A disaster prevention and emergency communication command management system based on navigation, communication and remote sensing technologies

Abstract

The present invention discloses a disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies. The present invention relates to the technical fields of emergency communication and disaster management, and includes: a data acquisition and fusion module, which is used to obtain multi-source data from communication network status, navigation and positioning information, and remote sensing monitoring data, and process the multi-source data using a dynamic weighted fusion algorithm. This disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies can significantly reduce the lag of disaster emergency decision-making and improve the emergency response efficiency by utilizing data acquisition and fusion algorithms, accurate disaster evolution prediction models, and optimized resource scheduling schemes; through intelligent decision support and resource scheduling, it ensures that emergency command personnel can make correct decisions quickly and efficiently, minimize the losses caused by disasters to the greatest extent, and ensure that emergency resources can be allocated in a timely manner in extreme situations to ensure the continuity of emergency response.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency communication and disaster management, and specifically to a disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies. Background Art

[0002] In disaster emergency scenarios, existing systems generally have the problem of spatio-temporal heterogeneity of communication, navigation, and remote sensing data (communication network status, navigation and positioning information, and remote sensing monitoring data): communication data (5G / satellite) exhibits high-frequency temporal characteristics (updated at the level of 1 ms), navigation data (Beidou / GPS) has spatial continuity characteristics (accuracy at the level of 0.1 m), and remote sensing data (SAR / optical satellite) shows spatial discrete characteristics (resolution at the level of 10 m); the existing technology uses Kalman filtering in static weighted fusion algorithms, which is difficult to achieve dynamic coupling analysis across time scales, resulting in a decision-making delay of 3-5 minutes in emergency situation awareness and the loss of the critical decision-making window period in rapidly evolving disasters such as typhoons and wildfires; there is dynamic decision-making lag, and the traditional rule engine-based command system Drools cannot adapt to the mutation characteristics of disaster scenarios. In extreme cases where the base station damage rate > 30%, the generation time of the emergency resource scheduling plan exceeds 15% of the 72-hour golden rescue standard. Summary of the Invention

[0003] (I) Technical Problems to be Solved

[0004] In view of the deficiencies of the prior art, the present invention provides a disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies, which solves the problems of spatio-temporal heterogeneity and decision-making lag in existing systems.

[0005] (II) Technical Solutions

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies, comprising:

[0007] A data acquisition and fusion module, which is used to obtain multi-source data from the communication network status, navigation and positioning information, and remote sensing monitoring data. The module processes the multi-source data using a dynamic weighted fusion algorithm. The multi-source data includes communication data, navigation data, and remote sensing data. The communication data is 5G / satellite communication data, the navigation data is Beidou / GPS data, and the remote sensing data is SAR / optical satellite data;

[0008] A disaster evolution prediction module, which predicts the evolution trend, influence range, and change in disaster level of a disaster through the NSGA-II multi-objective optimization algorithm based on the disaster type, evolution law, and real-time data, and obtains a disaster evolution prediction result;

[0009] Resource scheduling optimization module, according to the disaster evolution prediction results, on-site resource situation and emergency requirements, by accessing the emergency resource database, makes intelligent allocation based on the information of emergency supplies, personnel, vehicles and equipment, and generates a resource scheduling plan through a dual-objective optimization model. The generated plan can ensure the completion of emergency resource scheduling within the specified time, and ensure that the emergency resource scheduling time does not exceed 15% of the 72-hour golden rescue standard;

[0010] Command and decision-making module, used to analyze the fused multi-source data, disaster evolution prediction results and resource scheduling plan, generate emergency command decisions, and provide real-time feedback on resource deployment and emergency response to commanders through a visualization platform;

[0011] Communication guarantee and real-time feedback module, which guarantees the stable communication between the emergency command system and on-site personnel. This module combines satellite communication and 5G network to ensure real-time communication feedback can still be provided during disasters;

[0012] Among them, the data acquisition and fusion module uses a deep learning-based spatio-temporal feature recognition method for data fusion, optimizes spatio-temporal heterogeneity, improves data fusion efficiency, and reduces the impact of spatio-temporal heterogeneity problems; the data acquisition and fusion module includes a data center, the data center is connected to multiple data sources, and the multiple data sources include data from the power, communication, and transportation industries for real-time analysis and fusion of spatio-temporal data; the disaster evolution prediction module introduces meteorological data and historical disaster cases for training to improve the accuracy of disaster evolution prediction; the resource scheduling optimization module adjusts the resource scheduling strategy according to the real-time evolution state of the disaster, resource distribution and emergency response progress through a dynamic adjustment algorithm; the communication guarantee and real-time feedback module includes a multi-path communication guarantee system, and ensures that commanders can obtain real-time feedback through satellite communication, 5G network and low-power wide-area network LPWAN communication methods.

[0013] Preferably, the data acquisition and fusion module processes multi-source data using a dynamic weighted fusion algorithm, collects data in real time from multiple data sources, which include but are not limited to communication data: 5G / satellite communication data, navigation data: Beidou / GPS data, and remote sensing monitoring data: SAR / optical satellite data. In addition to the above data, the module also obtains real-time information from data sources in the power, communication, and transportation industries. Each data source has different spatio-temporal characteristics, including update frequency, accuracy, and time span. The multi-source data collected is preprocessed, mainly including steps such as data denoising, standardization, time alignment, and spatial interpolation. These steps ensure the spatio-temporal consistency between different data sources for subsequent processing. For navigation data and remote sensing data, spatial interpolation processing is performed to make them comparable at the same spatial resolution, and time resampling is used to ensure temporal consistency. A spatio-temporal feature recognition method based on deep learning (such as convolutional neural network CNN or recurrent neural network RNN) is used to identify the spatio-temporal features of each data source and extract key spatio-temporal patterns. The deep learning model can learn and understand the spatio-temporal relationships between different data sources, and perform effective feature extraction and optimization while keeping the characteristics of each data source unchanged. During the fusion process, dynamic weights are assigned to each data source according to its timeliness, accuracy, and importance in emergency response. Through dynamic weighted fusion, a comprehensive spatio-temporal dataset is generated, covering the data characteristics from different sources. This dataset contains information in multiple dimensions such as communication, navigation, and remote sensing, and has high timeliness and spatial accuracy. This fused dataset will be used as the input for subsequent disaster evolution prediction, resource scheduling optimization, and emergency decision-making generation, supporting the rapid and accurate execution of disaster prevention and emergency response.

[0014] Preferably, the disaster evolution prediction module predicts the evolution trend, impact range, and change in disaster level of the disaster. The process of obtaining the disaster evolution prediction result includes receiving multi-source data as input, which includes but is not limited to meteorological data (such as temperature, precipitation, wind speed), historical disaster case data, real-time sensor data (such as earthquake, fire, flood sensor data), and meteorological warning information; all input data is integrated through the data acquisition and fusion module to ensure the spatio-temporal consistency and integrity of the data;

[0015] The NSGA-II multi-objective optimization algorithm is adopted to construct a disaster evolution prediction model. According to different disaster types and evolution rules, this model comprehensively considers the evolution trend, influence range, and changes in disaster levels of disasters through an optimization algorithm. The NSGA-II multi-objective optimization algorithm gradually optimizes each dimension of disaster evolution prediction through processes such as population initialization, crossover, mutation, and selection, ensuring that the algorithm can give the best prediction results. By introducing historical disaster case data and real-time meteorological data, supervised learning is used to train the model so that the model can learn the laws of disaster evolution. Through historical disaster data, the model can identify the patterns and trends of disaster evolution. The model is dynamically optimized based on real-time meteorological data, sensor data, and meteorological warning data, automatically adjusting the parameters and weights in the prediction model to improve the accuracy of prediction results. Through the trained and optimized model, the disaster evolution prediction module can predict the disaster evolution trend, including key indicators such as the occurrence, expansion speed, and intensity change of disasters. The module predicts the expansion direction and development trend of disasters by comparing real-time data and historical evolution data, including the path of storms and the spread direction of fires, to obtain the disaster evolution trend.

[0016] According to the predicted disaster evolution trend, the module further calculates the possible influence range of the disaster, including predicting the affected areas of typhoon, flood, or fire disasters based on meteorological data and disaster types. At the same time, the module evaluates the disaster level according to the evolution process of the disaster, such as from tropical storm to severe typhoon, or from small-scale fire to large-scale wildfire. The prediction results include the disaster evolution trend, the predicted influence range, and the changes in disaster levels.

[0017] Preferably, the specific process of the resource scheduling optimization module generating a resource scheduling plan according to the disaster evolution prediction results, on-site resource conditions, and emergency requirements through a bi-objective optimization model includes: obtaining the disaster evolution trend, influence range, and changes in disaster levels from the disaster evolution prediction module; obtaining real-time information from the emergency resource database, including the quantity, location, and status of available emergency supplies, personnel, vehicles, and equipment; evaluating the emergency requirements at the disaster site according to the type and intensity of the disaster, that is, evaluating the resource demand situation at the disaster site, including the urgency of medical treatment, transportation, and communication.

[0018] The resource scheduling optimization module conducts real-time evaluation of the current on-site resources to determine the availability, distribution, remaining quantity, and urgency of various resources. The module also predicts the resource demand in combination with the evolution of the disaster. For example, at the initial stage of the disaster, the module may predict a high demand for transportation and communication equipment resources; as the disaster expands, the demand for medical treatment and material resources may increase.

[0019] The resource scheduling optimization module constructs a two-objective optimization model with two objectives, including Objective 1 and Objective 2, aiming to achieve optimization in two aspects. Objective 1: Minimize the time of resource scheduling to ensure that resources can reach the demand area as soon as possible and avoid delaying emergency rescue; in particular, ensure that the resource scheduling time does not exceed 15% of the 72-hour golden rescue standard. Objective 2: Maximize the resource scheduling benefit to ensure the reasonable allocation and efficient utilization of resources, so that limited resources can cover more disaster-stricken areas and meet key needs, and avoid resource waste or over-allocation.

[0020] By using the advanced optimization algorithm NSGA-II, the balance between scheduling time and benefit is considered simultaneously; the optimization process is based on the disaster evolution prediction results, resource status and demand, and calculates the possibilities of different resource scheduling plans; the model selects the optimal solution by comparing different scheduling plans to ensure that the resource scheduling after the disaster can respond timely and effectively.

[0021] Through the optimization algorithm, the resource scheduling optimization module generates a set of resource scheduling plans that meet timeliness and benefit; the plans include the specific allocation paths of each resource, the required transportation methods, the allocation priorities and time nodes; after the plans are generated, the module will fine-tune the plans according to the dynamic situation of real-time resources to ensure that the plans can adapt to the changing disaster process and on-site conditions; the generated resource scheduling plans will be notified to the emergency command personnel through the command decision-making module to initiate the resource allocation operation; the resource scheduling optimization module will continuously receive the data fed back by the emergency command personnel and the site, and optimize the scheduling plan in real time according to the latest situation.

[0022] Preferably, the command decision-making module includes an intelligent push system, which automatically pushes decision-making plans to the emergency command personnel according to the disaster situation, resource situation and task requirements.

[0023] Preferably, the process of the command decision-making module generating emergency command decisions by analyzing the fused multi-source data, disaster evolution prediction results and resource scheduling plans: The command decision-making module receives data from different sources, and the command decision-making module comprehensively analyzes the input data to obtain the analysis results. The analysis process includes: Conducting disaster situation analysis: Analyze the current and predicted disaster situations, and evaluate the expansion trend, affected areas and danger levels of the disaster by comparing the disaster evolution prediction results with real-time data; Conducting resource status assessment: Evaluate the status of current available emergency resources and the resources that have been scheduled to ensure whether the resources are effectively utilized and whether they can meet the needs brought about by the expansion of the disaster; Conducting emergency task demand analysis: According to the disaster evolution and resource scheduling situation, analyze the completion status of current emergency tasks and future resource requirements, and evaluate whether there are delays or resource shortages in the tasks.

[0024] Based on the analysis results, the command and decision-making module generates emergency command decisions, including: task assignment: according to the urgency of the disaster and resource availability, the command and decision-making module generates clear task allocations, including instructions for dispatching rescue personnel, materials, and equipment to different disaster areas; according to real-time feedback and predicted disaster development, adjust the priorities of emergency resources and generate resource scheduling commands to ensure that resources can be promptly allocated to the areas in greatest need; generate an optimized emergency response plan, including task assignment, resource scheduling, and material supply.

[0025] Preferably, the command and decision-making module includes the assignment and progress monitoring of emergency tasks, and adjusts the execution priorities of emergency tasks in real time to automatically optimize the emergency response plan under different disaster scenarios.

[0026] Preferably, the process by which the communication guarantee and real-time feedback module ensures stable communication between the emergency command system and on-site personnel includes: before the disaster occurs, the communication guarantee and real-time feedback module evaluates communication requirements; the evaluation content includes the communication environment in the disaster area, the availability of communication infrastructure, and the communication requirements of on-site personnel and emergency equipment; the module will evaluate the key areas and personnel that need to ensure communication according to the type, scale, and affected area of the disaster to ensure stable communication between key resources and the command system during the disaster.

[0027] To ensure the reliability of communication during the disaster, the communication guarantee and real-time feedback module configures a multi-path communication system, including the deployment of satellite communication, 5G network, and low-power wide-area network LPWAN. According to the type of disaster, affected area, and on-site environment, the communication guarantee and real-time feedback module automatically selects the most suitable communication link; including, in urban areas, giving priority to using the 5G network for fast data transmission; while in remote areas without 5G signals, giving priority to enabling satellite communication or LPWAN; the module continuously monitors the stability and quality of each communication link and dynamically adjusts the communication method used according to the real-time status of the link to ensure the stability and reliability of the communication system.

[0028] The communication guarantee module monitors the quality of all communication links in real time, including signal strength, bandwidth, latency, and packet loss rate; the module can identify the risks of communication interruption or quality degradation in real time and quickly take countermeasures; if an abnormal communication link is detected, the communication guarantee module will automatically switch to a backup link; including: when the ground communication base station fails, the module will automatically enable the satellite communication link to restore communication to ensure that the communication between emergency command personnel and on-site personnel is not interrupted.

[0029] According to the severity of the disaster situation and on-site feedback, the communication guarantee module adjusts the allocation of communication resources in real time; including, in key areas of the disaster area: post-disaster rescue or medical rescue points, the communication guarantee module will prioritize the communication needs of these areas; the module ensures smooth communication between the command center and on-site personnel, rescue teams, and medical personnel by dispatching existing communication resources, reducing any potential communication bottlenecks;

[0030] On-site personnel use a real-time feedback mechanism, which includes voice communication, video backhaul, and data upload, to transmit the latest situation in the disaster area back to the command center; the communication guarantee module ensures the stable transmission of this information, preventing command delays caused by poor communication; the command personnel make decisions based on on-site information and transmit new instructions, dispatching plans, and decisions to on-site personnel through the same communication link, ensuring real-time synchronization of on-site response and command.

[0031] Preferably, the process of the command decision-making module adjusting the execution priority of emergency tasks in real time includes: the command decision-making module uses an intelligent push system to push the generated emergency command decisions to emergency command personnel in real time, ensuring that they can timely understand the disaster dynamics, resource status, and task instructions; the pushed content includes the current disaster situation, resource dispatching status, and task priority, helping the command personnel make quick decisions;

[0032] The command decision-making module continuously monitors the progress of various emergency tasks, including task execution status, resource allocation, and on-site feedback; according to the real-time development of the disaster, on-site feedback, and resource availability, the command decision-making module evaluates the priority of current emergency tasks; for example, if the resource demand in the severely affected area is high, the task priority in that area will be increased; when the disaster situation changes, the command decision-making module will adjust the execution priority of tasks in real time to ensure that the emergency response always focuses on the most critical areas; the module automatically updates the task execution instructions according to the change in priority and provides real-time feedback to relevant emergency personnel to ensure that they complete tasks according to the latest priority; based on the real-time task execution situation and priority adjustment, the command decision-making module will continuously optimize the emergency response plan; through analyzing and integrating multi-source data, disaster evolution prediction results, and resource dispatching plans by the command decision-making module, emergency command decisions are generated and the resource deployment and emergency response situation are real-time fed back to the command personnel through the intelligent push system; the process of adjusting the execution priority of emergency tasks in real time ensures that in the process of rapid disaster evolution, the emergency response plan can be timely optimized, improving the timeliness and effectiveness of disaster response.

[0033] Preferably, the process of the command and decision-making module for real-time adjustment of the execution priority of emergency tasks is as follows: The command and decision-making module evaluates and analyzes the emergency tasks through the disaster evolution prediction results, on-site resource conditions, and emergency requirements; based on the type, severity, resource allocation, and task urgency of the disaster, the module allocates specific emergency tasks; sets priorities. According to the task urgency, the affected area of the disaster area, the availability of existing resources, and their importance in disaster response, the module assigns priorities to each task. High-priority tasks are processed first, and high-priority tasks include rescue in severely affected areas and restoration of important infrastructure; the command and decision-making module matches the on-site available resources with the task requirements; through intelligent allocation, the module ensures that each task can obtain appropriate resource support to ensure the smooth execution of the tasks. Among them, the on-site available resources include rescue teams, materials, and equipment; monitoring the progress of emergency tasks, the command and decision-making module continuously tracks the execution progress of tasks through on-site feedback; the module evaluates the completion status of tasks to ensure that it is carried out within the predetermined time frame. On-site feedback includes real-time data, video monitoring, and task reports; the module compares the task progress with the predetermined progress and automatically updates the task execution status according to the progress; if there is a delay, the module will identify the reason and timely adjust the resource allocation or task allocation;

[0034] The command and decision-making module dynamically evaluates the priorities of tasks according to the new data during the disaster evolution process, the on-site task execution progress, and resource status; according to the changes in the disaster situation, the module makes real-time adjustments to the priorities of tasks. Among them, the changes in the disaster situation include the spread of the disaster and the emergence of more resource requirements;

[0035] Automatic priority adjustment: If the disaster situation changes, the module will automatically adjust the priorities of tasks; including, if the disaster situation in a certain area intensifies, the module will automatically increase the priorities of tasks in that area and allocate more resources to that area for response; after the priority adjustment, the command and decision-making module updates the task allocation according to the adjusted priorities to ensure that resource allocation gives priority to supporting high-priority tasks; the module automatically generates new scheduling instructions and transmits the updated task instructions to the executors in real time.

[0036] (III) Beneficial effects

[0037] The present invention provides a disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies. It has the following beneficial effects:

[0038] The disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies can significantly reduce the lag in disaster emergency decision-making and improve the emergency response efficiency by utilizing data acquisition and fusion algorithms, accurate disaster evolution prediction models, and optimized resource scheduling schemes. Through intelligent decision support and resource scheduling, it ensures that emergency command personnel can make correct decisions quickly and efficiently, minimizing the losses caused by disasters, and ensuring the timely allocation of emergency resources in extreme cases to ensure the continuity of emergency response. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic framework diagram of a disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies of the present invention;

[0040] Figure 2 It is a schematic flow diagram of the resource scheduling optimization module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] Please refer to Figure 1 and Figure 2 , the present invention provides a technical solution: a disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies, including:

[0043] A data acquisition and fusion module for obtaining multi-source data from communication network status, navigation and positioning information, and remote sensing monitoring data. The module uses a dynamic weighted fusion algorithm to process multi-source data to solve the spatio-temporal heterogeneity problem. The multi-source data includes communication data, navigation data, and remote sensing data. The communication data is satellite communication data, the navigation data is GPS data, and the remote sensing data is optical satellite data;

[0044] A disaster evolution prediction module, through the NSGA-II multi-objective optimization algorithm, based on disaster types, evolution laws, and real-time data, predicts the evolution trend, impact range, and disaster level change of disasters to obtain disaster evolution prediction results;

[0045] Resource scheduling optimization module, according to the disaster evolution prediction results, on-site resource situation and emergency requirements, through accessing the emergency resource database, conducts intelligent allocation based on the information of emergency supplies, personnel, vehicles, and equipment, generates a resource scheduling plan through a dual-objective optimization model, and the generated plan can ensure that the emergency resource scheduling is completed within the specified time, ensuring that the emergency resource scheduling time does not exceed 15% of the 72-hour golden rescue standard;

[0046] Command and decision-making module, used to analyze the fused multi-source data, disaster evolution prediction results and resource scheduling plan, generate emergency command decisions, and provide real-time feedback on resource deployment and emergency response to the commanders through the visualization platform;

[0047] Communication guarantee and real-time feedback module, guarantees the stable communication between the emergency command system and on-site personnel. The module combines satellite communication and 5G network to ensure that real-time communication feedback can still be provided during disasters;

[0048] Among them, the data acquisition and fusion module uses a deep learning-based spatio-temporal feature recognition method for data fusion, optimizes spatio-temporal heterogeneity, improves data fusion efficiency, and reduces the impact of spatio-temporal heterogeneity problems; the data acquisition and fusion module includes a data center, and the data center is connected to multiple data sources. The multiple data sources include data from the power, communication, and transportation industries, and conducts real-time analysis and fusion of spatio-temporal data;

[0049] The disaster evolution prediction module introduces meteorological data and historical disaster cases for training to improve the accuracy of disaster evolution prediction;

[0050] The resource scheduling optimization module adjusts the resource scheduling strategy according to the real-time disaster evolution status, resource distribution and emergency response progress through a dynamic adjustment algorithm;

[0051] The communication guarantee and real-time feedback module includes a multi-path communication guarantee system, and ensures that commanders can obtain real-time feedback through satellite communication, 5G network and low-power wide-area network LPWAN communication methods.

[0052] The data acquisition and fusion module uses a dynamic weighted fusion algorithm to process multi-source data, collecting data in real time from multiple data sources, which include but are not limited to communication data: satellite communication data, navigation data: GPS data, and remote sensing monitoring data: optical satellite data. In addition to the above data, the module also obtains real-time information from data sources in the power, communication, and transportation industries. Each data source has different spatio-temporal characteristics, including update frequency, accuracy, and time span. The multi-source data collected is preprocessed, mainly including steps such as data denoising, standardization, time alignment, and spatial interpolation. These steps ensure the spatio-temporal consistency between different data sources for subsequent processing. For navigation data and remote sensing data, spatial interpolation processing is performed to make them comparable at the same spatial resolution, and time resampling is used to ensure consistency in time. A spatio-temporal feature recognition method based on deep learning, namely the convolutional neural network CNN, is used to identify the spatio-temporal features of each data source and extract key spatio-temporal patterns. The deep learning model can learn and understand the spatio-temporal relationships between different data sources, and perform effective feature extraction and optimization while keeping the characteristics of each data source unchanged. During the fusion process, according to the timeliness, accuracy, and importance of each data source in the emergency response, a dynamic weight is assigned to each data source; the weight assignment strategy is based on the following factors: satellite communication data usually has a high timeliness, so a higher weight is given; while optical satellite data may have a large spatial coverage but a low timeliness, so an appropriate lower weight is given. Dynamic weighted fusion continuously adjusts the weight of each data source through the deep learning model to ensure that data with strong timeliness and high accuracy dominates in the fusion process. The basis for dynamic weight adjustment includes the quality, timeliness of real-time data, and specific requirements in the disaster emergency scenario. Through dynamic weighted fusion, a comprehensive spatio-temporal data set is generated, covering the data characteristics from different sources. This data set contains information in multiple dimensions such as communication, navigation, and remote sensing, and has high timeliness and spatial accuracy. This fused data set will be used as the input for subsequent disaster evolution prediction, resource scheduling optimization, and emergency decision-making generation, supporting the rapid and accurate execution of disaster prevention and emergency response. The data fusion process is not static, but a real-time dynamic adjustment process. As the disaster develops and the on-site environment changes, the quality and availability of data sources may fluctuate. Therefore, the data acquisition and fusion module will adjust the fusion strategy and weights in real time according to the latest input and feedback to ensure continuous optimization of the fusion effect. The deep learning model will perform continuous learning and updating to adapt to the changes in data sources and new emergency requirements in different disaster scenarios.

[0053] The process of the disaster evolution prediction module predicting the evolution trend, impact scope, and disaster level change of a disaster to obtain the disaster evolution prediction result includes receiving multi-source data as input, which includes meteorological data, historical disaster case data, real-time sensor data, and meteorological warning information; all input data is integrated through the data acquisition and fusion module to ensure the spatio-temporal consistency and integrity of the data. Among them, the meteorological data includes temperature, precipitation, and wind speed, and the real-time sensor data includes earthquake, fire, and flood sensor data;

[0054] The NSGA-II multi-objective optimization algorithm is used to construct a disaster evolution prediction model. According to different disaster types and evolution laws, this model comprehensively considers the evolution trend, impact scope, and disaster level change of the disaster through the optimization algorithm; the NSGA-II multi-objective optimization algorithm gradually optimizes each dimension of the disaster evolution prediction through the processes of population initialization, crossover, mutation, and selection to ensure that the algorithm can give the best prediction result. By introducing historical disaster case data and real-time meteorological data, supervised learning is used to train the model so that the model can learn the laws of disaster evolution. Through historical disaster data, the model can identify the patterns and trends of disaster evolution; the model is dynamically optimized based on real-time meteorological data, sensor data, and meteorological warning data, automatically adjusting the parameters and weights in the prediction model to improve the accuracy of the prediction result; through the trained and optimized model, the disaster evolution prediction module can predict the disaster evolution trend, including key indicators such as the occurrence, expansion speed, and intensity change of the disaster. The module predicts the expansion direction and development trend of the disaster, including the path of the storm and the spread direction of the fire, by comparing real-time data and historical evolution data to obtain the disaster evolution trend;

[0055] According to the predicted disaster evolution trend, the module further calculates the possible impact scope of the disaster, including predicting the affected areas of typhoon, flood, or fire disasters according to meteorological data and disaster types; at the same time, the module evaluates the disaster level according to the evolution process of the disaster, such as from tropical storm to severe typhoon, or from small-scale fire to large-scale wildfire; the prediction results include the disaster evolution trend, the predicted impact scope, and the disaster level change. These prediction results will be used as the input for modules such as emergency decision-making, resource scheduling, and disaster response to help emergency commanders make timely and effective decisions; during the disaster occurrence process, the disaster evolution prediction module will continuously receive new real-time data, and dynamically adjust the prediction result through online learning and model update to adapt to the rapid changes of the disaster; through continuous real-time data feedback, the module can automatically correct the prediction deviation to ensure the timeliness and accuracy of the disaster evolution prediction;

[0056] The disaster evolution prediction module predicts the evolution trend, influence scope and disaster level change of the disaster, and obtains the disaster evolution prediction result, which fully demonstrates that the model based on the NSGA-II multi-objective optimization algorithm dynamically predicts the disaster evolution according to historical data, real-time data and meteorological warning data, and provides accurate decision-making basis for the emergency management system.

[0057] The specific process of the resource scheduling optimization module generating a resource scheduling plan according to the disaster evolution prediction result, on-site resource situation and emergency demand through a two-objective optimization model includes: obtaining the evolution trend, influence scope and disaster level change of the disaster from the disaster evolution prediction module; obtaining real-time information from the emergency resource database, including the quantity, location and status of available emergency supplies, personnel, vehicles and equipment; evaluating the emergency demand at the disaster site according to the type and intensity of the disaster, that is, evaluating the resource demand situation at the disaster site, including the urgent degree of medical treatment, transportation and communication.

[0058] The resource scheduling optimization module conducts a real-time assessment of the current on-site resources to determine the availability, distribution, remaining quantity and urgency of various resources; the module will also predict the resource demand in combination with the evolution of the disaster; it is included that in the initial stage of the disaster, the module may predict a relatively high demand for transportation and communication equipment resources; and as the disaster expands, the demand for medical treatment and material resources may increase.

[0059] The resource scheduling optimization module constructs a two-objective optimization model and sets two objectives, including Objective 1 and Objective 2, aiming to achieve optimization in two aspects. Objective 1: Minimize the time of resource scheduling to ensure that resources can reach the demand area as soon as possible and avoid delaying emergency rescue; especially ensure that the resource scheduling time does not exceed 15% of the 72-hour golden rescue standard. Objective 2: Maximize the resource scheduling benefit to ensure the reasonable allocation and efficient utilization of resources, so that limited resources can cover more disaster-stricken areas and meet key needs, and avoid resource waste or over-allocation.

[0060] By using the advanced optimization algorithm NSGA-II and considering the balance between scheduling time and benefit at the same time; the optimization process calculates the possibility of different resource scheduling plans based on the disaster evolution prediction result, resource status and demand; the model selects the optimal solution by comparing different scheduling plans to ensure that the resource scheduling after the disaster can respond in a timely and effective manner.

[0061] Through an optimization algorithm, the resource scheduling optimization module generates a set of resource scheduling plans that meet timeliness and benefits; the plans include the specific allocation paths of each resource, the required transportation methods, the priorities of allocation, and the time nodes; after the plans are generated, the module will fine-tune the plans according to the dynamic situation of real-time resources to ensure that the plans can adapt to the changing disaster process and on-site conditions; the generated resource scheduling plans will be notified to the emergency command personnel through the command decision-making module to initiate the resource allocation operation; during the execution of resource scheduling, the module will monitor information such as disaster evolution, resource allocation, and task progress in real time to ensure that the scheduling plans can be executed smoothly; if there are resource shortages, demand changes, or the disaster evolution speed accelerates, the module will dynamically adjust the existing scheduling plans and reallocate resources to cope with new challenges; the resource scheduling optimization module will continuously receive data from emergency command personnel and on-site feedback and optimize the scheduling plans in real time according to the latest situation; as the disaster progresses, the module will continuously adjust the resource scheduling plans to ensure that all resources can be quickly and efficiently deployed and allocated within the golden rescue time.

[0062] Based on the disaster evolution prediction results, on-site resource conditions, and emergency requirements, the resource scheduling optimization module generates resource scheduling plans through a bi-objective optimization model. The process includes data acquisition, resource evaluation, bi-objective optimization, plan generation, execution, and dynamic adjustment to ensure that emergency resource scheduling can efficiently and accurately respond to the changes in disasters and maximize the emergency response efficiency.

[0063] The command decision-making module includes an intelligent push system. The intelligent push system automatically pushes decision-making plans to emergency command personnel according to the disaster situation, resource conditions, and task requirements.

[0064] The process of the command and decision-making module generating emergency command decisions by analyzing and integrating multi-source data, disaster evolution prediction results, and resource scheduling plans: The command and decision-making module receives data from different sources, including the integrated multi-source data, disaster evolution prediction results, and resource scheduling plans. The integrated multi-source data is provided by the data collection and integration module and includes communication data, navigation data, and remote sensing monitoring data. The disaster evolution prediction results are the evolution trend, impact scope, and disaster level of the disaster generated by the disaster evolution prediction module. The resource scheduling plan is the resource allocation plan generated by the resource scheduling optimization module and includes the allocated resources, scheduling routes, and priorities. The command and decision-making module comprehensively analyzes the input data to obtain analysis results. The analysis process includes: Conducting disaster situation analysis: Analyze the current and predicted disaster situations, and evaluate the expansion trend, affected areas, and danger levels of the disaster by comparing the disaster evolution prediction results with real-time data. Conducting resource status assessment: Evaluate the status of currently available emergency resources and the resources that have been scheduled to ensure whether the resources are effectively utilized and can meet the demands brought about by the expansion of the disaster. Conducting emergency task requirement analysis: Analyze the completion status of current emergency tasks and future resource requirements based on disaster evolution and resource scheduling, and evaluate whether there are task delays or resource shortages.

[0065] Based on the analysis results, the command and decision-making module generates emergency command decisions, including: Assigning tasks: According to the urgency of the disaster and resource availability, the command and decision-making module generates clear task assignments, including instructions to dispatch rescue personnel, materials, and equipment to different disaster areas. Adjust the priorities of emergency resources according to real-time feedback and predicted disaster development, and generate resource scheduling commands to ensure that resources can be promptly deployed to the areas in greatest need. Generate an optimized emergency response plan, including task assignment, resource scheduling, and material supply.

[0066] The command and decision-making module includes the allocation and progress monitoring of emergency tasks, and adjusts the execution priorities of emergency tasks in real time to automatically optimize the emergency response plan under different disaster scenarios.

[0067] The process of the command and decision-making module for real-time adjustment of the execution priority of emergency tasks includes: The command and decision-making module uses an intelligent push system to push the generated emergency command decisions to emergency command personnel in real time, ensuring that they can timely understand the disaster dynamics, resource status, and task instructions; The pushed content includes the current disaster situation, resource scheduling status, and task priority, helping command personnel make decisions quickly; The command and decision-making module continuously monitors the progress of various emergency tasks, including task execution status, resource allocation, and on-site feedback; According to the real-time development of the disaster, on-site feedback, and resource availability, the command and decision-making module evaluates the priority of current emergency tasks; For example, if the resource demand in the severely affected area is high, the task priority in that area will be increased; When the disaster situation changes, new disaster areas emerge, or there is a shortage of resources in a certain area, the command and decision-making module will adjust the execution priority of tasks in real time to ensure that the emergency response always focuses on the most critical areas; The module automatically updates the task execution instructions according to the change in priority and provides real-time feedback to relevant emergency personnel to ensure that they complete tasks according to the latest priority; Based on the real-time task execution situation and priority adjustment, the command and decision-making module will continuously optimize the emergency response plan; For example, if the disaster situation develops rapidly, the command and decision-making module can allocate more resources to high-priority areas; This optimization process is a dynamic, feedback-driven process that continuously adjusts the emergency response strategy through real-time data, on-site feedback, and task progress monitoring.

[0068] By analyzing the fused multi-source data, disaster evolution prediction results, and resource scheduling plans through the command and decision-making module, emergency command decisions are generated, and the resource deployment and emergency response situation are provided to the command personnel in real time through the intelligent push system; The process of real-time adjustment of the execution priority of emergency tasks ensures that during the rapid evolution of disasters, the emergency response plan can be optimized in a timely manner, improving the timeliness and effectiveness of disaster response.

[0069] The process of the communication guarantee and real-time feedback module for ensuring stable communication between the emergency command system and on-site personnel includes: Before the disaster occurs, the communication guarantee and real-time feedback module evaluates the communication requirements; The evaluation content includes the communication environment in the disaster area, the availability of communication infrastructure, and the communication requirements of on-site personnel and emergency equipment; The module will evaluate the key areas and personnel that need to ensure communication according to the type, scale, and affected area of the disaster, ensuring stable communication between key resources and the command system during the disaster.

[0070] To ensure the reliability of communication during disasters, the communication guarantee and real-time feedback module configures a multi-path communication system, including the deployment of satellite communication, 5G network, and low-power wide-area network LPWAN. The deployment process is as follows: Satellite communication: During disasters, especially when the ground communication network is damaged or unavailable, satellite communication provides stable global coverage to ensure uninterrupted communication between the command center and on-site personnel; 5G network: The 5G network provides high-bandwidth and low-latency communication capabilities, capable of supporting real-time data transmission, such as video surveillance, real-time location tracking, and big data uploading, to ensure that commanders can obtain instant feedback on the on-site situation; Low-power wide-area network LPWAN: Suitable for large-scale and low-power sensor data transmission, especially in areas far from the city center or with limited communication infrastructure, to ensure communication remains unobstructed even in remote areas; According to the type of disaster, affected area, and on-site environment, the communication guarantee and real-time feedback module automatically selects the most suitable communication link; including, in urban areas, giving priority to using the 5G network for fast data transmission; while in remote areas without 5G signals, giving priority to enabling satellite communication or LPWAN; The module continuously monitors the stability and quality of each communication link and dynamically adjusts the communication method used according to the real-time status of the link to ensure the stability and reliability of the communication system;

[0071] The communication guarantee module monitors the quality of all communication links in real time, including signal strength, bandwidth, latency, and packet loss rate; The module can identify the risk of communication interruption or quality degradation in real time and quickly take countermeasures; If an abnormal communication link is detected, such as signal loss or excessive transmission delay, the communication guarantee module will automatically switch to the backup link; including: when a ground communication base station fails, the module will automatically enable the satellite communication link to restore communication and ensure uninterrupted communication between emergency commanders and on-site personnel;

[0072] According to the severity of the disaster situation and on-site feedback, the communication guarantee module adjusts the allocation of communication resources in real time; including, in key areas of the disaster area: post-disaster rescue or medical rescue points, the communication guarantee module will give priority to ensuring the communication needs of these areas; The module ensures smooth communication between the command center and on-site personnel, rescue teams, and medical personnel by dispatching existing communication resources, reducing any potential communication bottlenecks;

[0073] On-site personnel use the real-time feedback mechanism, which includes voice communication, video backhaul, and data uploading, to send the latest situation in the disaster area back to the command center; The communication guarantee module ensures the stable transmission of this information and prevents command lag caused by poor communication; Commanders make decisions based on on-site information and transmit new instructions, dispatching plans, and decisions to on-site personnel through the same communication link to ensure real-time synchronization of on-site response and command;

[0074] As the disaster progresses, the communication guarantee and real-time feedback module continuously optimizes the communication plan based on new real-time data and on-site feedback; the module adaptively adjusts the priority and the allocation of communication resources to ensure that the communication needs of critical tasks are met; during the disaster response process, the module adjusts its communication strategy through continuous monitoring and feedback to ensure stable and reliable communication between the emergency command system and on-site personnel under any disaster scenario;

[0075] The communication guarantee and real-time feedback module ensures stable communication between the emergency command system and on-site personnel; through the multi-path communication guarantee system, combining communication means such as satellite communication, 5G network and LPWAN, it ensures that communication is not interrupted during a disaster; it also has functions of automatic monitoring, recovery and optimization of communication links to ensure stable communication between the command center and on-site personnel under different disaster scenarios to support efficient emergency response.

[0076] The process of the command and decision-making module for real-time adjustment of the execution priority of emergency tasks is as follows: the command and decision-making module evaluates and analyzes the emergency tasks through the disaster evolution prediction results, on-site resource situation and emergency requirements; based on the type, severity, resource allocation and task urgency of the disaster, the module assigns specific emergency tasks; sets the priority, and according to the task urgency, the affected area of the disaster area, the availability of existing resources and their importance in the disaster response, the module assigns a priority to each task, and high-priority tasks are processed first. High-priority tasks include rescue in severely affected areas and restoration of important infrastructure; the command and decision-making module matches the available resources on-site with the task requirements; the module ensures that each task can obtain appropriate resource support through intelligent allocation to ensure the smooth execution of the task. Among them, the available resources on-site include rescue teams, materials and equipment;

[0077] For the progress monitoring of emergency tasks, the command and decision-making module continuously tracks the execution progress of tasks through on-site feedback; the module evaluates the completion status of tasks to ensure that it is carried out according to the predetermined time frame. On-site feedback includes real-time data, video monitoring and task reports;

[0078] The module compares the task progress with the predetermined progress and automatically updates the task execution status according to the progress; if there is a delay, the module will identify the reason and adjust the resource allocation or task allocation in a timely manner;

[0079] The command and decision-making module dynamically evaluates the priority of tasks according to new data, on-site task execution progress and resource status during the disaster evolution process; according to the change of the disaster situation, the module makes real-time adjustment to the priority of tasks. Among them, the change of the disaster situation includes the spread of the disaster and the emergence of more resource requirements;

[0080] Automatic priority adjustment: If the disaster situation changes, the module will automatically adjust the priority of tasks; for example, if the disaster situation in a certain area intensifies, the module will automatically increase the priority of tasks in that area and allocate more resources to respond in that area; after the priority adjustment, the command and decision-making module updates the task allocation according to the adjusted priority to ensure that resource allocation gives priority to supporting high-priority tasks; the module automatically generates new scheduling instructions and transmits the updated task instructions to the executors in real time;

[0081] The command and decision-making module updates the task instructions according to the adjusted priority and resource allocation situation; the new task instructions will be transmitted to the on-site emergency personnel through the communication guarantee system to ensure that the on-site task execution meets the latest priority requirements; the module continuously collects on-site feedback and adjusts the task execution under real-time monitoring; as the tasks progress, the module continuously optimizes the resource allocation to ensure flexibility and efficiency during the response process;

[0082] Through the command and decision-making module, during the disaster emergency response, by allocating and monitoring the progress of emergency tasks and adjusting the execution priority of tasks in real time, it is ensured that emergency tasks can be allocated and adjusted according to the real-time disaster situation priority, resources can be optimally utilized, and the disaster response can be carried out accurately and efficiently;

[0083] The disaster prevention and emergency communication command and management system based on communication, navigation, and remote sensing technologies of the present invention can significantly reduce the lag of disaster emergency decision-making and improve the emergency response efficiency by using efficient data collection and fusion algorithms, accurate disaster evolution prediction models, and optimized resource scheduling schemes; through intelligent decision support and resource scheduling, it is ensured that emergency command personnel can make correct decisions quickly and efficiently, minimize the losses caused by disasters, and ensure that emergency resources can be allocated in a timely manner in extreme situations to ensure that the emergency response is not interrupted, where extreme situations include base station damage and network interruption.

[0084] It should be further noted that in the specific implementation process, disaster warning and data collection are carried out first: after the typhoon warning is issued, the data collection and fusion module starts to work and collects data in real time from different data sources: meteorological bureaus, satellites, 5G communication networks, and navigation data; the steps are as follows:

[0085] S1: Meteorological data: The path, wind speed, and precipitation of the typhoon are obtained in real time through meteorological sensors and satellite remote sensing equipment;

[0086] S2: Navigation data: The Beidou / GPS system provides real-time positioning information of the disaster area for analyzing the geographical distribution of the disaster situation;

[0087] S3: Remote sensing data: The affected area and facility damage situation of the disaster area are monitored using SAR / optical satellite images;

[0088] S4: Communication Data: Collect the communication status of the disaster area through the 5G / satellite communication network, including network disconnection and base station damage;

[0089] The data acquisition and fusion module preprocesses the above data sources, including denoising, standardization, and time alignment, to ensure the spatio-temporal consistency of the data; adopts deep learning methods to dynamically adjust the weights of the data sources to ensure that high-timeliness data dominates in the fusion, where high-timeliness data includes 5G communication data;

[0090] Conduct disaster evolution prediction: The disaster evolution prediction module predicts the evolution trend, influence range, and disaster level of the typhoon based on real-time data and historical case data through an improved NSGA-II multi-objective optimization algorithm;

[0091] Through model calculation, it is predicted that the typhoon will affect the coastal areas within 72 hours, the wind speed will continue to increase, and severe storm surges and heavy rainfall are expected; according to the disaster evolution results, the model predicts that the affected areas of the disaster include provinces such as Guangdong, Fujian, and Zhejiang, and may affect millions of residents; according to real-time meteorological data, it is predicted that the typhoon will gradually upgrade from a tropical storm to a severe typhoon, and the disaster level of the affected disaster area will gradually increase;

[0092] The resource scheduling optimization module generates a resource scheduling plan based on the disaster evolution prediction results and emergency requirements; assuming that the disaster area requires a large amount of medical resources, emergency personnel, and transportation vehicles, the process is as follows: The module accesses the emergency resource database and evaluates the available resources on site, including medical equipment, rescue personnel, relief supplies, and transportation vehicles;

[0093] Set scheduling goals: Goal 1: Minimize the time of resource scheduling to ensure that supplies and personnel can reach the disaster area within 72 hours; Goal 2: Maximize the resource scheduling benefit, reasonably allocate resources, avoid waste, and ensure that key areas can receive sufficient support; through the NSGA-II optimization algorithm, the module generates multiple scheduling plans and selects the optimal plan to ensure that medical rescue teams and urgently needed supplies can reach the disaster area in time, and optimize the allocation of transportation vehicles according to the resource allocation situation;

[0094] The command and decision-making module generates emergency command decisions based on the disaster evolution prediction results, resource scheduling plans, and real-time feedback information; emergency command personnel view the situation of the disaster area through the visualization platform and receive intelligent push resource allocation instructions; the command and decision-making module dynamically adjusts the task priorities, and medical assistance and disaster area rescue in high-priority tasks will be given priority;

[0095] According to the evolution process of the disaster, the resource allocation instructions are updated in real time to ensure the deployment of key resources in the areas where they are most needed; the command personnel receive task instructions in real time to ensure the synchronization of resource scheduling and on-site task execution;

[0096] The communication guarantee and real-time feedback module ensures stable communication between the disaster area and the command center; during a disaster, especially when some base stations are damaged, satellite communication and 5G networks provide stable communication guarantees; the module adjusts the communication link in real time according to the communication quality to ensure that commanders can obtain on-site feedback at any time and make task adjustments;

[0097] Through the above embodiments, the practical application of the present invention in emergency disaster management is demonstrated. The system ensures the efficiency and accuracy of disaster response through efficient data collection and fusion, accurate disaster evolution prediction, intelligent resource scheduling optimization, flexible command decision generation, and reliable communication guarantee links; within 72 hours after the disaster occurs, the system helps emergency commanders allocate resources and tasks in a timely manner, and through intelligent decision support, maximizes rescue benefits and minimizes disaster losses.

[0098] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0099] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A disaster prevention emergency communication command and management system based on communication, navigation and remote control technology, characterized in that: include: Data acquisition and fusion module, used to obtain multi-source data from communication network status, navigation positioning information, and remote sensing monitoring data, and use dynamic weighted fusion algorithm to process multi-source data; The disaster evolution prediction module uses the NSGA-II multi-objective optimization algorithm to predict the evolution trend, impact range and disaster level changes of disasters based on disaster types, evolution laws and real-time data, and obtains disaster evolution prediction results; The resource scheduling optimization module, based on the disaster evolution prediction results, on-site resource conditions and emergency needs, accesses the emergency resource database, intelligently allocates emergency materials, personnel, vehicles and equipment information, and generates resource scheduling plans through a dual-objective optimization model; The command decision module is used to analyze the integrated multi-source data, disaster evolution prediction results and resource scheduling plans, generate emergency command decisions, and provide real-time feedback on resource deployment and emergency response to commanders through a visualization platform; The communication guarantee and real-time feedback module ensures stable communication between the emergency command system and on-site personnel, and provides communication feedback when a disaster occurs by combining satellite communication and 5G networks; Among them, the data acquisition and fusion module adopts a spatiotemporal feature recognition method based on deep learning for data fusion; the data acquisition and fusion module includes a data center, which is connected to multiple data sources, including data from the power, communication, and transportation industries, to perform real-time analysis and fusion of spatiotemporal data; the disaster evolution prediction module introduces meteorological data and historical disaster cases for training; the resource scheduling optimization module adjusts the resource scheduling strategy according to the real-time evolution status of the disaster, resource distribution, and emergency response progress through a dynamic adjustment algorithm; The data acquisition and fusion module uses a dynamic weighted fusion algorithm to process multi-source data, collects data from multiple data sources in real time, obtains real-time information from data sources in the power, communication, and transportation industries, pre-processes the collected multi-source data, and identifies the spatiotemporal features of each data source based on a deep learning spatiotemporal feature recognition method, extracts key spatiotemporal patterns, and assigns dynamic weights to each data source based on its timeliness, accuracy, and importance in emergency response; generates a spatiotemporal data set through dynamic weighted fusion as input for subsequent disaster evolution prediction, resource scheduling optimization, and emergency decision-making; The disaster evolution prediction module predicts the evolution trend, impact range and disaster level changes of disasters to obtain the disaster evolution prediction results, receives multi-source data as input, adopts the NSGA-II multi-objective optimization algorithm, constructs a disaster evolution prediction model, and considers the evolution trend, impact range and disaster level changes of disasters through the optimization algorithm according to different disaster types and evolution laws; optimizes the disaster evolution prediction dimension through population initialization, crossover, mutation and selection processes, introduces historical disaster case data and real-time meteorological data, uses supervised learning to train the model, dynamically optimizes based on real-time meteorological data, sensor data and meteorological warning data, automatically adjusts the parameters and weights in the prediction model, predicts the disaster evolution trend through the trained and optimized model, compares the real-time data and historical evolution data, predicts the expansion direction and development trend of the disaster, and obtains the disaster evolution trend; calculates the disaster impact range according to the disaster evolution trend, and at the same time, evaluates the disaster level according to the evolution process of the disaster; The resource scheduling optimization module generates a resource scheduling plan through a dual-objective optimization model according to the disaster evolution prediction results, on-site resource conditions and emergency needs. The process includes: obtaining the evolution trend, impact range and disaster level change of the disaster; obtaining real-time information from the emergency resource database, evaluating the emergency needs of the disaster site according to the type and intensity of the disaster, and conducting a real-time evaluation of the current on-site resources to determine the resource availability, distribution, remaining quantity and urgency; predicting the resource demand in combination with the evolution of the disaster; constructing a dual-objective optimization model, setting two goals, including goal one and goal two, and calculating the possibility of different resource scheduling plans by considering the balance between scheduling time and benefits through the optimization algorithm NSGA-II, and generating a resource scheduling plan through the optimization algorithm; the resource scheduling plan notifies the emergency command personnel through the command decision module to start the resource allocation operation.

2. According to claim 1, a disaster prevention emergency communication command and management system based on communication, navigation and remote control technology is characterized by: The command decision module includes an intelligent push system, which automatically pushes decision plans to emergency commanders based on disaster situations, resource conditions and task requirements.

3. The disaster prevention emergency communication command and management system based on communication, navigation and remote control technology according to claim 2 is characterized by: The command decision module analyzes the integrated multi-source data, disaster evolution prediction results and resource scheduling plans to generate an emergency command decision process: receiving data from different sources, comprehensively analyzing the input data to obtain analysis results. The analysis process includes: analyzing the current and predicted situation of the disaster, and evaluating the expansion trend, affected area and degree of danger of the disaster by comparing the disaster evolution prediction results with real-time data; evaluating the status of currently available emergency resources and scheduled resources; analyzing the completion status of the current emergency task and future resource requirements based on the disaster evolution and resource scheduling, and evaluating whether the task is delayed or there is a shortage of resources; based on the analysis results, the command decision module generates an emergency command decision.

4. The disaster prevention emergency communication command and management system based on communication, navigation and remote control technology according to claim 3 is characterized by: The command decision module includes the allocation and progress monitoring of emergency tasks, and real-time adjustment of emergency task execution priorities.

5. The disaster prevention emergency communication command and management system based on communication, navigation and remote control technology according to claim 4 is characterized by: The process of the communication guarantee and real-time feedback module ensuring stable communication between the emergency command system and on-site personnel includes: evaluating communication needs before a disaster occurs; the evaluation content includes the communication environment in the disaster area, the availability of communication infrastructure, and the communication needs of on-site personnel and emergency equipment. According to the type, scale and affected area of ​​the disaster, the key areas and personnel that need to ensure communication are evaluated, and a multi-path communication system is configured, including the deployment of satellite communication, 5G network and low-power wide area network LPWAN, and communication links are selected according to the type of disaster, affected area and on-site environment; the stability and quality of each communication link are continuously monitored, and the communication mode used is adjusted according to the real-time status of the link; the quality of the communication link is monitored in real time, the risk of communication interruption or quality degradation is identified in real time, and countermeasures are taken; if an abnormality in the communication link is detected, it is automatically switched to the backup link; the allocation of communication resources is adjusted in real time according to the severity of the disaster and on-site feedback.

6. The disaster prevention emergency communication command and management system based on communication, navigation and remote control technology according to claim 5 is characterized by: The process of the command decision module adjusting the priority of emergency task execution in real time includes: through the intelligent push system, the generated emergency command decision is pushed to the emergency command personnel in real time, and the push content includes the current disaster situation, resource scheduling status, and task priority. The progress of various emergency tasks is continuously monitored, and the priority of the current emergency task is evaluated according to the real-time development of the disaster, on-site feedback and resource availability. When the disaster situation changes, the execution priority of the task is adjusted, and according to the change in priority, the task execution instructions are updated and fed back to the emergency personnel.

7. The disaster prevention emergency communication command and management system based on communication, navigation and remote control technology according to claim 6 is characterized by: The process of the command decision module adjusting the priority of emergency task execution in real time is as follows: evaluating and analyzing the emergency tasks through disaster evolution prediction results, on-site resource conditions and emergency needs; assigning emergency tasks based on the type, severity, resource allocation and task urgency of the disaster; Priority setting: assigning priority to each task based on the urgency of the task, the scope of the disaster area, the availability of existing resources and their importance in disaster response. High-priority tasks are given priority, matching the available resources on site with the task requirements; monitoring the progress of emergency tasks, continuously tracking the progress of task execution through on-site feedback; evaluating the completion status of tasks; comparing the progress of tasks with the scheduled progress, and automatically updating the task execution status based on the progress; dynamically evaluating the priority of tasks based on new data during the evolution of the disaster, the progress of on-site task execution and the status of resources; adjusting the priority of tasks in real time based on changes in the disaster situation; adjusting the priority of tasks if the disaster situation changes; After the priority is adjusted, the task allocation is updated according to the adjusted priority to generate new scheduling instructions, and the updated task instructions are transmitted to the executors in real time.

Images