A bus starting and ending point passenger flow data processing method, device and equipment

Abstract

The application discloses a bus starting and ending point passenger flow data processing method, device and equipment, and relates to the technical field of bus passenger flow data processing. The method comprises the following steps: according to the trip information in the electronic route sheet data, splitting the starting and ending point pairing data, and based on the passenger body state and dressing features collected in the same trip operation period, re-matching the features of the starting and ending point pairing data; for each trip, according to the opening and closing door time information and the vehicle positioning data in the station passenger getting-on and getting-off data, judging whether there is vehicle positioning data matched with the opening and closing door time information in the preset time window, and according to the positioning validity result, correcting and processing the getting-on and getting-off station information in the station passenger getting-on and getting-off data. The above scheme re-matches the features of the starting and ending point pairing data of the same trip, corrects the getting-on and getting-off station information according to the positioning validity result, and improves the accuracy, availability and consistency of the bus starting and ending point passenger flow data.

Description

Technical Field

[0001] This application relates to the field of public transportation technology, and more particularly to the field of bus passenger flow data processing technology, specifically to a method, apparatus, and equipment for processing passenger flow data at bus origin and destination points. Background Technology

[0002] As a core data source reflecting the operational status of public transportation and passenger travel patterns, the quality of bus origin-destination passenger flow data directly determines the scientific and rational nature of public transportation companies' operational decisions.

[0003] Existing technologies mainly rely on simple time-period filtering or manual correction, which has a series of problems such as mixed matching of passenger body shape and clothing characteristics from multiple trips, inconsistency between uploaded boarding and alighting stations and actual stopping stations, OD (Origin-Destination) matching errors, unusable data, and low accuracy of station passenger flow statistics. Summary of the Invention

[0004] This application provides a method, apparatus, and equipment for processing passenger flow data at bus origin and destination points, so as to improve the accuracy, availability, and consistency of passenger flow data at bus origin and destination points.

[0005] According to one aspect of this application, a method for processing passenger flow data at bus origin and destination points is provided, the method comprising:

[0006] The system acquires passenger pick-up and drop-off data at bus stops, origin-destination pairing data, and bus operation benchmark data; wherein the bus operation benchmark data includes electronic waybill data and vehicle positioning data.

[0007] Based on the shift information in the electronic waybill data, the origin-destination pairing data is split and processed, and based on the passenger body shape and clothing characteristics collected during the same shift's operating period, the origin-destination pairing data is re-matched.

[0008] For each bus trip, based on the door opening and closing time information in the passenger pick-up and drop-off data at the station and the vehicle positioning data, it is determined whether there is vehicle positioning data that matches the door opening and closing time information within a preset time window, thus obtaining the positioning validity result of the bus.

[0009] Based on the location validity results, the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected.

[0010] According to another aspect of this application, a bus origin-destination passenger flow data processing device is provided, the device comprising:

[0011] The data acquisition module is used to acquire passenger pick-up and drop-off data at bus stops, origin-destination pairing data, and bus operation benchmark data; wherein, the bus operation benchmark data includes electronic waybill data and vehicle positioning data;

[0012] The feature matching module is used to split the origin-destination pairing data according to the shift information in the electronic waybill data, and to re-match the origin-destination pairing data based on the passenger body shape and clothing characteristics collected during the same shift's operating period.

[0013] The positioning validity result determination module is used to determine, for each shift, whether there is vehicle positioning data that matches the door opening and closing time information in the passenger pick-up and drop-off data at the station and the vehicle positioning data within a preset time window, and to obtain the positioning validity result of the bus.

[0014] The passenger pick-up and drop-off station information correction module is used to correct the passenger pick-up and drop-off station information in the station pick-up and drop-off data based on the location validity result.

[0015] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0016] One or more processors;

[0017] Memory, used to store one or more programs;

[0018] When one or more programs are executed by one or more processors, the one or more processors implement any of the bus origin-destination passenger flow data processing methods provided in the embodiments of this application.

[0019] According to another aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements any of the bus origin-destination passenger flow data processing methods provided in the embodiments of this application.

[0020] According to another aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the bus origin-destination passenger flow data processing methods provided in the embodiments of this application.

[0021] This application acquires bus station passenger pick-up and drop-off data, origin-destination pairing data, and bus operation baseline data. The bus operation baseline data includes electronic route sheet data and onboard location data. Based on the trip information in the electronic route sheet data, the origin-destination pairing data is split and processed. Then, based on passenger body shape and clothing characteristics collected during the same trip's operating hours, the origin-destination pairing data undergoes re-feature matching processing. For each trip, based on the door opening and closing time information in the station passenger pick-up and drop-off data and the onboard location data, it is determined whether there is onboard location data matching the door opening and closing time information within a preset time window, obtaining the bus's location validity result. Based on the location validity result, the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected. This scheme, by re-feature matching the origin-destination pairing data for the same trip and correcting the passenger pick-up and drop-off station information based on the location validity result, improves the accuracy, usability, and consistency of bus origin-destination passenger flow data. It provides reliable data support for bus operation scheduling optimization, route planning, and passenger flow characteristic analysis. Attached Figure Description

[0022] Figure 1 This is a flowchart of a method for processing passenger flow data at bus origin and destination points according to Embodiment 1 of this application;

[0023] Figure 2 This is a flowchart of a method for processing passenger flow data at bus origin and destination points according to Embodiment 2 of this application;

[0024] Figure 3 This is a schematic diagram of a bus origin-destination passenger flow data processing device according to Embodiment 3 of this application;

[0025] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the bus origin and destination passenger flow data processing method of Embodiment 4 of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Furthermore, it should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of relevant data such as station passenger pick-up and drop-off data, origin-destination pairing data, and public transport operation benchmark data involved in the technical solution of this application have all been authorized by users and have undergone relevant de-identification processing, comply with the provisions of relevant laws and regulations, and do not violate public order and good morals.

[0029] Example 1

[0030] Figure 1 This is a flowchart illustrating a method for processing passenger flow data at bus origin and destination points according to Embodiment 1 of this application. This embodiment is applicable to situations involving the management of passenger flow data at bus origin and destination points, and can be executed by a bus origin and destination point passenger flow data processing device. This device can be implemented in hardware and / or software and can be configured in a computer device, such as a server. Figure 1 As shown, the method includes:

[0031] S110. Obtain passenger pick-up and drop-off data, origin-destination pairing data, and bus operation benchmark data for buses; wherein, the bus operation benchmark data includes electronic waybill data and vehicle positioning data.

[0032] The data includes: Station boarding / alighting data, raw data recording passenger boarding and alighting at various bus stops, which may include route number, license plate number, door opening / closing time, number of passengers boarding, number of passengers alighting, and boarding / alighting stops. Each stop generates a record, reflecting the real-time passenger flow at a single stop. Origin / destination pairing data is complete travel chain data generated by matching passenger body shape and clothing characteristics. This may include passenger ID (identification), boarding stop, alighting stop, and travel time. After a bus arrives at its final stop, all boarding / alighting details collected for that trip are matched against passenger body shape and clothing characteristics to generate individual passenger boarding and alighting stop information, i.e., OD pairing data, fully reflecting the passenger's travel trajectory. Station boarding / alighting data and origin / destination pairing data can be collected using onboard OD collection devices, such as sensors and cameras. Bus operation benchmark data is a collective term for multi-source auxiliary data used to verify, correct, and supplement OD passenger flow data. To achieve precise management, bus operation benchmark data may include electronic waybill data and onboard positioning data. Electronic waybill data (operational data) mainly records the departure time, arrival time, route information, and license plate number of each vehicle for each shift, serving as the basis for shift division and data filtering. Vehicle location data mainly records the real-time location information of the vehicle, used to correct passenger pick-up and drop-off points, and may include timestamps, latitude and longitude information, etc.

[0033] Optionally, after obtaining the bus station pick-up and drop-off data, origin-destination pairing data, and bus operation benchmark data, the method further includes: determining the effective operating time of the bus for each trip based on the electronic waybill data, and removing the station pick-up and drop-off data and origin-destination pairing data based on the effective operating time to obtain effective station pick-up and drop-off data and effective origin-destination pairing data.

[0034] Since passenger pick-up and drop-off data generated during non-operational periods (such as vehicle maintenance and dispatching) are not accurate passenger travel data and can easily interfere with passenger flow statistics, we use electronic waybills as a benchmark to extract the effective operating time periods for each vehicle and each trip. We then perform time-period filtering on both types of raw data: pick-up / drop-off data at stations and origin / destination pairing data. Specifically, we can verify whether the door opening / closing time of each record falls within the effective operating time period of the corresponding trip; pick-up / drop-off data records outside this time period are directly removed. We can also correlate the door opening / closing time of passenger boarding stations to determine if they fall within the corresponding operating time period, removing origin / destination pairing records outside this time period. By eliminating invalid interference items at the data source, we ensure that all subsequent data processed is valid data within the operating time periods.

[0035] S120. Based on the shift information in the electronic waybill data, the origin-destination pairing data is split and processed, and based on the passenger body shape and clothing characteristics collected during the same shift's operating period, the origin-destination pairing data is re-matched.

[0036] The shift information is a key element in the electronic waybill data, uniquely identifying a complete vehicle operation task, such as shift information 001. The operating period for the same shift is the valid time interval defined in the electronic waybill data for a single shift. Passenger posture and clothing characteristics are feature vectors extracted from images of passengers' posture and clothing collected by onboard cameras and other equipment. These may include head contour, hairstyle texture, shoulder width, head-to-shoulder ratio, hairstyle, height, backpack, clothing color, and other posture and clothing features. It should be noted that passenger posture and clothing characteristics are not facial features. The collection of passenger posture and clothing characteristics is limited to the interior space of the bus compartment during bus operations, specifically the field of view of the onboard equipment above the front and rear doors of the bus, and is not within the scope of public area monitoring. Furthermore, the collected images are overall scene images including passenger shapes and the compartment environment; posture and clothing characteristics are non-biometric overall appearance descriptions and cannot be used alone or in combination to identify a specific individual, nor do they contain any facial feature information. The collected data is used only for the correlation matching of passenger boarding and alighting behavior and passenger flow statistical analysis within this trip. The data storage period is consistent with the trip's operating cycle and does not involve the long-term retention of passenger personal information or cross-scenario application, which complies with the compliance requirements for public transportation operation data collection.

[0037] Due to positioning errors that prevent accurate identification of shift end points (such as signal loss at underground depots or confusion regarding the attribution of multiple stops), passenger body and clothing characteristics from multiple shifts are mixed for matching, leading to OD (Original Department) pairing errors. Therefore, this paper addresses this issue by using shifts defined in the electronic waybill data as independent units and performing secondary matching of passenger body and clothing characteristics based on shift boundaries to correct OD pairing results. Specifically, the original OD pairing data is split by shift, and matching is performed only on passenger body and clothing characteristics collected within the same shift's operating hours, preventing cross-shift feature associations. Furthermore, OD records from different shifts in the original matching can be deleted, and feature matching is re-performed within the corresponding shift to generate new OD pairing data. If passenger body and clothing characteristics within the same shift cannot be matched due to ambiguity or missing information, they are marked as unmatched OD records, with a reserved interface for future supplementation. By constraining shift boundaries, the accuracy of OD pairing is significantly improved, resolving the cross-shift matching distortion problem.

[0038] Optionally, after re-matching the origin-destination pairing data based on passenger body shape and clothing characteristics collected during the same operating period, the process further includes: traversing the processed origin-destination pairing data, filtering records where the boarding and alighting stations are the same to obtain invalid boarding and alighting records; and updating the processed origin-destination pairing data and the station boarding and alighting data based on the invalid boarding and alighting records.

[0039] Because intermediate stations may have non-boarding scenarios such as passengers asking questions and temporary boarding / alighting, invalid passenger flow data is generated at the same station, interfering with the actual passenger flow statistics. Therefore, based on the OD pairing data after secondary matching, invalid records of boarding / alighting at the same station are identified and removed, and the station passenger flow data is adjusted accordingly. Specifically, all OD pairing data is traversed, and records where the boarding and alighting stations are the same are selected and identified as invalid boarding / alighting records and removed; the number of passengers boarding and alighting at the corresponding station is reduced by 1 to ensure consistency between the station passenger flow data and the OD pairing data.

[0040] Optionally, after re-matching the origin-destination pairing data based on passenger body shape and clothing characteristics collected during the same operating period, the method further includes: traversing the processed origin-destination pairing data, filtering out records where the boarding station is the first station and the alighting station is the last station; determining the number of records to be removed based on the ticketing type of the route, marking the records as invalid based on the number of records to be removed, and updating the passenger information for the first station boarding and the passenger information for the last station alighting in the station boarding and alighting data.

[0041] The ticketing types for bus routes can include self-service ticketing and manned ticketing. For self-service ticketing routes, only driver data needs to be removed, while for manned ticketing routes, both driver and conductor data need to be removed.

[0042] Because passenger flow data is mixed with driver and conductor boarding / alighting data, the statistical results are distorted. Therefore, by combining the ticketing method of the route, driver and conductor data can be accurately identified and removed, and passenger flow at the corresponding stations can be adjusted simultaneously. Specifically, the OD pairing data after re-feature matching is traversed, and records with boarding station as the first station and alighting station as the last station are selected for the entire journey (drivers and conductors usually follow the vehicle throughout the journey); the number of records to be removed is determined according to the ticketing method (1 record is removed for unmanned ticketing and 2 records are removed for ticketing with conductors), and the corresponding OD records are marked as invalid. At the same time, the number of passengers boarding at the first station (decrease by 1) and the number of passengers alighting at the last station (decrease by 1) are adjusted simultaneously to ensure passenger flow data balance.

[0043] S130. For each bus trip, based on the door opening and closing time information in the passenger pick-up and drop-off data at the station and the vehicle positioning data, determine whether there is vehicle positioning data that matches the door opening and closing time information within a preset time window, and obtain the positioning validity result of the bus.

[0044] Each bus trip represents a complete operational task executed by the bus according to the electronic waybill data, from departure from the first station to arrival at the last station. The preset time window is manually set, representing the maximum allowable range of time deviation to tolerate equipment clock errors and network latency; this embodiment does not specifically limit this. The positioning validity result characterizes the determination of whether the onboard positioning data is usable, providing a basis for subsequent strategy selection. The positioning validity result can include valid and invalid.

[0045] S140. Based on the location validity result, the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected.

[0046] Due to signal obstruction in areas such as tunnels, overpasses, and underpasses, or abnormal situations such as network transmission failures and equipment malfunctions, the uploaded passenger pick-up and drop-off points may differ from the actual stops, affecting the accuracy of OD matching and passenger flow statistics. Therefore, scenarios with valid positioning and scenarios with missing positioning may occur. It is necessary to correct the passenger pick-up and drop-off point information in the station data based on the positioning validity results. Specifically, a dual strategy of "prioritizing positioning signals and smoothing with empirical values" can be adopted, combined with passenger pick-up and drop-off times to correct station attribution.

[0047] Optionally, the station passenger boarding and alighting data includes boarding passenger information and alighting passenger information. Correspondingly, it also includes: for each trip, based on the station passenger flow balance principle, determining the number of passengers remaining at the current station according to the boarding passenger information, alighting passenger information, and remaining passenger information at the previous station, and determining whether the remaining passenger information is negative; if the remaining passenger information is negative, summing the absolute value of the remaining passenger information with the boarding passenger information at the first station to obtain the updated boarding passenger information at the first station; based on the updated boarding passenger information at the first station, re-executing the process of determining the remaining passenger information at the current station according to the boarding passenger information, alighting passenger information, and remaining passenger information at the previous station, until the remaining passenger information at all stations is non-negative.

[0048] The station passenger flow balance principle satisfies the physical conservation constraint, meaning the number of passengers in the carriage cannot be negative and must eventually reach zero. The number of passengers remaining at the current station is the actual number of passengers in the carriage when the vehicle leaves the current station. The number of passengers remaining at the previous station is the number of passengers already in the carriage before the vehicle arrived at the current station.

[0049] Because the driver shuts off the main power after the vehicle arrives at the terminal station, causing a power outage for the OD (Original Departure) equipment, it is impossible to collect passenger boarding data during the power outage period. Simultaneously, the passenger alighting data at the terminal station is incomplete, leading to an imbalance in passenger flow data. Therefore, a recursive calculation logic is adopted to supplement the missing data based on the principle of station passenger flow balance, ensuring that the cumulative passenger boarding volume and cumulative passenger alighting volume within a given trip are consistent.

[0050] Specifically, starting from the first stop, the number of passengers remaining at each stop is calculated sequentially, initially starting at 0. The formula is: Number of passengers remaining at the current stop = Number of passengers remaining at the previous stop + Number of passengers boarding at the current stop - Number of passengers alighting at the current stop. If the calculated number of passengers remaining at a certain stop is negative, it is determined that the number of passengers boarding at the first stop was missing. The absolute value of the negative value is added to the number of passengers boarding at the first stop, and the recursive calculation is repeated until the number of passengers remaining at all stops is non-negative. By default, the number of passengers alighting at the last stop is equal to the number of passengers remaining at the second-to-last stop, forcibly ensuring that the cumulative number of passengers boarding in this trip equals the cumulative number of passengers alighting, achieving logical balance in passenger flow data. Through recursive calculation and synchronous adjustment of passenger flow, the balance of passenger flow data within the trip is ensured, guaranteeing the rigor of the data logic.

[0051] This application embodiment acquires bus station passenger pick-up and drop-off data, origin-destination pairing data, and bus operation benchmark data. The bus operation benchmark data includes electronic route sheet data and onboard positioning data. Based on the trip information in the electronic route sheet data, the origin-destination pairing data is split and processed. Then, based on passenger body shape and clothing characteristics collected during the same trip's operating hours, the origin-destination pairing data undergoes re-feature matching processing. For each trip, based on the door opening and closing time information in the station passenger pick-up and drop-off data and the onboard positioning data, it is determined whether there is onboard positioning data matching the door opening and closing time information within a preset time window, obtaining the bus's positioning validity result. Based on the positioning validity result, the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected. This scheme, by re-feature matching the origin-destination pairing data for the same trip and correcting the passenger pick-up and drop-off station information based on the positioning validity result, improves the accuracy, usability, and consistency of bus origin-destination passenger flow data. It provides reliable data support for bus operation scheduling optimization, route planning, and passenger flow characteristic analysis.

[0052] Example 2

[0053] Figure 2This is a flowchart of a bus origin-destination passenger flow data processing method according to Embodiment 2 of this application. Based on the technical solutions of the above embodiments, this embodiment refines the step of "correcting the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data according to the positioning validity result" to: "If the positioning validity result is valid, a positioning priority strategy is adopted. Based on the spatial relationship between the stations corresponding to the route information in the vehicle positioning data and the electronic waybill data, the target passenger pick-up and drop-off stations of the bus are determined, and the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected according to the target passenger pick-up and drop-off stations; if the positioning validity result is invalid, an empirical value smoothing strategy is adopted. Based on the preset empirical value of travel time between stations, the station passenger pick-up and drop-off data, and the electronic waybill data, the target passenger pick-up and drop-off stations of the bus are determined, and the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected according to the target passenger pick-up and drop-off stations." It should be noted that for parts not detailed in this embodiment, please refer to the relevant descriptions in other embodiments. Figure 2 As shown, the method includes:

[0054] S210. Obtain passenger pick-up and drop-off data, origin-destination pairing data, and bus operation benchmark data for buses; wherein, the bus operation benchmark data includes electronic waybill data and vehicle positioning data.

[0055] S220. Based on the shift information in the electronic waybill data, the origin-destination pairing data is split and processed, and based on the passenger body shape and clothing characteristics collected during the same shift's operating period, the origin-destination pairing data is re-matched.

[0056] S230. For each bus trip, based on the door opening and closing time information in the passenger pick-up and drop-off data at the station and the vehicle positioning data, determine whether there is vehicle positioning data that matches the door opening and closing time information within a preset time window, and obtain the positioning validity result of the bus.

[0057] S240. If the location validity result is valid, a location priority strategy is adopted. Based on the spatial relationship between the stations corresponding to the route information in the vehicle location data and the electronic waybill data, the target passenger pick-up and drop-off stations of the bus are determined, and the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected according to the target passenger pick-up and drop-off stations.

[0058] The positioning priority strategy prioritizes the use of GPS spatial positioning to determine stations. The spatial relationships between stations can include topological relationships such as the distance between stations on the line and the order of stations.

[0059] Optionally, a location-first strategy is adopted to determine the target passenger pick-up and drop-off points for buses based on the spatial relationship between the stations corresponding to the route information in the vehicle positioning data and the electronic route slip data. This includes: calculating the distance between the vehicle positioning data and the stations corresponding to the route information in the electronic route slip data, determining the nearest station and offset distance of the bus; and determining the nearest station as the target passenger pick-up and drop-off point of the bus if the offset distance is less than or equal to a preset distance threshold.

[0060] Specifically, in scenarios where positioning is effective, the door opening and closing times of each passenger pick-up and drop-off record can be extracted, correlated with concurrent vehicle positioning data, to determine the actual location of the vehicle. By spatially matching real-time GPS coordinates with route station coordinates, the actual stopping station of the vehicle can be determined, and the passenger pick-up and drop-off station information in the station pick-up and drop-off data can be corrected accordingly.

[0061] S250. If the location validity result is invalid, an empirical value smoothing strategy is adopted. Based on the preset empirical value of travel time between stations, the station passenger pick-up and drop-off data and the electronic waybill data, the target passenger pick-up and drop-off stations of the bus are determined, and the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected according to the target passenger pick-up and drop-off stations.

[0062] The empirical value smoothing strategy is based on historical statistical patterns of travel time to estimate station locations. Preset empirical values ​​for travel time between stations are generated based on historical operational data and are used for station correction in scenarios with missing location signals.

[0063] Optionally, an empirical value smoothing strategy is adopted, based on preset empirical values ​​of travel time between stations, the station passenger pick-up and drop-off data, and the electronic route slip data, to determine the target passenger pick-up and drop-off stations for the bus. This includes: determining the bus's travel time based on door opening and closing time information in the station passenger pick-up and drop-off data and departure time information in the electronic route slip data; determining the cumulative travel time of each station corresponding to the route information in the electronic route slip data based on the preset empirical values ​​of travel time between stations, and determining the target station interval for the bus based on the matching relationship between the travel time and the cumulative travel time of each station; and determining the target passenger pick-up and drop-off stations for the bus using a time series smoothing algorithm based on the preset empirical values ​​of travel time between stations, the travel time, and the target station interval.

[0064] Specifically, in scenarios where location is missing, the average travel time between stations (empirical value) can be calculated based on the historical operation data of the route. Combined with the departure time and passenger pick-up and drop-off times, the station intervals of the vehicle at the time of passenger pick-up and drop-off can be estimated. The pick-up and drop-off stations can be smoothed through time series to ensure that the station affiliation is consistent with the travel time sequence.

[0065] Optionally, determining the target passenger pick-up and drop-off points for the bus using a time series smoothing algorithm, based on the preset experience value of travel time between stations, the travel duration already completed, and the target station interval, includes: determining the relative position ratio of the travel duration within the target station interval based on the preset experience value of travel time between stations, the travel duration already completed, and the target station interval; obtaining the passenger pick-up and drop-off probability distribution of each station within the target station interval statistically analyzed over a preset time period; and determining the passenger pick-up and drop-off point with the highest probability as the target passenger pick-up and drop-off point for the bus based on the relative position ratio and the passenger pick-up and drop-off probability distribution.

[0066] Specifically, the travel time of the target station interval can be determined based on the empirical value of the travel time between preset stations; the difference between the travel time already traveled and the cumulative travel time of the starting station in the target station interval can be calculated to obtain the interval offset time; the interval offset time can be divided by the interval travel time to obtain the relative position ratio; then the passenger pick-up and drop-off probability distribution of each station in the target station interval can be obtained according to the preset time period; based on the relative position ratio and the passenger pick-up and drop-off probability distribution, the passenger pick-up and drop-off station with the highest probability can be determined as the target passenger pick-up and drop-off station for the bus.

[0067] In one optional implementation, the time interval for the bus to stop at the first station can be determined based on the electronic waybill data; feature matching processing can be performed on all passenger posture and clothing characteristics collected within the time interval; and the passenger boarding / alighting data and the origin / destination pairing data can be updated based on the feature matching processing results.

[0068] Because the first stop has a long stop time, there is a possibility of passengers from the previous trip getting off and passengers boarding in the current trip being mixed up, leading to incorrect trip assignments and distorted passenger flow statistics (e.g., drivers and cleaning staff getting on and off at the same stop). Therefore, using the time interval between vehicle entry and exit from the first stop as the boundary, passenger characteristics within this interval are subjected to secondary pairing to separate trip assignments. Specifically, the time of the bus entering and leaving the first stop is extracted to determine the first stop stop time interval; all passenger body shape and clothing characteristics collected within this interval are paired. If a passenger's exit characteristic matches another passenger's boarding characteristic (i.e., getting on and off at the same stop), it is determined to be a non-real passenger or a passenger from the previous trip, and the corresponding passenger entry / exit record and OD pairing data are removed; the number of people corresponding to the remaining unmatched boarding characteristics is taken as the real number of passengers boarding at the first stop of this trip, and the station's passenger entry / exit data and subsequent passenger flow calculation base are updated simultaneously.

[0069] This application embodiment acquires bus station passenger pick-up and drop-off data, origin-destination pairing data, and bus operation benchmark data. The bus operation benchmark data includes electronic route sheet data and onboard positioning data. Based on the trip information in the electronic route sheet data, the origin-destination pairing data is split and processed. Then, based on passenger body shape and clothing characteristics collected during the same trip's operating hours, the origin-destination pairing data undergoes re-feature matching processing. For each trip, based on the door opening and closing time information in the station passenger pick-up and drop-off data and the onboard positioning data, it is determined whether there is onboard positioning data matching the door opening and closing time information within a preset time window, thus obtaining the bus's positioning validity result. Based on the positioning validity result, the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected. This solution, by re-feature matching the origin-destination pairing data for the same trip and correcting the passenger pick-up and drop-off station information based on the positioning validity result, uses electronic route sheet data as the core benchmark and integrates positioning signals, empirical values, and feature matching technologies, improving the accuracy, usability, and consistency of bus origin-destination passenger flow data. It provides reliable data support for optimizing public transport operation scheduling, route planning, and passenger flow characteristic analysis.

[0070] Example 3

[0071] Figure 3 This is a schematic diagram of a bus origin-destination passenger flow data processing device according to Embodiment 3 of this application. This embodiment is applicable to situations involving the management of bus origin-destination passenger flow data. The bus origin-destination passenger flow data processing device can be implemented in hardware and / or software, and can be configured in a computer device, such as a server. Figure 3 As shown, the device includes:

[0072] The data acquisition module 310 is used to acquire passenger pick-up and drop-off data at bus stops, origin-destination pairing data, and bus operation benchmark data; wherein, the bus operation benchmark data includes electronic waybill data and vehicle positioning data;

[0073] The feature matching module 320 is used to split the origin-destination pairing data according to the shift information in the electronic waybill data, and to re-match the origin-destination pairing data based on the passenger body shape and clothing characteristics collected during the same shift's operating period.

[0074] The positioning validity result determination module 330 is used to determine, for each shift, whether there is vehicle positioning data that matches the door opening and closing time information in the passenger pick-up and drop-off data at the station and the vehicle positioning data within a preset time window, and to obtain the positioning validity result of the bus.

[0075] The passenger pick-up and drop-off station information correction module 340 is used to correct the passenger pick-up and drop-off station information in the station pick-up and drop-off data based on the location validity result.

[0076] Optional, the passenger pick-up and drop-off station information correction module 340 includes:

[0077] The effective result correction unit is used to, if the positioning validity result is valid, adopt a positioning priority strategy, determine the target passenger pick-up and drop-off points of the bus based on the spatial relationship between each station corresponding to the route information in the vehicle positioning data and the electronic waybill data, and correct the passenger pick-up and drop-off point information in the station passenger pick-up and drop-off data according to the target passenger pick-up and drop-off points.

[0078] The invalid result correction unit is used to, if the positioning validity result is invalid, adopt an empirical value smoothing strategy, determine the target passenger pick-up and drop-off stations of the bus based on the preset empirical value of travel time between stations, the passenger pick-up and drop-off data of the stations and the electronic waybill data, and correct the passenger pick-up and drop-off station information in the passenger pick-up and drop-off data according to the target passenger pick-up and drop-off stations.

[0079] Optional, effective result correction unit, including:

[0080] The station and distance determination subunit is used to calculate the distance between the vehicle positioning data and each station corresponding to the route information in the electronic waybill data, and to determine the nearest station and offset distance of the bus.

[0081] The first target passenger pick-up and drop-off station determination subunit is used to determine the nearest station as the target passenger pick-up and drop-off station for the bus when the offset distance is less than or equal to a preset distance threshold.

[0082] Optional, invalid result correction unit, including:

[0083] The unit for determining the travel time is used to determine the travel time of the bus based on the door opening and closing time information in the passenger pick-up and drop-off data at the station and the departure time information in the electronic waybill data.

[0084] The target station interval determination subunit is used to determine the cumulative travel time of each station corresponding to the route information in the electronic waybill data based on the preset experience value of travel time between stations, and to determine the target station interval of the bus based on the matching relationship between the travel time and the cumulative travel time of each station.

[0085] The second target passenger pick-up and drop-off station determination subunit is used to determine the target passenger pick-up and drop-off stations of the bus based on the preset travel time experience value between stations, the travel time already traveled, and the target station interval using a time series smoothing algorithm.

[0086] Optionally, the second target passenger pick-up and drop-off point is determined as a sub-unit, specifically used for:

[0087] Based on the preset travel time experience value between stations, the travel time already traveled, and the target station interval, determine the relative position ratio of the travel time within the target station interval;

[0088] Obtain the probability distribution of passenger pick-up and drop-off at each station within the target station interval for a preset time period;

[0089] Based on the relative position ratio and the passenger boarding / alighting probability distribution, the passenger boarding / alighting station with the highest probability is determined as the target passenger boarding / alighting station for the bus.

[0090] Optionally, the station passenger boarding and alighting data includes passenger boarding information and passenger alighting information; correspondingly, the device further includes:

[0091] The module for determining the number of passengers remaining at a station is used to determine the number of passengers remaining at the current station for each trip based on the principle of passenger flow balance at the station, according to the number of passengers boarding at the current station, the number of passengers alighting at the current station, and the number of passengers remaining at the previous station, and to determine whether the number of passengers remaining at the station is negative.

[0092] The module for determining the number of passengers boarding at the first station is used to sum the absolute value of the number of passengers holding the vehicle and the number of passengers boarding at the first station when the number of passengers holding the vehicle is determined to be negative, so as to obtain the updated number of passengers boarding at the first station.

[0093] The recursive calculation module is used to re-execute the calculation based on the updated boarding information at the first station, the boarding information at the current station, the alighting information at the current station, and the remaining passengers information at the previous station to determine the remaining passengers information at the current station, until the remaining passengers information at all stations are non-negative.

[0094] Optionally, the device further includes,

[0095] The driver and passenger data removal module is used to re-match the origin-destination pairing data based on passenger body shape and clothing characteristics collected during the same operating period. After reprocessing the origin-destination pairing data, it traverses the processed origin-destination pairing data to filter out records where the boarding station is the first station and the alighting station is the last station. Based on the ticketing type of the route, it determines the number of records to be removed and marks the records as invalid according to the number of records to be removed. It also updates the passenger information for the first station and the passenger information for the last station in the station boarding and alighting data.

[0096] This application embodiment acquires bus station passenger pick-up and drop-off data, origin-destination pairing data, and bus operation benchmark data. The bus operation benchmark data includes electronic route sheet data and onboard positioning data. Based on the trip information in the electronic route sheet data, the origin-destination pairing data is split and processed. Then, based on passenger body shape and clothing characteristics collected during the same trip's operating hours, the origin-destination pairing data undergoes re-feature matching processing. For each trip, based on the door opening and closing time information in the station passenger pick-up and drop-off data and the onboard positioning data, it is determined whether there is onboard positioning data matching the door opening and closing time information within a preset time window, obtaining the bus's positioning validity result. Based on the positioning validity result, the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected. This scheme, by re-feature matching the origin-destination pairing data for the same trip and correcting the passenger pick-up and drop-off station information based on the positioning validity result, improves the accuracy, usability, and consistency of bus origin-destination passenger flow data. It provides reliable data support for bus operation scheduling optimization, route planning, and passenger flow characteristic analysis.

[0097] The bus origin-destination passenger flow data processing device provided in this application embodiment can execute the bus origin-destination passenger flow data processing method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing each bus origin-destination passenger flow data processing method.

[0098] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0099] Example 4

[0100] Figure 4 This is a schematic diagram of the structure of an electronic device 410 implementing the bus origin-destination passenger flow data processing method according to an embodiment of this application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0101] like Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0102] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0103] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the bus origin-destination passenger flow data processing method.

[0104] In some embodiments, the bus origin-destination passenger flow data processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the bus origin-destination passenger flow data processing method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured as the bus origin-destination passenger flow data processing method by any other suitable means (e.g., by means of firmware).

[0105] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable public transport origin-destination passenger flow data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0109] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0110] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0111] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0112] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for processing passenger flow data at bus origin and destination points, characterized in that, include: The system acquires passenger pick-up and drop-off data at bus stops, origin-destination pairing data, and bus operation benchmark data; wherein the bus operation benchmark data includes electronic waybill data and vehicle positioning data. Based on the shift information in the electronic waybill data, the origin-destination pairing data is split and processed, and based on the passenger body shape and clothing characteristics collected during the same shift's operating period, the origin-destination pairing data is re-matched. For each bus trip, based on the door opening and closing time information in the passenger pick-up and drop-off data at the station and the vehicle positioning data, it is determined whether there is vehicle positioning data that matches the door opening and closing time information within a preset time window, thus obtaining the positioning validity result of the bus. If the location validity result is valid, a location priority strategy is adopted. Based on the spatial relationship between each station corresponding to the route information in the vehicle location data and the electronic waybill data, the target passenger pick-up and drop-off stations of the bus are determined, and the passenger pick-up and drop-off station information in the station pick-up and drop-off data is corrected according to the target passenger pick-up and drop-off stations. The spatial relationship between each station includes the distance between stations and the station order of each station on the route. If the location validity result is invalid, an empirical value smoothing strategy is adopted. Based on the preset empirical value of travel time between stations, the station passenger pick-up and drop-off data, and the electronic waybill data, the target passenger pick-up and drop-off stations of the bus are determined, and the passenger pick-up and drop-off station information in the station passenger pick-up and drop-off data is corrected according to the target passenger pick-up and drop-off stations.

2. The method according to claim 1, characterized in that, A location-first strategy is adopted to determine the target passenger pick-up and drop-off points for buses based on the spatial relationships between the stations corresponding to the route information in the vehicle positioning data and the electronic waybill data, including: Calculate the distance between the vehicle positioning data and each station corresponding to the route information in the electronic waybill data to determine the nearest station and offset distance of the bus. If the offset distance is less than or equal to a preset distance threshold, the nearest station will be determined as the target passenger pick-up and drop-off station for the bus.

3. The method according to claim 1, characterized in that, An experience-based smoothing strategy is employed, based on preset experience values ​​for travel time between stations, passenger pick-up and drop-off data at the stations, and electronic waybill data, to determine the target passenger pick-up and drop-off stations for buses, including: Based on the door opening and closing time information in the passenger pick-up and drop-off data at the stations and the departure time information in the electronic waybill data, the travel time of the bus is determined. Based on the preset experience value of travel time between stations, the cumulative travel time of each station corresponding to the route information in the electronic waybill data is determined, and the target station interval of the bus is determined based on the matching relationship between the travel time and the cumulative travel time of each station. Using a time series smoothing algorithm, the target passenger pick-up and drop-off points for buses are determined based on the empirical values ​​of travel time between preset stations, the travel time already traveled, and the target station interval.

4. The method according to claim 3, characterized in that, The step of determining the target passenger pick-up and drop-off points for buses using a time series smoothing algorithm, based on the preset experience value of travel time between stations, the travel time already completed, and the target station interval, includes: Based on the preset travel time experience value between stations, the travel time already traveled, and the target station interval, determine the relative position ratio of the travel time within the target station interval; Obtain the probability distribution of passenger pick-up and drop-off at each station within the target station interval for a preset time period; Based on the relative position ratio and the passenger boarding / alighting probability distribution, the passenger boarding / alighting station with the highest probability is determined as the target passenger boarding / alighting station for the bus.

5. The method according to claim 1, characterized in that, The passenger boarding and alighting data at the station includes information on the number of passengers boarding and alighting. Correspondingly, the method also includes: For each trip, based on the principle of passenger flow balance at each station, the number of passengers boarding at the current station, the number of passengers alighting at the current station, and the number of passengers remaining at the previous station are used to determine the number of passengers remaining at the current station, and it is determined whether the number of passengers remaining is negative. If the number of passengers remaining in the vehicle is determined to be negative, the absolute value of the number of passengers remaining in the vehicle is summed with the number of passengers boarding at the first station to obtain the updated number of passengers boarding at the first station. Based on the updated boarding passenger information at the first station, the process is repeated to determine the number of passengers remaining at the current station based on the boarding passenger information, the alighting passenger information, and the remaining passenger information at the previous station, until the number of passengers remaining at all stations is a non-negative value.

6. The method according to claim 1, characterized in that, After re-matching the origin-destination pairing data based on passenger body shape and clothing characteristics collected during the same operating period, the method further includes: The processed origin-destination pairing data is traversed to filter out the entire origin-destination records where the boarding station is the first station and the alighting station is the last station. Based on the ticketing type of the route, determine the number of passengers to be removed, and mark the entire origin and destination records as invalid according to the number of passengers removed, and update the passenger information of the first station boarding and the passenger information of the last station alighting in the station boarding and alighting data.

7. A device for processing passenger flow data at bus origin and destination points, characterized in that, include: The data acquisition module is used to acquire passenger pick-up and drop-off data at bus stops, origin-destination pairing data, and bus operation benchmark data; wherein, the bus operation benchmark data includes electronic waybill data and vehicle positioning data; The feature matching module is used to split the origin-destination pairing data according to the shift information in the electronic waybill data, and to re-match the origin-destination pairing data based on the passenger body shape and clothing characteristics collected during the same shift's operating period. The positioning validity result determination module is used to determine, for each shift, whether there is vehicle positioning data that matches the door opening and closing time information in the passenger pick-up and drop-off data at the station and the vehicle positioning data within a preset time window, and to obtain the positioning validity result of the bus. The passenger pick-up and drop-off station information correction module includes: The effective result correction unit is used to, if the positioning validity result is valid, adopt a positioning priority strategy, determine the target passenger pick-up and drop-off points of the bus based on the spatial relationship between each station corresponding to the route information in the vehicle positioning data and the electronic waybill data, and correct the passenger pick-up and drop-off point information in the station passenger pick-up and drop-off data according to the target passenger pick-up and drop-off points; wherein, the spatial relationship between each station includes the distance between stations and the station order of each station on the route. The invalid result correction unit is used to, if the positioning validity result is invalid, adopt an empirical value smoothing strategy, determine the target passenger pick-up and drop-off stations of the bus based on the preset empirical value of travel time between stations, the passenger pick-up and drop-off data of the stations and the electronic waybill data, and correct the passenger pick-up and drop-off station information in the passenger pick-up and drop-off data according to the target passenger pick-up and drop-off stations.

8. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the bus origin-destination passenger flow data processing method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the bus origin-destination passenger flow data processing method as described in any one of claims 1-6.

Images