Air-ground collaborative management method based on mutual inductance verification

Abstract

The application discloses an air-ground collaborative management method based on mutual sensing verification, relates to the technical field of intelligent sensing, and comprises the following steps: determining a target area, arranging multiple groups of sensors, collecting and acquiring air parameter data and ground parameter data; transmitting the data to a data processing center through wireless communication technology to extract key information, acquire air key information and ground key information; presetting mutual sensing verification indexes, verifying the air key information and the ground key information, and acquiring verification results; if the verification results are accurate, inputting an air-ground collaborative management decision model to acquire a collaborative management decision; and performing air-ground collaborative management based on the collaborative management decision. The technical problem that the traditional air-ground collaborative management method in the prior art cannot comprehensively reflect the reliability of data and further leads to time delay of the collaborative management decision because the traditional air-ground collaborative management method relies on manual monitoring and scheduling is solved, and the technical effects of improving the accuracy and timeliness of data processing and management decisions are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent sensing technology, in particular to an air-ground collaborative management method based on mutual sensing verification. BACKGROUND

[0002] With the development of big data and artificial intelligence, air-ground collaborative systems have received widespread attention in recent years. It is a comprehensive management technology that involves the collaborative management of air traffic and ground traffic. This approach has been applied in multiple fields. Modern air-ground collaborative management methods use artificial intelligence and machine learning algorithms to achieve intelligent management and control of the transportation system. For example, by using machine learning algorithms, traffic flow and congestion can be predicted, and appropriate management decisions can be made in advance to improve the efficiency and smoothness of the transportation system.

[0003] Traditional air-ground collaborative management methods mainly rely on manual monitoring and scheduling. This approach has some technical limitations when dealing with air-ground coordination issues, and cannot fully reflect the reliability of the data, resulting in delays in collaborative management decisions. This application introduces a verification index through comprehensive analysis of air-ground data, which can enhance data processing capabilities and improve the efficiency of air-ground collaborative management. SUMMARY

[0004] The embodiments of the present application provide an air-ground collaborative management method based on mutual sensing verification, which solves the technical problem of the traditional air-ground collaborative management method in the prior art, which relies on manual monitoring and scheduling and cannot fully reflect the reliability of the data, resulting in delays in collaborative management decisions, and achieves the technical effect of improving the efficiency and accuracy of data processing and management decisions.

[0005] In view of the above problems, the embodiments of the present application provide an air-ground collaborative management method based on mutual sensing verification, which comprises: determining a target area, arranging multiple groups of sensors in the target area, respectively collecting air data and ground data, obtaining air parameter data and ground parameter data; transmitting the air parameter data and the ground parameter data to a data processing center based on wireless communication technology; extracting key information from the air parameter data and the ground parameter data based on the data processing center, obtaining air key information and ground key information; presetting a mutual sensing verification index, verifying the air key information and the ground key information based on the mutual sensing verification index, obtaining a verification result; based on the verification result, if the verification result is accurate, inputting an air-ground collaborative management decision model to obtain a collaborative management decision; based on the collaborative management decision, air-ground collaborative management is performed.

[0006] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0007] The air-ground collaborative management method based on mutual sensing verification provided by the embodiment of the application, through the sensor arranged in the target area, collects air and ground data, obtains air parameter data and ground parameter data, transmits to the data processing center through wireless communication technology to extract key information, obtains air key information and ground key information; preset mutual sensing verification index, verify the air key information and ground key information, obtain the verification result; if the verification result is accurate, input the air-ground collaborative management decision model, obtain the collaborative management decision; based on the collaborative management decision, the air-ground collaborative management is carried out. The technical problem that the traditional air-ground collaborative management method in the prior art cannot fully reflect the reliability of the data due to the dependence on manual monitoring and scheduling, and further leads to the time delay of the collaborative management decision is solved, and the technical effects of improving the efficiency and accuracy of data processing and management decision are achieved.

[0008] The above description is only a summary of the technical scheme of the application, in order to better understand the technical means of the application, which can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 The flowchart of the air-ground collaborative management method based on mutual sensing verification provided by the embodiment of the application is shown in the figure;

[0010] Figure 2 The flowchart of obtaining the verification result in the air-ground collaborative management method based on mutual sensing verification provided by the embodiment of the application is shown in the figure;

[0011] Figure 3 The flowchart of obtaining the collaborative management decision in the air-ground collaborative management method based on mutual sensing verification provided by the embodiment of the application is shown in the figure;

[0012] Figure 4 The flowchart of obtaining the air-ground collaborative management decision model in the air-ground collaborative management method based on mutual sensing verification provided by the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0013] The embodiment of the application provides an air-ground collaborative management method based on mutual sensing verification, which is used to solve the technical problem that the traditional air-ground collaborative management method in the prior art cannot fully reflect the reliability of the data due to the dependence on manual monitoring and scheduling, and further leads to the time delay of the collaborative management decision, and achieves the technical effects of improving the efficiency and accuracy of data processing and management decision.

[0014] In order to better understand the above technical scheme, the above technical scheme will be described in detail in combination with the drawings of the specification and the specific embodiments.

[0015] like Figure 1 As shown in the figure, this application provides an air-ground cooperative management and control method based on mutual inductance verification, the method including the following steps:

[0016] S100: Determine the target area, and deploy multiple sets of sensors within the target area to collect air data and ground data respectively, thereby obtaining air parameter data and ground parameter data.

[0017] Specifically, the target area is determined, and different types of sensors are installed in the area to be monitored to collect various data from the air and the ground, acquiring air and ground parameter data. The target area is the selected area that needs to be monitored, including areas requiring special management due to security, traffic, or other reasons. Multiple sets of sensors are deployed to cover different monitoring needs. These sensors include radar, cameras, thermometers, ground sensors, weather detectors, and environmental sensors. The sensors collect air and ground data from the target area. Air data includes the position, speed, and altitude of aircraft, as well as images and videos acquired from the air. Air parameter data refers to the identification of aerial targets, such as airplanes and drones, from images or signals collected by radar, drones, and other sensor equipment using image processing and pattern recognition technologies. Ground data includes traffic flow, population density, and environmental conditions. Ground parameter data refers to data generated by monitoring road traffic flow, vehicle speed, and other parameters through ground sensors or cameras, and then analyzing traffic conditions. For example, a city needs to host a large-scale concert, expected to attract hundreds of thousands of attendees and significant media attention. To ensure the smooth running of the event, the organizers and city security department decide to adopt an air-ground collaborative control method based on mutual sensing verification. The target area would be set at the concert venue and its surrounding area within a few kilometers, or even further. Cameras, drones, air quality detectors, and other sensors would be installed inside and outside the venue, deployed as needed, to collect data from the air and ground in the venue area, including crowd flow, vehicle congestion, drone surveillance video, and air traffic data. By deploying multiple sets of sensors to collect data, comprehensive environmental awareness can be obtained, supporting subsequent analysis and decision-making.

[0018] S200: The air-to-ground parameter data and the ground parameter data are transmitted to the data processing center using wireless communication technology.

[0019] Specifically, the collected air and ground parameter data are transmitted in real time to the data processing center via wireless communication technology. Wireless communication technology is a communication method that utilizes the characteristics of electromagnetic waves propagating in free space for information exchange. It enables contactless data transmission between electronic devices, thereby achieving information transfer and real-time data processing. This ensures the stability and security of data transmission, preventing data loss or tampering and reducing communication interference. The data processing center is responsible for receiving, storing, processing, and analyzing data from various sources. In the air-ground collaborative control system, the data processing center plays a crucial role, acting as the "brain" of the entire system. It is responsible for processing and analyzing data from air and ground sensors, generating critical information and decision support based on this data. Simultaneously, the data processing center possesses powerful data storage capabilities, capable of storing large amounts of raw and processed data. It can monitor data flow in real time, ensuring data accuracy and integrity, promptly monitoring data changes, and quickly responding to emergencies, providing decision-makers with critical information and decision support. For example, transmitting collected air and ground data from the concert venue area to the data processing center in real time via wireless network enables real-time data monitoring and analysis, helping to improve monitoring and management efficiency and ensuring the system can effectively cope with various challenges.

[0020] S300: Based on the data processing center, key information is extracted from the air-to-air parameter data and the ground parameter data to obtain key air-to-air information and key ground information.

[0021] Specifically, the data processing center processes the acquired air and ground parameter data to extract key air and ground information. Key information refers to data extracted from a large volume of data that directly impacts subsequent decision-making, such as real-time location, movement trajectory, and conflict information. The data processing center employs different technologies and methods when extracting air and ground parameter data. Processing and analyzing the collected data to extract key information effectively reduces the possibility of data errors. For air parameter data, remote sensing satellite data and radar can be used to extract the movement trajectory and parameter changes of relevant aerial targets. For ground parameter data, more accurate terrain and traffic information can be obtained through UAV remote sensing systems and ground observation technologies. For example, the data processing center uses advanced data analysis algorithms to extract key information, such as crowd gathering hotspots, potential security threats, and traffic congestion points, providing more valuable data support and improving the efficiency and accuracy of the air-ground collaborative control system.

[0022] S400: Preset mutual inductance verification index, and verify the air key information and the ground key information based on the mutual inductance verification index to obtain the verification result.

[0023] Specifically, based on monitoring objectives and control requirements, a set of verification indicators is established to verify the key airspace information and the key ground information, and to obtain verification results. Verification indicators are a set of standards used to evaluate and verify the consistency and accuracy of data between different sensors or monitoring systems, including data range, rate of change, thresholds, etc., used to detect whether the data is within a reasonable range. Verifying key airspace information and key ground information using preset verification indicators involves comparing data from different sensors, evaluating data ranges, etc., to ensure the accuracy and reliability of the data. Mutual inductance verification technology, based on the principle of electromagnetic induction, achieves accurate measurement and verification of electrical energy by measuring parameters such as voltage and current of mutual inductors. In key information verification, mutual inductance verification technology can be analogously applied to data verification. Specifically, one or more verification standards or models can be set, and the collected data can be compared with these standards or models to verify the accuracy and consistency of the data. Through comparison, verification results are obtained to determine the accuracy and reliability of the data. The verification results include the verification results of each mutual inductance verification indicator and a comprehensive verification coefficient. If the verification results are accurate, these data will be used for subsequent decision support. Mutual inductance verification technology ensures accurate information transmission and reception by calibrating and verifying the communication and data exchange processes between unmanned systems, thus providing reliable data support for the collaborative control of unmanned systems. The application of mutual inductance verification technology improves the accuracy and efficiency of air-to-ground collaborative management and control, reducing risks caused by information errors or inconsistencies. It enables unmanned systems to perform tasks with greater confidence, especially in information sharing, target localization, path planning, and obstacle avoidance, thereby enhancing overall collaborative combat capabilities. Furthermore, mutual inductance verification helps improve the system's anti-interference capabilities and environmental adaptability, enabling unmanned systems to operate stably in more complex and variable environments. For example, setting mutual inductance verification indicators for concert venues and management requirements, and verifying the collected data to ensure its accuracy, helps prevent potential dangers in advance and improves overall safety and security capabilities.

[0024] S500: Based on the verification result, if the verification result is accurate, input the air-ground collaborative management and control decision model to obtain the collaborative management and control decision.

[0025] Specifically, based on the verification results, if the data is accurate, it will be input into the air-ground collaborative control decision-making model to obtain collaborative control decisions. The air-ground collaborative control decision-making model is a complex algorithm or system that uses data collected from air and ground sensors, verified through a mutual sensing mechanism, to formulate specific control measures and decisions. This model is typically based on artificial intelligence, machine learning, operations research, and other optimization techniques, aiming to achieve efficient and intelligent decision support. Collaborative control decisions refer to the specific decision results output by the model, which guide how to implement specific control measures in the air and on the ground, including but not limited to adjusting traffic flow, strengthening security measures in target areas, guiding crowd movement, and optimizing resource allocation. The core advantage of the air-ground collaborative control decision-making model lies in its ability to comprehensively analyze air and ground data and quickly generate optimal control strategies based on this information. This approach helps improve response speed and decision quality, thereby achieving more effective management in complex and dynamic environments. For example, based on the verification results, if the data is accurate, it is input into the air-ground collaborative management and control decision model, and control measures are proposed based on the analysis results, such as adjusting traffic flow, guiding crowd evacuation, and strengthening security measures in specific areas.

[0026] S600: Perform air-ground collaborative management based on the aforementioned collaborative management decision.

[0027] Specifically, based on the results of the output collaborative control decisions, on-site personnel and the command center conduct real-time air-ground collaborative control, achieving coordinated management of air and ground resources, optimizing resource allocation, and improving management efficiency. For example, based on the decision-making model and the decision results obtained from the analysis of the concert venue, on-site security personnel and the command center conduct real-time collaborative control.

[0028] Furthermore, step S100 provided in this application embodiment also includes:

[0029] S110: Access historical air parameter data and historical ground parameter data, and extract the types of target data collected;

[0030] S120: Determine the multiple sets of sensors based on the types of target data collected;

[0031] S130: Deploy sensors based on the multiple sets of sensors and the target area;

[0032] S140: Based on the multiple sets of sensors, data is collected from the target area to obtain air parameter data and ground parameter data.

[0033] Specifically, based on historical air and ground parameter data, including data collected in the past in the target area or similar areas, this data helps to understand the characteristics and needs of the target area. Through analysis of historical data, the system identifies key data types that need to be collected, including specific types of meteorological data, traffic flow, and population density. Based on the required data types, multiple sets of sensors are determined. For example, cameras and geomagnetic sensors are selected to monitor traffic flow, while radar and drones are selected to identify aerial targets. Based on the characteristics of the selected sensors and the specific conditions of the target area, a sensor deployment plan is designed, including the location, number, and configuration of the sensors, to ensure comprehensive coverage of the target area and effective monitoring, thereby acquiring the necessary data. The deployed sensors begin operating, collecting air and ground parameter data from the target area. Through real-time monitoring and data analysis, management can promptly detect and respond to potential security threats, such as abnormal behavior or overcrowding. The system intelligently selects and deploys sensors based on historical data and target monitoring requests, thereby improving the accuracy and efficiency of data collection, ensuring that the collected data meets the actual needs of air-ground collaborative management and control, and providing reliable support for decision-making.

[0034] Furthermore, step S300 provided in this application embodiment also includes:

[0035] S310: Perform data preprocessing on the air-to-air parameter data and the ground parameter data to obtain the processed air-to-air parameter data and ground parameter data;

[0036] S320: Based on image recognition technology, extract key parameters from the air-to-air parameter data to obtain key air-to-air information;

[0037] S330: Based on data analysis technology, extract key data from the ground parameter data to obtain key ground information.

[0038] Specifically, the collected air-to-air and ground-based parameter data contain noise, outliers, or do not conform to the preset format. Data preprocessing is performed on these data to improve its quality and usability, ensuring consistency and accuracy. This includes data cleaning, data integration, data transformation, and data reduction. Data cleaning mainly involves identifying and handling missing and outlier values; data integration merges data from different sources and addresses inconsistencies; data transformation converts data into a more suitable format for analysis, such as standardization or normalization; and data reduction improves processing efficiency and model performance. Air-to-air parameter data, especially image or video data, is analyzed using image recognition technology to extract key information, including identifying specific objects and detecting motion patterns. Aerial targets, such as aircraft and drones, are identified from images or signals collected by sensors such as radar and drones. These identified aerial targets are continuously tracked to obtain key parameters such as their position, speed, and altitude, acquiring crucial air-to-air information, including the target's trajectory and parameter changes. For ground parameter data, data analysis techniques, including statistical analysis and machine learning algorithms, are used to extract key information to identify trends, patterns, or anomalies. Ground sensors or cameras are used to monitor parameters such as road traffic flow and vehicle speed, analyzing traffic conditions, including changes in traffic volume. Sensor devices are used to monitor the status of ground facilities, such as bridges, tunnels, and power facilities, obtaining key data such as temperature, humidity, and pressure to determine their operational status. Key information about the right toe is extracted from raw air and ground parameter data for subsequent mutual sensing verification and decision-making models to support air-ground collaborative management. Combining image recognition and data analysis techniques, crucial information for decision-making is extracted from complex data, thereby improving the overall system performance and decision quality.

[0039] Furthermore, such as Figure 2 As shown, step S400 provided in this application embodiment further includes:

[0040] S410: Preset mutual inductance verification indicators, which include spatiotemporal consistency indicators, data logical relationship indicators, data range indicators, and data integrity indicators;

[0041] S420: Apply the mutual inductance verification index to the air key information and the ground key information, and perform item-by-item verification;

[0042] S430: Assign weights according to the importance of the mutual inductance verification index, and calculate the verification coefficient based on the weight assignment;

[0043] S440: Obtain the verification results, which include spatiotemporal consistency verification results, data logical relationship verification results, data range verification results, data integrity verification results, and verification coefficients.

[0044] Specifically, mutual sensing verification indicators are set, including spatiotemporal consistency indicators, data logical relationship indicators, data range indicators, and data integrity indicators. Spatiotemporal consistency indicators check whether aerial targets and ground events are consistent in time and space. Temporal consistency requires sensor data synchronization, and spatial consistency requires that the conditions reflected by sensor data match reality. For example, whether the trajectory of an aerial target is related to ground traffic flow or events. Data logical relationship verification indicators verify the logical relationship between key aerial and ground information, helping to discover inconsistencies in the data and thus identify potential sensor malfunctions or data errors. For example, when an aerial target approaches a ground facility, does the monitoring data of the ground facility show a corresponding reaction or change? Data range indicators check whether the collected data is within a reasonable range, helping to identify outliers. For example, whether parameters such as the flight altitude and speed of aerial targets are within normal ranges; whether parameters such as temperature and pressure of ground facilities are within safe thresholds. Data integrity indicators ensure that the collected data is complete and without omissions or deficiencies, which is crucial for ensuring the comprehensiveness and reliability of the data. For example, checking whether sensor devices are working properly throughout the entire period and whether the data is continuous and uninterrupted. If data from a certain sensor is lost during a certain period, it may affect the assessment of the overall situation.

[0045] Based on preset mutual inductance verification indicators, the key air-to-ground information and key ground information are verified item by item. Different weights are assigned to the mutual inductance verification indicators according to their importance to the decision-making process, which can be based on historical data, decision objectives, expert opinions, etc. Weight allocation refers to the process of allocating relative importance among different data and indicators. Each indicator may have a different degree of influence on the final decision, so different weights need to be assigned to it in order to provide a better solution during the decision-making process. Based on the weighted verification results, a verification coefficient is calculated. The verification coefficient is a comprehensive indicator, calculated based on the weight allocation and the verification results of each indicator, and is used to evaluate the overall quality and controllability of the data. Finally, a verification result is obtained, including the spatiotemporal consistency verification result, the data logical relationship verification result, the data range verification result, the data integrity verification result, and the verification coefficient. The combined use of weight allocation and verification coefficient enables decision-makers to more objectively and comprehensively evaluate the quality of data, and to consider the importance of different indicators in the decision-making process, ensuring that the data used for decision-making is accurate. This helps to improve the efficiency and effectiveness of air-ground collaborative management and control, and reduce misjudgments and decision-making errors caused by data problems.

[0046] Furthermore, such asFigure 3 As shown, step S500 provided in this application embodiment further includes:

[0047] S510: Evaluate the verification result and make a judgment based on the evaluation result;

[0048] S520: Establish an initial collaborative management and control decision model, wherein the input data of the initial collaborative management and control decision model is the verification result, and the output data is the collaborative management and control decision;

[0049] S530: Collect historical data, and perform supervised training on the initial collaborative management and control decision model based on the historical data to obtain the air-ground collaborative management and control decision model;

[0050] S540: If the verification result is accurate, input the air-ground collaborative management and control decision model to obtain the collaborative management and control decision.

[0051] Specifically, the obtained verification results are evaluated to ensure that all preset verification indicators have passed and that the data meets requirements in terms of logic, scope, completeness, and spatiotemporal consistency. After passing the evaluation, the verification results are confirmed to be accurate and used for subsequent input into the collaborative control decision-making model. An initial collaborative control decision-making model is built, including machine learning algorithms and optimization algorithms, to process and analyze the input verification results and obtain corresponding collaborative control decisions. This step is equivalent to providing response suggestions for specific situations. The model is trained using historical datasets, including past verification results and corresponding control decisions. Supervised learning methods are used to learn from past data and corresponding correct results to obtain the air-ground collaborative control decision-making model. Through training, the model can infer the optimal control decision from the verification results. If the verification result is considered accurate, it will be input into the air-ground collaborative control decision-making model, which will generate collaborative control decisions to guide actual air-ground collaborative control operations, i.e., generating the optimal decision for a specific situation. Historical data and verification results are used to train a model capable of generating accurate control decisions. Air-ground collaborative control ensures the effective coordination between aerial UAV monitoring and ground safety measures, improving overall security capabilities. This approach combines data validation and machine learning techniques to improve the efficiency and effectiveness of air-ground collaborative management.

[0052] Furthermore, step S500 provided in this application embodiment also includes:

[0053] The S550 establishes a verification result evaluation module. If the verification result is inaccurate, the verification result is input into the verification result evaluation module.

[0054] S560 analyzes each verification result in the verification result evaluation module and filters out verification information that does not meet the mutual inductance verification index.

[0055] S570 constructs an error-decision database based on the historical data, the error-decision database including error verification information and error solutions;

[0056] S580 inputs the verification information into the error-decision database to perform scheme matching and obtain a solution.

[0057] Specifically, a module for evaluating the accuracy of verification results is built. This module can process data from different sensors and assess its correctness, including verification coefficients and error ranges. When a verification result is inaccurate, it is input into the verification result evaluation module. Each input verification result is analyzed to determine the cause of inaccuracy, such as analyzing the logical relationships between data points and data ranges. Based on preset mutual inductance verification indicators, verification information that does not meet the standards is filtered out, such as data with logical errors or data exceeding the range. An error-decision database is built based on historical data. This database includes error verification information and error solutions; that is, each unmet indicator corresponds to a solution. Verification information is input into the error-decision database for solution matching, that is, the unmet indicator is input into the database to match the corresponding solution. By building the error-decision database, errors in the verification process can be effectively recorded and tracked, and solution references can be provided. This helps improve the stability and reliability of the system and promotes continuous improvement.

[0058] Furthermore, such as Figure 4 As shown, step S530 provided in this application embodiment further includes:

[0059] S531: Generate a sample dataset based on the historical data;

[0060] S532: Obtain a preset data partitioning ratio, and divide the sample dataset into a training dataset and an evaluation dataset according to the preset data partitioning ratio;

[0061] S533: Supervised training of the initial collaborative management and control decision model is performed using the training dataset. When the model output results tend to converge, the output results of the initial collaborative management and control decision model are verified using the evaluation dataset.

[0062] S534: Obtain the preset model verification accuracy index. When the accuracy of the output result of the initial collaborative management and control decision model meets the preset model verification accuracy index, the collaborative management and control decision model is obtained.

[0063] Specifically, a sample dataset is generated based on historical data, and a preset data partitioning ratio is determined, for example, 80% of the data is used for training and 20% for evaluation. This ratio can be adjusted according to project needs and data volume. Before partitioning, the data is usually randomly shuffled to ensure that each sample has an equal chance of being assigned to either the training or evaluation dataset. From the shuffled data, it is divided into training and evaluation datasets according to the preset ratio, ensuring that the two datasets are independent and that samples from one dataset do not appear in the other. The training dataset is input into the initial collaborative control decision model for supervised training, and the model parameters are iteratively updated until the model output results tend to converge, i.e., the model performance no longer shows significant improvement. Convergence can be determined by observing the model's performance metrics or by using preset stopping conditions. The evaluation dataset is used to test the model's performance. During the validation process, the model outputs prediction results for the evaluation dataset, and the results are validated. Based on specific needs and expected goals, a preset model validation accuracy metric is set. When the output accuracy of the initial collaborative control decision model meets the preset accuracy metric, it indicates that the model can achieve the expected performance level in practical applications and can be used for actual air-ground collaborative control decisions. This approach combines model training, validation, and deployment, which helps improve the reliability and accuracy of the model and ensures that the air-ground collaborative management and control decision-making model can achieve the expected performance level in practical applications.

[0064] Furthermore, step S580 in this embodiment of the application also includes:

[0065] S581: If the verification information does not match the error-decision database, then generate alarm data;

[0066] S582: The alarm data is sent to staff for processing using visualization technology.

[0067] Specifically, verification information is input into the error-decision database and compared with the records stored therein. If the verification information does not match any record in the database, the system generates alarm data, including the mismatched verification information, the time and location of the occurrence, and potential risks. An alarm system can be designed to respond quickly to this alarm data, including audible and visual alarms, SMS notifications, and app alerts. The type and amount of information displayed to staff should be determined based on the needs, and visualization tools such as pie charts, bar charts, and line graphs should be selected to allow staff to see the data intuitively and handle it promptly, improving communication efficiency and effectiveness. Ensure that the alarm data is easily accessible, viewable through mobile devices, computers, or other terminal devices, and provide sufficient information so that staff can take appropriate action. Upon receiving the alarm data, staff should take immediate action, including adjusting on-site safety measures, adding monitoring equipment, and guiding crowd evacuation.

[0068] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages:

[0069] The air-ground collaborative management and control method based on mutual inductance verification provided in this application involves deploying sensors in the target area to collect air and surface data, obtaining air and ground parameter data, and transmitting this data to a data processing center via wireless communication technology for key information extraction, acquiring key air and ground information. Preset mutual inductance verification indicators are used to verify the key air and ground information, and verification results are obtained. If the verification results are accurate, they are input into the air-ground collaborative management and control decision model to obtain collaborative management and control decisions. Air-ground collaborative management and control is then performed based on these decisions. This method solves the technical problem in existing traditional air-ground collaborative management and control methods, which rely on manual monitoring and scheduling, failing to fully reflect data reliability and thus causing delays in collaborative management and control decisions. It achieves the technical effect of improving the efficiency and accuracy of data processing and management and control decisions.

[0070] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for air-ground cooperative control based on mutual inductance verification, characterized in that, The method includes: A target area is determined, and multiple sets of sensors are deployed within the target area to collect air data and ground data, respectively, to obtain air parameter data and ground parameter data; The air-to-ground parameter data and the ground parameter data are transmitted to the data processing center using wireless communication technology. Based on the data processing center, key information is extracted from the air-to-air parameter data and the ground parameter data to obtain key air-to-air information and key ground information. A preset mutual inductance verification index is used to verify the air key information and the ground key information, and the verification result is obtained. Based on the verification results, if the verification results are accurate, the data is input into the air-ground collaborative management and control decision model to obtain collaborative management and control decisions. Air-ground coordinated management and control are carried out based on the aforementioned coordinated management and control decisions; The method further includes: setting a preset mutual inductance verification index, verifying the air-to-air key information and the ground-to-ground key information based on the mutual inductance verification index, and obtaining the verification result; the method also includes: Preset mutual inductance verification indicators, which include spatiotemporal consistency indicators, data logical relationship indicators, data range indicators, and data integrity indicators; The mutual inductance verification index is applied to the air key information and the ground key information for item-by-item verification. Weights are assigned based on the importance of the mutual inductance verification index, and verification coefficients are calculated based on the weights. Obtain the verification results, which include spatiotemporal consistency verification results, data logical relationship verification results, data range verification results, data integrity verification results, and verification coefficients. Based on the verification result, if the verification result is accurate, the result is input into the air-ground collaborative management and control decision model to obtain a collaborative management and control decision. The method further includes: The verification results are evaluated, and a judgment is made based on the evaluation results; An initial collaborative management and control decision model is established, wherein the input data of the initial collaborative management and control decision model is the verification result, and the output data is the collaborative management and control decision; Collect historical data, and perform supervised training on the initial collaborative management and control decision model based on the historical data to obtain the air-ground collaborative management and control decision model; If the verification result is accurate, then input the air-ground collaborative management and control decision model to obtain collaborative management and control decisions.

2. The method according to claim 1, characterized in that, The method further includes: determining a target area, deploying multiple sets of sensors within the target area to collect aerial and surface data, and obtaining aerial parameter data and ground parameter data; and defining the target area. Access historical air parameter data and historical ground parameter data to extract the types of target data collected. The multiple sets of sensors are determined based on the types of data collected from the target. Sensors are deployed based on the combination of the multiple sets of sensors and the target area; Data is collected from the target area using the multiple sets of sensors to obtain air and ground parameter data.

3. The method according to claim 1, characterized in that, Based on the data processing center's extraction of key information from the air-to-air parameter data and the ground parameter data, to obtain key air-to-air information and key ground information, the method further includes: The air-to-air parameter data and the ground parameter data are preprocessed to obtain the processed air-to-air parameter data and ground parameter data; Based on image recognition technology, key parameters are extracted from the air-to-air parameter data to obtain key air-to-air information; Based on data analysis technology, key data is extracted from the ground parameter data to obtain key ground information.

4. The method according to claim 1, characterized in that, The method further includes supervising the training of the initial collaborative management and control decision model based on the historical data, and performing such training. A sample dataset is generated based on the historical data. Obtain a preset data partitioning ratio, and divide the sample dataset into a training dataset and an evaluation dataset according to the preset data partitioning ratio; The initial collaborative management and control decision model is trained under supervision using the training dataset. When the model output tends to converge, the output of the initial collaborative management and control decision model is verified using the evaluation dataset. Obtain a preset model validation accuracy index. When the output accuracy of the initial collaborative management and control decision model meets the preset model validation accuracy index, the collaborative management and control decision model is obtained.

5. The method according to claim 1, characterized in that, The method further includes: A verification result evaluation module is set up. If the verification result is inaccurate, the verification result is input into the verification result evaluation module. The verification result evaluation module analyzes each verification result and filters out verification information that does not meet the mutual inductance verification index. An error-decision database is built based on the historical data, and the error-decision database includes error verification information and error solutions. The verification information is input into the error-decision database for scheme matching to obtain a solution.

6. The method according to claim 5, characterized in that, The method further includes: If the verification information does not match the error-decision database, alarm data is generated; The alarm data is sent to staff for processing using visualization technology.

Images