A vehicle type trajectory recognition method and system based on mobile phone signaling data

Abstract

The present invention discloses a vehicle type trajectory identification method and system based on mobile phone signaling data, comprising the following steps: obtaining mobile phone signaling data from an operator to generate a vehicle trajectory point sequence; determining and eliminating abnormal trajectory points based on the spatial distance and time interval between trajectory points, performing spatiotemporal interpolation to complete long-term breakpoints, and sorting them by time; extracting vehicle trajectory statistical features, including total travel distance, total number of stops, and total parking time; mapping parking points to passenger, freight, and mixed parking areas, calculating passenger and freight feature scores for vehicles in mixed parking areas, and determining passenger or freight transport after comprehensive scoring; for vehicles determined to be passenger transport, first identifying buses based on trajectory repetition rate and the maximum number of mobile phones connected in the vehicle, and then calculating travel time and spatial regularity indicators to distinguish private cars from taxis, with taxis including online ride-hailing vehicles; and outputting the classification results of each vehicle type and the corresponding complete trajectory sequence.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation technology, and in particular relates to a vehicle type trajectory recognition method and system based on mobile phone signaling data. By analyzing and processing mobile phone signaling data, the trajectories of vehicles of different types in a complex fusion area can be accurately identified. Background Art

[0002] In the development of intelligent transportation systems, accurate identification and analysis of vehicle trajectories is a key foundation for numerous applications, including traffic flow optimization, intelligent navigation, and traffic safety management. Traditional vehicle trajectory identification methods face numerous challenges in complex and integrated areas, such as commercial districts, transportation hubs, and port areas in urban centers, where traffic volumes are high, vehicle types are diverse, and trajectories are complex.

[0003] Existing vehicle trajectory recognition methods often rely on specific sensor devices, such as GPS locators and on-board On-Board Devices (OBD). These methods not only require the installation of additional hardware, which is costly, but also fail to effectively identify vehicles without such equipment. Furthermore, some trajectory recognition methods based on video surveillance are limited by the coverage of monitoring equipment and environmental factors (such as weather and lighting), making it difficult to achieve comprehensive and accurate vehicle trajectory recognition in complex convergence areas.

[0004] Mobile phones are widely used in our daily lives, and the signaling data they generate contains a wealth of location and movement information. However, research on using mobile phone signaling data for vehicle-type trajectory recognition is relatively limited, and suffers from issues such as low recognition accuracy and inability to effectively process complex fusion regional data.

[0005] Existing technologies using mobile phone signaling data primarily focus on activity chain reconstruction techniques based on human travel patterns (e.g., CN202210208596.9 and CN202311199605.3). However, relatively little research has been conducted on vehicles based on mobile phone signaling. Invention patent CN202311711150.9 describes a method for estimating the average number of passengers on a road section based on mobile phone signaling data, demonstrating the effectiveness of mobile phone signaling for identifying aggregated traffic trips. However, existing technologies have yet to address the problem of identifying vehicle trajectories based on their intended use, particularly for private cars, taxis, and freight vehicles, which are difficult to distinguish based solely on the number of passengers on board. Summary of the Invention

[0006] The purpose of this invention is to overcome the problems of high cost, limited coverage, and low recognition accuracy in the existing vehicle trajectory recognition methods, and to provide a vehicle-type trajectory recognition method and system based on mobile phone signaling data. The present invention uses mobile phone signaling data to achieve efficient and accurate identification of the trajectories of different types of vehicles, such as private cars, buses, taxis (online ride-hailing vehicles), and freight vehicles in complex integrated areas. In particular, it provides data support for the subsequent large-scale promotion and application of intelligent connected vehicle-road collaboration environments and dynamic traffic management based on vehicle types.

[0007] The purpose of the present invention is achieved through the following technical solutions:

[0008] A vehicle type trajectory recognition method based on mobile phone signaling data, comprising:

[0009] S1. Trajectory data generation: Obtain mobile phone signaling data from the operator and generate a vehicle trajectory point sequence based on the mobile phone signaling data;

[0010] S2. Data cleaning and completion: Based on the spatial distance and time interval between trajectory points, abnormal trajectory points are identified and removed, long-term breakpoints are completed through spatiotemporal interpolation, and sorted by time;

[0011] S3. Extracting vehicle trajectory statistical features: Divide the trajectory into segments based on the base station handover data, determine the parking points based on the speed and dwell time thresholds, and obtain the vehicle trajectory statistical features, including the total travel distance, total number of stops, and total parking time;

[0012] S4. Passenger and freight attribute determination: Map parking spots to passenger, freight, and mixed parking areas. Calculate passenger and freight attribute scores for vehicles in mixed parking areas. Determine passenger or freight based on the comprehensive score.

[0013] S5. Passenger transport vehicle classification: For vehicles identified as passenger transport, buses are first identified based on trajectory repetition rate and the maximum number of connected mobile phones in the vehicle. Travel time and spatial regularity indicators are then calculated to distinguish between private cars and taxis, including online ride-hailing vehicles.

[0014] S6. Result output: Output the classification results of each vehicle type and the corresponding complete trajectory point sequence.

[0015] Furthermore, step S1 includes:

[0016] S101. Mobile phone signaling data is used to record communication information between user equipment and base stations, including the International Mobile Subscriber Identity (IMSI), base station ID, timestamp, signal strength, latitude and longitude information, and event type information. Event types include location update, base station handover, call establishment, and call release.

[0017] S102, retaining location update, base station handover, base station ID, timestamp, and latitude and longitude information, and filtering out incomplete or abnormal mobile phone signaling data;

[0018] S103, query the location information of the base station according to the base station ID to form a base station location table ; Mobile phone signaling data Converted to location information, ;in, is the i-th data in the mobile phone signaling data; Indicates the timestamp of the i-th mobile phone signaling data, that is, the specific time of the mobile phone signaling data;

[0019] S104, each Base station location As a trajectory point , the trajectory point sequence of the generated vehicle is: ,in, , n represents the total number of trajectory points.

[0020] Furthermore, step S2 includes:

[0021] S201, set judgment conditions: if , then remove the trajectory points ;in, Represents trajectory points and The spatial distance is calculated as follows: Where R is the radius of the Earth, which is 6371 km; represents the time interval between adjacent trajectory points, , Indicates the upper limit of reasonable speed; 、 Respectively represent the timestamps of the i-th and i+1-th mobile phone signaling data; , n represents the total number of trajectory points;

[0022] S202: If there are long breakpoints longer than 10 minutes in the trajectory point sequence, the breakpoints are completed by time interpolation and base station position interpolation. The interpolation formula is as follows:

[0023] ;

[0024] in, and Respectively represent the base station position and timestamp of the completed interpolation;

[0025] S203, track point sequence T is sorted by time Sorting;

[0026] .

[0027] Furthermore, step S3 includes:

[0028] S301, identifying continuous trajectory segments based on base station switching data from mobile phone signaling data , each trajectory segment is defined as the path of the vehicle during continuous driving or stationary period, and the expression is as follows:

[0029] ;

[0030] in, , m represents the upper limit of the number of different trajectory segments into which the vehicle is divided;

[0031] If the time interval between two consecutive trajectory points , it is divided into different segments;

[0032] S302: Calculate the speed of the vehicle between adjacent trajectory points ,like Parking time , it is determined to be a parking point; S is used to represent the set of parking points, Represents trajectory points and spatial distance; Take 1-3m / s, Take 5-10 minutes;

[0033] S303, extract trajectory statistical features, including total movement distance Total number of stops , represents the total number of trajectory points in the trajectory point sequence that meet the parking conditions; the total parking time , which represents the total stay time between parking points.

[0034] Furthermore, step S4 includes:

[0035] S401: Analyze the parking location of the vehicle based on the mobile phone signaling data and divide the parking areas into the following three categories:

[0036] Passenger parking area , for passenger vehicles, including stations and airport parking areas;

[0037] Freight parking area , for freight vehicles, including port loading and unloading areas and logistics centers;

[0038] Mixed parking area , areas where both passenger and freight vehicles are allowed to park, including parking lots at integrated transportation hubs;

[0039] S402: Using the base station location information P, classify the parking location of the vehicle into one of three types of parking areas:

[0040] like , then the vehicle attribute is a passenger vehicle;

[0041] like , then the vehicle attribute is a freight vehicle;

[0042] like , enter the judgment process of mixed parking area;

[0043] S403, mixed parking area vehicle attribute judgment: If , then it is a freight vehicle; if , then it is a passenger vehicle; Represents the freight feature score, based on the degree of overlap between the parking area and the freight-related area Ratio of parking time Calculation, the calculation formula is as follows:

[0044] ;

[0045] ;

[0046] ;

[0047] Represents the freight feature score, based on the degree of overlap between the parking area and the passenger-related area and the ratio of short-term parking times Calculation, the calculation formula is as follows:

[0048] ;

[0049] ;

[0050] ;

[0051] in, and Represents the number of times the vehicle stops in freight and passenger transport related areas respectively; Indicates the total driving time of the vehicle; Indicates the total parking time of the vehicle; Indicates the number of short-term vehicle stops; and Respectively represent balance and The weight coefficient in the freight score; and Respectively represent balance and The weight coefficient in the passenger rating of The total number of stops; short time refers to less than 5 minutes;

[0052] S404: Calculate the parking area and score of each vehicle, output the vehicle attribute classification result, and for the specific classification method of passenger vehicle models, proceed to step S5;

[0053] The freight vehicles are used for cargo transportation, including container trucks and logistics vehicles;

[0054] The passenger vehicles are used for passenger transport, including private cars, buses and taxis, and taxis include online-hailing taxis.

[0055] Furthermore, step S5 includes:

[0056] S501, bus identification, including:

[0057] S5011. Extract the vehicle trajectory sequence T from the mobile phone signaling data. ;like , it is determined that the trajectory is fixed, and the process goes to S5012 to continue the determination; wherein, It represents the trajectory repetition rate, that is, the degree of matching between the vehicle trajectory and the number of historical trajectory segments. The calculation method is as follows:

[0058] ;

[0059] Indicates the number of trajectory segments matched by the vehicle, Indicates the number of historical trajectory segments; represents the trajectory repetition rate threshold, which is set to 0.8;

[0060] S5012. Count the maximum number of mobile phones Q that are connected to the base station at the same time during the time period of the trajectory sequence T. If , then the corresponding vehicle is identified as a bus; Indicates the passenger number threshold; range is 7-10;

[0061] S502: Classification of private cars and taxis, including:

[0062] S5021. Calculate travel regularity, including travel time regularity, travel space regularity, and travel regularity indicators;

[0063] First, calculate the regularity of vehicle travel time , The lower it is, the more regular the travel time is;

[0064] ;

[0065] in, represents the average of all travel times; represents the timestamp of the i-th mobile phone signaling data record; N represents the number of timestamps of mobile phone signaling data records;

[0066] Secondly, calculate the regularity of travel space ,Using the starting and ending locations of vehicles, the spatial aggregation degree is calculated,through the density clustering algorithm DBSCAN;

[0067] ;

[0068] ;

[0069] ;

[0070] ;

[0071] ;

[0072] in, and The i'th and jth clusters represent the starting and ending points respectively; and is the number of clusters; and Indicates the number of points in clusters i' and j; and Indicates the total number of points at the starting and ending points; Indicates the proportion of starting cluster i'; represents the proportion of endpoint cluster j;

[0073] Finally, calculate the travel regularity index Comprehensive travel time regularity and travel space regularity , the calculation method of travel regularity index is as follows:

[0074] ;

[0075] in, and is a weight factor used to balance the importance of temporal and spatial regularity, and Take 0.4 and 0.6 respectively;

[0076] S5022, classification judgment rules: If , it is determined to be a private car. If , then it is determined to be a taxi, where represents the regularity threshold, Take 0.65–0.80;

[0077] S503: Output the classification result of passenger vehicle types based on the trajectory repetition rate and travel regularity index.

[0078] Furthermore, the specific steps of step S6 are as follows:

[0079] S601. Output freight vehicle set, the evaluation criteria are ;

[0080] S602: Output passenger vehicle set, the evaluation criteria are ;

[0081] S603: Output bus vehicle set, the evaluation criteria are , and ;

[0082] S604: Output the private car set, the evaluation criteria are and ;

[0083] S605: Output the taxi vehicle set, and the evaluation criteria are and ;

[0084] in represents the freight characteristic score, represents the freight characteristic score, represents the trajectory repetition rate, represents the trajectory repetition rate threshold, represents the passenger number threshold, Indicates the travel regularity index, represents the regularity threshold.

[0085] The present invention also provides a vehicle type trajectory recognition device based on mobile phone signaling data, based on the vehicle type trajectory recognition method, comprising:

[0086] Data collection module, used to obtain and standardize mobile phone signaling data from communication operators;

[0087] The data processing module is used to generate a sequence of vehicle trajectory points based on mobile phone signaling data. Based on the spatial distance and time interval between trajectory points, abnormal trajectory points are identified and removed, and long-term breakpoints are interpolated and supplemented in time and space, and sorted by time.

[0088] The vehicle trajectory statistical feature extraction module is used to divide the trajectory segments according to the base station switching data, determine the parking points based on the speed and dwell time thresholds, and obtain the vehicle trajectory statistical features, including the total travel distance, total number of stops, and total parking time;

[0089] The vehicle attribute determination module maps parking spots to passenger, freight, and mixed parking areas, calculates passenger and freight characteristic scores for vehicles in mixed parking areas, and determines whether they are passenger or freight based on the comprehensive scores;

[0090] The passenger vehicle classification module is used to identify buses based on trajectory repetition rate and the maximum number of connected mobile phones within the vehicle. It then calculates travel time and spatial regularity indicators to distinguish between private cars and taxis, including online ride-hailing vehicles.

[0091] The result output module is used to integrate and output the classification results of each vehicle type and the corresponding complete trajectory sequence, and supports visual reports or external interface calls.

[0092] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the vehicle type trajectory recognition method based on mobile phone signaling data are implemented.

[0093] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle type trajectory recognition method based on mobile phone signaling data are implemented.

[0094] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0095] 1. Low cost and wide coverage: Leveraging existing operator mobile phone signaling, massive location data can be obtained without installing additional hardware on the vehicle. The high coverage of mobile phone signaling enables full coverage identification of vehicles without GPS devices or on-board OBD.

[0096] 2. High-precision identification: Multi-level cleaning and spatiotemporal interpolation complement the system to eliminate base station switching noise and improve trajectory integrity and accuracy. Refined parking point extraction and zoning scoring effectively distinguish between passenger and freight vehicles, reducing misjudgments.

[0097] 3. Multi-vehicle classification capability: Accurately identify buses based on trajectory repetition rate and the number of intra-vehicle connections; distinguish between private cars and taxis based on temporal and spatial regularity indicators, taking into account travel time concentration and origin and destination distribution characteristics.

[0098] 4. Real-time and batch processing: The data acquisition module supports real-time streaming and historical batch processing, which can meet the needs of daily monitoring and post-analysis; the result output module provides an interface design to facilitate docking with the intelligent connected vehicle-road collaborative platform and traffic management system.

[0099] 5. Supports refined traffic management: Provides detailed traffic flow information by vehicle type for traffic planning, helping to alleviate congested sections of private car roads, deploy bus lanes, and control freight time periods; accurately monitors the trajectory of illegally operated vehicles, freight overloads, and abnormal routes, assisting security and law enforcement. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] Figure 1 Schematic diagram of the process of the present invention;

[0101] Figure 2 This is a schematic diagram of vehicle type trajectory recognition based on mobile phone signaling data in this embodiment;

[0102] Figure 3 Schematic diagram of the specific process of step S1 in the method of the present invention;

[0103] Figure 4 Schematic diagram of the specific process of step S4 in the method of the present invention;

[0104] Figure 5 Schematic diagram of the specific process of step S5 in the method of the present invention;

[0105] Figure 6 Application architecture diagram of the system provided by the present invention. DETAILED DESCRIPTION

[0106] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0107] This example uses Lingang Road as a reference to explain the present invention's technology in detail. Lingang Road is a long-standing mixed traffic system for both passenger and freight traffic, posing significant safety risks and severe congestion, especially during peak hours. This invention identifies vehicle types and estimates based on mobile phone signaling data, providing data support for the optimized design of dynamic traffic management within Lingang Road's connected environment, such as dedicated lanes for passenger and freight separation, bus lanes, and commercial vehicle lanes.

[0108] See Figure 1 , the method flow chart of the present invention is as follows:

[0109] S1. Trajectory data generation: obtain mobile phone signaling data from the operator and generate a trajectory point sequence for the vehicle; see Figure 3 , specifically:

[0110] S101. Data Acquisition and Analysis: Mobile phone signaling data originates from operator records and is used to record communication information between user devices and base stations. Specifically, it includes: IMSI (International Mobile Subscriber Identity), Cell ID, Timestamp, Event Type, RSSI, Latitude, and Longitude. Event types include: Location Update, Cell Switching, Call Establishment, and Call Release.

[0111] To illustrate the receiving and processing process of mobile phone signaling data, Figure 2 This example shows a schematic diagram of vehicle-type trajectory recognition based on mobile phone signaling data. Mobile phone signaling data signals are received via 4G / 5G base stations and then transmitted and processed via a cloud platform. The information recorded in the mobile phone signaling data is shown in Table 1.

[0112] Table 1 Example of mobile phone signaling data collection format

[0113] IMSI Cell ID Timestamp Event Type RSSI Latitude Longitude 460011234567890 101234 2024 / 12 / 30 9:00 Location Update -78dBm 39.904200 116.4074 460011234567890 101235 2024 / 12 / 30 9:02 Handover -70dBm 39.906100 116.4107 460011234567890 101236 2024 / 12 / 30 9:05 Location Update -65dBm 39.909600 116.4143 460021234567891 101237 2024 / 12 / 30 9:06 Handover -80dBm 39.912300 116.4178 460021234567891 101238 2024 / 12 / 30 9:08 Call Setup -72dBm 39.915100 116.4214 460031234567892 101239 2024 / 12 / 30 9:10 Location Update -75dBm 39.917900 116.4249 460031234567892 101240 2024 / 12 / 30 9:12 Handover -68dBm 39.920500 116.4285 460041234567893 101241 2024 / 12 / 30 9:15 Location Update -74dBm 39.923100 116.4321 460041234567893 101242 2024 / 12 / 30 9:18 Handover -67dBm 39.925800 116.4356 460051234567894 101243 2024 / 12 / 30 9:20 Call Setup -71dBm 39.928600 116.4392

[0114] S102, data screening: only retain signaling data related to the location, remove data unrelated to the trajectory, and filter out incomplete or abnormal data records.

[0115] S103, base station positioning mapping: query the base station location information (latitude and longitude information) according to the base station ID (Cell ID) to form a base station location table ; Mobile phone signaling data Converted to location information, .in, is the i-th record in the mobile phone signaling data; Indicates the timestamp of the i-th record, that is, the specific time of the record.

[0116] S104, trajectory point generation: each Base station location As a trajectory point The trajectory point sequence is: ,in, , n represents the total number of trajectory points.

[0117] S2. Data cleaning and completion: Based on the spatial distance and time interval between trajectory points, abnormal trajectory points are identified and removed, long-term breakpoints are interpolated and completed in space and time, and sorted by time. Specifically:

[0118] S201, Data Cleaning:

[0119] If the distance between some trajectory points is abnormally large and the time interval is extremely short (possibly due to base station switching errors or multipath effects), they are considered abnormal points and removed. , then remove the points .in, express and The spatial distance is usually calculated based on the spherical distance formula, which is as follows: ; Where R is the radius of the Earth, usually 6371km; Represents the time interval between adjacent trajectory points , Indicates the upper limit of reasonable speed, preferably, The appropriate value is 120km / h.

[0120] S202, trajectory breakpoint completion: If there are long-term (greater than 10 minutes) breakpoints in the trajectory, they are completed through time interpolation and base station position interpolation. The interpolation formula is as follows:

[0121] ;

[0122] in, and Respectively represent the position and timestamp of the completion interpolation.

[0123] S203, time series sorting: sort the trajectory point sequence T by time Sorting;

[0124] .

[0125] S3. Extracting vehicle trajectory statistical features: Divide the trajectory into segments based on the base station switching data, determine the parking points based on the speed and dwell time thresholds, and obtain the vehicle trajectory statistical features, including the total travel distance, total number of stops, and total parking time. Specifically:

[0126] S301, track segment division: according to the base station switching data of the mobile phone signaling, identify the continuous track segments , each trajectory segment is defined as the path of the vehicle during continuous driving or stationary period, and the expression is as follows:

[0127] ;

[0128] in, , m represents the upper limit of the number of different trajectory segments into which the vehicle is divided; the trajectory segment division rule is: if the time interval between two consecutive trajectory points , it is divided into different segments. The appropriate value is 5-10min.

[0129] S302, parking point identification. Calculate the vehicle's speed between adjacent trajectory points ,like Parking time , it is determined to be a parking point. Let S represent the set of parking points, that is, the set of points in the trajectory segment with a speed close to zero and a very small position change.

[0130] Preferably, in this embodiment The appropriate value is 1-3m / s.

[0131] S303, trajectory statistical feature extraction: including total moving distance Total number of stops : The total number of points in the trajectory point sequence that meet the parking conditions; the total parking time : The total dwell time between stops. The total time of the track segment is the time of the last track point minus the time of the first track point.

[0132] S4. Passenger and freight attribute determination: Map parking spots to passenger, freight, and mixed parking areas, calculate passenger and freight feature scores for vehicles in mixed parking areas, and determine passenger or freight after comprehensive scoring; Figure 4 As shown, specifically:

[0133] S401. Parking area division. Based on mobile phone signaling data, analyze the parking location of the vehicle and divide the parking area into the following three categories:

[0134] Passenger parking area : Dedicated to passenger vehicles (such as stations, airport parking areas, etc.);

[0135] Freight parking area : Dedicated to freight vehicles (such as port loading and unloading areas, logistics centers, etc.);

[0136] Mixed parking area : Areas that allow both passenger and freight vehicles to park (such as parking lots at integrated transportation hubs).

[0137] S402, parking area determination. Using the base station location information P, the parking location of the vehicle is classified into one of the above areas:

[0138] like , then the vehicle attribute is a passenger vehicle;

[0139] like , then the vehicle attribute is a freight vehicle;

[0140] like , enter the judgment process of mixed parking area.

[0141] S403, determine the vehicle attributes in the mixed parking area. , then it is a freight vehicle; if , then it is a passenger vehicle;

[0142] Represents the freight feature score, based on the degree of overlap between the parking area and the freight-related area Ratio of parking time Calculation, the calculation formula is as follows:

[0143] ;

[0144] ;

[0145] ;

[0146] Represents the freight feature score, based on the degree of overlap between the parking area and the passenger-related area and the ratio of short-term parking times Calculation, the calculation formula is as follows:

[0147] ;

[0148] ;

[0149] ;

[0150] in, and Represents the number of times the vehicle stops in freight and passenger transport related areas respectively; Indicates the total driving time of the vehicle; Display the total parking time of the vehicle; Indicates the number of short-term (less than 5 minutes) parking times of the vehicle; and Respectively represent balance and The weight coefficient in the freight score; and Respectively represent balance and The weight coefficient in the passenger transport score. Preferably, in this embodiment and The appropriate value is 0.7. and The value is 0.3.

[0151] S404: Calculate the parking area and score of each vehicle, output the vehicle attribute classification result, and for the specific classification method of passenger vehicle models, go to step S5.

[0152] Freight vehicles: mainly used for cargo transportation, such as container trucks, logistics vehicles, etc.

[0153] Passenger vehicles: mainly used for passenger transport, such as private cars, buses, taxis (online ride-hailing services), etc.

[0154] S5. Passenger transport vehicle classification: For vehicles identified as passenger transport, first identify buses based on trajectory repetition rate and the maximum number of mobile phones connected in the vehicle, then calculate travel time and spatial regularity indicators to distinguish between private cars and taxis. Taxis include online ride-hailing vehicles; see Figure 5 , specifically:

[0155] S501, bus identification. The notable characteristics of buses include running on fixed routes with periodicity or repetition, and usually having a large number of passengers on board, resulting in a large number of mobile phones connecting to the base station at the same time. Specifically, they include:

[0156] S5011, trajectory repetition rate calculation. Extract the vehicle trajectory sequence T from the signaling data, ;like , it is determined that the trajectory is fixed, and the process goes to S5012 to continue determination.

[0157] in, It represents the trajectory repetition rate, that is, the degree of matching between the vehicle trajectory and the number of historical trajectory segments. The calculation method is as follows:

[0158] ;

[0159] Indicates the number of trajectory segments matched by the vehicle, Indicates the number of historical trajectory segments, represents the trajectory repetition rate threshold, preferably, 0.8 is appropriate.

[0160] S5012, statistics on the upper limit of the number of people in the vehicle. Statistical trajectory sequence T in the time period, the maximum number of mobile phones Q that the vehicle is connected to the base station at the same time; if , then the corresponding vehicle is identified as a bus. represents the passenger number threshold, preferably, The appropriate value is 7-10.

[0161] S502. Classification of private cars and taxis (online ride-hailing). The main difference between private cars and taxis (online ride-hailing) lies in their travel regularity. Private cars generally have a high degree of temporal and spatial regularity, while taxis (online ride-hailing) travel behavior is more random. Specifically, it includes:

[0162] S5021. Calculation of travel regularity.

[0163] First, calculate the regularity of vehicle travel time , the lower the value, the higher the regularity of travel time.

[0164] ;

[0165] in, It represents the average of all travel times, represents the timestamp of the i-th mobile phone signaling data record; N represents the number of timestamps of mobile phone signaling data records.

[0166] Secondly, calculate the regularity of travel space Using the starting and ending locations of the vehicles, the density clustering algorithm DBSCAN is used to calculate the degree of spatial aggregation. The closer it is to 1, the more concentrated the distribution of the starting and ending points is, and the higher the spatial regularity is; The closer it is to 0, the more dispersed the location distribution of the starting and ending points is, and the lower the spatial regularity is.

[0167] ;

[0168] ;

[0169] ;

[0170] ;

[0171] ;

[0172] in, and The i'th and jth clusters represent the starting and ending points respectively; and is the number of clusters; and Indicates the number of points in clusters i' and j; and Indicates the total number of points at the starting and ending points; Indicates the proportion of starting cluster i'; represents the proportion of endpoint cluster j;

[0173] Finally, calculate the travel regularity index Comprehensive travel time regularity and travel space regularity , the calculation method of travel regularity index is as follows:

[0174] ;

[0175] in, and is a weight factor used to balance the importance of temporal and spatial regularity. Preferably, and The appropriate values ​​are 0.4 and 0.6 respectively.

[0176] S5022: Classification determination rules.

[0177] like , it is determined to be a private car. If , it is determined to be a taxi (online car-hailing). represents the regularity threshold, preferably, The appropriate value is 0.65-0.80.

[0178] S503: Output the classification result of passenger vehicle types based on the trajectory repetition rate and travel regularity index.

[0179] S6. Result output: Output the classification results of each vehicle type and the corresponding complete trajectory sequence. The specific steps are as follows:

[0180] S601. Output freight vehicle set, the evaluation criteria are ;

[0181] S602: Output passenger vehicle set, the evaluation criteria are ;

[0182] S603: Output bus vehicle set, the evaluation criteria are , and ;

[0183] S604: Output the private car set, the evaluation criteria are and ;

[0184] S605. Output the taxi (online car-hailing) vehicle set, and the evaluation criteria are and .

[0185] in represents the freight characteristic score, represents the freight characteristic score, represents the trajectory repetition rate, represents the trajectory repetition rate threshold, represents the passenger number threshold, Indicates the travel regularity index, represents the regularity threshold.

[0186] Based on the same inventive concept, the embodiment of the present invention provides a specific implementation of a vehicle type trajectory recognition system based on mobile phone signaling data that can implement a vehicle type trajectory recognition method. Figure 6 , specifically including the following contents:

[0187] The data acquisition module, serving as the input source for the entire system, is responsible for acquiring mobile phone signaling data from telecommunications operators. This signaling data includes information such as base station ID, timestamp, and signal strength (RSSI), reflecting the communication process between the mobile phone and the base station. Based on this data, vehicle location and time information can be extracted. The core function of this module is to standardize complex, raw signaling data and ensure the integrity and accuracy of the collected data. Furthermore, this module supports both real-time data stream collection and batch processing of historical data, providing input support for subsequent modules.

[0188] The data processing module extracts information such as base station IDs and timestamps from mobile phone signaling data and maps it to base station locations, generating a sequence of vehicle trajectory points. Based on the spatial distances and time intervals between trajectory points, it identifies and removes anomalous trajectory points, performs spatiotemporal interpolation to complete long-term discontinuities, and sorts them by time. The processed data must be high-quality and continuous, providing a reliable foundation for subsequent attribute determination and classification.

[0189] The vehicle trajectory statistical feature extraction module is used to divide the trajectory segments according to the base station switching data, determine the parking points based on the speed and dwell time thresholds, and obtain the vehicle trajectory statistical features, including the total travel distance, total number of stops, and total parking time;

[0190] The vehicle attribute determination module distinguishes whether the vehicle is a passenger vehicle or a freight vehicle by analyzing the parking area and behavior characteristics of the vehicle. , freight parking area , mixed parking area ), preliminarily determine the attributes of the vehicle. If the parking spot is located in a mixed parking area, further calculate the freight feature score and passenger characteristics score , combined with the vehicle's parking time and parking area distribution, the vehicle attributes are finally determined. This module is the key part of the system to achieve passenger and freight classification, providing input for subsequent passenger vehicle classification.

[0191] Passenger vehicle classification module: The passenger vehicle classification module further divides the vehicles that have been identified as passenger vehicles into buses, private cars and taxis (online ride-hailing vehicles). First, the trajectory repetition rate And the analysis of the number of passengers Q in the car, identify the bus. Then, for non-bus vehicles, the travel regularity index , comprehensive temporal regularity (standard deviation of temporal distribution ) and spatial regularity (clustering of starting and ending points ), distinguishing between private cars and taxis (online ride-hailing services). This module uses multidimensional feature analysis to ensure classification accuracy.

[0192] The result output module, the terminal component of the system, integrates the classification results and outputs each vehicle's attribute category and trajectory data. This output includes each vehicle's classification (freight / passenger), the specific type of passenger vehicle (bus, private car, or taxi), and the corresponding complete trajectory sequence T. Furthermore, this module supports formatting the output results into visual reports or interfaces for external systems to access, facilitating analysis and decision-making by traffic management departments or logistics operators. This module also provides statistical analysis capabilities, such as evaluating the accuracy of classification results and monitoring traffic flow dynamics.

[0193] Preferably, the embodiments of the present application further provide a specific implementation of an electronic device capable of implementing all steps of the vehicle type trajectory recognition method based on mobile phone signaling data in the above embodiment, and the electronic device specifically includes the following contents:

[0194] Processor, memory, communications interface, and bus;

[0195] Among them, the processor, memory, and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between related devices such as server-side devices, metering devices, and user-side devices.

[0196] The processor is used to call the computer program in the memory. When the processor executes the computer program, all steps of the vehicle type trajectory recognition method based on mobile phone signaling data in the above embodiment are implemented.

[0197] Embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the vehicle-type trajectory recognition method based on mobile phone signaling data in the above-mentioned embodiment. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the vehicle-type trajectory recognition method based on mobile phone signaling data in the above-mentioned embodiment.

[0198] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the hardware + program embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0199] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0200] Although this application provides method steps such as the embodiments or flowcharts, more or fewer steps may be included based on routine or non-inventive work. The order of steps listed in the embodiments is merely one of many possible execution sequences and does not represent the only execution sequence. When executed in an actual device or client product, the methods may be executed sequentially according to the embodiments or the accompanying drawings, or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0201] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0202] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0203] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0204] The present invention is not limited to the embodiments described above. The above description of the specific embodiments is intended to describe and illustrate the technical solutions of the present invention. The above specific embodiments are merely illustrative and not restrictive. Without departing from the scope of the present invention and the scope of protection of the claims, those skilled in the art may make various specific modifications based on the teachings of the present invention, all of which fall within the scope of protection of the present invention.

Claims

1. A vehicle type trajectory recognition method based on mobile phone signaling data, characterized in that: include: S1. Trajectory data generation: Obtain mobile phone signaling data from the operator and generate a vehicle trajectory point sequence based on the mobile phone signaling data; S2. Data cleaning and completion: Based on the spatial distance and time interval between trajectory points, abnormal trajectory points are identified and removed, long-term breakpoints are completed through spatiotemporal interpolation, and sorted by time; S3. Extracting vehicle trajectory statistical features: Divide the trajectory into segments based on the base station handover data, determine the parking points based on the speed and dwell time thresholds, and obtain the vehicle trajectory statistical features, including the total travel distance, total number of stops, and total parking time; S4. Passenger and freight attribute determination: Map parking spots to passenger, freight, and mixed parking areas. Calculate passenger and freight attribute scores for vehicles in mixed parking areas. Determine whether the vehicles are passenger or freight based on the comprehensive score. This includes: S401: Analyze the parking location of the vehicle based on the mobile phone signaling data and divide the parking areas into the following three categories: Passenger parking area , for passenger vehicles, including stations and airport parking areas; Freight parking area , for freight vehicles, including port loading and unloading areas and logistics centers; Mixed parking area , areas where both passenger and freight vehicles are allowed to park, including parking lots at integrated transportation hubs; S402: Using the base station location information P, classify the parking location of the vehicle into one of three types of parking areas: like , then the vehicle attribute is a passenger vehicle; like , then the vehicle attribute is a freight vehicle; like , enter the judgment process of mixed parking area; S403, mixed parking area vehicle attribute judgment: If , then it is a freight vehicle; if , then it is a passenger vehicle; Represents the freight feature score, based on the degree of overlap between the parking area and the freight-related area Ratio of parking time Calculation, the calculation formula is as follows: ； ； ； Represents the passenger transport feature score, based on the degree of overlap between the parking area and the passenger transport related area and the ratio of short-term parking times Calculation, the calculation formula is as follows: ； ； ； in, and Represents the number of times the vehicle stops in freight and passenger transport related areas respectively; Indicates the total driving time of the vehicle; Indicates the total parking time of the vehicle; Indicates the number of short-term vehicle stops; and Respectively represent balance and The weight coefficient in the freight score; and Respectively represent balance and The weight coefficient in the passenger rating of The total number of stops; short time refers to less than 5 minutes; S404: Calculate the parking area and score of each vehicle, output the vehicle attribute classification result, and for the specific classification method of passenger vehicle models, proceed to step S5; The freight vehicles are used for cargo transportation, including container trucks and logistics vehicles; The passenger vehicles are used for passenger transport, including private cars, buses and taxis, and taxis include online-hailing taxis; S5. Passenger transport vehicle classification: For vehicles identified as passenger transport, buses are first identified based on trajectory repetition rate and the maximum number of mobile phones connected in the vehicle. Travel time and spatial regularity indicators are then calculated to distinguish between private cars and taxis. Taxis include online ride-hailing vehicles. This includes: S501, bus identification, including: S5011. Extract the vehicle trajectory sequence T from the mobile phone signaling data. ;like , it is determined that the trajectory is fixed, and the process goes to S5012 to continue the determination; wherein, It represents the trajectory repetition rate, that is, the degree of matching between the vehicle trajectory and the number of historical trajectory segments. The calculation method is as follows: ； Indicates the number of trajectory segments matched by the vehicle, Indicates the number of historical trajectory segments; represents the trajectory repetition rate threshold, which is set to 0.8; S5012. Count the maximum number of mobile phones Q that are connected to the base station at the same time during the time period of the trajectory sequence T; if , then the corresponding vehicle is identified as a bus; Indicates the passenger number threshold; range is 7-10; S502: Classification of private cars and taxis, including: S5021. Calculate travel regularity, including travel time regularity, travel space regularity, and travel regularity indicators; First, calculate the regularity of vehicle travel time , The lower it is, the more regular the travel time is; Secondly, calculate the regularity of travel space ,Using the starting and ending locations of vehicles, the spatial aggregation degree is calculated,through the density clustering algorithm DBSCAN; ； ； ； ； ； in, and The i'th and jth clusters represent the starting and ending points respectively; and is the number of clusters; and Indicates the number of points in clusters i' and j; and Indicates the total number of points at the starting and ending points; Indicates the proportion of starting cluster i'; represents the proportion of endpoint cluster j; Finally, calculate the travel regularity index Comprehensive travel time regularity and travel space regularity , the calculation method of travel regularity index is as follows: ； in, and is a weight factor used to balance the importance of temporal and spatial regularity, and Take 0.4 and 0.6 respectively; S5022, classification judgment rules: If , it is determined to be a private car. If , then it is determined to be a taxi, where represents the regularity threshold, Take 0.65–0.80; S503: Outputting the classification results of passenger vehicles based on the trajectory repetition rate and travel regularity index; S6. Result output: Output the classification results of each vehicle type and the corresponding complete trajectory point sequence.

2. The vehicle type trajectory recognition method based on mobile phone signaling data according to claim 1 is characterized in that: Step S1 includes: S101. Mobile phone signaling data is used to record communication information between user equipment and base stations, including the International Mobile Subscriber Identity (IMSI), base station ID, timestamp, signal strength, latitude and longitude information, and event type information. Event types include location update, base station handover, call establishment, and call release. S102, retaining location update, base station handover, base station ID, timestamp, and latitude and longitude information, and filtering out incomplete or abnormal mobile phone signaling data; S103, query the location information of the base station according to the base station ID to form a base station location table ; Mobile phone signaling data Converted to location information, ;in, is the i-th data in the mobile phone signaling data; Indicates the timestamp of the i-th mobile phone signaling data, that is, the specific time of the mobile phone signaling data; S104, each Base station location As a trajectory point , the trajectory point sequence of the generated vehicle is: ,in, , n represents the total number of trajectory points.

3. The vehicle type trajectory recognition method based on mobile phone signaling data according to claim 1 is characterized in that: Step S2 includes: S201, set judgment conditions: if , then remove the trajectory points ;in, Represents trajectory points and The spatial distance is calculated as follows: Where R is the radius of the Earth, which is 6371 km; represents the time interval between adjacent trajectory points, , Indicates the upper limit of reasonable speed; 、 Respectively represent the timestamps of the i-th and i+1-th mobile phone signaling data; , n represents the total number of trajectory points; S202: If there are long breakpoints longer than 10 minutes in the trajectory point sequence, the breakpoints are completed by time interpolation and base station position interpolation. The interpolation formula is as follows: ； in, and Respectively represent the base station position and timestamp of the completed interpolation; S203, track point sequence T is sorted by time Sorting; 。 4. The vehicle type trajectory recognition method based on mobile phone signaling data according to claim 1 is characterized in that: Step S3 includes: S301, identifying continuous trajectory segments based on base station switching data from mobile phone signaling data , each trajectory segment is defined as the path of the vehicle during continuous driving or stationary period, and the expression is as follows: ； in, , m represents the upper limit of the number of different trajectory segments into which the vehicle is divided; j represents a number of trajectory points; If the time interval between two consecutive trajectory points , it is divided into different segments; S302: Calculate the speed of the vehicle between adjacent trajectory points ,like And the time interval , it is determined to be a parking point; S is used to represent the set of parking points, Represents trajectory points and spatial distance; Take 1-3m / s, Take 5-10 minutes; S303, extract trajectory statistical features, including total movement distance Total number of stops , represents the total number of trajectory points in the trajectory point sequence that meet the parking conditions; the total parking time , which represents the total stay time between parking points.

5. The vehicle type trajectory recognition method based on mobile phone signaling data according to claim 1 is characterized in that: The specific steps of step S6 are as follows: S601. Output freight vehicle set, the evaluation criteria are ; S602: Output passenger vehicle set, the evaluation criteria are ; S603: Output bus vehicle set, the evaluation criteria are , and ; S604: Output the private car set, the evaluation criteria are and ; S605: Output the taxi vehicle set, and the evaluation criteria are and ; in represents the freight characteristic score, represents the passenger characteristics score, represents the trajectory repetition rate, represents the trajectory repetition rate threshold, represents the passenger number threshold, Indicates the travel regularity index, represents the regularity threshold.

6. A vehicle type trajectory recognition device based on mobile phone signaling data, based on the vehicle type trajectory recognition method according to any one of claims 1 to 5, characterized in that: include: Data collection module, used to obtain and standardize mobile phone signaling data from communication operators; The data processing module is used to generate a sequence of vehicle trajectory points based on mobile phone signaling data. Based on the spatial distance and time interval between trajectory points, abnormal trajectory points are identified and removed, and long-term breakpoints are interpolated and supplemented in time and space, and sorted by time. The vehicle trajectory statistical feature extraction module is used to divide the trajectory segments according to the base station switching data, determine the parking points based on the speed and dwell time thresholds, and obtain the vehicle trajectory statistical features, including the total travel distance, total number of stops, and total parking time; The vehicle attribute determination module maps parking spots to passenger, freight, and mixed parking areas, calculates passenger and freight characteristic scores for vehicles in mixed parking areas, and determines whether they are passenger or freight based on the comprehensive scores; The passenger vehicle classification module is used to identify buses based on trajectory repetition rate and the maximum number of connected mobile phones within the vehicle. It then calculates travel time and spatial regularity indicators to distinguish between private cars and taxis, including online ride-hailing vehicles. The result output module is used to integrate and output the classification results of each vehicle type and the corresponding complete trajectory sequence, and supports visual reports or external interface calls.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the vehicle type trajectory recognition method based on mobile phone signaling data according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle type trajectory recognition method based on mobile phone signaling data as described in any one of claims 1 to 5 are implemented.

Images