A multi-source threat strategy generation method and system of a drone navigation deception data set integration computing system

Abstract

The application provides a multi-source threat strategy generation method and system of a UAV navigation deception data integrated computing system. First, the navigation signal data of the UAV and multi-source threat perception data are obtained, wherein the multi-source threat perception data includes geographic space radio frequency fingerprints and visual trajectory features. Second, the geographic space radio frequency fingerprints and visual trajectory features are fused to generate a dynamic threat situation map. Third, based on the antigen-antibody reaction mechanism, a matching relationship between the dynamic threat situation map and the UAV navigation protocol vulnerability library is constructed, and semantic ambiguity points that can be exploited are identified. Finally, navigation deception strategies are generated under the constraints of the navigation signal space-time. The technical solution provided by the application not only realizes accurate identification and adaptive response of abnormal behaviors of the UAV and navigation protocol vulnerabilities, but also ensures the naturalness and concealment of the deception process, and improves the reliability and environmental adaptability of the UAV guidance.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) navigation security technology, and in particular to a method and system for generating multi-source threat strategies in an UAV navigation deception data integration and computing system. Background Technology

[0002] With the increasing popularity of commercial drone applications such as logistics delivery and aerial photography, irregular flight operations of drones in civilian scenarios such as logistics parks and commercial airspace are on the rise. At the same time, it is necessary to support a precise navigation and guidance strategy that can intelligently sense the operating status of drones.

[0003] Current technical solutions mainly adopt a protocol parsing method based on a predefined rule base. By comparing the feature patterns of known UAV navigation protocols, potential security risks are identified, and corresponding navigation guidance signals are generated according to a fixed algorithm.

[0004] However, this approach still has significant drawbacks. The static rule base struggles to adapt to dynamically changing flight environments and diverse UAV behavior patterns, and cannot flexibly respond to unforeseen flight conditions or new variations of navigation protocols. Furthermore, the lack of an intelligent fusion mechanism for multi-source perception data leads to inconsistent navigation commands in complex civilian environments, reducing the reliability of safe guidance. Summary of the Invention

[0005] This application provides a method and system for generating multi-source threat strategies in a drone navigation deception data integration computing system, which solves the problems in the prior art where static rule bases are difficult to adapt to dynamic flight environments and diverse drone behavior patterns, lack of intelligent fusion mechanism for multi-source perception data, and the generation of guidance strategies that are prone to inconsistent navigation commands in complex environments.

[0006] Firstly, this application provides a method for generating multi-source threat strategies in an unmanned aerial vehicle (UAV) navigation deception data integration computing system, including:

[0007] Acquire real-time navigation signal data and multi-source threat perception data of the target UAV, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring equipment and visual trajectory features from optical sensors;

[0008] The geospatial radio frequency fingerprint and the visual trajectory features are fused in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics.

[0009] Based on the antigen-antibody response mechanism of the biological immune system, a matching relationship is constructed between a dynamic threat situation map and a predefined vulnerability database of UAV navigation protocols, and the semantic ambiguities that can be exploited in a specific UAV navigation protocol are identified based on the matching relationship.

[0010] Based on the semantic ambiguity points, a navigation deception strategy is generated under the constraint of maintaining the spatiotemporal continuity of navigation signals.

[0011] Optionally, real-time navigation signal data and multi-source threat perception data of the target UAV are acquired, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring equipment and visual trajectory features from optical sensors, including:

[0012] The radio spectrum monitoring equipment pre-deployed at fixed monitoring points receives the navigation frequency band radio frequency signal of the target UAV and extracts the pulse sequence carrying the signal strength distribution pattern from the radio frequency signal;

[0013] A geospatial radio frequency fingerprint reflecting the spatial location of the target UAV is constructed based on the pulse sequence;

[0014] The visible light video stream of the target drone is acquired by an optical sensor, and pixel clusters containing the motion contour sequence of the target drone are extracted from the visible light video stream. Visual trajectory features are formed based on the motion trajectory of the pixel clusters.

[0015] The geospatial radio frequency fingerprint and the visual trajectory features are encapsulated into multi-source threat perception data with a unified timestamp.

[0016] Optionally, the geospatial radio frequency fingerprint and the visual trajectory features are fused in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics, including:

[0017] Establish a spatial mapping relationship between the pulse sequence contained in the geospatial radio frequency fingerprint and the pixel clusters contained in the visual trajectory features;

[0018] Based on the aforementioned spatial mapping relationship, pulse sequences with a unified timestamp are temporally correlated with pixel clusters to form a spatiotemporally correlated data group.

[0019] The spatiotemporal correlated data set is overlaid with predefined environmental geographic information to obtain the overlay result;

[0020] Based on the overlay results, a dynamic threat situation map is generated that includes the real-time location, trajectory, and environmental constraints of the target UAV.

[0021] Optionally, based on the antigen-antibody response mechanism of the biological immune system, a matching relationship is constructed between a dynamic threat situation map and a predefined database of vulnerabilities in UAV navigation protocols. Based on this matching relationship, exploitable semantic ambiguities in specific UAV navigation protocols are identified, including:

[0022] Based on the antigen-antibody response mechanism of the biological immune system, the abnormal behavior characteristics of drones contained in the dynamic threat situation map are used as antigen representations.

[0023] The protocol defect patterns stored in the UAV navigation protocol vulnerability database are used as antibody templates;

[0024] By simulating the specific binding mechanism of antigens and antibodies in the biological immune system, a matching relationship between the antigen characterization and the antibody template is established.

[0025] Based on the matching relationship, exploitable semantic ambiguities in the navigation protocol data segment are identified from the matched protocol defect patterns.

[0026] Optionally, by simulating the specific binding mechanism of antigens and antibodies in the biological immune system, a matching relationship between the antigen characterization and the antibody template is established, including:

[0027] Extract a set of key parameters describing the abnormal behavior of the drone from the antigen characterization to form an antigen feature vector;

[0028] Extract the set of key attributes describing the protocol defect patterns from the antibody template to form an antibody feature vector;

[0029] Calculate the configurational matching degree between the antigen feature vector and the antibody feature vector in the vector space;

[0030] Matching antibody templates are selected based on configurational matching to establish a matching relationship between antigen characterization and antibody templates.

[0031] Optionally, based on the semantic ambiguity points, a navigation deception strategy is generated under the constraint of maintaining the spatiotemporal continuity of the navigation signal, including:

[0032] Based on the location information of the semantic ambiguity points in the navigation protocol data segment, misleading navigation parameters consistent with the original navigation signal format are constructed;

[0033] The dynamic response characteristics of the target UAV navigation system are obtained, including the navigation parameter update rate and trajectory smoothness requirements.

[0034] The misleading navigation parameters are organized into a continuous signal frame structure according to the time series, ensuring that the parameter change amplitude between adjacent signal frames conforms to the dynamic response characteristics;

[0035] The signal frame structure is associated with the actual geospatial coordinates to construct a misleading flight path with geometric topological consistency;

[0036] A navigation deception strategy containing a timestamp sequence is generated based on the misleading flight path.

[0037] Optionally, the signal frame structure is associated with actual geospatial coordinates to construct a misleading flight path with geometric topological consistency, including:

[0038] The navigation parameter sequence, which includes position coordinates and heading angle data, is extracted from the signal frame structure.

[0039] The location coordinates in the navigation parameter sequence are mapped to the actual geospatial coordinate system to form a discrete path point set;

[0040] The connection relationship between adjacent discrete path points is determined based on the heading angle data;

[0041] A continuous spatial path curve is generated based on the discrete path point set and connection relationships.

[0042] The spatial path curve is smoothed to ensure that the path curvature change conforms to the flight dynamics constraints of the UAV, thus forming the misleading flight path.

[0043] Secondly, this application provides a multi-source threat strategy generation system for an unmanned aerial vehicle (UAV) navigation deception data integration computing system, comprising:

[0044] The acquisition module acquires real-time navigation signal data and multi-source threat perception data of the target UAV, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring equipment and visual trajectory features from optical sensors.

[0045] The fusion module fuses the geospatial radio frequency fingerprint with the visual trajectory features in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics.

[0046] The module constructs a matching relationship between a dynamic threat landscape map and a predefined vulnerability database of drone navigation protocols, based on the antigen-antibody reaction mechanism of the biological immune system, and identifies exploitable semantic ambiguities in specific drone navigation protocols based on the matching relationship.

[0047] The generation module generates a navigation deception strategy based on the semantic ambiguity points, while maintaining the spatiotemporal continuity of the navigation signal.

[0048] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a multi-source threat strategy generation method for a drone navigation deception data integration computing system as described in the first aspect above.

[0049] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a multi-source threat strategy generation method for a drone navigation deception data integration computing system as described in the first aspect.

[0050] This application addresses the problem of insufficient multi-source data fusion capabilities in existing technologies by generating dynamic threat situation maps with environmental context semantics through the fusion of multi-source threat perception data. By introducing the antigen-antibody reaction mechanism of the biological immune system to establish dynamic matching relationships, it achieves adaptive identification of unknown threats and novel protocol vulnerabilities, overcoming the limitations of static rule bases in adapting to dynamic environments. Finally, under the constraint of maintaining the spatiotemporal continuity of navigation signals, it generates deception strategies, ensuring the reliability and consistency of the deception strategies in complex environments.

[0051] Furthermore, by associating the signal frame structure with geospatial coordinates, a misleading flight path with geometric topological consistency is constructed, solving the problem of insufficient spatial continuity of navigation commands in existing technologies. By smoothing the spatial path curve and conforming to the flight mechanics constraints of UAVs, it is ensured that the generated misleading path not only meets the requirements of spatiotemporal continuity of navigation signals but also has the feasibility of actual flight, significantly improving the environmental adaptability and execution reliability of the deception strategy.

[0052] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 A flowchart of a multi-source threat strategy generation method for a drone navigation deception data integration computing system provided in this application is shown;

[0055] Figure 2 This paper presents a schematic diagram of the structure of a multi-source threat strategy generation system for a drone navigation deception data integration computing system provided in this application;

[0056] Figure 3 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0057] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0058] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0059] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] Figure 1 This application provides a flowchart of a multi-source threat strategy generation method for an unmanned aerial vehicle (UAV) navigation deception data integration computing system, as shown in the flowchart. Figure 1 As shown, the method includes:

[0061] Step 101: Acquire real-time navigation signal data and multi-source threat perception data of the target UAV, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring equipment and visual trajectory features from optical sensors.

[0062] Optionally, step 101 may specifically include the following steps:

[0063] Step 1011: Receive the navigation frequency band radio frequency signal of the target UAV through radio spectrum monitoring equipment pre-deployed at a fixed monitoring point, and extract the pulse sequence carrying the signal strength distribution pattern from the radio frequency signal;

[0064] Step 1012: Construct a geospatial radio frequency fingerprint reflecting the spatial location of the target UAV based on the pulse sequence;

[0065] Step 1013: Acquire the visible light video stream of the target UAV through an optical sensor, extract pixel clusters containing the motion contour sequence of the target UAV from the visible light video stream, and form visual trajectory features based on the motion trajectory of the pixel clusters;

[0066] Step 1014: Encapsulate the geospatial radio frequency fingerprint and the visual trajectory features into multi-source threat perception data with a unified timestamp.

[0067] In the above scheme, real-time navigation signal data refers to the positioning and navigation-related signals continuously emitted by the UAV during flight; multi-source threat perception data is fused data collected by multiple sensors, including geospatial radio frequency fingerprints (a spatial location identifier generated by analyzing the distribution pattern of radio frequency signal strength) from radio spectrum monitoring equipment and visual trajectory features from optical sensors (trajectory data formed by analyzing the target motion contour in the video stream); radio spectrum monitoring equipment is a hardware device used to receive radio frequency signals in a specific frequency band; optical sensors are imaging devices that collect visible light or infrared video; navigation frequency band radio frequency signals are specific frequency wireless signals used by the UAV in navigation and communication; pulse sequences of signal strength distribution patterns are data packets of intensity changes arranged in time sequence in the radio frequency signal; visible light video stream is an image sequence continuously collected by optical sensors; and pixel clusters of motion contour sequences are sets of pixels in the video stream that describe the shape and motion state of the target UAV.

[0068] In this scheme, firstly, in step 1011, radio spectrum monitoring equipment pre-deployed at a fixed monitoring point receives the navigation frequency band radio frequency signal of the target UAV, and uses signal processing technology to extract the pulse sequence carrying the signal strength distribution pattern from the radio frequency signal. Secondly, in step 1012, a geospatial radio frequency fingerprint reflecting the spatial location of the target UAV is constructed based on the spatial characteristics of the pulse sequence. Simultaneously, in step 1013, an optical sensor acquires the visible light video stream of the target UAV, and computer vision technology is used to extract pixel clusters containing the motion contour sequence of the target UAV from the video stream, and visual trajectory features are formed based on the motion changes of the pixel clusters. Finally, in step 1014, the geospatial radio frequency fingerprint and visual trajectory features are encapsulated in time-synchronized multi-source threat perception data with a unified timestamp.

[0069] For example, in a logistics park in region A, a Type B radio spectrum monitoring device deployed at a high point in the park continuously receives the navigation frequency band radio frequency signals from drones, while a Type C optical sensor collects visible light video streams. The signal processing unit extracts pulse sequences with intensity distribution characteristics from the radio frequency signals, and the computer vision system identifies clusters of moving contour pixels from the video stream. These data are then timestamped to generate multi-source threat perception data packets containing spatial location and visual trajectory information.

[0070] This solution enables precise capture of UAV navigation signals and collaborative acquisition of multi-source perception data. Through complementary verification of radio frequency signals and visual data, it improves the reliability of target spatial positioning and the continuity of trajectory tracking, providing a high-quality multimodal data foundation for subsequent threat analysis.

[0071] Step 102: The geospatial radio frequency fingerprint and the visual trajectory features are fused in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics.

[0072] Optionally, step 102 may specifically include the following steps:

[0073] Step 1021: Establish the spatial mapping relationship between the pulse sequence contained in the geospatial radio frequency fingerprint and the pixel clusters contained in the visual trajectory features;

[0074] Step 1022: Based on the spatial mapping relationship, pulse sequences with a unified timestamp are temporally associated with pixel clusters to form a spatiotemporally associated data group;

[0075] Step 1023: Overlay the spatiotemporal correlation data group with predefined environmental geographic information to obtain the overlay result;

[0076] Step 1024: Generate a dynamic threat situation map based on the overlay results, which includes the real-time location, trajectory, and environmental constraints of the target UAV.

[0077] In the above scheme, the dynamic threat situation map is a visual data map that comprehensively represents the real-time motion status of the UAV and its relationship with the surrounding environment. It includes the UAV's real-time location (the instantaneous spatial coordinates of the UAV), motion trajectory (the path formed by the continuous movement of the UAV), and the constraints of the surrounding environment (the spatial relationship between the UAV and surrounding geographical elements such as buildings and no-fly zones). The spatial mapping relationship is a method to establish the coordinate correspondence between radio frequency signal pulse sequences and visual pixel clusters. The spatiotemporal correlation data group is a structured dataset formed by fusing spatial data with time synchronization characteristics. The predefined environmental geographic information is pre-entered digital map data containing geographical elements such as building outlines and terrain elevation. The overlay result is a comprehensive data expression generated by fusing multi-source data and geographic information.

[0078] In this scheme, firstly, a spatial mapping relationship is established between the pulse sequence contained in the geospatial radio frequency fingerprint and the pixel cluster contained in the visual trajectory features through the coordinate transformation algorithm in step 1021, spatially aligning the radio frequency signal data and visual data in different coordinate systems. Secondly, based on the spatial mapping relationship, the pulse sequence with a unified timestamp and the pixel cluster are temporally correlated in step 1022, forming a spatiotemporally correlated data group that simultaneously contains spatial location and temporal information. Then, in step 1023, the spatiotemporally correlated data group is overlaid with predefined environmental geographic information, and the UAV motion data is integrated with geographic environmental elements through a spatial fusion algorithm. Finally, based on the overlay result in step 1024, a dynamic threat situation map containing the real-time position, motion trajectory, and surrounding environmental constraints of the target UAV is generated using situation visualization technology.

[0079] Following the previous specific step, in the application scenario of a logistics park in region A, the system fuses the geospatial radio frequency fingerprint and visual trajectory features obtained in step 101. By establishing a spatial mapping between radio frequency pulse sequences and visual pixel clusters, the coordinates of the UAV in radio positioning are unified with the visual observation coordinates. Subsequently, the time-synchronized data is overlaid with environmental geographic information such as warehouse building boundaries, loading and unloading areas, and no-fly zones in the park's digital map, ultimately generating a dynamic threat situation map that displays the UAV's location, flight path, and spatial relationship with surrounding buildings in real time.

[0080] This solution achieves spatiotemporal fusion of multi-source heterogeneous data. By integrating radio frequency positioning data and visual trajectory data under a unified spatiotemporal framework and combining them with environmental geographic information, a dynamic situation map that can comprehensively reflect the relationship between the UAV's motion state and environmental constraints is generated.

[0081] Step 103: Based on the antigen-antibody response mechanism of the biological immune system, construct a matching relationship between the dynamic threat situation map and the predefined UAV navigation protocol vulnerability database, and identify exploitable semantic ambiguities in specific UAV navigation protocols based on the matching relationship.

[0082] Optionally, step 103 may specifically include the following steps:

[0083] Step 1031: Based on the antigen-antibody response mechanism of the biological immune system, the abnormal behavior characteristics of the drones contained in the dynamic threat situation map are used as antigen representations.

[0084] Step 1032: Use the protocol defect patterns stored in the UAV navigation protocol vulnerability database as antibody templates;

[0085] Step 1033: By simulating the specific binding mechanism of antigens and antibodies in the biological immune system, a matching relationship is established between the antigen characterization and the antibody template;

[0086] Step 1033 may specifically include the following steps:

[0087] The set of key parameters describing the abnormal behavior of the UAV is extracted from the antigen characterization to form an antigen feature vector. The set of key attributes describing the protocol defect pattern is extracted from the antibody template to form an antibody feature vector. The configuration matching degree of the antigen feature vector and the antibody feature vector in the vector space is calculated. Matching antibody templates are selected based on the configuration matching degree to establish the matching relationship between the antigen characterization and the antibody template.

[0088] Step 1034: Based on the matching relationship, identify exploitable semantic ambiguities in the navigation protocol data segment from the matched protocol defect patterns.

[0089] In the above scheme, the antigen-antibody reaction mechanism draws on the biological principle of specific binding between antigens and antibodies in the biological immune system; the UAV navigation protocol vulnerability database is a database storing known navigation protocol defects; semantic ambiguity points are data segments in the navigation protocol that may have interpretation discrepancies; antigen representation is the transformation of abnormal UAV behavior characteristics into data representations similar to antigens; protocol defect patterns are feature templates describing known vulnerabilities in the navigation protocol; antibody templates are structured descriptions of protocol defect patterns; the specific binding mechanism is a computational method simulating the precise matching of antigens and antibodies in biological immunity; the key parameter set is the core feature group describing abnormal UAV behavior; the antigen feature vector is the representation of key parameters as mathematical vectors; the key attribute set is the core feature group describing protocol defect patterns; the antibody feature vector is the representation of key attributes as mathematical vectors; and configuration matching degree is an indicator measuring the similarity between two vectors in spatial structure.

[0090] In this scheme, firstly, step 1031, based on the antigen-antibody reaction mechanism of the biological immune system, uses the abnormal behavior features of UAVs contained in the dynamic threat situation map as antigen representations to extract abnormal features such as abnormal flight trajectories and sudden speed changes. Secondly, step 1032 uses protocol defect patterns stored in the UAV navigation protocol vulnerability database as antibody templates and loads known navigation protocol vulnerability feature patterns. Then, step 1033 simulates the specific binding mechanism of antigen and antibody in the biological immune system, extracting a set of key parameters describing the abnormal behavior of UAVs from the antigen representation to form an antigen feature vector, and extracting a set of key attributes describing the protocol defect patterns from the antibody template to form an antibody feature vector. The configurational matching degree of the antigen feature vector and the antibody feature vector in the vector space is calculated, and matching antibody templates are selected based on the configurational matching degree to establish a matching relationship between the antigen representation and the antibody template. Finally, step 1034, based on the matching relationship, identifies exploitable semantic ambiguities in the navigation protocol data segments from the matched protocol defect patterns.

[0091] Following the previous specific step, in the application scenario of a logistics park in region A, the system, based on the dynamic threat situation map generated in step 102, detected abnormal circling behavior of a drone near warehouse B. The system transforms this abnormal behavior feature into an antigen characterization, and simultaneously calls the defect pattern of the C-type drone protocol from the navigation protocol vulnerability database as an antibody template. By calculating the configurational matching degree between the antigen feature vector and the antibody feature vector, it is found that this abnormal behavior highly matches a GPS latitude and longitude verification vulnerability, ultimately identifying the semantic ambiguity point in the latitude and longitude data verification area of ​​the protocol.

[0092] This solution introduces an innovative analogy of biological immune mechanisms to achieve intelligent matching between abnormal drone behavior and protocol vulnerabilities, enabling it to adaptively identify new threat patterns and potential vulnerabilities in various navigation protocols.

[0093] Step 104: Based on the semantic ambiguity points, generate a navigation deception strategy while maintaining the spatiotemporal continuity of the navigation signal.

[0094] Optionally, step 104 may specifically include the following steps:

[0095] Step 1041: Based on the location information of the semantic ambiguity point in the navigation protocol data segment, construct misleading navigation parameters that are consistent with the original navigation signal format;

[0096] Step 1042: Obtain the dynamic response characteristics of the target UAV navigation system, wherein the dynamic response characteristics include the navigation parameter update rate and trajectory smoothness requirements;

[0097] Step 1043: Organize the misleading navigation parameters into a continuous signal frame structure according to the time series to ensure that the parameter change amplitude between adjacent signal frames conforms to the dynamic response characteristics;

[0098] Step 1044: Associate the signal frame structure with the actual geospatial coordinates to construct a misleading flight path with geometric topological consistency;

[0099] Step 1044 may specifically include the following steps:

[0100] The navigation parameter sequence, which includes position coordinates and heading angle data, is extracted from the signal frame structure. The position coordinates in the navigation parameter sequence are mapped to the actual geospatial coordinate system to form a discrete path point set. The connection relationship between adjacent discrete path points is determined based on the heading angle data. A continuous spatial path curve is generated based on the discrete path point set and the connection relationship. The spatial path curve is smoothed to ensure that the path curvature change conforms to the flight dynamics constraints of the UAV, thus forming the misleading flight path.

[0101] Step 1045: Generate a navigation deception strategy containing a timestamp sequence based on the misleading flight path.

[0102] In the above scheme, the spatiotemporal continuity of navigation signals refers to the coherence of navigation signals in the time dimension and the geometric consistency in the spatial dimension; the navigation decoy strategy is a sequence of instructions used to guide the UAV to a safe area; the position information in the navigation protocol data segment refers to the specific location of semantically ambiguous points in the protocol data structure; the original navigation signal is the standard signal format used by the UAV during normal communication; misleading navigation parameters are parameters containing induced information constructed by imitating the original signal format; dynamic response characteristics are the UAV navigation system's ability to respond to parameter changes; the navigation parameter update rate is the frequency at which the system processes navigation data updates; the trajectory smoothness requirement is the curvature change limit of the UAV's flight path; continuous signal frames are parameter data packets organized in chronological order; the parameter change amplitude is the degree of difference in parameter values ​​between adjacent signal frames; the actual geographic spatial coordinates are latitude and longitude coordinates in the real world; the misleading flight path is a virtual path that guides the UAV to the target area; the navigation parameter sequence is a set of navigation parameters arranged in time; the position coordinates are point data of spatial position; the heading angle data are angle values ​​describing the flight direction; the discrete path point set is a scattered group of spatial points; the connection relationship is the topological connection method between path points; and the spatial path curve is a continuous curve connecting discrete points.

[0103] In this scheme, firstly, step 1041 uses the location information of semantically ambiguous points in the navigation protocol data segment to construct misleading navigation parameters consistent with the original navigation signal format using protocol simulation technology, maintaining compatibility between the parameter format and the original signal. Secondly, step 1042 obtains the dynamic response characteristics of the target UAV navigation system, including system characteristics such as navigation parameter update rate and trajectory smoothness requirements. Then, step 1043 organizes the misleading navigation parameters into a continuous signal frame structure according to the time series, and uses a parameter gradation algorithm to ensure that the parameter change amplitude between adjacent signal frames conforms to the dynamic response characteristics. Next, step 1044 associates the signal frame structure with the actual geospatial coordinates, extracts the navigation parameter sequence from the signal frame structure, maps the position coordinates to the geographic coordinate system to form a discrete path point set, determines the connection relationship between adjacent discrete path points based on the heading angle data, generates a continuous spatial path curve based on the discrete path point set and connection relationship, and smooths the spatial path curve to conform to the UAV flight mechanical constraints, ultimately forming a misleading flight path. Finally, step 1045 generates a navigation deception strategy containing a timestamp sequence based on the misleading flight path.

[0104] Following the previous specific step, in the application scenario of a logistics park in region A, based on the semantic ambiguity points in the latitude and longitude verification area identified in step 103, the system constructs misleading navigation parameters containing offset coordinates. According to the dynamic response characteristics of the C-type UAV, the misleading parameters are organized into continuous signal frames updated every 100 milliseconds. These signal frames are associated with the park's geographical coordinates to generate a flight path guiding the UAV to a designated safe area. This path maintains a smooth curvature and conforms to the UAV's flight characteristics, ultimately forming a complete deception strategy containing a time series.

[0105] This solution ensures the compatibility of the generated deception strategy with the UAV navigation system by maintaining the spatiotemporal continuity of navigation signals. By constructing a misleading flight path with consistent geometric topology, the deception process is made natural, smooth, and difficult to detect, thus improving the success rate and reliability of navigation deception and providing an effective technical means for the safe guidance of UAVs.

[0106] Figure 2 This application provides a schematic diagram of the structure of a multi-source threat strategy generation system within a drone navigation deception data integration and computing system, as shown in the diagram. Figure 2 As shown, the system includes:

[0107] The acquisition module 21 acquires real-time navigation signal data and multi-source threat perception data of the target UAV, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring devices and visual trajectory features from optical sensors.

[0108] The fusion module 22 fuses the geospatial radio frequency fingerprint with the visual trajectory features in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics.

[0109] Module 23 is constructed based on the antigen-antibody reaction mechanism of the biological immune system to build a matching relationship between a dynamic threat situation map and a predefined vulnerability database of UAV navigation protocols, and to identify exploitable semantic ambiguities in specific UAV navigation protocols based on the matching relationship.

[0110] The generation module 24 generates a navigation deception strategy based on the semantic ambiguity points, while maintaining the spatiotemporal continuity of the navigation signal.

[0111] Figure 2 The multi-source threat strategy generation system of the drone navigation deception data integration computing system described above can execute... Figure 1 The implementation principle and technical effects of the multi-source threat strategy generation method for the UAV navigation deception data integration computing system described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit performs its operations in the multi-source threat strategy generation system of the UAV navigation deception data integration computing system described in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0112] In one possible design, Figure 2 The multi-source threat strategy generation system of the drone navigation deception data integration computing system shown in the embodiment can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0113] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0114] The processing component 32 is used for the above Figure 1 The embodiment describes a method for generating multi-source threat strategies in a drone navigation deception data integration and computing system.

[0115] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0116] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0117] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0118] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0119] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0120] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0121] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown illustrates a method for generating multi-source threat strategies in a drone navigation deception data integration computing system.

[0122] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0123] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0124] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for generating multi-source threat strategies in a drone navigation deception data integration and computing system, characterized in that, include: Acquire real-time navigation signal data and multi-source threat perception data of the target UAV, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring equipment and visual trajectory features from optical sensors; The geospatial radio frequency fingerprint and the visual trajectory features are fused in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics. Based on the antigen-antibody reaction mechanism of the biological immune system, a matching relationship is constructed between a dynamic threat situation map and a predefined vulnerability database of UAV navigation protocols. Based on this matching relationship, exploitable semantic ambiguities in the UAV navigation protocols are identified. This includes: using abnormal UAV behavior features contained in the dynamic threat situation map as antigenic representations; using protocol defect patterns stored in the UAV navigation protocol vulnerability database as antibody templates; establishing a matching relationship between the antigenic representations and the antibody templates by simulating the specific binding mechanism of antigens and antibodies in the biological immune system; and identifying exploitable semantic ambiguities in navigation protocol data segments from the matched protocol defect patterns based on the matching relationship. Based on the semantic ambiguity points, a navigation deception strategy is generated under the constraint of maintaining the spatiotemporal continuity of the navigation signal. This includes: constructing misleading navigation parameters consistent with the original navigation signal format based on the location information of the semantic ambiguity points in the navigation protocol data segment; acquiring the dynamic response characteristics of the target UAV navigation system, including navigation parameter update rate and trajectory smoothness requirements; organizing the misleading navigation parameters into a continuous signal frame structure according to a time series, ensuring that the parameter change amplitude between adjacent signal frames conforms to the dynamic response characteristics; associating the signal frame structure with actual geospatial coordinates to construct a misleading flight path with geometric topological consistency; and generating a navigation deception strategy containing a timestamp sequence based on the misleading flight path.

2. The method according to claim 1, characterized in that, Acquire real-time navigation signal data and multi-source threat perception data of the target UAV, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring equipment and visual trajectory features from optical sensors, including: The radio spectrum monitoring equipment pre-deployed at fixed monitoring points receives the navigation frequency band radio frequency signal of the target UAV and extracts the pulse sequence carrying the signal strength distribution pattern from the radio frequency signal; A geospatial radio frequency fingerprint reflecting the spatial location of the target UAV is constructed based on the pulse sequence; The visible light video stream of the target drone is acquired by an optical sensor, and pixel clusters containing the motion contour sequence of the target drone are extracted from the visible light video stream. Visual trajectory features are formed based on the motion trajectory of the pixel clusters. The geospatial radio frequency fingerprint and the visual trajectory features are encapsulated into multi-source threat perception data with a unified timestamp.

3. The method according to claim 1, characterized in that, The geospatial radio frequency fingerprint and the visual trajectory features are fused in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics, including: Establish a spatial mapping relationship between the pulse sequence contained in the geospatial radio frequency fingerprint and the pixel clusters contained in the visual trajectory features; Based on the aforementioned spatial mapping relationship, pulse sequences with a unified timestamp are temporally correlated with pixel clusters to form a spatiotemporally correlated data group; The spatiotemporal correlated data set is overlaid with predefined environmental geographic information to obtain the overlay result; Based on the overlay results, a dynamic threat situation map is generated that includes the real-time location, trajectory, and environmental constraints of the target UAV.

4. The method according to claim 1, characterized in that, By simulating the specific binding mechanism of antigens and antibodies in the biological immune system, a matching relationship is established between the antigen characterization and the antibody template, including: Extract a set of key parameters describing the abnormal behavior of the drone from the antigen characterization to form an antigen feature vector; Extract the set of key attributes describing the protocol defect patterns from the antibody template to form an antibody feature vector; Calculate the configurational matching degree between the antigen feature vector and the antibody feature vector in the vector space; Matching antibody templates are selected based on configurational matching to establish a matching relationship between antigen characterization and antibody templates.

5. The method according to claim 1, characterized in that, Associating the signal frame structure with actual geospatial coordinates to construct a misleading flight path with geometric topological consistency includes: The navigation parameter sequence, which includes position coordinates and heading angle data, is extracted from the signal frame structure. The location coordinates in the navigation parameter sequence are mapped to the actual geospatial coordinate system to form a discrete path point set; The connection relationship between adjacent discrete path points is determined based on the heading angle data; A continuous spatial path curve is generated based on the discrete path point set and connection relationships. The spatial path curve is smoothed to ensure that the path curvature change conforms to the flight dynamics constraints of the UAV, thus forming the misleading flight path.

6. A multi-source threat strategy generation system for an unmanned aerial vehicle (UAV) navigation deception data integration computing system, applied to the multi-source threat strategy generation method for an UAV navigation deception data integration computing system according to any one of claims 1-5, characterized in that, include: The acquisition module acquires real-time navigation signal data and multi-source threat perception data of the target UAV, wherein the multi-source threat perception data includes geospatial radio frequency fingerprints from radio spectrum monitoring equipment and visual trajectory features from optical sensors. The fusion module fuses the geospatial radio frequency fingerprint with the visual trajectory features in the spatiotemporal dimension to generate a dynamic threat situation map with environmental context semantics. The module constructs a matching relationship between a dynamic threat landscape map and a predefined vulnerability database of drone navigation protocols, based on the antigen-antibody reaction mechanism of the biological immune system, and identifies exploitable semantic ambiguities in drone navigation protocols based on the matching relationship. The generation module generates a navigation deception strategy based on the semantic ambiguity points, while maintaining the spatiotemporal continuity of the navigation signal.

7. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the multi-source threat strategy generation method of the UAV navigation deception data integration computing system as described in any one of claims 1 to 5.

8. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements a multi-source threat strategy generation method for a drone navigation deception data integration computing system as described in any one of claims 1 to 5.

Images