Vehicle-mounted positioning data analysis method and system and computer readable storage medium

Abstract

The invention discloses a vehicle-mounted positioning data analysis method and system and a computer readable storage medium, through transverse comparison of multiple vehicle data in a single road section and optimization processing of the vehicle data, the efficiency and accuracy of positioning data analysis are greatly improved, a vehicle-mounted terminal with slightly abnormal positioning precision can be effectively and rapidly identified, and the vehicle-mounted positioning data analysis efficiency is improved. Maintenance and continuous improvement of the vehicle-mounted positioning device are facilitated, filtering and compensation are not needed, and it can be ensured that the positioning precision of all vehicles is within the range meeting the requirement.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle-mounted positioning data, and in particular to a vehicle-mounted positioning data analysis method, system and computer-readable storage medium. Background Art

[0002] The dispatching onboard terminal (terminal) installed on public buses relies heavily on satellite positioning performance for various services, including station detection, automatic station announcements, kilometer accounting, and vehicle route trajectory matching analysis. The terminal obtains the vehicle's current location data by parsing and applying information such as time, date, speed, position coordinates, heading angle, and positioning status in RMC or GGA format output by the positioning module. Therefore, the quality of satellite positioning coordinate data directly affects the accuracy of various bus data.

[0003] When using vehicle satellite positioning data, the output coordinates of the terminal's internal positioning module can easily drift when the vehicle passes through tunnel entrances and exits, under overpasses, or is obstructed by tall buildings or boulevards. Furthermore, large speed fluctuations can easily cause a speeding alarm to sound even when the vehicle is traveling at normal speeds. In more serious cases, a speeding alarm record can be uploaded to the dispatch platform, leading to incorrect assessments of the driver and unnecessary trouble.

[0004] To address data anomalies caused by satellite positioning, current technology primarily analyzes individual vehicle trajectory data, removing significant deviations, suppressing drift, and obtaining more accurate trajectories for purposes such as mileage calculation. When external factors such as network issues cause batch data anomalies, it is impossible to identify positioning data quality issues caused by individual vehicle positioning antenna failures, antenna repositioning, and loose interfaces. Existing filtering and prediction methods compensate for positioning anomalies, but these methods suffer from significant deviations in accuracy and cannot fundamentally address positioning device failures and anomalies. Summary of the Invention

[0005] To solve the technical problems existing in the background technology, the present invention proposes a vehicle-mounted positioning data analysis method, system and computer-readable storage medium.

[0006] The present invention proposes a method for analyzing vehicle-mounted positioning data, comprising the following steps: S1. Collect the original positioning data of buses on all routes, split the original positioning data of each bus according to the station, and obtain the original positioning data set of each bus between two adjacent stations; S2. Select two adjacent bus stops, extract the original positioning data of all buses passing through the route between the two adjacent stops on this section of the route, cluster the original positioning data of the buses on this section of the route based on noise, identify trajectory clusters, and mark the core points and boundary points of the trajectory clusters; S3, obtain the core trajectory according to the core point fitting of the trajectory cluster in S2; S4, taking the core trajectory of S3 as the center, calculate the anomaly score of each boundary point.

[0007] Preferably, the method further includes: S5, repeating S2-S4, calculating the abnormality scores of the boundary points of a single bus on all its trajectories, calculating the abnormality index of the single bus on all routes based on the above abnormality scores, and determining the abnormality of the bus's on-board positioning device.

[0008] Preferably, in S5, the anomaly index of a single bus on all routes is calculated based on the above-mentioned anomaly scores, specifically, the anomaly scores in a single trajectory of a single bus are summed to obtain a total anomaly score, and the total anomaly scores of multiple trajectories of a single bus are averaged to obtain the positioning anomaly index of the single bus.

[0009] Preferably, in S3, the core trajectory is obtained by fitting the core points of the trajectory cluster in S2, specifically, performing least squares calculation on the core points in S2 to obtain trajectory points, and forming the core trajectory through trajectory points corresponding to multiple core points.

[0010] Preferably, in S4, the calculation of the anomaly score of each boundary point with the core trajectory of S4 as the center specifically includes: S41, calculate the distance from all boundary points to the core trajectory; S42, constructing a random isolation tree of the above distance using the isolation forest algorithm to obtain the average path length of the boundary points; S43, calculating the anomaly score of the corresponding point according to the average path length.

[0011] Preferably, in S42, the abnormality score is calculated using the following formula: ; in, , is Euler's constant, is the total number of original positioning data of all buses passing through the route between the two adjacent stations in S2, n i is the i-th boundary point, L i is the average path length of the i-th boundary point.

[0012] Preferably, the boundary points include positioning boundary points and noise boundary points.

[0013] In the present invention, the proposed vehicle positioning data analysis method optimizes the vehicle data by horizontally comparing the data of multiple vehicles on a single road section, greatly improving the efficiency and accuracy of positioning data analysis. It can effectively and quickly identify vehicle terminals with slightly abnormal positioning accuracy, which is conducive to the maintenance and continuous improvement of vehicle positioning devices. Without filtering and compensation, it can ensure that the positioning accuracy of all vehicles is within the required range.

[0014] The present invention also provides a vehicle-mounted positioning data analysis system, comprising: memory for storing computer programs; A processor is used to implement the steps of the above-mentioned vehicle-mounted positioning data analysis method when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium, on which a vehicle positioning data analysis program is stored. When the vehicle positioning data analysis program is executed by a processor, the steps of the vehicle positioning data analysis method described above are implemented.

[0016] In the present invention, the vehicle-mounted positioning data analysis system and computer-readable storage medium proposed have similar technical effects to the above-mentioned vehicle-mounted positioning data analysis method, and therefore are not described in detail. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention provides a flow chart of an embodiment of a vehicle-mounted positioning data analysis method.

[0018] Figure 2 A schematic diagram of the core trajectory of an implementation of a vehicle-mounted positioning data analysis method proposed in the present invention. DETAILED DESCRIPTION

[0019] Reference Figure 1 The present invention proposes a vehicle positioning data analysis method, comprising the following steps: S1. Collect the original positioning data of all bus routes, cut the original positioning data of each bus according to the station, and obtain the original positioning data set of each bus between two adjacent stations.

[0020] Specifically, the original positioning data of all buses of the bus company (without drift suppression and correction) are collected. The original positioning data of each bus is divided according to the station, and the original positioning data set of each bus between two adjacent stations is obtained: {(bus1, point 1), ...(bus n, point m)}.

[0021] S2. Select two adjacent bus stops, extract the original positioning data of all buses passing through the route between the two adjacent stops, perform clustering processing on the original positioning data of the buses on this section of the route based on noise, identify trajectory clusters, and mark the core points and boundary points of the trajectory clusters. Among them, the boundary points include positioning boundary points and noise boundary points.

[0022] Specifically, select a set of two adjacent stops, extract the original positioning data of all vehicles passing through this route on this section of the route, and the total number of trajectories is , identify trajectory clusters by the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method, and mark the core points {k1, k2 ……} and boundary points {n1, n2 ……}.

[0023] S3. Fit the core trajectory according to the core points of the trajectory clusters in S2; Specifically, as Figure 2 shown, perform least squares calculation on the core points in S2 to obtain trajectory points, and form a core trajectory through the trajectory points corresponding to multiple core points. Perform least squares regression calculation on all core points {k1, k2 ……} to obtain a core trajectory. Among them, the sum of the squares of the distances between all core points and the core trajectory is the smallest.

[0024] S4. Take the core trajectory in S3 as the center and calculate the anomaly score of each boundary point.

[0025] Specifically include: S41. Calculate the distances from all boundary points to the core trajectory; Specifically, calculate the distances {x1, x2……} from all boundary points {n1, n2 ……} to the core trajectory, and obtain the maximum values max_xL and max_xR on both sides of the core trajectory respectively; S42. Take the core trajectory as the center, construct random isolation trees for the above distances through the isolation forest algorithm, and obtain the average path length of the boundary points; Specifically, construct random isolation trees with a distance d (d is a random number, and d < max_xL, d < max_XR) from the core trajectory through the isolation forest algorithm, construct multiple isolation trees, and obtain the average path lengths {L1, L2, ……} of the boundary points and noise points {n1, n2 ……}; S43. Calculate the anomaly score of the corresponding point according to the average path length; among them, the anomaly score is calculated by the following formula: ; Among them, , is Euler's constant, is the total number of original positioning data of all buses passing through the route between the two adjacent stations in S2, n i is the i-th boundary point, L i is the average path length of the i-th boundary point.

[0026] Specifically, through the formula Calculate anomaly scores {s1, s2, ...}; in, , is Euler's constant.

[0027] Through S1-S4, the abnormal situation of a single bus between two adjacent stops relative to all buses in the area can be obtained. Without filtering or compensation, the influence of external factors of positioning anomalies is eliminated, and objective and accurate reference information can be provided to indicate whether the bus's vehicle positioning device needs to be repaired or improved.

[0028] In utilizing vehicle anomaly score data, the analysis method of this embodiment may further include: S5, repeating S2-S4 to calculate anomaly scores for boundary points of a single bus along its entire trajectory, calculating an anomaly index for the single bus on all routes based on the anomaly scores, and determining anomalies in the bus's onboard positioning device. Anomaly index thresholds may be set for all buses on a single route to determine positioning anomalies for buses on that route.

[0029] Specifically, the anomaly index of a single bus on all routes is calculated based on the above anomaly scores. Specifically, the anomaly scores in a single trajectory of a single bus are summed to obtain a total anomaly score, and the total anomaly scores of multiple trajectories of a single bus are averaged to obtain the positioning anomaly index of the single bus.

[0030] By comparing the data of multiple vehicles on a single road section horizontally, the vehicle data is optimized and processed, which greatly improves the efficiency and accuracy of positioning data analysis. It can effectively and quickly identify vehicle terminals with slight abnormalities in positioning accuracy, which is conducive to the maintenance and continuous improvement of vehicle-mounted positioning devices. Without filtering and compensation, it can ensure that the positioning accuracy of all vehicles is within the required range.

[0031] In practical applications of the anomaly index, steps S2-S4 can be repeated until all vehicle anomaly positioning scores between adjacent stations are calculated. These scores are sorted and marked on a map to identify vehicle positioning devices with significant positioning deviations that require repair, allowing for more intuitive monitoring of vehicle positioning.

[0032] This embodiment also provides a vehicle-mounted positioning data analysis system, including: memory for storing computer programs; A processor is used to implement the steps of the above-mentioned vehicle-mounted positioning data analysis method when executing the computer program.

[0033] The processor is used to control the overall operation of the data analysis system to complete all or part of the steps in the above-mentioned analysis method. The memory is used to store various types of data to support the operation of the analysis system. This data may include, for example, instructions for any application or method operating on the analysis system, as well as application-related data such as contact information, sent and received messages, images, audio, video, etc.

[0034] The memory can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0035] In addition, the analysis system may further include a communication unit, a multimedia unit and an interface unit. The multimedia unit may include a screen, such as a touch screen, for displaying the analysis results. The interface unit is used to provide human-computer interaction, and may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication unit is used for wired or wireless communication between the analysis system and other systems. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0036] This embodiment further provides a readable storage medium, on which a vehicle positioning data analysis program is stored. When the vehicle positioning data analysis program is executed by a processor, the steps of the vehicle positioning data analysis method described above are implemented.

[0037] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0038] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A vehicle-mounted positioning data analysis method, characterized in that: The following steps are involved: S1. Collect the original positioning data of buses on all routes, split the original positioning data of each bus according to the station, and obtain the original positioning data set of each bus between two adjacent stations; S2. Select two adjacent bus stops, extract the original positioning data of all buses passing through the route between the two adjacent stops on this section of the route, cluster the original positioning data of the buses on this section of the route based on noise, identify trajectory clusters, and mark the core points and boundary points of the trajectory clusters; S3, obtain the core trajectory according to the core point fitting of the trajectory cluster in S2; S4, taking the core trajectory of S3 as the center, calculate the anomaly score of each boundary point.

2. The vehicle-mounted positioning data analysis method according to claim 1, characterized in that: Also includes: S5. Repeat S2-S4 to calculate the abnormality scores of the boundary points of a single bus on all its trajectories. Calculate the abnormality index of the single bus on all routes based on the abnormality scores to determine the abnormality of the bus's onboard positioning device.

3. The vehicle-mounted positioning data analysis method according to claim 2, characterized in that: In S5, the anomaly index of a single bus on all routes is calculated based on the above anomaly scores. Specifically, the anomaly scores in a single trajectory of a single bus are summed to obtain a total anomaly score, and the total anomaly scores of multiple trajectories of a single bus are averaged to obtain the positioning anomaly index of the single bus.

4. The vehicle-mounted positioning data analysis method according to claim 1, characterized in that: In S3, the core trajectory is obtained by fitting the core points of the trajectory cluster in S2. Specifically, the core points in S2 are calculated by least squares method to obtain trajectory points, and the core trajectory is formed by trajectory points corresponding to multiple core points.

5. The vehicle-mounted positioning data analysis method according to claim 1, characterized in that: In S4, the anomaly score of each boundary point is calculated with the core trajectory of S4 as the center, specifically including: S41, calculate the distance from all boundary points to the core trajectory; S42, constructing a random isolation tree of the above distance using the isolation forest algorithm to obtain the average path length of the boundary points; S43, calculating the anomaly score of the corresponding point according to the average path length.

6. The vehicle-mounted positioning data analysis method according to claim 5, characterized in that: In S42, the abnormality score is calculated using the following formula: ; in, , is Euler's constant, is the total number of original positioning data of all buses passing through the route between the two adjacent stations in S2, ni is the i-th boundary point, and Li is the average path length of the i-th boundary point.

7. The vehicle-mounted positioning data analysis method according to claim 1, characterized in that: The boundary points include positioning boundary points and noise boundary points.

8. A vehicle-mounted positioning data analysis system, characterized in that: include: memory for storing computer programs; A processor, configured to implement the steps of the vehicle-mounted positioning data analysis method according to any one of claims 1 to 7 when executing the computer program.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a vehicle positioning data analysis program, which, when executed by a processor, implements the steps of the vehicle positioning data analysis method according to any one of claims 1 to 7.

Images