Disaster emergency rescue command system and method

Abstract

The invention discloses a disaster emergency rescue command system and method, and relates to the technical field of rescue command systems. Comprising an information collection module which collects information, including disaster situations, personnel distribution and environmental conditions, of a disaster site through sensors and communication equipment; the collected information is input into the system, so that accurate disaster assessment can be conveniently obtained; the decision support module determines optimal allocation of rescue resources by using a linear programming model according to disaster assessment provided by the information collection module, and plans a rescue path by using a graph theory algorithm; and the command control module is used for converting the rescue decision of the decision support module into a specific rescue instruction. According to the system, the disaster assessment time can be shortened through real-time monitoring and rapid data processing, and the rescue decision-making speed is increased; optimal configuration of resources is realized through an algorithm, resource waste is avoided, and resource availability at a critical moment is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of rescue command systems, and in particular to a disaster emergency rescue command system and method. Background Art

[0002] In the field of disaster emergency management, an effective rescue command system is crucial to ensuring rapid, orderly and efficient rescue operations; traditionally, disaster response relies on experience and improvisational decision-making, which often leads to uneven resource allocation, rescue delays and inefficiency.

[0003] With the development of science and technology, disaster emergency rescue work is increasingly relying on high-tech means. However, the existing rescue command system often has problems such as single function and low efficiency, which cannot meet the rescue needs in complex disaster environments.

[0004] After searching, the Chinese patent application number CN202111566534.7 discloses an integrated air-ground command and dispatch system for forest fire rescue, including the following contents: data support system: used to obtain the external data source required for the operation of this system; data fusion system: used to fuse the acquired external data source; joint command center: the joint command headquarters exchanges data with the command and dispatch decision system through the joint command center, and issues air-ground rescue command decisions; rescue site air command system: used to issue command decisions to aviation rescue forces, supervise aviation rescue forces to implement the rescue command decisions of the joint command center, and complete the real-time feedback of the fire situation at the fire site to the command and dispatch decision system, data fusion system and data support system. The command and dispatch system in the above patent has the following shortcomings: it cannot provide auxiliary decision-making functions and needs to be improved. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a disaster emergency rescue command system and method.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A disaster emergency rescue command system, comprising:

[0008] Information collection module: The information collection module collects information on the disaster site through various sensors and communication equipment, including the disaster situation, personnel distribution, and environmental conditions; the collected information is input into the system to obtain an accurate disaster assessment;

[0009] Decision support module: The decision support module uses a linear programming model to determine the optimal allocation of rescue resources based on the disaster assessment provided by the information collection module, and uses a graph theory algorithm to plan the rescue path;

[0010] Command and control module: The command and control module is used to convert the rescue decisions of the decision support module into specific rescue instructions and send them to rescuers; it also monitors the rescue progress and adjusts the rescue strategy in a timely manner;

[0011] Communication coordination module: The communication coordination module is used to establish and maintain the communication link between the rescue command system and the rescuers, ensuring the accurate transmission of rescue instructions and the real-time feedback of rescue information;

[0012] Logistics support module: The logistics support module is used to manage rescue resources; dynamically adjust resource allocation according to rescue needs to ensure the smooth progress of rescue work;

[0013] Data analysis module: The data analysis module analyzes the data generated during the rescue process to evaluate the rescue effect and improve the rescue strategy; uses machine learning algorithms to predict future disaster developments and uses statistical methods to evaluate rescue efficiency;

[0014] Risk Assessment and Prediction Module: The risk assessment and prediction module uses historical data and real-time data, combined with probability models and deep learning algorithms, to predict the type, time and impact range of disasters that may occur in the future; helping decision makers prepare in advance and take preventive measures;

[0015] Intelligent dispatch module: The intelligent dispatch module uses genetic algorithm or ant colony algorithm optimization algorithm to intelligently dispatch the actions of the rescue team; it automatically adjusts the route and task allocation of the rescue team according to the real-time situation to maximize efficiency and response speed;

[0016] Virtual training module: The virtual training module uses virtual reality technology to provide rescue personnel with a simulated rescue environment so that they can become familiar with various possible disaster scenarios and response strategies before actual operations.

[0017] Preferably: the information collection module includes:

[0018] Real-time monitoring unit, using ground sensors, drones and satellite image technology to monitor the environmental conditions, disaster spread speed and impact range of the disaster area in real time; based on image analysis and pattern recognition technology, to assess the disaster situation at the early stage of the disaster;

[0019] Data transmission unit, which transmits the collected data to the command center; it adopts multi-channel transmission technology and is based on data compression and error correction algorithms to improve transmission efficiency and accuracy;

[0020] The data preprocessing unit preprocesses the collected data, including cleaning, standardization and preliminary analysis; by using data mining technology and machine learning algorithms, useful information is extracted from large amounts of messy data to provide a basis for subsequent decision support.

[0021] Preferably: the decision support module includes:

[0022] Disaster Assessment Unit: Conduct in-depth analysis and assessment of the disaster situation based on the data provided by the information collection module; use Markov chain models or fuzzy logic to simulate the development trend and possible impact of the disaster situation;

[0023] Resource optimization unit: optimize the allocation of rescue resources; by establishing an optimization model for resource allocation and using particle swarm algorithm to solve it, find the optimal resource allocation plan under the current disaster situation;

[0024] Rescue Path Planning Unit: used to plan the best path for the rescue team; by analyzing the terrain, road conditions and disaster distribution in the disaster area, using graph theory algorithms and heuristic search algorithms to plan a safe and efficient rescue path;

[0025] Emergency plan generation unit: Automatically generates targeted emergency plans based on disaster assessment and other relevant information; including the configuration of rescue teams, allocation of materials and evacuation plans, etc., to provide guidance and reference for rescue operations.

[0026] Preferably, when the disaster assessment unit performs the assessment, the development trend of the disaster is simulated by a Markov chain model, which is specifically the following formula:

[0027] P(X t+1 =s′|X t =s) = P s,s′

[0028] Among them, X t represents the disaster status at time t, p s，s′ is the transition probability from state s to state s′; the dynamics of the system is based on X t+1 =M·X t Calculate, M is the transition matrix, which contains the probabilities of transitions between possible states.

[0029] Preferably, the rescue path planning unit plans the rescue path through a graph theory algorithm, specifically:

[0030] In a graph G = (V, E), where V is the set of vertices, E is the set of edges, and each edge e∈E has weight w e Representing for example or time, the graph theory algorithm finds the shortest path from a source point s to all other points; for each vertex v∈V, a distance estimate is maintained and updated by the following steps:

[0031] Initialize d v , and all other d v =∞;

[0032] For all v∈V, set prevv ∈None;

[0033] For each vertex u adjacent to s, set d u =w s，u ;

[0034] For each vertex v∈V, do the following:

[0035] Find the unprocessed vertex u with the minimum distance estimate;

[0036] Mark u as processed; for each vertex v adjacent to u, if d u +w u，v <d v , then update d v =d u +w u，v , and set prev v =u;

[0037] Finally, v It is the length of the shortest path from s to v.

[0038] Preferably: the command and control module includes:

[0039] Rescue instruction issuing unit: converts the rescue decision generated by the decision support module into specific instructions and sends them to rescuers through the communication coordination module; the instructions include detailed information such as rescue target, path, timetable and resource allocation;

[0040] Progress monitoring unit: monitors the rescue progress and on-site conditions in real time, compares data with the information collection module, promptly understands the actual effect of the rescue operation, and provides feedback to decision makers;

[0041] Strategy adjustment unit: automatically or manually adjusts the rescue strategy based on the feedback from the progress monitoring unit and other real-time information; by using adaptive algorithms and machine learning technology, it can ensure that the rescue strategy always conforms to the actual situation and maximizes the rescue efficiency;

[0042] Logging unit: records detailed logs of all rescue activities, including command issuance, execution status, time consumption and resource use;

[0043] The communication coordination module comprises:

[0044] Information encryption and decryption unit: encrypts and decrypts transmitted information to ensure the security of sensitive information; based on encryption algorithms and dynamic key management technology, prevents information from being intercepted or tampered with during transmission;

[0045] Voice and video communication unit: Provides voice and video communication services, enabling rescuers and commanders to communicate and coordinate in real time; supports multi-party conferencing and real-time video streaming;

[0046] Message push unit: responsible for pushing important notifications and instructions to rescuers;

[0047] The logistics support module includes:

[0048] Resource Inventory Management Unit: manages and tracks all rescue resources, including supplies, equipment and personnel; based on database management system and Internet of Things technology, monitors the usage status and location of resources in real time to ensure efficient use of resources;

[0049] Transport Scheduling Unit: used to plan and manage the transport routes and schedules of relief supplies;

[0050] Maintenance and repair unit: used to perform regular maintenance and data collection on rescue equipment to ensure the normal operation of the equipment; based on the equipment status monitoring system and remote diagnosis technology, discover and solve potential problems.

[0051] Preferably: the data analysis module includes:

[0052] Performance Evaluation Unit: Quantitatively evaluate the performance of rescue operations and analyze the effectiveness of rescue operations by comparing the actual results with the expected goals; use statistical analysis methods and data visualization techniques to present the evaluation results;

[0053] Trend Analysis Unit: Analyze the long-term trends and pattern changes of rescue data, predict the possible development of disasters and rescue needs in the future; use time series analysis and machine learning algorithms to reveal the regularity behind the data;

[0054] Feedback Learning Unit: Collect feedback from rescuers and victims and use it to improve future rescue strategies; continuously optimize the rescue process and improve the quality of rescue by establishing a feedback loop mechanism and using adaptive learning algorithms;

[0055] The risk assessment and prediction module includes:

[0056] Disaster Simulation Unit: This unit uses computer simulation technology to reconstruct disaster scenarios and predict their possible development trends; creating three-dimensional disaster models by combining geographic information systems (GIS) and high-performance computing resources;

[0057] Probability calculation unit: This unit is responsible for calculating the probability of various disasters and the size of potential risks; performing probability inference and risk assessment based on statistical methods and Bayesian networks;

[0058] Early warning system unit: automatically sends early warning signals to potentially affected areas and populations based on risk assessment results and other relevant information;

[0059] Risk Map Generation Unit: Generates detailed risk maps to guide rescue operations and urban planning; used to display disaster risk levels in different areas, locations of critical infrastructure, and evacuation route information.

[0060] Preferably: the intelligent scheduling module includes:

[0061] Team management unit: responsible for managing the information of all teams involved in the rescue, including the team members' professional skills and equipment; quickly finding and deploying appropriate rescue teams through the team database and application classification algorithms;

[0062] Task allocation unit: automatically allocates tasks to rescue teams based on the severity of the disaster and the team's capabilities; ensures fairness and efficiency of task allocation based on optimization algorithms such as ant colony algorithms;

[0063] Route Optimization Unit: Optimizes the rescue team's route to avoid congested areas and dangerous areas; updates route instructions in real time by collecting real-time traffic data and applying dynamic routing algorithms;

[0064] The task allocation unit selects a path based on the ant colony algorithm by pheromone concentration, and optimizes the path selection by global and local pheromone update rules; the basic formula for pheromone update is:

[0065]

[0066] in, and are the new and old pheromone concentrations on the path, ρ is the pheromone evaporation rate, is the amount of pheromone left by the kth item (kth ant) ​​on the path in the previous step.

[0067] Preferably: the virtual training module includes:

[0068] Environmental simulation unit: Generates virtual environment for rescue personnel to train; uses 3D modeling technology and graphics rendering algorithms to create the environment;

[0069] Mission editing unit: provides customization of various rescue missions and scenarios to test and improve the response capabilities of rescuers;

[0070] Interactive Feedback Unit: Provides immediate feedback and evaluation functions to guide rescuers on how to improve their skills during training; provides personalized advice and guidance by collecting performance data, decision tree algorithms, and application evaluation algorithms;

[0071] Skills testing unit: evaluates rescuers’ skill level and training effectiveness through testing procedures;

[0072] The interactive feedback unit is based on a decision tree algorithm, where each branch represents a prediction result and each node represents a judgment condition for a feature. Through the path from the root node to the leaf node of the tree, specific classification rules are obtained to provide customized explanations and suggestions for individual performance data. The data is segmented by recursively selecting the best features to minimize the impurity metric. For classification problems, impurity is defined as:

[0073]

[0074] Among them, G(t) is the Gini impurity of node t, C is the number of categories, and p i is the probability of the i-th class sample in node t;

[0075] The partition attribute is selected by information gain, and the calculation formula is:

[0076]

[0077] Where IG(T, X, a) is the information gain of attribute X on value a, H(T) is the entropy of set T, V(X, a) is the partition of attribute X on value a, and T v is the set of samples in partition v.

[0078] Preferably, the command method of the disaster emergency rescue command system comprises the following steps:

[0079] S1: The information collection module collects information on the disaster site through various sensors and communication devices;

[0080] S2: The decision support module uses a linear programming model to determine the optimal allocation of rescue resources based on the disaster assessment provided by the information collection module, and uses a graph theory algorithm to plan the rescue path;

[0081] S3: The command and control module is used to convert the rescue decision of the decision support module into specific rescue instructions and send them to the rescuers;

[0082] S4: Rescuers carry out rescue missions according to rescue instructions;

[0083] S5: The intelligent dispatch module conducts real-time intelligent dispatch of the rescue team’s actions;

[0084] S6: Rescuers communicate and cooperate in a timely manner based on the communication coordination module to complete the rescue mission.

[0085] The beneficial effects of the present invention are:

[0086] 1. The system of the present invention, real-time monitoring and rapid data processing can shorten the disaster assessment time and speed up the rescue decision-making; the algorithm can achieve the optimal allocation of resources, avoid resource waste, and ensure the availability of resources at critical moments.

[0087] 2. The system of the present invention reduces the time and cost expenditure in rescue operations based on intelligent scheduling and path planning, and improves the overall rescue efficiency; encryption technology and dynamic key management ensure the secure transmission of sensitive information and prevent information leakage.

[0088] 3. In the system of the present invention, the virtual training module provides a simulated environment so that rescue personnel can become familiar with various disaster scenarios before actual operations and improve their practical capabilities; the risk assessment and prediction module helps to identify potential risks in advance, take preventive measures, and reduce the impact of disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 The present invention provides a flow chart of a disaster emergency rescue command method. DETAILED DESCRIPTION

[0090] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.

[0091] Embodiment 1:

[0092] A disaster emergency rescue command system, comprising:

[0093] Information collection module: The information collection module collects information on the disaster site through various sensors and communication equipment, including the disaster situation, personnel distribution, and environmental conditions; the collected information is input into the system to obtain an accurate disaster assessment;

[0094] Decision support module: The decision support module uses a linear programming model to determine the optimal allocation of rescue resources based on the disaster assessment provided by the information collection module, and uses a graph theory algorithm to plan the rescue path;

[0095] Command and control module: The command and control module is used to convert the rescue decisions of the decision support module into specific rescue instructions and send them to rescuers; it also monitors the rescue progress and adjusts the rescue strategy in a timely manner;

[0096] Communication coordination module: The communication coordination module is used to establish and maintain the communication link between the rescue command system and the rescuers, ensuring the accurate transmission of rescue instructions and the real-time feedback of rescue information;

[0097] Logistics support module: The logistics support module is used to manage rescue resources, including personnel, equipment, materials, etc.; dynamically adjust resource allocation according to rescue needs to ensure the smooth progress of rescue work;

[0098] Data analysis module: The data analysis module analyzes the data generated during the rescue process to evaluate the rescue effect and improve the rescue strategy; uses machine learning algorithms to predict future disaster developments and uses statistical methods to evaluate rescue efficiency;

[0099] Risk Assessment and Prediction Module: The risk assessment and prediction module uses historical data and real-time data, combined with probability models and deep learning algorithms, to predict the type, time and impact range of disasters that may occur in the future; helping decision makers prepare in advance and take preventive measures;

[0100] Intelligent dispatch module: The intelligent dispatch module uses optimization algorithms such as genetic algorithm or ant colony algorithm to intelligently dispatch the actions of the rescue team; it automatically adjusts the routes and task allocation of the rescue team according to the real-time situation to maximize efficiency and response speed;

[0101] Virtual training module: The virtual training module uses virtual reality technology to provide rescue personnel with a simulated rescue environment so that they can become familiar with various possible disaster scenarios and response strategies before actual operations.

[0102] Wherein, the information collection module includes:

[0103] Real-time monitoring unit, using ground sensors, drones and satellite image technology to monitor the environmental conditions, disaster spread speed and impact range of the disaster area in real time; based on image analysis and pattern recognition technology, to assess the disaster situation at the early stage of the disaster;

[0104] Data transmission unit, which transmits the collected data to the command center; it adopts multi-channel transmission technology and is based on data compression and error correction algorithms to improve transmission efficiency and accuracy;

[0105] The data preprocessing unit preprocesses the collected data, including cleaning, standardization and preliminary analysis; by using data mining technology and machine learning algorithms, useful information is extracted from large amounts of messy data to provide a basis for subsequent decision support.

[0106] Wherein, the decision support module includes:

[0107] Disaster Assessment Unit: Conduct in-depth analysis and assessment of the disaster situation based on the data provided by the information collection module; use Markov chain models or fuzzy logic to simulate the development trend and possible impact of the disaster situation;

[0108] Resource optimization unit: optimize the allocation of rescue resources; by establishing an optimization model for resource allocation and using particle swarm algorithm to solve it, find the optimal resource allocation plan under the current disaster situation;

[0109] Rescue Path Planning Unit: used to plan the best path for the rescue team; by analyzing the terrain, road conditions and disaster distribution in the disaster area, using graph theory algorithms and heuristic search algorithms to plan a safe and efficient rescue path;

[0110] Emergency plan generation unit: Automatically generates targeted emergency plans based on disaster assessment and other relevant information; including the configuration of rescue teams, allocation of materials and evacuation plans, etc., to provide guidance and reference for rescue operations.

[0111] When the disaster assessment unit performs the assessment, the development trend of the disaster is simulated by the Markov chain model, which is specifically the following formula:

[0112] P(X t+1 =s′|X t =s) = p s,s′

[0113] Among them, X t represents the disaster status at time t, p s，s′ is the transition probability from state s to state s′; the dynamics of the system is based on X t+1 =M·X t Calculate, M is the transition matrix, which contains the probabilities of transitions between possible states.

[0114] The rescue path planning unit plans the rescue path through a graph theory algorithm, specifically:

[0115] In a graph G = (V, E), where V is the set of vertices, E is the set of edges, and each edge e∈E has weight w e Representing for example or time, the graph theory algorithm finds the shortest path from a source point s to all other points; for each vertex v∈V, a distance estimate is maintained and updated by the following steps:

[0116] Initialize d v , and all other d v =∞;

[0117] For all v∈V, set prev v ∈None;

[0118] For each vertex u adjacent to s, set d u =w s，u ;

[0119] For each vertex v∈V, do the following:

[0120] Find the unprocessed vertex u with the minimum distance estimate;

[0121] Mark u as processed; for each vertex v adjacent to u, if d u+w u，v <d v , then update d v =d u +w u，v , and set prev v =u;

[0122] Finally, v It is the length of the shortest path from s to v.

[0123] Wherein, the command and control module includes:

[0124] Rescue instruction issuing unit: converts the rescue decision generated by the decision support module into specific instructions and sends them to rescuers through the communication coordination module; the instructions include detailed information such as rescue target, path, timetable and resource allocation;

[0125] Progress monitoring unit: monitors the rescue progress and on-site conditions in real time, compares data with the information collection module, promptly understands the actual effect of the rescue operation, and provides feedback to decision makers;

[0126] Strategy adjustment unit: automatically or manually adjusts the rescue strategy based on the feedback from the progress monitoring unit and other real-time information; by using adaptive algorithms and machine learning technology, it can ensure that the rescue strategy always conforms to the actual situation and maximizes the rescue efficiency;

[0127] Logging unit: records detailed logs of all rescue activities, including command issuance, execution status, time consumption and resource usage.

[0128] Wherein, the communication coordination module includes:

[0129] Information encryption and decryption unit: encrypts and decrypts transmitted information to ensure the security of sensitive information; based on encryption algorithms and dynamic key management technology, prevents information from being intercepted or tampered with during transmission;

[0130] Voice and video communication unit: Provides voice and video communication services, enabling rescuers and commanders to communicate and coordinate in real time; supports multi-party conferencing and real-time video streaming;

[0131] Message push unit: responsible for pushing important notifications and instructions to rescuers.

[0132] Wherein, the logistics support module includes:

[0133] Resource Inventory Management Unit: manages and tracks all rescue resources, including supplies, equipment and personnel; based on database management system and Internet of Things technology, monitors the usage status and location of resources in real time to ensure efficient use of resources;

[0134] Transport Scheduling Unit: used to plan and manage the transport routes and schedules of relief supplies;

[0135] Maintenance and repair unit: used to perform regular maintenance and data collection on rescue equipment to ensure the normal operation of the equipment; based on the equipment status monitoring system and remote diagnosis technology, discover and solve potential problems.

[0136] Wherein, the data analysis module includes:

[0137] Performance Evaluation Unit: Quantitatively evaluate the performance of rescue operations and analyze the effectiveness of rescue operations by comparing the actual results with the expected goals; use statistical analysis methods and data visualization techniques to present the evaluation results;

[0138] Trend Analysis Unit: Analyze the long-term trends and pattern changes of rescue data, predict the possible development of disasters and rescue needs in the future; use time series analysis and machine learning algorithms to reveal the regularity behind the data;

[0139] Feedback Learning Unit: Collect feedback from rescuers and victims and use it to improve future rescue strategies; continuously optimize the rescue process and improve the quality of rescue by establishing a feedback loop mechanism and using adaptive learning algorithms.

[0140] Wherein, the risk assessment and prediction module includes:

[0141] Disaster Simulation Unit: This unit uses computer simulation technology to reconstruct disaster scenarios and predict their possible development trends; creating three-dimensional disaster models by combining geographic information systems (GIS) and high-performance computing resources;

[0142] Probability calculation unit: This unit is responsible for calculating the probability of various disasters and the size of potential risks; performing probability inference and risk assessment based on statistical methods and Bayesian networks;

[0143] Early warning system unit: automatically sends early warning signals to potentially affected areas and populations based on risk assessment results and other relevant information;

[0144] Risk Map Generation Unit: Generates detailed risk maps to guide rescue operations and urban planning; used to display disaster risk levels in different areas, locations of critical infrastructure, and evacuation route information.

[0145] Wherein, the intelligent scheduling module includes:

[0146] Team management unit: responsible for managing the information of all teams involved in the rescue, including the team members' professional skills and equipment; quickly finding and deploying appropriate rescue teams through the team database and application classification algorithms;

[0147] Task allocation unit: automatically allocates tasks to rescue teams based on the severity of the disaster and the team's capabilities; ensures fairness and efficiency of task allocation based on optimization algorithms such as ant colony algorithms;

[0148] Route Optimization Unit: Optimizes the rescue team's route to avoid congested areas and dangerous zones; updates route instructions in real time by collecting real-time traffic data and applying dynamic routing algorithms.

[0149] The task allocation unit selects the path based on the ant colony algorithm by pheromone concentration, and optimizes the path selection by global and local pheromone update rules; the basic formula for pheromone update is:

[0150]

[0151] in, and are the new and old pheromone concentrations on the path, ρ is the pheromone evaporation rate, is the amount of pheromone left by the kth item (kth ant) ​​on the path in the previous step.

[0152] Wherein, the virtual training module includes:

[0153] Environmental simulation unit: Generates virtual environment for rescue personnel to train; uses 3D modeling technology and graphics rendering algorithms to create the environment;

[0154] Mission editing unit: provides customization of various rescue missions and scenarios to test and improve the response capabilities of rescuers;

[0155] Interactive Feedback Unit: Provides immediate feedback and evaluation functions to guide rescuers on how to improve their skills during training; provides personalized advice and guidance by collecting performance data, decision tree algorithms, and application evaluation algorithms;

[0156] Skill Testing Unit: Evaluate the skill level and training effectiveness of rescuers through testing procedures.

[0157] Embodiment 2:

[0158] A disaster emergency rescue command system and method, this embodiment is based on embodiment 1:

[0159] The interactive feedback unit is based on a decision tree algorithm, where each branch represents a prediction result and each node represents a judgment condition for a feature. Through the path from the root node to the leaf node of the tree, specific classification rules are obtained to provide customized explanations and suggestions for individual performance data. The data is segmented by recursively selecting the best features to minimize the impurity metric. For classification problems, impurity is defined as:

[0160]

[0161] Among them, G(t) is the Gini impurity of node t, C is the number of categories, and p i is the probability of the i-th class sample in node t;

[0162] The partition attribute is selected by information gain, and the calculation formula is:

[0163]

[0164] Where IG(T, X, a) is the information gain of attribute X on value a, H(T) is the entropy of set T, V(X, a) is the partition of attribute X on value a, and T v is the set of samples in partition v.

[0165] Embodiment 3:

[0166] A disaster emergency rescue command method comprises the following steps:

[0167] S1: The information collection module collects information on the disaster site through various sensors and communication devices;

[0168] S2: The decision support module uses a linear programming model to determine the optimal allocation of rescue resources based on the disaster assessment provided by the information collection module, and uses a graph theory algorithm to plan the rescue path;

[0169] S3: The command and control module is used to convert the rescue decision of the decision support module into specific rescue instructions and send them to the rescuers;

[0170] S4: Rescuers carry out rescue missions according to rescue instructions;

[0171] S5: The intelligent dispatch module conducts real-time intelligent dispatch of the rescue team’s actions;

[0172] S6: Rescuers communicate and cooperate in a timely manner based on the communication coordination module to complete the rescue mission.

[0173] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A disaster emergency rescue command system, characterized in that: include: Information collection module: The information collection module collects information on the disaster site through various sensors and communication equipment, including the disaster situation, personnel distribution, and environmental conditions; The collected information is input into the system to obtain accurate disaster assessment; Decision support module: The decision support module uses a linear programming model to determine the optimal allocation of rescue resources based on the disaster assessment provided by the information collection module, and uses a graph theory algorithm to plan the rescue path; Command and control module: The command and control module is used to convert the rescue decisions of the decision support module into specific rescue instructions and send them to rescuers; it also monitors the rescue progress and adjusts the rescue strategy in a timely manner; Communication coordination module: The communication coordination module is used to establish and maintain the communication link between the rescue command system and the rescuers, ensuring the accurate transmission of rescue instructions and the real-time feedback of rescue information; Logistics support module: The logistics support module is used to manage rescue resources; dynamically adjust resource allocation according to rescue needs to ensure the smooth progress of rescue work; Data analysis module: The data analysis module analyzes the data generated during the rescue process to evaluate the rescue effect and improve the rescue strategy; Use machine learning algorithms to predict future disaster developments and statistical methods to evaluate rescue efficiency; Risk Assessment and Prediction Module: The risk assessment and prediction module uses historical data and real-time data, combined with probability models and deep learning algorithms, to predict the type, time and impact range of disasters that may occur in the future; helping decision makers prepare in advance and take preventive measures; Intelligent dispatch module: The intelligent dispatch module uses genetic algorithm or ant colony algorithm optimization algorithm to intelligently dispatch the actions of the rescue team; it automatically adjusts the routes and task allocation of the rescue team according to the real-time situation to maximize efficiency and response speed; Virtual training module: The virtual training module uses virtual reality technology to provide rescue personnel with a simulated rescue environment so that they can become familiar with various possible disaster scenarios and response strategies before actual operations.

2. A disaster emergency rescue command system according to claim 1, characterized in that: The information collection module includes: Real-time monitoring unit, using ground sensors, drones and satellite image technology to monitor the environmental conditions, disaster spread speed and impact range of the disaster area in real time; based on image analysis and pattern recognition technology, to assess the disaster situation at the early stage of the disaster; Data transmission unit, which transmits the collected data to the command center; it adopts multi-channel transmission technology and is based on data compression and error correction algorithms to improve transmission efficiency and accuracy; The data preprocessing unit preprocesses the collected data, including cleaning, standardization and preliminary analysis; by using data mining technology and machine learning algorithms, useful information is extracted from large amounts of messy data to provide a basis for subsequent decision support.

3. A disaster emergency rescue command system according to claim 1, characterized in that: The decision support module includes: Disaster Assessment Unit: Conduct in-depth analysis and assessment of the disaster situation based on the data provided by the information collection module; use Markov chain models or fuzzy logic to simulate the development trend and possible impact of the disaster situation; Resource optimization unit: optimize the allocation of rescue resources; by establishing an optimization model for resource allocation and using particle swarm algorithm to solve it, find the optimal resource allocation plan under the current disaster situation; Rescue Path Planning Unit: used to plan the best path for the rescue team; by analyzing the terrain, road conditions and disaster distribution in the disaster area, using graph theory algorithms and heuristic search algorithms to plan a safe and efficient rescue path; Emergency plan generation unit: Automatically generates targeted emergency plans based on disaster assessment and other relevant information; including the configuration of rescue teams, allocation of materials and evacuation plans, etc., to provide guidance and reference for rescue operations.

4. A disaster emergency rescue command system according to claim 3, characterized in that: When the disaster assessment unit performs the assessment, the development trend of the disaster is simulated by the Markov chain model, which is specifically the following formula: P(X t+1 =s′|X t =s)=P s,s′ Among them, X t represents the disaster status at time t, p s，s′ is the transition probability from state s to state s′; the dynamics of the system is based on X t+1 =M·X t Calculate, M is the transition matrix, which contains the probabilities of transitions between possible states.

5. A disaster emergency rescue command system according to claim 4, characterized in that: The rescue path planning unit plans the rescue path through a graph theory algorithm, specifically: In a graph G = (V, E), where V is the set of vertices, E is the set of edges, and each edge e∈E has weight w e Representing for example or time, the graph theory algorithm finds the shortest path from a source point s to all other points; for each vertex v∈V, a distance estimate is maintained and updated by the following steps: Initialize d v , and all other d v =∞; For all v∈V, set prev v ∈None; For each vertex u adjacent to s, set d u =w s，u ; For each vertex v∈V, do the following: Find the unprocessed vertex u with the minimum distance estimate; Mark u as processed; for each vertex v adjacent to u, if d u +w u，v <d v , then update d v =d u +w u，v , and set prev v =u; Finally, v It is the length of the shortest path from s to v.

6. A disaster emergency rescue command system according to claim 1, characterized in that: The command and control module includes: Rescue instruction issuing unit: converts the rescue decision generated by the decision support module into specific instructions and sends them to rescuers through the communication coordination module; the instructions include detailed information such as rescue target, path, timetable and resource allocation; Progress monitoring unit: monitors the rescue progress and on-site conditions in real time, compares data with the information collection module, promptly understands the actual effect of the rescue operation, and provides feedback to decision makers; Strategy adjustment unit: automatically or manually adjusts the rescue strategy based on the feedback from the progress monitoring unit and other real-time information; by using adaptive algorithms and machine learning technology, it can ensure that the rescue strategy always conforms to the actual situation and maximizes the rescue efficiency; Logging unit: records detailed logs of all rescue activities, including command issuance, execution status, time consumption and resource use; The communication coordination module comprises: Information encryption and decryption unit: encrypts and decrypts transmitted information to ensure the security of sensitive information; based on encryption algorithms and dynamic key management technology, prevents information from being intercepted or tampered with during transmission; Voice and video communication unit: Provides voice and video communication services, enabling rescuers and commanders to communicate and coordinate in real time; supports multi-party conferencing and real-time video streaming; Message push unit: responsible for pushing important notifications and instructions to rescuers; The logistics support module includes: Resource Inventory Management Unit: manages and tracks all rescue resources, including supplies, equipment and personnel; based on database management system and Internet of Things technology, monitors the usage status and location of resources in real time to ensure efficient use of resources; Transport Scheduling Unit: used to plan and manage the transport routes and schedules of relief supplies; Maintenance and repair unit: used to perform regular maintenance and data collection on rescue equipment to ensure the normal operation of the equipment; based on the equipment status monitoring system and remote diagnosis technology, discover and solve potential problems.

7. A disaster emergency rescue command system according to claim 1, characterized in that: The data analysis module includes: Performance Evaluation Unit: Quantitatively evaluate the performance of rescue operations and analyze the effectiveness of rescue operations by comparing the actual results with the expected goals; use statistical analysis methods and data visualization techniques to present the evaluation results; Trend Analysis Unit: Analyze the long-term trends and pattern changes of rescue data, predict the possible development of disasters and rescue needs in the future; use time series analysis and machine learning algorithms to reveal the regularity behind the data; Feedback Learning Unit: Collect feedback from rescuers and victims and use it to improve future rescue strategies; continuously optimize the rescue process and improve the quality of rescue by establishing a feedback loop mechanism and using adaptive learning algorithms; The risk assessment and prediction module includes: Disaster Simulation Unit: This unit uses computer simulation technology to reconstruct disaster scenarios and predict their possible development trends; creating three-dimensional disaster models by combining geographic information systems (GIS) and high-performance computing resources; Probability calculation unit: This unit is responsible for calculating the probability of various disasters and the size of potential risks; performing probability inference and risk assessment based on statistical methods and Bayesian networks; Early warning system unit: automatically sends early warning signals to potentially affected areas and populations based on risk assessment results and other relevant information; Risk Map Generation Unit: Generates detailed risk maps to guide rescue operations and urban planning; used to display disaster risk levels in different areas, locations of critical infrastructure, and evacuation route information.

8. A disaster emergency rescue command system according to claim 1, characterized in that: The intelligent scheduling module includes: Team management unit: responsible for managing the information of all teams involved in the rescue, including the team members' professional skills and equipment; quickly finding and deploying appropriate rescue teams through the team database and application classification algorithms; Task allocation unit: automatically allocates tasks to rescue teams based on the severity of the disaster and the team's capabilities; ensures fairness and efficiency of task allocation based on optimization algorithms such as ant colony algorithms; Route Optimization Unit: Optimizes the rescue team's route to avoid congested areas and dangerous areas; updates route instructions in real time by collecting real-time traffic data and applying dynamic routing algorithms; The task allocation unit selects a path based on the ant colony algorithm by pheromone concentration, and optimizes the path selection by global and local pheromone update rules; the basic formula for pheromone update is: in, and are the new and old pheromone concentrations on the path, ρ is the pheromone evaporation rate, is the amount of pheromone left by the kth item (kth ant) ​​on the path in the previous step.

9. A disaster emergency rescue command system according to claim 1, characterized in that: The virtual training module includes: Environmental simulation unit: Generates virtual environment for rescue personnel to train; uses 3D modeling technology and graphics rendering algorithms to create the environment; Mission editing unit: provides customization of various rescue missions and scenarios to test and improve the response capabilities of rescuers; Interactive Feedback Unit: Provides immediate feedback and evaluation functions to guide rescuers on how to improve their skills during training; provides personalized advice and guidance by collecting performance data, decision tree algorithms, and application evaluation algorithms; Skills testing unit: evaluates rescuers’ skill level and training effectiveness through testing procedures; The interactive feedback unit is based on a decision tree algorithm, where each branch represents a prediction result and each node represents a judgment condition for a feature. Through the path from the root node to the leaf node of the tree, specific classification rules are obtained to provide customized explanations and suggestions for individual performance data. The data is segmented by recursively selecting the best features to minimize the impurity metric. For classification problems, impurity is defined as: Among them, G(t) is the Gini impurity of node t, C is the number of categories, and p i is the probability of the i-th class sample in node t; The partition attribute is selected by information gain, and the calculation formula is: Where IG(T, X, a) is the information gain of attribute X on value a, H(T) is the entropy of set T, V(X, a) is the partition of attribute X on value a, and T v is the set of samples in partition v.

10. A disaster emergency rescue command system according to claim 1, characterized in that: The command method of the disaster emergency rescue command system comprises the following steps: S1: The information collection module collects information on the disaster site through various sensors and communication devices; S2: The decision support module uses a linear programming model to determine the optimal allocation of rescue resources based on the disaster assessment provided by the information collection module, and uses a graph theory algorithm to plan the rescue path; S3: The command and control module is used to convert the rescue decision of the decision support module into specific rescue instructions and send them to the rescuers; S4: Rescuers carry out rescue missions according to rescue instructions; S5: The intelligent dispatch module conducts real-time intelligent dispatch of the rescue team’s actions; S6: Rescuers communicate and cooperate in a timely manner based on the communication coordination module to complete the rescue mission.

Images