step, the emergency response plan is divided into four levels according to the severity and scope of the emergency, with the first-level emergency response plan corresponding to the most severe and extensive emergency, and the fourth-level emergency response plan corresponding to the least severe and extensive emergency; the activation conditions and response procedures of each level of emergency response plan are clearly defined to ensure that the corresponding level of emergency response plan can be activated quickly in an emergency.

[0013] The second aspect of this application provides an emergency response control method based on big data analysis-assisted decision-making, comprising the following steps:

[0014] Emergency response plan database construction steps: Based on historical on-site monitoring data of emergencies and their corresponding emergency response plans, establish the characteristics of emergencies and their corresponding emergency response plans to form an emergency response plan database, and update and optimize the emergency response plan database through machine learning algorithms;

[0015] Prediction model construction steps: Construct an emergency prediction model using the on-site monitoring data of the emergency as input and the accident characteristics of the emergency as output. Divide the on-site monitoring data of the emergency into a training set and a test set. Train the emergency prediction model using the training set and verify the trained emergency prediction model using the test set. The accident characteristics of the emergency include the time of the emergency, the location of the emergency, the type of the emergency, and the level of the emergency.

[0016] Prediction steps: Input real-time monitoring data of the emergency site into the emergency prediction model to predict the characteristics of the emergency;

[0017] Decision-making steps: Based on the predicted characteristics of the emergency incident, search the emergency plan database for emergency plans that match the characteristics of the emergency incident, and select the best matching emergency plan as the final emergency plan.

[0018] Emergency procedures: Control and implement the final emergency plan;

[0019] Update steps: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and the actual rescue decision data to update and optimize the emergency plan database.

[0020] In some embodiments of the second aspect, the emergency response plan database construction step includes the following steps:

[0021] Data acquisition steps: Acquire the on-site monitoring data of the historical emergencies and their corresponding emergency plans;

[0022] Data processing steps: The emergency plan is structured and decomposed into multiple smallest executable units with a clear execution order. Different levels of emergency plans are classified according to the type, severity, and scope of impact of the emergency, forming the emergency plan database.

[0023] Update steps: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and the actual rescue decision data to update and optimize the emergency plan database.

[0024] In some embodiments of the second aspect, updating and optimizing the emergency plan database in the update step includes: adjusting the order of the minimum executable units, adding or removing certain minimum executable units, and modifying the content of the minimum executable units.

[0025] In some embodiments of the second aspect, during the emergency response steps, when controlling the execution of the final emergency plan, the emergency plan is executed according to a preset control strategy based on the type of the emergency. The methods for controlling the execution of the emergency plan include automatic joint control, manual joint control, and delayed start joint control. The automatic joint control automatically executes the smallest executable unit in the emergency plan according to the type of the emergency and the preset control strategy. The manual joint control manually controls the execution of the smallest executable unit in the emergency plan according to the type of the emergency and the preset control strategy. The delayed start joint control delays the execution of the smallest executable unit in the emergency plan according to the type of the emergency and the preset control strategy.

[0026] A third aspect of this application provides an emergency response control system based on big data analysis-assisted decision-making, used to implement the emergency response control method based on big data analysis-assisted decision-making as described in any of the second aspects, comprising:

[0027] The data acquisition module is used to acquire historical on-site monitoring data of emergencies and their corresponding emergency plans;

[0028] The data monitoring system is used to monitor real-time data at the scene of an emergency.

[0029] The data processing module is used to perform structured processing on the emergency plan, decompose the emergency plan into multiple smallest executable units with a clear execution sequence, establish the relationship between each smallest executable unit, and classify emergency plans into different scenarios and levels according to the type, severity, and scope of impact of the emergency, forming an emergency plan database; and divide the historical emergency event on-site monitoring data into training set and test set;

[0030] The prediction model building module uses on-site monitoring data of emergencies as input and the characteristics of emergencies as output to build an emergency prediction model.

[0031] The training and validation module is used to train the emergency event prediction model using the training set and to validate the trained emergency event prediction model using the test set.

[0032] The prediction module inputs the real-time monitoring data of the emergency site into the emergency prediction model to predict the characteristics of the emergency.

[0033] The decision support module searches the emergency plan database for emergency plans that match the predicted characteristics of the emergency incident based on the predicted characteristics of the emergency incident, and outputs the most matching emergency plan as the final emergency plan.

[0034] The emergency control unit, in conjunction with the data monitoring system, controls the execution of the final emergency plan.

[0035] The update module records on-site monitoring data, the final emergency plan implemented, and actual rescue decision data for each emergency event. It also uses machine learning algorithms to learn from the on-site monitoring data and actual rescue decision data to update and optimize the emergency plan database.

[0036] In some embodiments of the third aspect, the data monitoring system includes any one or more combinations of a fire monitoring unit, a video monitoring unit, a traffic monitoring unit, a lighting monitoring unit, and a ventilation monitoring unit.

[0037] In some embodiments of the third aspect, the fire monitoring unit includes: a flame detector, installed on the top or side wall of the highway tunnel, for detecting flames inside the highway tunnel; a temperature detector, installed on the top or side wall of the highway tunnel, for detecting the temperature inside the highway tunnel; a smoke detector, installed on the top or side wall of the highway tunnel, for detecting the smoke concentration inside the highway tunnel; a fire alarm control module, used to determine whether an alarm needs to be issued or a fire extinguishing procedure needs to be initiated based on the signals detected by the flame detector, the temperature detector, and the smoke detector and preset conditions; a control panel, connected between the fire alarm control module and the gas extinguishing system, wherein when the fire alarm control module determines that a fire extinguishing procedure needs to be initiated, the control panel activates the gas extinguishing system to enable the gas extinguishing system to work and extinguish the fire; an alarm module, connected to the fire alarm control module, for issuing an alarm signal when the fire alarm control module determines that an alarm needs to be issued; and a fire graphics workstation, connected to the fire alarm control module, for graphically displaying fire information.

[0038] In some embodiments of the third aspect, the video surveillance unit includes: a network camera for acquiring video footage inside a highway tunnel; a network hard disk recorder for recording and storing video data; a video management server connected to the network camera and the network hard disk recorder for managing and controlling the video stream and automatically switching the monitoring screen, wherein the video management server is linked with other monitoring units in the data monitoring system; and a display module connected to the video management server for displaying the video footage.

[0039] In some embodiments of the third aspect, the traffic monitoring unit includes: a vehicle detector for real-time collection of traffic flow, vehicle speed, and vehicle type within the highway tunnel; an over-height detector for detecting over-height vehicles; a video analysis device connected to the vehicle detector and the over-height detector for converting the information detected by the vehicle detector and the over-height detector into traffic intelligence information, the traffic intelligence information including road condition information, guidance information, and speed limit reminder information; a display device connected to the video analysis device for displaying the traffic intelligence information; and an indicator device connected to the video analysis device for indicating lane usage and tunnel traffic status.

[0040] In some embodiments of the third aspect, the lighting monitoring unit includes: a light intensity detector for detecting the light intensity of ambient light; and a lighting control module for obtaining a brightness setting for the current environment through a machine learning algorithm based on the detected light intensity and a preset lighting standard, and adjusting the brightness of the lighting fixtures according to the brightness setting.

[0041] In some embodiments of the third aspect, the ventilation monitoring unit includes: a CO / VI detector, installed on the side wall of the highway tunnel, for detecting carbon monoxide (CO) concentration and visibility (VI); a wind speed and direction detector, for detecting wind speed and direction inside the highway tunnel; a fan, for increasing gas pressure inside the highway tunnel and discharging gas; and a ventilation control module, connected to the CO / VI detector, the wind speed and direction detector, and the fan, for controlling the operation of the fan according to the monitored CO concentration, visibility (VI), and ventilation requirements.

[0042] In some embodiments of the third aspect, the emergency control unit includes an emergency control module and a communication unit. The emergency control module is used to coordinate with the data monitoring system to control the execution of the final emergency plan and to control the communication unit to perform emergency communication.

[0043] In some embodiments of the third aspect, the emergency control module includes:

[0044] The automatic control module automatically executes the smallest executable unit in the emergency plan according to the preset control strategy based on the type of emergency.

[0045] The manual control module manually controls and executes the smallest executable unit in the emergency plan according to the preset control strategy based on the type of emergency.

[0046] The delayed start-up control module executes the smallest executable unit in the emergency plan according to the preset control strategy based on the type of emergency.

[0047] In some embodiments of the third aspect, the communication unit includes a wired broadcasting unit and a wired telephone unit; the wired broadcasting unit is used to issue emergency instructions and notices to relevant personnel at the scene of the emergency, and to dispatch and organize the evacuation of personnel and vehicles; the wired telephone unit is used to provide a communication network for emergency communication.

[0048] Compared to related technologies, the emergency response plan management method provided in this application structures the emergency response plan, decomposes it into multiple smallest executable units that are executed sequentially, and then classifies them into different levels of emergency response plans to form an emergency response plan database. This database is updated based on the actual situation of each emergency, ensuring that the emergency response plan is always synchronized with actual needs. This achieves electronic emergency response plans, optimizes the management of emergency response plans by scenario and level, provides effective handling guidance during emergency response, and improves the execution efficiency of emergency response plans in actual emergency handling processes.

[0049] Compared to related technologies, the emergency response and control method and system based on big data analysis-assisted decision-making provided in this application utilizes big data analysis technology to construct a prediction model for emergencies, accurately assess emergencies, select emergency plans from a timely updated emergency plan database, recommend the final emergency plan corresponding to the emergency to emergency personnel, assist in decision-making, and quickly and correctly link and control various systems to carry out emergency rescue work, thereby improving the flexibility and real-time nature of emergency response. Attached Figure Description

[0050] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0051] Figure 1 is a flowchart of the emergency response plan management method for sudden events described in an embodiment of this application;

[0052] Figure 2 is a flowchart of the update step performed using a machine learning algorithm in an embodiment of this application;

[0053] Figure 3 is a flowchart of the emergency response control method based on big data analysis-assisted decision-making according to an embodiment of this application;

[0054] Figure 4 is a structural block diagram of the emergency response control system based on big data analysis-assisted decision-making according to an embodiment of this application;

[0055] Figure 5 is a structural block diagram of the fire monitoring unit described in an embodiment of this application;

[0056] Figure 6 is a structural block diagram of the video surveillance unit described in an embodiment of this application;

[0057] Figure 7 is a structural block diagram of the traffic monitoring unit described in an embodiment of this application;

[0058] Figure 8 is a structural block diagram of the lighting monitoring unit described in an embodiment of this application;

[0059] Figure 9 is a structural block diagram of the ventilation monitoring unit described in an embodiment of this application;

[0060] Figure 10 is a structural block diagram of the emergency control unit described in an embodiment of this application;

[0061] Figure 11 is a structural block diagram of the computer device described in an embodiment of this application. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0063] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0064] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0065] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the objects before and after it are in an "or" relationship.

[0066] According to a first aspect of this application, an emergency response plan management method for sudden events is provided. Figure 1 is a flowchart of the emergency response plan management method for sudden events according to an embodiment of this application. As shown in Figure 1, the process includes the following steps:

[0067] S11. Data Acquisition Steps: Acquire historical on-site monitoring data of emergencies and their corresponding emergency plans. Specifically, on-site monitoring data includes fire data, environmental data, traffic data, and facility operational status data. Fire data includes, for example, smoke sensor data, temperature sensor data, and fire protection facility status data; environmental data includes, for example, air quality and meteorological data; traffic data includes, for example, traffic flow statistics, congestion conditions, and accident hotspots; facility operational status data includes, for example, facility structural safety status, maintenance records, operational status, and malfunctions. Based on the on-site monitoring data, the accident characteristics of emergencies can be established, thereby accurately identifying the type and level of emergencies. The emergency plans corresponding to the historical on-site monitoring data of emergencies refer to the emergency response measures taken after an emergency occurs, based on the on-site monitoring data and actual conditions, including evacuating people, activating fire protection systems, sealing off the accident area, providing emergency medical services, and repairing damaged facilities. By analyzing these emergency response measures, their effectiveness can be evaluated, and emergency plans for future emergencies can be optimized accordingly, providing matching emergency plans for subsequent similar or identical emergencies.

[0068] S12. Data processing steps: The emergency plan is structured and decomposed into multiple smallest executable units with a clear execution order. The relationship between each smallest executable unit is established. Emergency plans are classified into different levels according to the type, severity and scope of impact of the emergency, forming an emergency plan database.

[0069] It should be noted that the minimum executable unit (MINU) specifically refers to the smallest executable step in an emergency response plan. By structuring the emergency response plan, the description and execution standards of each MINU are standardized, facilitating accurate understanding and operation by emergency personnel. Each MINU is clearly defined, specific, and actionable, providing clear guidance for emergency personnel during execution. Logically sequencing the MINUs clarifies their execution order and establishes connections between them, ensuring smooth transitions during execution.

[0070] Specifically, emergency response plans are categorized into four types based on the type of emergency: fire, earthquake, chemical leak, and traffic accident. It should be noted that specific emergency response procedures are developed for each type of emergency response plan, including initial response, resource allocation, and on-site handling. Furthermore, historical emergencies are classified into different types according to the above criteria, and the steps in the actual rescue decision-making data corresponding to different types of historical emergencies are used as the emergency response procedures for the respective types.

[0071] Specifically, based on the severity and scope of the emergency, emergency response plans are divided into four levels. Level 1 emergency response plans correspond to the most severe and impactful emergencies, while Level 4 plans correspond to the least severe and impactful emergencies, with the severity and scope decreasing sequentially from Level 1 to Level 4. The activation conditions and response procedures for each level of emergency response plan are clearly defined to ensure rapid activation of the corresponding level in emergency situations. The assessment criteria for the severity and scope of an emergency include one or more of the following: casualties (e.g., number of deaths, number of injuries), property damage (e.g., direct economic losses, indirect economic losses), environmental impact (e.g., area of ​​pollution, degree of ecological damage), social impact (e.g., degree of public panic, degree of social disorder), and duration. The activation conditions for each level of emergency response plan are the threshold values ​​set according to the corresponding assessment criteria for the emergency level. When the threshold value set for the corresponding level is reached, the emergency response plan corresponding to that level is activated.

[0072] Specifically, in some embodiments, the severity and scope of the emergency response plan for Level 1 are as follows: causing 3 or more deaths; or fewer than 3 deaths and 5 or more serious injuries; or 10 or more serious injuries; or causing direct economic losses of 10 million yuan or more; or a vehicle collision in a tunnel or on an overpass, accompanied by fuel tank leakage and fire. The severity and scope of the emergency response plan for Level 2 are as follows: causing fewer than 3 deaths; or 3 to 10 serious injuries; or 10 or more minor injuries; or causing direct economic losses of 1 million yuan to 10 million yuan; or a continuous collision of 3 or more vehicles in a tunnel or on an overpass; or a collision of 2 or more vehicles accompanied by fuel tank leakage; or a vehicle fire. The severity and scope of the emergency response plan for Level 3 are as follows: causing fewer than 3 serious injuries; or 3 to 10 minor injuries; or causing direct economic losses of 100,000 yuan to 1 million yuan. The Level IV emergency response plan corresponds to the following levels of severity and impact of the emergency: causing minor injuries to fewer than 3 people; or causing direct economic losses of less than 100,000 yuan.

[0073] S13. Update steps: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and actual rescue decision data to update and optimize the emergency plan database.

[0074] Machine learning algorithms are used to learn emergency response plans, which are then updated and optimized in real time based on actual implementation. These updates and optimizations include adjusting the order of the smallest executable units (MINUs), adding or removing certain MINUs, and modifying the content of the MINUs. Through continuous updates and optimization, the emergency response plans are ensured to remain synchronized with reality, improving their flexibility and real-time performance in response to emergencies.

[0075] It's important to note that whenever an accident occurs, staff correct the accident information to ensure data accuracy. This corrected information includes key details such as the accident type, level, and environmental factors. Simultaneously, decisions made by staff during actual emergency response are recorded. Machine learning algorithms utilize this corrected accident information and actual rescue decision data for learning. These algorithms analyze accident characteristics, rescue outcomes, and the correlation between decisions and results. Over time and with data accumulation, the machine learning algorithms can identify which decisions are more effective in specific environments, thereby continuously optimizing emergency plans. Specifically, the machine learning algorithms update the accident information and emergency plans supporting decision-making based on each accident and its corresponding emergency response policy. This update is not a simple replacement but rather a fine-tuning or restructuring of existing emergency plans through machine learning algorithms to ensure that the emergency response plan better suits the actual situation and rescue needs.

[0076] Specifically, as shown in Figure 2, the above S13 update step includes:

[0077] S131 Data Extraction and Preprocessing Steps: Key information is extracted from historical emergency incident information, including: incident type (fire, earthquake, chemical leak, traffic accident), incident level (Level 1 to 4), environmental factors (weather, geographical location, traffic conditions, etc.), and actual rescue decisions (including specific action decisions, resource allocation, and deployment of rescue personnel). This key information is preprocessed, including noise removal, handling missing data, and converting the data into a format suitable for machine learning model input. Specific preprocessing methods can be found in existing technologies and will not be elaborated upon in this application.

[0078] S132 Steps for Selecting a Machine Learning Algorithm: Select a machine learning algorithm based on the complexity of the sudden incident and the characteristics of the data. The following is a brief introduction to several available machine learning algorithms; those skilled in the art can select the appropriate algorithm based on the specific circumstances.

[0079] (1) Decision Tree

[0080] Decision trees can be used to build a model that predicts optimal rescue decisions based on accident information. They find the optimal decision path by progressively splitting the dataset and are suitable for data with clearly defined decision nodes and outcomes. Decision tree algorithms can identify the factors that have the greatest impact on rescue decisions, thereby optimizing emergency response plans.

[0081] (2) Random Forest

[0082] Random forest is an ensemble method based on decision trees. It reduces the risk of overfitting of a single decision tree by building multiple decision trees and improves the accuracy of predictions. It is suitable for complex and multidimensional data, has high accuracy, and is robust to outliers.

[0083] (3) Support Vector Machine (SVM)

[0084] Support Vector Machines (SVMs) are powerful classification algorithms that can handle high-dimensional data and nonlinear problems. By selecting an appropriate kernel function, accident characteristics and emergency response decisions can be effectively classified.

[0085] (4) Deep Learning

[0086] For situations involving large amounts of data and complex nonlinear relationships, deep neural networks (such as fully connected neural networks and convolutional neural networks) can better capture the hidden features in the data, have strong fitting capabilities, and are suitable for complex pattern recognition, such as automatically learning the correlation between rescue decisions and accident features from a large amount of historical data.

[0087] Step S133: Model Training and Validation. The data obtained in step S131 is used to train and validate the machine learning model selected in step S132. During model training, historical accident data is divided into training and test sets according to a set ratio (e.g., 80% training, 20% test; other ratios may be used as needed). The selected machine learning model is trained using the training set, and hyperparameters are adjusted. During model validation, the trained model is validated using test set data, evaluating its accuracy, recall, F1-score, and other metrics. The analysis results from the machine learning model can yield the optimal rescue decision-making strategy for each accident type and environmental factor, which can be used to update and optimize the emergency response plan database.

[0088] In the S13 update step, the database update methods include the following two:

[0089] Fine-tuning decision rules: Adjusting the decision rules in the emergency plan based on the decision weights output by the machine learning model. For example, if a certain type of accident requires the deployment of more rescue personnel under specific weather conditions, the corresponding decision tree can update the resource allocation recommendations for that part.

[0090] New emergency response plan generation: New emergency response plans are generated through machine learning models to optimize decision-making processes, reduce response time, or improve rescue efficiency.

[0091] The emergency response plan management method described in this application digitizes the emergency response plan, manages it by scenario and level, and updates and optimizes it based on actual implementation through machine learning algorithms. This provides effective emergency response during emergency handling, assists emergency personnel in decision-making, and improves the flexibility and real-time nature of emergency response.

[0092] A second aspect of this application provides an emergency response control method based on big data analysis-assisted decision-making. Figure 3 is a flowchart of the emergency response control method based on big data analysis-assisted decision-making according to an embodiment of this application. The following will describe each step of the control method in detail with reference to Figure 3.

[0093] S21: Emergency plan database construction steps: Based on historical emergency monitoring data and corresponding emergency plans, establish emergency accident characteristics and corresponding emergency plans to form an emergency plan database, and update and optimize the emergency plan database through machine learning algorithms; for specific methods, refer to the emergency plan management method for emergencies provided in any embodiment of the first aspect of this application.

[0094] S22. Prediction model construction steps: Construct an emergency prediction model using emergency on-site monitoring data as input and emergency accident characteristics as output. Divide the emergency on-site monitoring data into a training set and a test set. Train the emergency prediction model using the training set and verify the trained emergency prediction model using the test set. The emergency accident characteristics include emergency time, emergency location, emergency type, and emergency level.

[0095] The emergency prediction model we have built can accurately identify emergencies and obtain more realistic rescue needs.

[0096] S23. Prediction Steps: Input real-time monitoring data of the emergency site into the emergency prediction model to predict the characteristics of the emergency.

[0097] S24. Decision-making steps: Based on the predicted characteristics of the emergency, search the emergency plan database for emergency plans that match the characteristics of the emergency, and select the best matching emergency plan as the final emergency plan.

[0098] S25. Emergency Procedures: Control and implement the final emergency plan.

[0099] Specifically, when controlling the execution of the final emergency plan, the emergency plan is executed according to the type of emergency and a preset control strategy. The methods for controlling the execution of the emergency plan include automatic linkage, manual linkage, and delayed activation linkage. The preset control strategy is configured based on different emergency types, directions, and start and end station numbers. Here, direction refers to the direction of vehicle travel; station number represents the mileage within the tunnel, for example, 1800 meters from the tunnel entrance to the exit is represented by station number k1+800. For different emergency types, control strategies are formulated, specifying under what circumstances which equipment actions are triggered, and setting control strategies for various equipment, including activation, deactivation, and parameter adjustment. For example, when the emergency type is a fire, the preset control strategy activates the fire extinguishing system, turns on the smoke extraction equipment, and issues evacuation instructions through the broadcast system. Users can select the appropriate linkage method to control the execution of the emergency plan for different emergency types.

[0100] Specifically, automatic control is the smallest executable unit in an emergency plan that automatically executes according to a preset control strategy based on the type of emergency. In other words, when preset control conditions are met (e.g., smoke or high temperature is detected), the preset control strategy is automatically triggered to execute the corresponding emergency plan without human intervention. For example, in the event of a fire, fire extinguishing devices and smoke extraction equipment are automatically activated.

[0101] Specifically, manual control refers to the manual execution of the smallest executable unit in an emergency plan according to a preset control strategy based on the type of emergency. It should be noted that manual control is suitable for scenarios requiring manual confirmation or intervention under special circumstances. For example, after confirming that a fire has been extinguished, the operator can manually shut down the fire suppression system.

[0102] Delayed start-up control is the smallest executable unit in an emergency plan that executes the response according to a preset control strategy based on the type of emergency. It should be noted that the activation of certain devices or systems requires a delay to avoid accidental operation or to coordinate with the actions of other equipment. For example, after a fire alarm, it may be necessary to first broadcast evacuation instructions, then delay for a few seconds before activating the fire suppression system to ensure sufficient time for evacuation. Delayed start-up is achieved by setting a timer or conditional trigger.

[0103] S26. Update Step: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and actual rescue decision data to update and optimize the emergency plan database. For details, refer to step S13 of the emergency plan management method provided in the first aspect of this application.

[0104] The emergency response and control method based on big data analysis-assisted decision-making described in this application utilizes big data analysis technology to construct a prediction model for emergencies, accurately assess emergencies, select emergency plans from a timely updated emergency plan database, recommend the final emergency plan corresponding to the emergency to emergency personnel, assist in decision-making, and quickly and correctly coordinate and control various systems to carry out emergency rescue work, thereby improving the flexibility and real-time nature of emergency response.

[0105] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0106] A third aspect of this application provides an emergency response control system based on big data analysis-assisted decision-making, used to implement the emergency response control method based on big data analysis-assisted decision-making described in the second aspect of this application. Figure 4 is a structural block diagram of the emergency response control system based on big data analysis-assisted decision-making according to an embodiment of this application. The emergency response control system based on big data analysis-assisted decision-making includes:

[0107] Data acquisition module 1 is used to acquire historical on-site monitoring data of emergencies and their corresponding emergency plans; specifically, data acquisition module 1 can be a data input interface, such as a network data interface or a mobile storage device interface.

[0108] Data monitoring system 2 is used to monitor environmental data, traffic data, and facility operation status data at the scene of emergencies in real time;

[0109] Data processing module 3 is used to perform structured processing on the emergency plans acquired by data acquisition module 1, decompose the emergency plans into multiple smallest executable units with a clear execution order, establish the relationship between each smallest executable unit, and classify emergency plans into different scenarios and levels according to the type, severity and scope of impact of the emergency, forming an emergency plan database; and divide the on-site monitoring data of historical emergencies into training sets and test sets.

[0110] Prediction model building module 4 uses the on-site monitoring data of the emergency obtained by data acquisition module 1 as input and the accident characteristics of the emergency as output to build an emergency prediction model;

[0111] Training and validation module 5 is used to train the emergency event prediction model using the training set and to validate the trained emergency event prediction model using the test set.

[0112] Prediction module 6 inputs real-time monitoring data from the emergency site into the emergency prediction model to predict the characteristics of the emergency.

[0113] The decision support module 7 searches the emergency plan database for emergency plans that match the predicted characteristics of the emergency incident based on the predicted characteristics of the emergency incident, and outputs the most matching emergency plan as the final emergency plan.

[0114] Emergency control unit 8, linked with data monitoring system 2, controls the execution of the final emergency plan;

[0115] Module 9 is updated to record on-site monitoring data, the final emergency plan implemented, and actual rescue decision data for each emergency. It also uses machine learning algorithms to learn from the on-site monitoring data and actual rescue decision data to update and optimize the emergency plan database.

[0116] It is understood that the above-mentioned emergency response control system also includes a memory 101 and at least one processor 102. The data acquired by the data acquisition module 1 and the emergency plan database are stored in the memory 101. The processor 102 is used to execute the following program modules stored in the memory 101: data processing module 3, prediction model construction module 4, training and verification module 5, prediction module 6, decision support module 7, and update module 9, so as to implement the emergency response control method based on big data analysis for decision support as described in any embodiment of the second aspect of this application.

[0117] Specifically, the data monitoring system 2 includes any one or more of the following: fire monitoring unit 21, video monitoring unit 22, traffic monitoring unit 23, lighting monitoring unit 24, and ventilation monitoring unit 25.

[0118] The following describes an embodiment of the fire monitoring unit with reference to Figure 5.

[0119] In some embodiments, the fire monitoring unit 21 includes a flame detector 211, a temperature detector 212, a smoke detector 213, a fire alarm control module 214, a control panel 215, an alarm module 216, and a fire graphics workstation 217. The fire alarm control module 214 connects to the flame detector 211, temperature detector 212, smoke detector 213, control panel 214, alarm module 215, and fire graphics workstation 216. It is used to determine whether an alarm needs to be issued or a fire extinguishing procedure needs to be initiated based on the signals detected by the flame detector 211, temperature detector 212, and smoke detector 213 and preset conditions, and sends control signals to the control panel 215 and alarm module 216 to control their operation. Specifically, the fire alarm control module 214 can be a fire alarm controller.

[0120] Flame detectors are installed on the top or side walls of highway tunnels to detect flames inside the tunnels. Specifically, in one embodiment, the flame detector is a dual-wavelength flame detector. The flame detector sends the detected flame signal to the fire alarm control module, which generates an alarm control signal and sends it to the alarm module to activate the alarm.

[0121] Temperature detectors are installed on the top or side walls of highway tunnels to detect the temperature inside the tunnels. Specifically, in some embodiments, distributed temperature-sensing fiber optic detectors are used. The temperature detectors send the detected temperature signals to the fire alarm control module. When the detected temperature inside the highway tunnel reaches a preset threshold, the fire alarm control module generates an alarm control signal and sends it to the alarm module to activate the alarm.

[0122] Smoke detectors are installed on the top or side walls of highway tunnels to detect the smoke concentration inside. Specifically, in some embodiments, photoelectric smoke detectors are used. The smoke detectors send the detected smoke concentration signal to the fire alarm control module. When the smoke concentration in the highway tunnel reaches a preset threshold, the fire alarm control module generates an alarm control signal and sends it to the alarm module to activate the alarm.

[0123] The control panel is connected between the fire alarm control module and the gas extinguishing system. When the fire alarm control module determines that the extinguishing procedure needs to be activated, it receives the extinguishing control signal sent by the fire alarm control module. The control panel then activates the gas extinguishing system according to the control signal, so that the gas extinguishing system can work to extinguish the fire.

[0124] The alarm module issues an alarm signal when the fire alarm control module determines that an alarm needs to be issued. Specifically, the fire alarm control module generates an alarm control signal when it determines that an alarm needs to be issued, controlling the alarm module to issue the alarm signal. In some embodiments, the alarm module includes a manual alarm button and an audible and visual alarm. The manual alarm button is manually triggered when personnel discover a fire, and the audible and visual alarm is activated upon receiving the alarm control signal, emitting audible and visual signals to remind personnel to evacuate.

[0125] The fire monitoring unit works as follows: when detectors in the tunnel detect flames, smoke, or abnormal temperatures, they immediately transmit signals to the fire alarm control module. The fire alarm control module determines the severity and location of the fire based on preset algorithms and logic, and then displays the relevant information on a fire graphics workstation. If it determines that a fire suppression procedure needs to be initiated, the fire alarm control module will activate the fire suppression system via the control panel. Simultaneously, it will control the audible and visual alarms to sound, reminding personnel to evacuate promptly.

[0126] The fire graphics workstation is connected to the fire alarm control module and is used for graphically displaying fire information. The fire graphics workstation provides an intuitive graphical interface to display fire information, helping the operator quickly identify the location of the fire source and the fire situation.

[0127] The embodiments of the video surveillance unit will be described below in conjunction with FIG. 6.

[0128] In some embodiments, the video surveillance unit 22 includes a network camera 221, a network digital video recorder 222, a video management server 223, and a display module 224.

[0129] The network camera is used to obtain video images inside the highway tunnel. In some embodiments, the network camera adopts a high-definition network camera, and the real-time high-definition video of the monitoring area is captured in real time through the network camera, ensuring the clarity and detail display of the images.

[0130] In some embodiments, the video signal collected by the network camera is converted into an optical signal through the signal transmission and conversion module 225 for long-distance and high-speed transmission, and the receiving end then converts the optical signal back into an electrical signal. This ensures the stability and anti-interference ability of the signal. Specifically, the signal transmission and conversion module adopts an EPON optical terminal.

[0131] In some embodiments, the signal transmission and conversion module 225 distributes the electrical signal to the video management server 223, the network digital video recorder 222, and the display module 224 through a video switch 226.

[0132] The network digital video recorder is used for recording and storing video data. The network digital video recorder can record and store video data continuously for 24 hours, ensuring the traceability of historical data.

[0133] In some embodiments, the network digital video recorder 222 sends the stored video data to the video recycling bin 227 for playback, which is convenient for post-event analysis and evidence collection.

[0134] The video management server is used for managing and controlling the video stream, automatically switching the monitoring screen, and the video management server is linked with other monitoring units in the data monitoring system. For example: in case of a fire, the video management server can automatically switch to the monitoring screen of the fire occurrence area. The video management server is linked with other monitoring units such as the fire monitoring unit to improve the response speed in case of an emergency.

[0135] The display module is connected to the video management server and is used for displaying video images. In some embodiments, the display module includes a color liquid crystal monitor and an ultra-narrow-edge liquid crystal splicing screen, and the color liquid crystal monitor and the ultra-narrow-edge liquid crystal splicing screen display the monitoring screen in real time, providing intuitive visual information for the monitoring personnel.

[0136] The following describes an embodiment of the traffic monitoring unit with reference to Figure 7.

[0137] In some embodiments, the traffic monitoring unit 23 includes a vehicle detector 231, an over-height detector 232, a video analysis device 233, a display device 234, and an indicator device 235.

[0138] Vehicle detectors are used to collect real-time data on traffic flow, speed, and vehicle type within highway tunnels.

[0139] The over-height detector is used to detect whether there are vehicles exceeding the height limit. Specifically, in some embodiments, the over-height detector has a built-in audible and visual alarm that can trigger an alarm.

[0140] A video analysis device, connected to the vehicle detector and the over-height detector, is used to convert the information detected by the vehicle detector and the over-height detector into traffic intelligence information, which includes road condition information, guidance information and speed limit reminder information.

[0141] In some embodiments, the video analytics device includes a video analytics processor, a video analytics server, a video analytics switch, and a video analytics workstation. The video analytics processor and video analytics server are responsible for receiving and processing video data from various monitoring points. The video analytics switch is responsible for the rapid exchange of data, ensuring smooth transmission of real-time information. The video analytics workstation is used by operators to analyze traffic conditions.

[0142] The display device is used to display traffic information. In some embodiments, the display device is a variable message sign, a variable guidance sign, and a variable speed limit sign. The variable message sign and variable guidance sign are located outside the highway tunnel to provide real-time traffic information and guidance information, while the variable speed limit sign is located inside the highway tunnel to provide real-time speed limit information.

[0143] The indicating device is used to indicate lane usage and tunnel accessibility. In some embodiments, the indicating device includes a lane indicator and a tunnel closure indicator, wherein the lane indicator indicates lane usage and the tunnel closure indicator indicates tunnel accessibility.

[0144] The traffic monitoring unit works as follows: First, vehicle detectors and height-over-limit detectors collect real-time vehicle information on the road, including traffic flow, speed, vehicle type, and the presence of vehicles exceeding height limits. This information is rapidly transmitted via a video analysis switch to a video analysis processor and server for processing. The analyzed data is transformed into valuable traffic intelligence, which is then disseminated to drivers in real-time through variable message signs, variable guidance signs, and variable speed limit signs to help them make informed driving decisions. Simultaneously, lane indicators and tunnel closure signs dynamically adjust their display content according to traffic conditions to ensure smooth and safe traffic flow. In emergencies, such as the detection of vehicles exceeding height limits or traffic congestion, the traffic monitoring unit immediately activates audible and visual alarms and disseminates emergency information through variable message signs, responding and handling emergencies as quickly as possible.

[0145] The following describes an embodiment of the lighting monitoring unit with reference to Figure 8.

[0146] In some embodiments, the lighting monitoring unit 24 includes a light intensity detector 241 and a lighting control module 242. The light intensity detector 241 monitors the intensity of ambient light. The light intensity detector 241 can be a light sensor, which acquires the current ambient light intensity value and transmits it to the lighting control module 242. The lighting control module 242 uses a machine learning algorithm to obtain a brightness setting for the current environment based on the monitored light intensity and a preset lighting standard, and adjusts the brightness of the lighting fixture 243 according to the brightness setting. The lighting control module can be implemented using a microcontroller, power regulation circuit, etc.

[0147] The lighting control unit employs advanced machine learning algorithms. These algorithms analyze ambient light intensity and lighting needs in real time, then automatically adjust the brightness of the lamps to achieve optimal lighting effects. This intelligent adjustment not only enhances lighting comfort and usability but also significantly improves energy efficiency, achieving the goals of energy conservation and emission reduction.

[0148] Specifically, the light intensity detector continuously monitors the intensity of ambient light and feeds this data back to the lighting control module. The lighting control module, using machine learning algorithms, intelligently calculates the most suitable brightness setting for the current environment based on the light intensity data and preset lighting standards. Then, the lighting control module automatically adjusts the brightness of the lighting fixtures to ensure uniform, comfortable, and energy-efficient lighting effects on-site. The method for automatically adjusting the brightness of lighting fixtures using machine learning algorithms includes the following steps:

[0149] S31 Data Collection and Preprocessing: The collected data includes ambient light intensity (light intensity measured by a light intensity detector, in Lux), time, preset lighting standards (usually the target brightness range), and luminaire brightness (the brightness of the lighting fixtures after adjustment or the power setting of the lighting fixtures); the data is standardized to ensure that data of different magnitudes can be balanced in the model.

[0150] Step S32: Select a machine learning algorithm based on the relationship between ambient light intensity and lighting brightness. For example, if the relationship between ambient light intensity and lighting brightness is complex, a random forest regression model can be chosen, which can effectively handle complex nonlinear relationships.

[0151] S33 Model Training and Evaluation Steps: Use historical data as input to train the model using the machine learning algorithm selected in step S32, and evaluate the trained model to ensure that the model can predict the appropriate lamp brightness under different environmental conditions.

[0152] S34 Real-time control steps: Input the real-time data collected in step S31 into the trained model to predict the appropriate light brightness, and transmit the predicted brightness value to the lighting fixtures through the lighting control module to adjust the brightness of the lighting fixtures.

[0153] S35 Feedback Step: If there is a deviation between the adjusted brightness and the preset lighting standard, the deviation will be fed back to the model for optimization.

[0154] The following describes an embodiment of the ventilation monitoring unit with reference to Figure 9.

[0155] In some embodiments, the ventilation monitoring unit 25 includes a CO / VI detector 251, a wind speed and direction detector 252, a fan 253, and a ventilation control module 254. The CO / VI detector 251 is installed on the sidewall of the highway tunnel and is used to detect the carbon monoxide (CO) concentration and visibility (VI). The wind speed and direction detector 252 is used to detect the wind speed and direction inside the highway tunnel. The fan 253 is used to increase the gas pressure inside the highway tunnel and exhaust gas. The ventilation control module 254 is used to control the operating status of the fan based on the monitored CO concentration, visibility (VI), and ventilation requirements.

[0156] The ventilation monitoring unit works as follows: It collects environmental data in real time through CO / VI detectors and wind speed and direction detectors. The ventilation control module determines the current air quality and ventilation needs, and adjusts the fan's operating status accordingly, such as starting, stopping, or adjusting the fan speed, to ensure that the on-site air quality is maintained at its optimal level. The functions of the ventilation control module can be implemented using a controller.

[0157] The following describes an embodiment of the emergency control unit 8 with reference to Figure 10.

[0158] In some embodiments, the emergency control unit 8 includes an emergency control module 81 and a communication unit 82. The emergency control module 81 is used to coordinate with the data monitoring system 2 to control the execution of the final emergency plan and to control the communication unit 82 to conduct emergency communication.

[0159] In some embodiments, the emergency control module 81 includes an automatic control module 811, a manual control module 812, and a delayed-start control module 813. The automatic control module 811 automatically executes the smallest executable unit in the emergency plan according to a preset control strategy based on the type of the emergency. The manual control module 812 manually controls the execution of the smallest executable unit in the emergency plan according to a preset control strategy based on the type of the emergency. The delayed-start control module 813 executes the smallest executable unit in the emergency plan after a delay according to a preset control strategy based on the type of the emergency. It is understood that the automatic control module 811, the manual control module 812, and the delayed-start control module 813 are stored in the memory 101 and executed by the processor 102 to respectively implement the above functions.

[0160] In some embodiments, the communication unit 82 includes a wired broadcasting unit 821 and a wired telephone unit 822; the wired broadcasting unit 821 is used to issue emergency instructions and notices to relevant personnel at the scene of an emergency, and to dispatch and organize the evacuation of personnel and vehicles; the wired telephone unit 822 is used to provide a communication network for emergency communication.

[0161] In some embodiments, the wired broadcast unit includes a broadcast server (integrating a network audio server and a speech synthesizer), a broadcast switch, a digital tuner, a broadcast control box, a microphone, a digital audio processor, a power amplifier unit, a fault detector, a field monitor, a monitor speaker, an Ethernet serial port server, a broadcast zone controller, a broadcast splitter box, and a speaker.

[0162] The broadcast server is used to manage broadcast content and allocate audio signals according to preset playlists or real-time needs.

[0163] Broadcast switches connect to broadcast servers via a network and are used to distribute audio signals allocated by the broadcast server to various broadcast areas.

[0164] The broadcast control box is used to control broadcast content and broadcast areas.

[0165] Microphones are used to record emergency information. Specifically, microphones include wireless microphones and broadcast microphones.

[0166] The digital audio processor is responsible for optimizing audio quality and ensuring the clarity of the broadcast.

[0167] The power amplifier unit (including the power controller and the power amplifier) ​​is used to amplify the audio signal to drive the speaker to cover a wider area.

[0168] Fault detectors and on-site monitors monitor the operational status of the wired broadcast unit in real time, ensuring its proper functioning during critical moments. Monitoring speakers allow operators to listen to the broadcast content, ensuring broadcast quality. An Ethernet serial server enables networked management of the wired broadcast unit, while broadcast zone control boxes and broadcast splitter boxes are used for precise control of broadcast content in different areas.

[0169] The speaker is used to play amplified audio signals.

[0170] The specific working principle of the wired broadcast unit is as follows: Under normal circumstances, the broadcast server distributes audio signals to various broadcast areas through a broadcast switch according to a preset playlist or real-time demand. When an emergency announcement needs to be made, operators can record emergency information through the broadcast control box, wireless microphone, or broadcast microphone. This information is optimized by a digital audio processor, amplified by a power controller and power amplifier, and finally broadcast through the speaker network. Simultaneously, fault detectors and on-site monitoring devices continuously monitor the status of the wired broadcast unit to ensure accurate information transmission. Throughout the process, an Ethernet serial server provides remote monitoring and management functions, making the wired broadcast unit more intelligent and efficient.

[0171] In some embodiments, a wired telephone unit includes a softswitch server, a network switch, a call center console, a recording device, a maintenance gateway workstation, an audio patch panel, a splitter, digital telephones, and emergency telephones. The softswitch server connects to other devices within the wired telephone unit via the network switch, enabling rapid data exchange and processing. The call center console serves as the operating interface for the wired telephone unit, providing intuitive call management and monitoring functions. The recording device records important call content for subsequent analysis and verification. The maintenance gateway workstation is responsible for the system's daily maintenance and troubleshooting, ensuring the continuous and stable operation of the wired telephone unit. The primary function of the wired telephone unit is to provide stable and reliable communication in alarm situations, disaster relief, and other special circumstances, ensuring that information reaches the emergency control unit quickly and accurately.

[0172] Compared to conventional wired telephone systems, wired telephone units are characterized by their high scalability and powerful emergency communication capabilities. The softswitch server, as the core of the system, not only provides flexible line configuration and expansion space but also ensures communication stability under extreme conditions. The network switch ensures high-speed data transmission and exchange, providing strong support for real-time communication. Regarding equipment connectivity, in the event of an emergency or special incident, the wired telephone unit can quickly activate emergency communication mode. Emergency telephones, as dedicated emergency communication equipment, can establish contact with the emergency control unit immediately, report the situation on site, and request support. Simultaneously, digital telephones also provide high-quality voice communication capabilities, ensuring accurate information transmission during critical moments such as disaster relief and rescue.

[0173] The working principle of the above-mentioned emergency response control system will be explained using a fire as an example.

[0174] S1. The system detects fire alarm information through the fire monitoring unit;

[0175] S2. The prediction module retrieves real-time video and traffic conditions near the fire location to assist emergency personnel in predicting the situation of emergencies.

[0176] S3. Emergency personnel determine and confirm the accident situation based on the predicted emergency situation;

[0177] S4. The minimum executable unit recommended by the auxiliary decision-making module to handle this accident situation is: (1) Turn on all nearby lights. (2) Turn on nearby fire extinguishers. (3) Control the front and rear traffic lights to prohibit pedestrians and vehicles from entering the scene. (4) Turn on the communication unit to broadcast the accident information.

[0178] S5. Emergency personnel will select the smallest executable unit one by one and control the implementation of the smallest executable unit through the emergency control module.

[0179] S6. Save the event process as data for subsequent machine learning optimization of emergency response plans.

[0180] The emergency response and control system based on big data analysis-assisted decision-making described in this application utilizes big data analysis technology to construct a prediction model for emergencies, accurately assess emergencies, select emergency plans from a timely updated emergency plan database, recommend the final emergency plan corresponding to the emergency to emergency personnel, assist in decision-making, and quickly and correctly link and control various systems to carry out emergency rescue work, thereby improving the flexibility and real-time nature of emergency response.

[0181] A fourth aspect of this application provides a computer device, as shown in FIG11, including at least one processor 102, a memory 101, and computer program instructions stored on the memory 101.

[0182] Specifically, the processor 102 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0183] Memory 101 may include a mass storage device for data or instructions. For example, and not limitingly, memory 101 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 101 may include removable or non-removable (or fixed) media. Where appropriate, memory 101 may be internal or external to a data processing device. In a particular embodiment, memory 101 is non-volatile memory. In a particular embodiment, memory 101 includes read-only memory (ROM) and random access memory (RAM).

[0184] The memory 101 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 102.

[0185] The processor 102 reads and executes computer program instructions stored in the memory 101 to implement the emergency response control method based on big data analysis-assisted decision-making in any of the embodiments of the second aspect described above.

[0186] In some embodiments, the computer device may further include a communication interface 103 and a bus 104. As shown in FIG8, the processor 102, memory 101, and communication interface 103 are connected through the bus 104 and communicate with each other.

[0187] The communication interface 103 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. The communication interface 103 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0188] Bus 104 includes hardware, software, or both, that couples components of a computer device together. Bus 104 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus.

[0189] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0190] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for managing emergency response plans for sudden incidents, characterized in that, Includes the following steps: Data acquisition steps: Acquire historical on-site monitoring data of emergencies and their corresponding emergency response plans; Data processing steps: The emergency plan is structured and decomposed into multiple smallest executable units with a clear execution order. Different levels of emergency plans are classified according to the type, severity, and scope of impact of the emergency, forming an emergency plan database. Update steps: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and the actual rescue decision data to update and optimize the emergency plan database.

2. The emergency response plan management method for sudden incidents as described in claim 1, characterized in that, In the data processing step, the emergency response plan is divided into four categories based on the type of emergency: fire, earthquake, chemical leak, and traffic accident.

3. The emergency response plan management method for sudden incidents as described in claim 1, characterized in that, In the data processing step, the emergency response plan is divided into four levels according to the severity and scope of the emergency. The level 1 emergency response plan corresponds to the most severe and impactful emergency, while the level 4 emergency response plan corresponds to the least severe and impactful emergency. The activation conditions and response procedures for each level of emergency response plan are clearly defined to ensure that the corresponding level of emergency response plan can be activated quickly in an emergency.

4. An emergency response control method based on big data analytics-assisted decision-making, characterized in that, Includes the following steps: Emergency response plan database construction steps: Based on historical on-site monitoring data of emergencies and their corresponding emergency response plans, establish the characteristics of emergencies and their corresponding emergency response plans to form an emergency response plan database, and update and optimize the emergency response plan database through machine learning algorithms; Prediction model construction steps: Construct an emergency prediction model using the on-site monitoring data of the emergency as input and the accident characteristics of the emergency as output. Divide the on-site monitoring data of the emergency into a training set and a test set. Train the emergency prediction model using the training set and verify the trained emergency prediction model using the test set. The accident characteristics of the emergency include the time of the emergency, the location of the emergency, the type of the emergency, and the level of the emergency. Prediction steps: Input real-time monitoring data of the emergency site into the emergency prediction model to predict the characteristics of the emergency; Decision-making steps: Based on the predicted characteristics of the emergency incident, search the emergency plan database for emergency plans that match the characteristics of the emergency incident, and select the best matching emergency plan as the final emergency plan. Emergency procedures: Control and implement the final emergency plan; Update steps: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and the actual rescue decision data to update and optimize the emergency plan database.

5. The emergency response control method according to claim 4, characterized in that, The steps for constructing the emergency response plan database include the following: Data acquisition steps: Acquire the on-site monitoring data of the historical emergencies and their corresponding emergency plans; Data processing steps: The emergency plan is structured and decomposed into multiple smallest executable units with a clear execution order. Different levels of emergency plans are classified according to the type, severity, and scope of impact of the emergency, forming the emergency plan database. Update steps: For each emergency, record the on-site monitoring data, the final emergency plan implemented, and the actual rescue decision data. Then, use machine learning algorithms to learn from the on-site monitoring data and the actual rescue decision data to update and optimize the emergency plan database.

6. The emergency response control method according to claim 5, characterized in that, In the update step, updating and optimizing the emergency plan database includes: adjusting the order of the minimum executable units, adding or removing certain minimum executable units, and modifying the content of the minimum executable units.

7. The emergency response control method as described in claim 5, characterized in that, In the emergency response steps, when controlling the execution of the final emergency plan, the emergency plan is executed according to a preset control strategy based on the type of emergency. The methods for controlling the execution of the emergency plan include automatic joint control, manual joint control, and delayed start joint control. The automatic joint control automatically executes the smallest executable unit in the emergency plan according to the type of emergency and the preset control strategy. The manual joint control manually controls the execution of the smallest executable unit in the emergency plan according to the type of emergency and the preset control strategy. The delayed start joint control delays the execution of the smallest executable unit in the emergency plan according to the type of emergency and the preset control strategy.

8. An emergency response control system based on big data analytics-assisted decision-making, used to implement the emergency response control method based on big data analytics-assisted decision-making as described in any one of claims 4-7, characterized in that, include: The data acquisition module is used to acquire historical on-site monitoring data of emergencies and their corresponding emergency plans; The data monitoring system is used to monitor real-time data at the scene of an emergency. The data processing module is used to perform structured processing on the emergency plan, decompose the emergency plan into multiple smallest executable units with a clear execution sequence, establish the relationship between each smallest executable unit, and classify emergency plans into different scenarios and levels according to the type, severity, and scope of impact of the emergency, forming an emergency plan database; and divide the historical emergency event on-site monitoring data into training set and test set; The prediction model building module uses on-site monitoring data of emergencies as input and the characteristics of emergencies as output to build an emergency prediction model. The training and validation module is used to train the emergency event prediction model using the training set and to validate the trained emergency event prediction model using the test set. The prediction module inputs the real-time monitoring data of the emergency site into the emergency prediction model to predict the characteristics of the emergency. The decision support module searches the emergency plan database for emergency plans that match the predicted characteristics of the emergency incident based on the predicted characteristics of the emergency incident, and outputs the most matching emergency plan as the final emergency plan. The emergency control unit, in conjunction with the data monitoring system, controls the execution of the final emergency plan. The update module records on-site monitoring data, the final emergency plan implemented, and actual rescue decision data for each emergency event. It also uses machine learning algorithms to learn from the on-site monitoring data and actual rescue decision data to update and optimize the emergency plan database.

9. The emergency response control system as described in claim 8, characterized in that, The data monitoring system includes any one or more of the following: fire monitoring unit, video monitoring unit, traffic monitoring unit, lighting monitoring unit, and ventilation monitoring unit.

10. The emergency response control system as described in claim 9, characterized in that, The fire monitoring unit includes: a flame detector, installed on the top or side wall of the highway tunnel to detect flames inside the tunnel; a temperature detector, installed on the top or side wall of the tunnel to detect the temperature inside the tunnel; a smoke detector, installed on the top or side wall of the tunnel to detect the smoke concentration inside the tunnel; a fire alarm control module, used to determine whether to issue an alarm or initiate a fire extinguishing procedure based on the signals detected by the flame detector, temperature detector, and smoke detector, and preset conditions; a control panel, connected between the fire alarm control module and the gas extinguishing system, which activates the gas extinguishing system to extinguish the fire when the fire alarm control module determines that a fire extinguishing procedure needs to be initiated; an alarm module, connected to the fire alarm control module, which issues an alarm signal when the fire alarm control module determines that an alarm needs to be issued; and a fire graphics workstation, connected to the fire alarm control module, used to graphically display fire information.

11. The emergency response control system as described in claim 9, characterized in that, The video surveillance unit includes: a network camera for acquiring video footage inside the highway tunnel; a network hard disk recorder for recording and storing video data; a video management server connected to the network camera and the network hard disk recorder for managing and controlling the video stream and automatically switching monitoring footage; the video management server is linked with other monitoring units in the data monitoring system; and a display module connected to the video management server for displaying the video footage.

12. The emergency response control system as described in claim 9, characterized in that: The traffic monitoring unit includes: a vehicle detector for real-time collection of traffic flow, speed, and vehicle type within the highway tunnel; an over-height detector for detecting over-height vehicles; a video analysis device connected to the vehicle detector and the over-height detector for converting the information detected by the vehicle detector and the over-height detector into traffic intelligence information, including road condition information, guidance information, and speed limit reminder information; a display device connected to the video analysis device for displaying the traffic intelligence information; and an indicator device connected to the video analysis device for indicating lane usage and tunnel traffic status.

13. The emergency linkage control system as described in claim 9, characterized in that: The lighting monitoring unit includes: a light intensity detector for detecting the light intensity of ambient light; and a lighting control module for obtaining the brightness setting of the current environment through a machine learning algorithm based on the detected light intensity and a preset lighting standard, and adjusting the brightness of the lighting fixtures according to the brightness setting.

14. The emergency response control system as described in claim 9, characterized in that: The ventilation monitoring unit includes: a CO / VI detector, installed on the side wall of the highway tunnel, for detecting carbon monoxide (CO) concentration and visibility (VI); a wind speed and direction detector, for detecting wind speed and direction inside the highway tunnel; a fan, for increasing gas pressure inside the highway tunnel and exhausting gas; and a ventilation control module, connected to the CO / VI detector, the wind speed and direction detector, and the fan, for controlling the operation of the fan based on the monitored CO concentration, visibility (VI), and ventilation requirements.

15. The emergency response control system as described in claim 8, characterized in that, The emergency control unit includes an emergency control module and a communication unit. The emergency control module is used to coordinate with the data monitoring system to control the execution of the final emergency plan and to control the communication unit to conduct emergency communication.

16. The emergency response control system as described in claim 15, characterized in that, The emergency control module includes: an automatic control module, which automatically executes the smallest executable unit in the emergency plan according to the type of emergency and a preset control strategy; a manual control module, which manually controls the execution of the smallest executable unit in the emergency plan according to the type of emergency and a preset control strategy; and a delayed start control module, which executes the smallest executable unit in the emergency plan after a delay according to the type of emergency and a preset control strategy.

17. The emergency response control system as described in claim 15, characterized in that, The communication unit includes a wired broadcasting unit and a wired telephone unit; the wired broadcasting unit is used to issue emergency instructions and notices to relevant personnel at the scene of the emergency, and to dispatch and organize the evacuation of personnel and vehicles; the wired telephone unit is used to provide a communication network for emergency communication.

Images