Intelligent verification method and system for vehicle-mounted satellite positioning device

Abstract

The invention relates to the technical field of traffic intelligent management, in particular to an intelligent verification method and system for a vehicle-mounted satellite positioning device, and the method comprises the following steps: constructing a dynamic signal fitting model of the vehicle-mounted satellite positioning device; performing cooperative verification on the vehicle-mounted satellite positioning device according to the dynamic signal fitting model to obtain a preliminary verification result; constructing a verification chain and an evidence storage chain to obtain a credible verification result of the preliminary verification result; constructing a cloud digital twinborn model based on the credible verification result to obtain a digital twinborn body of the vehicle-mounted satellite positioning device; and establishing a detection and verification platform of the vehicle-mounted satellite positioning device, and detecting the digital twin to obtain an intelligent verification result, thereby realizing intelligent verification of the vehicle-mounted satellite positioning device. According to the invention, an intelligent verification full-process closed loop of the vehicle-mounted satellite positioning device is constructed, the verification efficiency and the device reliability are significantly improved, and the intelligent level of road transportation safety supervision is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation management, and in particular to an intelligent verification method and system for an in-vehicle satellite positioning device. Background Art

[0002] With the rapid development of intelligent transportation and vehicle networking technologies, in-vehicle satellite positioning devices have become core components for vehicle safety supervision, autonomous driving, and logistics scheduling. However, existing detection technologies still face significant bottlenecks: Firstly, traditional detection methods are mostly limited to module-level single-point testing and lack the ability to simulate dynamic scenarios at the vehicle level. Especially in complex environments such as tunnels and urban canyons, signal attenuation and multipath effects lead to significant positioning errors, and there are deviations between the detection results and the actual working conditions. Secondly, the detection process highly depends on manual operations and static standard signal sources, making it difficult to adapt to the synchronous verification requirements of multi-band signals, and the heterogeneity of operator platform interfaces causes low data collection efficiency. Thirdly, the security and credibility of detection data are insufficient, lacking a full-link encryption and traceability mechanism, being easily tampered with or lost, and it is difficult to meet the detection and verification requirements.

[0003] In the current technical system, the detection of in-vehicle terminals mostly adopts a serial single-device testing mode, which cannot achieve parallel and efficient detection of multiple devices. The differences in operator platform interface protocols result in the need for multiple manual adaptations of detection data, which is time-consuming and error-prone; the hot and cold data hybrid storage architecture restricts the performance of large-scale historical trajectory backtracking and real-time analysis; in addition, the traceability of detection errors relies on empirical judgment and lacks intelligent diagnosis means, making it impossible to accurately identify hidden faults such as chip aging and antenna offset. Although some solutions introduce analog signal sources, their scenarios are fixed and parameter adjustments are lagging, making it difficult to dynamically simulate real road environments, resulting in low detection coverage and severely restricting the large-scale application and reliability verification of in-vehicle positioning devices.

[0004] In view of this, the present invention constructs a dynamic signal fitting model to achieve verification and detection accuracy in complex environments; combines the verification chain and the evidence storage chain, and constructs a cloud digital twin model and a detection and verification platform for in-vehicle satellite positioning devices, breaks through the problem of data heterogeneity, and ensures that the detection process is efficient, transparent, and compliant with functional safety standards; fills the gaps in parallel detection, adaptive scenario simulation, and data trusted management in the existing technology, and provides technical support for the high-precision positioning and full-life cycle management of intelligent connected vehicles. Summary of the Invention

[0005] Aiming at the defects in the prior art, the present invention provides an intelligent verification method and system for an in-vehicle satellite positioning device.

[0006] To achieve the above object, in a first aspect, the present invention provides an intelligent verification method for an in-vehicle satellite positioning device, and the method includes the following steps: constructing a dynamic signal fitting model of the in-vehicle satellite positioning device by combining multi-modal analog signals and adaptive scenario signals; performing collaborative verification on the in-vehicle satellite positioning device according to the dynamic signal fitting model to obtain a preliminary verification result; constructing a verification chain and an evidence storage chain, and obtaining a credible verification result of the preliminary verification result by combining the verification chain and the evidence storage chain; constructing a cloud digital twin model based on the credible verification result, and obtaining a digital twin of the in-vehicle satellite positioning device according to the cloud digital twin model; establishing a detection and verification platform for the in-vehicle satellite positioning device, and performing detection on the digital twin according to the detection and verification platform to obtain an intelligent verification result, so as to realize the intelligent verification of the in-vehicle satellite positioning device. The present invention improves the positioning accuracy and environmental adaptability through multi-modal signal fusion and dynamic modeling, and the collaborative verification mechanism enhances the comprehensiveness and accuracy of data verification; combining the verification chain and the evidence storage chain ensures the anti-tampering and traceability of the verification result, and constructs a data basis with high credibility; the digital twin realizes the real-time mapping of the device operation state, reducing the physical test cost; the detection and verification platform automatically completes the verification, forming a process closed-loop, significantly improving the verification efficiency and device reliability, and providing full-life-cycle intelligent guarantee for the in-vehicle satellite positioning device.

[0007] Optionally, the constructing a dynamic signal fitting model of the in-vehicle satellite positioning device by combining multi-modal analog signals and adaptive scenario signals includes: performing virtual scenario fitting based on an analog signal generating device to obtain the multi-modal analog signals; constructing a three-dimensional road model, and mapping the physical environment according to the three-dimensional road model to obtain the adaptive scenario signals; dynamically fusing the multi-modal analog signals and the adaptive scenario signals to construct the dynamic signal fitting model. The present invention generates multi-modal signals through an analog signal generating device, virtually reproduces complex electromagnetic environments and extreme scenarios, and breaks through the limitations of physical tests; the three-dimensional road model accurately maps the topological features of the physical environment, combines real-time traffic flow and weather data to generate adaptive scenario signals, enhancing the authenticity of environmental perception; and then constructs a dynamic signal fitting model, realizing the complementarity of virtual data and real data, significantly improving the signal anti-interference ability and multi-source data fusion accuracy of the positioning device in dynamic scenarios, providing a simulation environment basis for subsequent verification, and reducing the risks and costs of real vehicle tests.

[0008] Optionally, the collaborative verification of the vehicle-mounted satellite positioning device according to the dynamic signal fitting model to obtain a preliminary verification result includes: obtaining a dynamic signal through the dynamic signal fitting model, and performing data fusion on the dynamic signal and the original data of the vehicle-mounted satellite positioning device to obtain a fused signal; performing filtering processing on the fused signal to further obtain a corrected positioning trajectory of the vehicle-mounted satellite positioning device; obtaining a standard value of the dynamic signal, and obtaining an error value of the corrected positioning trajectory in combination with the standard value; setting a dynamic threshold according to the dynamic fitting model, and obtaining a multi-dimensional anomaly detection result of the vehicle-mounted satellite positioning device based on the dynamic threshold; performing collaborative verification by combining the error value and the multi-dimensional anomaly detection result to obtain the preliminary verification result. The present invention generates a high-fidelity dynamic signal through a dynamic signal fitting model, significantly improves the positioning trajectory accuracy after filtering processing by fusing with the original data, and effectively suppresses interference and noise; realizes quantitative evaluation of positioning performance based on standard value error analysis, and the dynamic threshold mechanism can adaptively adjust the anomaly detection sensitivity to cover multi-dimensional fault modes such as electromagnetic interference, signal occlusion, and clock drift; the collaborative verification framework combines error tracing and anomaly diagnosis to form a closed-loop feedback mechanism, providing an accurate device performance baseline for reliable verification.

[0009] Optionally, constructing a verification chain and an evidence preservation chain, and obtaining a reliable verification result of the preliminary verification result by combining the verification chain and the evidence preservation chain includes: obtaining a timing evidence chain, and constructing the verification chain based on the timing evidence chain in combination with distributed verification nodes; establishing a multi-modal data chain, and constructing the evidence preservation chain based on the multi-modal data chain in combination with a privacy protection mechanism; performing cross-verification on the preliminary verification result by combining the verification chain and the evidence preservation chain to obtain the reliable verification result. The present invention constructs a verification chain and an evidence preservation chain through blockchain technology to achieve full-link reliable traceability of the verification process. The verification chain collaborates based on the timing evidence chain and distributed nodes to ensure that the verification logic is transparent and tamper-proof; the evidence preservation chain integrates multi-modal data and a privacy protection mechanism to ensure the complete storage of original data and verification evidence. The cross-verification of the two can automatically compare multi-dimensional verification results, identify data tampering and logical loopholes, form an anti-counterfeiting and auditable closed-loop verification system, and significantly improve the credibility of the preliminary verification result.

[0010] Optionally, the cross-verification of the preliminary verification result by combining the verification chain and the evidence deposit chain to obtain the credible verification result includes: performing pre-verification on the preliminary verification result based on the verification chain to obtain a first verification result; performing evidence deposit verification on the first verification result according to the evidence deposit chain to obtain a second verification result; and performing post-verification on the second verification result based on the verification chain to obtain the credible verification result. The present invention constructs a dual guarantee mechanism; pre-verification uses the distributed consensus mechanism of the verification chain to exclude logical fallacies; evidence deposit chain verification is based on multi-modal data evidence deposit and privacy protection technology to achieve the complete anchoring of original data and operation traces; post-verification forms a closed-loop feedback to eliminate the risk of single-point failure; and the credibility of the preliminary verification result is improved.

[0011] Optionally, constructing a cloud digital twin model based on the credible verification result, and obtaining a digital twin of the vehicle-mounted satellite positioning device according to the cloud digital twin model includes: performing standardization processing and feature extraction on the credible verification result to obtain key features, and constructing a feature correlation spectrum based on the key features; constructing the cloud digital twin model of the vehicle-mounted satellite positioning device according to the feature correlation spectrum; and performing real-time dynamic mapping on the vehicle-mounted satellite positioning device based on the cloud digital twin model to obtain the digital twin. The present invention eliminates data heterogeneity through standardization processing and feature extraction, providing high-precision input for the twin model; the feature correlation spectrum reveals the deep coupling relationship between parameters such as positioning error, signal interference, and hardware status, enabling the cloud digital twin model to have the ability of full-element mapping; the real-time dynamic mapping mechanism can synchronize the state evolution of the device and the twin, reducing the physical test cost.

[0012] Optionally, constructing the cloud digital twin model of the vehicle-mounted satellite positioning device according to the feature correlation spectrum includes: establishing a model hierarchical architecture of the cloud digital twin model, where the model hierarchical architecture includes a physical layer, a signal layer, and a behavior layer; and performing hybrid modeling on the vehicle-mounted satellite positioning device based on the feature correlation spectrum in combination with the model hierarchical architecture to obtain the cloud digital twin model. The present invention realizes the virtual mapping of the vehicle-mounted positioning device through hierarchical hybrid modeling; the hierarchical architecture realizes modular decoupling, facilitating algorithm optimization for specific levels; hybrid modeling takes into account physical constraints and data-driven characteristics, cloud deployment supports elastic expansion, and combined with the feature correlation spectrum to achieve automatic parameter tuning, shortening the verification cycle.

[0013] Optionally, the establishment of the detection and verification platform of the vehicle-mounted satellite positioning device includes: establishing a multi-level platform architecture, the multi-level platform architecture includes a terminal layer, a storage layer, a service layer, an application layer and an interface layer; the detection and verification platform is obtained based on the multi-level platform architecture. The present invention constructs a detection and verification platform architecture for vehicle-mounted satellite positioning devices, and realizes modular management and efficient collaboration through layered design; the terminal layer directly connects to the equipment to ensure the accuracy of data collection; the storage layer provides safe and reliable data management; the service layer encapsulates the detection algorithm and data analysis capabilities; the application layer realizes human-computer interaction and result visualization; the interface layer opens up cross-system data interaction; improves detection efficiency and scalability, and realizes standardized, automated and intelligent full-process management.

[0014] Optionally, the detection of the digital twin based on the detection and verification platform obtains an intelligent verification result, and realizes the intelligent verification of the vehicle-mounted satellite positioning device, including: obtaining the typical failure mode of the digital twin based on the cloud digital twin model, and obtaining the sequence signal of the typical failure mode; fitting the positioning behavior of the vehicle-mounted satellite positioning device in combination with the multimodal simulation signal and the sequence signal, and obtaining the metrological parameters of the vehicle-mounted satellite positioning device; and obtaining a detection and verification report as the intelligent verification result of the vehicle-mounted satellite positioning device by comparing and verifying the metrological parameters through the detection and verification platform. The present invention realizes high-precision verification through digital twin technology: based on the injection of sequence signals of typical failure modes, typical failure scenarios are identified and the fault reproduction cycle is shortened; the fusion fitting of multimodal signals and fault sequences reduces the simulation error of positioning behavior; the detection and verification platform automatically completes the comparison of metrological parameters to obtain intelligent verification results; and a closed-loop intelligent verification system is formed.

[0015] In the second aspect, the present invention provides an intelligent verification system for a vehicle-mounted satellite positioning device, the system executes the intelligent verification method for the vehicle-mounted satellite positioning device provided by the present invention, the system includes an input device, an output device, a processor and a memory, and its gain lies in: the hardware facilities integrated by the present invention have excellent performance, the input device, the output device, the processor and the memory are interconnected, the information transmission between the various components is smooth, and an efficient information processing system is constructed through the interaction of multiple hardware facilities. The present invention constructs an efficient information processing architecture, forms a closed-loop verification mechanism, significantly improves the verification efficiency and accuracy of the vehicle-mounted satellite positioning device, reduces the cost of manual intervention, and provides an intelligent solution for the quality assurance of the vehicle-mounted positioning device. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of an intelligent calibration method for a vehicle-mounted satellite positioning device according to an embodiment of the present invention;

[0017] Figure 2Schematic diagram of the platform architecture of the detection and verification platform according to an embodiment of the present invention;

[0018] Figure 3 Operation flowchart of the detection and verification platform according to an embodiment of the present invention;

[0019] Figure 4 Intelligent verification system framework diagram of a vehicle-mounted satellite positioning device according to an embodiment of the present invention. Detailed implementation manners

[0020] The following will describe in detail the specific embodiments of the present invention. It should be noted that the embodiments described here are only for illustrative purposes and are not used to limit the present invention. In the following description, in order to provide a thorough understanding of the present invention, a large number of specific details are set forth. However, it is obvious to those of ordinary skill in the art that the present invention does not have to employ these specific details. In other instances, well-known circuits, software, or methods have not been specifically described in order to avoid obscuring the present invention.

[0021] Throughout the specification, references to "one embodiment", "an embodiment", "an example", or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in one embodiment", "in an embodiment", "an example", or "an example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. Additionally, the particular features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Moreover, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0022] Please refer to Figure 1 , an embodiment of the present invention provides an intelligent verification method for a vehicle-mounted satellite positioning device, and the method includes the following steps:

[0023] S1. Construct a dynamic signal fitting model of the vehicle-mounted satellite positioning device by combining multi-modal analog signals and adaptive scene signals.

[0024] Among them, S1 specifically includes the following steps:

[0025] S11. Perform virtual scene fitting based on the analog signal generating device to obtain the multi-modal analog signals.

[0026] In this embodiment, a parametric virtual scene library is constructed by a multi-modal analog signal generating device, and the time-domain characteristics of the signal are associated with spatial geometric constraints. First, based on the radio architecture, a signal generating module is designed to establish an analog signal generating device that supports the generation of multi-frequency signals. Each frequency point is independently configured with parameters such as power spectral density, code phase offset, and Doppler frequency shift. Secondly, a three-dimensional space coordinate system is introduced to perform geometric modeling on the virtual scene, and environmental parameters such as building height, road curvature, and vegetation occlusion rate are mapped into signal attenuation factors and reflection coefficients.

[0027] Specifically, a multipath signal superposition model is constructed to satisfy the following relationship:

[0028]

[0029] Where, is the multi-modal analog signal at time , is the total amount of path signals, is the index variable of the path signal, is the amplitude of the th path signal, is the base of the natural logarithm, is the imaginary unit, is the carrier angular frequency, is the initial phase, is the signal attenuation factor, is the propagation distance, is the total amount of obstacles, is the index variable of the obstacle, is the reflection coefficient, is the step function, is the th path signal and the th obstacle, is the distance threshold.

[0030] Furthermore, the multipath signal superposition model breaks through the limitations of traditional two-dimensional signal simulation and realizes the precise correspondence between the signal power spectrum and the physical environment through spatial geometric constraints.

[0031] S12. Construct a three-dimensional road model, and map the physical environment according to the three-dimensional road model to obtain the adaptive scene signal.

[0032] In this embodiment, the core of the adaptive scene signal is to construct a high-precision three-dimensional road model and realize the dynamic mapping of environmental physical characteristics; based on the high-precision map and real-time traffic flow data, a three-dimensional road model is constructed, and elements such as lane lines, traffic signs, and building outlines are extracted through point cloud semantic segmentation technology to generate a scene topology map with topological relationships. On this basis, using the measured data of on-vehicle cameras and radars, parameters such as the positions of obstacles and vehicle density in the model are updated in real time through environmental perception algorithms, and the dynamic occlusion area is calculated based on the physical engine. The adaptive scene signal generation module calculates the satellite visibility using the ray tracing algorithm according to the current model state, obtains real-time atmospheric parameters, and dynamically generates an adaptive scene signal including error terms such as ionospheric delay and tropospheric refraction.

[0033] Specifically, the three-dimensional road model is constructed by collecting point cloud data through lidar, and the three-dimensional road model satisfies the following relationship:

[0034]

[0035] Wherein, is the mathematical representation function of the road, is the total amount of point cloud data, is the index variable of the point cloud data, is the weight coefficient of the th point cloud data, is the three-dimensional coordinate of the th point cloud data, is the spatial diffusion parameter of the

[0036] In an alternative embodiment, a dynamic road feature matrix is constructed in combination with the geometric parameters of the road, and the dynamic road feature matrix is fused with the adaptive scene signal. The dynamic road feature matrix serves as a supplement to the adaptive scene signal to enhance the accuracy.

[0037] Specifically, the above-mentioned adaptive scene signal satisfies the following relationship:

[0038]

[0039] Wherein, is the adaptive scene signal at time , is the fusion function, is the mathematical representation function of the road, is the dynamic road feature matrix, is the time.

[0040] S13. Dynamically fuse the multi-modal simulation signal and the adaptive scene signal to construct the dynamic signal fitting model.

[0041] In this embodiment, a dynamic fusion algorithm is used to dynamically fuse multi-modal analog signals and adaptive scene signals; a spatio-temporal attention network is constructed, and the signal temporal features and spatial distribution features are extracted through a three-dimensional convolutional layer; an adaptive fusion gating mechanism is designed to dynamically adjust the weight coefficients of multi-modal signals according to the current scene complexity; during the fusion process, the signal consistency index is continuously monitored, and when it is detected that the multipath error exceeds the threshold, the model reconstruction process is automatically triggered. By deeply integrating physical signal generation and digital scene driving, a full-life-cycle test solution is provided for vehicle-mounted positioning devices.

[0042] Specifically, obtain the quality evaluation value of the multi-modal analog signal, obtain the confidence index value of the adaptive scene signal, and construct a dynamic signal fitting model by combining the quality evaluation value and the confidence index value. The dynamic signal fitting model satisfies the following relationship:

[0043]

[0044] where is the fitted dynamic signal, is the quality evaluation value, is the time of the multi-modal analog signal, is the confidence index value, is the time of the adaptive scene signal.

[0045] S2. Perform collaborative verification on the vehicle-mounted satellite positioning device according to the dynamic signal fitting model to obtain a preliminary verification result.

[0046] In this embodiment, a dynamic signal is obtained through a dynamic signal fitting model, and the dynamic signal is data-fused with the original data of the vehicle-mounted satellite positioning device to obtain a fused signal; the fused signal is filtered to obtain the corrected positioning trajectory of the vehicle-mounted satellite positioning device; the standard value of the dynamic signal is obtained, and the error value of the corrected positioning trajectory is obtained by combining the standard value; a dynamic threshold is set according to the dynamic fitting model, and a multi-dimensional anomaly detection result of the vehicle-mounted satellite positioning device is obtained based on the dynamic threshold; the preliminary verification result is obtained through collaborative verification by combining the error value and the multi-dimensional anomaly detection result.

[0047] First, dynamic signals are obtained through a dynamic signal fitting model. The dynamic signals include, but are not limited to, multipath effects and non-line-of-sight propagation characteristics in typical scenarios such as urban canyons, viaducts, and tunnel entrances and exits. The dynamic signals are spatially and temporally aligned with the original observation data of the vehicle-mounted satellite positioning device through time synchronization, and a dynamic weight fusion algorithm is used to achieve data fusion. During the fusion process, the weight ratio of the simulated signal and the original data is adjusted in real time according to the quality assessment value and the confidence index value. Robust estimation theory is introduced in the data fusion to ensure that the fused signal suppresses abnormal interference while retaining effective information. The finally generated fused signal combines the dynamic characteristics of real observations and the scene prior knowledge of the simulated signal, providing high-quality input for subsequent processing.

[0048] Secondly, multi-level filtering processing is performed on the fused signal: The first level uses an improved Kalman filter to achieve real-time compensation for the dynamic model error of the carrier by adaptively adjusting the process noise covariance matrix. The filter introduces a road curvature constraint term, which converts the road geometric parameters into additional constraint conditions of the state equation, effectively suppressing the trajectory divergence problem of traditional Kalman filtering in curved road scenarios. The second level deploys a particle filter, and the dynamic signal fitting model is used to resample the particle weights. In non-line-of-sight scenarios such as tunnels and urban canyons, the particle set converges towards the prediction area of the simulated signal, improving positioning continuity. The third level uses a two-way smoothing algorithm to perform backward correction on the historical trajectory by combining the observation information at future times, so that the positioning result remains consistent in the time domain. Through the three-level filtering architecture, while ensuring real-time performance, the error of the positioning trajectory is optimized to obtain a corrected positioning trajectory.

[0049] Subsequently, a high-precision reference trajectory is constructed by a laser tracker deployed in the calibration site as the standard value of the dynamic signal, providing a benchmark for error analysis. The position deviation components between the corrected trajectory and the reference trajectory are calculated as error values, including positioning error, speed error, mileage error, and direction angle error. Spatiotemporal correlation error analysis is introduced, and by calculating the autocorrelation function and cross-correlation function of the error sequence, the periodic error components caused by multipath effects and the trend error components caused by changes in satellite geometry distribution are identified. The error report includes an integrity risk index, and the probability that the positioning result exceeds the allowable error boundary is evaluated based on the protection level algorithm, providing a quantitative basis for collaborative verification.

[0050] Specifically, the above positioning error satisfies the following relationship:

[0051]

[0052] where is the positioning error of point is the measured coordinate of point is the standard coordinates, is the measured coordinates of the point coordinates, is the standard coordinates;

[0053] The above speed error satisfies the following relationship:

[0054]

[0055] where, is the speed error of the vehicle-mounted satellite positioning device, is the measured average speed of the vehicle-mounted satellite positioning device, is the simulated standard speed;

[0056] The above mileage error satisfies the following relationship:

[0057]

[0058] where, is the mileage error of the vehicle-mounted satellite positioning device, is the measured mileage of the vehicle-mounted satellite positioning device, is the simulated standard mileage;

[0059] The above direction angle error satisfies the following relationship:

[0060]

[0061] where, is the azimuth angle error of the vehicle-mounted satellite positioning device, is the measured azimuth angle of the vehicle-mounted satellite positioning device, is the simulated standard azimuth angle.

[0062] Then, according to the current scene characteristics and the device working state, a dynamic threshold is obtained based on the dynamic signal fitting model. For example, in the urban canyon scene, the dynamic threshold of the carrier-to-noise ratio is reduced compared to the open scene to adapt to the signal attenuation characteristics; in the high-speed scene, the dynamic threshold range of the frequency shift change rate is expanded to avoid misjudging normal dynamics. The multi-dimensional anomaly detection engine simultaneously monitors three types of indicators: the signal layer, the geometric layer, and the physical layer. The signal layer detects anomalies such as sudden drops in the carrier-to-noise ratio; the geometric layer analyzes the distribution of positioning residuals; the physical layer verifies the kinematic constraints of the carrier. The detection results are presented in the form of an anomaly severity score, and fuzzy logic is used to fuse the detection results of each dimension into a quantitative indicator as the multi-dimensional anomaly detection result.

[0063] Finally, collaborative verification introduces a confidence weighting mechanism to assign weights according to the detection credibility of each indicator: fuse the error value with the multi-dimensional anomaly detection results and perform cross-verification to obtain a preliminary verification result; the verification result is presented in a three-dimensional visualization form, including a positioning error heat map, an abnormal event timeline, and the device health status. The preliminary verification report includes four core conclusions: positioning accuracy level, functional compliance determination, abnormal event list, and maintenance suggestions. The quality assessment efficiency of the vehicle-mounted satellite positioning device is improved.

[0064] S3. Construct a verification chain and an evidence storage chain, and obtain a credible verification result of the preliminary verification result by combining the verification chain and the evidence storage chain.

[0065] In this embodiment, to construct a verification chain, first, the original observation data stream of the positioning device is collected in real time through the multi-source sensor network of the vehicle terminal, including but not limited to satellite original observations, inertial measurement unit data, wheel speedometer pulse signals, and environmental images captured by the camera. Timestamps are injected into the original observation data stream and arranged in strict chronological order to form an immutable time-series evidence chain. To ensure the integrity and anti-destruction of the time-series evidence chain, an improved chained sharding storage technology is adopted to cut the continuous data stream into data blocks of a fixed duration. Each data block generates a unique hash value and is chained to the hash value of the previous data block. The sharding nodes of the time-series evidence chain are deployed on vehicle-mounted devices, roadside base stations, and cloud servers to form a three-level storage architecture. In the distributed verification node deployment link, roadside base stations with edge computing capabilities along the road are selected as core nodes, and adjacent vehicle terminals are used as lightweight nodes to construct a heterogeneous verification network. Each node loads a lightweight consensus algorithm to perform parallel verification on the received evidence chain shards: the core node performs full-data verification, and the lightweight node only verifies key feature parameters. When the nodes reach a verification consensus, the evidence chain shard is marked as a credible fragment. Finally, all credible fragments are spliced in chronological order to obtain the verification chain.

[0066] In the pre-verification stage of the preliminary verification result, the verification chain ensures the credibility of the result through a three-layer verification mechanism. The first layer is the temporal consistency verification, which aligns the positioning trajectory in the preliminary verification result with the original observation evidence chain stored in the verification chain in terms of time and space, and calculates the trajectory similarity using the dynamic time warping algorithm. When the similarity is lower than the preset threshold, an anomaly flag is triggered and the result confidence level is reduced. The second layer is the device status verification, which extracts the working status parameters of the positioning device from the verification chain and cross-verifies them with the device health assessment report in the preliminary verification result. If a sudden drop in the number of satellite signal locks and an abnormal decrease in the carrier-to-noise ratio are detected, it is determined that there is a deviation in the device status assessment. The third layer is the environmental adaptability verification, which dynamically adjusts the expected threshold of the positioning accuracy based on the environmental perception data in the verification chain. The pre-verification finally generates the first verification result including the verification pass rate, the anomaly flag list, and the confidence score, providing a credible input for the subsequent evidence preservation verification.

[0067] In this embodiment, an evidence preservation chain is constructed. First, the original observation data stream is preprocessed, and dynamic obfuscation processing is performed on sensitive information involving personal privacy. A multi-modal data chain is established based on the temporal evidence chain. In terms of the privacy protection mechanism design, a privacy protection middleware based on homomorphic encryption is deployed to encrypt and store key data such as the positioning trajectory. The consensus mechanism of the evidence preservation chain only allows authorized institutions to participate in the consensus process to ensure the credibility of the evidence preservation operation. The finally generated multi-modal evidence preservation chain includes a triple structure of a data fingerprint chain, an operation audit chain, and a device identity chain.

[0068] In the evidence preservation verification stage, first, multi-modal data fragments associated with the first verification result are extracted from the evidence preservation chain, including the original observations of the positioning device, environmental perception data, and device work logs. The evidence preservation verification process adopts a three-layer verification architecture: the first layer is the data integrity verification, which realizes anti-tampering detection by comparing the hash value of the data block to be verified with the hash fingerprint stored in the evidence preservation chain. The second layer is the privacy protection compliance verification, which checks whether the face obfuscation processing meets the anonymization standard and whether the position data truncation retains sufficient accuracy through a formal verification tool. The third layer is the business logic consistency verification, which compares the key parameters in the first verification result with the historical data in the evidence preservation chain in terms of trends and detects abnormal mutation points using a long short-term memory network. The evidence preservation verification finally generates the second verification result including the verification pass rate, the privacy compliance score, and the data tampering suspicion index, providing a credible input for the post-verification and significantly enhancing the auditability of the verification result.

[0069] Furthermore, in the post-verification stage, the verification chain performs a final verification on the second verification result through a three-layer verification mechanism. First, a temporal consistency depth verification is carried out. The key parameters in the second verification result are spatially and temporally aligned with the original temporal evidence chain stored in the verification chain, and the trajectory similarity is calculated using the dynamic time warping algorithm. When an anomaly occurs, an anomaly flag is triggered and an artificial review process is initiated. Secondly, a device status traceability verification is implemented. The working status parameters of the positioning device are extracted from the verification chain and cross-verified with the second verification result, and the device failure probability is calculated through a Bayesian network. Finally, an environmental adaptability final verification is carried out. Based on the high-precision map data in the verification chain, the expected threshold of the positioning accuracy is dynamically adjusted. The post-verification finally generates a credible verification result including the verification pass rate, root cause analysis of anomalies, and confidence matrix, and automatically triggers the subsequent processing process through the blockchain smart contract. Through spatio-temporal coupling verification, device status traceability, and environmental intelligent adaptation, the credibility of the preliminary verification result is improved.

[0070] S4. Construct a cloud digital twin model based on the credible verification result, and obtain the digital twin of the vehicle-mounted satellite positioning device according to the cloud digital twin model.

[0071] In this embodiment, to construct the digital twin of the vehicle-mounted satellite positioning device, first, the credible verification result is subjected to standardization processing and deep feature extraction. The core parameters such as positioning error, signal carrier-to-noise ratio, and device temperature are normalized to eliminate the dimension difference, ensuring the comparability of verification results under different batches and different scenarios. In the feature extraction link, an improved random forest algorithm is deployed to screen key features from the standardized data. To reveal the non-linear association between features, the mutual information method is used to calculate the correlation between features, and a weighted feature association network is constructed. The nodes represent key features, and the edge weights reflect the association strength between features.

[0072] Furthermore, a graph convolutional network is introduced to perform topological analysis on the feature association network to identify deep association patterns such as positioning error propagation paths and device failure coupling modes. The finally generated feature association spectrum contains triple information of feature importance ranking, association path topological structure, and dynamic influence coefficient, providing an accurate feature association map for the cloud digital twin model, enabling the model to accurately simulate the complex behavior patterns of the vehicle-mounted satellite positioning device in the real world.

[0073] In this embodiment, the cloud digital twin model adopts a three-dimensional hierarchical architecture, consisting of a physical layer, a signal layer, and a behavior layer, and realizes data interaction and model coupling through a feature correlation spectrum. The physical layer focuses on the hardware characteristics of the vehicle-mounted satellite positioning device, and the modeling scope covers core parameters such as antenna phase center deviation, crystal oscillator frequency drift, and RF front-end noise coefficient. The performance evolution law of the vehicle-mounted satellite positioning device under temperature change, mechanical vibration, and electromagnetic interference is established through the finite element analysis method. The behavior layer models the dynamic response of the device in complex scenarios through the Markov decision process. The state transition probability matrix is dynamically updated by the error coupling coefficient in the feature correlation spectrum. The Kalman filter is used as the core fusion algorithm, and its state equation and observation equation dynamically adjust the noise covariance matrix through the error propagation path in the feature correlation spectrum to ensure a high degree of consistency between the model output and the physical entity state.

[0074] Furthermore, the hybrid modeling process integrates the advantages of data-driven and mechanism modeling. First, the key features in the feature correlation spectrum are mapped to each model layer: the physical layer parameters are correlated with the test data of the hardware through support vector regression; the signal layer noise model uses a generative adversarial network to fit the measured signal distribution and generate interference signal samples that conform to the real scenario; the behavior layer decision model combines the deep reinforcement learning algorithm and dynamically adjusts the action strategy through the scenario features in the feature correlation spectrum. Model coupling is achieved through a bidirectional mapping mechanism. In the forward mapping, the physical layer parameters drive the signal layer to generate simulated observation data, and the behavior layer predicts the positioning trajectory based on the simulated data. In the reverse mapping, the measured positioning error is used to invert the cause of the hardware failure through the adjoint method. The finally generated cloud digital twin model supports bidirectional closed-loop verification: forward simulation can predict the positioning performance boundary under different scenarios, and reverse tracing can locate the hardware failure, improving the maintainability of the vehicle-mounted satellite positioning device.

[0075] The above cloud digital twin model includes:

[0076] First, based on the multi-body dynamics and signal propagation theory, describe the dynamic behavior of the vehicle-mounted satellite positioning device, construct a state evolution equation, and satisfy the following relationship:

[0077]

[0078] Where, is the state vector, is the evolution function, is the influence parameter, is the physical parameter, is the noise.

[0079] Secondly, establish an observation equation, and satisfy the following relationship:

[0080]

[0081] Where, is the observation vector, is the observation function, is the state vector, is the observation parameter, is the observation noise.

[0082] Finally, combining with the observation equation, the state of the twin is updated based on the real-time verification data, satisfying the following relationship:

[0083]

[0084] where, is the updated state vector, is the state vector, is the change amount of the state vector.

[0085] In this embodiment, the real-time dynamic mapping of the vehicle-mounted satellite positioning device is realized based on the cloud digital twin model, and a data-driven closed-loop mapping mechanism is constructed. First, a two-way communication link is established with the vehicle-mounted terminal through the Internet of Things protocol, and the edge computing node is used to preprocess the original positioning data, including coordinate system conversion, multi-source sensor data fusion and noise filtering, to ensure the data quality input into the cloud model. The cloud model deploys a lightweight neural network architecture, continuously receives the real-time positioning stream data uploaded by the vehicle-mounted end through the federated learning mechanism, and dynamically adjusts the model parameters in combination with the spatio-temporal attention mechanism to realize the state synchronization between the physical entity and the digital twin.

[0086] During the dynamic mapping process, a three-dimensional visualization engine of the digital twin is constructed, the longitude and latitude coordinates are converted into three-dimensional spatial positions, and the motion trajectory is rendered in real time in combination with the vehicle dynamics model. The state monitoring module of the digital twin is developed synchronously, and the Kalman filtering algorithm is used to compensate key parameters such as satellite signal strength and positioning dilution of precision. When positioning drift or signal shielding anomaly is detected, the warning state flag of the digital twin is triggered.

[0087] A feedback optimization channel between the digital twin and the physical entity is established, and the cloud analysis results are transmitted back to the vehicle-mounted terminal through the digital thread technology. When the digital twin predicts a decrease in satellite signal quality, it can automatically trigger the vehicle-mounted terminal to switch to the inertial navigation mode or activate the auxiliary positioning module. The continuous optimization link uses the reinforcement learning algorithm to dynamically adjust the model weight parameters according to the deviation between the actual positioning effect and the prediction result of the digital twin, forming an iterative closed loop.

[0088] S5. Establish a detection and verification platform for the vehicle-mounted satellite positioning device, and perform detection on the digital twin based on the detection and verification platform to obtain an intelligent verification result, so as to realize the intelligent verification of the vehicle-mounted satellite positioning device.

[0089] In this embodiment, the detection and verification platform for in-vehicle satellite positioning devices of operating vehicles aims to establish a unified and comprehensively integrated application platform. This platform is based on the networks of the production network, office network, and Internet, utilizes cloud computing technology and combines with the Internet of Things technology platform, and provides a comprehensively collaborative, penetrative management information system that can support adaptive adjustment requirements with the support of policies, regulations, various security guarantee systems, and standard specification systems.

[0090] Please refer to Figure 2 , which shows the schematic diagram of the platform architecture of the detection and verification platform; it includes the terminal layer: responsible for the access, data parsing, and storage of satellite positioning devices, the storage layer: the business layer is mainly responsible for the maintenance and management of the basic data of the verification platform, the service layer: the business services for each business object (such as users, standard devices, etc.), the application layer: the system applications based on various service combinations, and the interface layer: the interface services between this system and external systems.

[0091] Specifically, the main functions of the detection and verification platform include but are not limited to vehicle satellite positioning device access service, positioning device data parsing service, positioning device control service, positioning device data storage service, positioning device data query service, detection and verification management, detection and verification report management, report statistics, system management, and handheld mobile terminal detection equipment.

[0092] Please refer to Figure 3 , which shows the operation flow chart of the detection and verification platform; the operation process includes:

[0093] When the vehicle arrives at the area to be inspected, the vehicle owner or driver submits an application for verifying the in-vehicle satellite positioning device to the verification personnel. The verification personnel use the handheld mobile positioning device detection equipment to identify the vehicle license plate and form a detection and verification business entrustment agreement form. The content of the agreement form shall at least include: license plate number, positioning device manufacturer, positioning device model, positioning device identification, owner, contact information, email address, etc. The system automatically supplements necessary information such as the detection and verification time and supports printing in a specified format. The vehicle owner or driver can sign and confirm on the agreement form.

[0094] After the handheld mobile terminal detection device recognizes the vehicle license plate, it sends relevant information such as the license plate to the background verification management system. The verification management system establishes a temporary verification communication transmission channel between the vehicle satellite positioning device and the verification management system through the transportation vehicle dynamic safety supervision platform and the operation service provider platform, automatically performs relevant settings on the vehicle satellite positioning device, temporarily changes the data sending interval time to send data once every 5 seconds, and notifies the on-site verification personnel of the setting result through the verification management system. Then it starts the standard signal of the Global Navigation Satellite System (GNSS) and remotely controls the satellite positioning device to restart through the handheld mobile terminal detection device.

[0095] After the on-site verification personnel obtain normal feedback information through the handheld mobile terminal detection device, they start the inspection and verification, including automatic verification and manual inspection.

[0096] Automatic verification: According to the signals sent by the GNSS standard signal simulator, all satellite positioning data reported by the positioning device during the signal source time period are extracted, and through standard algorithms, the error values between the actual data of the positioning device and the standard signal data and whether the key functions meet the requirements are calculated. It mainly includes: positioning error: the error value and whether it is within the allowable error range; speed error: the error value and whether it is within the allowable error range; mileage error: the error value and whether it is within the allowable error range; direction angle error: the error value and whether it is within the allowable error range; overspeed alarm function: whether an alarm is generated as required.

[0097] The positioning points, speed, mileage, and azimuth angle for inspection and verification can be set according to user needs, and the required analog signal source is made according to the needs. At the same time, relevant parameters are configured on the platform, and the corresponding data source is selected for inspection and verification.

[0098] Manual inspection: For parts that cannot be automatically detected during the inspection and verification process, the inspection and verification platform supports manual inspection and filling in the inspection results. The inspection method is to perform specified operations manually and then judge and analyze by using the positioning device data query service or observing the status of the positioning device. The inspection items mainly include: equipment appearance, left turn signal status, right turn signal status, brake status, low beam status, high beam status, and Adaptive Cruise Control (ACC) status.

[0099] The management system collects the data of each measurement parameter according to the verification requirements, compares, analyzes, and calculates the uploaded inspection data with the standard data on the platform, and obtains the verification result (qualified or unqualified).

[0100] The verification management system obtains the verification results and sends them back to the handheld mobile terminal detection device of on-site verification personnel, and automatically generates a detection and verification result feedback form. If the result is qualified, the original verification record and verification certificate shall be automatically generated, and the qualified verification result shall be sent back to the on-site verification personnel's terminal; if the verification result is unqualified, the unqualified verification result and the actual verification data of the corresponding unqualified parameters shall be sent back to the handheld mobile terminal detection device of on-site verification personnel, and the on-site verification personnel shall notify the vehicle owner or driver who submitted the inspection on the spot and sign and confirm the verification result on the verification result feedback form.

[0101] After the equipment verification is completed, turn off the GNSS standard signal source. The system automatically restores the set equipment, resets it to the original state, and restarts the equipment. At the same time, it notifies the on-site detection personnel through the mobile terminal.

[0102] After the entire detection and verification process is completed, the generated original verification record and verification certificate will be produced. At the same time, the verification results can also be uploaded to relevant systems such as the provincial transportation administration management system.

[0103] In this embodiment, in-depth fault injection analysis is performed on the digital twin through the cloud digital twin model. Using the historical fault database and real-time operation data, a long short-term memory network is used to perform temporal modeling on the state evolution trajectory of the digital twin, and typical fault modes such as satellite signal loss of lock, multipath effect interference, and clock drift are identified. For each type of fault mode, a fault propagation tree based on the Monte Carlo method is constructed to simulate the evolution path from a single fault point to system-level failure, and a sequence signal containing dimension information such as the fault occurrence time, duration, and parameter offset is generated. This sequence signal adopts a time-event two-dimensional coding method to convert physical quantities such as the sudden change of the satellite signal carrier-to-noise ratio and the divergence of the positioning solution into standardized fault feature vectors. To enhance the signal generalization ability, an adversarial generative network is introduced to perform data enhancement on real fault samples, generating a virtual fault case library covering complex scenarios such as extreme weather and urban canyons, providing high-fidelity training data for subsequent positioning behavior fitting.

[0104] Furthermore, inject the typical fault sequence signal into the satellite navigation signal simulation source to generate a radio frequency signal containing specific fault characteristics, and at the same time perform closed-loop interaction with the digital twin. The adaptive Kalman filtering algorithm is used to perform spatio-temporal registration on multi-modal signals to solve the data synchronization problem caused by the sampling rate differences of different sensors. During the signal fusion process, a transfer learning mechanism is introduced, and the pre-trained deep residual network is used to extract the deep features of the signal, and the domain adaptation technology is used to eliminate the distribution differences between the measured signal and the simulation signal. Based on the fused signal, the metrological parameters such as position, velocity, and attitude are calculated in real time. To improve the parameter accuracy, a dynamic weight adjustment strategy is developed, and the confidence weights of each modal signal are automatically assigned according to the signal quality indicator to ensure centimeter-level accuracy can still be maintained in a complex electromagnetic environment.

[0105] In an alternative embodiment, the detection and verification platform adopts a dual-channel parallel verification architecture and establishes a standard metrological parameter baseline library and a dynamic threshold adaptive mechanism. In the standard channel, the reference trajectory data of the vehicle-mounted satellite positioning device is obtained through a high-precision laser tracker. In the test channel, the metrological parameters output by the digital twin are compared with the reference data in real time, the Mahalanobis distance algorithm is used to calculate the parameter deviation degree, and an intelligent anomaly state identification is realized in combination with a support vector machine classifier. To solve the problem of high missed detection rate of the traditional threshold method, the normal parameter fluctuation range is automatically updated according to the historical verification data. When a parameter anomaly is detected, the reverse traceability function of the digital twin is triggered to locate the root cause of the fault and generate a detection and verification report containing the fault type, impact assessment, repair suggestions, etc. The final intelligent verification result not only includes quantitative evaluation indicators, but also displays the fault propagation path and parameter evolution trend through the digital twin visualization interface to provide decision support for equipment maintenance.

[0106] Please refer to Figure 4 , in an alternative embodiment, the present invention provides an intelligent verification system for a vehicle-mounted satellite positioning device, the system includes an input device, an output device, a processor, and a memory, and the hardware facilities are interconnected. Among them, the memory is used to store computer programs, the computer programs include program instructions, and the processor is configured to call the program instructions to execute the specific implementation steps of the intelligent verification method for the vehicle-mounted satellite positioning device provided by the present invention. The intelligent verification system for the vehicle-mounted satellite positioning device provided by the present invention has a complete structure, is objective and stable, and improves the overall applicability and practical application ability of the present invention.

[0107] In summary, the intelligent verification method and system for an in-vehicle satellite positioning device provided by the method of the present invention improve the positioning accuracy and environmental adaptability through multi-modal signal fusion and dynamic modeling, and the collaborative verification mechanism enhances the comprehensiveness and accuracy of data verification; the combination of the verification chain and the evidence storage chain ensures the tamper-proof and traceability of the verification results, and constructs a data foundation with high credibility; the digital twin realizes the real-time mapping of the device operation state and reduces the physical test cost; the detection and verification platform automatically completes the verification to form a process closed-loop, significantly improving the verification efficiency and device reliability, providing intelligent guarantee for the whole life cycle of the in-vehicle satellite positioning device. The method of the present invention is easy to understand, simple in calculation, with less workload, and convenient for engineering application, providing a theoretical basis and technical support for the further development of traffic intelligent management technology.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention.

Claims

1. An intelligent verification method for an in-vehicle satellite positioning device, characterized in that, It includes the following steps: Construct a dynamic signal fitting model of the vehicle-mounted satellite positioning device by combining multi-modal analog signals and adaptive scene signals; Perform collaborative verification on the vehicle-mounted satellite positioning device according to the dynamic signal fitting model to obtain a preliminary verification result; Construct a verification chain and an evidence preservation chain, and obtain a reliable verification result of the preliminary verification result by combining the verification chain and the evidence preservation chain; Construct a cloud digital twin model based on the reliable verification result, and obtain a digital twin of the vehicle-mounted satellite positioning device according to the cloud digital twin model; Establish a detection and verification platform for the vehicle-mounted satellite positioning device, and perform detection on the digital twin based on the detection and verification platform to obtain an intelligent verification result, so as to realize the intelligent verification of the vehicle-mounted satellite positioning device.

2. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 1, wherein The construction of the dynamic signal fitting model of the vehicle-mounted satellite positioning device by combining multi-modal analog signals and adaptive scene signals includes: Perform virtual scene fitting based on an analog signal generating device to obtain the multi-modal analog signal; Construct a three-dimensional road model, and map the physical environment according to the three-dimensional road model to obtain the adaptive scene signal; Dynamically fuse the multi-modal analog signal and the adaptive scene signal to construct the dynamic signal fitting model.

3. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 1, characterized in that, The collaborative verification of the vehicle-mounted satellite positioning device according to the dynamic signal fitting model to obtain a preliminary verification result includes: Obtain a dynamic signal through the dynamic signal fitting model, and perform data fusion on the dynamic signal and the original data of the vehicle-mounted satellite positioning device to obtain a fusion signal; Perform filtering processing on the fusion signal, and then obtain the corrected positioning trajectory of the vehicle-mounted satellite positioning device; Obtain the standard value of the dynamic signal, and obtain the error value of the corrected positioning trajectory in combination with the standard value; Set a dynamic threshold according to the dynamic fitting model, and obtain a multi-dimensional anomaly detection result of the vehicle-mounted satellite positioning device based on the dynamic threshold; Perform collaborative verification by combining the error value and the multi-dimensional anomaly detection result to obtain the preliminary verification result.

4. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 1, characterized in that The construction of the verification chain and the evidence preservation chain, and obtaining a reliable verification result of the preliminary verification result by combining the verification chain and the evidence preservation chain includes: Obtain a time-sequential evidence chain, and construct the verification chain by combining the time-sequential evidence chain with distributed verification nodes; Establish a multi-modal data chain, and construct the evidence preservation chain based on the multi-modal data chain in combination with a privacy protection mechanism; Perform cross-verification on the preliminary verification result by combining the verification chain and the evidence preservation chain to obtain the reliable verification result.

5. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 4, characterized in that, The cross-verification of the preliminary verification result by combining the verification chain and the evidence preservation chain to obtain the reliable verification result includes: Perform pre-verification on the preliminary verification result based on the verification chain to obtain a first verification result; Perform evidence preservation verification on the first verification result according to the evidence preservation chain to obtain a second verification result; Perform post-verification on the second verification result according to the verification chain to obtain the reliable verification result.

6. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 1, characterized in that The construction of the cloud digital twin model based on the reliable verification result, and obtaining a digital twin of the vehicle-mounted satellite positioning device according to the cloud digital twin model includes: Standardize the trusted verification result and extract features to obtain key features, and construct a feature association spectrum based on the key features; Construct a cloud digital twin model of the vehicle-mounted satellite positioning device according to the feature association spectrum; Perform real-time dynamic mapping on the vehicle-mounted satellite positioning device based on the cloud digital twin model to obtain the digital twin.

7. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 6, characterized in that, The constructing the cloud digital twin model of the vehicle-mounted satellite positioning device according to the feature association spectrum includes: Establish a model hierarchical architecture of the cloud digital twin model, where the model hierarchical architecture includes a physical layer, a signal layer, and a behavior layer; Based on the feature association spectrum and combined with the model hierarchical architecture, perform hybrid modeling on the vehicle-mounted satellite positioning device to obtain the cloud digital twin model.

8. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 1, characterized in that The establishing the detection and verification platform of the vehicle-mounted satellite positioning device includes: Establish a multi-level platform architecture, where the multi-level platform architecture includes a terminal layer, a storage layer, a service layer, an application layer, and an interface layer; Obtain the detection and verification platform based on the multi-level platform architecture.

9. The intelligent verification method of the vehicle-mounted satellite positioning device according to claim 1, characterized in that, The performing detection on the digital twin based on the detection and verification platform to obtain an intelligent verification result and realizing intelligent verification of the vehicle-mounted satellite positioning device includes: Obtain the typical fault mode of the digital twin based on the cloud digital twin model, and acquire the sequence signal of the typical fault mode; Fit the positioning behavior of the vehicle-mounted satellite positioning device by combining the multi-modal analog signal and the sequence signal, and acquire the measurement parameters of the vehicle-mounted satellite positioning device; Compare and verify the measurement parameters through the detection and verification platform to obtain a detection and verification report as the intelligent verification result of the vehicle-mounted satellite positioning device.

10. An intelligent verification system for an in-vehicle satellite positioning device, characterized in that, The system includes an input device, an output device, a processor, and a memory. The input device, the output device, the processor, and the memory are interconnected. Among them, the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the intelligent verification method of the vehicle-mounted satellite positioning device according to any one of claims 1-9.

Images