Highway Vehicle Spatiotemporal Path Prediction Method and Device

Abstract

The present invention discloses a method and device for predicting the spatio-temporal path of highway vehicles, which relates to the field of traffic information technology. The method includes: determining a target highway section to be predicted and dividing the target highway section into sub-highway sections to obtain a set of sub-highway sections; obtaining the sub-passing duration of all target vehicles when passing through each sub-highway section and calculating the sub-comprehensive passing duration of each sub-highway section; determining an abnormal sub-highway section based on the sub-comprehensive passing duration and further determining the abnormal influence factor of the abnormal sub-highway section, and performing spatio-temporal path prediction of vehicles based on the abnormal influence factor. It can be seen that implementing the present invention can improve the determination accuracy of the set of abnormal sub-highway sections, and further improve the determination accuracy of the abnormal influence factors of the abnormal sub-highway sections, thereby improving the accuracy and stability of the spatio-temporal path prediction of highway vehicles.

Description

Technical Field

[0001] The present invention relates to the field of traffic information technology, and in particular, to a method and device for predicting the spatio-temporal path of highway vehicles. Background Art

[0002] At present, the construction of highways is gradually transforming into a stage of high-quality and high-efficiency intelligent highway development. As one of the development directions in the field of intelligent transportation, the prediction of the spatio-temporal path of vehicles is a crucial link in the construction of intelligent highways. The prediction of the spatio-temporal path of vehicles depends on the prior perception and simulation calculation of the highway traffic state. In the prior art, the spatio-temporal path of vehicles is mainly predicted by simulating the traffic operation state, and it is difficult to analyze the actual road conditions and traffic flow rules, such as complex traffic conditions, bad weather (such as rain, snow, fog, hail, sandstorms, etc.), and special road conditions (such as complex construction sections, blurred lane lines, etc.), which leads to inaccurate and unstable prediction of the spatio-temporal path of vehicles. Therefore, there is an urgent need to provide a new method for predicting the spatio-temporal path of highway vehicles to improve the accuracy and stability of the prediction. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and device for predicting the spatio-temporal path of highway vehicles, which can improve the accuracy and stability of the prediction of the spatio-temporal path of highway vehicles.

[0004] To solve the above technical problem, in the first aspect, the present invention discloses a method for predicting the spatio-temporal path of highway vehicles, the method comprising:

[0005] Determine a target highway section to be predicted;

[0006] Divide the target highway section to determine a set of sub-highway sections containing multiple sub-highway sections;

[0007] Obtain the sub-passage duration of all target vehicles passing through the target highway section within a preset first time range when passing through each of the sub-highway sections;

[0008] Based on the sub-passage duration of all target vehicles in each of the sub-highway sections, calculate the sub-comprehensive passage duration of each of the sub-highway sections;

[0009] Determine a set of abnormal sub-highway sections containing multiple abnormal sub-highway sections from the set of sub-highway sections; the abnormal sub-highway section is the sub-highway section corresponding to the sub-comprehensive passage duration being abnormal data;

[0010] For each abnormal sub-highway section in the set of abnormal sub-highway sections, determine the abnormal influence factor of the abnormal sub-highway section;

[0011] Based on all the abnormal influencing factors of each of the abnormal sub-highway sections, perform a vehicle spatio-temporal path prediction operation on the target highway section, where the vehicle spatio-temporal path prediction operation is used to predict the spatio-temporal paths of vehicles passing through the target highway section within a preset subsequent second time range.

[0012] As an alternative implementation manner, in the first aspect of the present invention, before dividing the target highway section to determine a set of sub-highway sections including a plurality of sub-highway sections, the method further includes:

[0013] Obtain the passing durations of all target vehicles passing through the target highway section within a preset first time range;

[0014] Based on the passing durations of all the target vehicles, calculate the comprehensive passing duration of the target highway section;

[0015] Judge whether the comprehensive passing duration meets a preset passing duration threshold to obtain a comprehensive passing duration judgment result;

[0016] When the comprehensive passing duration judgment result is used to indicate that the comprehensive passing duration does not meet the passing duration threshold, trigger the operation of dividing the target highway section to determine a set of sub-highway sections including a plurality of sub-highway sections.

[0017] As an alternative implementation manner, in the first aspect of the present invention, all the target vehicles have corresponding vehicle types;

[0018] And the calculating the comprehensive passing duration of the target highway section based on the passing durations of all the target vehicles includes:

[0019] Based on each vehicle type and the number of target vehicles of that vehicle type, determine the passing duration weight of that vehicle type;

[0020] Based on the passing duration of each target vehicle under each vehicle type, calculate the average passing duration of all the target vehicles under that vehicle type;

[0021] Based on the passing duration weight of each vehicle type and the average passing duration of all the target vehicles under that vehicle type, calculate the comprehensive passing duration of the target highway section.

[0022] As an alternative implementation manner, in the first aspect of the present invention, for each abnormal sub-highway section in the set of abnormal sub-highway sections, determining the abnormal influencing factors of the abnormal sub-highway section includes:

[0023] Identify all target intelligent assisted driving vehicles from all the said target vehicles;

[0024] For each of the said target intelligent assisted driving vehicles, obtain the first auxiliary data set, the second auxiliary data set and the third auxiliary data set of the target intelligent assisted driving vehicle;

[0025] The first auxiliary data set includes at least one of forward collision warning data, rear collision warning data, blind spot monitoring warning data, lane change warning data, lane departure warning data, forward crossing warning data and rear crossing warning data;

[0026] The second auxiliary data set includes at least one of automatic emergency braking data, automatic emergency avoidance data, lane keeping assistance data, lane departure assistance data, lane centering assistance data, intelligent speed limit assistance data, acceleration / deceleration lane change assistance data and automatic overtaking assistance data;

[0027] The third auxiliary data set includes at least one of intelligent assisted driving takeover mileage, intelligent assisted driving takeover ratio and intelligent assisted driving manual takeover times;

[0028] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, determine the abnormal influence factor of the abnormal sub-highway section based on the first auxiliary data set, the second auxiliary data set and the third auxiliary data set of all the said target intelligent assisted driving vehicles on the abnormal sub-highway section.

[0029] As an optional implementation manner, in the first aspect of the present invention, the determining the abnormal influence factor of the abnormal sub-highway section based on the first auxiliary data set, the second auxiliary data set and the third auxiliary data set of all the said target intelligent assisted driving vehicles on the abnormal sub-highway section for each of the abnormal sub-highway sections in the set of abnormal sub-highway sections includes:

[0030] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, determine the corresponding edge sub-section server, and the edge sub-section server is used for data processing of the abnormal sub-highway section;

[0031] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set, perform a first correlation analysis and a second correlation analysis on the abnormal sub-highway section on the edge sub-section server corresponding to the abnormal sub-highway section to obtain a first correlation analysis result and a second correlation analysis result; the first correlation analysis is used to analyze the collaborative correlation between the auxiliary data within each of the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions; the second correlation analysis is used to analyze the modal correlation between the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions.

[0032] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, based on the first correlation analysis result and the second correlation analysis result of the abnormal sub-highway section, determine the abnormal impact factors of the abnormal sub-highway section.

[0033] As an optional implementation manner, in the first aspect of the present invention, the performing a vehicle spatio-temporal path prediction operation on the target highway section based on all the abnormal impact factors of each of the abnormal sub-highway sections includes:

[0034] Based on the target highway section, generate an initial full-course road model of the target highway section;

[0035] Based on all the abnormal impact factors of each of the abnormal sub-highway sections, generate an abnormal sub-road model of the abnormal sub-highway section;

[0036] Based on the abnormal sub-road models of all the abnormal sub-highway sections, correct the initial full-course road model to obtain a corrected full-course road model of the target highway section;

[0037] Based on all the abnormal impact factors of all the abnormal sub-highway sections, the corrected full-course road model, and all the vehicle types, generate a predicted spatio-temporal path corresponding to each vehicle type within the target highway section.

[0038] As an optional implementation manner, in the first aspect of the present invention, the dividing the target highway section to determine a set of sub-highway sections including multiple sub-highway sections includes:

[0039] Determine all the toll stations, main-road ETC gantries, and ramp ETC gantries of the target highway section;

[0040] Based on all the toll stations, the main road ETC gantries, and the ramp ETC gantries, divide the target highway section to obtain a set of shortest sub-highway sections containing multiple shortest sub-highway sections;

[0041] For each shortest sub-highway section in the set of shortest sub-highway sections, determine whether the section length of the shortest sub-highway section meets a preset sub-highway section length threshold to obtain a length threshold judgment result for the shortest sub-highway section;

[0042] For each shortest sub-highway section in the set of shortest sub-highway sections, when the length threshold judgment result of the shortest sub-highway section is used to indicate that the section length of the shortest sub-highway section does not meet the sub-highway section length threshold, determine the target shortest sub-highway section corresponding to the shortest sub-highway section; splice the shortest sub-highway section and the target shortest sub-highway section corresponding to the shortest sub-highway section to obtain a spliced shortest sub-highway section corresponding to the shortest sub-highway section; the target shortest sub-highway section is the shortest sub-highway section with a shorter length among the two adjacent shortest sub-highway sections of the shortest sub-highway section;

[0043] Based on all the shortest sub-highway sections that have not been spliced and all the spliced shortest sub-highway sections in the set of shortest sub-highway sections, determine a set of sub-highway sections containing multiple sub-highway sections.

[0044] A second aspect of the present invention discloses a device for predicting the spatio-temporal path of highway vehicles, and the device includes:

[0045] A determination module, configured to determine a target highway section to be predicted;

[0046] A division module, configured to divide the target highway section to determine a set of sub-highway sections containing multiple sub-highway sections;

[0047] A first acquisition module, configured to acquire the sub-passage durations of all target vehicles passing through the target highway section within a preset first time range when passing through each sub-highway section;

[0048] A first calculation module, configured to calculate the sub-comprehensive passage duration of each sub-highway section based on the sub-passage durations of all target vehicles of each sub-highway section;

[0049] The determination module is further configured to determine a set of abnormal sub-highway sections containing multiple abnormal sub-highway sections from the set of sub-highway sections; the abnormal sub-highway section is the sub-highway section corresponding to an abnormal sub-comprehensive passage duration; for each abnormal sub-highway section in the set of abnormal sub-highway sections, determine the abnormal influence factor of the abnormal sub-highway section;

[0050] A prediction module, configured to perform a vehicle spatio-temporal path prediction operation on the target highway section based on all the abnormal impact factors of each of the abnormal sub-highway sections, where the vehicle spatio-temporal path prediction operation is used to predict the spatio-temporal paths of vehicles passing through the target highway section within a preset subsequent second time range.

[0051] As an alternative implementation manner, in the second aspect of the present invention, before the division module divides the target highway section to determine a set of sub-highway sections including multiple sub-highway sections, the apparatus further includes:

[0052] A second acquisition module, configured to acquire the passing durations of all target vehicles passing through the target highway section within a preset first time range;

[0053] A second calculation module, configured to calculate the comprehensive passing duration of the target highway section based on the passing durations of all the target vehicles;

[0054] A judgment module, configured to judge whether the comprehensive passing duration meets a preset passing duration threshold to obtain a comprehensive passing duration judgment result;

[0055] A trigger module, configured to trigger the division module to perform the operation of dividing the target highway section to determine a set of sub-highway sections including multiple sub-highway sections when the comprehensive passing duration judgment result indicates that the comprehensive passing duration does not meet the passing duration threshold.

[0056] As an alternative implementation manner, in the second aspect of the present invention, all the target vehicles have corresponding vehicle types;

[0057] And the specific manner in which the second calculation module calculates the comprehensive passing duration of the target highway section based on the passing durations of all the target vehicles includes:

[0058] Determine the passing duration weight of each vehicle type based on each vehicle type and the number of target vehicles of that vehicle type;

[0059] Calculate the average passing duration of all target vehicles of each vehicle type based on the passing duration of each target vehicle of each vehicle type;

[0060] Calculate the comprehensive passing duration of the target highway section based on the passing duration weight of each vehicle type and the average passing duration of all target vehicles of that vehicle type.

[0061] As an alternative implementation, in the second aspect of the present invention, for each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, the specific manner for the determination module to determine the abnormal influence factor of the abnormal sub-highway section includes:

[0062] Determine all target intelligent assisted driving vehicles from all the target vehicles;

[0063] For each of the target intelligent assisted driving vehicles, obtain the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of the target intelligent assisted driving vehicle;

[0064] The first auxiliary data set includes at least one of forward collision warning data, rear collision warning data, blind spot monitoring warning data, lane change warning data, lane departure warning data, forward cross warning data, and rear cross warning data;

[0065] The second auxiliary data set includes at least one of automatic emergency braking data, automatic emergency avoidance data, lane keeping assistance data, lane departure assistance data, lane centering assistance data, intelligent speed limit assistance data, acceleration / deceleration lane change assistance data, and automatic overtaking assistance data;

[0066] The third auxiliary data set includes at least one of intelligent assisted driving takeover mileage, intelligent assisted driving takeover ratio, and intelligent assisted driving manual takeover times;

[0067] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of all the target intelligent assisted driving vehicles on the abnormal sub-highway section, determine the abnormal influence factor of the abnormal sub-highway section.

[0068] As an alternative implementation, in the second aspect of the present invention, for each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, the specific manner for the determination module to determine the abnormal influence factor of the abnormal sub-highway section based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of all the target intelligent assisted driving vehicles on the abnormal sub-highway section includes:

[0069] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, determine the corresponding edge sub-section server, and the edge sub-section server is used for data processing of the abnormal sub-highway section;

[0070] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set, perform a first correlation analysis and a second correlation analysis on the abnormal sub-highway section on the edge sub-section server corresponding to the abnormal sub-highway section to obtain a first correlation analysis result and a second correlation analysis result; the first correlation analysis is used to analyze the collaborative correlation between the auxiliary data within each of the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions; the second correlation analysis is used to analyze the modal correlation between the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions.

[0071] For each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, based on the first correlation analysis result and the second correlation analysis result of the abnormal sub-highway section, determine the abnormal influence factor of the abnormal sub-highway section.

[0072] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the prediction module performs a vehicle spatio-temporal path prediction operation on the target highway section based on all the abnormal influence factors of each of the abnormal sub-highway sections includes:

[0073] Based on the target highway section, generate an initial full-course road model of the target highway section;

[0074] Based on all the abnormal influence factors of each of the abnormal sub-highway sections, generate an abnormal sub-road model of the abnormal sub-highway section;

[0075] Based on the abnormal sub-road models of all the abnormal sub-highway sections, correct the initial full-course road model to obtain a corrected full-course road model of the target highway section;

[0076] Based on all the abnormal influence factors of all the abnormal sub-highway sections, the corrected full-course road model, and all the vehicle types, generate a predicted spatio-temporal path corresponding to each vehicle type within the target highway section.

[0077] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the division module divides the target highway section to determine a set of sub-highway sections including multiple sub-highway sections includes:

[0078] Determine all the toll stations, main-road ETC gantries, and ramp ETC gantries of the target highway section;

[0079] Perform highway section division on the target highway section based on all the toll stations, the main-road ETC gantries, and the ramp ETC gantries, to obtain a shortest sub-highway section set including a plurality of shortest sub-highway sections;

[0080] For each shortest sub-highway section in the shortest sub-highway section set, determine whether the section length of the shortest sub-highway section meets a preset sub-highway section length threshold, to obtain a length threshold judgment result of the shortest sub-highway section;

[0081] For each shortest sub-highway section in the shortest sub-highway section set, when the length threshold judgment result of the shortest sub-highway section is used to indicate that the section length of the shortest sub-highway section does not meet the sub-highway section length threshold, determine the target shortest sub-highway section corresponding to the shortest sub-highway section; splice the shortest sub-highway section and the target shortest sub-highway section corresponding to the shortest sub-highway section, to obtain a spliced shortest sub-highway section corresponding to the shortest sub-highway section; the target shortest sub-highway section is the shortest sub-highway section with a shorter length among the two adjacent shortest sub-highway sections of the shortest sub-highway section;

[0082] Based on all the shortest sub-highway sections that have not been spliced and all the spliced shortest sub-highway sections in the shortest sub-highway section set, determine a sub-highway section set including a plurality of sub-highway sections.

[0083] A third aspect of the present invention discloses another highway vehicle spatio-temporal path prediction device, the device includes:

[0084] A memory storing executable program code;

[0085] A processor coupled to the memory;

[0086] The processor calls the executable program code stored in the memory to execute the highway vehicle spatio-temporal path prediction method disclosed in the first aspect of the present invention.

[0087] A fourth aspect of the present invention discloses a computer storage medium, the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the highway vehicle spatio-temporal path prediction method disclosed in the first aspect of the present invention.

[0088] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0089] In an embodiment of the present invention, a target highway section to be predicted is determined, and the target highway section is divided into sub-highway sections to obtain a set of sub-highway sections; the sub-passing durations of all target vehicles when passing through each sub-highway section are obtained, and the sub-comprehensive passing duration of each sub-highway section is calculated; based on the sub-comprehensive passing duration, an abnormal sub-highway section is determined, and further an abnormal influence factor of the abnormal sub-highway section is determined, and vehicle spatio-temporal path prediction is performed based on the abnormal influence factor; which is beneficial to improving the determination accuracy of the set of abnormal sub-highway sections, and further improving the determination accuracy of the abnormal influence factor of the abnormal sub-highway section, thereby improving the accuracy and stability of highway vehicle spatio-temporal path prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0091] Figure 1 is a schematic flowchart of a method for predicting highway vehicle spatio-temporal paths disclosed in an embodiment of the present invention;

[0092] Figure 2 is a schematic flowchart of another method for predicting highway vehicle spatio-temporal paths disclosed in an embodiment of the present invention;

[0093] Figure 3 is a schematic structural diagram of a device for predicting highway vehicle spatio-temporal paths disclosed in an embodiment of the present invention;

[0094] Figure 4 is a schematic structural diagram of another device for predicting highway vehicle spatio-temporal paths disclosed in an embodiment of the present invention;

[0095] Figure 5 is a schematic structural diagram of yet another device for predicting highway vehicle spatio-temporal paths disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0096] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0097] In the description and claims of the present invention and the above-mentioned drawings, terms such as "first" and "second" are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or terminal comprising a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or terminals.

[0098] Reference to "embodiment" herein means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0099] The present invention discloses a method and device for predicting the spatio-temporal path of highway vehicles. Implementing the present invention can determine a target highway section to be predicted and divide the target highway section to obtain a set of sub-highway sections; obtain the sub-passage duration of all target vehicles when passing through each sub-highway section and calculate the sub-comprehensive passage duration of each sub-highway section; determine an abnormal sub-highway section based on the sub-comprehensive passage duration and further determine the abnormal influence factor of the abnormal sub-highway section, and perform spatio-temporal path prediction of vehicles based on the abnormal influence factor; which is beneficial to improving the determination accuracy of the set of abnormal sub-highway sections, and further improving the determination accuracy of the abnormal influence factor of the abnormal sub-highway section, thereby improving the accuracy and stability of the spatio-temporal path prediction of highway vehicles. The following will be described in detail respectively.

[0100] Embodiment 1

[0101] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for predicting the spatio-temporal path of highway vehicles disclosed in an embodiment of the present invention. Among them, Figure 1 the described method can be applied to any scenario that requires spatio-temporal path prediction of passing vehicles on a highway section, and the embodiments of the present invention do not make limitations. As Figure 1 shown, the method for predicting the spatio-temporal path of highway vehicles includes the following operations:

[0102] 101. Determine the target highway section to be predicted;

[0103] 102. Divide the target highway section to determine a set of sub-highway sections containing multiple sub-highway sections;

[0104] 103. Obtain the sub - passing duration of all target vehicles passing through the target highway section within a preset first - time range when passing through each sub - highway section;

[0105] In the embodiments of the present invention, the first - time range can be freely set according to many factors such as prediction time accuracy, server computing power, peak commuting hours, holidays, etc., and the embodiments of the present invention do not make limitations;

[0106] 104. Calculate the sub - comprehensive passing duration of each sub - highway section based on the sub - passing durations of all target vehicles on each sub - highway section;

[0107] In the embodiments of the present invention, it can be understood that the sub - passing duration of a target vehicle refers to the duration of the target vehicle passing through each sub - highway section; the sub - comprehensive passing duration refers to the passing duration obtained by comprehensively weighing and analyzing the sub - passing durations of all target vehicles on each sub - highway section;

[0108] 105. Determine an abnormal sub - highway - section set containing multiple abnormal sub - highway sections from the sub - highway - section set;

[0109] In the embodiments of the present invention, an abnormal sub - highway section is a sub - highway section for which the corresponding sub - comprehensive passing duration is abnormal data; the abnormal data can be understood as the sub - comprehensive passing duration being too long and exceeding a preset threshold, or from the perspective that the sub - comprehensive passing duration is too short and there are a large number of speeding behaviors. The embodiments of the present invention do not make limitations;

[0110] 106. For each abnormal sub - highway section in the abnormal sub - highway - section set, determine the abnormal influence factor of the abnormal sub - highway section;

[0111] In the embodiments of the present invention, the abnormal influence factors include many factors such as complex traffic - situation influence factors, bad - weather influence factors, and special - road - condition influence factors. Determining the abnormal influence factor of the abnormal sub - highway section can be through methods such as on - site investigation, querying weather forecasts and accident information, etc. The embodiments of the present invention do not make limitations;

[0112] 107. Based on all the abnormal influence factors of each abnormal sub - highway section, perform a vehicle spatio - temporal path prediction operation on the target highway section;

[0113] In the embodiments of the present invention, the vehicle spatio-temporal path prediction operation is used to predict the spatio-temporal paths of vehicles passing through a target highway section within a preset subsequent second time range; performing prediction on the target highway section based on the abnormal influence factor can be understood as marking special situations such as congestion, bad weather, accidents, etc. on the sub-highway sections corresponding to the abnormal influence factor, as well as marking driving conditions such as speed reduction and stopping forward, and displaying them by generating a topology map or a model map; spatio-temporal path prediction can be understood as predicting that a vehicle passing through this highway section can reach a certain node (position) of this highway section at a certain moment.

[0114] It can be seen that implementing the method described in the embodiments of the present invention can determine the target highway section to be predicted and divide the target highway section to obtain a set of sub-highway sections; obtain the sub-passing durations of all target vehicles when passing through each sub-highway section and calculate the sub-comprehensive passing duration of each sub-highway section; determine the abnormal sub-highway sections based on the sub-comprehensive passing duration and further determine the abnormal influence factors of the abnormal sub-highway sections, and perform vehicle spatio-temporal path prediction based on the abnormal influence factors; which is beneficial to improving the determination accuracy of the set of abnormal sub-highway sections, and further improving the determination accuracy of the abnormal influence factors of the abnormal sub-highway sections, thereby improving the accuracy and stability of the spatio-temporal path prediction of highway vehicles.

[0115] In an alternative embodiment, for each abnormal sub-highway section in the set of abnormal sub-highway sections in step 106 above, determining the abnormal influence factor of the abnormal sub-highway section may include:

[0116] Determine all target intelligent assisted driving vehicles from all target vehicles;

[0117] For each target intelligent assisted driving vehicle, obtain the first auxiliary data set, the second auxiliary data set and the third auxiliary data set of the target intelligent assisted driving vehicle;

[0118] The first auxiliary data set includes at least one of forward collision warning data, rear collision warning data, blind spot monitoring warning data, lane change warning data, lane departure warning data, forward cross warning data and rear cross warning data;

[0119] The second auxiliary data set includes at least one of automatic emergency braking data, automatic emergency avoidance data, lane keeping assist data, lane departure assist data, lane centering assist data, intelligent speed limit assist data, acceleration / deceleration lane change assist data and automatic overtaking assist data;

[0120] The third auxiliary data set includes at least one of intelligent assisted driving takeover mileage, intelligent assisted driving takeover ratio, and intelligent assisted driving manual takeover times;

[0121] For each abnormal sub-highway section in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of all target intelligent assisted driving vehicles on the abnormal sub-highway section, determine the abnormal influence factor of the abnormal sub-highway section.

[0122] In this alternative embodiment, the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set can be obtained from intelligent assisted driving vehicles that have an authorized relationship or a cooperative relationship with the highway service unit. The embodiments of the present invention do not make limitations; it can be understood that the data included in the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set can be used as indirect auxiliary data for inferring that there are factors affecting normal traffic on the highway section. For example, when there are complex road conditions on the highway, the automatic emergency avoidance data and the number of times of manual takeover of intelligent assisted driving will increase significantly.

[0123] It can be seen that this alternative embodiment can determine all target intelligent assisted driving vehicles from all target vehicles, obtain multiple auxiliary data sets of the target intelligent assisted driving vehicles, determine the abnormal influence factor of the abnormal sub-highway section based on the auxiliary data, improve the utilization rate of the driving data of the target vehicles, and further improve the determination accuracy of the abnormal influence factor of the abnormal sub-highway section, thereby improving the accuracy and stability of the spatio-temporal path prediction of highway vehicles.

[0124] In another alternative embodiment, for each abnormal sub-highway section in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of all target intelligent assisted driving vehicles on the abnormal sub-highway section, determining the abnormal influence factor of the abnormal sub-highway section may include:

[0125] For each abnormal sub-highway section in the set of abnormal sub-highway sections, determine the corresponding edge sub-section server, and the edge sub-section server is used for data processing of the abnormal sub-highway section;

[0126] For each abnormal sub-highway section in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set, perform the first correlation analysis and the second correlation analysis on the abnormal sub-highway section on the edge sub-section server corresponding to the abnormal sub-highway section to obtain the first correlation analysis result and the second correlation analysis result; the first correlation analysis is used to analyze the collaborative correlation between the auxiliary data within each of the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions; the second correlation analysis is used to analyze the modal correlation between the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions;

[0127] For each abnormal sub-highway section in the set of abnormal sub-highway sections, based on the first correlation analysis result and the second correlation analysis result of the abnormal sub-highway section, determine the abnormal influence factor of the abnormal sub-highway section.

[0128] In this optional embodiment, the edge sub-section server can be established at locations such as toll stations with server storage and computing conditions to meet the needs of edge computing. At the same time, while completing the edge computing of each abnormal sub-highway section, all abnormal sub-highway sections can also be jointly learned to train relevant models for predicting the spatio-temporal path of highway vehicles. The embodiments of the present invention do not limit this.

[0129] It can be seen that this optional embodiment can determine the edge sub-section server corresponding to each abnormal sub-highway section and perform correlation analysis on the abnormal sub-highway section on the edge sub-section server, which is beneficial to reducing the load pressure of cloud (assembly) computing through the edge computing ability of the edge sub-section server and improving the data processing efficiency of the abnormal sub-highway section; further, determining the abnormal influence factor of the abnormal sub-highway section according to the correlation analysis is beneficial to improving the accuracy of determining the abnormal influence factor of the abnormal sub-highway section, and thus improving the accuracy of predicting the spatio-temporal path of highway vehicles.

[0130] In another optional embodiment, the division of the target highway section into a set of sub-highway sections including multiple sub-highway sections in step 102 above may include:

[0131] Determine all toll stations, main-road ETC gantries, and ramp ETC gantries of the target highway section;

[0132] Based on all toll stations, main-road ETC gantries, and ramp ETC gantries, divide the target highway section to obtain a set of shortest sub-highway sections including multiple shortest sub-highway sections;

[0133] For each shortest sub-highway section in the set of shortest sub-highway sections, determine whether the section length of the shortest sub-highway section meets a preset sub-highway section length threshold to obtain a length threshold judgment result of the shortest sub-highway section;

[0134] For each shortest sub-highway section in the set of shortest sub-highway sections, when the length threshold judgment result of the shortest sub-highway section is used to indicate that the road length of the shortest sub-highway section does not meet the sub-highway section length threshold, determine the target shortest sub-highway section corresponding to the shortest sub-highway section; splice the shortest sub-highway section with the target shortest sub-highway section corresponding to the shortest sub-highway section to obtain the spliced shortest sub-highway section corresponding to the shortest sub-highway section; the target shortest sub-highway section is the shortest sub-highway section with a shorter length among the two adjacent shortest sub-highway sections of the shortest sub-highway section;

[0135] Based on all the shortest sub-highway sections that have not been spliced and all the spliced shortest sub-highway sections in the set of shortest sub-highway sections, determine a set of sub-highway sections containing multiple sub-highway sections.

[0136] In this optional embodiment, it can be understood that when the spliced shortest sub-highway section still does not meet the sub-highway section length threshold, splicing needs to be continued until the spliced shortest sub-highway section meets the highway section length threshold; determining a set of sub-highway sections containing multiple sub-highway sections based on all the shortest sub-highway sections that have not been spliced and all the spliced shortest sub-highway sections in the set of shortest sub-highway sections can be understood as taking all the shortest sub-highway sections that have not been spliced and all the spliced shortest sub-highway sections as sub-highway sections.

[0137] It can be seen that this optional embodiment can divide highway sections based on all toll stations, main road ETC gantries, and ramp ETC gantries, obtain the shortest sub-highway sections and judge whether the road length of each shortest sub-highway section meets the conditions. When the conditions are met, determine the corresponding target shortest sub-highway section and splice the shortest sub-highway section with the corresponding target shortest sub-highway section. After all splicing is completed, determine the set of sub-highway sections; it is beneficial to improve the accuracy of highway section division, thereby improving the accuracy of determining abnormal sub-highway sections, and thus improving the accuracy and stability of highway vehicle spatio-temporal path prediction.

[0138] Embodiment Two

[0139] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of a method for predicting the spatio-temporal path of highway vehicles disclosed in an embodiment of the present invention. Among them, Figure 2 The described method can be applied to any scenario that requires spatio-temporal path prediction of passing vehicles on highway sections, and the embodiments of the present invention do not make limitations. As Figure 2 shown, the method for predicting the spatio-temporal path of highway vehicles includes the following operations:

[0140] 201. Determine the target highway section to be predicted;

[0141] 202. Obtain the passing durations of all target vehicles passing through the target highway section within a preset first time range;

[0142] 203. Calculate the comprehensive passing duration of the target highway section based on the passing durations of all target vehicles;

[0143] 204. Determine whether the comprehensive passing duration meets a preset passing duration threshold to obtain a comprehensive passing duration judgment result;

[0144] 205. When the comprehensive passing duration judgment result indicates that the comprehensive passing duration does not meet the passing duration threshold, divide the target highway section to determine a set of sub-highway sections including multiple sub-highway sections;

[0145] 206. Obtain the sub-passing durations of all target vehicles passing through the target highway section within a preset first time range when passing through each sub-highway section;

[0146] 207. Calculate the sub-comprehensive passing duration of each sub-highway section based on the sub-passing durations of all target vehicles of each sub-highway section;

[0147] 208. Determine a set of abnormal sub-highway sections including multiple abnormal sub-highway sections from the set of sub-highway sections;

[0148] In the embodiments of the present invention, an abnormal sub-highway section is a sub-highway section whose corresponding sub-comprehensive passing duration is abnormal data;

[0149] 209. For each abnormal sub-highway section in the set of abnormal sub-highway sections, determine the abnormal influence factor of the abnormal sub-highway section;

[0150] 210. Perform a vehicle spatio-temporal path prediction operation on the target highway section based on all the abnormal influence factors of each abnormal sub-highway section;

[0151] In the embodiments of the present invention, the vehicle spatio-temporal path prediction operation is used to predict the spatio-temporal paths of vehicles passing through in a preset second time range after the target highway section; it can be understood that when the comprehensive passing duration judgment result indicates that the comprehensive passing duration meets the passing duration threshold, at this time, from the perspective of the entire target highway section, it can be determined that there is no need to divide it and further determine abnormal sub-sections.

[0152] In the embodiments of the present invention, for other descriptions of steps 201, 205, 206, 207, 208, 200, and 210, please refer to the detailed descriptions of steps 101, 102, 103, 104, 105, 106, and 107 in Embodiment 1, and the embodiments of the present invention will not be elaborated herein.

[0153] It can be seen that implementing the method described in the embodiments of the present invention can determine the target highway section to be predicted, obtain the passing times of all target vehicles passing through the target highway section and calculate the comprehensive passing time of the target highway section. When the comprehensive passing time does not meet the passing time threshold, the target highway section is divided to obtain a set of sub-highway sections; obtain the sub-passing times of all target vehicles when passing through each sub-highway section and calculate the sub-comprehensive passing time of each sub-highway section; determine the abnormal sub-highway section based on the sub-comprehensive passing time and further determine the abnormal influence factor of the abnormal sub-highway section, and perform vehicle spatio-temporal path prediction based on the abnormal influence factor; which is beneficial to improving the determination accuracy of highway section division, reducing the cost brought by dividing the target highway section and subsequent calculations when the comprehensive passing time meets the standard, and improving the efficiency of highway vehicle spatio-temporal path prediction.

[0154] In an alternative embodiment, there is a corresponding vehicle type for all target vehicles;

[0155] In the embodiments of the present invention, the vehicle types can be divided into three categories: passenger cars, freight cars, and special vehicles; or the passenger cars, freight cars, and special vehicles can be further classified. For example, passenger cars include Class 1 passenger cars, Class 2 passenger cars, Class 3 passenger cars, and Class 4 passenger cars. The approved number of passengers for a Class 1 passenger car should be ≤ 9 people, and the vehicle length should be less than 6000 mm; the approved number of passengers for a Class 2 passenger car is 10 - 19 people, and the vehicle length should be less than 6000 mm; the approved number of passengers for a Class 3 passenger car should be ≤ 39 people, and the vehicle length should not be less than 6000 mm; the approved number of passengers for a Class 4 passenger car should be ≥ 40 people, and the vehicle length should not be less than 6000 mm. The present invention does not limit the classification and determination of vehicle types.

[0156] Moreover, calculating the comprehensive passing time of the target highway section based on the passing times of all target vehicles in step 203 above may include:

[0157] Determine the passing time weight of each vehicle type based on each vehicle type and the number of target vehicles under that vehicle type;

[0158] Calculate the average passing time of all target vehicles under each vehicle type based on the passing time of each target vehicle under each vehicle type;

[0159] Calculate the comprehensive passing time of the target highway section based on the passing time weight of each vehicle type and the average passing time of all target vehicles under that vehicle type.

[0160] In the embodiments of the present invention, it can be understood that based on each vehicle type and the number of target vehicles under that vehicle type, the passing duration weight of the vehicle type can be determined, and the passing duration weight can be flexibly adjusted according to the passing duration weights of the preset vehicle types in combination with the number of target vehicles under the vehicle type. The embodiments of the present invention do not make any limitations.

[0161] It can be seen that this optional embodiment can determine the passing duration weight of each vehicle type and calculate the average passing duration of all target vehicles under each vehicle type, and calculate the comprehensive passing duration of the target highway section based on the passing duration weight and the average passing duration of each vehicle type; it is beneficial to improve the determination accuracy of the comprehensive passing duration, and further improve the judgment accuracy of whether the comprehensive passing duration meets the threshold.

[0162] In another optional embodiment, the vehicle spatio-temporal path prediction operation on the target highway section based on all abnormal impact factors of each abnormal sub-highway section in step 210 above may include:

[0163] Based on the target highway section, generate an initial full-course road model of the target highway section;

[0164] Based on all abnormal impact factors of each abnormal sub-highway section, generate an abnormal sub-road model of the abnormal sub-highway section;

[0165] Based on the abnormal sub-road models of all abnormal sub-highway sections, correct the initial full-course road model to obtain a corrected full-course road model of the target highway section;

[0166] Based on all abnormal impact factors of all abnormal sub-highway sections, the corrected full-course road model, and all vehicle types, generate a predicted spatio-temporal path corresponding to each vehicle type within the target highway section.

[0167] In the embodiments of the present invention, it can be understood that correcting the initial full-course road model based on the abnormal sub-road models of all abnormal sub-highway sections can be understood as replacing the corresponding sub-section models in the initial full-course road model with the abnormal sub-road models of all abnormal sub-highway sections; generating a predicted spatio-temporal path corresponding to each vehicle type within the target highway section based on all abnormal impact factors of all abnormal sub-highway sections, the corrected full-course road model, and all vehicle types can be understood as marking special situations such as congestion, bad weather, and accidents on the sub-highway sections corresponding to the abnormal impact factors, as well as marking driving conditions such as speed reduction and stopping forward corresponding to all vehicle types, and reflecting them on the corrected full-course road model, and displaying them by generating a topological map or a model diagram.

[0168] It can be seen that the optional embodiment can generate an initial full - length road model of the target highway section, generate an abnormal sub - road model based on the abnormal influence factors, and correct the initial full - length road model to obtain a corrected full - length road model of the target highway section, which is beneficial to improving the correction accuracy of the initial full - length road model. Further, generating a predicted spatio - temporal path based on all abnormal influence factors, the corrected full - length road model, and all vehicle types is beneficial to improving the accuracy of spatio - temporal path prediction of highway vehicles.

[0169] Embodiment III

[0170] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of a highway vehicle spatio - temporal path prediction device disclosed in an embodiment of the present invention. Among them, Figure 3 The described device can be applied to any scenario that requires spatio - temporal path prediction of passing vehicles on a highway section, and the embodiments of the present invention do not make limitations. As Figure 3 shown, the highway vehicle spatio - temporal path prediction device may include:

[0171] A determination module 301, configured to determine a target highway section to be predicted;

[0172] A division module 302, configured to divide the target highway section into highway sub - sections and determine a set of sub - highway sections including multiple sub - highway sections;

[0173] A first acquisition module 303, configured to acquire the sub - passing durations of all target vehicles passing through the target highway section within a preset first time range when passing through each sub - highway section;

[0174] A first calculation module 304, configured to calculate the sub - comprehensive passing duration of each sub - highway section based on the sub - passing durations of all target vehicles in each sub - highway section;

[0175] The determination module 301 is further configured to determine a set of abnormal sub - highway sections including multiple abnormal sub - highway sections from the set of sub - highway sections; for each abnormal sub - highway section in the set of abnormal sub - highway sections, determine the abnormal influence factor of the abnormal sub - highway section;

[0176] In the embodiments of the present invention, an abnormal sub - highway section is a sub - highway section whose corresponding sub - comprehensive passing duration is abnormal data;

[0177] A prediction module 305, configured to perform a vehicle spatio - temporal path prediction operation on the target highway section based on all abnormal influence factors of each abnormal sub - highway section, where the vehicle spatio - temporal path prediction operation is used to predict the spatio - temporal paths of vehicles passing through the target highway section within a subsequent preset second time range.

[0178] It can be seen that implementing the device described in the embodiments of the present invention can determine the target highway section to be predicted, divide the target highway section into sub-highway sections to obtain a set of sub-highway sections, obtain the sub-passing time of all target vehicles when passing through each sub-highway section, and calculate the sub-comprehensive passing time of each sub-highway section. Based on the sub-comprehensive passing time, determine the abnormal sub-highway section and further determine the abnormal influence factor of the abnormal sub-highway section, and perform vehicle spatio-temporal path prediction based on the abnormal influence factor, which is beneficial to improving the determination accuracy of the set of abnormal sub-highway sections, thereby improving the determination accuracy of the abnormal influence factor of the abnormal sub-highway section, and thus improving the accuracy and stability of highway vehicle spatio-temporal path prediction.

[0179] In an alternative embodiment, as Figure 4 shown, the device further includes:

[0180] A second acquisition module 306, configured to acquire the passing time of all target vehicles passing through the target highway section within a preset first time range before the division module 302 divides the target highway section into highway sections to determine a set of sub-highway sections including multiple sub-highway sections;

[0181] A second calculation module 307, configured to calculate the comprehensive passing time of the target highway section based on the passing time of all target vehicles;

[0182] A judgment module 308, configured to judge whether the comprehensive passing time meets a preset passing time threshold to obtain a comprehensive passing time judgment result;

[0183] A trigger module 309, configured to trigger the division module to perform an operation of dividing the target highway section into highway sections to determine a set of sub-highway sections including multiple sub-highway sections when the comprehensive passing time judgment result indicates that the comprehensive passing time does not meet the passing time threshold.

[0184] It can be seen that implementing the device described in this alternative embodiment can determine the target highway section to be predicted, acquire the passing time of all target vehicles passing through the target highway section and calculate the comprehensive passing time of the target highway section. When the comprehensive passing time does not meet the passing time threshold, divide the target highway section into highway sections to obtain a set of sub-highway sections, acquire the sub-passing time of all target vehicles when passing through each sub-highway section, and calculate the sub-comprehensive passing time of each sub-highway section. Based on the sub-comprehensive passing time, determine the abnormal sub-highway section and further determine the abnormal influence factor of the abnormal sub-highway section, and perform vehicle spatio-temporal path prediction based on the abnormal influence factor, which is beneficial to improving the determination accuracy of highway section division, reducing the cost brought by dividing the target highway section and subsequent calculations when the comprehensive passing time meets the standard, and improving the efficiency of highway vehicle spatio-temporal path prediction.

[0185] In another alternative embodiment, there is a corresponding vehicle type for all target vehicles;

[0186] Moreover, the specific manner in which the second calculation module 307 calculates the comprehensive passing duration of the target highway section based on the passing durations of all target vehicles includes:

[0187] Determine the passing duration weight of each vehicle type based on each vehicle type and the number of target vehicles under that vehicle type;

[0188] Calculate the average passing duration of all target vehicles under each vehicle type based on the passing duration of each target vehicle under each vehicle type;

[0189] Calculate the comprehensive passing duration of the target highway section based on the passing duration weight of each vehicle type and the average passing duration of all target vehicles under that vehicle type.

[0190] It can be seen that the device described in implementing this alternative embodiment can determine the passing duration weight of each vehicle type and calculate the average passing duration of all target vehicles under each vehicle type, and calculate the comprehensive passing duration of the target highway section based on the passing duration weight and average passing duration of each vehicle type; this is beneficial to improving the determination accuracy of the comprehensive passing duration, and further improving the judgment accuracy of whether the comprehensive passing duration meets the threshold.

[0191] In yet another alternative embodiment, for each abnormal sub-highway section in the set of abnormal sub-highway sections, the specific manner in which the determination module 301 determines the abnormal influence factor of the abnormal sub-highway section includes:

[0192] Determine all target intelligent assisted driving vehicles from all target vehicles;

[0193] For each target intelligent assisted driving vehicle, obtain the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of the target intelligent assisted driving vehicle;

[0194] The first auxiliary data set includes at least one of forward collision warning data, rear collision warning data, blind spot monitoring warning data, lane change warning data, lane departure warning data, forward crossing warning data, and rear crossing warning data;

[0195] The second auxiliary data set includes at least one of automatic emergency braking data, automatic emergency avoidance data, lane keeping assist data, lane departure assist data, lane centering assist data, intelligent speed limit assist data, acceleration / deceleration lane change assist data, and automatic overtaking assist data;

[0196] The third auxiliary data set includes at least one of the intelligent assisted driving takeover mileage, the intelligent assisted driving takeover ratio, and the number of manual takeovers of intelligent assisted driving;

[0197] For each abnormal sub-highway section in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of all target intelligent assisted driving vehicles on this abnormal sub-highway section, determine the abnormal influence factor of this abnormal sub-highway section.

[0198] It can be seen that the device described in this optional embodiment can determine all target intelligent assisted driving vehicles from all target vehicles, obtain multiple auxiliary data sets of the target intelligent assisted driving vehicles, determine the abnormal influence factor of the abnormal sub-highway section based on the auxiliary data, improve the utilization rate of the driving data of the target vehicles, and further improve the determination accuracy of the abnormal influence factor of the abnormal sub-highway section, thereby improving the accuracy and stability of the spatio-temporal path prediction of highway vehicles.

[0199] In another optional embodiment, the specific manner in which the determination module 301 determines the abnormal influence factor of each abnormal sub-highway section in the set of abnormal sub-highway sections based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of all target intelligent assisted driving vehicles on this abnormal sub-highway section includes:

[0200] For each abnormal sub-highway section in the set of abnormal sub-highway sections, determine the corresponding edge sub-section server, and the edge sub-section server is used for data processing of this abnormal sub-highway section;

[0201] For each abnormal sub-highway section in the set of abnormal sub-highway sections, based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set, perform the first correlation analysis and the second correlation analysis on this abnormal sub-highway section on the edge sub-section server corresponding to this abnormal sub-highway section to obtain the first correlation analysis result and the second correlation analysis result; the first correlation analysis is used to analyze the collaborative correlation between the auxiliary data within each of the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions; the second correlation analysis is used to analyze the modal correlation between the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set from the perspective of highway abnormal conditions;

[0202] For each abnormal sub-highway section in the set of abnormal sub-highway sections, determine the abnormal influence factor of this abnormal sub-highway section based on the first correlation analysis result and the second correlation analysis result of this abnormal sub-highway section.

[0203] It can be seen that the device described in implementing this alternative embodiment can determine the edge sub-section server corresponding to each abnormal sub-highway section and perform correlation analysis on the abnormal sub-highway section on the edge sub-section server, which helps to reduce the load pressure of cloud (total assembly) computing through the edge computing ability of the edge sub-section server and improve the data processing efficiency of the abnormal sub-highway section. Further, determining the abnormal impact factors of the abnormal sub-highway section based on correlation analysis helps to improve the accuracy of determining the abnormal impact factors of the abnormal sub-highway section, and further improve the accuracy of highway vehicle spatio-temporal path prediction.

[0204] In yet another alternative embodiment, the specific manner in which the prediction module 305 performs vehicle spatio-temporal path prediction operations on the target highway section based on all the abnormal impact factors of each abnormal sub-highway section includes:

[0205] Based on the target highway section, generate an initial full-course road model of the target highway section;

[0206] Based on all the abnormal impact factors of each abnormal sub-highway section, generate an abnormal sub-road model of the abnormal sub-highway section;

[0207] Based on the abnormal sub-road models of all the abnormal sub-highway sections, correct the initial full-course road model to obtain a corrected full-course road model of the target highway section;

[0208] Based on all the abnormal impact factors of all the abnormal sub-highway sections, the corrected full-course road model, and all vehicle types, generate a predicted spatio-temporal path corresponding to each vehicle type within the target highway section.

[0209] It can be seen that the device described in implementing this alternative embodiment can generate an initial full-course road model of the target highway section, generate an abnormal sub-road model based on the abnormal impact factors, and correct the initial full-course road model to obtain a corrected full-course road model of the target highway section, which helps to improve the correction accuracy of correcting the initial full-course road model. Further, generating a predicted spatio-temporal path based on all the abnormal impact factors, the corrected full-course road model, and all vehicle types helps to improve the accuracy of highway vehicle spatio-temporal path prediction.

[0210] In yet another alternative embodiment, the specific manner in which the division module 302 divides the target highway section to determine a set of sub-highway sections including multiple sub-highway sections includes:

[0211] Determine all toll stations, main-road ETC gantries, and ramp ETC gantries of the target highway section;

[0212] Divide the target highway section based on all toll stations, main-road ETC gantries, and ramp ETC gantries to obtain a set of shortest sub-highway sections containing multiple shortest sub-highway sections;

[0213] For each shortest sub-highway section in the set of shortest sub-highway sections, determine whether the section length of the shortest sub-highway section meets a preset sub-highway section length threshold to obtain a length threshold judgment result for the shortest sub-highway section;

[0214] For each shortest sub-highway section in the set of shortest sub-highway sections, when the length threshold judgment result of the shortest sub-highway section is used to indicate that the section length of the shortest sub-highway section does not meet the sub-highway section length threshold, determine the target shortest sub-highway section corresponding to the shortest sub-highway section; splice the shortest sub-highway section with the target shortest sub-highway section corresponding to the shortest sub-highway section to obtain a spliced shortest sub-highway section corresponding to the shortest sub-highway section; the target shortest sub-highway section is the shortest sub-highway section with a shorter length among the two adjacent shortest sub-highway sections of the shortest sub-highway section;

[0215] Based on all the shortest sub-highway sections that have not been spliced and all the spliced shortest sub-highway sections in the set of shortest sub-highway sections, determine a set of sub-highway sections containing multiple sub-highway sections.

[0216] It can be seen that the device described in the optional embodiment can divide the highway section based on all toll stations, main-road ETC gantries, and ramp ETC gantries, obtain the shortest sub-highway sections and judge whether the section length of each shortest sub-highway section meets the conditions. When the conditions are met, determine the corresponding target shortest sub-highway section and splice the shortest sub-highway section with the corresponding target shortest sub-highway section. After all splicing is completed, determine the set of sub-highway sections; it is beneficial to improve the accuracy of highway section division, and further improve the accuracy of determining abnormal sub-highway sections, thereby improving the accuracy and stability of highway vehicle spatio-temporal path prediction.

[0217] Embodiment 4

[0218] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of another highway vehicle spatio-temporal path prediction device disclosed in the embodiments of the present invention. As Figure 5 shown, the highway vehicle spatio-temporal path prediction device may include:

[0219] A memory 401 storing executable program code;

[0220] A processor 402 coupled to the memory 401;

[0221] The processor 402 calls the executable program code stored in the memory 401 and executes the steps in the highway vehicle spatio-temporal path prediction method described in Embodiment 1 or Embodiment 2 of the present invention.

[0222] Embodiment 5

[0223] An embodiment of the present invention discloses a computer storage medium storing computer instructions, which when called, are used to execute the steps in the highway vehicle spatio-temporal path prediction method described in Embodiment 1 or Embodiment 2 of the present invention.

[0224] Embodiment 6

[0225] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the highway vehicle spatio-temporal path prediction method described in Embodiment 1 or Embodiment 2.

[0226] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative work.

[0227] Through the specific descriptions of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, and the storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0228] Finally, it should be noted that: The disclosed highway vehicle spatio-temporal path prediction method and device according to the embodiments of the present invention are only the preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the spatiotemporal path of vehicles on a highway, characterized in that: The method comprises: Determine the target highway section to be predicted; Dividing the target highway section into highway sections to determine a sub-highway section set including a plurality of sub-highway sections; Obtaining the sub-passing time of all target vehicles passing through the target expressway section within a preset first time range when passing through each of the sub-expressway sections; Calculating the sub-comprehensive passing time of each sub-highway section based on the sub-passing time of all target vehicles in each sub-highway section; Determine an abnormal sub-highway section set including a plurality of abnormal sub-highway sections from the sub-highway section set; the abnormal sub-highway section is the sub-highway section whose corresponding sub-comprehensive passing time is abnormal data; For each of the abnormal sub-highway sections in the abnormal sub-highway section set, determining an abnormal impact factor of the abnormal sub-highway section; Based on all the abnormal influencing factors of each abnormal sub-highway section, a vehicle spatiotemporal path prediction operation is performed on the target highway section, wherein the vehicle spatiotemporal path prediction operation is used to predict the spatiotemporal path of vehicles passing through the target highway section within a subsequent preset second time range; Wherein, for each of the abnormal sub-highway sections in the set of abnormal sub-highway sections, determining the abnormal impact factor of the abnormal sub-highway section comprises: Determine all target intelligent assisted driving vehicles from all the target vehicles; For each of the target intelligent assisted driving vehicles, obtaining a first auxiliary data set, a second auxiliary data set, and a third auxiliary data set of the target intelligent assisted driving vehicle; The first auxiliary data set includes at least one of forward collision warning data, rear collision warning data, blind spot monitoring warning data, lane change warning data, lane departure warning data, forward crossing warning data, and rear crossing warning data; The second auxiliary data set includes at least one of automatic emergency braking data, automatic emergency avoidance data, lane keeping assistance data, lane departure assistance data, lane centering assistance data, intelligent speed limit assistance data, acceleration and deceleration lane change assistance data and automatic overtaking assistance data; The third auxiliary data set includes at least one of the intelligent assisted driving takeover mileage, the intelligent assisted driving takeover ratio, and the number of intelligent assisted driving manual takeovers; For each abnormal sub-highway section in the abnormal sub-highway section set, the abnormal impact factor of the abnormal sub-highway section is determined based on the first auxiliary data set, the second auxiliary data set and the third auxiliary data set of all the target intelligent assisted driving vehicles in the abnormal sub-highway section.

2. The method for predicting the spatiotemporal path of a highway vehicle according to claim 1, characterized in that: Before dividing the target highway section into highway sections and determining a sub-highway section set including a plurality of sub-highway sections, the method further includes: Obtaining the passing time of all target vehicles passing through the target expressway section within a preset first time range; Calculate the comprehensive passing time of the target expressway section based on the passing time of all the target vehicles; Determine whether the comprehensive passing time meets a preset passing time threshold, and obtain a comprehensive passing time determination result; When the comprehensive passing time judgment result is used to indicate that the comprehensive passing time does not meet the passing time threshold, it triggers the execution of the operation of dividing the target expressway section into expressway sections and determining a sub-expressway section set including multiple sub-expressway sections.

3. The method for predicting the spatiotemporal path of a highway vehicle according to claim 2, characterized in that: All the target vehicles have corresponding vehicle types; And, the comprehensive passing time of the target expressway section is calculated based on the passing time of all the target vehicles, including: Based on each of the vehicle types and the number of the target vehicles under the vehicle type, determining a passing time weight of the vehicle type; Based on the passing time of each target vehicle under each vehicle type, calculating the average passing time of all target vehicles under the vehicle type; Based on the passing time weight of each vehicle type and the average passing time of all the target vehicles of the vehicle type, the comprehensive passing time of the target expressway section is calculated.

4. The method for predicting the spatiotemporal path of a highway vehicle according to claim 1, characterized in that: For each abnormal sub-highway section in the abnormal sub-highway section set, determining the abnormal impact factor of the abnormal sub-highway section based on the first auxiliary data set, the second auxiliary data set, and the third auxiliary data set of all the target intelligent assisted driving vehicles in the abnormal sub-highway section, comprises: For each abnormal sub-highway section in the abnormal sub-highway section set, determining an edge sub-highway section server corresponding thereto, wherein the edge sub-highway section server is used for data processing of the abnormal sub-highway section; For each abnormal sub-highway section in the abnormal sub-highway section set, based on the first auxiliary data set, the second auxiliary data set and the third auxiliary data set, a first association analysis and a second association analysis are performed on the abnormal sub-highway section on the edge sub-highway section server corresponding to the abnormal sub-highway section to obtain a first association analysis result and a second association analysis result; the first association analysis is used to analyze the collaborative association between the auxiliary data within each set of the first auxiliary data set, the second auxiliary data set and the third auxiliary data set based on the perspective of the abnormal condition of the highway; the second association analysis is used to analyze the modal association between the first auxiliary data set, the second auxiliary data set and the third auxiliary data set based on the perspective of the abnormal condition of the highway; For each of the abnormal sub-highway sections in the abnormal sub-highway section set, an abnormal impact factor of the abnormal sub-highway section is determined based on the first association analysis result and the second association analysis result of the abnormal sub-highway section.

5. The method for predicting the spatiotemporal path of a highway vehicle as claimed in claim 3, characterized in that: The performing of a vehicle spatiotemporal path prediction operation on the target highway section based on all the abnormal impact factors of each abnormal sub-highway section includes: Based on the target expressway section, generating an initial full-course road model of the target expressway section; Based on all the abnormal influencing factors of each abnormal sub-highway section, generating an abnormal sub-road model of the abnormal sub-highway section; Based on the abnormal sub-road models of all the abnormal sub-highway sections, the initial full-course road model is modified to obtain a modified full-course road model of the target high-speed section; Based on all the abnormal influencing factors of all the abnormal sub-highway sections, the modified full-course road model and all the vehicle types, a predicted space-time path corresponding to each vehicle type in the target high-speed section is generated.

6. The method for predicting the spatiotemporal path of a highway vehicle according to any one of claims 1 to 5, characterized in that: The step of dividing the target highway section into highway sections and determining a sub-highway section set including a plurality of sub-highway sections includes: Determine all toll stations, main road ETC gantries and ramp ETC gantries on the target expressway section; Divide the target expressway section into expressway sections based on all the toll stations, the main road ETC gantries and the ramp ETC gantries to obtain a shortest sub-expressway section set including multiple shortest sub-expressway sections; For each of the shortest sub-highway sections in the shortest sub-highway section set, determining whether the section length of the shortest sub-highway section meets a preset sub-highway section length threshold, and obtaining a length threshold determination result of the shortest sub-highway section; For each of the shortest sub-highway sections in the shortest sub-highway section set, when the length threshold judgment result of the shortest sub-highway section is used to indicate that the section length of the shortest sub-highway section does not meet the sub-highway section length threshold, determine the target shortest sub-highway section corresponding to the shortest sub-highway section; splice the shortest sub-highway section with the target shortest sub-highway section corresponding to the shortest sub-highway section to obtain the spliced ​​shortest sub-highway section corresponding to the shortest sub-highway section; the target shortest sub-highway section is the shortest sub-highway section with the shorter length of the two shortest sub-highway sections adjacent to the shortest sub-highway section; Based on all the unjoined shortest sub-freeway sections in the shortest sub-freeway section set and all the joined shortest sub-freeway sections, a sub-freeway section set including a plurality of sub-freeway sections is determined.

7. A device for predicting the spatiotemporal path of vehicles on a highway, characterized in that: The device comprises: A determination module, used to determine a target highway section to be predicted; A division module, used for dividing the target highway section into highway sections and determining a sub-highway section set including a plurality of sub-highway sections; An acquisition module, used for acquiring the sub-passing time of all target vehicles passing through the target expressway section within a preset first time range when passing through each sub-expressway section; A calculation module, used for calculating the sub-comprehensive passing time of each sub-highway section based on the sub-passing time of all target vehicles in each sub-highway section; The determination module is further used to determine an abnormal sub-highway section set including a plurality of abnormal sub-highway sections from the sub-highway section set; the abnormal sub-highway section is the sub-highway section whose corresponding sub-comprehensive passing time is abnormal data; for each abnormal sub-highway section in the abnormal sub-highway section set, determine the abnormal impact factor of the abnormal sub-highway section; A prediction module, configured to perform a vehicle spatiotemporal path prediction operation on the target highway section based on all the abnormal influencing factors of each abnormal sub-highway section, wherein the vehicle spatiotemporal path prediction operation is used to predict the spatiotemporal path of vehicles passing through the target highway section within a subsequent preset second time range; The specific manner in which the determination module determines the abnormal impact factor of each abnormal sub-highway section in the abnormal sub-highway section set includes: Determine all target intelligent assisted driving vehicles from all the target vehicles; For each of the target intelligent assisted driving vehicles, obtaining a first auxiliary data set, a second auxiliary data set, and a third auxiliary data set of the target intelligent assisted driving vehicle; The first auxiliary data set includes at least one of forward collision warning data, rear collision warning data, blind spot monitoring warning data, lane change warning data, lane departure warning data, forward crossing warning data, and rear crossing warning data; The second auxiliary data set includes at least one of automatic emergency braking data, automatic emergency avoidance data, lane keeping assistance data, lane departure assistance data, lane centering assistance data, intelligent speed limit assistance data, acceleration and deceleration lane change assistance data and automatic overtaking assistance data; The third auxiliary data set includes at least one of the intelligent assisted driving takeover mileage, the intelligent assisted driving takeover ratio, and the number of intelligent assisted driving manual takeovers; For each abnormal sub-highway section in the abnormal sub-highway section set, the abnormal impact factor of the abnormal sub-highway section is determined based on the first auxiliary data set, the second auxiliary data set and the third auxiliary data set of all the target intelligent assisted driving vehicles in the abnormal sub-highway section.

8. A device for predicting the spatiotemporal path of vehicles on a highway, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the steps in the highway vehicle spatiotemporal path prediction method as described in any one of claims 1-6.

9. A computer storage medium, characterized in that The computer storage medium stores computer instructions, and when the computer instructions are called, the steps in the highway vehicle spatiotemporal path prediction method according to any one of claims 1 to 6 are executed.

Images