Real-time satellite visibility spoofing detection method and system based on satellite trajectory estimation

Abstract

This invention relates to the field of satellite trajectory calculation technology and discloses a real-time satellite visibility spoofing detection method based on satellite trajectory prediction. The method includes: calculating a list of visible satellites at the receiver's geographical location and current time using a satellite trajectory model; detecting and analyzing received satellite signals to determine whether they belong to the list of visible satellites; and analyzing and determining the authenticity of the received satellite signals based on historical satellite data and the analyzed satellite signals. By employing advanced signal analysis techniques and machine learning algorithms, this invention can quickly identify and distinguish between normal and spoofed signals, performing particularly well in complex and dynamic environments. Furthermore, the detection method based on real-time satellite trajectory prediction enables the system to respond promptly to potential threats, improving overall security.

Description

Technical Field

[0001] This invention relates to the field of satellite trajectory calculation technology, specifically to a real-time satellite visibility deception detection method and system based on satellite trajectory prediction. Background Technology

[0002] In recent years, Global Navigation Satellite System (GNSS) technology has developed rapidly, becoming an indispensable infrastructure in modern society. With the successive deployment of systems such as GPS, BeiDou, and GLONASS, satellite navigation has demonstrated enormous application potential in transportation, agriculture, military, and personal positioning. At the same time, continuous advancements in related technologies have made the acquisition, processing, and application of satellite signals increasingly precise and efficient. In particular, the development of high-precision positioning technology has provided strong support for cutting-edge applications such as autonomous driving and intelligent transportation systems. However, with the widespread adoption of satellite navigation systems, security and reliability issues have gradually emerged, especially the risks of spoofing and deception.

[0003] While existing methods for detecting spoofing signals have improved the security of satellite navigation systems to some extent, they still have many shortcomings. First, existing methods largely rely on traditional signal analysis techniques, lacking adaptability to real-time dynamic environments, resulting in poor detection performance in complex conditions. Furthermore, many detection algorithms have limited ability to extract signal features, failing to effectively distinguish between normal and spoofed signals, especially under conditions of poor signal quality. In addition, existing technologies suffer from low computational efficiency when processing large amounts of real-time data, making it difficult to meet high real-time requirements. These shortcomings render existing technologies inadequate for handling modern complex application scenarios. Therefore, achieving more efficient and accurate real-time satellite signal spoofing detection has become a pressing issue that needs to be addressed. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is the accuracy and real-time performance of spoofing signal detection in satellite navigation systems. Existing technologies struggle to effectively identify spoofing signals in complex environments and lack sufficient signal feature extraction capabilities, failing to meet the demands of modern high-precision positioning applications.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a real-time satellite visibility deception detection method based on satellite trajectory prediction, comprising:

[0007] Based on the receiver's geographical location and current time, a list of visible satellites at that location and current time is calculated using a satellite trajectory model;

[0008] Detect and analyze received satellite signals to determine whether they belong to the list of visible satellites;

[0009] Based on historical satellite data and analyzed satellite signals, we determine whether the received satellite signals are authentic.

[0010] As a preferred embodiment of the real-time satellite visibility deception detection method based on satellite trajectory prediction described in this invention, the geographical location includes the longitude, latitude, and altitude of the receiver's location.

[0011] The current time includes the receiver's current Coordinated Universal Time and epoch information.

[0012] As a preferred embodiment of the real-time satellite visibility deception detection method based on satellite trajectory prediction described in this invention, the calculation of the visible satellite list includes: accessing the latest satellite almanac data; calculating the position of each satellite at a given time using Kepler's laws; and adjusting the propagation path of the satellite signal using an atmospheric refraction model to ensure calculation accuracy.

[0013] Calculate the elevation and azimuth angles of each satellite relative to the receiver, determine whether the satellite is within the field of view, and record all satellites that meet the conditions into the visible satellite list;

[0014] The satellite almanac data includes the orbital parameters and timestamp information for each satellite.

[0015] As a preferred embodiment of the real-time satellite visibility deception detection method based on satellite trajectory prediction described in this invention, the detection and analysis of received satellite signals includes: converting the received satellite signals into digital signals, demodulating the digital signals, extracting key features of the digital signals through fast Fourier transform, and marking the digital signals as valid signals if the key features of the digital signals match the features of visible satellites.

[0016] If the signal is not in the list of visible satellites, mark it as a suspicious signal;

[0017] The key features include frequency features, intensity features, and phase features.

[0018] As a preferred embodiment of the real-time satellite visibility deception detection method based on satellite trajectory prediction described in this invention, the historical satellite data includes key features of normal signals and key features of known deception signals.

[0019] Analyzing and determining whether the received satellite signal is genuine involves using the key features of normal signals and the key features of known spoofing signals to construct key feature vectors for normal signals and key feature vectors for known spoofing signals, respectively, and then training a prediction model.

[0020] The prediction model combines the outputs of support vector machines and random forests, and obtains the final prediction result through weighted voting, as expressed by the formula:

[0021] Output of the SVM model:

[0022] ,

[0023] in, This represents the key feature vector of the input. Represents the prediction function of the SVM model;

[0024] Output of the random forest model:

[0025] ,

[0026] in, This represents the key feature vector of the input. This represents the prediction function of the random forest model;

[0027] ,

[0028] ,

[0029] in, This indicates the final prediction result. This represents the predicted output of the SVM model. This represents the predicted output of the random forest model; Represents the weights of the SVM model. The weights represent the weights of the random forest model. ; The entropy of the input feature vector is represented by... Representation of features The probability distribution, Indicates the total number of features; Represents the normalization function; The parameter representing the adjustment of information entropy.

[0030] As a preferred embodiment of the real-time satellite visibility deception detection method based on satellite trajectory prediction described in this invention, the analysis and judgment of whether the received satellite signal is genuine further includes converting the prediction result into a probability of authenticity, expressed by the following formula:

[0031] ,

[0032] in, This indicates the final prediction result. This indicates that the parameters are being adjusted. Indicates parameter adjustment;

[0033] Set a probability threshold ,when If so, then the satellite signal is a genuine signal;

[0034] when If so, the satellite signal is a deceptive signal.

[0035] As a preferred embodiment of the real-time satellite visibility deception detection method based on satellite trajectory prediction described in this invention, the key features of the digital signal are used to construct a key feature vector, the key feature vector is input into the prediction model for analysis, the prediction model outputs the probability of the authenticity of the satellite signal, and the authenticity of the satellite signal is determined according to the set probability threshold.

[0036] As a preferred embodiment of the real-time satellite visibility deception detection method based on satellite trajectory prediction described in this invention, the geographical location and time module acquires the geographical location and current time of the receiver;

[0037] The satellite trajectory calculation module calculates a list of visible satellites at a specific location and time.

[0038] Signal receiving and analysis module: detects and analyzes received satellite signals to determine whether they belong to the list of visible satellites;

[0039] The feature extraction and judgment module extracts key features of the signal and constructs feature vectors.

[0040] The deception signal detection module analyzes the authenticity of received signals based on historical data and machine learning models.

[0041] A computer device includes: a memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the method described in any one of the present invention.

[0042] A computer-readable storage medium having a computer program stored thereon, characterized in that: when the computer program is executed by a processor, it implements the steps of the method described in any one of the present invention.

[0043] The beneficial effects of this invention are as follows: The real-time satellite visibility spoofing detection method based on satellite trajectory prediction provided by this invention, by employing advanced signal analysis technology and machine learning algorithms, can quickly identify and distinguish between normal signals and spoofed signals, especially performing excellently in complex and dynamic environments. Furthermore, the detection method based on real-time satellite trajectory prediction enables the system to respond promptly to potential threats, improving overall security. This innovation not only enhances the reliability of satellite navigation but also provides a solid technical foundation for applications in fields such as autonomous driving and intelligent transportation, thereby promoting the development and security of related industries. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 The first embodiment of the present invention provides an overall flowchart of a real-time satellite visibility deception detection method based on satellite trajectory prediction. Detailed Implementation

[0046] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0047] Example 1, referring to Figure 1 As an embodiment of the present invention, a real-time satellite visibility deception detection method based on satellite trajectory prediction is provided, comprising:

[0048] S1: Based on the receiver's geographical location and current time, calculate the list of visible satellites at that location and current time using a satellite trajectory model.

[0049] Geographic location includes the longitude, latitude, and altitude of the receiver's location.

[0050] The current time includes the receiver's current Coordinated Universal Time and epoch information.

[0051] The calculation of the visible satellite list includes accessing the latest satellite almanac data; using Kepler's laws to calculate the position of each satellite at a given time; and employing an atmospheric refraction model to adjust the propagation path of satellite signals to ensure calculation accuracy.

[0052] Furthermore, this ensures that the satellite navigation system maintains high-precision positioning in complex environments, reduces navigation errors caused by signal interference or loss, and enhances user safety and trust.

[0053] S2: Detect and analyze the received satellite signals to determine whether they belong to the list of visible satellites.

[0054] Calculate the elevation and azimuth angles of each satellite relative to the receiver, determine whether the satellite is within the field of view, and record all satellites that meet the conditions into the visible satellite list.

[0055] Satellite almanac data includes the orbital parameters and timestamp information for each satellite.

[0056] Furthermore, by introducing efficient signal feature extraction technology and combining it with machine learning models for real-time analysis, it is possible to quickly distinguish between normal signals and deceptive signals, thereby improving the accuracy of detection.

[0057] S3: Based on historical satellite data and analyzed satellite signals, analyze and determine whether the received satellite signals are genuine.

[0058] The detection and analysis of received satellite signals includes converting the received satellite signals into digital signals, demodulating the digital signals, extracting key features of the digital signals through fast Fourier transform, and marking the digital signals as valid signals if the key features of the digital signals match the characteristics of visible satellites.

[0059] If the signal is not in the list of visible satellites, mark it as a suspicious signal.

[0060] The key features include frequency features, intensity features, and phase features.

[0061] The historical satellite data includes key features of normal signals and key features of known spoofing signals.

[0062] Analyzing and determining whether the received satellite signal is genuine involves using key features of normal signals and key features of known spoofing signals to construct key feature vectors for normal signals and key feature vectors for known spoofing signals, respectively, and then training a prediction model.

[0063] The prediction model combines the outputs of support vector machines and random forests, and obtains the final prediction result through weighted voting, as expressed by the formula:

[0064] Output of the SVM model:

[0065] ,

[0066] in, This represents the key feature vector of the input. This represents the prediction function of the SVM model.

[0067] Output of the random forest model:

[0068] ,

[0069] in, This represents the key feature vector of the input. This represents the prediction function of the random forest model.

[0070] ,

[0071] ,

[0072] in, This indicates the final prediction result. This represents the predicted output of the SVM model. This represents the predicted output of the random forest model; Represents the weights of the SVM model. The weights represent the weights of the random forest model. ; The entropy of the input feature vector is represented by... Representation of features The probability distribution, Indicates the total number of features; Represents the normalization function; The parameter representing the adjustment of information entropy.

[0073] Analyzing and determining whether a received satellite signal is genuine also includes converting the prediction result into a probability of authenticity, expressed by the formula:

[0074] ,

[0075] in, This indicates the final prediction result. This indicates that the parameters are being adjusted. This indicates that the parameters are being adjusted.

[0076] Set a probability threshold ,when If so, then the satellite signal is a genuine signal.

[0077] when If so, the satellite signal is a deceptive signal.

[0078] probability threshold It is dynamic, and the formula is expressed as:

[0079] ,

[0080] in, Indicates a dynamic threshold. The entropy of the input feature vector is represented by... This indicates the final prediction result. Indicates weight, Represents the exponential coefficient. This indicates an adjustment parameter that controls the shape of the Sigmoid function. Indicates the amplitude coefficient. and This indicates the order of the polynomial and the product term.

[0081] The range of its value is from 0 to positive infinity.

[0082] The key features of the digital signal are used to construct a key feature vector. This key feature vector is then input into a prediction model for analysis. The prediction model outputs the probability of the satellite signal's authenticity and determines whether the satellite signal is genuine based on a set probability threshold.

[0083] Furthermore, by combining machine learning algorithms such as support vector machines and random forests, the ability to judge the authenticity of satellite signals has been improved, enabling it to adapt and learn in a constantly changing environment, thereby optimizing the recognition process.

[0084] Example 2, an embodiment of the present invention, provides a real-time satellite visibility deception detection system based on satellite trajectory prediction, comprising:

[0085] The geolocation and time module obtains the receiver's geolocation and current time.

[0086] The satellite trajectory calculation module calculates a list of visible satellites at a specific location and time.

[0087] Signal reception and analysis module: detects and analyzes received satellite signals to determine whether they belong to the list of visible satellites.

[0088] The feature extraction and judgment module extracts key features of the signal and constructs feature vectors.

[0089] The deception signal detection module analyzes the authenticity of received signals based on historical data and machine learning models.

[0090] Example 3, an embodiment of the present invention, differs from the previous two embodiments in that:

[0091] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0092] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0093] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0094] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0095] Example 4 selected four typical geographical environments for experiments, including urban, rural, mountainous, and water environments, to simulate real-world application scenarios of varying complexity. In each environment, normal satellite signals and spoofing signals of different intensities were simulated to evaluate the detection performance of the method under different conditions.

[0096] A high-precision GNSS receiver is configured to ensure stable reception of satellite signals in various environments. The receiver's geographical location parameters (longitude, latitude, and altitude) and current time (Coordinated Universal Time and epoch information) are accurately recorded for subsequent steps using satellite trajectory models to calculate the list of visible satellites. Utilizing the latest satellite ephemeris data, and employing Kepler's laws and atmospheric refraction models, the position of each satellite at a given time is precisely calculated, and its elevation and azimuth angles relative to the receiver are determined, thereby generating the list of visible satellites.

[0097] In the signal detection and analysis phase, the received satellite signals are converted into digital signals, and frequency, intensity, and phase features are extracted using Fast Fourier Transform (FFT). These key features are constructed into feature vectors and input into Support Vector Machine (SVM) and Random Forest (RF) models for classification prediction. A weighted voting mechanism combines the outputs of SVM and RF to generate the final prediction result. A dynamic threshold formula is used to adjust the threshold based on the entropy of the input feature vector, and the Sigmoid function converts the prediction result into a probability of truth.

[0098] During the experiment, different signal strengths were set, and the transmission power was adjusted to simulate normal and spoofed signals of varying intensities. Each signal type was repeatedly received and analyzed 20 times in different environments to ensure data reliability and statistical significance. All experimental data were systematically recorded in Table 1 for subsequent analysis and comparison. The experimental results are shown in Table 1.

[0099] Table 1 Experimental Data

[0100] ,

[0101] Based on the analysis of the experimental data above, Table 1 shows the recognition rate performance of traditional spoofing signal detection methods and the method of this invention under different signal strength conditions in four different geographical environments. The data clearly shows that the method of this invention is significantly superior to existing methods in all environments and signal types, specifically in terms of improved recognition rates of both real and spoofing signals.

[0102] First, in urban environments, traditional methods achieve a 92% recognition rate for normal signals, while the method of this invention improves this to 98%, demonstrating higher accuracy. This improvement is mainly attributed to the dual-model fusion mechanism combining SVM and random forest, as well as the introduction of dynamic thresholds, which effectively reduces false recognition and false negative rates. For spoofing signals, traditional methods achieve recognition rates of 88% and 90%, while the method of this invention improves these rates to 95% and 97%, significantly enhancing the ability to detect counterfeit signals.

[0103] In rural environments, the traditional method achieved a normal signal recognition rate of 89% and a spoofing signal recognition rate of 85% and 88%, respectively, while the method of this invention improved these rates to 95% and 93%, respectively. This demonstrates that the method of this invention maintains high detection performance even under conditions of low signal quality and minimal environmental interference. Data from mountainous and aquatic environments further validated the robustness of the method of this invention. In mountainous areas, the traditional method achieved recognition rates of 85% for normal signals and 80% for spoofing signals, while the method of this invention improved these rates to 90% and 92%. In aquatic environments, the traditional method achieved recognition rates of 90% and 87%, while the method of this invention reached 97% and 96%, respectively. These results indicate that the method of this invention provides more reliable detection results regardless of whether the signal strength is low or the environmental complexity is high.

[0104] Data analysis further reveals that traditional methods suffer from high false positive and false negative rates when processing deceptive signals, especially under conditions of low signal strength or significant environmental interference, where detection performance degrades significantly. In contrast, the method of this invention, through dynamic thresholding and multi-model fusion, not only improves the recognition rate but also effectively reduces the false positive and false negative rates, enhancing the overall reliability and security of the system.

[0105] Furthermore, by introducing information entropy as an adjustment factor for the dynamic threshold, the method of this invention can adaptively adjust the detection sensitivity according to the complexity and uncertainty of the input features. This innovative design enables the method of this invention to maintain efficient and accurate detection performance in different application scenarios, significantly outperforming traditional methods that rely on fixed thresholds and single classification models.

[0106] In this embodiment, the Support Vector Machine (SVM) and Random Forest (RF) models, after training, significantly improve the accuracy of signal authenticity judgment by combining a weighted voting mechanism and dynamic threshold adjustment. Specifically, when the SVM model is used alone, the recognition rate reaches 92% and 90% in urban and aquatic environments, respectively; when the RF model is used alone, the recognition rate is 88% and 87%, respectively. However, after combining the dual-model fusion and dynamic threshold mechanism of this invention, the recognition rates are increased to 98% and 97%, respectively, showing a significant performance improvement.

[0107] Furthermore, the algorithm's operational efficiency in practical applications has been optimized. Through parallel computing and optimized algorithm structure, the method of this invention can quickly respond to and accurately determine the authenticity of satellite signals in application scenarios with high real-time requirements, such as autonomous driving and intelligent transportation systems, ensuring the high reliability and security of the system. In contrast, traditional methods, due to their low computational efficiency in complex environments, struggle to meet real-time requirements, limiting their application potential in highly dynamic applications.

[0108] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A real-time satellite visibility deception detection method based on satellite trajectory prediction, characterized in that, include: Based on the receiver's geographical location and current time, a list of visible satellites at that location and current time is calculated using a satellite trajectory model; Calculating the list of visible satellites includes accessing the latest satellite almanac data; The position of each satellite at a given time is calculated using Kepler's laws. An atmospheric refraction model is used to adjust the propagation path of the satellite signals to ensure calculation accuracy. Calculate the elevation and azimuth angles of each satellite relative to the receiver, determine whether the satellite is within the field of view, and record all satellites that meet the conditions into the visible satellite list; The satellite almanac data includes the orbital parameters and timestamp information for each satellite; Detect and analyze received satellite signals to determine whether they belong to the list of visible satellites; The detection and analysis of received satellite signals includes converting the received satellite signals into digital signals, demodulating the digital signals, extracting key features of the digital signals through fast Fourier transform, and marking the digital signals as valid signals if the key features of the digital signals match the characteristics of visible satellites. If the signal is not in the list of visible satellites, mark it as a suspicious signal; The key features include frequency features, intensity features, and phase features; Based on historical satellite data and analyzed satellite signals, we analyze and determine whether the received satellite signals are genuine. The historical satellite data includes key features of normal signals and key features of known spoofing signals; Analyzing and determining whether the received satellite signal is genuine involves using the key features of normal signals and the key features of known spoofing signals to construct key feature vectors for normal signals and key feature vectors for known spoofing signals, respectively, and then training a prediction model. The prediction model combines the outputs of support vector machines and random forests, and obtains the final prediction result through weighted voting, as expressed by the formula: Output of the SVM model: ； Where x represents the key feature vector of the input. This represents the prediction function of the SVM model; Output of the random forest model: ； Where x represents the key feature vector of the input. This represents the prediction function of the random forest model; ； in, This indicates the final prediction result. This represents the predicted output of the SVM model. This represents the predicted output of the random forest model; Represents the weights of the SVM model. The weights of the random forest model are represented. ; The entropy of the input feature vector is represented by... This represents the probability distribution of the features, where N represents the total number of features; Represents the normalization function; The parameter representing the adjustment of information entropy; The key features of the digital signal are used to construct a key feature vector. This key feature vector is then input into a prediction model for analysis. The prediction model outputs the probability of the satellite signal's authenticity and determines whether the satellite signal is genuine based on a set probability threshold.

2. The real-time satellite visibility deception detection method based on satellite trajectory prediction as described in claim 1, characterized in that: The geographical location includes the longitude, latitude, and altitude of the receiver's location; The current time includes the receiver's current Coordinated Universal Time and epoch information.

3. The real-time satellite visibility deception detection method based on satellite trajectory prediction as described in claim 2, characterized in that: Analyzing and determining whether a received satellite signal is genuine also includes converting the prediction result into a probability of authenticity, expressed by the formula: ； in, This indicates the final prediction result. This indicates that the parameters are being adjusted. Indicates parameter adjustment; Set a probability threshold ,when If so, then the satellite signal is a genuine signal; then If so, then the satellite signal is a deceptive signal.

4. A real-time satellite visibility deception detection system based on satellite trajectory prediction, employing the real-time satellite visibility deception detection method based on satellite trajectory prediction as described in any one of claims 1 to 3, characterized in that: The geolocation and time module obtains the receiver's geolocation and current time; The satellite trajectory calculation module calculates a list of visible satellites at a specific location and time. Signal receiving and analysis module: detects and analyzes received satellite signals to determine whether they belong to the list of visible satellites; The feature extraction and judgment module extracts key features of the signal and constructs feature vectors. The deception signal detection module analyzes the authenticity of received signals based on historical data and machine learning models.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the real-time satellite visibility deception detection method based on satellite trajectory prediction as described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the real-time satellite visibility deception detection method based on satellite trajectory prediction as described in any one of claims 1 to 3.

Images