A disaster response intelligent command system and control method thereof

Abstract

This application discloses an intelligent command system and control method for disaster response, relating to the field of emergency response. The system includes: an environmental information collection module for acquiring environmental information of a target area; a disaster early warning module for acquiring the aforementioned environmental information and generating disaster early warning information based on the environmental information; an intelligent decision-making module for acquiring the aforementioned environmental information and generating emergency response instructions and resource management instructions based on the aforementioned environmental information; an emergency response module for acquiring the aforementioned emergency response instructions and generating an emergency response plan based on the aforementioned emergency response instructions; a resource management module for acquiring the aforementioned resource management instructions and generating a resource management plan based on the aforementioned resource management instructions; and a human information collection module for intelligent interaction with feedback personnel to acquire human information, which is used to correct the aforementioned emergency response instructions and resource management instructions.

Description

Technical Field

[0001] This specification relates to the field of emergency response; more specifically, this application relates to an intelligent command system for disaster response and its control method. Background Technology

[0002] In the context of today's rapid development of information technology, the high-speed growth of the social economy is also accompanied by the frequent occurrence of emergencies, which often result in serious casualties and economic losses. While relevant emergency command systems can integrate various data and uniformly dispatch and control terminals of different roles, the final emergency decisions are still largely made by personnel. This typically reduces the accuracy of risk assessment and the timeliness of contingency plan dissemination, easily leading to the expansion and spread of disasters.

[0003] Therefore, it is necessary to build a comprehensive emergency command system platform to improve the efficiency and speed of emergency event management. Summary of the Invention

[0004] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] Firstly, this application proposes a disaster response intelligent command system, the system comprising:

[0006] The environmental information collection module is used to acquire environmental information of the target area, including sensor information, satellite information and meteorological information, and send the environmental information to the disaster early warning module and the intelligent decision-making module.

[0007] The disaster early warning module is used to acquire the aforementioned environmental information and generate disaster early warning information based on the aforementioned environmental information. The disaster early warning module generates the aforementioned disaster early warning information based on a machine learning model.

[0008] The intelligent decision-making module is used to acquire the aforementioned environmental information and generate emergency response instructions and resource management instructions based on the aforementioned environmental information. The intelligent decision-making module generates the aforementioned emergency response instructions and resource management instructions based on Monte Carlo simulation, agent-based model, genetic algorithm and particle swarm optimization algorithm.

[0009] An emergency response module is used to obtain the aforementioned emergency response instructions and generate an emergency response plan based on the aforementioned emergency response instructions. The emergency response module generates the emergency response plan based on a rule engine and simulation results.

[0010] The resource management module is used to obtain the above-mentioned resource management instructions and generate a resource management scheme based on the above-mentioned resource management instructions. The above-mentioned resource management module generates the resource management scheme based on dynamic programming and heuristic algorithms.

[0011] The human information collection module is used to intelligently interact with the feedback personnel to obtain human information. This human information is used to correct the emergency response instructions and resource management instructions. The human information collection module completes the intelligent interaction with the feedback personnel based on a large language model.

[0012] Secondly, embodiments of this application also propose a control method for the disaster response intelligent command system described in the first aspect, comprising:

[0013] The environmental information collection module collects environmental information about the target area and sends the environmental information to the disaster early warning module and the intelligent decision-making module.

[0014] The aforementioned disaster early warning module generates the aforementioned disaster early warning information based on the aforementioned environmental information and through the aforementioned machine learning model.

[0015] The intelligent decision-making module controls the above-mentioned emergency response instructions and resource management instructions based on the above-mentioned environmental information through Monte Carlo simulation, agent-based model, genetic algorithm and particle swarm optimization algorithm.

[0016] The aforementioned emergency response module generates an emergency response plan based on the aforementioned emergency response instructions, using a rule engine and simulation results.

[0017] The aforementioned resource management module generates resource management schemes based on the aforementioned resource management instructions using dynamic programming and heuristic algorithms.

[0018] The aforementioned human information collection module obtains human information by completing intelligent interaction with feedback personnel based on a large language model.

[0019] The aforementioned emergency response instructions and resource management instructions were corrected using the manual information provided.

[0020] In one feasible implementation, the aforementioned disaster early warning module generates the disaster early warning information based on the aforementioned environmental information and through the aforementioned machine learning model, including:

[0021] The above environmental information is preprocessed to obtain preprocessed first environmental information, wherein the preprocessing operations include noise filtering, outlier detection and data smoothing.

[0022] The aforementioned first environmental information is input into the machine learning model corresponding to the disaster type to generate the aforementioned disaster early warning information corresponding to different disaster types.

[0023] In one feasible implementation, the aforementioned intelligent decision-making module generates the aforementioned emergency response instructions and resource management instructions based on the aforementioned environmental information through Monte Carlo simulation, agent-based models, genetic algorithms, and particle swarm optimization algorithms, including:

[0024] The above environmental information is preprocessed to obtain preprocessed second environmental information. The preprocessing operations include noise filtering, outlier detection, and data smoothing.

[0025] Monte Carlo simulation was used based on the preprocessed second environmental information to obtain simulation evaluation results of multiple possible response schemes;

[0026] Based on the preprocessed environmental information described above, an agent-based model is used to simulate the performance of each response participant in multiple possible response scenarios.

[0027] The above disaster early warning information is generated based on the above simulation evaluation results and the above simulation performance results;

[0028] Based on the aforementioned second environmental information and available resource information, a population of initialization resource allocation schemes and a population of initialization examples are randomly generated.

[0029] Based on the above initial resource allocation scheme, the population is subjected to multiple iterations using a genetic algorithm to obtain preliminary optimization results.

[0030] Based on the above preliminary optimization results and the above initial example group, multiple iterations are performed using the particle swarm optimization algorithm to obtain the final optimization results.

[0031] The resource management instructions are generated based on the final optimization results.

[0032] In one feasible implementation, the aforementioned control emergency response module generates an emergency response plan based on the aforementioned emergency response instructions through a rule engine and simulation results, including:

[0033] The above emergency response instructions are processed using a rule engine to obtain an optimized emergency response plan.

[0034] The optimized emergency response plan was simulated using a disaster response simulation tool to obtain simulation results.

[0035] An emergency response plan is generated based on the simulation results and optimization suggestions from the rule engine.

[0036] In one feasible implementation, the aforementioned control resource management module generates a resource management scheme based on the aforementioned resource management instructions using dynamic programming and heuristic algorithms, including:

[0037] Based on the above resource management instructions, the dynamic programming method is applied to the resource knowledge graph to plan the dynamic programming results of the resources. The resource knowledge graph stores information on resource type, location, dependency relationship, historical usage efficiency and emergency response strategy.

[0038] Based on the dynamic programming results above, resource allocation is further optimized using the particle swarm optimization algorithm to obtain the aforementioned resource management scheme.

[0039] In one feasible implementation, the large language model includes an embedding layer, a Transformer encoding layer, an output layer, and auxiliary components. The Transformer encoding layer includes multiple Transformer units, the output layer includes multiple fully connected layers and an activation function, wherein the activation function is a softmax activation function, the auxiliary components include a Dropout layer and a Layer Normalization layer, and the optimizer of the large language model is an Adam optimizer.

[0040] In one feasible implementation, the above-mentioned modification of the emergency response instructions and resource management instructions using the aforementioned human information includes:

[0041] The authenticity of the aforementioned human-generated information is evaluated based on expert evaluation methods and intelligent evaluation models in order to obtain effective human-generated information.

[0042] Based on the aforementioned valid human information, the above emergency response instructions and resource management instructions were revised.

[0043] In one feasible implementation, the above-mentioned evaluation of the authenticity of the human-made information based on expert evaluation methods and intelligent evaluation models to obtain valid human-made information includes:

[0044] Obtain the identity of the person who reported the information;

[0045] A preliminary authenticity score is determined based on the identity of the reporter mentioned above;

[0046] The above-mentioned manual information is preprocessed to obtain key information;

[0047] The aforementioned key information was sent to the expert review unit to obtain an expert authenticity score through expert evaluation.

[0048] Send the above key information to the above intelligent evaluation model to obtain the model's authenticity score;

[0049] Obtain the first weight corresponding to the above expert authenticity scores;

[0050] Obtain the second weight corresponding to the above model's authenticity score;

[0051] The final authenticity is determined based on the above preliminary authenticity score, the above expert authenticity score, the above first weight, the above model authenticity score, and the above second weight;

[0052] The above-mentioned valid human information is determined based on the final authenticity and authenticity assessment threshold.

[0053] In one feasible implementation, the first weight information is negatively correlated with the disaster level, the second weight information is positively correlated with the disaster level, the first weight information is negatively correlated with the disaster occurrence time, and the second weight information is positively correlated with the disaster occurrence event.

[0054] The aforementioned authenticity assessment threshold is positively correlated with the aforementioned disaster level, and the aforementioned authenticity assessment threshold is negatively correlated with the aforementioned disaster occurrence time.

[0055] In summary, the disaster response intelligent command system of this application utilizes an environmental information collection module to automatically collect key data from multiple sources (such as sensors, satellites, and weather stations) to obtain real-time information on environmental changes in the target area. This real-time data acquisition and transmission significantly improves the speed and accuracy of disaster early warning, enabling emergency response to be initiated in the early stages of disaster formation, greatly reducing potential losses and impacts. The intelligent decision-making module integrates various advanced algorithms such as Monte Carlo simulation, agent-based models, genetic algorithms, and particle swarm optimization algorithms, enabling it to comprehensively consider various situations and variables, and simulate and evaluate different emergency response and resource allocation schemes. This not only enhances the scientific nature of decision-making but also ensures the most effective decisions are made in complex and ever-changing disaster environments. The resource management module dynamically adjusts resource allocation through dynamic programming and heuristic algorithms to optimize resource utilization efficiency. This ensures that limited resources can be quickly and rationally allocated to where they are most needed, especially maximizing resource utilization efficiency under resource constraints. The human information collection module interacts intelligently with on-site personnel based on a large language model, collecting feedback and information from the front lines in real time. This interaction not only enhances the breadth and depth of information collection but also improves the accuracy and reliability of information through intelligent model analysis. Furthermore, real-time updated human-generated information can be used to promptly revise emergency response and resource management instructions, further improving their adaptability and effectiveness. The efficient information exchange and coordination mechanisms between modules in the system design ensure rapid response in emergencies. From early warning to decision-making, resource allocation, and emergency response, each link is closely connected and seamlessly collaborates, ensuring the smooth and efficient operation of the entire emergency management process. Through these optimization measures, this solution's intelligent disaster response command system not only improves the speed and efficiency of disaster response but also significantly reduces casualties and economic losses caused by disasters, enhancing the overall emergency management capabilities of society.

[0056] The intelligent disaster response command system proposed in this application, along with other advantages, objectives, and features of this application, will be partly apparent from the following description and partly understood by those skilled in the art through study and practice of this application. Attached Figure Description

[0057] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0058] Figure 1 A structural schematic diagram of a disaster response intelligent command system provided in this application embodiment;

[0059] Figure 2 This is a schematic flowchart of a control method provided in an embodiment of this application. Detailed Implementation

[0060] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0061] Please see Figure 1 This is a structural schematic diagram of a disaster response intelligent command system 10 provided in an embodiment of this application, which may specifically include:

[0062] The environmental information collection module 101 is used to acquire environmental information of the target area, including sensor information, satellite information and meteorological information, and send the environmental information to the disaster early warning module 102 and the intelligent decision-making module 103.

[0063] The disaster early warning module 102 is used to acquire the aforementioned environmental information and generate disaster early warning information based on the aforementioned environmental information. The disaster early warning module 102 generates the aforementioned disaster early warning information based on a machine learning model.

[0064] The intelligent decision-making module 103 is used to acquire the above-mentioned environmental information and generate emergency response instructions and resource management instructions based on the above-mentioned environmental information. The intelligent decision-making module 103 generates the above-mentioned emergency response instructions and resource management instructions based on Monte Carlo simulation, agent-based model, genetic algorithm and particle swarm optimization algorithm.

[0065] Emergency response module 104 is used to obtain the above-mentioned emergency response instructions and generate an emergency response plan based on the above-mentioned emergency response instructions. The above-mentioned emergency response module 104 generates an emergency response plan based on a rule engine and simulation results.

[0066] Resource management module 105 is used to obtain the above-mentioned resource management instructions and generate a resource management scheme based on the above-mentioned resource management instructions. The above-mentioned resource management module 105 generates the resource management scheme based on dynamic programming and heuristic algorithms.

[0067] The human information collection module 106 is used to intelligently interact with the feedback personnel to obtain human information. The human information is used to correct the emergency response instructions and resource management instructions. The human information collection module 106 completes the intelligent interaction with the feedback personnel based on a large language model.

[0068] For example, the environmental information collection module 101 is responsible for collecting environmental information from the target area, including sensor information, satellite information, and meteorological information. This information is obtained through various sensor devices, satellite systems, and meteorological monitoring stations, covering multiple environmental parameters such as temperature, humidity, rainfall, and wind speed. The collected environmental information will be sent to the disaster early warning module 102 and the intelligent decision-making module 103 for further processing and analysis.

[0069] The disaster early warning module 102 receives data from the environmental information collection module 101 and generates disaster early warning information based on this environmental information. This module uses a machine learning model to analyze environmental data and predict possible disasters, such as floods, typhoons, or earthquakes. The machine learning model can identify patterns and trends in the data, thereby providing accurate early warning information.

[0070] The intelligent decision-making module 103 also receives environmental information and generates emergency response and resource management instructions based on this information. This module utilizes Monte Carlo simulations, agent-based models, genetic algorithms, and particle swarm optimization algorithms to optimize the decision-making process. These advanced algorithms can simulate different response plans and resource allocation strategies, selecting the most effective solution to address the disaster.

[0071] The emergency response module 104 is responsible for receiving emergency response instructions generated by the intelligent decision-making module 103 and generating specific emergency response plans based on these instructions. This module uses a rule engine and simulation results to formulate response plans, such as evacuation plans, rescue team deployment, and first aid station setup.

[0072] The resource management module 105 receives resource management instructions from the intelligent decision-making module 103 and generates a resource management plan based on these instructions. This module uses dynamic programming and heuristic algorithms to optimize resource allocation, ensuring efficient resource utilization during disaster response.

[0073] The human information collection module 106 acquires human information through intelligent interaction with on-site feedback personnel. This module interacts based on a large language model, enabling it to understand and respond to natural language input. The collected human information is used to correct emergency response instructions and resource management instructions, ensuring the real-time nature and accuracy of the instructions.

[0074] In summary, this system utilizes an environmental information collection module to automatically gather key data from multiple sources (such as sensors, satellites, and weather stations) to obtain real-time information on environmental changes in the target area. This real-time data acquisition and transmission significantly improves the speed and accuracy of disaster early warning, enabling emergency response to be initiated in the early stages of disaster formation, greatly reducing potential losses and impacts. The intelligent decision-making module integrates various advanced algorithms, including Monte Carlo simulation, agent-based models, genetic algorithms, and particle swarm optimization, to comprehensively consider various situations and variables, simulating and evaluating different emergency response and resource allocation schemes. This not only enhances the scientific nature of decision-making but also ensures the most effective decisions are made in complex and ever-changing disaster environments. The resource management module dynamically adjusts resource allocation through dynamic programming and heuristic algorithms to optimize resource utilization efficiency. This ensures that limited resources are quickly and rationally allocated to where they are most needed, maximizing resource utilization efficiency, especially in resource-scarce situations. The human information collection module interacts intelligently with on-site personnel based on a large language model, collecting feedback and information from the front lines in real time. This interaction not only improves the breadth and depth of information collection but also enhances the accuracy and reliability of information through intelligent model analysis. Furthermore, real-time updated human information can be used to promptly revise emergency response and resource management instructions, further enhancing their adaptability and effectiveness. The efficient information exchange and coordination mechanisms between modules in the system design ensure rapid response in emergencies. From early warning to decision-making, resource allocation, and emergency response, each link is closely connected and seamlessly collaborates, ensuring the smoothness and efficiency of the entire emergency management process. Through these optimization measures, this intelligent disaster response command system not only improves the speed and efficiency of disaster response but also significantly reduces casualties and economic losses caused by disasters, enhancing the overall emergency management capabilities of society.

[0075] The second aspect, please refer to Figure 2 The present application also provides a flowchart illustrating a control method for the aforementioned intelligent disaster response command system, comprising:

[0076] S110. Control the above-mentioned environmental information collection module to collect the environmental information of the target area, and send the environmental information to the above-mentioned disaster early warning module and the above-mentioned intelligent decision-making module;

[0077] For example, the environmental information collection module gathers environmental information about the target area, including sensor data, satellite data, and meteorological data. This ensures the system can acquire accurate real-time data, providing fundamental support for disaster early warning and emergency decision-making. The collected information is automatically sent to the disaster early warning module and the intelligent decision-making module for further analysis and processing.

[0078] S120. The above-mentioned disaster early warning module generates the above-mentioned disaster early warning information based on the above-mentioned environmental information and through the above-mentioned machine learning model.

[0079] For example, machine learning techniques can be used to analyze environmental data, issue timely disaster warnings, and predict the likelihood and potential impact of disasters. Machine learning models will identify abnormal patterns and trends in the data, thereby generating warnings about disasters such as floods, typhoons, and earthquakes.

[0080] S130. The intelligent decision-making module above controls the generation of the above emergency response instructions and the above resource management instructions based on the above environmental information through Monte Carlo simulation, agent-based model, genetic algorithm and particle swarm optimization algorithm.

[0081] For example, the intelligent decision-making module, based on environmental information, generates emergency response and resource management instructions through Monte Carlo simulations, agent-based models, genetic algorithms, and particle swarm optimization algorithms. These advanced algorithms simulate and evaluate different emergency response and resource allocation schemes to select the optimal strategy. The algorithm comprehensively considers various environmental factors and resource conditions to optimize the decision-making process and improve the efficiency of disaster response.

[0082] S140. The above-mentioned emergency response module generates an emergency response plan based on the above-mentioned emergency response instructions through a rule engine and simulation results;

[0083] For example, the emergency response control module generates an emergency response plan based on emergency response instructions, using a rule engine and simulation results. According to the instructions provided by the intelligent decision-making module, specific operational steps and strategies are formulated, including evacuation plans and rescue deployments. The rule engine, combined with simulation results, determines the most effective response measures, such as evacuation routes and the allocation of rescue resources.

[0084] S150. Control the above-mentioned resource management module to generate a resource management scheme based on the above-mentioned resource management instructions using dynamic programming and heuristic algorithms;

[0085] For example, the resource management module generates resource management plans based on resource management instructions using dynamic programming and heuristic algorithms. This ensures that resources are allocated and used rationally and effectively, especially when resources are limited. These algorithms optimize resource allocation, ensuring that relief supplies, personnel, and equipment can quickly reach where they are most needed.

[0086] S160. Control the above-mentioned human information collection module to obtain human information by completing intelligent interaction with the feedback personnel based on a large language model;

[0087] For example, the human information collection module obtains human information through intelligent interaction with feedback personnel based on a large language model. It collects real-time feedback from frontline rescue workers and disaster victims to adjust and optimize the emergency response. The large language model allows the module to understand natural language input, enabling it to quickly and accurately collect key information.

[0088] S170. Correct the above emergency response instructions and resource management instructions using the aforementioned manual information.

[0089] For example, emergency response and resource management instructions are revised based on collected human information. This ensures all operational instructions are updated with the latest field information, improving the adaptability and effectiveness of the response. The revision process involves reassessing previous decisions and making necessary adjustments based on the latest information.

[0090] In summary, by acquiring data in real time through an automated environmental information collection module and rapidly generating accurate early warning information through a disaster early warning module, this system can react quickly and ensure effective measures are taken in the early stages of a disaster. The intelligent decision-making module employs advanced decision support tools such as Monte Carlo simulation, agent-based models, genetic algorithms, and particle swarm optimization algorithms to simulate various emergency response and resource allocation schemes in complex disaster environments, thereby selecting the optimal solution. The resource management module uses dynamic programming and heuristic algorithms to optimize resource allocation and usage. This not only ensures the optimal use of limited resources in disaster response but also reduces resource waste and improves resource utilization efficiency. The human information collection module interacts intelligently with on-site personnel based on a large language model, collecting real-time feedback and updates from the front lines and promptly using this information to revise emergency response and resource management instructions. The system design ensures rapid information flow and efficient coordination between modules, enabling seamless integration and rapid implementation of early warning information dissemination, decision-making information transmission, and resource allocation execution. By improving the accuracy of early warnings and the timeliness of responses, this system can significantly reduce economic losses and casualties caused by disasters. The system ensures that effective measures are taken before or in the early stages of a disaster to mitigate its overall impact.

[0091] In some examples, the aforementioned disaster early warning module generates disaster early warning information based on the aforementioned environmental information and through the aforementioned machine learning model, including:

[0092] The above environmental information is preprocessed to obtain preprocessed first environmental information, wherein the preprocessing operations include noise filtering, outlier detection and data smoothing.

[0093] The aforementioned first environmental information is input into the machine learning model corresponding to the disaster type to generate the aforementioned disaster early warning information corresponding to different disaster types.

[0094] For example, the purpose of preprocessing is to improve data quality, ensuring that the data input into the machine learning model is accurate and reliable, thereby enhancing the accuracy and credibility of disaster early warning. Noise filtering aims to remove random noise from environmental information. Noise may be caused by sensor malfunctions, data transmission errors, or external environmental factors.

[0095] Noise filtering operations include, but are not limited to, using digital filters (such as low-pass filters, high-pass filters) or statistical methods (such as moving averages) to smooth data.

[0096] Outlier detection operations are used to identify and process outliers in data that may distort the results of predictive models. Outlier detection operations include, but are not limited to, statistical tests (such as Z-score or IQR methods) and distance- or density-based algorithms (such as local outlier factors).

[0097] Data smoothing operations aim to reduce short-term fluctuations in data to reveal longer-term trends. Data smoothing operations include, but are not limited to, moving averages and exponential smoothing.

[0098] Using specially trained machine learning models, early warning information is generated for different types of disasters based on preprocessed environmental information. This information helps in responding quickly to potential disaster events and taking necessary preventative measures in advance.

[0099] First, a specialized machine learning model is trained for each type of disaster (such as floods, typhoons, earthquakes, etc.). During the training phase, these models are fed historical environmental data and corresponding disaster occurrence records to learn the correlation between data patterns and disasters.

[0100] During the runtime phase, the preprocessed initial environmental information is input into the corresponding machine learning model. Each model evaluates the degree of matching between the current data and historical disaster patterns, and outputs the probability or risk level of a disaster.

[0101] Based on the model's output, the system generates disaster early warning information and releases it to government agencies, emergency response teams, and the public through various channels (such as mobile applications, social media, and broadcasting systems).

[0102] Through this highly automated and intelligent processing flow, this solution can effectively utilize environmental monitoring data to quickly and accurately generate disaster early warning information. This not only significantly improves the timeliness of disaster prevention and response but also reduces potential losses caused by disasters.

[0103] In some examples, the aforementioned control and intelligent decision-making module generates the aforementioned emergency response instructions and resource management instructions based on the aforementioned environmental information through Monte Carlo simulation, agent-based models, genetic algorithms, and particle swarm optimization algorithms, including:

[0104] The above environmental information is preprocessed to obtain preprocessed second environmental information. The preprocessing operations include noise filtering, outlier detection, and data smoothing.

[0105] Monte Carlo simulation was used based on the preprocessed second environmental information to obtain simulation evaluation results of multiple possible response schemes;

[0106] Based on the preprocessed environmental information described above, an agent-based model is used to simulate the performance of each response participant in multiple possible response scenarios.

[0107] The above disaster early warning information is generated based on the above simulation evaluation results and the above simulation performance results;

[0108] Based on the aforementioned second environmental information and available resource information, a population of initialization resource allocation schemes and a population of initialization examples are randomly generated.

[0109] Based on the above initial resource allocation scheme, the population is subjected to multiple iterations using a genetic algorithm to obtain preliminary optimization results.

[0110] Based on the above preliminary optimization results and the above initial example group, multiple iterations are performed using the particle swarm optimization algorithm to obtain the final optimization results.

[0111] The resource management instructions are generated based on the final optimization results.

[0112] For example, the collected environmental information is preprocessed, including noise filtering, outlier detection, and data smoothing, to obtain preprocessed second environmental information. This cleans and optimizes the data, ensuring the data quality and accuracy of subsequent algorithm processing.

[0113] Monte Carlo simulations are used to evaluate multiple possible response options based on preprocessed secondary environmental information. Monte Carlo simulations use random sampling techniques to estimate the effectiveness of various response options, helping decision-makers understand the potential performance of different options under different circumstances.

[0114] Agent-based models are used to simulate the performance of various response participants across multiple possible response scenarios. By simulating the behavior of each participant (such as rescue teams, medical personnel, and affected residents), agent-based models can provide detailed performance of each scenario in practice.

[0115] Disaster early warning information is generated by comprehensively analyzing the simulation evaluation results and simulation performance. This step transforms the simulation results into practical early warning information to guide actual disaster response activities.

[0116] Using the preprocessed second environmental information and available resource information, a resource allocation scheme population and particle swarm are randomly generated. This step forms the basis for the initial iteration of the optimization algorithm, providing multiple potential resource management schemes for optimization.

[0117] The initial resource allocation scheme population is iterated multiple times using a genetic algorithm to obtain preliminary optimization results. The genetic algorithm uses selection, crossover, and mutation operations to find the optimal resource management scheme, thereby improving resource utilization efficiency.

[0118] The preliminary optimization results are further iterated using the Particle Swarm Optimization (PSO) algorithm to obtain the final optimization result. PSO is an effective method for finding the global optimum by adjusting the scheme by tracking the historical best solutions of individuals and the swarm.

[0119] Resource management instructions are generated based on the final optimization results. The calculation results are then transformed into executable resource management operation instructions to ensure that resources are allocated most effectively during disaster response.

[0120] The method proposed in this application ensures that the intelligent disaster response command system can make scientific and accurate decisions in actual operation, maximize response speed and resource utilization efficiency, and thus effectively mitigate the impact of disasters.

[0121] In some examples, the aforementioned control and emergency response module generates an emergency response plan based on the aforementioned emergency response instructions through a rule engine and simulation results, including:

[0122] The above emergency response instructions are processed using a rule engine to obtain an optimized emergency response plan.

[0123] The optimized emergency response plan was simulated using a disaster response simulation tool to obtain simulation results.

[0124] An emergency response plan is generated based on the simulation results and optimization suggestions from the rule engine.

[0125] For example, the emergency response module receives emergency response instructions from the intelligent decision-making module and processes these instructions using a rules engine. The rules engine analyzes and processes the received instructions according to preset rules and logic, aiming to initially optimize these instructions and ensure their logical consistency and feasibility of implementation. The rules engine includes various conditional judgments, priority ranking, and resource allocation rules, which are designed based on past experience and best practices in emergency management.

[0126] The emergency response plan optimized by the rules engine is then subjected to detailed simulation using disaster response simulation tools. Through simulation, the implementation effect of the plan can be observed in a virtual environment, potential execution difficulties and outcomes can be assessed, and the response plan can be further optimized. Simulation tools can involve complex models, such as crowd evacuation models, traffic flow models, or resource allocation models, capable of simulating the performance and impact of specific plans in actual operation.

[0127] Based on the comprehensive simulation results and optimization suggestions provided by the rule engine, the final emergency response plan is determined. By combining the actual data from the simulation with the logical processing of the rule engine, the final emergency response plan is ensured to be feasible, optimally effective, and capable of rapid and efficient execution in real-world situations. A detailed analysis of the collected data is conducted, potentially including comparisons of different simulation scenarios, to select the emergency measures that best meet the current needs. Simultaneously, it is necessary to ensure that the plan complies with regulatory requirements, resource constraints, and time sensitivity.

[0128] By integrating rule engines and simulation tools, the method proposed in this application not only optimizes the design of emergency response plans but also improves their operability and effectiveness in real-world disaster situations. This approach allows decision-makers to gain a detailed understanding of the potential effects and risks of various emergency measures before implementation, thereby enabling them to make more informed decisions.

[0129] In some examples, the aforementioned control and resource management module generate resource management schemes based on the aforementioned resource management instructions using dynamic programming and heuristic algorithms, including:

[0130] Based on the above resource management instructions, the dynamic programming method is applied to the resource knowledge graph to plan the dynamic programming results of the resources. The resource knowledge graph stores information on resource type, location, dependency relationship, historical usage efficiency and emergency response strategy.

[0131] Based on the dynamic programming results above, resource allocation is further optimized using the particle swarm optimization algorithm to obtain the aforementioned resource management scheme.

[0132] For example, dynamic programming can be used to plan resource allocation by leveraging information stored in a resource knowledge graph. The resource knowledge graph contains key information such as resource type, location, dependencies, historical usage efficiency, and contingency response strategies. Dynamic programming is an optimization technique suitable for solving multi-stage decision problems. Through this method, the system can plan optimal or near-optimal resource allocation across multiple time steps, based on resource availability and demand, as well as other factors such as dependencies and historical data. The dynamic programming process obtains necessary input data from the resource knowledge graph, such as the location, type, and historical usage frequency of each resource. Then, based on this information, the system constructs state transition equations and decision processes to minimize costs or maximize benefits.

[0133] Resource allocation is further optimized using the Particle Swarm Optimization (PSO) algorithm. Building upon dynamic programming, PSO further refines resource allocation schemes. The PSO algorithm initializes a set of solutions (particles), each representing a potential resource allocation scheme. Each particle adjusts its position and velocity based on its own and the swarm's historical best solutions. Through an iterative process, particles move towards better resource allocation schemes until a stopping condition is met or a preset number of iterations is reached, ultimately determining the optimal resource management scheme.

[0134] By combining dynamic programming and particle swarm optimization, the method proposed in this application not only considers complex resource dependencies and constraints but also leverages collective intelligence to find the optimal resource allocation method. This approach significantly improves the scientific rigor, accuracy, and responsiveness of resource management, making it particularly suitable for dynamically changing disaster response environments. It ensures that resources can be rapidly and effectively deployed to critical areas, thereby maximizing their utility and minimizing the impact of disasters.

[0135] In some examples, the large language model described above includes: an embedding layer, a Transformer encoding layer, an output layer, and auxiliary components. The Transformer encoding layer includes multiple Transformer units, the output layer includes multiple fully connected layers and an activation function, which is the softmax activation function. The auxiliary components include a Dropout layer and a LayerNormalization layer, and the optimizer of the large language model is the Adam optimizer.

[0136] For example, the large language model structure includes an embedding layer, a Transformer encoding layer, an output layer, and auxiliary components, which are optimized using the Adam optimizer.

[0137] The primary function of the embedding layer is to transform the input natural language text (typically words or characters) into dense vector representations. These vectors are numerical forms that the model can process, capturing and representing the semantic and syntactic features of words. Embedding layers typically use pre-trained word embeddings such as GloVe or Word2Vec, or learn these representations during model training.

[0138] The Transformer Encoding Layer comprises multiple Transformer Units, each containing a self-attention mechanism and a feedforward neural network. The Transformer Encoding Layer utilizes self-attention to process the relationships between each part of the input data and all other parts, enabling the model to capture long-range dependencies. This layer is the core component for understanding and processing the input data. Each Transformer Unit computes an attention score for each element in the input sequence and updates its representation accordingly to better capture the contextual information of the text.

[0139] The output layer consists of multiple fully connected layers and an activation function. Using the softmax activation function, it transforms the neural network's output into a probability distribution, suitable for classification tasks. The main function of the output layer is to make the final task prediction based on the deep features passed from the Transformer encoding layer, such as sentiment analysis and text classification.

[0140] The auxiliary components include Dropout layers and Layer Normalization layers. Dropout layers are used to prevent overfitting by randomly "dropping" activations of some neurons during training to increase the model's generalization ability. Layer Normalization layers are used to stabilize the training of the neural network by normalizing the layer inputs to accelerate the training process and improve model performance.

[0141] The optimizer uses the Adam optimizer, which can help large language models converge faster during training and improve the model's performance on complex datasets.

[0142] In some examples, the above-mentioned emergency response instructions and resource management instructions are corrected using the aforementioned human information, including:

[0143] The authenticity of the aforementioned human-generated information is evaluated based on expert evaluation methods and intelligent evaluation models in order to obtain effective human-generated information.

[0144] Based on the aforementioned valid human information, the above emergency response instructions and resource management instructions were revised.

[0145] For example, the purpose of the assessment is to filter out reliable human-generated information for use in revising and updating emergency response and resource management directives. This is because, in emergency situations, received information may include inaccurate or misleading data, which could lead to inappropriate response measures.

[0146] Expert evaluation method: This method relies on the judgment of domain experts regarding the information. Experts assess the authenticity of the information based on their experience and knowledge, which may involve verifying the source of the information and checking the logical consistency of the content.

[0147] Intelligent evaluation models: These models automatically assess the authenticity of information using pre-trained machine learning models. These models may learn to identify characteristics of authentic information based on historical data, such as consistency and relevance to known facts.

[0148] Emergency response and resource management directives are revised based on validated and effective human information. This ensures that emergency response and resource allocation directives reflect the latest and most accurate scenario conditions, thereby improving the effectiveness and efficiency of response measures.

[0149] Adjustments to evacuation routes, rescue team deployments, and emergency medical service arrangements may be made based on real-time human information. For example, if received human information indicates that the disaster impact in a certain area is more severe than expected, it may be necessary to deploy more rescue resources or adjust evacuation orders.

[0150] Optimize the allocation and deployment of resources, such as disaster relief supplies and human resources, based on real-world human information. For example, if reliable information indicates an urgent need in a certain region, resource management directives will prioritize allocating resources to that region.

[0151] By combining expert intuition with data-driven analysis from intelligent assessment models, the method proposed in this application not only improves the accuracy of information authenticity assessment but also enables real-time adjustment and optimization of emergency response measures and resource allocation plans. This flexible and precise adjustment mechanism significantly enhances disaster response efficiency, reduces potential losses and impacts, and ensures the scientific validity and effectiveness of response measures.

[0152] In some examples, the authenticity of the aforementioned human-generated information is assessed based on expert evaluation methods and intelligent evaluation models to obtain valid human-generated information, including:

[0153] Obtain the identity of the person who reported the information;

[0154] A preliminary authenticity score is determined based on the identity of the reporter mentioned above;

[0155] The above-mentioned manual information is preprocessed to obtain key information;

[0156] The aforementioned key information was sent to the expert review unit to obtain an expert authenticity score through expert evaluation.

[0157] Send the above key information to the above intelligent evaluation model to obtain the model's authenticity score;

[0158] Obtain the first weight corresponding to the above expert authenticity scores;

[0159] Obtain the second weight corresponding to the above model's authenticity score;

[0160] The final authenticity is determined based on the above preliminary authenticity score, the above expert authenticity score, the above first weight, the above model authenticity score, and the above second weight;

[0161] The above-mentioned valid human information is determined based on the final authenticity and authenticity assessment threshold.

[0162] For example, verifying the identity of the person reporting human information is the initial step in assessing the information's authenticity. Knowing the source of the information helps in evaluating its credibility. For instance, information from experienced and reputable sources may be considered more reliable, and information reported by rescue workers is generally considered more trustworthy.

[0163] An initial authenticity score is given based on the reporter's background and historical records. This score provides a reference point for subsequent detailed evaluation, reflecting the initial credibility of the information.

[0164] The collected manual information is cleaned and extracted to remove noise, highlight key information, improve data quality, and ensure the accuracy of subsequent evaluations.

[0165] The pre-processed key information is submitted to the expert review unit for examination. Experts use their professional knowledge and experience to assess the authenticity of the information and provide an authenticity score based on their professional judgment.

[0166] Simultaneously, key information is also input into a pre-trained intelligent evaluation model. The intelligent model automatically assesses the authenticity of the information based on historical data and learned patterns, providing a data-driven authenticity score.

[0167] Determine the relative importance of expert scores (first weight) and model scores (second weight) in the final authenticity decision. The weighting reflects the level of trust and reliance on different evaluation methods and is adjusted according to the needs of the context.

[0168] By combining the preliminary authenticity score, expert authenticity score, model authenticity score, and their respective weights, a comprehensive final authenticity score is calculated. Integrating all evaluation results yields a comprehensive judgment that takes into account multiple factors.

[0169] The final authenticity score is compared with a set authenticity assessment threshold to determine whether the information is sufficiently authentic to be used for revising emergency response and resource management instructions. Information is considered valid only when its authenticity exceeds a certain threshold, ensuring that emergency command system decisions are based on reliable information.

[0170] Through this series of comprehensive and systematic steps, the method proposed in this application embodiment ensures that the disaster response command system can make rapid and accurate decisions based on highly reliable human information, greatly improving the efficiency and effectiveness of responding to emergencies.

[0171] In some examples, the first weight information is negatively correlated with the disaster level, the second weight information is positively correlated with the disaster level, the first weight information is negatively correlated with the time of disaster occurrence, and the second weight information is positively correlated with the disaster event.

[0172] The aforementioned authenticity assessment threshold is positively correlated with the aforementioned disaster level, and the aforementioned authenticity assessment threshold is negatively correlated with the aforementioned disaster occurrence time.

[0173] For example, the first weight is negatively correlated with the disaster severity level; that is, the higher the disaster severity level, the lower the weight of the expert score. Furthermore, the first weight is also negatively correlated with the time of disaster occurrence, meaning that the weight of the expert score gradually decreases from the initial stage of the disaster to its later stages. In the early stages of a disaster and for high-severity disasters, the situation on the ground may change rapidly, and expert judgments may be inaccurate or outdated due to a lack of up-to-date field information. Therefore, as the disaster severity increases and time progresses, the weight of the expert score decreases relative to data-driven models.

[0174] The second weight is positively correlated with both the disaster severity level and the time of disaster occurrence; that is, the weight of the model score increases as the disaster severity level rises and time progresses. Over time, more data is collected and analyzed by the model, potentially making its predictions more accurate and reliable. This is especially true for high-level disasters, where the model can quickly process large amounts of data, providing real-time and accurate assessments.

[0175] The accuracy assessment threshold is positively correlated with the disaster severity, meaning that as the disaster severity increases, the accuracy requirements for information become more stringent, and the assessment threshold rises. It is negatively correlated with the time since the disaster occurred, implying that the threshold gradually decreases over time. In severe disasters, the cost of misinformation is extremely high, thus requiring even stricter accuracy standards. As the disaster continues, emergencies may require a faster response, so the stringency of information requirements may decrease to facilitate a rapid reaction.

[0176] Through this dynamic adjustment mechanism, disaster response systems can flexibly adjust information assessment standards according to the severity and development stage of different disasters. This not only improves the flexibility and adaptability of information processing but also ensures that decision-making is based on the most reliable information available at different stages and for different types of disasters. This strategy helps improve the efficiency and accuracy of emergency response, thereby managing disasters more effectively and mitigating their impact.

[0177] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0178] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0179] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a mechanism for implementing the flowchart. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0180] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0181] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0182] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform the process of predicting the decomposition rate in alumina production in the corresponding embodiment.

[0183] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0184] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0185] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0186] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0187] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0188] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0189] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A control method for a disaster response intelligent command system, characterized in that, The system includes: an environmental information collection module, a disaster early warning module, an intelligent decision-making module, an emergency response module, a resource management module, and a manual information collection module; The method includes: The environmental information collection module is controlled to collect environmental information of the target area and send the environmental information to the disaster early warning module and the intelligent decision-making module; The disaster early warning module generates disaster early warning information based on the environmental information using a machine learning model; The intelligent decision-making module controls the generation of emergency response instructions and resource management instructions based on the environmental information through Monte Carlo simulation, agent-based model, genetic algorithm and particle swarm optimization algorithm; The emergency response module generates an emergency response plan based on the emergency response instructions using a rule engine and simulation results; The resource management module generates a resource management scheme based on the resource management instructions using dynamic programming and heuristic algorithms. The human information collection module is controlled to obtain human information by completing intelligent interaction with the feedback personnel based on a large language model; The emergency response instructions and resource management instructions are corrected using the aforementioned human information; The intelligent decision-making module, based on the environmental information, generates emergency response instructions and resource management instructions through Monte Carlo simulation, agent-based models, genetic algorithms, and particle swarm optimization algorithms, including: The environmental information is preprocessed to obtain preprocessed second environmental information, wherein the preprocessing operation includes noise filtering, outlier detection and data smoothing. Monte Carlo simulation is used based on the preprocessed second environmental information to obtain simulation evaluation results of multiple possible response schemes; Based on the preprocessed environmental information, an agent-based model is used to simulate the performance of each response participant in multiple possible response scenarios; The emergency response instructions are generated based on the simulation evaluation results and the simulation performance results. Based on the second environmental information and available resource information, an initial resource allocation scheme population and an initial particle swarm are randomly generated. Based on the initial resource allocation scheme, the population is subjected to multiple iterative operations using a genetic algorithm to obtain preliminary optimization results. Based on the preliminary optimization results and the initial particle swarm, multiple iterations are performed using the particle swarm optimization algorithm to obtain the final optimization results. The resource management instructions are generated based on the final optimization results. The emergency response module, based on the emergency response instructions, generates an emergency response plan through a rule engine and simulation results, including: The emergency response instructions are processed using a rule engine to obtain an emergency response plan optimized by the rule engine. The optimized emergency response plan was simulated using a disaster response simulation tool to obtain simulation results. An emergency response plan is generated based on the simulation results and optimization suggestions from the rule engine.

2. The control method according to claim 1, characterized in that, The disaster early warning module generates disaster early warning information based on the environmental information using a machine learning model, including: The environmental information is preprocessed to obtain preprocessed first environmental information, wherein the preprocessing operation includes noise filtering, outlier detection and data smoothing. The first environmental information is input into a machine learning model corresponding to the disaster type to generate the disaster early warning information corresponding to different disaster types.

3. The control method according to claim 1, characterized in that, The control module generates a resource management scheme based on the resource management instructions using dynamic programming and heuristic algorithms, including: The dynamic programming result of the plan is obtained by applying dynamic programming in the resource knowledge graph based on the resource management instructions. The resource knowledge graph stores information on resource type, location, dependency relationship, historical usage efficiency and emergency response strategy. Based on the dynamic programming results, resource allocation is further optimized using the particle swarm optimization algorithm to obtain the resource management scheme.

4. The control method according to claim 1, characterized in that, The large language model includes an embedding layer, a Transformer encoding layer, an output layer, and auxiliary components. The Transformer encoding layer includes multiple Transformer units. The output layer includes multiple fully connected layers and an activation function, which is a softmax activation function. The auxiliary components include a Dropout layer and a Layer Normalization layer. The optimizer of the large language model is the Adam optimizer.

5. The control method according to claim 1, characterized in that, The step of correcting the emergency response instructions and resource management instructions using the human information includes: The authenticity of the human-made information is evaluated based on expert evaluation methods and intelligent evaluation models to obtain valid human-made information; The emergency response instructions and resource management instructions are revised based on the valid human information.

6. The control method according to claim 5, characterized in that, The process of evaluating the authenticity of the manually generated information based on expert evaluation methods and intelligent evaluation models to obtain valid manually generated information includes: Obtain the identity of the person who reported the information; A preliminary authenticity score is determined based on the identity of the person who reported the information; The artificial information is preprocessed to obtain key information; The key information is sent to the expert review unit to obtain an expert authenticity score through expert evaluation. The key information is sent to the intelligent evaluation model to obtain a model authenticity score; Obtain the first weight corresponding to the expert authenticity score; Obtain the second weight corresponding to the model's authenticity score; The final authenticity is determined based on the preliminary authenticity score, the expert authenticity score, the first weight, the model authenticity score, and the second weight; The valid human information is determined based on the final authenticity and authenticity assessment threshold.

7. The control method according to claim 6, characterized in that, The first weight information is negatively correlated with the disaster level, the second weight information is positively correlated with the disaster level, the first weight information is negatively correlated with the disaster occurrence time, and the second weight information is positively correlated with the disaster occurrence time. The authenticity assessment threshold is positively correlated with the disaster level and negatively correlated with the time of disaster occurrence.

Images