A method, device, and storage medium for detecting GNSS satellite signal interference sources in vehicles.

Abstract

The application relates to the technical field of interference source detection, in particular to a vehicle GNSS satellite signal interference source detection method, equipment and a storage medium. The method comprises the following steps: collecting trajectory data of a vehicle; the trajectory data comprises time and position; analyzing the trajectory data to obtain an abnormal cluster of an abnormal phenomenon of aggregation; the abnormal cluster comprises a plurality of abnormal trajectory data; the number of the abnormal cluster is at least one; determining an abnormal area according to the abnormal cluster; counting the number of vehicles with positioning abnormalities in the abnormal area and the total number of vehicles passing through the abnormal area; and if the ratio of the number of vehicles to the total number of vehicles exceeds a set value, marking an interference source according to the abnormal area. The application can effectively identify trajectory abnormalities caused by GNSS interference, realize high-probability detection of the interference source, and provide strong technical support for the safety protection of an intelligent traffic system and electromagnetic environment management.

Description

Technical Field

[0001] This application relates to the field of interference source detection technology, and more specifically, to a method, device, and storage medium for detecting interference sources of GNSS satellite signals from vehicles. Background Technology

[0002] With the rapid development of intelligent vehicles and vehicle-to-everything (V2X) technologies, Global Navigation Satellite Systems (GNSS) have become the fundamental positioning source for core functions such as vehicle navigation, route planning, autonomous driving, and in-vehicle infotainment. However, due to multipath effects caused by urban skyscrapers and canyons, increasingly complex electromagnetic environments, and intentional or unintentional interference (including spoofing), positioning spoofing incidents are on the rise. These interferences can lead to positioning errors and time synchronization failures, directly threatening driving safety and the reliability of location services.

[0003] There is an urgent need to develop a method to identify sources of interference with GNSS satellite signals. Therefore, this application is hereby submitted. Summary of the Invention

[0004] The purpose of this application is to provide a method, device and storage medium for detecting GNSS satellite signal interference sources in vehicles, so as to accurately identify GNSS signal interference sources.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, this application provides a method for detecting GNSS satellite signal interference sources in vehicles, including:

[0007] Collect vehicle trajectory data; the trajectory data includes time and location;

[0008] The trajectory data is analyzed to obtain anomaly clusters exhibiting clustered anomalies; each anomaly cluster includes multiple anomalous trajectory data; the number of anomaly clusters is at least one.

[0009] The abnormal region is determined based on the abnormal clusters;

[0010] The system counts the number of vehicles with abnormal positioning within the abnormal area and the total number of vehicles passing through the abnormal area; if the ratio of the number of vehicles to the total number of vehicles exceeds a set value, the system marks the interference source according to the abnormal area.

[0011] Secondly, this application provides an electronic device, comprising:

[0012] At least one processor, and a memory communicatively connected to at least one of the processors;

[0013] The memory stores instructions that can be executed by at least one of the processors, which are executed by at least one of the processors to enable the at least one of the processors to perform the above-described vehicle GNSS satellite signal interference source detection method.

[0014] Thirdly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the above-described vehicle GNSS satellite signal interference source detection method.

[0015] Compared with the prior art, the beneficial effects of this application are as follows:

[0016] This application proposes a GNSS signal interference source detection method based on vehicle trajectory analysis. When a vehicle's GNSS positioning system suffers signal interference, its trajectory may exhibit sudden deviations, interruptions, or other abnormal phenomena. This application designs and implements a time-space fusion satellite signal interference source detection method by analyzing vehicle trajectory data. The method first processes the vehicle trajectory data, then uses clustering to identify vehicle groups exhibiting clustered anomalies within a specific spatiotemporal range; finally, it uses statistical methods to calculate the proportion of vehicles exhibiting anomalies to vehicles passing through that location, accurately locating the spatial position of potential interference sources.

[0017] This application can effectively identify trajectory anomalies caused by GNSS interference and achieve high-probability detection of interference sources, providing strong technical support for the safety protection of intelligent transportation systems and the management of electromagnetic environment. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific 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 from these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a method for detecting GNSS satellite signal interference sources in vehicles, provided in an embodiment of this application.

[0020] Figure 2 This is a schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0021] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0022] The present application will be further described in detail below with reference to the embodiments.

[0023] Figure 1 This is a flowchart of a vehicle GNSS satellite signal interference source detection method provided in this application embodiment. This method can be executed by a computer program and integrated into an electronic device. This embodiment uses a vehicle GNSS satellite signal interference source detection method integrated into the electronic device to detect the location of the interference source. Figure 1 As shown, this embodiment provides a method for detecting GNSS satellite signal interference sources in vehicles, including the following steps:

[0024] S110. Collect vehicle trajectory data; the trajectory data includes time and location.

[0025] During vehicle operation, trajectory data is collected via vehicle-to-everything (V2X) communication. Trajectory data fields include: vehicle identification number (VIN), time, and location; location can be represented by longitude and latitude.

[0026] Optionally, the original trajectory data was collected at irregular times and contains a lot of noise, so the trajectory data needs to be cleaned, i.e., preprocessed. The preprocessing includes time sorting, removal of stationary points, and downsampling of stacked trajectory data. Specifically:

[0027] Step 1: Sort by time: Extract the time from the trajectory data and sort each trajectory data in ascending order of time to ensure time continuity.

[0028] Step 2: Stationary Point Removal: In the continuous trajectory data, extract continuous trajectory data where the vehicle speed is less than a set stationary value, for example, 0.5 m / s. If the duration of the continuous trajectory data exceeds a set threshold, such as 300 s, the continuous trajectory data is determined to be all stationary points and removed.

[0029] Step 3: Downsampling of Stacked Trajectory Data: When encountering situations such as parking and waiting, a large amount of trajectory data can be stacked, creating noise. Therefore, downsampling is performed on the trajectory data stacking caused by parking and waiting, concentrating the large amount of stacked data into a single trajectory data point, while keeping the sampling rate of the remaining trajectory data unchanged. In specific implementation, the maximum allowable movement distance (in meters) of a vehicle during its stop is set to 10-20 meters (e.g., urban vehicles waiting at traffic lights or picking up / dropping off passengers). The minimum stop time (in seconds) is set to 60 seconds to avoid misjudgment due to short pauses. Based on the trajectory data, continuous trajectory data moving within 20 meters within 60 seconds is used as stacked trajectory data and downsampled.

[0030] Optionally, map matching is performed on the preprocessed trajectory data to obtain the trajectory segments corresponding to each road segment. The map data is publicly available road data downloaded from an open-source map website. This step implements the mapping from trajectory data to map roads.

[0031] Specifically, a map matching algorithm based on a Hidden Markov Model is used to perform map matching on the preprocessed trajectory data to obtain the trajectory segment corresponding to each road segment, including the following steps:

[0032] The first step is to convert the map data into a directed graph; in a directed graph, nodes represent intersections and edges represent road segments.

[0033] Only by converting map data into a graph structure can we subsequently use shortest path algorithms (such as Dijkstra's or A* algorithms) to calculate the road network distance between two points, which is the basis for calculating the state transition probability.

[0034] The second step is to map the preprocessed trajectory data into multiple candidate points on multiple candidate road segments based on the distance threshold.

[0035] For a given trajectory data (i.e., a trajectory point), perform a buffer analysis centered on that point with a certain radius (e.g., 50 meters) to search for all road segments falling into that buffer (the edge between adjacent nodes represents a road segment). These road segments are candidate road segments for the trajectory data.

[0036] From all candidate road segments, those with a Euclidean distance to the trajectory data less than a distance threshold (e.g., 20 meters) are further filtered out. This distance threshold is set based on the error range of typical positioning devices in urban environments (approximately 5-15 meters), with the aim of eliminating obviously impossible candidate road segments and greatly reducing the amount of subsequent calculations.

[0037] For each selected candidate road segment, calculate the vertical projection point from the trajectory point to that candidate road segment. This vertical projection point is the candidate point on that candidate road segment, and it contains information such as longitude, latitude, road segment ID, and location on the road segment.

[0038] The third step is to calculate the transition probability based on the road state transition relationship and select the optimal candidate point; the trajectory data mapped to the optimal candidate point on the same road segment constitutes a trajectory segment.

[0039] The candidate points generated for each trajectory data in the previous step are collected and connected in chronological order to form a "candidate point network". This network is called the road state transition relationship network, where rows represent time (t1, t2, ..., tn) and columns represent the candidate points at each time point. For example, time point t1 corresponds to candidate points L1 and L2 mapped to trajectory point A, and time point t2 corresponds to candidate points L3, L4, and L5 mapped to trajectory point B.

[0040] This candidate point network depicts all possibilities of transitioning from any candidate point at time t to any candidate point at time t+1. It's important to note that in practice, not all transition probabilities between candidate points are greater than 0. For example, a candidate point on a highway is unlikely to directly transition to a candidate point on an unconnected internal road within a residential area. Therefore, the transition probability between these two candidate points is 0. Furthermore, the feasibility of transitioning between two candidate points needs to be determined based on road topology. For instance, if a branch road is not connected to a highway, the transition probability between candidate points on those two roads is also 0.

[0041] For candidate point pairs with non-zero transition probabilities and Calculate from candidate points arrive The shortest path distance (i.e., road network distance) Calculate candidate point pairs and The corresponding original trajectory point and Euclidean distance between .

[0042] Calculate the difference between the shortest path distance and the Euclidean distance. The smaller the difference, the more the path conforms to the vehicle's driving logic, and the higher the transition probability of the candidate point pair. Select the optimal candidate point based on the highest transition probability. In this way, the optimal candidate point mapped to each trajectory data (or trajectory point) is obtained, with one trajectory data point mapping to one optimal candidate point. The trajectory data mapped to the optimal candidate points on the same road segment are considered as a trajectory segment, which includes multiple trajectory data points.

[0043] Optionally, feature extraction is performed on the trajectory data of each trajectory segment to obtain a feature vector for each trajectory data; the feature vector includes the instantaneous rate of change of velocity and the dynamic time warping distance.

[0044] The instantaneous velocity change rate is the change in velocity per unit time, calculated as unit distance / unit time. An instantaneous velocity change rate can be calculated for each trajectory data point.

[0045] Dynamic Time Warping (DTW) is a distance metric used to measure the similarity between two time series. In this embodiment, it measures the distance between multiple trajectory data sequences on a trajectory segment and multiple optimal candidate point sequences mapped to them. The optimal matching path between the two sequences is found through dynamic programming, and the minimum cumulative cost, i.e., the DTW distance, is calculated. All trajectory data on a trajectory segment share a single DTW distance.

[0046] S120. Analyze the trajectory data to obtain anomaly clusters that exhibit clustered anomalies; the anomaly clusters include multiple anomalous trajectory data; the number of the anomaly clusters is at least one.

[0047] This embodiment uses the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm to perform clustering analysis on trajectory data. DBSCAN discovers clusters of arbitrary shapes based on the concept of density and can automatically identify noise points. It does not require pre-specifying the number of clusters; instead, it determines the density relationship between data points based on two key parameters (neighborhood radius and minimum number of points). Specifically, it includes the following steps:

[0048] The first step is to set the neighborhood radius Eps and the minimum number of points MinPts. The input data is the time, position, and feature vector of each trajectory data (i.e., the aforementioned instantaneous velocity change rate and dynamic time warping distance). In this embodiment, the k-distance curve method is used to optimize the parameters Eps and MinPts.

[0049] In the first step, the spatiotemporal distance *d* between each trajectory data point and all other trajectory data points is calculated. Since trajectory data contains both temporal and spatial dimensions, traditional Euclidean distance cannot accurately measure the similarity of trajectory data. Therefore, the spatiotemporal distance *d* is defined as a weighted sum of temporal and spatial distances:

[0050] ;

[0051] in, The distance between two trajectory data points is the Euclidean distance or geodetic distance, in meters. The time difference between two trajectory data points, in seconds. The weights are used to adjust the proportion of time and space in the time-distance relationship.

[0052] Then, from all spatiotemporal distances, the k nearest spatiotemporal distances are selected and averaged to obtain the average distance for each trajectory data; where k is the initial value of the minimum number of points MinPts, for example, 100, meaning that at least 100 trajectory data are clustered together to be considered a cluster. The average distances of all trajectory data are sorted in ascending order, and the average distance corresponding to the inflection point is used as the current neighborhood radius Eps.

[0053] Calculate the harmonic mean F1-score for precision and recall by varying the minimum number of points (e.g., setting MinPts to 50, 75, 100, 125, and 150). The minimum number of points (MinPts) and the corresponding neighborhood radius (Eps) at which the harmonic mean reaches its maximum value are taken as the optimal values.

[0054] Specifically, fix the current minimum number of points (MinPts) and the neighborhood radius (Eps). Iterate through a pre-defined list of candidate MinPts values, for example, [50, 75, 100, 125, 150]. For each MinPts value, run the DBSCAN algorithm and compare the DBSCAN output (i.e., the predicted anomaly cluster) with the known true anomaly clusters, calculating the F1-Score. Select the MinPts value that maximizes the F1-Score as the optimal parameter. After determining the optimal MinPts, sort the average distances of all trajectory data within the cluster in ascending order, and use the average distances corresponding to inflection points / peaks as the optimal neighborhood radius (Eps).

[0055] The second step is to select any unvisited target trajectory data from all trajectory data.

[0056] Initialize the state of all trajectory data to "unvisited", and set the set of abnormal clusters C= The set of noise points N = Mark the target trajectory data as "visited".

[0057] The third step is to calculate the number of neighboring trajectory data within the neighborhood radius that are at a spatiotemporal distance from the target trajectory data.

[0058] Calculate the spatiotemporal distance between the target trajectory data and all other trajectory data, and filter the trajectory data whose spatiotemporal distance is within Eps, which are called neighborhood trajectory data. Count the number of neighborhood trajectory data, that is, the number of trajectory points in the neighborhood of the target trajectory data.

[0059] Step 4: Determine whether the number of neighborhood trajectory data is greater than or equal to the minimum number of points MinPts, and whether the feature vector of the target trajectory data satisfies at least one anomaly detection condition. If yes, proceed to Step 5; otherwise, if the number of neighborhood trajectory data is less than the minimum number of points, or the feature vector of the target trajectory data does not satisfy any anomaly detection condition, proceed to Step 6.

[0060] If the instantaneous rate of change of speed is greater than a set threshold, such as 120 km / h, the anomaly detection condition is met. If the dynamic time warp distance is greater than a set value, such as 100 m, the anomaly detection condition is met.

[0061] Step 5: Using the target trajectory data as the core point, generate a new anomaly cluster; traverse all neighboring trajectory data, and add neighboring trajectory data that meets at least one anomaly judgment condition to the new anomaly cluster to expand the cluster.

[0062] Step 6: If the number of neighborhood trajectory data is less than the minimum number of points MinPts, or if the feature vector of the target trajectory data does not meet any anomaly judgment condition, then the target trajectory data is added to the noise point set.

[0063] Return to step two, select any unvisited target trajectory data from all trajectory data, until all trajectory data has been visited, resulting in at least one anomaly cluster and a set of noise points.

[0064] Through the above steps, spatiotemporally clustered anomalous clusters are identified from the original trajectory data, and each anomalous cluster corresponds to a potential anomalous region.

[0065] S130. Determine the abnormal region based on the abnormal cluster.

[0066] Based on the above description, the anomaly cluster comprises multiple trajectory data. First, the center point of each anomaly cluster is determined, for example, by averaging the positions of all trajectory data within an anomaly cluster. A square region with a set side length (e.g., 300 meters) is then drawn centered on the center point to obtain the anomaly region.

[0067] S140. Count the number of vehicles with abnormal positioning in the abnormal area and the total number of vehicles passing through the abnormal area; if the ratio of the number of vehicles to the total number of vehicles exceeds a set value, mark the interference source according to the abnormal area.

[0068] The statistical period can be one day or one week; this embodiment does not specify a time limit. Each abnormal area needs to be statistically analyzed separately, and it needs to be determined whether to mark it as an interference source.

[0069] Within the statistical period, the presence of a vehicle within an abnormal area is determined by whether its trajectory data falls within that area. Based on the above description, a feature vector is calculated for each data point. If any feature vector satisfies the anomaly detection criteria, and the abnormal trajectory data falls within an abnormal area, the number of vehicles with abnormal positioning within that area is incremented by 1. The number of vehicles within an abnormal area is divided by the total number of vehicles to obtain the ratio. If the ratio exceeds 20%, an interference source is considered to exist within the abnormal area, and the location of the abnormal area is marked on the map, thus locating the interference source.

[0070] In summary, this application proposes a GNSS signal interference source detection method based on vehicle trajectory analysis. When a vehicle's GNSS positioning system suffers signal interference, its trajectory will exhibit abrupt deviations, interruptions, and other abnormal phenomena. This application designs and implements a time-space fusion satellite signal interference source detection method by analyzing vehicle trajectory data. This method first processes the vehicle trajectory data, then uses clustering to identify vehicle groups exhibiting clustered anomalies within a specific spatiotemporal range; finally, it calculates the proportion of vehicles exhibiting anomalies to vehicles passing through that location using statistical methods, accurately locating the spatial position of potential interference sources.

[0071] This application can effectively identify trajectory anomalies caused by GNSS interference and achieve high-probability detection of interference sources, providing strong technical support for the safety protection of intelligent transportation systems and the management of electromagnetic environment.

[0072] like Figure 2 As shown, this embodiment provides an electronic device, including:

[0073] At least one processor; and

[0074] A memory that is communicatively connected to at least one processor; wherein,

[0075] The memory stores instructions executable by at least one processor, which, when executed, enables the processor to perform the method described above. Since at least one processor in this electronic device is capable of performing the method, it possesses at least the same advantages as the method described above.

[0076] Optionally, the electronic device also includes interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The components are interconnected using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processor can process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to the interface). In other embodiments, multiple processors can be used with multiple memories, and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple electronic devices (e.g., as a server array, a group of blade servers, or a multiprocessor system) can be connected, each providing some of the necessary operations. Figure 2 Take processor 301 as an example.

[0077] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the vehicle GNSS satellite signal interference source detection method in this embodiment. The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 302, thereby realizing the aforementioned vehicle GNSS satellite signal interference source detection method.

[0078] The memory 302 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on terminal usage. Furthermore, the memory 302 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 302 may further include memory remotely located relative to the processor 301, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0079] The electronic device may further include an input device 303 and an output device 304. The processor 301, memory 302, input device 303, and output device 304 can be connected via a bus or other means. Figure 2 Taking the example of a connection between China and Israel via a bus.

[0080] Input device 303 can receive input digital or character information, and output device 304 may include a display device, an auxiliary lighting device (e.g., an LED), and a haptic feedback device (e.g., a vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touchscreen.

[0081] This embodiment provides a computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above. The computer instructions on this computer-readable storage medium, used to cause a computer to perform the methods described above, thus have at least the same advantages as the methods described above.

[0082] The medium in this application may be any combination of one or more computer-readable media. The medium may be a computer-readable signal medium or a computer-readable storage medium. The medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, the medium may be any tangible medium containing or storing a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0083] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0084] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF (Radio Frequency), or any suitable combination thereof.

[0085] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0086] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means, such as coaxial cable, optical fiber, digital subscriber line (DSL), or wireless means, such as infrared, wireless, microwave, etc. The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium, or a semiconductor medium, etc. It is worth noting that the computer-readable storage medium mentioned in the embodiments of this application can be a non-volatile storage medium, in other words, it can be a non-transient storage medium.

[0087] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0088] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method of detecting a GNSS satellite signal jammer source for a vehicle, characterized in that, The method is used for detecting the position of the interference source; When the GNSS positioning system of a vehicle is interfered, the vehicle trajectory will present abnormal phenomena of sudden deviation and interruption; The method comprises: In the process of vehicle driving, trajectory data of the vehicle is collected through the Internet of Vehicles; the trajectory data comprises time and position; The trajectory data is analyzed to obtain an abnormal cluster presenting an abnormal phenomenon of aggregation; the abnormal cluster comprises a plurality of abnormal trajectory data; the number of the abnormal cluster is at least one; if the instantaneous speed change rate of the trajectory data is greater than a set threshold, the abnormal determination condition is met; if the dynamic time warping distance of the trajectory data is greater than a set value, the abnormal determination condition is met; An abnormal area is determined according to the abnormal cluster; The number of vehicles presenting positioning abnormality in the abnormal area and the total number of vehicles passing through the abnormal area are counted; if the ratio of the number of vehicles to the total number of vehicles exceeds a set value, the interference source is marked according to the abnormal area.

2. The vehicle GNSS satellite signal jammer detection method according to claim 1, characterized in that, Before the trajectory data is analyzed to obtain the abnormal cluster presenting the abnormal phenomenon of aggregation, the method further comprises: The trajectory data is preprocessed; the preprocessing comprises time sorting, stationary point elimination and down-sampling of stacked trajectory data; The preprocessed trajectory data is subjected to map matching to obtain trajectory segments corresponding to each road section; Feature extraction is performed on the trajectory data on each trajectory segment to obtain a feature vector of each trajectory data; the feature vector comprises an instantaneous speed change rate and a dynamic time warping distance.

3. The vehicle GNSS satellite signal jammer detection method of claim 2, wherein, The preprocessed trajectory data is subjected to map matching to obtain trajectory segments corresponding to each road section, comprising: The preprocessed trajectory data is subjected to map matching by using a map matching algorithm based on a hidden Markov model to obtain trajectory segments corresponding to each road section.

4. The vehicle GNSS satellite signal jammer detection method according to claim 3, characterized in that, The preprocessed trajectory data is subjected to map matching by using a map matching algorithm based on a hidden Markov model to obtain trajectory segments corresponding to each road section, comprising: The map data is converted into a directed graph; the nodes in the directed graph represent intersections, and the edges represent road sections; The preprocessed trajectory data is mapped into a plurality of candidate points on a plurality of candidate road sections according to a distance threshold; The transition probability is calculated according to the road state transition relationship, and the optimal candidate point is selected; the trajectory data mapped into the optimal candidate point on the same road section constitutes a trajectory segment.

5. The vehicle GNSS satellite signal jammer detection method of claim 2, wherein, The trajectory data is analyzed to obtain the abnormal cluster presenting the abnormal phenomenon of aggregation, comprising: A neighborhood radius and a minimum point number are set, and the input data is the time, position and feature vector of each trajectory data; Any unvisited target trajectory data is selected from all the trajectory data; The number of neighborhood trajectory data with a spatio-temporal distance within the neighborhood radius from the target trajectory data is calculated; If the number of neighborhood trajectory data is greater than or equal to the minimum point number, and the feature vector of the target trajectory data meets at least one abnormal determination condition, the target trajectory data is taken as a core point to generate a new abnormal cluster; All the neighborhood trajectory data is traversed, and the neighborhood trajectory data meeting at least one abnormal determination condition is also added to the new abnormal cluster. If the number of the neighborhood trajectory data is less than the minimum point number, or the feature vector of the target trajectory data does not satisfy any abnormality judgment condition, the target trajectory data is added to the noise point set; Returning to select any unvisited target trajectory data from all the trajectory data until all the trajectory data are visited, and obtaining at least one abnormal cluster.

6. The vehicle GNSS satellite signal jammer detection method according to claim 5, characterized in that, Setting a neighborhood radius and a minimum point number, including: Calculating a space-time distance of each trajectory data from all the other trajectory data, the space-time distance being a weighted sum of a time distance and a space distance; From all the space-time distances, selecting k nearest space-time distances and averaging to obtain an average distance of each trajectory data; the k being an initial value of the minimum point number; Sorting the average distances of all the trajectory data in ascending order, and taking an average distance corresponding to an inflection point as a current neighborhood radius; By changing the minimum point number, calculating a harmonic mean of the precision and the recall rate; Taking the minimum point number and the corresponding neighborhood radius when the harmonic mean reaches a maximum value as optimal values.

7. The vehicle GNSS satellite signal jammer detection method of claim 1, wherein, Determining an abnormal area according to the abnormal cluster, including: Determining a center point position of each abnormal cluster; Drawing a square area with a set side length with the center point position as a center to obtain the abnormal area.

8. An electronic device, comprising: Including: At least one processor, and a memory connected in communication with the at least one processor; Wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the vehicle GNSS satellite signal interference source detection method in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The medium stores computer instructions, and the computer instructions are used to enable a computer to perform the vehicle GNSS satellite signal interference source detection method in any one of claims 1-7.

Images