Air-ground integrated low-altitude security command and control methods, systems, equipment and media

Abstract

This application discloses a method, system, equipment, and medium for low-altitude security command and control using a combined air-space-ground approach, relating to the technical field of unmanned aerial vehicles (UAVs). The method includes: generating a global dynamic situation map based on multi-source detection data; performing cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm; predicting subsequent confrontation stages and corresponding group behavior characteristics of the UAV swarm after the current confrontation stage based on the system configuration and key units; and generating a multi-stage induction signal sequence based on the current confrontation stage, subsequent confrontation stages, and group behavior characteristics. The induction signals, configured differently for each subsequent confrontation stage, are set to trigger a preset state response of the UAV swarm using the group behavior characteristics of that subsequent confrontation stage. This preset state response is planned as a favorable condition for executing the next stage induction signal. This application has the effect of improving the concealment of confrontation.

Description

Technical Field

[0001] This application relates to the technical field of unmanned aerial vehicles (UAVs), and in particular to low-altitude security command and control methods, systems, equipment and media for air-ground integrated systems. Background Technology

[0002] With their low cost, large scale, and flexible coordinated operations, drone swarms have become a new and prominent threat in the field of low-altitude security. These targets are capable of performing complex tasks such as distributed reconnaissance, coordinated jamming, and even saturation attacks, posing a serious challenge to the traditional low-altitude defense system that focuses on protecting key facilities and key airspaces.

[0003] Existing low-altitude security technologies are typically built upon a "detect-response" paradigm. The system detects targets using sensors such as radar and electro-optical sensors, then guides interceptor weapons or jamming equipment to engage them. This model is effective against single or small numbers of traditional aerial targets, but its inherent limitations become apparent when dealing with large-scale, highly maneuverable, and coordinated drone swarms. Its decision-making process heavily relies on the target's instantaneous physical parameters, lacking in-depth analysis and forward-looking prediction of the swarm's inherent behavioral patterns, coordination rules, and tactical intentions. This results in countermeasures often lagging behind the dynamic changes of the swarm, leading to a reactive and reactive approach.

[0004] To enhance proactive defense, some technical solutions employ countermeasures such as actively transmitting jamming or decoy signals. However, this approach faces a dilemma in practical applications: while simple, continuous, or high-intensity signal transmissions may affect some drones, they also significantly increase the risk of the defense system itself being detected, located, or even counterattacked, jeopardizing its battlefield survivability; on the other hand, reducing the transmission intensity or shortening the window to mitigate risk often fails to have a substantial impact on closely coordinated swarms. Existing technologies have failed to adequately resolve this contradiction.

[0005] Furthermore, the adversarial logic of existing defense systems is mostly based on pre-set rules or static plans. When the swarm takes unexpected actions or exhibits adaptive capabilities, static adversarial strategies are prone to failure, and the system lacks the closed-loop capability to evaluate and dynamically adjust strategies in real time based on the effects during the action, resulting in unstable overall defense effectiveness and insufficient adaptability.

[0006] Therefore, the current state of technology is significantly inadequate in dealing with intelligent drone swarms in terms of timeliness and foresight in countermeasures, balance between the stealth and effectiveness of proactive actions, and dynamic adaptability of strategies. There is an urgent need to develop a new generation of command and control methods that are more intelligent, flexible, dynamic, and capable of dealing with systemic threats. Summary of the Invention

[0007] To enhance the concealment of countermeasures, this application provides a method, system, equipment, and medium for low-altitude security command and control that integrates air, space, and ground.

[0008] Firstly, this application provides a low-altitude security command and control method that integrates air, space, and ground operations, employing the following technical solution:

[0009] A ground-air-space coordinated low-altitude security command and control method, wherein the method is executed by a command and control center, including:

[0010] Step S11: Obtain multi-source detection data of the UAV swarm through the air-space-ground collaborative system, and generate a global dynamic situation map based on the multi-source detection data;

[0011] Step S12: Perform cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm;

[0012] Step S13: Based on the system configuration and the key units, predict at least one subsequent confrontation phase of the drone swarm after the current confrontation phase and the corresponding group behavior characteristics;

[0013] Step S14: Generate a multi-stage induction signal sequence based on the current confrontation stage, the subsequent confrontation stage, and the group behavior characteristics. The induction signal configured differently for each subsequent confrontation stage is set to: use the group behavior characteristics of the subsequent confrontation stage to trigger the drone swarm to generate a preset state response. The preset state response is planned as a favorable condition for executing the next stage induction signal.

[0014] Step S15: sequentially apply the induction signals in the multi-stage induction signal sequence to the drone swarm, and after applying the induction signals, evaluate the state response of the drone swarm based on the updated global dynamic situation map;

[0015] Step S16: If the state response deviates from the expectation, then based on the latest global dynamic situation map, the execution will restart from step S12.

[0016] By employing the above technical solution, multi-source detection data of the UAV swarm is acquired through an air-space-ground collaborative system. Based on this data, a global dynamic situation map is generated. Cognitive analysis of the global dynamic situation map is then performed to obtain the system configuration, key units, and current confrontation stage of the UAV swarm. Based on the system configuration and key units, at least one subsequent confrontation stage and corresponding group behavior characteristics of the UAV swarm after the current confrontation stage are predicted. Then, based on the current confrontation stage, subsequent confrontation stages, and group behavior characteristics, a multi-stage induction signal sequence is generated. The induction signals, configured differently for each subsequent confrontation stage, are set to trigger a preset state response of the UAV swarm using the group behavior characteristics of that subsequent confrontation stage. This preset state response is planned as a favorable condition for executing the next stage induction signal. Induction signals from the multi-stage induction signal sequence are then sequentially applied to the UAV swarm. After applying the induction signals, the state response of the UAV swarm is evaluated based on the updated global dynamic situation map. If the state response deviates from the expectation, the process returns to the cognitive analysis step based on the latest global dynamic situation map. This invention achieves a tactical shift from passive response to active guidance in managing drone swarms through cognitive analysis and forward-looking prediction, enhancing the timeliness and initiative of the confrontation. Furthermore, by providing precise and differentiated signal guidance based on the behavioral characteristics of the swarm at different stages, it significantly reduces the exposure risk of the defense system itself while ensuring efficient interference, thus improving the concealment of the confrontation. On this basis, the method breaks through the discrete confrontation of single-point targets, realizing a leap in the ability to systematically guide and disintegrate the swarm by starting from the identification system configuration and key units. Relying on a dynamic decision-making closed loop based on real-time situation, the system can continuously adapt to complex confrontation environments, forming a command and control capability with strong robustness and adaptability.

[0017] Optionally, the step of generating a global dynamic situation map based on the multi-source detection data includes:

[0018] The multi-source detection data is subjected to spatiotemporal registration and coordinate unification processing to obtain collaborative detection data, wherein the multi-source detection data includes at least one of radar data, spectrum data, photoelectric data, and sound data;

[0019] The collaborative detection data is subjected to target association, track fusion and feature extraction to generate a target feature set, wherein the target feature set includes individual features and cluster features. The individual features include identity, type, location, speed, heading and signal strength. The cluster features include cluster number, density, geometric center, direction of movement, topology and communication mode.

[0020] By associating and fusing preset geographic information data, preset defense resource deployment data, and the target feature set, a global dynamic situation map is generated. The global dynamic situation map is used to characterize the spatial distribution, movement trend, and threat level of the UAV swarm.

[0021] By adopting the above technical solution, in order to generate a global dynamic situation map, spatiotemporal registration and coordinate unification processing are performed on multi-source detection data to obtain collaborative detection data. The multi-source detection data includes at least one of radar data, spectrum data, photoelectric data, and acoustic data. Then, target association, track fusion, and feature extraction are performed on the collaborative detection data to generate a target feature set. The target feature set includes individual features and swarm overall features. Individual features include identity, type, location, speed, heading, and signal strength. Swarm overall features include swarm number, density, geometric center, direction of movement, topology, and communication mode. Then, preset geographic information data, preset defense resource deployment data, and target feature set are associated and fused to generate a global dynamic situation map. The global dynamic situation map is used to characterize the spatial distribution, movement trend, and threat level of the UAV swarm.

[0022] Optionally, the step of performing cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm includes:

[0023] Based on the global dynamic situation map, a high-level feature set for representing behavior and intent is extracted;

[0024] Based on a preset behavior pattern library and similarity matching based on the high-level feature set, the current behavior pattern and tactical intent of the drone swarm are identified.

[0025] Based on a pre-defined knowledge base of typical swarm configurations, logical reasoning is performed according to the current behavior pattern and the tactical intent to deduce the command and control logic, unit functional roles and coordination rules of the drone swarm, and thus determine the corresponding system configuration.

[0026] Based on the command and control logic, the functional roles of the units, and the coordination rules, key units are identified from the drone swarm.

[0027] The system configuration, the behavioral state of the key units, and the current adversarial situation represented by the global dynamic situation map are matched with multiple preset adversarial stage models to determine the current adversarial stage of the drone swarm.

[0028] By adopting the above technical solution, in order to achieve cognitive analysis of the global dynamic situation map, a high-level feature set for representing behavior and intent is extracted based on the global dynamic situation map. Then, based on a preset behavior pattern library and similarity matching based on the high-level feature set, the current behavior pattern and tactical intent of the drone swarm are identified. Then, based on a preset typical swarm configuration knowledge base, logical reasoning is performed based on the current behavior pattern and tactical intent to deduce the command and control logic, unit functional roles, and coordination rules of the drone swarm, thereby determining the corresponding system configuration. Then, based on the command and control logic, unit functional roles, and coordination rules, key units are identified from the drone swarm. Finally, the system configuration, the behavior status of key units, and the current confrontation situation represented by the global dynamic situation map are matched with multiple preset confrontation stage models to determine the current confrontation stage of the drone swarm.

[0029] Optionally, the step of predicting at least one subsequent confrontation phase and the corresponding swarm behavior characteristics of the drone swarm after the current confrontation phase, based on the system configuration and the key units, includes:

[0030] Based on the system configuration, the key units, and the current confrontation stage, a preset tactical evolution knowledge graph is queried to obtain the typical tactical task chain with the highest matching degree to the current confrontation situation;

[0031] Based on the typical tactical mission chain, at least one subsequent confrontation phase is determined;

[0032] For each subsequent confrontation stage, based on a preset group behavior rule base, and according to the system configuration and the role behavior templates corresponding to the key units in the tactical evolution knowledge graph, the group behavior characteristics corresponding to that subsequent confrontation stage are deduced. The group behavior characteristics include at least cluster movement mode, communication interaction mode and attack mode.

[0033] By adopting the above technical solution, in order to obtain the subsequent confrontation stages and the corresponding group behavior characteristics, based on the system configuration, key units, and the current confrontation stage, a preset tactical evolution knowledge graph is queried to obtain the typical tactical task chain with the highest matching degree with the current confrontation situation. Then, based on the typical tactical task chain, at least one subsequent confrontation stage is determined. Then, for each subsequent confrontation stage, based on the preset group behavior rule base, the group behavior characteristics corresponding to the subsequent confrontation stage are deduced according to the role behavior templates corresponding to the system configuration and key units in the tactical evolution knowledge graph. Among them, the group behavior characteristics include at least cluster movement mode, communication interaction mode, and attack mode.

[0034] Optionally, the step of generating a multi-stage induction signal sequence based on the current confrontation stage, the subsequent confrontation stage, and the swarm behavior characteristics, wherein the induction signal configured differently for each of the subsequent confrontation stages is set as follows: utilizing the swarm behavior characteristics of the subsequent confrontation stage to trigger the drone swarm to generate a preset state response, the preset state response being planned as a favorable condition for executing the next stage induction signal, includes:

[0035] Based on the current confrontation phase and the subsequent confrontation phase, an overall guidance target is determined, and a phase guidance target serving the overall guidance target is set for the current confrontation phase and each of the subsequent confrontation phases. The phase guidance target is configured to guide the drone swarm into a preset state response, which is planned to both serve the overall guidance target and constitute favorable conditions for executing the next phase of guidance.

[0036] For the current confrontation phase and each subsequent confrontation phase, at least one induction signal is selected or combined from a preset induction signal library based on the group behavior characteristics corresponding to the confrontation phase. The induction signal is configured to trigger the corresponding phase induction target by utilizing the group behavior pattern corresponding to the confrontation phase.

[0037] For the inducement signals generated in the current confrontation phase and all subsequent confrontation phases, they are sorted and coordinated according to the order of each confrontation phase to generate a multi-stage inducement signal sequence. In the multi-stage inducement signal sequence, the inducement signals of adjacent phases are interconnected in terms of action logic, signal parameters and spatiotemporal configuration.

[0038] By adopting the above technical solution, in order to generate a multi-stage inducement signal sequence, an overall inducement target is determined based on the current confrontation stage and subsequent confrontation stages. Stage inducement targets serving the overall inducement target are set for the current confrontation stage and each subsequent confrontation stage. These stage inducement targets are configured to guide the drone swarm into a preset state response, which is planned to both serve the overall inducement target and constitute favorable conditions for executing the next stage of inducement. Then, for the current confrontation stage and each subsequent confrontation stage, at least one inducement signal is selected or combined from a preset inducement signal library based on the group behavior characteristics corresponding to that confrontation stage. The inducement signal is configured to trigger the corresponding stage inducement target using the group behavior pattern corresponding to that confrontation stage. Then, the inducement signals generated for the current confrontation stage and all subsequent confrontation stages are sorted and coordinated according to the order of each confrontation stage to generate a multi-stage inducement signal sequence. The inducement signals of adjacent stages in the multi-stage inducement signal sequence are interconnected in terms of operational logic, signal parameters, and spatiotemporal configuration.

[0039] Optionally, the step of sequentially applying the induction signals from the multi-stage induction signal sequence to the drone swarm, and evaluating the state response of the drone swarm based on the updated global dynamic situation map after applying the induction signals, includes:

[0040] Through multiple directional launch units of the aforementioned air-space-ground collaborative system, the induction signals in the multi-stage induction signal sequence are applied to the UAV swarm within the corresponding spatiotemporal window;

[0041] After the induction signal is applied, the latest multi-source detection data is obtained through the air-space-ground collaborative system, and the global dynamic situation map is updated.

[0042] Based on the updated global dynamic situation map, the state response features of the UAV swarm are extracted, and the state response features are compared with the stage guidance target corresponding to the guidance signal to evaluate whether the expectation has been achieved.

[0043] By adopting the above technical solution, in order to form a real-time closed loop of "application-evaluation" and realize the observability and measurability of the confrontation process, multiple directional launch units of the air-space-ground collaborative system apply multi-stage induction signal sequences to the UAV swarm within the corresponding spatiotemporal window. After applying the induction signals, the latest multi-source detection data is obtained through the air-space-ground collaborative system, and the global dynamic situation map is updated. Then, based on the updated global dynamic situation map, the state response characteristics of the UAV swarm are extracted, and the state response characteristics are compared with the stage induction targets corresponding to the induction signals to evaluate whether the expectations have been met.

[0044] Optionally, the air-space-ground collaborative system includes:

[0045] Space-based detection nodes are used to provide wide-area surveillance information;

[0046] Airborne detection and signaling nodes, including early warning aircraft and dedicated UAVs, are used for regional detection and induced signal transmission;

[0047] Ground-based detection and countermeasures nodes, including radar stations, electro-optical tracking equipment, directional jamming equipment, and decoy equipment, are used for precise terminal tracking and signal application;

[0048] The command and control center is connected to the space-based detection node, the air-based detection and signal application node, and the ground-based detection and countermeasure node through a communication network to achieve data aggregation, fusion, and command distribution.

[0049] By adopting the above technical solutions and the above-mentioned air-space-ground collaborative system, the integrated distributed integration of detection, tracking and signal application functions is realized, which effectively supports the dynamic adjustment and optimization of countermeasure strategies. At the same time, the distributed and multi-layered system architecture provides highly reliable and low-exposure physical support for the countermeasure process, and realizes a high degree of coordination and closed-loop operation of detection, decision-making, countermeasure and evaluation functions.

[0050] Secondly, this application also provides a low-altitude security command and control system that integrates air, space, and ground, employing the following technical solution:

[0051] A space-air-ground integrated low-altitude security command and control system is applied in a command and control center, which is equipped with:

[0052] The global dynamic situation map generation module is used to acquire multi-source detection data of UAV swarms through the air-space-ground collaborative system, and generate a global dynamic situation map based on the multi-source detection data.

[0053] The cognitive analysis module is used to perform cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm.

[0054] The prediction module is used to predict at least one subsequent confrontation phase and the corresponding group behavior characteristics of the drone swarm after the current confrontation phase, based on the system configuration and the key units.

[0055] The induction signal sequence generation module is used to generate a multi-stage induction signal sequence based on the current confrontation stage, the subsequent confrontation stage, and the group behavior characteristics. The induction signal, which is configured differently for each of the subsequent confrontation stages, is set to trigger the drone swarm to generate a preset state response by utilizing the group behavior characteristics of the subsequent confrontation stage. The preset state response is planned as a favorable condition for executing the next stage induction signal.

[0056] The induction signal application module is used to sequentially apply the induction signals in the multi-stage induction signal sequence to the drone swarm, and after applying the induction signals, evaluate the state response of the drone swarm based on the updated global dynamic situation map;

[0057] The replanning module is used to trigger the cognitive analysis module, the prediction module, the induced signal sequence generation module, the induced signal application module, and the replanning module to re-execute the processing flow based on the latest global dynamic situation map if the state response deviates from the expectation.

[0058] Thirdly, this application also provides a computer device, which adopts the following technical solution:

[0059] A computer device includes a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the computer program to implement the method described in the first aspect.

[0060] Fourthly, this application also provides a computer-readable storage medium, which adopts the following technical solution:

[0061] A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the method described in the first aspect.

[0062] In summary, this application includes at least the following beneficial technical effects: acquiring multi-source detection data of a drone swarm through an air-space-ground collaborative system, generating a global dynamic situation map based on the multi-source detection data, then performing cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the drone swarm, then predicting at least one subsequent confrontation stage of the drone swarm and its corresponding group behavior characteristics based on the system configuration and key units, and then generating a multi-stage induction signal sequence based on the current confrontation stage, subsequent confrontation stages, and group behavior characteristics. The induction signals, configured differently for each subsequent confrontation stage, are set to: trigger a preset state response of the drone swarm using the group behavior characteristics of that subsequent confrontation stage. This preset state response is planned as a favorable condition for executing the next stage induction signal. Then, the induction signals in the multi-stage induction signal sequence are sequentially applied to the drone swarm. After applying the induction signals, the state response of the drone swarm is evaluated based on the updated global dynamic situation map. If the state response deviates from the expectation, the process returns to the cognitive analysis step based on the latest global dynamic situation map. This invention achieves a tactical shift from passive response to active guidance in managing drone swarms through cognitive analysis and forward-looking prediction, enhancing the timeliness and initiative of the confrontation. Furthermore, by providing precise and differentiated signal guidance based on the behavioral characteristics of the swarm at different stages, it significantly reduces the exposure risk of the defense system itself while ensuring efficient interference, thus improving the concealment of the confrontation. On this basis, the method breaks through the discrete confrontation of single-point targets, realizing a leap in the ability to systematically guide and disintegrate the swarm by starting from the identification system configuration and key units. Relying on a dynamic decision-making closed loop based on real-time situation, the system can continuously adapt to complex confrontation environments, forming a command and control capability with strong robustness and adaptability. Attached Figure Description

[0063] Figure 1 This is a schematic diagram of the overall process of an embodiment of this application.

[0064] Figure 2 This is a schematic diagram of the system structure of this application.

[0065] Figure 3 This is a structural block diagram of the computer device described in this application. Detailed Implementation

[0066] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0067] This application discloses a low-altitude security command and control method that integrates air, space, and ground systems.

[0068] Reference Figure 1 A low-altitude security command and control method integrating air, space, and ground, characterized in that the method is executed by a command and control center, including:

[0069] Step S11: Obtain multi-source detection data of the UAV swarm through the air-space-ground collaborative system, and generate a global dynamic situation map based on the multi-source detection data.

[0070] It should be noted that the air-space-ground collaborative system refers to a heterogeneous detection network composed of multiple platforms, including space-based (such as satellites), air-based (such as early warning aircraft and UAVs), and ground-based (such as radar and optoelectronic power stations), capable of collecting data synchronously or asynchronously from different dimensions. Multi-source detection data includes, but is not limited to, radar traces, radio frequency signals, optical images, and acoustic features. The core of the global dynamic situation map lies in spatiotemporal registration, coordinate unification, target association, and trajectory fusion of these heterogeneous and asynchronous raw data, aggregating scattered observation information into a unified, spatiotemporally labeled comprehensive battlefield view. This view not only presents the real-time position, speed, heading, and other kinematic states of each individual UAV, but also preliminarily depicts the overall distribution, density, and movement trends of the cluster, and associates static information such as the geographical environment and friendly defense resources as context.

[0071] Step S12: Perform cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the drone swarm.

[0072] It should be noted that step S12 enables intelligent analysis of the deep information contained in the situation map. Cognitive analysis refers to using methods such as behavioral pattern matching, graph theory analysis, and machine learning to identify the organization and control pattern of the swarm, i.e., the system configuration (such as centralized command or distributed collaborative), from features such as swarm movement trajectories, inter-unit communication relationships, and topological structure. Simultaneously, it analyzes the pivotal role of each unit in the communication network, the specificity of its movement patterns, or the salience of its signal characteristics to locate key units that play a command and control, communication relay, or core attack role. Furthermore, by combining the overall behavior pattern of the swarm, its movement intentions, and its relative relationship with the protected area, it matches them with a pre-set typical tactical stage model to determine its current confrontation stage (such as reconnaissance patrol, formation penetration, or attack deployment). Step S12 provides qualitative and quantitative cognition of the enemy's combat system and current tactical intentions.

[0073] Step S13: Based on the system configuration and key units, predict at least one subsequent confrontation phase of the drone swarm after the current confrontation phase and the corresponding group behavior characteristics.

[0074] It should be noted that, based on the system configuration, key unit roles, and current stage already known in step S12, this method does not only focus on the current threat but also extrapolates the future. The prediction process relies on a pre-set tactical evolution knowledge graph and a swarm behavior rule base. By querying the knowledge graph for typical tactical sequences that best match the current cognitive state, it infers one or more subsequent confrontation stages that the drone swarm is most likely to enter. Then, for each predicted stage, based on its system configuration characteristics and key unit role behavior templates, combined with swarm dynamics and coordination rules, it infers the swarm behavior characteristics that the swarm may exhibit in that stage. These characteristics include specific swarm movement patterns (such as diffusion, aggregation, and detours), communication interaction patterns (such as command frequency and link switching), and attack patterns (such as aiming and diving). This provides a basis for planning countermeasures in advance.

[0075] Step S14: Generate a multi-stage induction signal sequence based on the current confrontation stage, subsequent confrontation stages, and group behavior characteristics.

[0076] Among them, the induction signal configured differently for each subsequent confrontation stage is set as follows: by utilizing the group behavior characteristics of the subsequent confrontation stage, the drone swarm is triggered to generate a preset state response, which is planned as a favorable condition for executing the induction signal of the next stage.

[0077] It should be noted that step S14 is the synthesis and concretization of the countermeasure strategy, the core idea of ​​which is to conduct multi-step, coherent induction design. First, based on the analysis of the current and future stages, a general induction target is determined (such as luring to the interception zone, driving away, or disintegrating). Then, for the current stage and each predicted subsequent stage, a specific stage induction target is set. The key is that the pre-set state response of the swarm expected to be triggered by each stage induction target is designed to both serve the overall target and create favorable conditions for the smooth implementation of the next stage of induction (for example, the first stage induction disperses the swarm formation, creating an opportunity for targeted communication interference in the second stage). Finally, for each stage, based on its predicted swarm behavior characteristics, the most likely induction signal to trigger the target response of that stage is selected from the pre-set induction signal library or dynamically generated (such as navigation deception signals of a specific mode, simulated control commands, or communication interference signals), and arranged in the stage sequence to form a logically coherent and interlocking multi-stage induction signal sequence.

[0078] Step S15: Apply the induction signals from the multi-stage induction signal sequence to the drone swarm in sequence, and evaluate the state response of the drone swarm based on the updated global dynamic situation map after applying the induction signals.

[0079] It should be noted that step S15 is the execution and effectiveness verification of the countermeasures. Sequential application refers to applying the current stage's induction signal to the swarm within the planned time and space window, strictly following the signal sequence generated in S14, using directional launch resources (such as ground jamming stations and dedicated UAVs) in the air-space-ground coordinated system. After applying the signal, the air-space-ground coordinated detection is immediately restarted to obtain an updated global dynamic situation map after the swarm's response. By comparing the changes in the situation map before and after applying the signal, the actual state response characteristics of the swarm (such as whether the formation changed as expected, whether key units lost contact, and whether the direction of movement deviated) are extracted. This actual response is then compared with the stage induction target preset in S14 to scientifically and objectively evaluate whether the induction effect has achieved the expected results.

[0080] Step S16: If the state response deviates from the expectation, then based on the latest global dynamic situation map, restart execution from step S12.

[0081] It should be noted that if the S15 assessment finds that the actual response of the swarm deviates from expectations (i.e., the induction was not completely successful or an unexpected countermeasure occurred), it indicates that the current cognitive, predictive, or induction strategies are no longer fully matched with the real-time evolving adversarial situation. In this case, the method will not continue executing the originally planned signal sequence, which may have become ineffective, but will immediately interrupt the current process. It will use the newly updated global dynamic situation map, reflecting the latest adversarial state, as a new input starting point and re-execute the complete decision-making process that began in step S12. This means that the system will re-cognize the swarm, re-predict its behavior, and regenerate and execute new induction strategies based on the latest data. This closed-loop mechanism ensures that the entire method can learn online, dynamically adjust, and continuously adapt to the swarm's tactical changes and countermeasures, thereby maintaining the effectiveness and robustness of the adversarial process.

[0082] In the above implementation, multi-source detection data of the UAV swarm is acquired through an air-space-ground collaborative system. Based on the multi-source detection data, a global dynamic situation map is generated. Then, cognitive analysis is performed on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm. Based on the system configuration and key units, at least one subsequent confrontation stage and corresponding group behavior characteristics of the UAV swarm after the current confrontation stage are predicted. Then, a multi-stage induction signal sequence is generated based on the current confrontation stage, the subsequent confrontation stage, and the group behavior characteristics. The induction signals, which are configured differently for each subsequent confrontation stage, are set to trigger a preset state response of the UAV swarm using the group behavior characteristics of the subsequent confrontation stage. This preset state response is planned as a favorable condition for executing the next stage induction signal. Then, the induction signals in the multi-stage induction signal sequence are applied to the UAV swarm in sequence. After applying the induction signals, the state response of the UAV swarm is evaluated based on the updated global dynamic situation map. If the state response deviates from the expectation, the cognitive analysis step is returned based on the latest global dynamic situation map. This invention achieves a tactical shift from passive response to active guidance in managing drone swarms through cognitive analysis and forward-looking prediction, enhancing the timeliness and initiative of the confrontation. Furthermore, by providing precise and differentiated signal guidance based on the behavioral characteristics of the swarm at different stages, it significantly reduces the exposure risk of the defense system itself while ensuring efficient interference, thus improving the concealment of the confrontation. On this basis, the method breaks through the discrete confrontation of single-point targets, realizing a leap in the ability to systematically guide and disintegrate the swarm by starting from the identification system configuration and key units. Relying on a dynamic decision-making closed loop based on real-time situation, the system can continuously adapt to complex confrontation environments, forming a command and control capability with strong robustness and adaptability.

[0083] As a further implementation of the method, the step of generating a global dynamic situation map based on multi-source detection data includes:

[0084] Step S21: Perform spatiotemporal registration and coordinate unification processing on the multi-source detection data to obtain collaborative detection data, wherein the multi-source detection data includes at least one of radar data, spectrum data, photoelectric data, and sound data.

[0085] Step S22: Perform target association, track fusion and feature extraction on the collaborative detection data to generate a target feature set. The target feature set includes individual features and cluster features. Individual features include identity, type, location, speed, heading and signal strength. Cluster features include cluster number, density, geometric center, direction of movement, topology and communication mode.

[0086] Step S23: The preset geographic information data, preset defense resource deployment data and target feature set are correlated and fused to generate a global dynamic situation map, which is used to characterize the spatial distribution, movement trend and threat level of the drone swarm.

[0087] In the above implementation, in order to generate a global dynamic situation map, spatiotemporal registration and coordinate unification processing are performed on multi-source detection data to obtain collaborative detection data. The multi-source detection data includes at least one of radar data, spectrum data, photoelectric data, and acoustic data. Then, target association, track fusion, and feature extraction are performed on the collaborative detection data to generate a target feature set. The target feature set includes individual features and swarm overall features. Individual features include identity, type, location, speed, heading, and signal strength. Swarm overall features include swarm number, density, geometric center, direction of movement, topology, and communication mode. Then, preset geographic information data, preset defense resource deployment data, and target feature set are associated and fused to generate a global dynamic situation map. The global dynamic situation map is used to characterize the spatial distribution, movement trend, and threat level of the UAV swarm.

[0088] As a further implementation of the method, a cognitive analysis of the global dynamic situation map is performed to obtain the system configuration, key units, and steps of the current confrontation phase of the UAV swarm, including:

[0089] Step S31: Based on the global dynamic situation map, extract a set of high-level features to represent behavior and intent.

[0090] Step S32: Based on a preset behavior pattern library and similarity matching based on a high-level feature set, identify the current behavior pattern and tactical intent of the drone swarm.

[0091] It should be noted that the preset behavior pattern library is a set of feature templates formed by summarizing and learning from historical data, tactical regulations, and simulations. Each template defines a combination of observable features (such as specific speed distribution, formation change patterns, and communication signal pulse patterns) corresponding to a certain typical tactical behavior (such as circling reconnaissance, formation assault, and diffusion jamming). The similarity matching in step S32 is to calculate the degree of matching between the high-level feature set extracted in real time and the features of each template in the library, thereby identifying the most likely current behavior pattern and tactical intention.

[0092] Step S33: Based on the preset typical swarm configuration knowledge base, logical reasoning is performed according to the current behavior pattern and tactical intent to deduce the command and control logic, unit functional roles and coordination rules of the drone swarm, and then determine the corresponding system configuration.

[0093] It should be noted that the pre-defined typical swarm configuration knowledge base systematically describes the inherent operating rules of different system configurations (such as centralized, distributed, and hierarchical). It defines the possible flow paths of command and control instructions under each configuration, the functional roles undertaken by different types of UAVs (such as command nodes, attack units, and relay units), and the interaction rules followed by them to achieve coordination. The logical reasoning in step S33 essentially takes the identified behavioral patterns and tactical intentions as input and performs deductions within the rule framework of this knowledge base to determine which system configuration and its rules best explain the currently observed swarm behavior.

[0094] Step S34: Identify key units from the drone swarm based on command and control logic, unit functional roles, and coordination rules.

[0095] Step S35: Match the system configuration, the behavioral state of key units, and the current adversarial situation represented by the global dynamic situation map with multiple preset adversarial stage models to determine the current adversarial stage of the drone swarm.

[0096] It should be noted that the pre-defined multiple adversarial phase models depict the sequential evolution of a drone swarm over time in a typical attack mission (such as assembly, approach, deployment, attack, and withdrawal). Each phase model is associated with the swarm system configuration, the set of state characteristics typically exhibited by key units, and the overall adversarial environment characteristics at that phase. The matching step S35 compares the currently analyzed system configuration, the real-time state of key units, and the battlefield environment situation with each phase model to determine which phase's characteristics best match at the current moment, thereby identifying the current adversarial phase.

[0097] In the above implementation, in order to achieve cognitive analysis of the global dynamic situation map, a high-level feature set for representing behavior and intent is extracted based on the global dynamic situation map. Then, based on a preset behavior pattern library and similarity matching based on the high-level feature set, the current behavior pattern and tactical intent of the drone swarm are identified. Then, based on a preset typical swarm configuration knowledge base, logical reasoning is performed based on the current behavior pattern and tactical intent to deduce the command and control logic, unit functional roles, and coordination rules of the drone swarm, thereby determining the corresponding system configuration. Then, based on the command and control logic, unit functional roles, and coordination rules, key units are identified from the drone swarm. Finally, the system configuration, the behavior state of the key units, and the current confrontation situation represented by the global dynamic situation map are matched with multiple preset confrontation stage models to determine the current confrontation stage of the drone swarm.

[0098] As a further implementation of the method, the steps of predicting at least one subsequent confrontation phase and the corresponding swarm behavior characteristics of the drone swarm after the current confrontation phase, based on the system configuration and key units, include:

[0099] Step S41: Based on the system configuration, key units, and current confrontation stage, query the preset tactical evolution knowledge graph to obtain the typical tactical task chain that best matches the current confrontation situation.

[0100] It should be noted that the pre-defined tactical evolution knowledge graph is a structured representation of domain knowledge. It systematically encodes, in the form of nodes and relationships, the possible development sequences and evolutionary paths (i.e., typical tactical mission chains) of the UAV swarm during various typical mission scenarios, representing the possible development phases of their combat stages. The query in step S41 essentially uses the currently known system configuration, key unit states, and current combat stage as query conditions to find the subsequent evolutionary sequence in the graph that has the highest matching degree—that is, is the most logically coherent and most likely to occur.

[0101] Step S42: Based on a typical tactical mission chain, determine at least one subsequent confrontation phase.

[0102] Step S43: For each subsequent confrontation stage, based on the preset group behavior rule base, according to the system configuration and the role behavior templates of key units in the tactical evolution knowledge graph, the group behavior characteristics corresponding to the subsequent confrontation stage are deduced. Among them, the group behavior characteristics include at least cluster movement mode, communication interaction mode and attack mode.

[0103] It should be noted that the preset group behavior rule base defines the collaborative behavior rules and dynamic models followed by various functional units (roles) under different system configuration constraints. The deduction in step S43 involves calling the corresponding behavior rules in this rule base under the predicted subsequent confrontation stage and the known system configuration framework, and combining them with the role behavior templates of key units to calculate or simulate the specific and observable behavior patterns (such as movement, communication, and attack patterns) that the swarm as a whole and key units are most likely to exhibit in this stage.

[0104] In the above implementation, in order to obtain the subsequent confrontation stage and the corresponding group behavior characteristics, based on the system configuration, key units and the current confrontation stage, a preset tactical evolution knowledge graph is queried to obtain the typical tactical task chain with the highest matching degree with the current confrontation situation. Then, based on the typical tactical task chain, at least one subsequent confrontation stage is determined. Then, for each subsequent confrontation stage, based on the preset group behavior rule base, the group behavior characteristics corresponding to the subsequent confrontation stage are deduced according to the role behavior templates corresponding to the system configuration and key units in the tactical evolution knowledge graph. The group behavior characteristics include at least cluster movement mode, communication interaction mode and attack mode.

[0105] As a further implementation of the method, a multi-stage induction signal sequence is generated based on the current adversarial stage, subsequent adversarial stages, and swarm behavior characteristics. The induction signal, configured differently for each subsequent adversarial stage, is set to: utilize the swarm behavior characteristics of that subsequent adversarial stage to trigger a preset state response in the drone swarm. This preset state response is planned as a step to execute favorable conditions for the next stage of induction signals, including:

[0106] Step S51: Based on the current confrontation phase and the subsequent confrontation phase, determine the overall guidance target, and set phase guidance targets for the current confrontation phase and each subsequent confrontation phase that serve the overall guidance target. The phase guidance target is configured to guide the drone swarm into a preset state response, which is planned to both serve the overall guidance target and constitute favorable conditions for executing the next phase of guidance.

[0107] Step S52: For the current confrontation stage and each subsequent confrontation stage, at least one induction signal is selected or combined from a preset induction signal library based on the group behavior characteristics corresponding to the confrontation stage. The induction signal is configured to trigger the corresponding stage induction target by utilizing the group behavior pattern corresponding to the confrontation stage.

[0108] Step S53: For the inducement signals generated in the current confrontation stage and all subsequent confrontation stages, sort and coordinate them according to the order of each confrontation stage to generate a multi-stage inducement signal sequence. In the multi-stage inducement signal sequence, the inducement signals of adjacent stages are interconnected in terms of action logic, signal parameters and spatiotemporal configuration.

[0109] In the above embodiments, in order to generate a multi-stage inducement signal sequence, an overall inducement target is determined based on the current confrontation stage and subsequent confrontation stages, and stage inducement targets serving the overall inducement target are set for the current confrontation stage and each subsequent confrontation stage. The stage inducement target is configured to guide the UAV swarm into a preset state response. This state response is planned to both serve the overall inducement target and constitute favorable conditions for executing the next stage of inducement. Then, for the current confrontation stage and each subsequent confrontation stage, at least one inducement signal is selected or combined from a preset inducement signal library according to the group behavior characteristics corresponding to the confrontation stage. The inducement signal is configured to trigger the corresponding stage inducement target using the group behavior pattern corresponding to the confrontation stage. Then, the inducement signals generated in the current confrontation stage and all subsequent confrontation stages are sorted and coordinated according to the order of each confrontation stage to generate a multi-stage inducement signal sequence. The inducement signals of adjacent stages in the multi-stage inducement signal sequence are interconnected in terms of action logic, signal parameters, and spatiotemporal configuration.

[0110] As a further implementation of the method, the step of sequentially applying induction signals from a multi-stage induction signal sequence to the drone swarm, and evaluating the state response of the drone swarm based on an updated global dynamic situation map after applying the induction signals, includes:

[0111] Step S61: Through multiple directional launch units of the air-space-ground collaborative system, inducement signals from a multi-stage inducement signal sequence are applied to the UAV swarm within the corresponding spatiotemporal window.

[0112] Step S62: After applying the induction signal, the latest multi-source detection data is obtained through the air-space-ground collaborative system, and the global dynamic situation map is updated.

[0113] Step S63: Based on the updated global dynamic situation map, extract the state response features of the UAV swarm, and compare the state response features with the stage guidance target corresponding to the guidance signal to evaluate whether the expectation has been achieved.

[0114] In the above implementation, in order to form a real-time closed loop of "application-evaluation" and to make the confrontation process observable and measurable, multiple directional launch units of the air-space-ground collaborative system apply multi-stage induction signal sequences to the UAV swarm within the corresponding spatiotemporal window. After applying the induction signals, the latest multi-source detection data is obtained through the air-space-ground collaborative system, and the global dynamic situation map is updated. Then, based on the updated global dynamic situation map, the state response characteristics of the UAV swarm are extracted, and the state response characteristics are compared with the stage induction targets corresponding to the induction signals to evaluate whether the expectations have been met.

[0115] As a further implementation of the method, the air-space-ground collaborative system includes:

[0116] Space-based detection nodes are used to provide wide-area surveillance information.

[0117] Airborne detection and signaling nodes, including early warning aircraft and dedicated unmanned aerial vehicles, are used for regional detection and induced signal transmission.

[0118] Ground-based detection and countermeasures nodes, including radar stations, electro-optical tracking equipment, directional jamming equipment, and decoy equipment, are used for precise end-point tracking and signal application.

[0119] The command and control center connects to space-based detection nodes, air-based detection and signal application nodes, and ground-based detection and countermeasure nodes through communication networks to achieve data aggregation, fusion, and command distribution.

[0120] In the above implementation, the integrated distributed system of air-space-ground coordination realizes the integrated detection, tracking and signal application functions, effectively supporting the dynamic adjustment and optimization of countermeasures. At the same time, the distributed and multi-layered system architecture provides highly reliable and low-exposure physical support for the countermeasures process, and realizes the highly coordinated and closed-loop operation of detection, decision-making, countermeasures and evaluation functions.

[0121] This application also discloses a low-altitude security command and control system that integrates air, space, and ground.

[0122] refer to Figure 2 A low-altitude security command and control system integrating air, space, and ground operations is applied in the command and control center, which is equipped with:

[0123] The global dynamic situation map generation module is used to acquire multi-source detection data of UAV swarms through the air-space-ground collaborative system, and generate a global dynamic situation map based on the multi-source detection data.

[0124] The cognitive analysis module is used to perform cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the drone swarm;

[0125] The prediction module is used to predict at least one subsequent confrontation phase and the corresponding swarm behavior characteristics of the drone swarm after the current confrontation phase, based on the system configuration and key units.

[0126] The inducement signal sequence generation module is used to generate a multi-stage inducement signal sequence based on the current confrontation stage, subsequent confrontation stages and group behavior characteristics. The inducement signal configured differently for each subsequent confrontation stage is set to: use the group behavior characteristics of the subsequent confrontation stage to trigger the drone swarm to generate a preset state response. The preset state response is planned as a favorable condition for executing the next stage inducement signal.

[0127] The induction signal application module is used to sequentially apply induction signals from a multi-stage induction signal sequence to the drone swarm, and after applying the induction signals, evaluate the state response of the drone swarm based on the updated global dynamic situation map.

[0128] The replanning module is used to trigger the cognitive analysis module, prediction module, inducement signal sequence generation module, inducement signal application module, and replanning module to re-execute the processing flow if the state response deviates from the expectation, based on the latest global dynamic situation map.

[0129] The air-space-ground coordinated low-altitude security command and control system of the present invention can realize any of the methods in the air-space-ground coordinated low-altitude security command and control method, and the specific working process of the air-space-ground coordinated low-altitude security command and control system of the present invention can refer to the corresponding process in the above-mentioned air-space-ground coordinated low-altitude security command and control method.

[0130] This application also discloses a computer device.

[0131] refer to Figure 3 A computer device includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement any of the above-mentioned methods of air-space-ground coordinated low-altitude security command and control.

[0132] This application also discloses a computer-readable storage medium.

[0133] A computer-readable storage medium storing a computer program that can be loaded by a processor and executed any of the above-described methods for low-altitude security command and control in a space-air-ground coordinated manner.

[0134] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0135] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A low-altitude security command and control method integrating air, space, and ground, characterized in that: The method is executed by the command and control center and includes: Step S11: Obtain multi-source detection data of the UAV swarm through the air-space-ground collaborative system, and generate a global dynamic situation map based on the multi-source detection data; Step S12: Perform cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm; Step S13: Based on the system configuration and the key units, predict at least one subsequent confrontation phase of the drone swarm after the current confrontation phase and the corresponding group behavior characteristics; Step S14: Generate a multi-stage induction signal sequence based on the current confrontation stage, the subsequent confrontation stage, and the group behavior characteristics. The induction signal configured differently for each subsequent confrontation stage is set to: use the group behavior characteristics of the subsequent confrontation stage to trigger the drone swarm to generate a preset state response. The preset state response is planned as a favorable condition for executing the next stage induction signal. Step S15: sequentially apply the induction signals in the multi-stage induction signal sequence to the drone swarm, and after applying the induction signals, evaluate the state response of the drone swarm based on the updated global dynamic situation map; Step S16: If the state response deviates from the expectation, then based on the latest global dynamic situation map, the execution will restart from step S12.

2. The air-space-ground coordinated low-altitude security command and control method according to claim 1, characterized in that, The step of generating a global dynamic situation map based on the multi-source detection data includes: The multi-source detection data is subjected to spatiotemporal registration and coordinate unification processing to obtain collaborative detection data, wherein the multi-source detection data includes at least one of radar data, spectrum data, photoelectric data, and sound data; The collaborative detection data is subjected to target association, track fusion and feature extraction to generate a target feature set, wherein the target feature set includes individual features and cluster features. The individual features include identity, type, location, speed, heading and signal strength. The cluster features include cluster number, density, geometric center, direction of movement, topology and communication mode. By associating and fusing preset geographic information data, preset defense resource deployment data, and the target feature set, a global dynamic situation map is generated. The global dynamic situation map is used to characterize the spatial distribution, movement trend, and threat level of the UAV swarm.

3. The air-space-ground coordinated low-altitude security command and control method according to claim 2, characterized in that, The steps of performing cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm include: Based on the global dynamic situation map, a high-level feature set for representing behavior and intent is extracted; Based on a preset behavior pattern library and similarity matching based on the high-level feature set, the current behavior pattern and tactical intent of the drone swarm are identified. Based on a pre-defined knowledge base of typical swarm configurations, logical reasoning is performed according to the current behavior pattern and the tactical intent to deduce the command and control logic, unit functional roles and coordination rules of the drone swarm, and thus determine the corresponding system configuration. Based on the command and control logic, the functional roles of the units, and the coordination rules, key units are identified from the drone swarm. The system configuration, the behavioral state of the key units, and the current adversarial situation represented by the global dynamic situation map are matched with multiple preset adversarial stage models to determine the current adversarial stage of the drone swarm.

4. The air-space-ground coordinated low-altitude security command and control method according to claim 1, characterized in that, The step of predicting at least one subsequent confrontation phase and corresponding swarm behavior characteristics of the drone swarm after the current confrontation phase, based on the system configuration and the key units, includes: Based on the system configuration, the key units, and the current confrontation stage, a preset tactical evolution knowledge graph is queried to obtain the typical tactical task chain with the highest matching degree to the current confrontation situation; Based on the typical tactical mission chain, at least one subsequent confrontation phase is determined; For each subsequent confrontation stage, based on a preset group behavior rule base, and according to the system configuration and the role behavior templates corresponding to the key units in the tactical evolution knowledge graph, the group behavior characteristics corresponding to that subsequent confrontation stage are deduced. The group behavior characteristics include at least cluster movement mode, communication interaction mode and attack mode.

5. The air-space-ground coordinated low-altitude security command and control method according to claim 1, characterized in that, The step of generating a multi-stage induction signal sequence based on the current confrontation stage, the subsequent confrontation stage, and the swarm behavior characteristics, wherein the induction signal configured differently for each of the subsequent confrontation stages is set as follows: utilizing the swarm behavior characteristics of that subsequent confrontation stage, triggering the drone swarm to generate a preset state response, which is planned as a favorable condition for executing the next stage induction signal, includes the following steps: Based on the current confrontation phase and the subsequent confrontation phase, an overall guidance target is determined, and a phase guidance target serving the overall guidance target is set for the current confrontation phase and each of the subsequent confrontation phases. The phase guidance target is configured to guide the drone swarm into a preset state response, which is planned to both serve the overall guidance target and constitute favorable conditions for executing the next phase of guidance. For the current confrontation phase and each subsequent confrontation phase, at least one induction signal is selected or combined from a preset induction signal library based on the group behavior characteristics corresponding to the confrontation phase. The induction signal is configured to trigger the corresponding phase induction target by utilizing the group behavior pattern corresponding to the confrontation phase. For the inducement signals generated in the current confrontation phase and all subsequent confrontation phases, they are sorted and coordinated according to the order of each confrontation phase to generate a multi-stage inducement signal sequence. In the multi-stage inducement signal sequence, the inducement signals of adjacent phases are interconnected in terms of action logic, signal parameters and spatiotemporal configuration.

6. The air-space-ground coordinated low-altitude security command and control method according to claim 5, characterized in that, The step of sequentially applying the induction signals from the multi-stage induction signal sequence to the drone swarm, and evaluating the state response of the drone swarm based on the updated global dynamic situation map after applying the induction signals, includes: Through multiple directional launch units of the aforementioned air-space-ground collaborative system, the induction signals in the multi-stage induction signal sequence are applied to the UAV swarm within the corresponding spatiotemporal window; After the induction signal is applied, the latest multi-source detection data is obtained through the air-space-ground collaborative system, and the global dynamic situation map is updated. Based on the updated global dynamic situation map, the state response features of the UAV swarm are extracted, and the state response features are compared with the stage guidance target corresponding to the guidance signal to evaluate whether the expectation has been achieved.

7. The air-space-ground coordinated low-altitude security command and control method according to claim 1, characterized in that, The air-space-ground coordinated system includes: Space-based detection nodes are used to provide wide-area surveillance information; Airborne detection and signaling nodes, including early warning aircraft and dedicated UAVs, are used for regional detection and induced signal transmission; Ground-based detection and countermeasures nodes, including radar stations, electro-optical tracking equipment, directional jamming equipment, and decoy equipment, are used for precise terminal tracking and signal application; The command and control center is connected to the space-based detection node, the air-based detection and signal application node, and the ground-based detection and countermeasure node through a communication network to achieve data aggregation, fusion, and command distribution.

8. A low-altitude security command and control system integrating air, space, and ground, characterized in that: It is applied to a command and control center, which is configured with: The global dynamic situation map generation module is used to acquire multi-source detection data of UAV swarms through the air-space-ground collaborative system, and generate a global dynamic situation map based on the multi-source detection data. The cognitive analysis module is used to perform cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm. The prediction module is used to predict at least one subsequent confrontation phase and the corresponding group behavior characteristics of the drone swarm after the current confrontation phase, based on the system configuration and the key units. The induction signal sequence generation module is used to generate a multi-stage induction signal sequence based on the current confrontation stage, the subsequent confrontation stage, and the group behavior characteristics. The induction signal, which is configured differently for each of the subsequent confrontation stages, is set to trigger the drone swarm to generate a preset state response by utilizing the group behavior characteristics of the subsequent confrontation stage. The preset state response is planned as a favorable condition for executing the next stage induction signal. The induction signal application module is used to sequentially apply the induction signals in the multi-stage induction signal sequence to the drone swarm, and after applying the induction signals, evaluate the state response of the drone swarm based on the updated global dynamic situation map; The replanning module is used to trigger the cognitive analysis module, the prediction module, the induced signal sequence generation module, the induced signal application module, and the replanning module to re-execute the processing flow based on the latest global dynamic situation map if the state response deviates from the expectation.

9. A computer device, characterized in that, The method includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and execute the method of any one of claims 1 to 7.

Images