Location data processing method and apparatus, management and control platform and electronic device

Abstract

A location data processing method and apparatus, a management and control platform and an electronic device, belonging to the technical field of traffic. The method comprises: acquiring current location data of and a driving route condition of each target object in real time, the driving route condition comprising a driving route and stop information (S210); according to the current location data, determining route location information of each target object on the driving routes (S220); according to the route location information and the stop information, determining a route distance between each target object and an adjacent stop (S230); and, according to an expected driving speed of each target object and the route distance corresponding to each target object, determining the arrival time of each target object arriving at the next stop, the expected driving speed being determined on the basis of the location data of each target object in the current time window and the corresponding route distance (S240).

Description

Positioning data processing method and device, control platform and electronic equipment Technical Field

[0001] The present disclosure relates to the field of transportation technology, and in particular to a positioning data processing method and device, a control platform, and electronic equipment. Background Art

[0002] For vehicles that travel along fixed stops (such as buses), quickly and accurately predicting their arrival at each stop can greatly improve passenger convenience, while facilitating vehicle scheduling and management by the control end, thereby improving resource utilization.

[0003] At present, most of the methods use the historical driving data of vehicles to summarize the patterns and predict the arrival of vehicles, which cannot achieve real-time prediction of the arrival situation, resulting in low accuracy of the vehicle arrival prediction.

[0004] Summary of the Invention

[0005] According to a first aspect of the present disclosure, a method for processing positioning data of a vehicle is provided, comprising: acquiring current positioning data and a driving route status of each target object in real time, the driving route status including driving route and station information; determining route position information of each target object on the driving route based on the current positioning data; determining a route distance between each target object and an adjacent station based on the route position information and the station information; and determining an arrival time of each target object at a next station based on an expected driving speed of each target object and the corresponding route distance of each target object, the expected driving speed being determined based on the positioning data and the corresponding route distance of each target object within a current time window.

[0006] Optionally, the method further includes: acquiring the current positioning data of each target object in real time and storing it in a message queue; consuming the data in the message queue based on streaming processing to form a location information set; acquiring the station information of the target route to form a station information set; and determining the driving route status of each target object based on the location information set and the station information set.

[0007] Optionally, determining the driving route condition of each target object includes: determining the driving trajectory corresponding to each target object based on the positioning data in the location information set; clustering each driving trajectory to obtain the route trajectory of each target object; matching each site information in the site information set with each road section information on the route trajectory to determine the correspondence between the site and the road section; a road section is a straight line segment on the route trajectory; determining the driving route condition based on each site information, the route trajectory, each road section information and the correspondence between the site and the road section.

[0008] Optionally, after clustering the driving trajectories, the method further includes: extracting key point information from the clustering results; and generating a line trajectory of each target object based on the key point information.

[0009] Optionally, the driving route condition includes information of each road section, and determining the route position information of each target object on the driving route includes: projecting the positioning point corresponding to the current positioning data onto the corresponding road section to determine the route position information of each target object on the driving route.

[0010] Optionally, the line distance includes a first line distance and a second line distance, and determining the line distance between each target object and an adjacent site includes: determining the first road section information between each target object and the previous site and the second road section information between each target object and the next site based on the line position information and adjacent site information of each target object; determining the first line distance between each target object and the previous site and the second line distance between each target object and the next site based on the first road section information and the second road section information.

[0011] Optionally, the method further includes: determining the first positioning point and the last positioning point of each target object in the current time window; the positioning points correspond to the positioning data; determining the driving distance of the current time window based on the line distance corresponding to the first positioning point and the line distance corresponding to the last positioning point; and determining the expected driving speed based on the driving distance and the duration of the current time window.

[0012] Optionally, the station information includes station locations, and determining the driving distance of the current time window includes: determining whether there is a station between the first positioning point and the last positioning point based on the station location; if there is no station, subtracting the second line distance corresponding to the first positioning point from the second line distance corresponding to the last positioning point, and using the difference result as the driving distance of the current time window; if there is a station, determining the station distance between the stations, and summing the station distance, the second distance corresponding to the first positioning point, and the first distance corresponding to the last positioning point, and using the sum result as the driving distance of the current time window.

[0013] Optionally, the method further includes: in response to the failure to obtain the positioning data of each target object at the specified time, determining the stop time of each target object at each station corresponding to the target route based on the first historical sample data of the target time period; the target time period is determined based on the rounds of the target object on the target route; based on the second historical sample data, using a pre-trained neural network prediction model, determining the travel time of each target object between each station; and determining the arrival time of each target object at each station based on the stop time and the travel time.

[0014] Optionally, the method further includes: in response to the failure to obtain the positioning data of each target object within the specified time, or the distance from the current positioning point to the projection point of the corresponding road section is greater than a preset threshold for a duration exceeding a warning threshold, generating an abnormal alarm, and the current positioning point corresponds to the current positioning data.

[0015] Optionally, the method further includes: pushing the route distance and the arrival time to an information display stand corresponding to the next stop of each target object in real time.

[0016] According to a second aspect of the present disclosure, a positioning data processing device for a vehicle is provided, comprising: an acquisition module configured to acquire, in real time, current positioning data and driving route conditions of each target object, the driving route conditions including driving route and station information; a position determination module configured to determine, based on the current positioning data, the route position information of each target object on the driving route; a distance determination module configured to determine, based on the route position information and the station information, the route distance between each target object and an adjacent station; and an arrival time determination module configured to determine, based on the expected driving speed of each target object and the route distance corresponding to each target object, the arrival time of each target object at the next station, the expected driving speed being determined based on the positioning data and the corresponding route distance of each target object within a current time window.

[0017] According to a third aspect of the present disclosure, a vehicle control platform is provided, comprising: the vehicle positioning data processing device of the above embodiment.

[0018] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned methods by executing the executable instructions.

[0019] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the methods described above is implemented.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0022] FIG1 shows an exemplary system architecture diagram of a method and apparatus for processing positioning data of a vehicle to which an embodiment of the present disclosure may be applied.

[0023] FIG2 schematically shows a flow chart of a method for processing positioning data of a vehicle in an exemplary embodiment of the present disclosure.

[0024] FIG3 schematically shows a flow chart of a process for determining a driving route condition in an exemplary embodiment of the present disclosure.

[0025] FIG4 schematically shows a schematic diagram of a route track, a station, and a road segment in an exemplary embodiment of the present disclosure.

[0026] FIG5 schematically shows a schematic diagram of projecting a site onto a road segment in an exemplary embodiment of the present disclosure.

[0027] FIG6 schematically shows a schematic diagram of the line distance from a positioning point to an adjacent site in an exemplary embodiment of the present disclosure.

[0028] FIG7 a schematically shows a process for determining the travel distance when the first and last positioning points are within one station in an exemplary embodiment of the present disclosure.

[0029] FIG7 b schematically illustrates a process for determining the travel distance when the first and last positioning points are not within a station in an exemplary embodiment of the present disclosure.

[0030] FIG8 schematically shows a structural diagram of a positioning data processing device for a vehicle in an exemplary embodiment of the present disclosure.

[0031] FIG9 schematically shows an electronic device for implementing the above method in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0033] It should be noted that, in the present disclosure, the terms "including", "configured with", and "set to" are used to express an open-ended inclusion, and mean that in addition to the listed elements / components / etc., there may be additional elements / components / etc.; the terms "first", "second", etc. are only used as labels and are not limitations on the number or order of their objects.

[0034] FIG1 illustrates an exemplary system architecture diagram of a method and apparatus for processing positioning data of a vehicle to which embodiments of the present disclosure may be applied. As shown in FIG1 , the system architecture may include: a vehicle 110, a server 120, and a display terminal 130. Vehicle 110 may be a vehicle that travels along a fixed station, such as a public transportation device (bus). Server 120 is a server that can control display terminal 130. Display terminal 130 is a terminal device that can display information, such as an electronic screen, television, or monitor installed at a station.

[0035] The technical solutions of the embodiments of the present disclosure are described in detail below:

[0036] The method for processing positioning data of a vehicle according to an embodiment of the present disclosure may be applied to the server 120 in FIG1 . Referring to FIG2 , the method for processing positioning data of a vehicle may include the following steps:

[0037] S210, obtaining the current positioning data and driving route status of each target object in real time, where the driving route status includes driving route and station information.

[0038] S220: Determine the route position information of each target object on the driving route based on the current positioning data.

[0039] S230: Determine the line distance between each target object and an adjacent site based on the line position information and site information.

[0040] S240: Determine the arrival time of each target object at the next stop based on the expected travel speed of each target object and the corresponding route distance of each target object, where the expected travel speed is determined based on the positioning data of each target object within the current time window and the corresponding route distance.

[0041] The beneficial effect of the embodiment of Figure 2 above is that the arrival time of the target object at the next stop can be predicted in real time by acquiring and processing the positioning data of the target object (vehicle) in real time. On the one hand, based on the real-time positioning data of each target object in the current time window and the corresponding route distance, the real-time prediction of the arrival time of the current target object is performed, avoiding the situation where the prediction results based on historical data cannot accurately reflect the current driving characteristics of the target object, and the driving characteristics of the target object can be quickly reflected in the predicted arrival time, thereby improving the accuracy of the arrival time prediction. On the other hand, passengers can reasonably plan their own itineraries based on the real-time predicted arrival time, improving the convenience and riding experience of passengers.

[0042] In order to make the technical solution of the present disclosure clearer, the steps of the method for processing the positioning data of a vehicle are described below.

[0043] In step S210, the current positioning data and driving route status of each target object are obtained in real time.

[0044] In this exemplary embodiment, the target object is a vehicle running on a specified traffic route, for example, the XX bus from location A to location B. One or more vehicles can run on a traffic route at the same time. The route status can include the actual route of each target object and the site information on the traffic route (such as bus stops). The site information can include the site name, site number, site identifier, site location (such as site longitude and latitude), and can also include site type (such as unchanged, newly added, updated, deleted, etc.), the route where the site is located (such as route number), site update time and other site-related information, which is not limited in this example. The route status can also include section information on the route (such as section name, section number, section identifier, etc.). The positioning data can include the GPS data of the target object (the longitude and latitude of the current location of the target object), the timestamp of the GPS data, the identifier of the target object, the number (such as the license plate number), etc., which is not limited in this example.

[0045] For example, referring to FIG3 , the driving route status can be determined offline based on the positioning data and station information of each target object, which can be achieved by the following steps:

[0046] Step S310: Acquire the current location data of each target object in real time and store it in a message queue.

[0047] In this exemplary embodiment, real-time positioning data sent by each target object is received to obtain the location information of each target object during its travel, and the location information is stored in a Kafka message queue. Kafka is an open source stream processing platform developed by the Apache Software Foundation. It is a high-throughput distributed publish-subscribe messaging system that can process all stream data in the message queue.

[0048] Step S320 : consuming data in the message queue based on streaming processing to form a location information set.

[0049] In this exemplary embodiment, the data in the message queue can be consumed based on a streaming processing engine (such as Flink, Spark Streaming). For example, the data in the message queue can be checked for data format (to eliminate data with incorrect format), and the data can be flattened to obtain multiple one-dimensional data (each data can correspond to the positioning data of a target object), and the flattened data can be written into a location information set in real time. The location information set can be a data table in a MySQL database.

[0050] Step S330: Acquire the site information of the target route to form a site information set.

[0051] In this exemplary embodiment, the site information can be acquired in advance or in real time, and this example does not limit the acquisition method. The acquired site information is stored in a site information set, which can be a data table in a MySQL database.

[0052] Step S340: Determine the driving trajectory corresponding to each target object based on the positioning data in the position information set.

[0053] In this exemplary embodiment, the driving trajectory of each target object can be drawn according to the real-time positioning data of each target object. For example, the real-time location points of each bus can be connected in chronological order to form a driving trajectory.

[0054] Step S350: clustering the driving trajectories to obtain the route trajectories of the target objects.

[0055] In this exemplary embodiment, various clustering algorithms can be used to perform clustering processing on each driving trajectory, such as the k-Means algorithm, the QuickBundles algorithm, etc. For example, the clustering processing is described using the QuickBundles algorithm as an example.

[0056] In the first step, the trajectories are numbered from 1 to N, where Vi represents the i-th trajectory. A cluster node is defined as a triplet c = (I, h, m), where I is a list of integer indices i = 1 to N, m is the number of trajectories in the cluster, and h is the sum of the trajectory distances. When a trajectory is added to a cluster, h is updated online.

[0057] In the second step, the first trajectory V1 is selected and placed in the defined cluster node c1. For each remaining trajectory, it is numbered Vi, i = 2, ..., N:

[0058] The third step is to calculate the cluster distance between the trajectory Vi and the centroid trajectory of all current cluster nodes, where the centroid trajectory of the cluster node is h / m;

[0059] The fourth step is to determine whether any clustering node has a clustering distance less than the preset clustering threshold. If so, trajectory i is added to the corresponding clustering node and the corresponding clustering node is updated; otherwise, a new clustering node is created. The above process is repeated until all N trajectories are clustered, and the generated clustering node is used as the route trajectory.

[0060] When the clustering results show multiple clusters (i.e., multiple cluster centers), the cluster center / node containing the most trajectories is selected as the route trajectory for that route. This route trajectory can be composed of multiple longitude and latitude points in the order of the driving route. This example reduces the amount of data corresponding to the trajectories by clustering the driving trajectories. This clustering process is fast and efficient.

[0061] In some embodiments, in order to further improve data processing efficiency, key point information in the clustering results may be extracted after clustering processing; and a line trajectory of each target object may be generated based on the key point information.

[0062] In this example implementation, the Douglas algorithm or function fitting can be used to extract key points from the clustering results to compress the trajectory data points and simplify the path.

[0063] Step S360 , matching the information of each station in the station information set with the information of each road section on the route track to determine the corresponding relationship between the station and the road section.

[0064] In this exemplary embodiment, a road segment can be a straight line segment on a route trajectory, for example, the route a vehicle travels between two adjacent turns. A route trajectory can include multiple road segments. As shown in FIG4 , the route trajectory includes road segment 1, road segment 2, road segment 3, road segment 4, and road segment 5. Each road segment can be numbered to distinguish it from another, and the road segment information can include starting point location information (latitude and longitude) and end point location information (latitude and longitude).

[0065] In this exemplary embodiment, the process of matching sites and road sections can be to project each site onto all road sections, and the matching road section of the site can be determined based on the projection distance between the projection point and the site. For example, the road section with the shortest projection distance can be used as the matching road section for the corresponding site. The projection method is shown in Figure 5. When the projection point of site a is on the road section (P1, P2), the projection distance is d1. When the projection point of site a is on the extension line of the road section (P1, P2), the projection distance can be the distance from site a to one end point of the road section, such as d2 or d3. This example can prepare for the real-time calculation of the subsequent path length by establishing the mapping relationship between sites and road sections in advance to meet the real-time requirements of the prediction.

[0066] Step S370: Determine the driving route status based on the information of each station, the route trajectory, the information of each road section, and the correspondence between the station and the road section.

[0067] In this exemplary embodiment, the driving route condition can be formed based on the information of each station, the route trajectory, the information of each road section and the correspondence between the stations and the road sections. The corresponding route map can also be drawn based on the driving route condition, and the correspondence between the stations and the road sections can be identified on the map.

[0068] The embodiment corresponding to Figure 3 above can ensure real-time data consumption through real-time acquisition and streaming processing of positioning data, and combine offline processing and analysis of the collected real-time data to obtain the driving route status of each target object (such as drawing a route map) to prepare for subsequent real-time arrival situation prediction and ensure the real-time prediction process.

[0069] In step S220 , the route position information of each target object on the driving route is determined based on the current positioning data.

[0070] In this exemplary embodiment, the current position (positioning point) of each target object can be determined based on the current positioning data (GPS data), and the corresponding positioning point can be mapped on the driving route to obtain the current position of each target object on the driving route.

[0071] For example, the positioning point corresponding to the current positioning data may be projected onto the corresponding road section to determine the route position information of each target object on the driving route.

[0072] In this exemplary embodiment, the positioning point is a location point determined by the current GPS positioning data. Each station (between the station and the previous station) may include one or more road sections, and the road section information within the station can be determined based on the matching relationship between the station and the road section. Based on the current positioning point, the next station information can be determined. Based on the next station information, it is determined which road sections the target object is currently located between. The positioning point is projected onto each road section, and the projection point is determined based on the projection distance (for example, the point with the shortest projection distance is used as the projection point). The road section where the projection point is located is then determined to be the road section where the target object is currently located. The projection point and the current road section can be used as the route position information of the target object on the driving route. The specific projection process can be shown in Figure 5 and will not be repeated here.

[0073] In step S230 , the route distance between each target object and an adjacent site is determined based on the route position information and site information.

[0074] In this exemplary embodiment, route distance refers to the actual distance between each target object and its adjacent station along the route. The route distance can include a first distance (the distance between the target object and the previous station along the route) and a second distance (the distance between the target object and the next station along the route).

[0075] Exemplarily, the line distance between each target object and the adjacent site may be determined through the following steps.

[0076] In the first step, based on the route position information and adjacent site information of each target object, the first section information between each target object and the previous site and the second section information between each target object and the next site are determined.

[0077] In this example embodiment, based on the location of the target object on the route, the road segment information between the location and the previous stop, namely, the first road segment and the start and end point information of the first road segment, can be determined. Based on the location of the target object on the route, the road segment information between the location and the next stop, namely, the second road segment and the start and end point information of the second road segment, can be determined.

[0078] It should be noted that a road segment can be divided into two segments using this location point. This location point serves as the end point of the first road segment, and all road segment information between the previous station and this location point serves as the first road segment information. This location point is also the starting point of the second road segment, and all road segment information between this location point and the next station serves as the second road segment information.

[0079] In the second step, a first route distance between each target object and the previous site and a second route distance between each target object and the next site are determined based on the first route section information and the second route section information.

[0080] In this example implementation, the length of each first road segment can be determined based on the start and end points of each first road segment in the first road segment information, and then the lengths of each first road segment can be summed to obtain the first route distance. Similarly, the second route distance can be obtained.

[0081] For example, as shown in Figure 6, s1, s2, and s3 are station locations, p0 and p1 are bus positioning points, and pp0 and pp1 are the projection points of p0 and p1 on the road section. The projection point pp0 divides the road section 1 into two sections, L1 and L2, and the projection point pp1 divides the road section 2 into two sections, L5 and L6. For the position point p0, the projection point is used as the position mapped to the line. The distance from p0 to the previous station s1 is L1, and the distance to the next station s2 is L2+L3; for the position point p1, its distance to the previous station s2 is L4+L5, and its distance to the next station s3 is L6+L7. Through this embodiment, the actual line distance from the positioning point to the adjacent station can be accurately determined, and the calculation time efficiency can meet the real-time requirements.

[0082] In step S240 , the arrival time of each target object at the next stop is determined based on the expected travel speed of each target object and the route distance corresponding to each target object.

[0083] In this exemplary embodiment, the expected travel speed is determined based on the positioning data of each target object within the current time window and the corresponding route distance. The length of the time window and the movement step size can be set and adjusted based on actual circumstances. For example, the time window length can be set to 5 minutes or 10 minutes, and the movement step size can be set to 5 seconds or 10 seconds, etc., but this example does not limit this. The expected travel speed can be used as the average speed of each target object to reach the next stop. The expected travel speed is divided by the route distance, and the arrival time at the next stop is determined based on this quotient.

[0084] In this example, the data used to determine the expected driving speed changes as the time window moves. That is, the expected driving speed changes dynamically over time and with the current driving conditions of the target object, making it closer to the actual situation and improving prediction accuracy.

[0085] Exemplarily, the expected driving speed may be determined through the following steps.

[0086] The first step is to determine the first and last positioning points of each target object in the current time window, wherein one or several positioning positions with similar positions can correspond to one positioning point.

[0087] In the second step, the travel distance in the current time window is determined based on the line distance corresponding to the first positioning point and the line distance corresponding to the last positioning point.

[0088] In this example implementation, it is first possible to determine whether there is a station between the first and last positioning points based on the station locations, that is, whether they cross stations. If there is no station, the second line distance corresponding to the first positioning point and the second line distance corresponding to the last positioning point are subtracted, and the difference result is used as the travel distance for the current time window. If there is a station, the station distance between the stations is determined, and the station distance, the second distance corresponding to the first positioning point, and the first distance corresponding to the last positioning point are summed, and the sum result is used as the travel distance for the current time window.

[0089] For example, as shown in Figure 7a, when the first and last positioning points are within the same station, assuming p0 is the first positioning point in the time window and p1 is the last positioning point in the time window, the figure shows that the travel distance between p0 and p1 is L2 + L3. The distance nd0 from p0 to the next station is L2 + L3 + L4, and the distance nd1 from p1 to the next station is L4. nd0 - nd1 = L2 + L3 + L4 - L4 = L2 + L3, indicating that the calculated result is consistent with the actual situation. As shown in Figure 6, when the first and last positioning points in the time window are not in the same station and there is only one station between the two positioning points, it can be seen from the figure that the driving distance between p0 and p1 is L2+L3+L4+L5; and the distance from p0 to the next station is nd0=L2+L3, and the distance from p1 to the previous station is ld1=L4+L5. Since there is only one station, the distance between stations is 0, then nd0+ld1=L2+L3+L4+L5, indicating that the calculated result is consistent with the actual situation. As shown in Figure 7b, when the first and last positioning points in the time window are not in the same station, and the distance between the two positioning points is greater than one station, it can be seen from the figure that the driving distance between p0 and p1 is L2+L3+L4+L5+L6+L7; there are two stations s2 and s3 between p0 and p1, so the distance between the stations is the distance from s2 to s3, L4+L5 (which can be obtained based on the longitude and latitude of the stations). The distance from p0 to the next station s2 is nd0=L2+L3, and the distance from p1 to the previous station s3 is ld1=L6+L7. Therefore, nd0+ld1+d23=L2+L3+L6+L7+L4+L5, indicating that the calculated result is consistent with the actual situation. It should be noted that when there are two or more stations between the first and last positioning points, the distances between the two or more stations can be added together.

[0090] The third step is to determine the expected driving speed based on the driving distance and the duration of the current time window.

[0091] In this example implementation, the quotient of the driving distance and the duration of the time window can be used as the expected driving speed, or the expected driving speed can be determined after correcting the calculation result, for example, by adding a correction factor, which is not limited in this example.

[0092] The above embodiment can quickly determine the window distance based on the time window through the line distance between the target object positioning point and the adjacent site, and then determine the expected driving speed in the time window, while improving the prediction accuracy, greatly reducing the calculation amount and improving the prediction efficiency.

[0093] During the driving process of a vehicle, the GPS signal is often interfered with in tunnels, areas with many obstacles, etc., and the GPS signal may be interrupted. For this situation, a time threshold can be set. When the signal interruption time does not exceed the specified time threshold, the most recent prediction result can be used as the current prediction result, or the most recent expected driving speed can be used to calculate the distance and arrival time to the station; when the signal interruption time exceeds the specified time threshold, the prediction result based on historical data can be used as the current prediction result. In this case, the prediction result can be marked, for example, the accuracy of the prediction result can be marked to remind the user.

[0094] In the above embodiment, the process of determining the route distance and the arrival time in steps S220-S240 can be processed in real time using a streaming processing framework to achieve real-time prediction of driving data.

[0095] In some embodiments, the method may further include the following steps:

[0096] In the first step, in response to failure to obtain positioning data of each target object at a specified time, based on first historical sample data of a target time period, the stop time of each target object at each station corresponding to the target route is determined.

[0097] In this example implementation, the target time period is determined based on the number of rounds of the target object on the target route. The time period can be divided according to the time period differences of the traffic environment that affect the driving behavior of the vehicle. For example, it can be divided into working days and non-working days. On working days, it can also be divided into morning peak, evening peak, normal time, etc. The time period can be divided according to the traffic data characteristics of each route. The time periods divided for each route can be the same or different. This example does not limit this. The rounds of the target object can be the number of vehicle trips on the route on that day, and the time period of the corresponding data can be determined based on the number of vehicle trips. The first historical sample data can be the stop time data of the target object at each station within the target time period for a period of time before the predicted day.

[0098] For example, to predict the target object's stop time at station n, the K-nearest neighbor algorithm can be used. For specific scenarios, an appropriate K value can be selected, such as K = 20. The stop times at the n-1 bus stops preceding station n can be selected as the stop time state vector at station n. The current state vector is analyzed, and then the K sample data closest to the current state vector (such as the stop time of the Xth bus at station j) are found in the first historical sample data. A weighted average of these K sample data is then taken to obtain the predicted stop time at the current station n.

[0099] In the second step, based on the second historical sample data, the pre-trained neural network prediction model is used to determine the travel time of each target object between each station.

[0100] In this example embodiment, the second historical sample data may include data on factors influencing inter-station travel time within a period of time (e.g., a week or a month) preceding the predicted day. For example, the influencing factor data may include the target object's daily average inter-station travel time, the average inter-station travel time for vehicles on the same day and shift in historical data, the time period, weather conditions, the number of intersections, and other data. The data corresponding to each factor in the influencing factor data is used to form an input vector, which is then input into a trained neural network model to output the target object's inter-station travel time. The neural network model may be a BP neural network model, and training may be performed using the factors influencing historical inter-station travel time and actual inter-station travel time as training data.

[0101] The third step is to determine the arrival time of each target object at each station based on the stop time and travel time.

[0102] In this example implementation, the arrival time of the target object at subsequent stations can be calculated step by step based on the departure time of the target object at the departure station, the stop time at each station, and the travel time between stations.

[0103] The beneficial effect of the above embodiment is that the arrival time prediction function can be maintained even when the GPS signal is interrupted, thereby avoiding interruption of the prediction result and improving the user experience.

[0104] In some embodiments, the method further includes: in response to the failure to receive the positioning data of each target object within a specified time, or the distance from the current positioning point to the projection point of the corresponding road section is greater than a preset threshold for a duration exceeding a warning threshold, generating an abnormal alarm, and the current positioning point corresponds to the current positioning data.

[0105] In this example implementation, if the positioning data of the target object is not received for a long period of time (e.g., 30 minutes), it is considered an abnormality and an abnormality alarm can be generated and fed back to the relevant object so that the relevant object can promptly investigate and handle the abnormal situation. If the distance from the positioning point to the road section projection point exceeds a preset threshold (e.g., more than 100 meters) for a certain period of time (e.g., the warning threshold is 10 minutes), an abnormality alarm is generated and fed back to the relevant object for processing. The abnormality alarm may include the alarm reason, alarm time, alarm type, and may also include relevant information such as the alarm source and alarm name, which are not limited in this example.

[0106] In some embodiments, the method further includes: pushing the route distance and arrival time to the information display stand corresponding to the next stop of each target object in real time.

[0107] In this example embodiment, when the server predicts the distance and arrival time of a target object to the next station, it can push this information to the information display stand of the next station so that the station information display stand will display the prediction result to facilitate passengers to arrange their time.

[0108] In some embodiments, the above prediction results may be pushed to the terminal device in real time, and transportation may be dispatched based on the above prediction results to improve resource utilization.

[0109] On the one hand, the present disclosure can collect and aggregate data in real time and determine the route status offline based on the real-time GPS data and station information of the vehicle during travel, even in the absence of real-time traffic condition data. When the station information is updated, the route status is updated. The prediction process is not restricted by third-party data support. At the same time, the determined route status is more consistent with the actual situation, providing a good data foundation for subsequent predictions. On the other hand, real-time processing of data based on the streaming processing framework achieves second-level predictions and improves prediction accuracy. Furthermore, by designing a prediction method based on a sliding time window and an idea of ​​determining the arrival time based on the distance between the target object and the adjacent station, the amount of calculation is greatly reduced and the prediction efficiency is improved while ensuring real-time and accuracy. In addition, the design of processing strategies for abnormal situations ensures user experience.

[0110] Corresponding to the above method embodiment, the present disclosure also discloses a positioning data processing device for a vehicle. Referring to FIG8 , FIG8 schematically shows a structural diagram 800 of the positioning data processing device for a vehicle in an exemplary embodiment of the present disclosure, including:

[0111] An acquisition module 810 is configured to acquire the current location data and travel route status of each target object in real time, where the travel route status includes travel route and station information;

[0112] The position determination module 820 is configured to determine the route position information of each target object on the driving route based on the current positioning data;

[0113] The distance determination module 830 is configured to determine the route distance between each target object and an adjacent site based on the route location information and site information;

[0114] The arrival time determination module 840 is configured to determine the arrival time of each target object at the next stop based on the expected driving speed of each target object and the corresponding route distance of each target object. The expected driving speed is determined based on the positioning data of each target object in the current time window and the corresponding route distance.

[0115] In an exemplary embodiment of the present disclosure, the apparatus further includes:

[0116] The driving route determination module is configured to obtain the current positioning data of each target object in real time and store it in a message queue; consume the data in the message queue based on streaming processing to form a location information set; obtain the station information of the target route to form a station information set; and determine the driving route status of each target object based on the location information set and the station information set.

[0117] In an exemplary embodiment of the present disclosure, the driving route determination module determines the driving route status of each target object based on the location information set and the station information set through the following steps:

[0118] Based on the positioning data in the location information set, the driving trajectory corresponding to each target object is determined; each driving trajectory is clustered to obtain the route trajectory of each target object; the information of each station in the station information set is matched with the information of each road section on the route trajectory to determine the correspondence between the station and the road section; a road section is a straight line segment on the route trajectory; based on the information of each station, the route trajectory, the information of each road section and the correspondence between the station and the road section, the driving route condition is determined.

[0119] In an exemplary embodiment of the present disclosure, the driving route determination module is further configured to: after clustering each driving trajectory, extract key point information from the clustering results; and generate a route trajectory of each target object based on the key point information.

[0120] In an exemplary embodiment of the present disclosure, the position determination module 820 is specifically configured to project the positioning point corresponding to the current positioning data onto the corresponding road section to determine the route position information of each target object on the driving route.

[0121] In an exemplary embodiment of the present disclosure, the distance determination module 830 is specifically configured to:

[0122] Based on the line position information and adjacent site information of each target object, the first section information between each target object and the previous site and the second section information between each target object and the next site are determined; based on the first section information and the second section information, the first line distance between each target object and the previous site and the second line distance between each target object and the next site are determined.

[0123] In an exemplary embodiment of the present disclosure, the arrival time determination module 840 is specifically configured to:

[0124] Determine the first and last positioning points of each target object within the current time window; the positioning points correspond to the positioning data; determine the driving distance in the current time window based on the line distance corresponding to the first and last positioning points; determine the expected driving speed based on the driving distance and the duration of the current time window.

[0125] In an exemplary embodiment of the present disclosure, the station information includes the station location, and the arrival time determination module 840 determines the travel distance in the current time window through the following steps:

[0126] Based on the station location, determine whether there is a station between the first and last positioning points; if there is no station, subtract the second line distance corresponding to the first positioning point from the second line distance corresponding to the last positioning point, and use the difference result as the driving distance for the current time window; if there is a station, determine the station distance between the stations, and sum the station distance, the second distance corresponding to the first positioning point, and the first distance corresponding to the last positioning point, and use the sum result as the driving distance for the current time window.

[0127] In an exemplary embodiment of the present disclosure, the apparatus further includes an exception handling module configured to:

[0128] In response to failure to obtain positioning data for each target object at a specified time, determining the stop time of each target object at each station corresponding to the target route based on first historical sample data for a target time period; the target time period is determined based on the number of rounds of the target object on the target route; and determining the travel time of each target object between each station using a pre-trained neural network prediction model based on second historical sample data for the target time period;

[0129] According to the stop time and travel time, the arrival time of each target object at each station is determined.

[0130] In an exemplary embodiment of the present disclosure, the apparatus further includes:

[0131] The alarm module is configured to generate an abnormal alarm in response to the failure to obtain the positioning data of each target object within a specified time, or the duration of the distance from the current positioning point to the projection point of the corresponding road section being greater than a preset threshold value exceeding the warning threshold value, and the current positioning point corresponds to the current positioning data.

[0132] In an exemplary embodiment of the present disclosure, the device further includes a push module configured to push the route distance and arrival time in real time to the information display stand corresponding to the next stop of each target object.

[0133] The specific details of each module / unit in the above device have been described in detail in the embodiment of the method part, so they will not be repeated here.

[0134] The present disclosure also provides a vehicle management and control platform, including the vehicle positioning processing device in any of the above embodiments.

[0135] In an exemplary embodiment of the present disclosure, an electronic device is further provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute all or part of the steps of the method for processing positioning data of a vehicle in this exemplary embodiment.

[0136] Figure 9 shows a schematic diagram of the structure of a computer system of an electronic device for implementing an embodiment of the present disclosure. It should be noted that the computer system 900 of the electronic device shown in Figure 9 is only an example and should not limit the functions and scope of use of the embodiment of the present disclosure.

[0137] As shown in FIG9 , a computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for system operation are also stored in the RAM 903. The CPU 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0138] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, and the like; an output section 907 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a local area network (LAN) card or a modem. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 910 as needed, so that a computer program read therefrom can be installed in the storage section 908 as needed.

[0139] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from a removable medium 911. When the computer program is executed by the central processing unit (CPU) 901, the various functions defined in the device of the present application are executed.

[0140] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the above methods is implemented.

[0141] It should be noted that the computer-readable storage media described in the present disclosure may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, radio frequency, or any suitable combination thereof.

[0142] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0143] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for processing positioning data of a vehicle, comprising: Acquire the current positioning data and driving route status of each target object in real time, wherein the driving route status includes driving route and station information; Determining the route position information of each of the target objects on the driving route according to the current positioning data; Determining the line distance between each target object and an adjacent site according to the line position information and the site information; The arrival time of each target object at the next station is determined according to the expected driving speed of each target object and the corresponding route distance of each target object, wherein the expected driving speed is determined based on the positioning data of each target object in the current time window and the corresponding route distance.

2. The method according to claim 1, wherein: The method further comprises: Obtain the current location data of each target object in real time and store it in the message queue; Consuming the data in the message queue based on streaming processing to form a location information set; Acquire the site information of the target route to form a site information set; The driving route status of each of the target objects is determined according to the location information set and the site information set.

3. The method according to claim 2, wherein: The determining of the driving route status of each target object includes: Determining the driving trajectory corresponding to each of the target objects according to the positioning data in the position information set; Performing clustering processing on each of the driving trajectories to obtain a route trajectory of each of the target objects; Matching each station information in the station information set with each road section information on the line track to determine the corresponding relationship between the station and the road section; a road section is a straight line segment on the line track; The driving route status is determined based on the site information, the route trajectory, the road section information and the correspondence between the site and the road section.

4. The method according to claim 3, wherein: After clustering the driving trajectories, the method further includes: Extract key point information from clustering results; A line track of each target object is generated according to the key point information.

5. The method according to claim 3, wherein: The driving route condition includes information of each road section, and determining the route position information of each target object on the driving route includes: The positioning point corresponding to the current positioning data is projected onto the corresponding road section to determine the route position information of each target object on the driving route.

6. The method according to claim 5, wherein: The line distance includes a first line distance and a second line distance, and determining the line distance between each target object and an adjacent site includes: According to the line location information and adjacent site information of each target object, determine the distance between each target object and the above first section information between a site and second section information between each target object and the next site; According to the first road section information and the second road section information, a first route distance between each target object and a previous site and a second route distance between each target object and a next site are determined.

7. The method according to claim 6, wherein: The method further comprises: Determine the first positioning point and the last positioning point of each target object in the current time window; the positioning points correspond to the positioning data; Determine the travel distance in the current time window according to the route distance corresponding to the first positioning point and the route distance corresponding to the last positioning point; The expected driving speed is determined according to the driving distance and the duration of the current time window.

8. The method according to claim 7, wherein: The station information includes the station location, and determining the driving distance in the current time window includes: Determine, according to the site location, whether there is a site between the first positioning point and the last positioning point; If there is no station, subtract the second route distance corresponding to the first positioning point from the second route distance corresponding to the last positioning point, and use the subtraction result as the travel distance in the current time window; If there are sites, determine the site distance between the sites, and sum the site distance, the second distance corresponding to the first positioning point, and the first distance corresponding to the last positioning point, and use the sum result as the driving distance in the current time window.

9. The method according to any one of claims 1 to 8, wherein: The method further comprises: In response to failure to obtain the positioning data of each target object at the specified time, determining the stop time of each target object at each station corresponding to the target route based on the first historical sample data of the target time period; the target time period is determined based on the rounds of the target object on the target route; Based on the second historical sample data, using a pre-trained neural network prediction model, determining the travel time of each target object between each station; The arrival time of each target object at each station is determined according to the stop time and the travel time.

10. The method according to any one of claims 1 to 8, wherein: The method further comprises: In response to the failure to obtain the positioning data of each target object within the specified time, or the distance from the current positioning point to the projection point of the corresponding road section is greater than the preset threshold for a duration exceeding the warning threshold, an abnormal alarm is generated, and the current positioning point corresponds to the current positioning data.

11. The method according to any one of claims 1 to 8, wherein: The method further comprises: The route distance and the arrival time are pushed in real time to the information display stand corresponding to the next station of each target object.

12. A positioning data processing device for a vehicle, comprising: An acquisition module is configured to acquire the current positioning data and driving route status of each target object in real time, wherein the driving route status includes driving route and station information; A position determination module, configured to determine the route position information of each of the target objects on the driving route according to the current positioning data; A distance determination module is configured to determine the route distance between each target object and an adjacent site according to each route position information and the site information; The arrival time determination module is configured to determine the arrival time of each target object at the next station according to the expected driving speed of each target object and the corresponding line distance of each target object, wherein the expected driving speed is determined based on the positioning data of each target object in the current time window and the corresponding line distance.

13. A vehicle control platform, comprising the device as claimed in claim 12.

14. An electronic device, comprising: Memory, for storing computer instructions; A processor, configured to read the computer instructions and execute the method according to any one of claims 1 to 11.

15. A computer-readable storage medium storing a computer program, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images