Vehicle route matching method and public transportation information query method

Abstract

The embodiment of the application can be applied to the field of transportation and relates to a vehicle line matching method and a public transportation information query method. The vehicle line matching method comprises the following steps: acquiring at least one map line comprising at least one line segment and vehicle trajectory data comprising a plurality of trajectory points; determining at least one candidate line segment corresponding to each trajectory point from the at least one map line; generating the attribution probability of each trajectory point on the corresponding candidate line segment, and performing turn cutting on the vehicle trajectory data based on the at least one candidate line segment to obtain at least two turn segments; performing quantitative evaluation on the at least two turn segments respectively based on the attribution probability of each trajectory point on the corresponding candidate line segment to obtain the quantitative evaluation result corresponding to each of the at least two turn segments; and performing line planning solving based on the quantitative evaluation result corresponding to each of the at least two turn segments to obtain a vehicle line matching result. The method can realize accurate vehicle line matching.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a vehicle route matching method, apparatus, computer equipment, storage medium and computer program product, as well as a public transportation information query method, apparatus, computer equipment, storage medium and computer program product. Background Technology

[0002] With the development of computer technology, map services have emerged, providing convenience for people's daily travel. A key supporting technology for map services is route matching technology, which establishes a correlation between vehicle trajectories and routes on electronic maps, thereby enabling users to access services such as real-time public transportation information.

[0003] In traditional technology, the way public transportation information is queried is as follows: the map service provider pre-maps the route data provided by the vehicle data provider onto its own internal map routes to obtain the vehicle route matching results. When it receives a public transportation information query request, it responds to the public transportation information query request and feeds back the corresponding public transportation information based on the vehicle route matching results.

[0004] However, the quality of route data provided by vehicle data providers varies. Some can provide static route data, while others cannot. Furthermore, the static route data provided may not be updated in a timely manner, and it cannot be guaranteed that the static route data is completely consistent with the actual vehicle routes. In addition, since the route names provided by vehicle data providers may differ from the route names provided by map service providers, it is impossible to make an accurate mapping relationship from the route names. These factors will lead to the inability to achieve accurate vehicle route matching, and thus the inability to provide accurate public transportation information. Summary of the Invention

[0005] Therefore, it is necessary to address the above-mentioned technical problems by providing a vehicle route matching method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can achieve accurate vehicle route matching, as well as a public transportation information query method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can provide accurate public transportation information.

[0006] Firstly, this application provides a vehicle route matching method. The method includes:

[0007] Acquire at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points.

[0008] From at least one map route, determine at least one candidate route segment corresponding to each trajectory point;

[0009] Generate the probability of each trajectory point belonging to each candidate route segment, and based on at least one candidate route segment, divide the vehicle trajectory data into trip segments to obtain at least two trip segments;

[0010] Based on the probability of each trajectory point belonging to each candidate route segment, at least two trips are quantitatively evaluated to obtain the corresponding quantitative evaluation results for each of the at least two trips.

[0011] The route planning solution is obtained by solving the route planning problem based on the corresponding quantitative evaluation results of at least two trip segments.

[0012] Secondly, this application also provides a vehicle route matching device. The device includes:

[0013] The data acquisition module is used to acquire at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points.

[0014] The candidate route segment determination module is used to determine at least one candidate route segment corresponding to each trajectory point from at least one map route.

[0015] The processing module is used to generate the probability of each trajectory point belonging to each candidate route segment, and to divide the vehicle trajectory data into trip segments based on at least one candidate route segment to obtain at least two trip segments.

[0016] The quantitative evaluation module is used to perform quantitative evaluation on at least two trips based on the probability of each trajectory point belonging to each candidate route segment, and obtain the corresponding quantitative evaluation results for each of the at least two trips.

[0017] The route planning and solving module is used to solve the route planning based on the corresponding quantitative evaluation results of at least two trip segments, and obtain the vehicle route matching results.

[0018] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0019] Acquire at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points.

[0020] From at least one map route, determine at least one candidate route segment corresponding to each trajectory point;

[0021] Generate the probability of each trajectory point belonging to each candidate route segment, and based on at least one candidate route segment, divide the vehicle trajectory data into trip segments to obtain at least two trip segments;

[0022] Based on the probability of each trajectory point belonging to each candidate route segment, at least two trips are quantitatively evaluated to obtain the corresponding quantitative evaluation results for each of the at least two trips.

[0023] The route planning solution is obtained by solving the route planning problem based on the corresponding quantitative evaluation results of at least two trip segments.

[0024] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0025] Acquire at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points.

[0026] From at least one map route, determine at least one candidate route segment corresponding to each trajectory point;

[0027] Generate the probability of each trajectory point belonging to each candidate route segment, and based on at least one candidate route segment, divide the vehicle trajectory data into trip segments to obtain at least two trip segments;

[0028] Based on the probability of each trajectory point belonging to each candidate route segment, at least two trips are quantitatively evaluated to obtain the corresponding quantitative evaluation results for each of the at least two trips.

[0029] The route planning solution is obtained by solving the route planning problem based on the corresponding quantitative evaluation results of at least two trip segments.

[0030] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0031] Acquire at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points.

[0032] From at least one map route, determine at least one candidate route segment corresponding to each trajectory point;

[0033] Generate the probability of each trajectory point belonging to each candidate route segment, and based on at least one candidate route segment, divide the vehicle trajectory data into trip segments to obtain at least two trip segments;

[0034] Based on the probability of each trajectory point belonging to each candidate route segment, at least two trips are quantitatively evaluated to obtain the corresponding quantitative evaluation results for each of the at least two trips.

[0035] The route planning solution is obtained by solving the route planning problem based on the corresponding quantitative evaluation results of at least two trip segments.

[0036] Sixthly, this application provides a method for querying public transportation information. The method includes:

[0037] In response to public transportation information query requests, determine route and station identifiers;

[0038] The target route is determined based on the route identifier. Based on the real-time routes of each public transport, at least one target public transport vehicle under the target route is determined. The real-time routes of each public transport are obtained by vehicle route matching based on the candidate routes in the candidate route set of each public transport. The candidate routes in the candidate route set of each public transport are obtained by the above vehicle route matching method.

[0039] Obtain the location information of at least one target public transport vehicle, and determine the estimated arrival time of each of the at least one target public transport vehicle based on the location information and station identifiers;

[0040] Based on the estimated arrival time of at least one target public transport vehicle, the public transport information query results are fed back to the sender of the public transport information query request.

[0041] Seventhly, this application also provides a public transportation information query device. The device includes:

[0042] The response module is used to respond to public transportation information query requests and determine the route identifier and station identifier;

[0043] The query module is used to determine the target route based on the route identifier, and to determine at least one target public transport vehicle under the target route based on the real-time routes of each public transport vehicle. The real-time routes of each public transport vehicle are obtained by vehicle route matching based on the candidate routes in the candidate route set of each public transport vehicle. The candidate routes in the candidate route set of each public transport vehicle are obtained by the above vehicle route matching method.

[0044] The estimation module is used to obtain the location information of at least one target public transport vehicle and, based on the location information and station identifiers, determine the corresponding estimated arrival time of each of the at least one target public transport vehicle.

[0045] The feedback module is used to return the public transportation information query results to the sender of the public transportation information query request based on the estimated arrival time of at least one target public transportation vehicle.

[0046] Eighthly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0047] In response to public transportation information query requests, determine route and station identifiers;

[0048] The target route is determined based on the route identifier. Based on the real-time routes of each public transport, at least one target public transport vehicle under the target route is determined. The real-time routes of each public transport are obtained by vehicle route matching based on the candidate routes in the candidate route set of each public transport. The candidate routes in the candidate route set of each public transport are obtained by the above vehicle route matching method.

[0049] Obtain the location information of at least one target public transport vehicle, and determine the estimated arrival time of each of the at least one target public transport vehicle based on the location information and station identifiers;

[0050] Based on the estimated arrival time of at least one target public transport vehicle, the public transport information query results are fed back to the sender of the public transport information query request.

[0051] Ninthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0052] In response to public transportation information query requests, determine route and station identifiers;

[0053] The target route is determined based on the route identifier. Based on the real-time routes of each public transport, at least one target public transport vehicle under the target route is determined. The real-time routes of each public transport are obtained by vehicle route matching based on the candidate routes in the candidate route set of each public transport. The candidate routes in the candidate route set of each public transport are obtained by the above vehicle route matching method.

[0054] Obtain the location information of at least one target public transport vehicle, and determine the estimated arrival time of each of the at least one target public transport vehicle based on the location information and station identifiers;

[0055] Based on the estimated arrival time of at least one target public transport vehicle, the public transport information query results are fed back to the sender of the public transport information query request.

[0056] Tenthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0057] In response to public transportation information query requests, determine route and station identifiers;

[0058] The target route is determined based on the route identifier. Based on the real-time routes of each public transport, at least one target public transport vehicle under the target route is determined. The real-time routes of each public transport are obtained by vehicle route matching based on the candidate routes in the candidate route set of each public transport. The candidate routes in the candidate route set of each public transport are obtained by the above vehicle route matching method.

[0059] Obtain the location information of at least one target public transport vehicle, and determine the estimated arrival time of each of the at least one target public transport vehicle based on the location information and station identifiers;

[0060] Based on the estimated arrival time of at least one target public transport vehicle, the public transport information query results are fed back to the sender of the public transport information query request.

[0061] The aforementioned vehicle route matching method, apparatus, computer equipment, storage medium, and computer program product, by determining at least one candidate route segment corresponding to each trajectory point from at least one map route, and generating the attribution probability of each trajectory point on the corresponding candidate route segment, can realize the attribution analysis of each trajectory point. By dividing the vehicle trajectory data into trip segments based on at least one candidate route segment, at least two trip segments can be obtained. Thus, based on the attribution probability of each trajectory point on the corresponding candidate route segment, at least two trip segments can be quantitatively evaluated to obtain the corresponding quantitative evaluation results of at least two trip segments. Furthermore, route planning can be solved based on the corresponding quantitative evaluation results of at least two trip segments to obtain the vehicle route matching result. The entire process, by utilizing the attribution probability and route planning solution to perform route matching at the trip segment level, can achieve accurate vehicle route matching.

[0062] The aforementioned public transportation information query method, device, computer equipment, storage medium, and computer program product, by utilizing vehicle route matching methods to obtain accurate candidate route sets for each public transportation, can obtain real-time routes for each public transportation by quantitatively evaluating the candidate routes in each public transportation candidate route set. In response to public transportation information query requests, it can determine route identifiers and station identifiers, identify target routes based on route identifiers, identify at least one target public transportation vehicle under the target route based on the real-time routes of each public transportation, obtain the location information of each target public transportation vehicle, determine the estimated arrival time of each target public transportation vehicle based on the location information and station identifiers, and feed back the public transportation information query results to the sender of the public transportation information query request based on the estimated arrival time of each target public transportation vehicle, thus achieving accurate feedback of public transportation information. Attached Figure Description

[0063] Figure 1 This is an application environment diagram of the vehicle route matching method in one embodiment;

[0064] Figure 2 This is a flowchart illustrating a vehicle route matching method in one embodiment;

[0065] Figure 3 This is a schematic diagram illustrating the process of segmenting a map route to obtain multiple route segments in one embodiment;

[0066] Figure 4 This is a schematic diagram illustrating the acquisition of vehicle trajectory data in one embodiment;

[0067] Figure 5 This is a schematic diagram of the structure of trajectory point data in one embodiment;

[0068] Figure 6 This is a flowchart illustrating the vehicle route matching method in another embodiment;

[0069] Figure 7 This is an application environment diagram of a public transportation information query method in one embodiment;

[0070] Figure 8 This is a schematic diagram illustrating the display of public transportation information query results in one embodiment;

[0071] Figure 9 This is a flowchart illustrating a public transportation information query method in one embodiment;

[0072] Figure 10 This is a structural block diagram of a vehicle route matching device in one embodiment;

[0073] Figure 11 This is a structural block diagram of a public transportation information query device in one embodiment;

[0074] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0075] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0076] The vehicle route matching method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, vehicle 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other servers. Server 104 acquires at least one map route and vehicle trajectory data of vehicle 102. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points. From the at least one map route, it determines at least one candidate route segment corresponding to each trajectory point, generates the probability of each trajectory point's affiliation on each candidate route segment, and, based on the at least one candidate route segment, divides the vehicle trajectory data into trips to obtain at least two trip segments. Based on the probability of each trajectory point's affiliation on each candidate route segment, it performs quantitative evaluation on each of the at least two trip segments to obtain the corresponding quantitative evaluation results for each of the at least two trip segments. Based on the corresponding quantitative evaluation results for each of the at least two trip segments, it performs route planning to obtain the vehicle route matching result. Vehicle 102 can be, but is not limited to, various types of autonomous and non-autonomous vehicles. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0077] In one embodiment, such as Figure 2 As shown, a vehicle route matching method is provided, which is applied to... Figure 1 Taking server 104 as an example, the following steps are included:

[0078] Step 202: Obtain at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points.

[0079] Map routes refer to routes related to vehicle operation included in the map data provided by the map service provider. A map route includes at least one route segment and at least one station. For example, when the vehicle is public transportation, the map route refers to routes related to public transportation operation included in the map data provided by the map service provider. Specifically, a map route can refer to a public transportation route. Route segments are obtained by dividing the map route into segments of preset lengths, which can be configured according to the actual application scenario. For example, such as... Figure 3 As shown, the thick black lines represent map routes. By cutting the map routes into segments according to preset lengths (represented by dashed lines), multiple route segments can be obtained.

[0080] Vehicle trajectory data refers to a chronologically ordered collection of locations along a vehicle's actual route. For example, vehicle trajectory data could specifically refer to a chronologically ordered collection of locations along a vehicle's actual route within a single day. Vehicle trajectory data includes data from multiple trajectory points, which are location nodes recorded when a vehicle travels along its actual route. The data associated with each trajectory point can include its longitude, latitude, timestamp, speed, and data source route identifier.

[0081] Specifically, the server will obtain at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points. In practical applications, the server can directly obtain vehicle trajectory data from a data provider.

[0082] In a specific application, such as Figure 4 As shown, vehicle 402 can transmit its real-time location to satellite positioning system 404, and satellite positioning system 404 can transmit the real-time location information of vehicle 402 to server 406 owned by data provider. Server 406 owned by data provider can generate vehicle trajectory data based on the received real-time location information of vehicle 402, so server 408 can obtain vehicle trajectory data from server 406 owned by data provider. In a specific application, server 408 can be a map service provider's server, which can be used to provide map services to users.

[0083] In a specific application, the server 406 owned by the data provider, based on the received real-time location information of vehicle 402, preprocesses the real-time location information to generate vehicle trajectory data. For example, the real-time location information can specifically be GPS (Global Positioning System) trajectory point data. The server 406 owned by the data provider will sort and merge the GPS trajectory points of the same vehicle in each city for one day by time to obtain the vehicle trajectory data for each vehicle. The GPS trajectory point data includes the longitude, latitude, timestamp, speed, and data source route identifier of the trajectory points. Longitude, latitude, and timestamp are required data, while speed and data source route identifier are optional data; if missing, they can be set to preset values, such as -1.

[0084] Furthermore, the data provider's server 406 formats the GPS track point data, using the vehicle identifier as the key and information such as longitude, latitude, timestamp, speed, and data source route identifier as the value. For example, the structure of the formatted GPS track point data can be as follows: Figure 5 As shown.

[0085] Step 204: From at least one map route, determine at least one candidate route segment corresponding to each trajectory point.

[0086] Among them, the candidate route segment refers to the route segment that matches the trajectory point selected from multiple route segments of at least one map route, and the trajectory point may belong to the corresponding candidate route segment.

[0087] Specifically, in at least one map route, each map route includes at least one route segment. The server will determine at least one candidate route segment corresponding to each trajectory point from at least one map route. In practical applications, the server can start from the first trajectory point in the vehicle trajectory data to determine at least one candidate route segment corresponding to it, and then process each trajectory point after the first trajectory point in the same way in a loop until the last trajectory point, thus completing the processing of all trajectory points and determining at least one candidate route segment corresponding to each trajectory point.

[0088] In a specific application, for each trajectory point in the vehicle trajectory data, the server can set a search radius, calculate the distance between the target trajectory point and at least one line segment included in each map line, and identify line segments whose distance to the target trajectory point is less than the search radius as candidate line segments corresponding to the target trajectory point. The size of the search radius can be configured according to the actual application scenario.

[0089] In a specific application, the server can pre-process the map into a grid. The gridded map can be divided into M*N grids, where M and N are both positive integers, and each grid has a corresponding grid index number. At least one line segment included in each map line is projected into the M*N grids and associated with the corresponding grid index number. For each trajectory point in the vehicle trajectory data, the server projects the target trajectory point into the M*N grids. Based on the grid index number of the grid to which the target trajectory point is projected, a candidate region consisting of a*b grids is determined, where a is an integer greater than 0 and less than or equal to M, and b is an integer greater than 0 and less than or equal to N. Based on the grid index number of the candidate region's grids, the associated line segment is determined, and this associated line segment is identified as at least one candidate line segment corresponding to the target trajectory point. The size of the candidate region can be configured according to the actual application scenario.

[0090] Step 206: Generate the probability of each trajectory point belonging to each candidate route segment, and based on at least one candidate route segment, divide the vehicle trajectory data into trip segments to obtain at least two trip segments.

[0091] The attribution probability refers to the probability that each trajectory point lies on each corresponding candidate route segment. The higher the attribution probability, the greater the probability that the trajectory point lies on the corresponding candidate route segment, meaning the better the match between the trajectory point and the corresponding candidate route segment. For example, the attribution probability can specifically refer to the probability that each trajectory point lies on each corresponding candidate route segment calculated by a matching algorithm based on a Hidden Markov Model.

[0092] Specifically, the server generates the probability of each trajectory point belonging to each candidate route segment based on each trajectory point and at least one corresponding candidate route segment. Then, based on the at least one candidate route segment, it determines at least one candidate map route from at least one map route. Finally, it matches each trajectory point with each of the at least one candidate map route to obtain at least two trips. Here, a candidate map route refers to a map route that may match a trajectory point.

[0093] In practical applications, the server calculates the observation probability and transition probability of each trajectory point on each corresponding candidate line segment using a matching algorithm based on a Hidden Markov Model (HMM). Then, based on these probabilities, the server obtains the assignment probability of each trajectory point on each candidate line segment. The HMM is a statistical model used to describe a Markov process with hidden unknown parameters. The challenge lies in determining the hidden parameters from the observable parameters and then using these parameters for further analysis.

[0094] In practical applications, after determining at least one candidate route segment, the server will use the map route that includes any one of the candidate route segments as a candidate map route to determine at least one candidate map route from the at least one map route. Then, it will match the trajectory points by projecting them onto each of the at least one candidate map route to obtain at least two trips.

[0095] Step 208: Based on the probability of each trajectory point belonging to each candidate route segment, perform quantitative evaluation on at least two trip segments respectively to obtain the corresponding quantitative evaluation results for at least two trip segments.

[0096] Quantitative assessment refers to an evaluation method that uses quantitative analysis and calculation to judge a train segment. For example, a specific method of quantitative assessment might be to score a train segment through quantitative analysis and calculation, and then use the score to make a judgment about the train segment. The quantitative assessment result refers to the result obtained after conducting the quantitative assessment. For example, the quantitative assessment result could specifically refer to the score obtained after conducting the quantitative assessment.

[0097] Specifically, for each of the at least two trip segments, the server will obtain the average adsorption score of the trajectory points in each trip segment based on the probability of each trajectory point being assigned to each candidate route segment, and then obtain the corresponding quantitative evaluation result of the trip segment based on the average adsorption score of the trajectory points in each trip segment.

[0098] In practical applications, since the targeted trip segment corresponds to at least one candidate map route, the server can filter the probability of each trajectory point belonging to the candidate route segment under the candidate map route corresponding to the targeted trip segment from the probability of each trajectory point belonging to the corresponding candidate route segment. Thus, the probability of each trajectory point belonging to the candidate route segment under the candidate map route corresponding to the targeted trip segment can be used as the average adsorption score of the trajectory points in each trip segment of the targeted trip segment.

[0099] In specific applications, when obtaining the corresponding quantitative evaluation result for a given trip based on the average adsorption score of trajectory points in each trip segment, the server will calculate the line trip completeness of trajectory points in each trip segment. By combining the average adsorption score and line trip completeness of trajectory points in each trip segment, the trip matching completeness of trajectory points in each trip segment will be obtained. Based on the trip matching completeness of trajectory points in each trip segment, the corresponding quantitative evaluation result for the given trip segment will be obtained.

[0100] The route completeness refers to the coverage of trajectory points in a route segment relative to the candidate map route corresponding to the target route segment. The server calculates the first route length of trajectory points in each route segment, and then divides the first route length by the second route length of the candidate map route corresponding to the target route segment to obtain the route completeness of trajectory points in each route segment. Furthermore, when calculating the first route length of trajectory points in each route segment, the server can use the distance between the trajectory points in each route segment and the trajectory points in the first route segment of the target route segment as the first route length, or it can use the distance between the trajectory points in each route segment and the trajectory points in the last route segment of the target route segment as the first route length. This embodiment does not limit the calculation method of the first route length.

[0101] Step 210: Solve the route planning based on the corresponding quantitative evaluation results of at least two trip segments to obtain the vehicle route matching results.

[0102] Among them, route planning and solving refers to performing dynamic programming to find a route that matches the vehicle trajectory data. Dynamic programming is the process of optimizing the decision-making process. In this embodiment, it refers to the process of optimizing the route.

[0103] Specifically, the server sorts at least two trip segments according to their respective start times to obtain a trip segment sequence. Based on the quantitative evaluation result of the first trip segment in the sequence, a reference current route matching score is obtained. Starting from the second trip segment, each trip segment in the sequence is used as the current trip segment. Based on the quantitative evaluation result of the current trip segment, at least one route planning score is obtained for that current trip segment. By comparing the reference current route matching score with the at least one route planning score of the current trip segment, it is determined whether the current route matching score needs to be updated. This process continues until all trip segments in the sequence have been traversed. Finally, the vehicle route matching result is obtained for the corresponding trip segment based on the latest current route matching score. Here, the at least one route planning score for the current trip segment refers to the score obtained after route planning based on the current trip segment.

[0104] The aforementioned vehicle route matching method determines at least one candidate route segment for each trajectory point from at least one map route, generates the attribution probability of each trajectory point on each candidate route segment, and enables attribution analysis of each trajectory point. By segmenting the vehicle trajectory data into trips based on at least one candidate route segment, at least two trip segments can be obtained. Based on the attribution probability of each trajectory point on each candidate route segment, at least two trip segments can be quantitatively evaluated to obtain the corresponding quantitative evaluation results for each of the at least two trip segments. Then, route planning can be solved based on the corresponding quantitative evaluation results of at least two trip segments to obtain the vehicle route matching result. The entire process, by using attribution probability and route planning to perform route matching at the trip segment level, can achieve accurate vehicle route matching.

[0105] In one embodiment, generating the probability of each trajectory point belonging to each corresponding candidate line segment includes:

[0106] Generate the observation probability and transition probability of each trajectory point on the corresponding candidate line segment;

[0107] The observation probability and transition probability of each trajectory point on each candidate route segment are weighted separately to obtain the belonging probability of each trajectory point on each candidate route segment.

[0108] The observation probability represents the likelihood of matching a trajectory point to a corresponding line segment. The observation probability can be calculated based on the distance from the trajectory point to each candidate line segment; the shorter the distance, the higher the observation probability. The transition probability represents the likelihood of transitioning from a candidate line segment of the previous adjacent trajectory point to a candidate line segment of the current trajectory point.

[0109] Specifically, the server will use the timestamp of each trajectory point as the current trajectory point, determine the corresponding candidate line segments for the current trajectory point, generate the observation probability and transfer probability of the current trajectory point on the corresponding candidate line segments, and then weight the observation probability and transfer probability of each trajectory point on the corresponding candidate line segments to obtain the belonging probability of each trajectory point on the corresponding candidate line segments.

[0110] In practical applications, when weighting the observation probability and transition probability of each trajectory point on its respective candidate line segment, the weighting coefficients can be configured according to the actual application scenario, and the sum of the weighting coefficients is 1. In one specific application, the weighting coefficients for observation probability and transition probability can be the same, i.e., both 0.5. In another specific application, the weighting coefficient for transition probability can be greater than the weighting coefficient for observation probability; for example, the weighting coefficient for transition probability can be 0.7, and the weighting coefficient for observation probability can be 0.3.

[0111] In this embodiment, by generating the observation probability and transition probability of each trajectory point on each candidate route segment, and by weighting the observation probability and transition probability of each trajectory point on each candidate route segment, the belonging probability of each trajectory point on each candidate route segment can be obtained. Thus, the belonging probability can be used to accurately determine whether each trajectory point is on each candidate route segment, thereby achieving accurate vehicle route matching.

[0112] In one embodiment, generating the observation probability and transition probability of each trajectory point on the corresponding candidate line segment includes:

[0113] Each trajectory point is sequentially used as the current trajectory point to obtain the distance between the current trajectory point and the corresponding candidate line segments;

[0114] Based on the distance between the current trajectory point and each corresponding candidate route segment, the observation probability of the current trajectory point on each corresponding candidate route segment is obtained. The observation probability is negatively correlated with the distance.

[0115] When the current trajectory point is the first trajectory point, the transition probability of the current trajectory point on each corresponding candidate line segment is determined to be the preset probability;

[0116] When the current trajectory point is not the first trajectory point, based on each candidate route segment of the current trajectory point, the corresponding transfer route segment is obtained from each candidate route segment of the previous trajectory point adjacent to the current trajectory point. Based on each candidate route segment of the current trajectory point and the transfer route segment corresponding to the candidate route segment, the transfer probability of the current trajectory point on each corresponding candidate route segment is obtained. The transfer route segment and the corresponding candidate route segment belong to the same map route.

[0117] Specifically, the server sequentially uses each trajectory point as the current trajectory point. Based on the position of the current trajectory point and the positions of the corresponding candidate route segments on the map, it obtains the distance between the current trajectory point and each candidate route segment. Based on the distance between the current trajectory point and each candidate route segment, it obtains the observation probability of the current trajectory point on each candidate route segment. The observation probability is negatively correlated with the distance. In practical applications, the server can obtain the observation probability of the current trajectory point on each candidate route segment based on the distance between the current trajectory point and each candidate route segment and a pre-configured observation probability calculation formula. The pre-configured observation probability calculation formula can be configured according to the actual application scenario, as long as it satisfies the negative correlation between the observation probability and the distance. In this embodiment, the pre-configured observation probability calculation formula is not specifically limited.

[0118] Specifically, since the transition probability represents the likelihood of transitioning from a candidate line segment of an adjacent previous trajectory point to a candidate line segment of the current trajectory point, and the first trajectory point does not have an adjacent previous trajectory point, when generating the transition probability of each trajectory point on its corresponding candidate line segments, the server needs to first determine whether the current trajectory point is the first trajectory point. If the current trajectory point is the first trajectory point, the transition probability of the current trajectory point on its corresponding candidate line segments is set to the preset probability. If the current trajectory point is not the first trajectory point, based on the candidate line segments of the current trajectory point, the corresponding transition line segments are obtained from the candidate line segments of the corresponding previous trajectory point. Then, based on the candidate line segments of the current trajectory point and the corresponding transition line segments, the transition probability of the current trajectory point on its corresponding candidate line segments is obtained. The transition line segments and the corresponding candidate line segments belong to the same map line. The preset probability can be configured according to the actual application scenario. For example, the preset probability can be 0.

[0119] In a specific application, an example is given to illustrate the determination of transfer route segments and the calculation of transfer probabilities. Assume trajectory point A is the first trajectory point, which has no adjacent previous trajectory point. Therefore, its transfer probability on each candidate route segment (a1, a2) is a preset probability. Trajectory point B is the second trajectory point, which has an adjacent previous trajectory point A. Based on the candidate route segments (b1, b2) of trajectory point B, the server will obtain the corresponding transfer route segments from each candidate route segment (a1, a2) of trajectory point A. Since a1 and b1 belong to the same map route 1, the transfer route segment for b1 is a1. Since a2 and b2 belong to the same map route 2, the transfer route segment for b2 is a2.

[0120] In practical applications, when obtaining the transition probability of the current trajectory point on each candidate line segment and the corresponding transition line segment based on the current trajectory point, the server determines the first projection point of the current trajectory point on the corresponding candidate line segment and the second projection point of the adjacent previous trajectory point on the transition line segment for each candidate line segment of the current trajectory point. The sum of the difference between the horizontal coordinates and the vertical coordinates of the first projection point and the second projection point on the map is determined as the projection point distance, and the sum of the difference between the horizontal coordinates and the vertical coordinates of the current trajectory point and the adjacent previous trajectory point on the map is determined as the trajectory point distance. The ratio of the projection point distance to the trajectory point distance is determined as the transition probability.

[0121] In this embodiment, by sequentially taking each trajectory point as the current trajectory point, the distance between the current trajectory point and each corresponding candidate line segment is obtained. Based on the distance between the current trajectory point and each corresponding candidate line segment, the observation probability can be calculated. At the same time, by determining whether the current trajectory point is the first trajectory point, different methods can be used to calculate the transition probability.

[0122] In one embodiment, based on at least one candidate route segment, vehicle trajectory data is divided into trip segments to obtain at least two trip segments, including:

[0123] Based on at least one candidate route segment, determine at least one candidate map route from at least one map route;

[0124] For each candidate map route in at least one candidate map route, project multiple trajectory points onto the corresponding candidate map route to obtain the projection points of each trajectory point under the corresponding candidate map route.

[0125] Based on the candidate map route and the projection points of each trajectory point under the candidate map route, determine the trajectory points for trip segmentation.

[0126] Based on the trajectory points of each trip, the trip is divided into trip segments to obtain the corresponding trip segments of the candidate map route.

[0127] Each candidate map route is treated as at least two segments.

[0128] The trip segmentation trajectory point refers to the trajectory point used for trip segmentation. Specifically, it can include a first target trajectory point representing the starting station or the ending station, and a second target trajectory point representing the vehicle's reversal. The starting station refers to the first station in the candidate map route, and the ending station refers to the last station in the candidate map route. For example, when the candidate map route is a public transportation route, the starting station is the first station in the public transportation route, and the ending station is the last station in the public transportation route. Vehicle reversal refers to the situation where the vehicle moves backward during operation.

[0129] Specifically, the server will use a map route that includes any segment from at least one candidate route as a candidate map route to determine at least one candidate map route from at least one map route. For each candidate map route, multiple trajectory points are projected onto the corresponding candidate map route to obtain the projection points of each trajectory point under the corresponding candidate map route. Based on the first and last stations in the corresponding candidate map route and the projection points of each trajectory point under the corresponding candidate map route, a first target trajectory point representing the starting station or the ending station is determined, and it is determined whether there is a second target trajectory point representing the vehicle's reversal. If a second target trajectory point exists, the first and second target trajectory points are used as trip segmentation trajectory points for trip division. Trip division is performed based on the first and second target trajectory points to obtain the corresponding trip segments of the corresponding candidate map route. If no second target trajectory point exists, the first target trajectory point is used as the trip segmentation trajectory point. Trip division is performed based on the first target trajectory point to obtain the corresponding trip segments of the corresponding candidate map route. After obtaining the corresponding trip segments for each candidate map route, each corresponding trip segment for each candidate map route will be treated as at least two trip segments.

[0130] In practical applications, when performing trip segmentation based on the first and second target trajectory points to obtain the corresponding trip segments of the target candidate map route, the server merges the second target trajectory points to obtain merged trajectory points. The first target trajectory point and the merged trajectory point are then used as split points for trip segmentation to obtain the corresponding trip segments of the target candidate map route. When performing trip segmentation based on the first target trajectory point to obtain the corresponding trip segments of the target candidate map route, the server directly uses the first target trajectory point as the split point for trip segmentation. Specifically, when merging the second target trajectory points to obtain merged trajectory points, the server merges at least two consecutively generated trajectory points from the second target trajectory points into one merged trajectory point.

[0131] In practical applications, the server calculates the first distance between the first station in the target candidate map route and the projection points of each trajectory point under the target candidate map route. The trajectory points corresponding to the projection points whose first distance to the first station is less than a preset first distance threshold are used as the first target trajectory points representing the starting station. The server also calculates the second distance between the last station in the target candidate map route and the projection points of each trajectory point under the target candidate map route. The trajectory points corresponding to the projection points whose second distance to the last station is less than a preset second distance threshold are used as the first target trajectory points representing the ending station. The preset first distance threshold and the preset second distance threshold can be configured according to the actual application scenario; they can be the same or different. This embodiment does not limit this.

[0132] In practical applications, the server can determine the projection point representing vehicle reversal based on a first distance or a second distance, and then use the trajectory point corresponding to the projection point representing vehicle reversal as the second target trajectory point. In one specific application, as trajectory points are generated, the first distance between the projection point of the trajectory point on the target candidate map route and the first station on the target candidate map route should increase. If the first distance continuously decreases as trajectory points are generated, then the existence of a projection point representing vehicle reversal can be confirmed. In another specific application, as trajectory points are generated, the second distance between the projection point of the trajectory point on the target candidate map route and the last station on the target candidate map route should decrease. If the second distance continuously increases as trajectory points are generated, then the existence of a projection point representing vehicle reversal can be confirmed.

[0133] It should be noted that, due to potential data drift at individual trajectory points, to accurately determine vehicle reversal, the determination of a projection point representing vehicle reversal needs to be based on the continuous occurrence of either a first decreasing distance or a second increasing distance. This continuous occurrence can be limited by the number of consecutive occurrences, which can be configured according to the actual application scenario. For example, three consecutive occurrences can be considered continuous occurrences.

[0134] In this embodiment, for each candidate map route in at least one candidate map route, by projecting multiple trajectory points onto the target candidate map route, the projection points of each trajectory point under the target candidate map route can be obtained. Then, based on the target candidate map route and the projection points of each trajectory point under the target candidate map route, the trip segmentation trajectory points used for trip segmentation can be determined. Thus, accurate trip segmentation can be achieved based on the trip segmentation trajectory points, and the corresponding trip segments of the target candidate map route can be obtained, thereby obtaining at least two trip segments.

[0135] In one embodiment, based on the probability of each trajectory point belonging to each corresponding candidate route segment, at least two trip segments are quantitatively evaluated to obtain the corresponding quantitative evaluation results for each of the at least two trip segments, including:

[0136] For each of the at least two trip segments, based on the probability of each trajectory point belonging to each candidate route segment, the average adsorption score of the trajectory points in each trip segment is obtained, and the route completeness of the trajectory points in each trip segment is calculated.

[0137] The average adsorption score of trajectory points in each segment and the route completeness are weighted separately to obtain the trip matching completeness of trajectory points in each segment;

[0138] Based on the completeness of the trajectory point matching in each segment, the corresponding quantitative evaluation results of the targeted segment are obtained.

[0139] The average adsorption score represents the probability that a trajectory point in each segment lies on the corresponding segment. The route completeness refers to the coverage of a trajectory point within a segment relative to the candidate map route corresponding to that segment. The segment matching completeness of trajectory points indicates the degree of matching between the trajectory points in the segment and the corresponding segment; a higher segment matching completeness indicates a higher degree of matching.

[0140] Specifically, since each target segment corresponds to at least one candidate map route, the server, based on the candidate map route corresponding to the target segment, can filter the probability of each trajectory point's assignment to a candidate route segment under the corresponding candidate map route. This probability can then be used as the average adsorption score for each trajectory point in each segment of the target segment. After obtaining the average adsorption score, the server calculates the route completeness of each trajectory point, weighting the average adsorption score and route completeness to obtain the route matching completeness of each trajectory point. Based on this completeness, a quantitative evaluation result for the target segment is obtained.

[0141] In practical applications, when weighting the average adsorption score and route completeness of trajectory points in each segment, the weighting coefficients can be configured according to the actual application scenario, and the sum of the weighting coefficients is 1. In one specific application, the weighting coefficients for the average adsorption score and route completeness can be the same, i.e., both 0.5. In another specific application, the weighting coefficient for the average adsorption score can be greater than the weighting coefficient for route completeness. In yet another specific application, the weighting coefficient for the average adsorption score can be less than the weighting coefficient for route completeness.

[0142] In practical applications, when obtaining the quantitative evaluation result for a specific trip segment based on the trip matching completeness of trajectory points in each trip segment, the server will superimpose the trip matching completeness of trajectory points in each trip segment to obtain the trip matching completeness for that specific trip segment. Then, based on this trip matching completeness, the server will obtain the quantitative evaluation result for that specific trip segment. In a particular application, the server can directly use the trip matching completeness for that specific trip segment as the quantitative evaluation result for that specific trip segment.

[0143] In a specific application, since the probability of each trajectory point being assigned to a candidate route segment under the candidate map route corresponding to the targeted trip segment can be used as the average adsorption score of the trajectory points in each trip segment, the average adsorption score of the trajectory points can be calculated by the following formula:

[0144] Score trip_match =α1*P emission +α2*P transition

[0145] Among them, Score trip_match P represents the average adsorption score (i.e., the probability of belonging). emission Let P be the observation probability, α1 be the weighting coefficient of the observation probability, and P be the observation probability. transition α is the transition probability, and α2 is the weighting coefficient of the transition probability.

[0146] In a specific application, the completeness of the pass matching of trajectory points in a pass segment can be calculated using the following formula:

[0147] Score trip_match_cover =α1*Score trip_cover +α2*Score trip_match

[0148] Among them, Score trip_match_cover Score represents the completeness of the pass matching of trajectory points in a pass segment. trip_cover The score represents the completeness of the route trips, where α1 is the weighting coefficient for the completeness of the route trips. trip_matchα2 is the weighting coefficient for the average adsorption score.

[0149] In this embodiment, the probability of a trajectory point in each segment being on the target segment can be quantitatively evaluated based on the attribution probability, and the average adsorption score of the trajectory point in each segment can be obtained. By calculating the line completeness of the trajectory point in each segment, and weighting the average adsorption score and line completeness of the trajectory point in each segment respectively, the line matching completeness of the trajectory point in each segment can be quantitatively evaluated, and the line matching completeness of the trajectory point in each segment can be obtained. Thus, based on the line matching completeness of the trajectory point in each segment, the quantitative evaluation of the target segment can be achieved, and the corresponding quantitative evaluation result of the target segment can be obtained.

[0150] In one embodiment, the quantitative evaluation result for the corresponding trip segment is obtained based on the trip matching completeness of trajectory points in each trip segment, including:

[0151] The completeness of the trip matching of the trajectory points in each trip segment is superimposed to obtain the completeness of the trip matching of the corresponding trip segment;

[0152] Obtain the quantitative evaluation value of the target trip segment, which includes at least one of the following: station matching degree, trip trajectory point coverage, and operating time score;

[0153] The weighted fusion of the quantitative evaluation value of the target segment and the corresponding segment matching completeness is used to obtain the corresponding quantitative evaluation result of the target segment.

[0154] The trip segment evaluation quantification value refers to the quantification value used to evaluate a trip segment, including at least one of the following: station matching degree, in-trip trajectory point coverage, and operating time score. Station matching degree refers to the degree of matching between the trajectory points in each segment of the target trip and the stations of the corresponding candidate map route. In-trip trajectory point coverage indicates the number of trajectory points in the trip segment relative to the coverage of trajectory points in the vehicle trajectory data. The operating time score is the score obtained by scoring the target trip segment based on the operating time of the corresponding candidate map route. The operating time of the candidate map route refers to the vehicle operating time of vehicles running along the candidate map route.

[0155] Specifically, the server overlays the trip matching completeness of trajectory points in each trip segment to obtain the corresponding trip matching completeness for that trip segment, and then obtains the trip segment evaluation quantification value for that trip segment. The trip segment evaluation quantification value and the corresponding trip matching completeness for that trip segment are then weighted and fused to obtain the corresponding quantitative evaluation result for that trip segment. The trip segment evaluation quantification value includes at least one of the following: station matching degree, trajectory point coverage within the trip, and operating time score.

[0156] In practical applications, the server determines the number of stations to be reached based on the location and speed of trajectory points in each segment. Here, a station refers to a station in the candidate map route corresponding to the target segment. After determining the number of stations to be reached, the server calculates the ratio of the number of stations to the total number of stations in the candidate map route corresponding to the target segment, and uses this ratio as the station matching degree.

[0157] In a specific application, arrival at a station can be determined in the following ways: If the speed within the station area is less than a speed threshold, the station can be considered to have arrived. The station area and speed threshold can be configured according to the actual application scenario. If there is a deceleration action within the area before the station and an acceleration action within the area after the station (i.e., acceleration less than 0 within the area before the station and acceleration greater than 0 within the area after the station), the station can also be considered to have arrived. The area before and after the station can be configured according to the actual application scenario. If the speed within the station area is significantly lower than the average driving speed outside the station area (less than N times), the station can also be considered to have arrived. The station area, non-station area, and N can be configured according to the actual application scenario.

[0158] In practical applications, the server counts the number of trajectory points in a trip segment and calculates the ratio of the number of trajectory points in the trip segment to the number of trajectory points in the vehicle trajectory data. This ratio is used as the trajectory point coverage in the trip. By analyzing the trajectory point coverage in the trip segment, the importance of the target trip segment to the trajectory points in the vehicle trajectory data can be determined.

[0159] In practical applications, the server obtains the operating time of the candidate map routes corresponding to the targeted trip segment. It compares this operating time with the timestamps of trajectory points in the first segment of the targeted trip segment to determine if the targeted trip segment is within the operating time. If the timestamp of the trajectory point in the first segment corresponds to the operating time, the targeted trip segment is within the operating time, and the server sets the operating time score as the first operating time score. If the timestamp of the trajectory point in the first segment does not correspond to the operating time, the targeted trip segment is not within the operating time, and the server sets the operating time score as the second operating time score. The first and second operating time scores can be configured according to the actual application scenario, with the first operating time score being higher than the second operating time score. By analyzing the operating time scores, the server can accurately determine whether the targeted trip segment matches the corresponding candidate map routes, avoiding inaccurate route matching due to a mismatch between the travel time of the targeted trip segment and the operating time of the candidate map routes, thus improving the accuracy of vehicle route matching.

[0160] In a specific application, the quantitative evaluation result can be calculated using the following formula:

[0161] Score trip_total =α1*ΣScore trip_match_cover +α2*Score stop_match +α3*Score point_cover +α4*Score operate_time

[0162] Among them, Score trip_total To quantify the evaluation results, Score trip_match_cover ∑Score represents the completeness of the pass matching of trajectory points in a pass segment. trip_match_cover Score represents the completeness of the corresponding pass match for the specified pass segment, where α1 is the weighting coefficient for the completeness of the corresponding pass match for the specified pass segment. stop_match The site relevance score is α2, where α2 is the weighting coefficient for the site relevance score. point_cover Score represents the coverage of trajectory points during a single trip, α3 is the weighting coefficient for the coverage of trajectory points during a single trip, and Score is the weighting coefficient for the coverage of trajectory points during a single trip. operate_time α4 is the weighting coefficient for the operating time score.

[0163] In this embodiment, by superimposing the completeness of the trajectory points in each segment, the completeness of the corresponding segment can be obtained. Thus, based on the obtained segment evaluation quantification value of the target segment, the segment evaluation quantification value and the corresponding completeness of the target segment can be weighted and fused to achieve quantitative evaluation by combining the segment evaluation quantification value and the corresponding completeness of the target segment, thereby obtaining an accurate quantitative evaluation result for the target segment.

[0164] In one embodiment, route planning is performed based on the quantitative evaluation results of at least two trip segments to obtain vehicle route matching results, including:

[0165] Sort at least two train segments according to their respective start times to obtain a train segment sequence;

[0166] Based on the quantitative evaluation result of the first segment in the segment sequence, the current route matching score is obtained;

[0167] Starting from the second segment, each segment in the segment sequence is taken as the current segment. Based on the quantitative evaluation result of the current segment, at least one route planning score is obtained for the current segment.

[0168] When the maximum route planning score in at least one route planning score of the current trip segment is the target route planning score that meets the score update condition, the target route planning score is updated to the current route matching score.

[0169] The vehicle route matching result is obtained based on the latest current route matching score of the corresponding route segment after all segments in the route sequence have been traversed.

[0170] The trip start time refers to the time when the trip begins, specifically the time node corresponding to the timestamp of the trajectory point in the first trip. The score update condition refers to the conditions for updating the matching score of the current route, which can be configured according to the actual application scenario. For example, the score update condition could be that the maximum route planning score is greater than the current route matching score.

[0171] Specifically, the server sorts at least two trip segments according to their respective start times to obtain a trip segment sequence. The quantitative evaluation result of the first trip segment in the trip segment sequence is used as the current route matching score. Starting from the second trip segment, each trip segment in the trip segment sequence is used as the current trip segment. Based on the quantitative evaluation result of the current trip segment and the quantitative evaluation results of the trip segments preceding the current trip segment in the trip segment sequence, route planning is performed to obtain at least one route planning score for the current trip segment. When the largest route planning score among the at least one route planning scores of the current trip segment is the target route planning score that meets the score update condition, the target route planning score is updated to the current route matching score. This process continues until all trip segments in the trip segment sequence have been traversed, meaning that starting from the second trip segment, all trip segments in the trip segment sequence have been used as the current trip segment. Based on the latest current route matching score, the corresponding trip segment is used to obtain the vehicle route matching result.

[0172] In practical applications, if the maximum route planning score among at least one route planning score for the current trip segment is not the target route planning score that satisfies the score update condition, the current route matching score will not be updated. The latest current route matching score corresponds to at least one trip segment, and each trip segment has corresponding candidate map routes. Based on the trip segment corresponding to the latest current route matching score, the server can determine the candidate map routes that match that trip segment, and thus use the matching candidate map routes as the vehicle route matching results.

[0173] In this embodiment, by sorting at least two trip segments, a trip segment sequence can be obtained. Based on the trip segment sequence, route planning can be solved according to the order in which the trip segments appear. When solving the route planning problem, it is determined whether the current route matching score should be updated by judging whether the maximum route planning score among at least one route planning score of the current trip segment meets the score update condition. This can achieve accurate updating of the current route matching score, thereby achieving accurate route planning and obtaining vehicle route matching results.

[0174] In one embodiment, obtaining at least one route planning score for the current trip segment based on the quantitative evaluation results of the current trip segment includes:

[0175] If there is at least one set of combinable segments in the current segment, the current segment is combinated with at least one set of combinable segments to obtain at least one set of combined segments for the current segment.

[0176] For each of at least one set of combined trip segments, the route planning score for the combined trip segment is obtained based on the quantitative evaluation results of each segment in the combined trip segment.

[0177] The route planning score of each group of combined trips is used as at least one route planning score for the current trip.

[0178] Among them, a splicable segment refers to a segment in the segment sequence that precedes the current segment and can be spliced ​​together with the current segment. For example, a splicable segment is a segment whose overlap rate with the current segment is less than the overlap rate threshold. Here, the overlap rate can specifically refer to at least one of the travel time overlap rate and the position overlap rate, and the overlap rate threshold can be configured according to the actual application scenario.

[0179] Specifically, the server determines whether there is at least one set of combinable segments for the current trip. If there is, the server concatenates the current trip with each of these combinable segments to obtain at least one set of combined trip segments. For each of these combined trip segments, the server adds the quantitative evaluation results of each segment within that combined trip segment to obtain a route planning score for that combined trip segment. The route planning scores of each combined trip segment are then used as at least one route planning score for the current trip. In practical applications, if there is no set of combinable segments for the current trip, the server directly uses the quantitative evaluation result of the current trip as at least one route planning score for that trip.

[0180] In specific applications, the server can determine at least one set of combinable segments for the current segment by calculating the travel time overlap rate between the current segment and each segment preceding the current segment in the segment sequence. The travel time overlap rate between each combinable segment in the at least one set of combinable segments and the current segment is less than the travel time overlap rate threshold. Furthermore, when the at least one set of combinable segments includes at least two combinable segments, the travel time overlap rate between each pair of combinable segments is less than the travel time overlap rate threshold.

[0181] In a specific application, for each segment in the trip sequence, the travel time of that segment can be obtained based on the timestamps of the trajectory points in the last segment and the timestamps of the trajectory points in the first segment. That is, the time interval between the timestamps of the trajectory points in the first and last segments is the travel time. For example, assuming the timestamp of the trajectory point in the last segment is 12:00 and the timestamp of the trajectory point in the first segment is 11:00, then the travel time of the segment is 11:00-12:00. If there is a segment with a travel time of 10:30-11:30, then the travel time overlap rate between this segment and the segment in question is 50%. The travel time overlap rate threshold can be configured according to the actual application scenario.

[0182] In specific applications, the server can determine at least one set of splicable segments for the current segment by calculating the positional overlap rate of the current segment and each segment preceding the current segment in the segment sequence. The positional overlap rate between each splicable segment in the at least one set of splicable segments and the current segment is less than the positional overlap rate threshold. Furthermore, when the at least one set of splicable segments includes at least two splicable segments, the positional overlap rate between each pair of splicable segments is less than the positional overlap rate threshold.

[0183] In a specific application, the positional overlap rate between any two train segments can be obtained based on the number of identical trajectory points in the two segments and the total number of trajectory points in the two segments. For example, the positional overlap rate between any two train segments can be the ratio of the smaller of the number of identical trajectory points in the two segments and the total number of trajectory points in the two segments. For instance, if there are 10 identical trajectory points in two train segments, one segment has a total of 100 trajectory points, and the other segment has a total of 110 trajectory points, then the positional overlap rate between the two train segments is 10%.

[0184] In a specific application, assuming the segment sequence is segment A-segment B-segment C, when solving the route planning problem, the server first uses the quantitative evaluation result of segment A as the current route matching score. Starting from segment B, it sequentially uses segments in the segment sequence (i.e., segment B, segment C, and segment D) as the current segment. Based on the quantitative evaluation result of the current segment, it obtains at least one route planning score for the current segment. When the largest route planning score among the at least one route planning score of the current segment is the target route planning score that satisfies the score update condition, the target route planning score is updated to the current route matching score. This process continues until all segments in the segment sequence have been traversed, and the vehicle route matching result is obtained based on the latest current route matching score for the corresponding segment.

[0185] The server first takes segment B as the current segment and determines whether segment A is a set of segments that can be spliced ​​together from segment B. If the overlap rate between segment A and segment B is less than the overlap rate threshold, then segment A can be a set of segments that can be spliced ​​together from segment B. The combined segment of segment B is segment A + segment B. For the combined segment (segment A + segment B), the quantitative evaluation results of segment A and segment B are superimposed to obtain the route planning score of the targeted combined segment (segment A + segment B). Obviously, the route planning score of the combined segment (segment A + segment B) is the target route planning score that meets the score update conditions. The route planning score of (segment A + segment B) is then updated to the current route matching score. If the overlap rate between trip segment A and trip segment B is greater than the overlap rate threshold, then they cannot be considered as a set of connectable trip segments of trip segment B. The server will directly use the quantitative evaluation result of trip segment B as at least one route planning score for trip segment B. If the quantitative evaluation result of trip segment B is greater than the quantitative evaluation result of trip segment A, then the quantitative evaluation result of trip segment B is considered to be the target route planning score that meets the score update conditions, and the quantitative evaluation result of trip segment B is updated to the current route matching score. Otherwise, the current route matching score is not updated.

[0186] Next, the server will use segment C as the current segment. If the overlap rate between segment A and segment C is less than the overlap rate threshold, the overlap rate between segment B and segment C is less than the overlap rate threshold, and the overlap rate between segment A and segment B is less than the overlap rate threshold, then a set of segments that can be spliced ​​together for segment C can be obtained as segment A + segment B, and the corresponding combined segment is segment A + segment B + segment C. By superimposing the quantitative evaluation results of segments A, B, and C, the route planning score of the combined segment (segment A + segment B + segment C) can be obtained. Obviously, the route planning score of the combined segment (segment A + segment B + segment C) is the target route planning score that meets the score update conditions. The route planning score of (segment A + segment B + segment C) is then updated to the current route matching score.

[0187] If the overlap rate of segment A and segment C is less than the overlap rate threshold, the overlap rate of segment B and segment C is less than the overlap rate threshold, and the overlap rate of segment A and segment B is greater than the overlap rate threshold, then at least one set of splicable segments for segment C can be obtained, namely segment A and segment B, and the corresponding at least one set of combined segments are (segment A + segment C) and (segment B + segment C). The server will overlay the quantitative evaluation results of trip A and trip C to obtain the route planning score of the combined trip (trip A + trip C), and then overlay the route planning scores of trip B and trip C to obtain the route planning score of the combined trip (trip B + trip C). The route planning scores of each combined trip will be used as at least one route planning score for trip C. When the largest route planning score among at least one route planning score of trip C (the route planning score of the combined trip (trip A + trip C) or the route planning score of the combined trip (trip B + trip C)) is the target route planning score that meets the score update conditions, the target route planning score will be updated to the current route matching score; otherwise, the current route matching score will not be updated.

[0188] In this embodiment, when there is at least one set of combinable segments in the current trip segment, the current trip segment is combined with at least one set of combinable segments to obtain at least one set of combined trip segments in the current trip segment. Thus, for each of the at least one set of combined trip segments, the route planning score of the target combined trip segment can be obtained based on the quantitative evaluation results of each segment in the target combined trip segment. Furthermore, the route planning score of each set of combined trip segments can be used as at least one route planning score of the current trip segment, thereby enabling the route planning solution for the current trip segment.

[0189] In one embodiment, such as Figure 6 As shown in the diagram, the vehicle route matching method of this application is illustrated by a flowchart, which specifically includes the following steps:

[0190] Step 602: Obtain at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data from multiple trajectory points.

[0191] Step 604: From at least one map route, determine at least one candidate route segment corresponding to each trajectory point;

[0192] Step 606: Generate the observation probability and transition probability of each trajectory point on the corresponding candidate line segment;

[0193] Step 608: Weight the observation probability and transfer probability of each trajectory point on each candidate route segment to obtain the ownership probability of each trajectory point on each candidate route segment.

[0194] Step 610: Based on at least one candidate route segment, determine at least one candidate map route from at least one map route;

[0195] Step 612: For each candidate map route in at least one candidate map route, project multiple trajectory points onto the corresponding candidate map route to obtain the projection points of each trajectory point under the corresponding candidate map route.

[0196] Step 614: Based on the candidate map route and the projection points of each trajectory point under the candidate map route, determine the trajectory points for trip segmentation.

[0197] Step 616: Perform trip segmentation based on the trip segmentation trajectory points to obtain the corresponding trip segments of the candidate map route.

[0198] Step 618: For each candidate map route, the corresponding segment is treated as at least two segments;

[0199] Step 620: For each of the at least two trip segments, based on the probability of each trajectory point belonging to each candidate route segment, obtain the average adsorption score of the trajectory points in each trip segment, and calculate the route completeness of the trajectory points in each trip segment.

[0200] Step 622: Weigh the average adsorption score of the trajectory points in each segment and the route completeness to obtain the route matching completeness of the trajectory points in each segment.

[0201] Step 624: Superimpose the completeness of the trajectory points in each segment to obtain the completeness of the corresponding segment.

[0202] Step 626: Obtain the quantitative evaluation value of the target trip segment. The quantitative evaluation value of the trip segment includes at least one of the following: station matching degree, trip trajectory point coverage, and operating time score.

[0203] Step 628: Weighted fusion of the quantitative value of the trip segment evaluation and the corresponding trip matching completeness of the targeted trip segment to obtain the corresponding quantitative evaluation result of the targeted trip segment.

[0204] Step 630: Sort at least two trip segments according to their respective start times to obtain a trip segment sequence;

[0205] Step 632: Based on the quantitative evaluation result of the first segment in the segment sequence, obtain the current route matching score;

[0206] Step 634: Starting from the second segment, take the segments in the segment sequence as the current segment in turn. When there is at least one set of segments that can be spliced ​​in the current segment, splice the current segment with at least one set of segments that can be spliced ​​in turn to obtain at least one set of combined segments for the current segment.

[0207] Step 636: For each of the at least one set of combined trip segments, obtain the route planning score of the targeted combined trip segment based on the quantitative evaluation results of each segment in the targeted combined trip segment.

[0208] Step 638: Use the route planning score of each group of combined trip segments as at least one route planning score for the current trip segment.

[0209] Step 640: When the maximum route planning score among at least one route planning score in the current trip segment is the target route planning score that satisfies the score update condition, update the target route planning score to the current route matching score.

[0210] Step 642, until all segments in the segment sequence have been traversed, obtain the vehicle route matching result based on the latest current route matching score for the corresponding segment.

[0211] The public transportation information query method provided in this application embodiment can be applied to, for example... Figure 7 In the application environment shown, terminal 702 communicates with server 704 via a network. A data storage system can store the data that server 704 needs to process. The data storage system can be integrated onto server 704 or placed in the cloud or on another server. In response to a user's public transportation information query request initiated by terminal 702, server 704 determines the route identifier and station identifier, determines the target route based on the route identifier, and identifies at least one target public transportation vehicle on the target route based on the real-time routes of each public transportation vehicle. The real-time routes of each public transportation vehicle are obtained through vehicle route matching based on candidate routes in a candidate route set for each public transportation vehicle. The candidate routes in the candidate route set for each public transportation vehicle are obtained through the above vehicle route matching method. Server 704 obtains the location information of at least one target public transportation vehicle, determines the estimated arrival time of each target public transportation vehicle based on the location information and station identifier, and feeds back the public transportation information query results to terminal 702 based on the estimated arrival times of each target public transportation vehicle. Figure 8 As shown, the map application in terminal 702 will display the location of the nearest vehicle based on the public transportation information query results fed back by server 704. Figure 8 (a certain station in the map) and estimated arrival time ( Figure 8 (6 minutes in the map app), and at the same time, the map application will also display the user's current location, current station, route-related information and other information.

[0212] Among them, terminal 702 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 704 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0213] In one embodiment, such as Figure 9 As shown, a vehicle route matching method is provided, which is applied to... Figure 7 Taking a 704 error on a server as an example, the steps are as follows:

[0214] Step 902: In response to the public transportation information query request, determine the route identifier and station identifier;

[0215] Step 904: Determine the target route based on the route identifier. Based on the real-time routes of each public transport, determine at least one target public transport vehicle under the target route. The real-time routes of each public transport are obtained by vehicle route matching based on the candidate routes in the candidate route set of each public transport. The candidate routes in the candidate route set of each public transport are obtained by the above vehicle route matching method.

[0216] Step 906: Obtain the location information of at least one target public transport vehicle, and determine the estimated arrival time of each of the at least one target public transport vehicle based on the location information and station identifier;

[0217] Step 908: Based on the estimated arrival time of at least one target public transport vehicle, the public transport information query results are fed back to the sender of the public transport information query request.

[0218] Here, "Public transportation information query request" refers to a request to query public transportation information. "Route identifier" refers to the identifier of the public transportation route to be queried. For example, the route identifier can be the route number of the public transportation route to be queried. "Station identifier" refers to the identifier of the station to be queried. For example, the station identifier can be the identifier of the user's current station or the station they are about to arrive at. "Target route" refers to the public transportation route corresponding to the route identifier. "Target public transportation" refers to public transportation operating on the target route.

[0219] Specifically, when a public transportation information query is needed, the server receives the query request. Upon receiving the request, the server responds by determining the route identifier and station identifier, which can be carried in the query request. After determining the route identifier and station identifier, the server queries a pre-defined route database based on the route identifier to determine the target route. It then matches the target route with the real-time routes of various public transportation services to identify at least one target public transportation vehicle on the target route. The server obtains the location information of each of these at least one target public transportation vehicles. Based on the location information and station identifier, it calculates the estimated arrival time for each of the at least one target public transportation vehicle. Finally, based on the estimated arrival time of each of the at least one target public transportation vehicle, the server sends the public transportation information query result back to the sender of the query request.

[0220] In practical applications, when associating a target route with real-time routes of various public transportation systems, if the name of the real-time route is the same as the name of the target route, then the public transportation currently operating under the real-time route can be used as the target public transportation under the target route. Station locations can be obtained based on station identifiers, allowing for the calculation of the estimated arrival time of at least one target public transportation unit based on the location information and station locations.

[0221] In practical applications, real-time routes for each public transportation system are obtained through vehicle route matching based on candidate routes from a pool of candidate routes for each public transportation system. During vehicle route matching, the server retrieves trajectory data for each public transportation system used for route matching and then performs route matching based on this trajectory data. The trajectory data used for route matching can be selected according to the actual application scenario. For example, the trajectory data used for route matching could specifically be trajectory data from the past five hours.

[0222] In a specific application, when matching candidate routes in the candidate route set of each public transportation system based on trajectory data used for route matching, the method used is similar to the vehicle route matching method in the above embodiments. The trajectory data used for route matching corresponds to the vehicle trajectory data in the vehicle route matching method in the above embodiments, and the candidate routes in the candidate route set correspond to at least one map route in the vehicle route matching method in the above embodiments. In this embodiment, the method of matching candidate routes in the candidate route set of each public transportation system based on trajectory data used for route matching will not be described in detail here.

[0223] In practical applications, the candidate routes for each public transportation vehicle are obtained through the vehicle route matching method described above. For each public transportation vehicle, the server acquires its vehicle trajectory data and performs vehicle route matching based on the trajectory data and at least one map route to obtain the candidate routes for that public transportation vehicle. In a specific application, each vehicle route matching operation yields one candidate route; by acquiring vehicle trajectory data from different time periods, multiple candidate routes can be obtained.

[0224] The aforementioned public transportation information query method, by utilizing vehicle route matching to obtain accurate candidate route sets for each public transportation system, can quantitatively evaluate the candidate routes in each public transportation system's candidate route set to obtain the real-time routes of each public transportation system. In response to public transportation information query requests, it can determine route identifiers and station identifiers, identify target routes based on route identifiers, determine at least one target public transportation system under the target route based on the real-time routes of each public transportation system, obtain the location information of each target public transportation system, determine the estimated arrival time of each target public transportation system based on the location information and station identifiers, and then feed back the public transportation information query results to the sender of the public transportation information query request based on the estimated arrival time of each target public transportation system, thus achieving accurate feedback of public transportation information.

[0225] It should be noted that this application can be applied to Intelligent Traffic Systems (ITS). Intelligent Traffic Systems, also known as Intelligent Transportation Systems, effectively integrate advanced technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control, and vehicle manufacturing, strengthening the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, improves the environment, and saves energy. By applying the vehicle route matching method and public transportation information query method provided in this application to Intelligent Traffic Systems, accurate feedback of public transportation information can be achieved.

[0226] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0227] Based on the same inventive concept, this application also provides a vehicle route matching device for implementing the vehicle route matching method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle route matching device embodiments provided below can be found in the limitations of the vehicle route matching method described above, and will not be repeated here.

[0228] In one embodiment, such as Figure 10 As shown, a vehicle route matching device is provided, including: a data acquisition module 1002, a candidate route segment determination module 1004, a processing module 1006, a quantitative evaluation module 1008, and a route planning solution module 1010, wherein:

[0229] The data acquisition module 1002 is used to acquire at least one map route and vehicle trajectory data. The map route includes at least one route segment, and the vehicle trajectory data includes data of multiple trajectory points.

[0230] The candidate route segment determination module 1004 is used to determine at least one candidate route segment corresponding to each trajectory point from at least one map route.

[0231] The processing module 1006 is used to generate the probability of each trajectory point belonging to each candidate route segment, and to divide the vehicle trajectory data into trip segments based on at least one candidate route segment to obtain at least two trip segments.

[0232] The quantitative evaluation module 1008 is used to perform quantitative evaluation on at least two trips based on the probability of each trajectory point belonging to each candidate route segment, and obtain the corresponding quantitative evaluation results for each of the at least two trips.

[0233] The route planning solution module 1010 is used to solve the route planning based on the corresponding quantitative evaluation results of at least two trip segments to obtain the vehicle route matching results.

[0234] The aforementioned vehicle route matching device, by determining at least one candidate route segment corresponding to each trajectory point from at least one map route, and generating the belonging probability of each trajectory point on the corresponding candidate route segment, can realize the belonging analysis of each trajectory point. By dividing the vehicle trajectory data into trips based on at least one candidate route segment, at least two trip segments can be obtained. Thus, based on the belonging probability of each trajectory point on the corresponding candidate route segment, at least two trip segments can be quantitatively evaluated to obtain the corresponding quantitative evaluation results of at least two trip segments. Then, based on the corresponding quantitative evaluation results of at least two trip segments, route planning can be solved to obtain the vehicle route matching result. The entire process, by using the belonging probability and route planning solution to perform route matching at the trip segment level, can achieve accurate vehicle route matching.

[0235] In one embodiment, the processing module is further configured to generate the observation probability and transfer probability of each trajectory point on each corresponding candidate line segment, and to weight the observation probability and transfer probability of each trajectory point on each corresponding candidate line segment to obtain the belonging probability of each trajectory point on each corresponding candidate line segment.

[0236] In one embodiment, the processing module is further configured to sequentially use each trajectory point as the current trajectory point, obtain the distance between the current trajectory point and each corresponding candidate route segment, and obtain the observation probability of the current trajectory point on each corresponding candidate route segment based on the distance between the current trajectory point and each corresponding candidate route segment. The observation probability is negatively correlated with the distance. When the current trajectory point is the first trajectory point, the transfer probability of the current trajectory point on each corresponding candidate route segment is determined to be a preset probability. When the current trajectory point is not the first trajectory point, based on each candidate route segment of the current trajectory point, the corresponding transfer route segment is obtained from each candidate route segment of the previous trajectory point adjacent to the current trajectory point. Based on each candidate route segment of the current trajectory point and the transfer route segment corresponding to the candidate route segment, the transfer probability of the current trajectory point on each corresponding candidate route segment is obtained. The transfer route segment and the corresponding candidate route segment belong to the same map route.

[0237] In one embodiment, the processing module is further configured to determine at least one candidate map route from at least one map route based on at least one candidate route segment; for each candidate map route, project multiple trajectory points onto the corresponding candidate map route to obtain the projection points of each trajectory point under the corresponding candidate map route; based on the corresponding candidate map route and the projection points of each trajectory point under the corresponding candidate map route, determine the trip segmentation trajectory points for trip segmentation; perform trip segmentation based on the trip segmentation trajectory points to obtain the corresponding trip segments of the corresponding candidate map route; and take the corresponding trip segments of each candidate map route as at least two trip segments.

[0238] In one embodiment, the quantitative evaluation module is further configured to, for each of at least two trip segments, obtain the average adsorption score of the trajectory points in each trip segment based on the probability of each trajectory point belonging to each corresponding candidate route segment, calculate the route trip completeness of the trajectory points in each trip segment, weight the average adsorption score and the route trip completeness of the trajectory points in each trip segment respectively, obtain the trip matching completeness of the trajectory points in each trip segment, and obtain the corresponding quantitative evaluation result of the trip segment based on the trip matching completeness of the trajectory points in each trip segment.

[0239] In one embodiment, the quantitative evaluation module is further used to superimpose the trip matching completeness of trajectory points in each trip segment to obtain the corresponding trip matching completeness of the targeted trip segment and obtain the trip segment evaluation quantitative value of the targeted trip segment. The trip segment evaluation quantitative value includes at least one of station matching degree, trajectory point coverage in the trip, and operating time score. The trip segment evaluation quantitative value and the corresponding trip matching completeness of the targeted trip segment are weighted and fused to obtain the corresponding quantitative evaluation result of the targeted trip segment.

[0240] In one embodiment, the route planning solution module is further configured to sort at least two trip segments according to their respective trip segment start times to obtain a trip segment sequence, obtain the current route matching score based on the quantitative evaluation result of the first trip segment in the trip segment sequence, and starting from the second trip segment, sequentially use the trip segments in the trip segment sequence as the current trip segment, obtain at least one route planning score for the current trip segment based on the quantitative evaluation result of the current trip segment, and when the largest route planning score among the at least one route planning scores of the current trip segment is the target route planning score that satisfies the score update condition, update the target route planning score to the current route matching score, until all trip segments in the trip segment sequence have been traversed, and obtain the vehicle route matching result based on the trip segment corresponding to the latest current route matching score.

[0241] In one embodiment, the route planning solution module is further configured to, when there is at least one set of splicable segments in the current trip segment, splice the current trip segment with at least one set of splicable segments to obtain at least one set of combined trip segments in the current trip segment, and for each set of combined trip segments in the at least one set of combined trip segments, obtain the route planning score of the targeted combined trip segment based on the quantitative evaluation results of each trip segment in the targeted combined trip segment, and use the route planning score of each set of combined trip segments as at least one route planning score of the current trip segment.

[0242] Based on the same inventive concept, this application also provides a public transportation information query device for implementing the public transportation information query method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more public transportation information query device embodiments provided below can be found in the limitations of the public transportation information query method described above, and will not be repeated here.

[0243] In one embodiment, such as Figure 11 As shown, a public transportation information query device is provided, including: a response module 1102, a query module 1104, a prediction module 1106, and a feedback module 1108, wherein:

[0244] The response module 1102 is used to respond to public transportation information query requests and determine the route identifier and station identifier;

[0245] The query module 1104 is used to determine the target route based on the route identifier, and to determine at least one target public transport vehicle under the target route based on the real-time routes of each public transport vehicle. The real-time routes of each public transport vehicle are obtained by vehicle route matching based on the candidate routes in the candidate route set of each public transport vehicle. The candidate routes in the candidate route set of each public transport vehicle are obtained by the above vehicle route matching method.

[0246] The estimation module 1106 is used to obtain the location information of at least one target public transport vehicle and determine the corresponding estimated arrival time of at least one target public transport vehicle based on the location information and station identifier.

[0247] Feedback module 1108 is used to provide public transportation information query results to the sender of the public transportation information query request based on the estimated arrival time of at least one target public transportation vehicle.

[0248] The aforementioned public transportation information query device, by utilizing a vehicle route matching method to obtain accurate candidate route sets for each public transportation system, can quantitatively evaluate the candidate routes in each public transportation candidate route set to obtain the real-time routes of each public transportation system. In response to public transportation information query requests, it can determine route identifiers and station identifiers, identify target routes based on route identifiers, determine at least one target public transportation system under the target route based on the real-time routes of each public transportation system, obtain the location information of each target public transportation system, determine the estimated arrival time of each target public transportation system based on the location information and station identifiers, and then feed back the public transportation information query results to the sender of the public transportation information query request based on the estimated arrival time of each target public transportation system, thus achieving accurate feedback of public transportation information.

[0249] The various modules in the aforementioned vehicle route matching device and public transportation information query device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0250] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 12 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data such as vehicle trajectory data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a vehicle route matching method and a public transportation information query method.

[0251] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0252] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0253] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0254] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0255] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0256] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0257] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0258] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle line matching method characterized by, The method comprises: acquiring at least one map route and vehicle trajectory data, the map route comprising at least one route segment, and the vehicle trajectory data comprising data of a plurality of trajectory points; determining at least one candidate route segment corresponding to each trajectory point from the at least one map route; generating a belonging probability of each trajectory point on the corresponding candidate route segment, and determining at least one candidate map route from the at least one map route based on the at least one candidate route segment; projecting the plurality of trajectory points onto each candidate map route to obtain a projection point of each trajectory point under the corresponding candidate map route; determining a trip segmentation trajectory point for trip segmentation based on the corresponding candidate map route and the projection point of each trajectory point under the corresponding candidate map route; performing trip segmentation based on the trip segmentation trajectory point to obtain a corresponding trip segment of the corresponding candidate map route; regarding each corresponding trip segment of each candidate map route as at least two trip segments; performing quantitative evaluation on the at least two trip segments based on the belonging probability of each trajectory point on the corresponding candidate route segment to obtain a corresponding quantitative evaluation result of each of the at least two trip segments; and performing route planning solving based on the corresponding quantitative evaluation result of each of the at least two trip segments to obtain a vehicle route matching result.

2. The method of claim 1, wherein, The method comprises: generating an observation probability and a transition probability of each trajectory point on the corresponding candidate route segment; weighting the observation probability and the transition probability of each trajectory point on the corresponding candidate route segment to obtain the belonging probability of each trajectory point on the corresponding candidate route segment.

3. The method of claim 2, wherein, The method comprises: obtaining a distance between the current trajectory point and the corresponding candidate route segment; obtaining an observation probability of the current trajectory point on the corresponding candidate route segment based on the distance between the current trajectory point and the corresponding candidate route segment, the observation probability being negatively correlated with the distance; when the current trajectory point is the first trajectory point, determining a transition probability of the current trajectory point on the corresponding candidate route segment as a preset probability; when the current trajectory point is not the first trajectory point, obtaining a corresponding transition route segment from each candidate route segment of a previous trajectory point adjacent to the current trajectory point based on each candidate route segment of the current trajectory point, and obtaining a transition probability of the current trajectory point on the corresponding candidate route segment based on each candidate route segment of the current trajectory point and the corresponding transition route segment belonging to the same map route.

4. The method of claim 1, wherein, The method comprises: For each of the at least two segments, based on the attribution probability of each trajectory point on the corresponding candidate route segment, an average absorption score of the trajectory points in the corresponding segment is obtained, and a route segment completeness of the trajectory points in the corresponding segment is calculated; The average absorption score and the route segment completeness of the trajectory points in each of the at least two segments are weighted respectively to obtain a segment matching completeness of the trajectory points in each of the at least two segments; Based on the segment matching completeness of the trajectory points in each of the at least two segments, a corresponding quantitative evaluation result of the corresponding segment is obtained.

5. The method of claim 4, wherein, The obtaining of the corresponding quantitative evaluation result of the corresponding segment based on the segment matching completeness of the trajectory points in each of the at least two segments comprises: The segment matching completeness of the trajectory points in each of the at least two segments is superimposed to obtain a corresponding segment matching completeness of the corresponding segment; A segment evaluation quantitative value of the corresponding segment is obtained, the segment evaluation quantitative value comprising at least one of a station matching degree, a trajectory point coverage in the segment, and an operation time score; The segment evaluation quantitative value and the corresponding segment matching completeness of the corresponding segment are weighted and fused to obtain the corresponding quantitative evaluation result of the corresponding segment.

6. The method of claim 1, wherein, The solving of the route planning based on the corresponding quantitative evaluation result of each of the at least two segments comprises: The at least two segments are sorted according to the segment start time of each of the at least two segments to obtain a segment sequence; A current route matching score is obtained based on the quantitative evaluation result of the first segment in the segment sequence; From the second segment, the segments in the segment sequence are sequentially taken as a current segment, and at least one route planning score of the current segment is obtained based on the quantitative evaluation result of the current segment; When the maximum route planning score of the at least one route planning score of the current segment is a target route planning score satisfying a score updating condition, the target route planning score is updated as the current route matching score; Until the segments in the segment sequence are traversed, a vehicle route matching result is obtained based on the corresponding segment of the latest current route matching score.

7. The method of claim 6, wherein, The obtaining of the at least one route planning score of the current segment based on the quantitative evaluation result of the current segment comprises: When there are at least one group of splicable segments in the current segment, the current segment is spliced with the at least one group of splicable segments respectively to obtain at least one group of combined segments of the current segment; For each of the at least one group of combined segments, a route planning score of the corresponding combined segment is obtained based on the quantitative evaluation result of each segment in the corresponding combined segment; The route planning scores of the groups of combined segments are taken as the at least one route planning score of the current segment.

8. A public transportation information inquiry method characterized by comprising: The method comprises: In response to a public transportation information query request, a route identifier and a station identifier are determined; determine a target route based on the route identifier, determine at least one target public transport under the target route based on real-time routes of each of the public transports, the real-time routes of each of the public transports being obtained by performing vehicle route matching based on a candidate route set of each of the public transports, the candidate route set of each of the public transports being obtained by the vehicle route matching method of any one of claims 1-7; obtain position information of each of the at least one target public transport, determine a corresponding estimated arrival time of each of the at least one target public transport based on the position information and the station identifier; feed back a public transport information query result to a sender of the public transport information query request based on the corresponding estimated arrival time of each of the at least one target public transport.

9. A vehicle line matching device characterized by comprising: The device comprises: a data acquisition module configured to acquire at least one map route and vehicle trajectory data, the map route comprising at least one route segment, and the vehicle trajectory data comprising data of a plurality of trajectory points; a candidate route segment determination module configured to determine at least one candidate route segment corresponding to each trajectory point from the at least one map route; a processing module configured to generate a belonging probability of each trajectory point on a corresponding candidate route segment, and determine at least one candidate map route from the at least one map route based on the at least one candidate route segment, project the plurality of trajectory points to each candidate map route to obtain a projection point of each trajectory point on the corresponding candidate map route, determine a trip cut trajectory point for trip cut based on the corresponding candidate map route and the projection point of each trajectory point on the corresponding candidate map route, perform trip cut based on the trip cut trajectory point to obtain a corresponding trip segment of the corresponding candidate map route, and take each candidate map route as at least two trip segments; a quantitative evaluation module configured to perform quantitative evaluation on the at least two trip segments based on the belonging probability of each trajectory point on the corresponding candidate route segment to obtain a corresponding quantitative evaluation result of each of the at least two trip segments; a route planning solving module configured to perform route planning solving based on the corresponding quantitative evaluation result of each of the at least two trip segments to obtain a vehicle route matching result.

10. The apparatus of claim 9, wherein, The processing module is further configured to generate an observation probability and a transition probability of each trajectory point on the corresponding candidate route segment, weight the observation probability and the transition probability of each trajectory point on the corresponding candidate route segment respectively, and obtain the belonging probability of each trajectory point on the corresponding candidate route segment.

11. The apparatus of claim 10, wherein, The processing module is further configured to sequentially take each trajectory point as a current trajectory point, obtain distances between the current trajectory point and each corresponding candidate route segment, respectively obtain observation probabilities of the current trajectory point on each corresponding candidate route segment based on the distances between the current trajectory point and each corresponding candidate route segment, the observation probability and the distance being negatively correlated, when the current trajectory point is a first trajectory point, determine transition probabilities of the current trajectory point on each corresponding candidate route segment as a preset probability, when the current trajectory point is not the first trajectory point, respectively obtain corresponding transition route segments from each candidate route segment of a last trajectory point adjacent to the current trajectory point based on each candidate route segment of the current trajectory point, and respectively obtain transition probabilities of the current trajectory point on each corresponding candidate route segment based on each candidate route segment of the current trajectory point and the corresponding transition route segment of the candidate route segment, the transition route segment and the corresponding candidate route segment belonging to the same map route.

12. The apparatus of claim 9, wherein, The quantitative evaluation module is further configured to, for each of the at least two segments, obtain average absorption scores of trajectory points in each of the segments based on the belonging probabilities of each trajectory point on each corresponding candidate route segment, and calculate route segment completeness of the trajectory points in each of the segments, respectively weight the average absorption scores and the route segment completeness of the trajectory points in each of the segments to obtain segment matching completeness of the trajectory points in each of the segments, and obtain the corresponding quantitative evaluation result of the segment based on the segment matching completeness of the trajectory points in each of the segments.

13. The apparatus of claim 12, wherein, The quantitative evaluation module is further configured to superimpose the segment matching completeness of the trajectory points in each of the segments to obtain corresponding segment matching completeness of the segment, obtain a segment evaluation quantitative value of the segment, the segment evaluation quantitative value including at least one of a station matching degree, a segment trajectory point coverage degree, and an operation time score, and weight and fuse the segment evaluation quantitative value and the corresponding segment matching completeness of the segment to obtain the corresponding quantitative evaluation result of the segment.

14. The apparatus of claim 9, wherein, The route planning solving module is further configured to sort the at least two segments according to segment start times of the at least two segments to obtain a segment sequence, obtain a current route matching score based on a quantitative evaluation result of a first segment in the segment sequence, and from a second segment, sequentially take each segment in the segment sequence as a current segment, obtain at least one route planning score of the current segment based on a quantitative evaluation result of the current segment, and when a maximum route planning score in the at least one route planning score of the current segment is a target route planning score satisfying a score updating condition, update the target route planning score as the current route matching score, until segments in the segment sequence are traversed, and obtain a vehicle route matching result based on a segment corresponding to a latest current route matching score.

15. The apparatus of claim 14, wherein, The line planning solving module is further configured to, when the current section has at least one group of splicable sections, splice the current section with the at least one group of splicable sections respectively to obtain at least one group of combined sections of the current section, and for each group of combined sections in the at least one group of combined sections, obtain a line planning score of the corresponding group of combined sections based on the quantitative evaluation results of the sections in the corresponding group of combined sections, and take the line planning scores of the groups of combined sections as at least one line planning score of the current section.

16. A public transportation information inquiry device characterized by comprising: The device comprises: a response module configured to determine a line identifier and a station identifier in response to a public transport information query request; a query module configured to determine a target line based on the line identifier, and determine at least one target public transport under the target line based on real-time lines of the public transports, the real-time lines of the public transports being obtained by performing vehicle line matching on candidate lines in a candidate line set of the public transports, and the candidate lines in the candidate line set of the public transports being obtained by using the vehicle line matching method in any one of claims 1 to 7; an estimation module configured to obtain position information of the at least one target public transport respectively, and determine respective estimated arrival times of the at least one target public transport based on the position information and the station identifier; a feedback module configured to feed back a public transport information query result to a sender of the public transport information query request based on the respective estimated arrival times of the at least one target public transport. 17.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-16. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 8.

18. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 8.

19. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 8.

Images