Verification judgment method based on real-time mileage and track of vehicle

Abstract

The invention discloses a verification and judgment method based on real-time mileage and track of a vehicle. The verification and judgment method comprises the following steps: collecting, storing and transmitting mileage data of the vehicle; analyzing the mileage data and the track point sequence, and identifying road sections of the same type and differences between the mileage data and the track point data in the road sections of the same type; comparing the difference between the real-time mileage data and the track point data of the target vehicle in the road sections of the same type with the difference calculated in the previous step; and when the difference value is greater than a preset proportion, determining that the motion of the target vehicle in the corresponding road section of the same type is abnormal. According to the method, the same type of check road sections are automatically divided through historical data, the exclusive check error coefficient of each road section is calculated, the same type of road sections are ensured, the error coefficient bs of the target vehicle in the specific check road section is calculated, the error coefficient bs is compared with the historical check coefficient of the road section, and an alarm is triggered, so that the abnormal driving condition is quickly found.

Description

Technical Field

[0001] This invention belongs to the field of vehicle mileage verification technology, specifically, it relates to a verification and judgment method based on real-time vehicle mileage and trajectory. Background Technology

[0002] In the field of vehicle monitoring, real-time verification of the accuracy of mileage and trajectory data is crucial for applications such as logistics management, taxi operation, and fleet dispatching. Current mainstream technologies typically rely on independent analysis of mileage data or GPS trajectory data directly reported by in-vehicle terminals, which has the following limitations:

[0003] Static threshold failure: Most systems use fixed thresholds to judge data anomalies (e.g., an alarm is triggered if the mileage deviation rate is >5%). However, in reality, different road sections (e.g., tunnels, viaducts, urban canyons) are significantly affected by factors such as signal interference and tire slippage. A uniform threshold can easily lead to a high false alarm rate or missed alarms.

[0004] Lack of road segment characteristic modeling: Traditional methods do not consider the differentiated impact of road type and environment on sensors (odometers / GPS). For example, GPS drift in tunnels can cause trajectory distance distortion, while odometers may accumulate false mileage on slippery roads. Existing technologies cannot dynamically adapt to road segment characteristics. Furthermore, anomaly detection in existing technologies largely relies on post-event offline analysis, making it difficult to detect sudden problems such as mileage tampering and sensor failures during transportation. Therefore, there is an urgent need for a vehicle monitoring method that can dynamically learn road segment error characteristics, integrate multi-source data for real-time verification, and adapt to vehicle model differences, in order to improve the accuracy and timeliness of anomaly detection. Summary of the Invention

[0005] The purpose of this invention is to provide a verification and judgment method based on real-time vehicle mileage and trajectory, which solves the problem that most existing technologies use fixed thresholds to judge data anomalies. However, in reality, different road sections are affected by factors such as signal interference and tire slippage, resulting in significant differences. A uniform threshold can easily lead to a high false alarm rate or missed alarms.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] The verification and judgment method based on real-time vehicle mileage and trajectory includes the following steps:

[0008] Step 1: Collect, store, and transmit vehicle mileage data;

[0009] Step 2: Analyze the mileage data and trajectory point sequence to identify the differences between mileage data and trajectory point data in the same type of road segment and in each type of road segment;

[0010] Step 3: Compare the differences between the real-time mileage data and trajectory point data of the target vehicle in each type of road segment with the differences calculated in Step 2.

[0011] When the difference between the two is greater than the preset ratio, it is considered that the target vehicle's movement in the corresponding road segment of the same type is abnormal.

[0012] As a further aspect of the present invention, the method for identifying road sections of the same type is as follows:

[0013] The mileage and trajectory data of each vehicle within the monitoring range were acquired within the preset time range in the past.

[0014] For a vehicle, the data is segmented according to time sequence. Data within the same group are continuous in time, thereby obtaining several groups of mileage data and trajectory point data.

[0015] The roads within the monitoring area are divided into m verification segments; m is a preset natural number.

[0016] Based on the spatial distribution of each verification section and the verification error coefficient of each verification section, the same type of road sections within the monitoring range are divided.

[0017] The resulting road segments of the same type meet the following conditions:

[0018] The standard deviation of the verification error coefficient of all verified road segments belonging to the same type of road segment is less than the preset value, that is, the verification error coefficient of all verified road segments belonging to the same type of road segment is consistent.

[0019] The average value of the verification error coefficients of all verified road segments belonging to the same type of road segment is greater than the preset maximum threshold D1 or less than the preset minimum threshold D2.

[0020] As a further aspect of the present invention, the method for calculating the verification error coefficient of the verification section is as follows:

[0021] Based on the mileage and trajectory point data contained in each group, obtain the first movement distance B1 and the second movement distance B2 of the vehicle within the corresponding time range; then calculate the error coefficient b of the vehicle within the corresponding time range according to b = B1 / B2.

[0022] For all monitored vehicles within the monitoring range, the error coefficient b is calculated for each corresponding time range, and the movement path of the vehicle within the monitoring range is determined based on the vehicle's trajectory point data and positioning data.

[0023] This allows us to obtain the motion paths for each vehicle and the error coefficients for each motion path, and to record the motion path as the original parameter path.

[0024] For a test segment, obtain all original parameter paths that completely cover it;

[0025] Further obtain the error coefficient b of all original parameter paths covering the verification segment, clean these error coefficients b, calculate the average value of the cleaned error coefficients b, and use the average value as the verification error coefficient of the corresponding verification segment.

[0026] The verification error coefficients for each verification section are calculated sequentially.

[0027] As a further aspect of the present invention, a speed threshold is set, and the verification error coefficient is only calculated when the vehicle's speed reaches the preset threshold.

[0028] As a further aspect of the present invention, when dividing road sections of the same type and calculating the error coefficient, the different vehicle models are considered, and different vehicles are distinguished according to their models.

[0029] As a further aspect of the present invention, Step 3 specifically includes:

[0030] When monitoring a target vehicle in real time, the trajectory point data of the target vehicle is first obtained, then the movement path of the target vehicle is obtained based on the trajectory point data, and then the same type of road segments covered by the movement path of the target vehicle are obtained.

[0031] Obtain the real-time error coefficient of the target vehicle in each of the same type of road sections it covers;

[0032] Mark the road sections of the same type covered by the target vehicle as the test sections;

[0033] For a test section, obtain the real-time error coefficient bs of the target vehicle in the test section, as well as the verification error coefficient corresponding to the test section;

[0034] When the ratio of bs-verification error coefficient to verification error coefficient is greater than the preset proportional coefficient, it is considered that the movement of the target vehicle in the corresponding inspection section is abnormal.

[0035] The beneficial effects of this invention are:

[0036] Dynamic road segment error modeling: Historical data is used to automatically divide similar verification road segments (such as tunnel groups and elevated sections), and each segment's unique verification error coefficient is calculated (e.g., weak GPS signals in tunnels lead to an average underestimation of trajectory distance by 8%). Standard deviation constraints and threshold filtering (e.g., coefficient > D1 or < D2) are employed to ensure high consistency of error characteristics within similar road segments, avoiding the aggregation of invalid road segments. Then, the error coefficient bs of the target vehicle on a specific verification road segment is calculated in real time and compared with the historical verification coefficient of that segment. An alarm is triggered when (bs - verification coefficient) / verification coefficient is greater than a preset proportional coefficient, thereby quickly detecting abnormal driving conditions. This invention, by combining spatial attributes and real-time data, significantly reduces false alarms caused by environmental interference, such as triggering alarms only on elevated road segments rather than globally.

[0037] This invention is based on time-series continuous data grouping (triggered when the speed reaches the target) to achieve real-time verification during driving and timely detection of anomalies such as odometer sensor tampering and GPS receiver failure. Attached Figure Description

[0038] The invention will now be further described with reference to the accompanying drawings.

[0039] Figure 1 This is a flowchart illustrating the verification and judgment method based on real-time vehicle mileage and trajectory of the present invention. Detailed Implementation

[0040] 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 embodiments of the present invention, and not all embodiments. 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.

[0041] Example 1

[0042] Verification and judgment methods based on real-time vehicle mileage and trajectory, such as Figure 1 As shown, it includes the following steps:

[0043] Step 1: First, the vehicle terminal collects, stores, and transmits the vehicle's mileage data;

[0044] The vehicle's trajectory point sequence is collected, stored, and transmitted through the vehicle-mounted terminal;

[0045] Step 2: The verification center analyzes the mileage data and trajectory point sequences uploaded by the vehicle terminal and / or storage unit to identify the differences between mileage data and trajectory point data in the same type of road segment and in each type of road segment.

[0046] Specifically, the method for identifying similar road sections is as follows:

[0047] The mileage and trajectory data of each vehicle within the monitoring range were acquired within the preset time range in the past.

[0048] For a vehicle, during its movement (a speed threshold can also be set, and subsequent data grouping and processing will only be carried out when the vehicle's speed reaches the preset threshold), the data is divided according to the time sequence. The data in the same group are continuous in time, thereby obtaining several groups of mileage data and trajectory point data.

[0049] Based on the mileage and trajectory point data contained in each group, obtain the first travel distance B1 and the second travel distance B2 of the vehicle within the corresponding time range;

[0050] The first travel distance B1 is calculated using the vehicle's mileage data;

[0051] The second travel distance B2 is calculated using the vehicle's trajectory point data;

[0052] Then, the error coefficient b of the vehicle within the corresponding time range is calculated according to b = B1 / B2;

[0053] For all monitored vehicles within the monitoring range, the error coefficient b is calculated for each corresponding time range, and the movement path of the vehicle within the monitoring range is determined based on the vehicle's trajectory point data and positioning data.

[0054] This allows us to obtain the motion paths for each vehicle and the error coefficients for each motion path, and to record the motion path as the original parameter path.

[0055] The roads within the monitoring area are divided into m verification segments; m is a preset natural number.

[0056] For a test segment, obtain all original parameter paths that completely cover it;

[0057] Further obtain the error coefficient b of all original parameter paths covering the verification segment, clean these error coefficients b, calculate the average value of the cleaned error coefficients b, and use the average value as the verification error coefficient of the corresponding verification segment.

[0058] The purpose of data cleaning is to identify and clean the portion of a set of error coefficients b that are significantly abnormally large or small, deviating greatly from the average data.

[0059] The verification error coefficients for each verification section are calculated sequentially.

[0060] Based on the spatial distribution of each verification section and the verification error coefficient of each verification section, the same type of road sections within the monitoring range are divided.

[0061] Specifically, the road segments of the same type obtained from the division meet the following conditions:

[0062] The standard deviation of the verification error coefficient of all verified road segments belonging to the same type of road segment is less than the preset value, that is, the verification error coefficient of all verified road segments belonging to the same type of road segment is consistent.

[0063] The average value of the verification error coefficients of all verified road segments belonging to the same type of road segment is greater than the preset maximum threshold D1 or less than the preset minimum threshold D2.

[0064] It should be noted that the monitoring range mentioned above refers to the spatial range. To facilitate understanding of its application, an example is given below:

[0065] For logistics companies, their vehicle transportation routes are the scope of their monitoring.

[0066] For taxi companies, their operating area is the scope of their monitoring.

[0067] To ensure the accuracy of the results, the different vehicle models should also be considered. Therefore, different vehicles can be distinguished by model as needed.

[0068] Step 3: When monitoring a vehicle in real time, for ease of description, the vehicle is referred to as the target vehicle. First, the trajectory point data of the target vehicle is obtained. Then, the movement path of the target vehicle is obtained based on the trajectory point data. Finally, the road segments of the same type covered by the movement path of the target vehicle are obtained.

[0069] Obtain the real-time error coefficient of the target vehicle in each of the same type of road sections it covers;

[0070] Mark the road sections of the same type covered by the target vehicle as the test sections;

[0071] For a test section, obtain the real-time error coefficient bs of the target vehicle in the test section, as well as the verification error coefficient corresponding to the test section;

[0072] When the ratio of bs-verification error coefficient to verification error coefficient is greater than the preset proportional coefficient, it is considered that the movement of the target vehicle in the corresponding inspection section is abnormal.

[0073] The above description is merely an example and illustration of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

Claims

1. A verification and judgment method based on real-time vehicle mileage and trajectory, characterized in that, Includes the following steps: Step 1: Collect, store, and transmit vehicle mileage data; Step 2: Analyze the mileage data and trajectory point sequence to identify the differences between mileage data and trajectory point data in the same type of road segment and in each type of road segment; Step 3: Compare the differences between the real-time mileage data and trajectory point data of the target vehicle in each type of road segment with the differences calculated in Step 2. When the difference between the two is greater than the preset ratio, it is considered that the target vehicle's movement in the corresponding road segment of the same type is abnormal.

2. The verification and judgment method based on real-time vehicle mileage and trajectory according to claim 1, characterized in that, The method for identifying similar road sections is as follows: The mileage and trajectory data of each vehicle within the monitoring range were acquired within the preset time range in the past. For a vehicle, the data is segmented according to time sequence. Data within the same group are continuous in time, thereby obtaining several groups of mileage data and trajectory point data. The roads within the monitoring area are divided into m verification segments; m is a preset natural number. Based on the spatial distribution of each verification section and the verification error coefficient of each verification section, the same type of road sections within the monitoring range are divided. The resulting road segments of the same type meet the following conditions: The standard deviation of the verification error coefficient of all verified road segments belonging to the same type of road segment is less than the preset value, that is, the verification error coefficient of all verified road segments belonging to the same type of road segment is consistent. The average value of the verification error coefficients of all verified road segments belonging to the same type of road segment is greater than the preset maximum threshold D1 or less than the preset minimum threshold D2.

3. The verification and judgment method based on real-time vehicle mileage and trajectory according to claim 2, characterized in that, The calculation method for the verification error coefficient of the verified road section is as follows: Based on the mileage and trajectory point data contained in each group, obtain the first movement distance B1 and the second movement distance B2 of the vehicle within the corresponding time range; then calculate the error coefficient b of the vehicle within the corresponding time range according to b = B1 / B2. For all monitored vehicles within the monitoring range, the error coefficient b is calculated for each corresponding time range, and the movement path of the vehicle within the monitoring range is determined based on the vehicle's trajectory point data and positioning data. This allows us to obtain the motion paths for each vehicle and the error coefficients for each motion path, and to record the motion path as the original parameter path. For a test segment, obtain all original parameter paths that completely cover it; Further obtain the error coefficient b of all original parameter paths covering the verification segment, clean these error coefficients b, calculate the average value of the cleaned error coefficients b, and use the average value as the verification error coefficient of the corresponding verification segment. The verification error coefficients for each verification section are calculated sequentially.

4. The verification and judgment method based on real-time vehicle mileage and trajectory according to claim 2 or 3, characterized in that, A speed threshold is set, and the verification error coefficient will only be calculated when the vehicle's speed reaches the preset threshold.

5. The verification and judgment method based on real-time vehicle mileage and trajectory according to claim 2 or 3, characterized in that, When dividing road sections of the same type and calculating the error coefficient, the different vehicle models are taken into account, and different vehicles are distinguished according to their models.

6. The verification and judgment method based on real-time vehicle mileage and trajectory according to claim 2 or 3, characterized in that, Step 3 specifically includes: When monitoring a target vehicle in real time, the trajectory point data of the target vehicle is first obtained, then the movement path of the target vehicle is obtained based on the trajectory point data, and then the same type of road segments covered by the movement path of the target vehicle are obtained. Obtain the real-time error coefficient of the target vehicle in each of the same type of road sections it covers; Mark the road sections of the same type covered by the target vehicle as the test sections; For a test section, obtain the real-time error coefficient bs of the target vehicle in the test section, as well as the verification error coefficient corresponding to the test section; When the ratio of bs-verification error coefficient to verification error coefficient is greater than the preset proportional coefficient, it is considered that the movement of the target vehicle in the corresponding inspection section is abnormal.

Images