A vehicle track anti-counterfeiting method and device, computer equipment and storage medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a vehicle trajectory anti-counterfeiting method and device, computer equipment and a storage medium, which comprise the following steps: collecting vehicle trajectory data based on a multi-source sensor; extracting road surface vibration semantic events and geomagnetic disturbance features based on the vehicle trajectory data; respectively matching and comparing the road surface vibration semantic events and the geomagnetic disturbance features with a preset geographical physical feature benchmark library to obtain matching and comparison results; and performing trajectory determination on the vehicle trajectory data according to the matching and comparison results. The application can be applied to the field of financial technology, etc. Road surface physical features and geomagnetic features are extracted from vehicle trajectory data collected by a multi-source sensor, the uniqueness of geographical physical features of different road sections is utilized, the collected features are matched with a preset benchmark library, the matching results of the physical features are combined to determine the authenticity of the trajectory, and therefore the trajectory determination precision is improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method, device, computer equipment, and storage medium for anti-counterfeiting of vehicle trajectory data. Background Technology

[0002] In the field of financial claims, auto insurance claims, as a crucial sub-segment, directly impact the asset security and service efficiency of financial institutions through the standardization and authenticity of its claims process. Furthermore, disaster prevention and mitigation, as a pre-emptive step in auto insurance services, are key measures to reduce financial claims risks and minimize losses for financial institutions. Whether it's determining accident liability and calculating claim amounts in auto insurance claims, or risk prediction and hazard identification in disaster prevention and mitigation, all rely heavily on vehicle driving trajectory data. The authenticity and accuracy of these driving trajectories have become the core basis for verifying the truth of accidents and preventing fraud in the financial claims process.

[0003] However, the GPS / base station-based vehicle positioning technology currently relied upon in financial claims and disaster prevention has many serious shortcomings. It is difficult to meet the high reliability and security requirements of trajectory data in the financial claims field. This not only affects the efficiency of auto insurance claims but also brings potential fraud risks and economic losses to financial institutions, as specifically manifested in the following ways: (1) GPS signals are easily forged: Through developer mode or "virtual location" apps, fraudsters can easily simulate any driving route, thereby forging accident trajectories and exaggerating claim amounts in financial claims. Existing positioning systems can only capture changes in coordinates and cannot effectively determine whether a vehicle has actually moved, making it difficult to identify such financial claim fraud and causing unnecessary economic losses to financial institutions.

[0004] (2) Frequent "Motorcycle Separation" Fraud: In order to obtain illegitimate financial claims, fraudsters may place a mobile phone with positioning function on another vehicle (such as a delivery vehicle) to simulate normal driving mileage, or have people walk with a mobile phone to simulate driving trajectory, thereby forging vehicle driving records, circumventing insurance clause restrictions, or falsely claiming compensation. Existing positioning systems only determine the vehicle driving status through speed parameters, which has extremely low accuracy. For example, when there is a traffic jam, the vehicle speed is similar to the walking speed, making it impossible to effectively distinguish between real driving trajectory and forged trajectory, further exacerbating the fraud risk of financial claims.

[0005] (3) Lack of physical environment feedback: The existing trajectory records are only at the level of pure geography. In the process of financial claims, when there is a dispute over the responsibility for the accident or suspected fraud, it is difficult to fully prove the authenticity and rationality of the accident by relying solely on the geographical coordinate trajectory. It cannot provide strong support for the determination of responsibility in financial claims, which is not conducive to financial institutions' accurate prevention of claims fraud and protection of their own asset security. Summary of the Invention

[0006] This invention provides a vehicle trajectory anti-counterfeiting method, device, computer equipment, and medium, which aims to improve the accuracy of vehicle trajectory determination.

[0007] In a first aspect, embodiments of the present invention provide a vehicle trajectory anti-counterfeiting method, comprising: Vehicle trajectory data is collected based on multi-source sensors; Based on the vehicle trajectory data, semantic events of road vibration and geomagnetic disturbance features are extracted; The road surface vibration semantic events and geomagnetic disturbance features are matched and compared with a preset geophysical feature benchmark library to obtain the matching and comparison results; The vehicle trajectory data is used to determine the trajectory based on the matching comparison results.

[0008] Secondly, embodiments of the present invention provide a vehicle trajectory anti-counterfeiting device, comprising: The data acquisition unit is used to collect vehicle trajectory data based on multi-source sensors; The data extraction unit is used to extract road vibration semantic events and geomagnetic disturbance features based on the vehicle trajectory data; The matching and comparison unit is used to match and compare the road surface vibration semantic events and geomagnetic disturbance features with a preset geophysical feature benchmark library to obtain the matching and comparison results. The trajectory determination unit is used to determine the trajectory of the vehicle trajectory data based on the matching comparison results.

[0009] Thirdly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described vehicle trajectory anti-counterfeiting method.

[0010] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described vehicle trajectory anti-counterfeiting method.

[0011] In the aforementioned vehicle trajectory anti-counterfeiting method, device, computer equipment, and storage medium, vehicle trajectory data can be collected by a client based on multi-source sensors; road vibration semantic events and geomagnetic disturbance features are extracted from the vehicle trajectory data; the road vibration semantic events and geomagnetic disturbance features are matched and compared with a preset geophysical feature benchmark library to obtain matching and comparison results; the vehicle trajectory data is used to determine the trajectory based on the matching and comparison results, and then the trajectory determination result is returned to the client. In this embodiment of the invention, road physical features and geomagnetic features are extracted from vehicle trajectory data collected by multi-source sensors. Utilizing the uniqueness of geophysical features of different road segments, the collected features are matched with a preset benchmark library. The authenticity of the trajectory is determined by combining the matching results of the physical features. This solves the problem that traditional GPS positioning trajectories are easily forged and cannot distinguish between vehicle separation and pedestrian pseudo-trajectories. It forms a dual trajectory verification evidence chain of physical and geographical elements, which can effectively identify trajectory fraud in car insurance claims scenarios, significantly improve the accuracy of vehicle trajectory anti-counterfeiting determination, and thus help financial institutions prevent claims fraud risks and protect their own asset security. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of an application environment for a vehicle trajectory anti-counterfeiting method according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating a vehicle trajectory anti-counterfeiting method according to an embodiment of the present invention; Figure 3 This is a system architecture diagram of a vehicle trajectory anti-counterfeiting method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a sub-process of the vehicle trajectory anti-counterfeiting method in one embodiment of the present invention; Figure 5 This is a schematic diagram of another sub-process of the vehicle trajectory anti-counterfeiting method in one embodiment of the present invention; Figure 6 This is a schematic diagram of a vehicle trajectory anti-counterfeiting device in one embodiment of the present invention; Figure 7 This is a schematic diagram of a substructure of the vehicle trajectory anti-counterfeiting device in one embodiment of the present invention; Figure 8 This is a schematic diagram of another substructure of the vehicle trajectory anti-counterfeiting device in one embodiment of the present invention; Figure 9 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention; Figure 10 This is another structural schematic diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] The vehicle trajectory anti-counterfeiting method provided in this invention can be applied to, for example... Figure 1 In this application environment, the client communicates with the server via a network. The server can collect vehicle trajectory data from multiple sources of sensors through the client; extract road vibration semantic events and geomagnetic disturbance features from the vehicle trajectory data; match and compare the road vibration semantic events and geomagnetic disturbance features with a preset geophysical feature benchmark library to obtain matching and comparison results; determine the trajectory of the vehicle trajectory data based on the matching and comparison results, and then return the trajectory determination result to the client. The client can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented using a standalone server or a server cluster consisting of multiple servers. The invention will be described in detail below through specific embodiments.

[0016] Please see Figure 2 , Figure 2 A flowchart of a vehicle trajectory anti-counterfeiting method provided in an embodiment of the present invention is shown, including steps S101 to S104.

[0017] S101: Vehicle trajectory data is collected based on multi-source sensors; S102: Extract road vibration semantic events and geomagnetic disturbance features based on the vehicle trajectory data; S103: The road surface vibration semantic events and geomagnetic disturbance features are matched and compared with the preset geophysical feature benchmark library to obtain the matching and comparison results; S104: Determine the trajectory of the vehicle trajectory data based on the matching comparison results.

[0018] In this embodiment, vehicle trajectory data is first collected using multi-source sensors; then, road vibration semantic events and geomagnetic disturbance features are extracted from the collected vehicle trajectory data; then, the extracted road vibration semantic events and geomagnetic disturbance features are matched and compared with a preset geophysical feature benchmark library to obtain matching and comparison results; finally, the vehicle trajectory data can be used to determine the trajectory based on the matching and comparison results.

[0019] This embodiment extracts road surface physical features and geomagnetic features from vehicle trajectory data collected by multi-source sensors. Utilizing the uniqueness of geophysical features in different road sections, the collected features are matched with a preset benchmark library. The authenticity of the trajectory is determined by combining the matching results of physical features. This solves the problems of traditional GPS positioning trajectories being easily forged and unable to distinguish between vehicle separation and pedestrian fake trajectories. It forms a dual trajectory verification evidence chain of physical and geographical data, which can effectively identify trajectory fraud in car insurance claims scenarios, significantly improve the accuracy of vehicle trajectory anti-counterfeiting judgment, and thus help financial institutions prevent claims fraud risks and protect their own asset security.

[0020] Combination Figure 3 In practical applications, when a user activates UBI (Usage-based insurance) or files a claim, corresponding data is collected using gyroscopes, accelerometers, and magnetometers. Road vibration semantic events and geomagnetic profile feature sequences (i.e., geomagnetic disturbance features) are then extracted and compared with a cloud-based geophysical feature benchmark database. If the match is successful, the verification is deemed complete, indicating that the vehicle trajectory data represents a real physical trajectory. If an anomaly is detected, a risk warning can be issued, such as a trajectory deviating from the physical environment, prompting manual verification or uploading of vehicle-mounted images. Thus, this embodiment can move property insurance trajectory monitoring from the "geographic coordinate layer" to the "physical sensor layer," effectively solving the problems of existing positioning technologies in financial claims and disaster prevention, and producing the following technical effects: First, it can accurately combat fraudulent claims in financial settlements. Compared to existing positioning technologies that can only capture geographic coordinates, this embodiment can sense real road vibrations and geomagnetic field changes in real time. Even if fraudsters simulate GPS tracks through virtual positioning, they cannot forge the physical environmental characteristics of the corresponding road surface, thus effectively intercepting false claims. It is estimated that it can intercept more than 20% of false claims from other locations, significantly reducing the economic losses of financial institutions caused by claims fraud and improving the authenticity and standardization of financial claims.

[0021] Secondly, it significantly improves the accuracy of usage-based insurance (UBI) pricing. This embodiment can accurately distinguish between two scenarios—"driving the vehicle" and "carrying a mobile phone on other means of transportation"—through the analysis of physical sensory data. This completely solves the problem of inaccurate mileage statistics caused by the separation of vehicle and vehicle in existing technologies, ensuring that premium calculation is based on real vehicle driving data, guaranteeing the fairness of premium pricing, further improving the service quality in the financial claims field, and enhancing the market competitiveness of financial institutions.

[0022] Third, it provides tamper-proof evidence of accidents for financial claims. The vibration semantics and magnetic field fluctuation data captured in this embodiment can constitute a "physical scene snapshot" at the moment of the accident, completely restoring the road environment and vehicle condition at the time of the accident, forming a dual chain of evidence of "physical + geographical". It has strong physical evidence persuasiveness in the process of claims investigation and liability determination, providing strong support for financial institutions to handle claims disputes and prevent fraud, further protecting the asset security of financial institutions, and improving the efficiency and credibility of financial claims.

[0023] In one embodiment, the multi-source sensor includes a gyroscope, an accelerometer, and a magnetometer, and step S101 includes: The angular velocity data of the vehicle is obtained based on the gyroscope; The linear acceleration data of the vehicle is obtained based on the accelerometer; The three-axis magnetic field strength data of the vehicle are obtained based on the magnetometer.

[0024] This embodiment uses gyroscopes, accelerometers, and magnetometers to collect angular velocity data, linear acceleration data, and three-axis magnetic field strength data, respectively. These three types of data together form complete vehicle trajectory data, which includes both dynamic motion parameters during vehicle travel and geomagnetic environment information along the vehicle's path, providing a sufficient data foundation for subsequent feature extraction and authenticity matching.

[0025] Furthermore, after collecting vehicle trajectory data, preprocessing can be performed on this raw data to ensure the accuracy and reliability of subsequent analysis. For example, firstly, the raw trajectory data can be denoised to filter out high-frequency noise caused by environmental electromagnetic interference or random fluctuations; secondly, data correction can be performed to correct potential zero-point drift, scale bias, or installation errors in the sensors themselves; finally, normalization can be implemented to convert data from different sources and with different dimensions to a uniform scale or range. These preprocessing steps can effectively eliminate various errors and interferences in the raw data, thereby improving the accuracy and reliability of the subsequent feature extraction process.

[0026] In one embodiment, step S102 includes: The linear acceleration data is identified to extract road surface physical events; wherein, the road surface physical events include vibration waveforms caused by bridge joints, speed bumps, manhole covers, and road surface damage. Align the physical events of the road surface with the spatiotemporal information of the corresponding road segment to form comparable semantic events of road vibration.

[0027] In this embodiment, when extracting road vibration semantic events, the typical vibration waveforms caused by special road structures are first identified from the linear acceleration data. These special structures include bridge joints, speed bumps, manhole covers, and various types of road damage. Each structure generates a vibration response signal with unique characteristics, which can correspond to a unique physical identifier for different road sections, thereby obtaining the road physical events. Then, the identified road physical events are spatiotemporally aligned with the timestamp information recorded during data acquisition and the road section spatial coordinates corresponding to the vehicle trajectory. The discrete vibration physical signals are converted into road vibration semantic events with clear location markers that can be directly compared with the features of the benchmark library, providing clear and accurate physical feature basis for subsequent matching verification.

[0028] Furthermore, in another embodiment, step S102 further includes: The triaxial magnetic field strength data is identified based on preset disturbance signal extraction rules in order to extract geomagnetic disturbance features.

[0029] In this embodiment, when processing the three-axis magnetic field strength data in vehicle trajectory data, a preset geomagnetic disturbance signal extraction rule is used to filter signal segments that meet the disturbance characteristics from the continuously collected magnetic field strength data, thereby extracting the geomagnetic disturbance characteristics of the corresponding road segment. Here, due to the differences in underground buried objects and roadbed materials, different road segments will form unique and stable geomagnetic disturbance characteristics. For example, when a vehicle passes through a metal structure bridge or tunnel, the magnetometer will generate a strong and specific disturbance signal. Therefore, this feature can serve as another core physical identifier for vehicle trajectory verification, further enriching the feature dimensions of trajectory verification in conjunction with road vibration semantic events.

[0030] Furthermore, the disturbance signal extraction rule described in this embodiment can be based on sliding window detection combined with threshold judgment. For example, the continuously collected triaxial magnetic field strength data is segmented according to a preset window size, and the variance and mean of the triaxial magnetic field strength in each segment are calculated. When the calculated variance exceeds the preset disturbance judgment threshold, the magnetic field signal in that window is judged as a geomagnetic disturbance signal, and the corresponding signal features are extracted as the geomagnetic disturbance features at that location.

[0031] In one embodiment, the geophysical feature reference database includes a cloud-based road surface physical fingerprint database and a cloud-based geomagnetic reference database, such as... Figure 4As shown, step S103 includes steps S201 to S203.

[0032] S201: Perform a consistency comparison between the road vibration semantic event and the cloud-based road physical fingerprint database to obtain the road vibration comparison result; S202: Perform profile flow matching between the geomagnetic disturbance characteristics and the cloud-based geomagnetic reference database to obtain the geomagnetic disturbance matching results; S203: The road vibration comparison results and the geomagnetic disturbance matching results are summarized into the matching comparison results.

[0033] In this embodiment, when obtaining the matching comparison results, the extracted road vibration semantic events are compared with the baseline vibration features of the corresponding road segment in the pre-built road physical fingerprint database in the cloud. This can be achieved, for example, by calculating feature similarity, thereby obtaining the road vibration comparison results. Here, the road vibration comparison results specifically refer to the similarity score between the extracted road vibration semantic events and the baseline features of the corresponding location in the baseline database. For example, if the similarity is higher than a preset road similarity threshold, it is determined that the road feature match is successful; otherwise, it is determined that there is no match.

[0034] On the other hand, the extracted geomagnetic disturbance features are matched with the corresponding road segment's reference geomagnetic features in the cloud-based geomagnetic reference library using profile flow matching. The matching degree between the geomagnetic disturbance features to be matched and the reference features is calculated, such as Consistency=Match(Streamgeo,Basemap), where Consistency represents the geomagnetic feature consistency score, Streamgeo is the geomagnetic disturbance feature profile flow to be matched, and Basemap is the corresponding geomagnetic profile reference in the reference library. If the score is higher than the preset geomagnetic matching threshold, the geomagnetic feature is considered to have passed the matching; otherwise, it is not matched. Finally, the geomagnetic disturbance matching result is obtained.

[0035] Finally, the comparison and matching results of the two parts are summarized to obtain a matching comparison result containing matching situations in two dimensions. This provides a two-dimensional basis for subsequent trajectory determination, avoids misjudgment that may occur with single feature matching, and further improves the reliability of the determination result.

[0036] Furthermore, this embodiment uses a pre-built benchmark library in the cloud to match and verify the two types of physical features. Relying on the storage and computing capabilities of the cloud, it can support the storage and efficient comparison of large-scale road segment feature data, ensuring the accuracy and timeliness of the matching process. Specifically, the cloud-based road surface physical fingerprint library can be pre-collected through crowdsourcing, performing multiple data collections, feature extractions, and feature aggregations on each road segment. Each road segment stores a corresponding standardized road vibration feature fingerprint. Similarly, the cloud-based geomagnetic benchmark library can also be constructed by pre-collecting geomagnetic disturbance features from each road segment, ensuring the stability and accuracy of the benchmark features.

[0037] In one embodiment, such as Figure 5 As shown, step S103 further includes steps S301 to S303.

[0038] S301: Obtain the vehicle's turning radius and, in conjunction with the angular velocity data and linear acceleration data, perform dynamic consistency verification to obtain the corresponding verification results; S302: Obtain vehicle vibration frequency characteristics and compare the vehicle vibration frequency characteristics with a preset walking vibration frequency to obtain a frequency comparison result; S303: The verification results and frequency comparison results are summarized into the matching comparison results.

[0039] This embodiment also introduces two additional dimensions: dynamic consistency verification and vibration frequency verification, to further improve the accuracy of trajectory determination. First, the vehicle's curvature is calculated based on its trajectory during movement. Combined with angular velocity data collected by a gyroscope and linear acceleration data collected by an accelerometer, the vehicle's motion parameters and trajectory curvature are verified to conform to the dynamic laws of vehicle movement, i.e., a=ωv, where a represents centripetal acceleration, ω represents angular velocity, and v represents the vehicle's linear velocity. If the deviation between the actual collected parameters and the theoretically calculated values ​​is within a preset allowable range, the dynamic consistency verification is considered successful; otherwise, it is considered unsuccessful, and this is used as the corresponding verification result. Next, vehicle vibration frequency features are extracted from the collected acceleration data. These features are compared with a preset walking vibration frequency range to determine whether the currently collected vibration features are more consistent with vehicle movement or human walking carrying the device. The frequency comparison result is obtained: if the vibration frequency falls within the preset walking vibration frequency range, it is determined to be human walking carrying the device; otherwise, it is determined to be vehicle movement carrying the device. Finally, the dynamic consistency verification result and the vibration frequency comparison result are summarized and added to the matching comparison result. This embodiment, by adding two new dimensions of verification—dynamics and vibration frequency—can effectively identify fraudulent situations where a person carries equipment and walks to forge a trajectory after the locomotive and train are separated. This further completes the verification dimensions for trajectory anti-counterfeiting and improves the accuracy of fake trajectory identification.

[0040] Therefore, the matching comparison results in this embodiment include road vibration comparison results, geomagnetic disturbance matching results, verification results, and frequency comparison results. After obtaining the complete matching comparison results, a comprehensive judgment can be made based on preset anti-counterfeiting judgment rules. For example, if all comparison results meet the preset true trajectory conditions, the current vehicle trajectory is output as the true trajectory; if any comparison result does not meet the preset true trajectory conditions, the current vehicle trajectory is output as a forged or fraudulent trajectory. This comprehensive judgment method combines multi-dimensional verification results, avoiding the misjudgment problems that may occur with single-dimensional verification. It can adapt to the trajectory anti-counterfeiting needs in different scenarios. In practical applications, the judgment weight of each verification result can be adjusted according to business needs, further improving the flexibility and accuracy of the judgment.

[0041] In one embodiment, step S104 includes: When the matching result is a match, the vehicle trajectory data is determined to be a real physical trajectory; When the matching result is inconsistent, it is determined that the vehicle trajectory data is abnormally forged.

[0042] In this embodiment, the final judgment can be directly output based on the consistency of the matching comparison results. That is, if all the features to be verified, such as the extracted road vibration semantic events and geomagnetic disturbance features, match the baseline features at the corresponding positions in the baseline library, and the dynamic consistency verification and vibration frequency verification both conform to vehicle driving characteristics, then the currently collected vehicle trajectory data is determined to be a genuine physical trajectory. Conversely, if any feature mismatch exists, or any additional verification fails to meet the requirements, the current vehicle trajectory data is determined to be abnormally forged, completing the entire trajectory anti-counterfeiting process. This judgment rule has clear logic and is simple to implement, directly outputting a clear trajectory judgment result. This meets the business needs of quickly identifying fraudulent trajectories in auto insurance claims scenarios, reduces the computational complexity of trajectory verification, and improves the processing efficiency of anti-counterfeiting judgment.

[0043] Figure 6 This is a schematic block diagram of a vehicle trajectory anti-counterfeiting device 600 provided in an embodiment of the present invention. The vehicle trajectory anti-counterfeiting device 600 includes: Data acquisition unit 601 is used to acquire vehicle trajectory data based on multi-source sensors; Data extraction unit 602 is used to extract road vibration semantic events and geomagnetic disturbance features based on the vehicle trajectory data; The matching and comparison unit 603 is used to match and compare the road vibration semantic event and geomagnetic disturbance features with a preset geophysical feature benchmark library to obtain the matching and comparison results. The trajectory determination unit 604 is used to determine the trajectory of the vehicle trajectory data based on the matching comparison result.

[0044] In this embodiment, vehicle trajectory data is first collected using multi-source sensors; then, road vibration semantic events and geomagnetic disturbance features are extracted from the collected vehicle trajectory data; then, the extracted road vibration semantic events and geomagnetic disturbance features are matched and compared with a preset geophysical feature benchmark library to obtain matching and comparison results; finally, the vehicle trajectory data can be used to determine the trajectory based on the matching and comparison results.

[0045] This embodiment extracts road surface physical features and geomagnetic features from vehicle trajectory data collected by multi-source sensors. Utilizing the uniqueness of geophysical features in different road sections, the collected features are matched with a preset benchmark library. The authenticity of the trajectory is determined by combining the matching results of physical features. This solves the problems of traditional GPS positioning trajectories being easily forged and unable to distinguish between vehicle separation and pedestrian fake trajectories. It forms a dual trajectory verification evidence chain of physical and geographical data, which can effectively identify trajectory fraud in car insurance claims scenarios, significantly improve the accuracy of vehicle trajectory anti-counterfeiting judgment, and thus help financial institutions prevent claims fraud risks and protect their own asset security.

[0046] Combination Figure 3 In practical applications, when a user activates UBI (Usage-based insurance) or files a claim, corresponding data is collected using gyroscopes, accelerometers, and magnetometers. Road vibration semantic events and geomagnetic profile feature sequences (i.e., geomagnetic disturbance features) are then extracted and compared with a cloud-based geophysical feature benchmark database. If the match is successful, the verification is deemed complete, indicating that the vehicle trajectory data represents a real physical trajectory. If an anomaly is detected, a risk warning can be issued, such as a trajectory deviating from the physical environment, prompting manual verification or uploading of vehicle-mounted images. Thus, this embodiment can move property insurance trajectory monitoring from the "geographic coordinate layer" to the "physical sensor layer," effectively solving the problems of existing positioning technologies in financial claims and disaster prevention, and producing the following technical effects: First, it can accurately combat fraudulent claims in financial settlements. Compared to existing positioning technologies that can only capture geographic coordinates, this embodiment can sense real road vibrations and geomagnetic field changes in real time. Even if fraudsters simulate GPS tracks through virtual positioning, they cannot forge the physical environmental characteristics of the corresponding road surface, thus effectively intercepting false claims. It is estimated that it can intercept more than 20% of false claims from other locations, significantly reducing the economic losses of financial institutions caused by claims fraud and improving the authenticity and standardization of financial claims.

[0047] Secondly, it significantly improves the accuracy of usage-based insurance (UBI) pricing. This embodiment can accurately distinguish between two scenarios—"driving the vehicle" and "carrying a mobile phone on other means of transportation"—through the analysis of physical sensory data. This completely solves the problem of inaccurate mileage statistics caused by the separation of vehicle and vehicle in existing technologies, ensuring that premium calculation is based on real vehicle driving data, guaranteeing the fairness of premium pricing, further improving the service quality in the financial claims field, and enhancing the market competitiveness of financial institutions.

[0048] Third, it provides tamper-proof evidence of accidents for financial claims. The vibration semantics and magnetic field fluctuation data captured in this embodiment can constitute a "physical scene snapshot" at the moment of the accident, completely restoring the road environment and vehicle condition at the time of the accident, forming a dual chain of evidence of "physical + geographical". It has strong physical evidence persuasiveness in the process of claims investigation and liability determination, providing strong support for financial institutions to handle claims disputes and prevent fraud, further protecting the asset security of financial institutions, and improving the efficiency and credibility of financial claims.

[0049] In one embodiment, the multi-source sensor includes a gyroscope, an accelerometer, and a magnetometer, and the data acquisition unit 601 includes: The first acquisition unit is used to acquire the angular velocity data of the vehicle based on the gyroscope; The second acquisition unit is used to acquire linear acceleration data of the vehicle based on the accelerometer; The third acquisition unit is used to acquire the three-axis magnetic field strength data of the vehicle based on the magnetometer.

[0050] This embodiment uses gyroscopes, accelerometers, and magnetometers to collect angular velocity data, linear acceleration data, and three-axis magnetic field strength data, respectively. These three types of data together form complete vehicle trajectory data, which includes both dynamic motion parameters during vehicle travel and geomagnetic environment information along the vehicle's path, providing a sufficient data foundation for subsequent feature extraction and authenticity matching.

[0051] Furthermore, after collecting vehicle trajectory data, preprocessing can be performed on this raw data to ensure the accuracy and reliability of subsequent analysis. For example, firstly, the raw trajectory data can be denoised to filter out high-frequency noise caused by environmental electromagnetic interference or random fluctuations; secondly, data correction can be performed to correct potential zero-point drift, scale bias, or installation errors in the sensors themselves; finally, normalization can be implemented to convert data from different sources and with different dimensions to a uniform scale or range. These preprocessing steps can effectively eliminate various errors and interferences in the raw data, thereby improving the accuracy and reliability of the subsequent feature extraction process.

[0052] In one embodiment, the data extraction unit 602 includes: An event extraction unit is used to identify the linear acceleration data in order to extract road surface physical events; wherein, the road surface physical events include vibration waveforms caused by bridge joints, speed bumps, manhole covers, and road surface damage. The spatiotemporal alignment unit is used to align the physical events of the road surface with the spatiotemporal information of the corresponding road segment to form comparable semantic events of road vibration.

[0053] In this embodiment, when extracting road vibration semantic events, the typical vibration waveforms caused by special road structures are first identified from the linear acceleration data. These special structures include bridge joints, speed bumps, manhole covers, and various types of road damage. Each structure generates a vibration response signal with unique characteristics, which can correspond to a unique physical identifier for different road sections, thereby obtaining the road physical events. Then, the identified road physical events are spatiotemporally aligned with the timestamp information recorded during data acquisition and the road section spatial coordinates corresponding to the vehicle trajectory. The discrete vibration physical signals are converted into road vibration semantic events with clear location markers that can be directly compared with the features of the benchmark library, providing clear and accurate physical feature basis for subsequent matching verification.

[0054] In one embodiment, the data extraction unit 602 further includes: The data identification unit is used to identify the triaxial magnetic field strength data based on preset disturbance signal extraction rules in order to extract the geomagnetic disturbance features therein.

[0055] In this embodiment, when processing the three-axis magnetic field strength data in vehicle trajectory data, a preset geomagnetic disturbance signal extraction rule is used to filter signal segments that meet the disturbance characteristics from the continuously collected magnetic field strength data, thereby extracting the geomagnetic disturbance characteristics of the corresponding road segment. Here, due to the differences in underground buried objects and roadbed materials, different road segments will form unique and stable geomagnetic disturbance characteristics. For example, when a vehicle passes through a metal structure bridge or tunnel, the magnetometer will generate a strong and specific disturbance signal. Therefore, this feature can serve as another core physical identifier for vehicle trajectory verification, further enriching the feature dimensions of trajectory verification in conjunction with road vibration semantic events.

[0056] Furthermore, the disturbance signal extraction rule described in this embodiment can be based on sliding window detection combined with threshold judgment. For example, the continuously collected triaxial magnetic field strength data is segmented according to a preset window size, and the variance and mean of the triaxial magnetic field strength in each segment are calculated. When the calculated variance exceeds the preset disturbance judgment threshold, the magnetic field signal in that window is judged as a geomagnetic disturbance signal, and the corresponding signal features are extracted as the geomagnetic disturbance features at that location.

[0057] In one embodiment, the geophysical feature reference database includes a cloud-based road surface physical fingerprint database and a cloud-based geomagnetic reference database, such as... Figure 7 As shown, the matching comparison unit 603 includes: The consistency comparison unit 701 is used to perform a consistency comparison between the road vibration semantic event and the cloud-based road physical fingerprint database to obtain the road vibration comparison result. The profile flow matching unit 702 is used to perform profile flow matching between the geomagnetic disturbance features and the cloud-based geomagnetic reference database to obtain the geomagnetic disturbance matching result. The first summarizing unit 703 is used to summarize the road vibration comparison results and the geomagnetic disturbance matching results into the matching comparison results.

[0058] In this embodiment, when obtaining the matching comparison results, the extracted road vibration semantic events are compared with the baseline vibration features of the corresponding road segment in the pre-built road physical fingerprint database in the cloud. This can be achieved, for example, by calculating feature similarity, thereby obtaining the road vibration comparison results. Here, the road vibration comparison results specifically refer to the similarity score between the extracted road vibration semantic events and the baseline features of the corresponding location in the baseline database. For example, if the similarity is higher than a preset road similarity threshold, it is determined that the road feature match is successful; otherwise, it is determined that there is no match.

[0059] On the other hand, the extracted geomagnetic disturbance features are matched with the corresponding road segment's reference geomagnetic features in the cloud-based geomagnetic reference library using profile flow matching. The matching degree between the geomagnetic disturbance features to be matched and the reference features is calculated, such as Consistency=Match(Streamgeo,Basemap), where Consistency represents the geomagnetic feature consistency score, Streamgeo is the geomagnetic disturbance feature profile flow to be matched, and Basemap is the corresponding geomagnetic profile reference in the reference library. If the score is higher than the preset geomagnetic matching threshold, the geomagnetic feature is considered to have passed the matching; otherwise, it is not matched. Finally, the geomagnetic disturbance matching result is obtained.

[0060] Finally, the comparison and matching results of the two parts are summarized to obtain a matching comparison result containing matching situations in two dimensions. This provides a two-dimensional basis for subsequent trajectory determination, avoids misjudgment that may occur with single feature matching, and further improves the reliability of the determination result.

[0061] Furthermore, this embodiment uses a pre-built benchmark library in the cloud to match and verify the two types of physical features. Relying on the storage and computing capabilities of the cloud, it can support the storage and efficient comparison of large-scale road segment feature data, ensuring the accuracy and timeliness of the matching process. Specifically, the cloud-based road surface physical fingerprint library can be pre-collected through crowdsourcing, performing multiple data collections, feature extractions, and feature aggregations on each road segment. Each road segment stores a corresponding standardized road vibration feature fingerprint. Similarly, the cloud-based geomagnetic benchmark library can also be constructed by pre-collecting geomagnetic disturbance features from each road segment, ensuring the stability and accuracy of the benchmark features.

[0062] In one embodiment, such as Figure 8 As shown, the matching comparison unit 603 further includes: The consistency verification unit 801 is used to obtain the vehicle's turning curvature and, in combination with the angular velocity data and linear acceleration data, perform dynamic consistency verification to obtain the corresponding verification results. The frequency comparison unit 802 is used to acquire vehicle vibration frequency characteristics and compare the vehicle vibration frequency characteristics with a preset walking vibration frequency to obtain a frequency comparison result. The second summarization unit 803 is used to summarize the verification results and frequency comparison results into the matching comparison results.

[0063] This embodiment also introduces two additional dimensions: dynamic consistency verification and vibration frequency verification, to further improve the accuracy of trajectory determination. First, the vehicle's curvature is calculated based on its trajectory during movement. Combined with angular velocity data collected by a gyroscope and linear acceleration data collected by an accelerometer, the vehicle's motion parameters and trajectory curvature are verified to conform to the dynamic laws of vehicle movement, i.e., a=ωv, where a represents centripetal acceleration, ω represents angular velocity, and v represents the vehicle's linear velocity. If the deviation between the actual collected parameters and the theoretically calculated values ​​is within a preset allowable range, the dynamic consistency verification is considered successful; otherwise, it is considered unsuccessful, and this is used as the corresponding verification result. Next, vehicle vibration frequency features are extracted from the collected acceleration data. These features are compared with a preset walking vibration frequency range to determine whether the currently collected vibration features are more consistent with vehicle movement or human walking carrying the device. The frequency comparison result is obtained: if the vibration frequency falls within the preset walking vibration frequency range, it is determined to be human walking carrying the device; otherwise, it is determined to be vehicle movement carrying the device. Finally, the dynamic consistency verification result and the vibration frequency comparison result are summarized and added to the matching comparison result. This embodiment, by adding two new dimensions of verification—dynamics and vibration frequency—can effectively identify fraudulent situations where a person carries equipment and walks to forge a trajectory after the locomotive and train are separated. This further completes the verification dimensions for trajectory anti-counterfeiting and improves the accuracy of fake trajectory identification.

[0064] Therefore, the matching comparison results in this embodiment include road vibration comparison results, geomagnetic disturbance matching results, verification results, and frequency comparison results. After obtaining the complete matching comparison results, a comprehensive judgment can be made based on preset anti-counterfeiting judgment rules. For example, if all comparison results meet the preset true trajectory conditions, the current vehicle trajectory is output as the true trajectory; if any comparison result does not meet the preset true trajectory conditions, the current vehicle trajectory is output as a forged or fraudulent trajectory. This comprehensive judgment method combines multi-dimensional verification results, avoiding the misjudgment problems that may occur with single-dimensional verification. It can adapt to the trajectory anti-counterfeiting needs in different scenarios. In practical applications, the judgment weight of each verification result can be adjusted according to business needs, further improving the flexibility and accuracy of the judgment.

[0065] In one embodiment, the trajectory determination unit 604 includes: The first determination unit is used to determine that the vehicle trajectory data is a real physical trajectory when the matching result is a match. The second determination unit is used to determine that the vehicle trajectory data is abnormally forged when the matching result is inconsistent.

[0066] In this embodiment, the final judgment can be directly output based on the consistency of the matching comparison results. That is, if all the features to be verified, such as the extracted road vibration semantic events and geomagnetic disturbance features, match the baseline features at the corresponding positions in the baseline library, and the dynamic consistency verification and vibration frequency verification both conform to vehicle driving characteristics, then the currently collected vehicle trajectory data is determined to be a genuine physical trajectory. Conversely, if any feature mismatch exists, or any additional verification fails to meet the requirements, the current vehicle trajectory data is determined to be abnormally forged, completing the entire trajectory anti-counterfeiting process. This judgment rule has clear logic and is simple to implement, directly outputting a clear trajectory judgment result. This meets the business needs of quickly identifying fraudulent trajectories in auto insurance claims scenarios, reduces the computational complexity of trajectory verification, and improves the processing efficiency of anti-counterfeiting judgment.

[0067] Specific limitations regarding vehicle trajectory anti-counterfeiting devices can be found in the limitations of vehicle trajectory anti-counterfeiting methods described above, and will not be repeated here. Each module in the aforementioned vehicle trajectory anti-counterfeiting device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0068] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a vehicle trajectory anti-counterfeiting method on the server side.

[0069] In one embodiment, a computer device is provided, which may be a client, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a vehicle trajectory anti-counterfeiting method on the client side.

[0070] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Vehicle trajectory data is collected based on multi-source sensors; Based on the vehicle trajectory data, semantic events of road vibration and geomagnetic disturbance features are extracted; The road surface vibration semantic events and geomagnetic disturbance features are matched and compared with a preset geophysical feature benchmark library to obtain the matching and comparison results; The vehicle trajectory data is used to determine the trajectory based on the matching comparison results.

[0071] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Vehicle trajectory data is collected based on multi-source sensors; Based on the vehicle trajectory data, semantic events of road vibration and geomagnetic disturbance features are extracted; The road surface vibration semantic events and geomagnetic disturbance features are matched and compared with a preset geophysical feature benchmark library to obtain the matching and comparison results; The vehicle trajectory data is used to determine the trajectory based on the matching comparison results.

[0072] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0073] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0074] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0075] It should be noted that any AI models, software tools, or components not belonging to this company appearing in the embodiments of this application are merely illustrative examples and do not represent actual use. All user personal information involved in the embodiments of this application has been authorized (with the knowledge and consent) by the relevant parties or has been fully authorized by all parties, and the executing entity may obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with relevant laws and regulations and do not violate public order and good morals.

[0076] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for preventing counterfeiting vehicle trajectory data, characterized in that, include: Vehicle trajectory data is collected based on multi-source sensors; Based on the vehicle trajectory data, semantic events of road vibration and geomagnetic disturbance features are extracted; The road surface vibration semantic events and geomagnetic disturbance features are matched and compared with a preset geophysical feature benchmark library to obtain the matching and comparison results; The vehicle trajectory data is used to determine the trajectory based on the matching comparison results.

2. The vehicle trajectory anti-counterfeiting method according to claim 1, characterized in that, The multi-source sensors include a gyroscope, an accelerometer, and a magnetometer. The acquisition of vehicle trajectory data based on the multi-source sensors includes: The angular velocity data of the vehicle is obtained based on the gyroscope; The linear acceleration data of the vehicle is obtained based on the accelerometer; The three-axis magnetic field strength data of the vehicle are obtained based on the magnetometer.

3. The vehicle trajectory anti-counterfeiting method according to claim 2, characterized in that, The extraction of road vibration semantic events and geomagnetic disturbance features based on the vehicle trajectory data includes: The linear acceleration data is identified to extract road surface physical events. Align the physical events of the road surface with the spatiotemporal information of the corresponding road segment to form comparable semantic events of road vibration.

4. The vehicle trajectory anti-counterfeiting method according to claim 2, characterized in that, The extraction of road vibration semantic events and geomagnetic disturbance features based on the vehicle trajectory data also includes: The triaxial magnetic field strength data is identified based on preset disturbance signal extraction rules in order to extract geomagnetic disturbance features.

5. The vehicle trajectory anti-counterfeiting method according to claim 1, characterized in that, The geophysical feature benchmark database includes a cloud-based road surface physical fingerprint database and a cloud-based geomagnetic benchmark database. The process of matching and comparing the road surface vibration semantic events and geomagnetic disturbance features with the preset geophysical feature benchmark database to obtain matching and comparison results includes: The road vibration semantic events are compared with the cloud-based road physical fingerprint database to obtain the road vibration comparison results. The geomagnetic disturbance characteristics are matched with the cloud-based geomagnetic reference database using profile flow matching to obtain the geomagnetic disturbance matching results; The road vibration comparison results and the geomagnetic disturbance matching results are summarized into the matching comparison results.

6. The vehicle trajectory anti-counterfeiting method according to claim 2, characterized in that, The step of matching and comparing the road surface vibration semantic events and geomagnetic disturbance features with a preset geophysical feature benchmark database to obtain matching and comparison results also includes: The vehicle's turning radius is obtained, and combined with the angular velocity data and linear acceleration data, dynamic consistency verification is performed to obtain the corresponding verification results. The vehicle vibration frequency characteristics are obtained and compared with the preset walking vibration frequency to obtain the frequency comparison result. The verification results and frequency comparison results are summarized into the matching comparison results.

7. The vehicle trajectory anti-counterfeiting method according to claim 1, characterized in that, The step of determining the vehicle trajectory data based on the matching comparison result includes: When the matching result is a match, the vehicle trajectory data is determined to be a real physical trajectory; When the matching result is inconsistent, it is determined that the vehicle trajectory data is abnormally forged.

8. A vehicle trajectory anti-counterfeiting device, characterized in that, include: The data acquisition unit is used to collect vehicle trajectory data based on multi-source sensors; The data extraction unit is used to extract road vibration semantic events and geomagnetic disturbance features based on the vehicle trajectory data; The matching and comparison unit is used to match and compare the road surface vibration semantic events and geomagnetic disturbance features with a preset geophysical feature benchmark library to obtain the matching and comparison results. The trajectory determination unit is used to determine the trajectory of the vehicle trajectory data based on the matching comparison results.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the vehicle trajectory anti-counterfeiting method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the vehicle trajectory anti-counterfeiting method as described in any one of claims 1 to 7.

Images