Station reporting data record filling method and system based on GPS and line station matching fusion

By analyzing historical station announcement records and GPS trajectory data, the system automatically identifies non-operational periods and matches routes, solving the problem of missing bus station announcement data and improving the completeness and accuracy of bus operation data.

CN121661858APending Publication Date: 2026-03-13SOYEA TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-28
Publication Date
2026-03-13

AI Technical Summary

Technical Problem

In existing technologies, missing or abnormal bus stop announcement data leads to inaccurate operational statistics, and manual data entry is inefficient, making it difficult to automatically identify vehicle routes and accurately restore stop announcement data in complex bus networks.

Method used

By acquiring historical station announcement records and GPS trajectory data, analyzing non-operational periods and calculating cumulative mileage, using the destination information of the previous trip to narrow down the route search range, and performing spatiotemporal matching to generate complete station announcement data records.

Benefits of technology

Automatically repairing missing station announcement data improves the completeness and accuracy of bus operation data, providing a basis for accurate capacity statistics and scheduling assessments without the need for manual intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121661858A_ABST
    Figure CN121661858A_ABST
Patent Text Reader

Abstract

The invention relates to a station reporting data record filling method and system based on GPS and line station matching fusion, and the method comprises the steps: analyzing a historical station reporting record of a vehicle and an original GPS track, automatically recognizing an operation blank period, and employing the terminal information of a previous shift to reduce a candidate line search range, so as to precisely restore missing in and out station data. According to the scheme, the problem that station reporting records are lost due to manual operation errors or equipment abnormity is effectively solved, the integrity and accuracy of bus operation data are effectively improved under the condition that manual intervention is not needed, and a real and reliable data basis is provided for transport capacity statistics and shift arrangement assessment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of public transportation technology, and in particular to a method and system for filling in station announcement data records based on GPS and route station matching and fusion. Background Technology

[0002] As an important part of urban infrastructure, the accuracy of public transportation system operation data is crucial for route planning, scheduling, and operation subsidy calculation. In modern intelligent bus dispatching systems, vehicle station announcement records are the core data source reflecting the actual operating status of vehicles.

[0003] However, in actual operation, due to various objective or subjective factors, missing or abnormal station reporting data often occurs. For example, the driver may forget to switch routes or directions after arriving at the terminal, the on-board terminal may not have downloaded the route file correctly, or the equipment may experience a temporary malfunction during operation. These situations can result in the system lacking corresponding station reporting records even though the vehicle has actually completed its operational task and the backend has received the vehicle's real-time GPS trajectory data.

[0004] Existing data processing methods typically ignore trips with missing stop announcement records or rely solely on manual post-trip data entry. This not only leads to severe distortion of operational statistics such as trip completion rate and mileage statistics, failing to accurately reflect operational conditions, but also results in low efficiency and difficulty in accurately reconstructing the actual arrival times of each stop. Furthermore, while GPS trajectory matching is a common technique, in complex bus networks with overlapping sections of multiple routes, how to automatically and accurately identify which route a vehicle was on due to human error when lacking route guidance, and precisely reconstruct logically consistent stop announcement data, remains a pressing technical challenge in the field of public transport data governance. Summary of the Invention

[0005] To address the aforementioned issues, this application provides a method and system for automatically repairing and supplementing missing bus stop announcement data based on GPS and route / stop matching fusion.

[0006] To achieve the above objectives, in a first aspect, embodiments of this application provide a method for filling station announcement data records based on GPS and route station matching fusion, comprising the following steps: S100. Obtaining historical station announcement records and original GPS trajectory data of the target vehicle; S101. Determining the known operating shift time period of the vehicle based on the historical station announcement records, and filtering out non-operating shift GPS datasets located outside the known operating shift time periods from the original GPS trajectory data; S102. Calculating the cumulative mileage of the non-operating shift GPS dataset, and if the cumulative mileage exceeds a preset mileage threshold, marking the corresponding non-operating shift as a period to be filled; S103. Determining a candidate operating route set for the target vehicle based on the last station announcement record before the period to be filled; S104. Performing spatiotemporal matching between the GPS data within the period to be filled and the station information of each route in the candidate operating route set, and calculating the route station matching rate; S105. Selecting the route with the highest route station matching rate as the target route, and generating a complete station announcement data record for the period to be filled based on the matching result.

[0007] Preferably, step S103 specifically includes: obtaining the end station information and route direction information of the previous operating shift before the time period to be filled; searching in the bus route database for all routes with the end station as the starting station; and using all the searched routes as the candidate operating route set.

[0008] Preferably, step S104 specifically includes: for each candidate route in the candidate operating route set, obtaining the coordinates of its standard starting station and standard ending station; calculating the distance from each GPS point within the time period to be filled to the standard starting station and standard ending station; selecting the latest GPS time point that is less than a first preset distance threshold from the standard starting station as the arrival time, and selecting the earliest GPS time point that is less than the first preset distance threshold from the standard ending station as the departure time; and extracting the GPS data within the time period to be filled that lies between the arrival time and the departure time as a valid matching data segment.

[0009] Preferably, after extracting the valid matching data segment, the method further includes: Match the GPS points in the valid matching data segment with the coordinates of the intermediate stations of the candidate route; When the distance between any GPS point and an intermediate station is less than or equal to a second preset distance threshold, the intermediate station is considered to be successfully matched.

[0010] Preferably, the formula for calculating the line station matching rate is: ;in, For the route station matching rate, To determine the number of successfully matched intermediate sites, This represents the total number of stations for the candidate route.

[0011] Preferably, before step S102, the method further includes: grouping the GPS dataset during non-operational periods, dividing the data between the earliest GPS time of the vehicle and the start time of the first operating shift, and the data between the end time of each operating shift and the start time of the next operating shift, into independent groups to be analyzed.

[0012] Preferably, in step S105, the step of generating the complete station reporting data record for the time period to be filled based on the matching result specifically includes: selecting the time of the first successful match and the time of the last successful match for each station from the line data with the highest matching rate; recording the time of the first successful match as the entry time and the time of the last successful match as the exit time; associating vehicle information, line information and up and down directions to construct complete vehicle operation schedule information and writing it into the database.

[0013] Preferably, the preset mileage threshold is used to filter out situations where the vehicle only moves or remains stationary within the depot.

[0014] Preferably, the method is an iterative process that continues until all non-operational periods exceeding a preset mileage threshold have completed data filling.

[0015] In a second aspect, embodiments of this application provide a station announcement data recording and filling system based on GPS and route station matching and fusion, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the method described in any embodiment of the first aspect.

[0016] The proposed method and system for filling in station announcement data based on GPS and route / station matching in this application automatically identifies operational gaps by analyzing historical station announcement records and original GPS trajectories. It also narrows down the search for candidate routes using the destination information of the previous trip, thus accurately restoring missing arrival and departure data. This solution effectively solves the problem of lost station announcement records due to human error or equipment malfunction, significantly improving the completeness and accuracy of public transport operation data without manual intervention, and providing a reliable data foundation for capacity statistics and scheduling assessments. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the method for filling station announcement data records based on GPS and route station matching and fusion provided in this application embodiment. Detailed Implementation

[0018] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application.

[0019] Firstly, embodiments of this application provide a method for filling station announcement data records based on GPS and route / station matching and fusion. This method is mainly applied to public transport data backend processing servers or cloud-based data governance platforms. For example... Figure 1 As shown, the method includes the following steps: S100. Obtain the target vehicle's historical station announcement records and raw GPS trajectory data.

[0020] Specifically, the system reads all data of a specified vehicle on a specific date from the database. Historical station announcement records usually include fields such as license plate number, route name, direction of travel, current station, and announcement time; raw GPS trajectory data usually includes information such as license plate number, GPS time, longitude, latitude, and speed.

[0021] S101. Based on the historical station announcement records, determine the known operating time periods of the vehicles, and filter out the non-operating time period GPS dataset from the original GPS trajectory data that is outside the known operating time periods.

[0022] In actual operation, vehicles have regular operating shifts, but there are also hidden operating periods due to malfunctions or lack of operation. This step aims to identify potential data gap periods by eliminating known normal data.

[0023] As a preferred implementation, to process the data more finely, the method further includes, before performing subsequent steps, grouping the non-operational period GPS dataset into independent groups for analysis: data between the earliest GPS time of a vehicle and the start time of the first operational shift, and data between the end time of each operational shift and the start time of the next operational shift. This divides the discrete GPS data of the entire day into several specific candidate shift segments.

[0024] S102. Calculate the cumulative mileage of the GPS dataset during non-operational periods. If the cumulative mileage exceeds a preset mileage threshold, mark the corresponding non-operational period as a period to be filled.

[0025] Specifically, mileage judgment can filter invalid data, while the preset mileage threshold is used to filter cases where the vehicle only moves or remains stationary within the depot. For example, if the GPS cumulative mileage during a non-operational period is only 0.5 kilometers, it may only be that the vehicle is moving or refueling within the depot, not actually operating, so there is no need to fill it in; if it exceeds the threshold, such as 5 kilometers, it is considered that the vehicle may have performed an operational task but did not report the data.

[0026] S103. Based on the last station report record before the time period to be filled, determine the set of candidate operating routes for the target vehicle.

[0027] This step aims to narrow down the matching range by utilizing the continuity logic of vehicle operations. Specifically, step S103 includes: first, obtaining the end station information and route direction information of the previous operating shift for the time period to be filled, for example, finding that the vehicle ended its previous shift at the train station; second, searching the bus route database for all routes with the end station as the starting station, for example, the system will automatically search for all routes originating from the train station; finally, using all the found routes as the candidate operating route set. In this way, blindly matching GPS data with all bus routes in the city is avoided, effectively improving computational efficiency and accuracy.

[0028] S104. Perform spatiotemporal matching between the GPS data within the time period to be filled and the station information of each route in the candidate operating route set, and calculate the route station matching rate.

[0029] To improve matching accuracy, step S104 specifically executes the following process: The first step is to obtain the coordinates of the standard origin station and standard destination station for each candidate route in the candidate operating route set.

[0030] The second step is to calculate the distance from each GPS point within the time period to be filled to the standard starting station and the standard ending station.

[0031] The third step is to perform time window filtering for the origin and destination: the latest GPS time point that is less than the first preset distance threshold (e.g., 50 meters) from the standard origin station is selected as the entry time, and the earliest GPS time point that is less than the first preset distance threshold from the standard destination station is selected as the exit time.

[0032] The fourth step is data extraction: GPS data within the time period to be filled, located between the arrival and departure times, is extracted as valid matching data segments. This step eliminates redundant trajectories where vehicles spend extended periods at the origin and destination or are subject to scheduling.

[0033] In this embodiment, after extracting the valid matching data segment, to further verify the route's consistency, the method further includes: matching the GPS points in the valid matching data segment with the coordinates of intermediate stations on the candidate route; when the distance between any GPS point and an intermediate station is less than or equal to a second preset distance threshold, the intermediate station is determined to be a successful match. In this embodiment, the second preset distance threshold can be the same as the first preset distance threshold, or it can be adjusted according to the actual road width.

[0034] Based on the above matching results, the formula for calculating the line station matching rate is as follows: ;in, For the route station matching rate, To determine the number of successfully matched intermediate sites, This represents the total number of stations on the candidate route. This formula quantifies the degree of overlap between a GPS track and a given route.

[0035] S105. Select the route with the highest station matching rate as the target route, and generate the complete station reporting data record for the time period to be filled based on the matching results.

[0036] Once the target route is determined, the matching results need to be converted into a standard database record format. Specifically, the steps in step S105 for generating records include: First, from the route data with the highest station matching rate, the time of the first successful match and the time of the last successful match for each station are selected. Then, the time of the first successful match is recorded as the arrival time, and the time of the last successful match is recorded as the departure time. Finally, vehicle information (such as license plate number), route information (such as route ID and name), and direction of travel are associated to construct complete vehicle operation schedule information and write it into the database. Thus, the previously missing station announcement data is successfully repaired.

[0037] Furthermore, it should be noted that the method is an iterative process until all non-operational periods exceeding the preset mileage threshold have completed data filling. That is, the system will perform the above processing on all suspected missing periods of the day for each vehicle until all data is cleaned.

[0038] Secondly, embodiments of this application also provide a station announcement data recording filling system based on GPS and route station matching fusion. This system can implement the method described in Embodiment 1 above, and the system includes: Memory, used to store computer programs; and A processor for executing the computer program to implement the method described in any embodiment of the first aspect.

[0039] Specifically, the processor executes the following steps by running programs in memory: acquiring historical station announcement records and raw GPS data; filtering GPS datasets from non-operational periods and calculating cumulative mileage; if a threshold is exceeded, determining a set of candidate routes based on the destination of the previous trip; performing spatiotemporal matching and matching rate calculation on the candidate routes; and finally selecting the best route, generating complete station announcement data records, and writing them into the database.

[0040] Those skilled in the art will understand that the various modules or units in the system described in the above embodiments can be merged, divided, or deleted according to actual needs. The implementation principle is the same as that of the above method embodiments, and will not be repeated here.

[0041] The method and system for filling in station announcement data based on GPS and route / station matching provided in this application analyzes historical vehicle announcement records and original GPS trajectories to automatically identify operational gaps and narrow down the search range of candidate routes using the destination information of the previous trip, thereby accurately restoring missing arrival and departure data. This solution effectively solves the problem of lost announcement records due to human error or equipment malfunction, and effectively improves the completeness and accuracy of public transport operation data without manual intervention, providing a reliable data foundation for capacity statistics and scheduling assessments.

[0042] In the description of this application, it should be noted that the terms "vertical", "up", "down", "horizontal", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0043] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0044] Finally, it should be noted that the above descriptions are merely preferred embodiments of this application and are not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for filling station announcement data records based on GPS and route station matching and fusion, characterized in that, The steps include: S100. Obtaining the target vehicle's historical station reporting records and raw GPS trajectory data; S101. Determine the known operating time periods of the vehicle based on the historical station announcement records, and filter out the non-operating time period GPS dataset from the original GPS trajectory data that is outside the known operating time periods; S102. Calculate the cumulative mileage of the non-operating time period GPS dataset. If the cumulative mileage exceeds a preset mileage threshold, mark the corresponding non-operating time period as a time period to be filled. S103. Based on the last station announcement record before the time period to be filled, determine the set of candidate operating routes for the target vehicle; S104. Perform spatiotemporal matching between the GPS data in the time period to be filled and the station information of each route in the candidate operating route set, and calculate the route station matching rate; S105. Select the route with the highest station matching rate as the target route, and generate the complete station reporting data record for the time period to be filled based on the matching results.

2. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 1, characterized in that, Step S103 specifically includes: obtaining the end station information and route direction information of the previous operating shift before the time period to be filled; searching in the bus route database for all routes with the end station as the starting station; and using all the searched routes as the candidate operating route set.

3. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 1, characterized in that, Step S104 specifically includes: for each candidate route in the candidate operating route set, obtaining the coordinates of its standard starting station and standard ending station; calculating the distance from each GPS point within the time period to be filled to the standard starting station and standard ending station; selecting the latest GPS time point that is less than a first preset distance threshold from the standard starting station as the arrival time, and selecting the earliest GPS time point that is less than the first preset distance threshold from the standard ending station as the departure time; and extracting the GPS data within the time period to be filled that lies between the arrival time and the departure time as a valid matching data segment.

4. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 3, characterized in that, After extracting the valid matching data segment, the method further includes: Match the GPS points in the valid matching data segment with the coordinates of the intermediate stations of the candidate route; When the distance between any GPS point and an intermediate station is less than or equal to a second preset distance threshold, the intermediate station is considered to be successfully matched.

5. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 4, characterized in that, The formula for calculating the line station matching rate is: ;in, For the route station matching rate, To determine the number of intermediate sites that were successfully matched, This represents the total number of stations for the candidate route.

6. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 1, characterized in that, Before step S102, the method further includes: grouping the GPS dataset during non-operational periods, dividing the data between the earliest GPS time of the vehicle and the start time of the first operating shift, and the data between the end time of each operating shift and the start time of the next operating shift, into independent groups to be analyzed.

7. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 1, characterized in that, In step S105, the step of generating the complete station reporting data record for the time period to be filled based on the matching results specifically includes: selecting the time of the first successful match and the time of the last successful match for each station from the line data with the highest matching rate; recording the time of the first successful match as the entry time and the time of the last successful match as the exit time; associating vehicle information, line information and up and down directions to construct complete vehicle operation schedule information and writing it into the database.

8. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 1, characterized in that, The preset mileage threshold is used to filter out situations where the vehicle only moves or remains stationary within the depot.

9. The method for filling station announcement data records based on GPS and route station matching and fusion according to claim 1, characterized in that, The method is an iterative process that continues until all non-operational periods exceeding the preset mileage threshold have completed data filling.

10. A station announcement data recording and filling system based on GPS and route station matching and fusion, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the method as described in any one of claims 1 to 9.