A method, apparatus, device and medium for generating highway section labels

Abstract

The present application relates to the technical field of high-speed section label generation, and provides a method, device, equipment and medium for generating high-speed section labels. The method of the present application includes: statistically analyzing the highway gantry passing data to obtain the regional traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of the high-speed section; clustering all high-speed sections based on the regional traffic ratio, long-distance traffic ratio, traffic flow, truck traffic ratio, and average vehicle speed to obtain clustering clusters; calculating the freight function value according to the traffic flow of the high-speed section in the historical time period and all vehicle types; generating freight labels according to all freight function values to obtain the freight labels of each high-speed section, and generating section labels according to all clustering clusters to obtain the section labels of each high-speed section. This method can improve the accuracy of high-speed section label generation.

Description

Technical Field

[0001] This application relates to the technical field of high-speed section label generation, and particularly relates to a method, device, equipment and medium for generating high-speed section labels. Background Art

[0002] The functions of labels for differentiating different high-speed sections are mainly reflected in aspects such as improving road transportation efficiency, ensuring traffic safety, and optimizing resource allocation. By dividing the high-speed sections with labels, more scientific and reasonable transportation plans can be formulated according to the characteristics and conditions of different sections, so as to make full use of the transportation capacity of the highway. This division helps transportation enterprises select appropriate sections for freight transportation, reduce transportation time and costs, and improve transportation efficiency. At the same time, for sections with different labels, corresponding traffic management measures and safety guarantee measures can be taken to better ensure the safety of freight vehicles and personnel. In addition, by optimizing resource allocation, the transportation capacity of the highway can be given full play, providing more powerful support for economic development. However, in the current analysis of high-speed sections, usually single data is used for label generation, resulting in low accuracy of high-speed section label generation. Summary of the Invention

[0003] This application provides a method, device, equipment and medium for generating high-speed section labels, which can solve the problem of low accuracy of high-speed section label generation.

[0004] In a first aspect, this application provides a method for generating high-speed section labels. The method for generating high-speed section labels includes:

[0005] Obtain the highway gantry passing data of the target area; the highway gantry passing data includes the time when each vehicle passing through the gantry in the target area passes through the gantry and the entrance toll station and exit toll station through which the vehicle passes. The multiple vehicles passing through the gantry in the target area include vehicles of various different vehicle types;

[0006] Based on the highway gantry passing data, conduct statistics to obtain the in-region traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of each high-speed section in the target area;

[0007] Based on the in-region traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of all high-speed sections, cluster all high-speed sections to obtain multiple clustering clusters;

[0008] For each high-speed section respectively, calculate the freight function value of the high-speed section according to the traffic flow of the high-speed section in the historical time period and all vehicle types; the freight function value is used to describe the truck passing efficiency of the high-speed section.

[0009] Generate freight labels based on all freight function values to obtain the freight labels for each highway section, and generate section labels based on all clustering clusters to obtain the section labels for each highway section; the freight labels are used to describe the passing conditions of freight vehicles on the highway section, and the section labels are used to describe the passing conditions of vehicles of all vehicle types on the highway section.

[0010] In a second aspect, the present application provides a device for generating highway section labels, including:

[0011] An acquisition module that acquires the highway gantry passing data of the target area; the highway gantry passing data includes the time when each vehicle passing through the gantry in the target area passes through the gantry and the entrance toll station and exit toll station through which the vehicle passes. The multiple vehicles passing through the gantry in the target area include vehicles of multiple different vehicle types;

[0012] A statistics module that performs statistics based on the highway gantry passing data to obtain the regional traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of each highway section in the target area;

[0013] A clustering module that clusters all highway sections based on the regional traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of all highway sections to obtain multiple clustering clusters;

[0014] A calculation module that, for each highway section, calculates the freight function value of the highway section according to the traffic flow of the highway section in the historical time period and all vehicle types; the freight function value is used to describe the passing efficiency of trucks on the highway section;

[0015] A label generation module that generates freight labels for each highway section according to all freight function values, and generates section labels for each highway section according to all clustering clusters; the freight labels are used to describe the passing conditions of freight vehicles on the highway section, and the section labels are used to describe the passing conditions of vehicles of all vehicle types on the highway section.

[0016] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned highway label generation method is implemented.

[0017] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium that stores a computer program. When the computer program is executed by a processor, the above-mentioned highway label generation method is implemented.

[0018] The above solution of this application has the following beneficial effects:

[0019] In the embodiments of this application, by generating section labels for highway sections based on the proportion of regional traffic, long-distance traffic, traffic flow, freight traffic proportion, and average vehicle speed, the information richness and accuracy of label generation can be improved. Generating freight labels for highway sections can describe the passing conditions of freight vehicles on highway sections. Combining section labels can realize label generation for highway sections from both freight and overall aspects, effectively improving the comprehensiveness and accuracy of label generation for highway sections.

[0020] Other beneficial effects of this application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a flowchart of a method for generating highway section labels provided by an embodiment of this application;

[0023] Figure 2 It is a statistical bar chart of the number of gantry passes provided by an embodiment of this application;

[0024] Figure 3 It is a statistical bar chart of the number of times vehicles enter the highway provided by an embodiment of this application;

[0025] Figure 4 It is a schematic diagram of a highway section provided by an embodiment of this application;

[0026] Figure 5 It is a schematic diagram of gantry distribution provided by an embodiment of this application;

[0027] Figure 6 It is a schematic diagram of vehicle trajectories provided by an embodiment of this application;

[0028] Figure 7 It is a silhouette coefficient curve graph provided by an embodiment of this application;

[0029] Figure 8 It is a traffic flow statistical graph provided by an embodiment of this application;

[0030] Figure 9 It is a statistical graph of the proportion of provincial traffic provided by an embodiment of this application;

[0031] Figure 10 Statistical chart of the traffic proportion over 500 kilometers provided by an embodiment of the present application;

[0032] Figure 11 Statistical chart of the truck traffic proportion provided by an embodiment of the present application;

[0033] Figure 12 Statistical chart of the average vehicle speed provided by an embodiment of the present application;

[0034] Figure 13 Schematic diagram of the clustering result of the highway section provided by an embodiment of the present application;

[0035] Figure 14 Schematic diagram of the freight label provided by an embodiment of the present application;

[0036] Figure 15 Schematic diagram of the structure of the highway section label generation device provided by an embodiment of the present application;

[0037] Figure 16 Schematic diagram of the structure of the terminal device provided by an embodiment of the present application. Detailed implementation manners

[0038] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0039] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0040] It should also be understood that the term " / and" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0041] Reference to "one embodiment" or "some embodiments" etc. described in the specification of this application means that a specific feature, structure or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments" etc. that appear at different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0042] In view of the problem of low accuracy in generating tags for existing highway sections, the embodiments of this application provide a method for generating highway section tags. By generating section tags for highway sections based on the traffic ratio within the region, the long-distance traffic ratio, traffic flow, truck traffic ratio, and average vehicle speed, it is possible to improve the information richness and accuracy of tag generation. Generating freight tags for highway sections can describe the passing conditions of freight vehicles on highway sections. Combining with the section tags, it is possible to generate tags for highway sections from both the freight and overall aspects, effectively improving the comprehensiveness and accuracy of tag generation for highway sections.

[0043] Next, an exemplary description will be given of the method for generating highway section tags provided by this application.

[0044] As Figure 1 shown, the method for generating highway section tags provided by this application includes the following steps:

[0045] Step 11, obtain the highway gantry passing data of the target area.

[0046] The above highway gantry passing data includes the time when each vehicle passing through the gantry in the target area within the historical time period, as well as the entrance toll station and exit toll station through which the vehicle passes (the information of the entrance toll station and exit toll station through which the vehicle passes is collected by the information collection devices on the gantries erected at the entrance toll station and exit toll station when the vehicle passes through the entrance toll station and exit toll station. Therefore, in the highway management gantry passing data, the time when the vehicle passes through the gantry is recorded. If the gantry corresponds to the entrance toll station or exit toll station through which the vehicle passes, the gantry is marked as the entrance toll station or exit toll station of the vehicle. The gantries of the entrance toll station and the exit toll station may not be the gantries within the target area). The multiple vehicles passing through the gantries in the target area include vehicles of multiple different vehicle types. The multiple vehicle types include multiple types of trucks (small trucks, large trucks, etc.) and other types (small passenger cars, large passenger cars, engineering vehicles, ambulances, etc.). The target area is the area where highway tags need to be generated, such as a province. The gantry is a door-frame type rack set on the highway for road traffic. Intelligent traffic cameras, speed measuring instruments and other devices are set on the gantry for collecting the driving information of vehicles.

[0047] Exemplarily, in the historical time period, a total of 10 vehicles passed through the gantries in the target area. Among them, the first vehicle only passed through three gantries, and the first gantry was the entrance toll station, and the third gantry was the exit toll station. Then the highway gantry passing data includes the time when the first vehicle passed through the three gantries, and the information that the first gantry was the entrance toll station and the third gantry was the exit toll station, and also includes the number of gantries passed through by the other 9 vehicles and the corresponding time, entrance toll station and exit toll station information.

[0048] In some embodiments of the present application, the highway gantry passing data in the historical time period can be obtained by accessing the gantry system of the target area, the positioning system of the vehicle, etc.

[0049] It should be noted that the highway gantry passing data also includes the vehicle license plate number, vehicle type, gantry information, etc. of the vehicle. For the integrity of the data, the gantry data and the vehicle passing data can be obtained, and then the gantry data and the passing data can be integrated to obtain the highway gantry passing data. After obtaining the gantry data, it needs to be preprocessed. Specifically, first, remove the redundant gantry data. There are some redundant data in the original gantry data. Extract the fields of "passing identification ID", "gantry number", "gantry HEX", "driving direction", "passing time", "billing vehicle license plate number", "billing vehicle type code", "billing vehicle category code", "entrance station HEX", "entrance name", "entrance time", "previous gantry HEX", "time of passing the previous gantry", "billing mileage", "longitude", "latitude", "pile number", "repetition times of billing vehicle license plate number" from the gantry data. The partial gantry data extracted is shown in Table 1.

[0050] Table 1

[0051]

[0052] NULL indicates data missing, and the gantry HEX is the number of the gantry. Next, remove the redundant passing data. There are some redundant data in the original passing data. Extract the fields of "passing identification ID", "billing vehicle license plate number", "entrance HEX", "entrance time", "exit HEX", "exit time", "accumulative billing mileage" from the passing data. The partial passing data extracted is shown in Table 2.

[0053] Table 2

[0054]

[0055] With the gantry data and the passing data, in theory, the complete trajectory of the vehicle from the entrance toll station to all the gantries passed through until the exit toll station can be traced. The extracted passing data and the extracted gantry data are screened out according to the same passing identification ID and merged. These trajectory data theoretically have the data from the entrance toll station to the gantries collected during the collection period and then to the exit toll station. The partial highway gantry passing data obtained after combining the gantry data and the passing data is shown in Table 3.

[0056] Table 3

[0057]

[0058] Exemplarily, for a certain target area, the number of vehicles within the investigation time is 1,136,951 vehicles, accounting for 6.9% of the gantry data. That is, approximately 14 gantry data are collected for each vehicle on average. The number of times each vehicle appears repeatedly is counted, that is, the number of gantries each vehicle passes through. It is found that 41.2% of the vehicles pass through the gantries 6 times or less, and the proportion of vehicles passing through the gantries 10 times or less is as Figure 2 shown. In the figure, the horizontal axis represents the number of gantries a vehicle passes through, and the vertical axis represents the vehicle proportion. It can be found that as the number of gantry passes increases, the corresponding number of vehicles as a whole shows a downward trend. Among them, 8.6% of the vehicles have only 1 gantry data record, and the vehicles passing through the gantries 10 times are less than 3.4%.

[0059] The number of times the vehicle enters the highway and the corresponding vehicle proportion are counted as Figure 3 shown. In the figure, the horizontal axis represents the number of times the vehicle enters the highway, and the vertical axis represents the vehicle proportion. It can be found that within the data collection range, 32.0% of the vehicles enter the highway only once; 16.7% of the vehicles enter the highway twice; only a very small number of vehicles enter the highway more than five times.

[0060] Step 12: Based on the highway gantry passing data for statistics, obtain the regional traffic proportion, long-distance traffic proportion, traffic flow in the historical time period, truck traffic proportion, and average vehicle speed of each highway section in the target area.

[0061] The above regional traffic proportion is used to describe the proportion of regional vehicles (vehicles with both the corresponding entrance toll station and exit toll station located within the target area) among all vehicles passing through the highway section. The long-distance traffic proportion is used to describe the proportion of long-distance vehicles among all vehicles passing through the highway section. The traffic flow in the historical time period is used to describe the number of vehicles passing through the highway section within the historical time period. The truck traffic proportion is used to describe the proportion of trucks among all vehicles passing through the highway section. The average vehicle speed is used to describe the average speed of vehicles passing through the highway section.

[0062] In some embodiments of the present application, the step of obtaining the regional traffic proportion, long-distance traffic proportion, traffic flow in the historical time period, truck traffic proportion, and average vehicle speed of each highway section in the target area based on the highway gantry passing data includes:

[0063] In the first step, for each vehicle in all highway gantry passing data, obtain all the gantries passed by the vehicle, the time of passing the gantries, the exit toll station and the entrance toll station from all highway gantry passing data, and integrate all the gantries passed by the vehicle, the time of passing the gantries, the exit toll station and the entrance toll station to obtain the vehicle's trajectory. If both the entrance toll station and the exit toll station passed by the vehicle belong to the gantries within the target area, the vehicle is regarded as a vehicle within the area. If the length of the vehicle's trajectory is greater than the length threshold, the vehicle is regarded as a long-distance vehicle.

[0064] Exemplarily, when integrating all the gantries passed by the vehicle, the time of passing the gantries, the exit toll station and the entrance toll station, take the location of the entrance toll station as the starting point, sort the locations of all the passed gantries in ascending order of the time of passing the gantries, and finally take the location of the exit toll station as the end point. If either the entrance toll station or the exit toll station passed by the vehicle does not belong to the gantries within the target area, the vehicle is not processed; if the length of the vehicle's trajectory is less than or equal to the length threshold, the vehicle is not processed.

[0065] In the second step, based on the trajectories of all vehicles and all vehicles within the area, calculate the regional traffic ratio of each highway section in the target area.

[0066] Specifically, for each highway section, count the total number of vehicles passing through the highway section based on the trajectories of all vehicles, count the number of vehicles within the area passing through the highway section based on the trajectories of all vehicles within the area, and calculate the ratio between the total number of vehicles passing through the highway section and the number of vehicles within the area passing through the highway section to obtain the regional traffic ratio.

[0067] In the third step, based on the trajectories of all vehicles and all long-distance vehicles, calculate the long-distance traffic ratio of each highway section in the target area.

[0068] Specifically, for each highway section, count the number of long-distance vehicles passing through the highway section based on the trajectories of all long-distance vehicles, and calculate the ratio between the total number of vehicles passing through the highway section and the number of long-distance vehicles passing through the highway section to obtain the long-distance traffic ratio of the highway section.

[0069] In the fourth step, calculate the traffic flow of each highway section in the target area during the historical time period based on the trajectories of all vehicles.

[0070] Specifically, for each highway section, take the total number of vehicles passing through the highway section as the traffic flow of the highway section during the historical time period.

[0071] Step 5: Calculate the truck traffic proportion of each highway section in the target area based on the trajectories of all vehicles and all vehicle types.

[0072] Specifically, for each highway section, count the number of trucks passing through the highway section according to the trajectories of vehicles of all vehicle types that are trucks, and calculate the ratio between the number of trucks passing through the highway section and the total number of vehicles passing through the highway section to obtain the truck traffic proportion.

[0073] Step 6: Calculate the average vehicle speed of each highway section in the target area based on the trajectories of all vehicles.

[0074] Specifically, for each highway section, perform the following steps:

[0075] Take the vehicles passing through the highway section in each trajectory as target vehicles;

[0076] For each target vehicle, calculate the time taken for the target vehicle to pass between adjacent gantries in the highway section, and calculate the ratio between the length and the time taken between adjacent gantries in the highway section to obtain the speed of the target vehicle between adjacent gantries in the highway section; if the speed of the target vehicle between adjacent gantries in the highway section is within the preset speed threshold range, consider the journey of the vehicle between adjacent gantries in the highway section as a normal journey without stops, and calculate the average value of the driving speeds of all target vehicles with normal journeys between the corresponding adjacent gantries in the highway section, thereby obtaining the average vehicle speed of this highway section.

[0077] Exemplarily, the average rate calculation formula can be used to calculate the time difference and distance between the starting point and the ending point of the vehicle passing through adjacent gantries to obtain the average speed of the vehicle between adjacent gantries. The adjacent gantries on the highway in the above text refer to any two adjacent gantries in this highway section.

[0078] The above highway section is exemplarily illustrated below with a specific example.

[0079] The highway sections in a certain province are as Figure 4 shown, Figure 4 where the numbers are the numbers of the highway sections, and the solid lines represent the highways in this province. The distribution of gantries on the highway sections in a local area of this province is as Figure 5 shown, Figure 5 where the solid lines represent the highways, the dots represent the gantries, the numbers and combinations of numbers and letters (such as 481A07) are the numbers of the gantries or toll stations, and the triangles represent the entrance toll stations and exit toll stations. The trajectories of some vehicles from the Figure 5 shown entrance toll station to the exit toll station are as Figure 6 shown, where the solid lines in the figure represent one vehicle trajectory (Path A), and the dashed lines represent another vehicle trajectory (Path B).

[0080] Step 13: Cluster all highway segments based on the regional traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of all highway segments, to obtain multiple clustering clusters.

[0081] Specifically, combine the regional traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of each highway segment into one data as a data point, and then use a clustering algorithm to cluster all data points to obtain multiple clustering clusters.

[0082] Exemplarily, the above clustering algorithm can be algorithms such as K-means clustering. In K-means clustering, the selection of k is very crucial, which determines the number of final clusters. In practical applications, some methods are usually used to select an appropriate k value, such as the elbow method, silhouette coefficient method, etc. By testing the silhouette coefficients corresponding to k values (number of classifications) from 2 to 10, the silhouette coefficients corresponding to different k values are as Figure 7 shown. The horizontal axis represents the value of the number of clusters k, and the vertical axis represents the silhouette coefficient. It can be found that 9 is the optimal k value, and it is most appropriate to divide the data into 9 categories. Therefore, all highway segments can be clustered to obtain 9 clustering clusters.

[0083] Step 14: For each highway segment, calculate the freight function value of the highway segment according to the traffic flow and all vehicle types in the historical time period of the highway segment.

[0084] The freight function value is used to describe the truck passing efficiency of the highway segment.

[0085] Specifically, through the formula:

[0086] ;

[0087] Calculate the freight function value .

[0088] Where, represents the proportion of the th type of truck among all vehicles passing through the highway segment, represents the total number of axles of the th type of truck, represents the number of truck types, represents the traffic flow of the highway segment in the historical time period, represents the average vehicle speed of the highway segment.

[0089] Exemplarily, there are some differences in the number of axles and weight of different types of freight trucks. The transportation effects borne by different types of freight trucks on a road section are also different. Therefore, it is necessary to distinguish different types of freight trucks. The definitions of different truck models are shown in Table 4.

[0090] Table 4

[0091]

[0092] It is worth mentioning that different factors are comprehensively considered, including the composition ratio of different types of freight trucks, their respective total number of axles (reflecting the heavy-load capacity of the vehicle and the potential impact on the road surface), the traffic flow of the road section (reflecting the busyness and passing capacity of the road section), and the average speed per hour of the road section (reflecting the traffic smoothness and efficiency). By calculating the proportion of each vehicle type in the traffic flow of the road section, the contribution degree of each type of freight truck to the freight function value can be accurately measured. At the same time, combined with the total number of axles of each vehicle type, the impact on the road section's transportation capacity and road surface wear can be further evaluated. The traffic flow and average speed of the road section are directly related to the actual passing capacity and traffic efficiency of the road section. The comprehensive application of these indicators provides strong data support for scientifically evaluating the freight function of highway sections, optimizing the selection of freight vehicles, and improving the operation efficiency of highways.

[0093] Step 15: Generate freight labels based on all freight function values to obtain the freight labels for each highway section, and generate section labels based on all clustering clusters to obtain the section labels for each highway section.

[0094] The above-mentioned freight labels are used to describe the passing conditions of freight vehicles on highway sections (for example, the freight labels can describe the freight grades of highway sections), and the section labels are used to describe the passing conditions of vehicles of all vehicle types on highway sections.

[0095] Specifically, the highway sections can be classified by grade according to the freight function values to obtain the freight labels of the highway sections. For example, highway sections with freight function values less than the first preset value are regarded as first-level freight grades, highway sections with freight function values greater than or equal to the first preset value and less than the second preset value are regarded as second-level freight grades, and highway sections greater than or equal to the second preset value are regarded as third-level freight sections. The larger the freight function value, the higher the freight grade, and the higher the passing capacity and passing efficiency of freight vehicles on the highway section. The labels of each clustering cluster can be obtained by classifying data such as the regional traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, freight truck traffic ratio, and vehicle average speed of the highway sections in each clustering cluster.

[0096] Exemplarily, classification models such as convolutional neural networks can be utilized for label classification to obtain the labels of the clustering clusters, and the labels are preset according to the actual road segment analysis requirements. For example, the label "High-traffic Province-dominated Road Segment" indicates that the proportion of intra-provincial traffic of the highway segments in this clustering cluster is extremely high. It may be the main highway channel connecting large cities or important economic regions within the province, with a large traffic flow and mainly intra-provincial vehicles.

[0097] It should be noted that after obtaining the freight labels and road segment labels, corresponding traffic management measures and safety guarantee measures can be adopted for the highway segments according to the freight labels and road segment labels. For example, for highway segments with a high freight level, there are more freight vehicles on this highway segment, and the consequences of traffic accidents are serious, so the safety facilities of this highway segment should be increased.

[0098] It is worth mentioning that generating road segment labels for highway segments based on the intra-regional traffic proportion, long-distance traffic proportion, traffic flow, freight vehicle traffic proportion, and average vehicle speed can improve the information richness and accuracy of label generation. Generating freight labels for highway segments can describe the passing conditions of freight vehicles on the highway segments. Combining the road segment labels can realize label generation for highway segments from both the freight and overall aspects, effectively improving the comprehensiveness and accuracy of label generation for highway segments.

[0099] The above steps will be exemplarily described below with a specific example.

[0100] All highway segments in a certain province are clustered into 9 clustering clusters, and the traffic flow statistics of the highway segments in the 9 clustering clusters in a certain historical time period are as Figure 8 shown, Figure 8 where the horizontal axis represents the traffic flow, with the unit of vehicles per hour (veh / h), and the vertical axis represents the frequency, Figure 8 a represents the traffic flow statistics of the 1st clustering cluster, Figure 8 b represents the traffic flow statistics of the 2nd clustering cluster, Figure 8 c represents the traffic flow statistics of the 3rd clustering cluster, Figure 8 d represents the traffic flow statistics of the 4th clustering cluster, Figure 8 e represents the traffic flow statistics of the 5th clustering cluster, Figure 8 f represents the traffic flow statistics of the 6th clustering cluster, Figure 8 g represents the traffic flow statistics of the 7th clustering cluster, Figure 8 h represents the traffic flow statistics of the 8th clustering cluster, Figure 8 i represents the traffic flow statistics of the 9th clustering cluster.

[0101] It can be found that from the perspective of traffic flow differences, the 9 clusters can be divided into several different traffic flow ranges. The traffic flows of cluster 5 and cluster 8 are the highest, which may represent busy urban centers or transportation hub areas. The traffic flows of cluster 1, cluster 7, and clusters 3, 4, and 6 are respectively at medium-high and medium levels, which may represent urban or suburban traffic with different densities and degrees of busyness. The traffic flows of cluster 2 and cluster 9 are relatively low, which may represent areas with relatively easy traffic or less developed areas.

[0102] The statistics of the proportion of intra-provincial traffic (i.e., regional traffic) of the highway sections in the 9 clusters are as Figure 9 shown, Figure 9 where the horizontal axis represents the value of the proportion of intra-provincial traffic, and the vertical axis represents the frequency. Figure 9 a represents the statistics of the proportion of intra-provincial traffic of the 1st cluster. Figure 9 b represents the statistics of the proportion of intra-provincial traffic of the 2nd cluster. Figure 9 c represents the statistics of the proportion of intra-provincial traffic of the 3rd cluster. Figure 9 d represents the statistics of the proportion of intra-provincial traffic of the 4th cluster. Figure 9 e represents the statistics of the proportion of intra-provincial traffic of the 5th cluster. Figure 9 f represents the statistics of the proportion of intra-provincial traffic of the 6th cluster. Figure 9 g represents the statistics of the proportion of intra-provincial traffic of the 7th cluster. Figure 9 h represents the statistics of the proportion of intra-provincial traffic of the 8th cluster. Figure 9 i represents the statistics of the proportion of intra-provincial traffic of the 9th cluster.

[0103] It can be found that the proportions of intra-provincial traffic of cluster 1, cluster 4, cluster 5, and cluster 7 are relatively high. A high proportion of intra-provincial traffic may indicate that the traffic flow in these cluster areas is mainly composed of vehicles from within the province, reflecting strong intra-provincial traffic connections and mobility. These areas may be intra-provincial transportation hubs, economic centers, or densely populated areas. The proportions of intra-provincial traffic of cluster 2 and cluster 8 are at medium levels, which indicates that in the traffic flow of these areas, vehicles from within and outside the province each account for a certain proportion, and there may be both strong intra-provincial traffic connections and certain extra-provincial traffic flows. These areas may be transportation arteries connecting the province with the outside world or have certain economic attractiveness. The proportions of intra-provincial traffic of cluster 3, cluster 6, and cluster 9 are relatively low. A low proportion of intra-provincial traffic may mean that in the traffic flow of these areas, the proportion of vehicles from outside the province is relatively large, reflecting strong extra-provincial traffic connections. Especially for cluster � and cluster 6, their proportions of intra-provincial traffic are much lower than those of other clusters, which may indicate that these areas are the main channels or destinations for vehicles from other provinces to enter the province, with strong cross-provincial traffic mobility. Although the proportion of intra-provincial traffic of cluster 9 is also low, there is still a certain proportion of intra-provincial traffic compared with cluster 3 and cluster 6.

[0104] From the perspective of the differences in the proportion of provincial transportation, the 9 clusters can be divided into three different proportion ranges: high, medium, and low. The high-proportion clusters may represent transportation hubs, economic centers, or densely populated areas within the province; the medium-proportion clusters may have both strong intra-provincial transportation connections and certain extra-provincial transportation flows; the low-proportion clusters may have strong extra-provincial transportation connections and are the main channels or destinations for vehicles from other provinces to enter the province.

[0105] The statistics of the proportion of traffic over 500 kilometers (long-distance traffic) on the highway sections in the 9 clusters are as Figure 10 shown. Figure 10 On the horizontal axis is the value of the proportion of traffic over 500 kilometers, and on the vertical axis is the frequency. Figure 10 a represents the statistics of traffic over 500 kilometers in the 1st cluster. Figure 10 b represents the statistics of traffic over 500 kilometers in the 2nd cluster. Figure 10 c represents the statistics of traffic over 500 kilometers in the 3rd cluster. Figure 10 d represents the statistics of traffic over 500 kilometers in the 4th cluster. Figure 10 e represents the statistics of traffic over 500 kilometers in the 5th cluster. Figure 10 f represents the statistics of traffic over 500 kilometers in the 6th cluster. Figure 10 g represents the statistics of traffic over 500 kilometers in the 7th cluster. Figure 10 h represents the statistics of traffic over 500 kilometers in the 8th cluster. Figure 10 i represents the statistics of traffic over 500 kilometers in the 9th cluster.

[0106] It can be found that the proportion of traffic over 500 kilometers in clusters 3 and 6 is the highest. A high long-distance traffic proportion may indicate that a large proportion of the traffic flow in these cluster areas comes from long-distance or highway vehicles, which may reflect the role of these areas as transportation hubs or long-distance travel destinations, or their relatively close transportation connections with surrounding areas. The proportion of traffic over 500 kilometers in cluster 8 is at a medium-high level, indicating that there is also a certain amount of long-distance traffic flow in this area, and it may be a transportation node connecting different regions. The proportions of traffic over 500 kilometers in clusters 2, 4, 5, 7, and 9 are relatively low. A low long-distance traffic proportion may mean that the long-distance traffic flow in these areas is less, and the traffic is mainly concentrated in local or short-distance trips. These areas may be within the city or in the surrounding areas, and the traffic demand is mainly for daily commuting and local activities. However, the proportion of traffic over 500 kilometers in cluster 1 is relatively low, indicating that the long-distance traffic flow in this area is very small, and the traffic is mainly concentrated in local or short-distance trips. This may be related to the specific geographical location, transportation network layout, or transportation policies of this area.

[0107] From the perspective of the difference in the proportion of long-distance transportation, the 9 clusters can be divided into three different proportion ranges: high, medium, and low. High-proportion clusters may represent transportation hubs or long-distance travel destinations, medium-proportion clusters may be transportation nodes connecting different regions, and low-proportion clusters may mainly focus on local or short-distance trips. This difference in the proportion of long-distance transportation is of great reference value for understanding the traffic mobility in different regions and formulating traffic planning strategies (such as highway construction, transportation hub layout, etc.). At the same time, it should also be noted that the proportion of long-distance transportation may be affected by various factors, including geographical location, traffic network layout, economic development level, etc.

[0108] The statistical results of the truck traffic proportion on the highway sections in the 9 clusters are as Figure 11 shown. Figure 11 The horizontal axis represents the value of the truck traffic proportion, and the vertical axis represents the frequency. Figure 11 a represents the statistical results of the truck traffic proportion in the 1st cluster. Figure 11 b represents the statistical results of the truck traffic proportion in the 2nd cluster. Figure 11 c represents the statistical results of the truck traffic proportion in the 3rd cluster. Figure 11 d represents the statistical results of the truck traffic proportion in the 4th cluster. Figure 11 e represents the statistical results of the truck traffic proportion in the 5th cluster. Figure 11 f represents the statistical results of the truck traffic proportion in the 6th cluster. Figure 11 g represents the statistical results of the truck traffic proportion in the 7th cluster. Figure 11 h represents the statistical results of the truck traffic proportion in the 8th cluster. Figure 11 i represents the statistical results of the truck traffic proportion in the 9th cluster.

[0109] It can be found that the proportion of truck traffic in Cluster 3 is the highest. A high proportion of truck traffic may indicate that this clustering area is an important node for freight transportation, with a large number of trucks entering and leaving, which may be involved in industries such as logistics, warehousing, and manufacturing. The average traffic proportion in Cluster 9 is also relatively high. Although slightly lower than that in Cluster 3, it still indicates that there is a certain demand for freight transportation in this area, and it may also be one of the distribution centers for freight transportation. The proportions of truck traffic in Clusters 6 and 8 are at a medium level respectively, indicating that there is also a certain amount of freight transportation activities in these areas, but compared with Clusters 3 and 9, the proportion of truck traffic is lower. The proportions of truck traffic in Clusters 1, 2, 4, 5, and 7 are relatively low. A low proportion of truck traffic may mean that the demand for freight transportation in these areas is less, or the truck traffic is masked by other types of traffic (such as private cars, etc.). From the perspective of the difference in the proportion of truck traffic, the 9 clusters can be divided into three different proportion intervals. High-proportion clusters (such as Clusters 3 and 9) may be important nodes for freight transportation, involving multiple industries related to logistics, warehousing, manufacturing, etc. Medium-proportion clusters (such as Clusters 6 and 8) also have a certain amount of freight transportation activities, but relatively less. Low-proportion clusters (such as Clusters 1, 2, 4, 5, and 7) have less demand for freight transportation, or truck traffic is not the main type of traffic in this area.

[0110] The average vehicle speed statistics of the highway sections in the 9 clusters are as Figure 12 shown, Figure 12 where the horizontal axis represents the average speed, with the unit of kilometers per hour (km / h), and the vertical axis represents the frequency. Figure 12 a represents the average speed statistics of the 1st cluster. Figure 12 b represents the average speed statistics of the 2nd cluster. Figure 12 c represents the average speed statistics of the 3rd cluster. Figure 12 d represents the average speed statistics of the 4th cluster. Figure 12 e represents the average speed statistics of the 5th cluster. Figure 12 f represents the average speed statistics of the 6th cluster. Figure 12 g represents the average speed statistics of the 7th cluster. Figure 12 h represents the average speed statistics of the 8th cluster. Figure 12 i represents the average speed statistics of the 9th cluster.

[0111] It can be found that from the perspective of speed differences, the 9 clusters can be divided into several different speed intervals. The average speeds of Clusters 2 and 7 are the highest, indicating that the traffic conditions in these two clusters are the smoothest. The average speed of Cluster 1 is the lowest, which may be affected by traffic congestion or poor road conditions, and the other clusters are between these two extremes.

[0112] The means of the five data for 9 clusters are shown in Table 5.

[0113] Table 5

[0114]

[0115] It can be found that the road labels corresponding to each clustering category are as follows:

[0116] Category 1 is a high-flow provincial-dominated road section. Its average traffic flow is high (932.0880), indicating a large traffic flow on this category of road sections. The average provincial traffic proportion is extremely high (0.8914161), indicating that mainly provincial vehicles pass through. The average speed is moderate (66.48984 km / h), probably affected by the large traffic flow. This category of road sections may be the main high-speed channels connecting large cities or important economic regions within the province, with a large traffic flow and mainly provincial vehicles.

[0117] Category 2 is a medium-flow mixed road section. Its average traffic flow is medium (552.2524), the average provincial traffic proportion is medium (0.4012433), but the proportion of trucks is relatively high (0.2899051), and the average speed is high (97.28498 km / h), indicating good road conditions and smooth traffic flow. This category of road sections may be mixed-use roads connecting different regions or cities, with both provincial vehicles and a certain proportion of vehicles from other provinces and trucks.

[0118] Category 3 is a high-truck-proportion road section. Its average traffic flow is medium (611.7678), the average provincial traffic proportion is low (0.2056401), but the proportion of trucks is extremely high (0.6294887), and the average speed is medium (81.85080 km / h). This category of road sections may be the main channels for goods transportation, with a high proportion of trucks, and may connect industrial areas, logistics centers or ports.

[0119] Category 4 is a medium-flow provincial-dominated road section. Its average traffic flow is medium (624.5211), the average provincial traffic proportion is high (0.7357545), and the average speed is moderately high (88.65332 km / h). It is similar to Category 1, but the traffic flow and speed are slightly lower. It may be a road connecting medium-sized cities or economic regions.

[0120] Category 5 is an extremely high-flow provincial-dominated road section. Its average traffic flow is extremely high (3112.2228), far higher than other categories, and the average provincial traffic proportion is high (0.8105511), and the average speed is medium (88.01008 km / h), probably affected by the extremely large traffic flow. This category of road sections may be the main high-speed channels connecting the largest cities or economic centers within a province, with an extremely large traffic flow.

[0121] Category 6 is a mixed section of high trucks and long-distance buses. Its average traffic flow is medium (614.2532), the average proportion of provincial traffic is relatively low (0.2316328), but the proportion of trucks is relatively high (0.3238583), and the proportion of long-distance buses may be relatively high. The average speed is medium to high (89.12245 km / h). This category of section may be a mixed-use road connecting different provinces or long-distance regions within the province, with both trucks and long-distance buses.

[0122] Category 7 is a high-flow highway section. Its average traffic flow is high (982.0054), the average proportion of provincial traffic is extremely high (0.8302548), the average speed is high (101.08568 km / h), which is the fastest among all categories. This category of section may be a highway connecting large cities or economic regions, with a large traffic flow and high speed, and excellent road conditions.

[0123] Category 8 is a medium to high-flow mixed section. Its average traffic flow is medium to high (1903.0337), the average proportion of provincial traffic is medium (0.4254804), the proportion of trucks is also relatively high (0.3504164), and the average speed is medium to high (91.97421 km / h). This category of section may be a mixed-use road connecting different cities or regions, with both provincial vehicles and a certain proportion of vehicles from other provinces and trucks, and good road conditions.

[0124] Category 9 is a low-flow mixed section. Its average traffic flow is low (381.0570), the average proportion of provincial traffic is medium (0.5207122), the proportion of trucks is also relatively high (0.4974762), and the average speed is medium (83.34337 km / h). This category of section may be a road connecting smaller cities or rural areas, with a low traffic flow but a relatively high proportion of trucks, and may be used for freight transportation or local traffic.

[0125] The clustering results of highway sections during the late night to early morning period are as [[ID=;14]] Figure 13 shown. The numbers in the figure represent the cluster numbers of the clusters. Different types of lines represent highway sections belonging to different clusters, with a total of 9 clusters.

[0126] Freight labels are generated for this province, and the preset freight grades are shown in Table 6.

[0127] [[ID=;21]]Table 6

[0128]

[0129] The freight labels of this province are as Figure 14 shown. Different types of lines in the figure represent highway sections with different freight grades, with a total of five grades.

[0130] It can be seen that the method of the present application can intuitively display the freight tags and section tags of highway sections, effectively improving the intuitiveness and comprehensiveness of highway section tags.

[0131] Next, an exemplary description of the highway section tag generation device provided by the present application will be given.

[0132] As Figure 15 shown, an embodiment of the present application provides a highway section tag generation device. The highway section tag generation device 1500 includes:

[0133] An acquisition module 1501, which acquires the highway gantry passing data of the target area; the highway gantry passing data includes the time when each vehicle passing through the gantry in the target area passes through the gantry and the entrance toll station and exit toll station through which the vehicle passes. The multiple vehicles passing through the gantry in the target area include vehicles of various different vehicle types;

[0134] A statistics module 1502, which performs statistics based on the highway gantry passing data to obtain the in-region traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of each highway section in the target area;

[0135] A clustering module 1503, which clusters all highway sections based on the in-region traffic ratio, long-distance traffic ratio, traffic flow in the historical time period, truck traffic ratio, and average vehicle speed of all highway sections to obtain multiple clustering clusters;

[0136] A calculation module 1504, which calculates the freight function value of each highway section according to the traffic flow of the highway section in the historical time period and all vehicle types; the freight function value is used to describe the truck passing efficiency of the highway section;

[0137] A tag generation module 1505, which generates freight tags for each highway section according to all freight function values, and generates section tags for each highway section according to all clustering clusters; the freight tags are used to describe the passing conditions of freight vehicles on the highway section, and the section tags are used to describe the passing conditions of vehicles of all vehicle types on the highway section.

[0138] It should be noted that for the information interaction, execution process, etc. between the above-mentioned devices / units, since they are based on the same concept as the method embodiment of the present application, their specific functions and the technical effects brought can be specifically referred to in the method embodiment part, and will not be elaborated here.

[0139] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated herein.

[0140] As Figure 16 shown, an embodiment of the present application provides a terminal device. The terminal device D10 in this embodiment includes: at least one processor D100 ( Figure 16 only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100. When the processor D100 executes the computer program D102, the steps in any of the foregoing method embodiments are implemented.

[0141] Specifically, when the processor D100 executes the computer program D102, by generating a section label for a highway section based on the traffic proportion within the area, the long-distance traffic proportion, the traffic flow, the truck traffic proportion, and the average vehicle speed, the information richness and accuracy of label generation can be improved. Generating a freight label for the highway section can describe the passing conditions of freight vehicles on the highway section. Combining the section label, label generation for the highway section can be realized from both the freight and overall aspects, effectively improving the comprehensiveness and accuracy of label generation for the highway section.

[0142] The so-called processor D100 may be a central processing unit (CPU, Central Processing Unit), and this processor D100 may also be other general-purpose processors, digital signal processors (DSP, Digital Signal Processor), application-specific integrated circuits (ASIC, Application Specific Integrated Circuit), field-programmable gate arrays (FPGA, Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0143] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as the hard disk or memory of the terminal device D10. In some other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk equipped on the terminal device D10, a smart media card (SMC, SmartMedia Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), etc. Further, the memory D101 may also include both the internal storage unit and the external storage device of the terminal device D10. The memory D101 is used to store an operating system, application programs, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory D101 may also be used to temporarily store the data that has been output or will be output.

[0144] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above various method embodiments can be implemented.

[0145] The embodiments of the present application provide a computer program product. When the computer program product runs on a terminal device, the terminal device can be made to execute the steps in the above various method embodiments.

[0146] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the high-speed section label generation method device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, USB flash drive, mobile hard disk, magnetic disk or optical disc, etc.

[0147] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0148] The above is the preferred implementation manner of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle described in this application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A method for generating a highway section label, characterized in that: include: Obtaining highway gantry traffic data for a target area; the highway gantry traffic data includes the time at which each vehicle passing through the gantry in the target area passes through the gantry, as well as the entrance and exit toll stations passed by the vehicle within a historical time period, wherein the multiple vehicles passing through the gantries in the target area include vehicles of multiple different types; Based on the highway gantry traffic data, statistics are performed to obtain the regional traffic ratio, long-distance traffic ratio, traffic flow in a historical time period, truck traffic ratio, and average vehicle speed of each highway section in the target area; All highway sections are clustered based on their regional traffic ratio, long-distance traffic ratio, traffic volume in historical time periods, truck traffic ratio, and average vehicle speed to obtain multiple clusters. For each of the expressway sections, the freight function value of the expressway section is calculated based on the traffic flow and all vehicle types of the expressway section in a historical time period; the freight function value is used to describe the truck traffic efficiency of the expressway section; Generating freight labels based on all freight function values to obtain freight labels for each of the expressway sections, and generating section labels based on all clusters to obtain section labels for each of the expressway sections; the freight labels are used to describe the traffic conditions of freight vehicles on the expressway section, and the section labels are used to describe the traffic conditions of all types of vehicles on the expressway section; The method clusters all highway sections based on their intra-regional traffic ratio, long-distance traffic ratio, traffic flow in historical time periods, truck traffic ratio, and average vehicle speed, to obtain multiple clusters, including: Combining the regional traffic ratio, long-distance traffic ratio, traffic volume in a historical time period, truck traffic ratio, and average vehicle speed of each highway section into one data point; Clustering algorithms are used to cluster all data points to obtain multiple clusters; Calculating the freight function value of the expressway section based on the traffic flow and all vehicle types of the expressway section in a historical time period includes: By formula: ； Calculating freight function value ; in, Indicates the number of vehicles passing through the expressway section. The proportion of trucks Indicates the The total number of axles of the truck, Indicates the number of truck types. Indicates the traffic flow of the expressway section in the historical time period, Indicates the average vehicle speed on the expressway section.

2. The method for generating a highway section label according to claim 1, wherein: The statistics based on the highway gantry traffic data are used to obtain the regional traffic ratio, long-distance traffic ratio, traffic flow in a historical time period, truck traffic ratio, and average vehicle speed of each highway section in the target area, including: For each vehicle in all highway gantry traffic data, all gantries the vehicle passed through, the time it passed through the gantry, and the exit and entrance toll stations it passed through are obtained from all highway gantry traffic data. All gantries the vehicle passed through, the time it passed through the gantry, and the exit and entrance toll stations it passed through are integrated to obtain the vehicle's trajectory. If the entrance and exit toll stations passed by the vehicle are both gantries within the target area, the vehicle is considered an in-area vehicle. If the vehicle's trajectory length is greater than a length threshold, the vehicle is considered a long-distance vehicle. Calculating the regional traffic ratio of each highway section in the target area based on the trajectories of all vehicles and all vehicles in the area; Calculating the proportion of long-distance traffic on each highway section in the target area based on the trajectories of all vehicles and all long-distance vehicles; Calculating the traffic flow of each highway section in the target area during a historical time period based on the trajectories of all vehicles; Calculating the truck traffic proportion on each highway section in the target area based on all vehicle trajectories and all vehicle types; The average vehicle speed of each highway section in the target area is calculated based on the trajectories of all vehicles.

3. The method for generating a highway section label according to claim 2, wherein: The calculating of the intra-regional traffic ratio of each highway section in the target area based on the trajectories of all vehicles and all vehicles in the area includes: For each of the expressway sections, the total number of vehicles passing through the expressway section is counted based on the trajectories of all vehicles, the number of vehicles in the area passing through the expressway section is counted based on the trajectories of vehicles in all areas, and the ratio between the total number of vehicles passing through the expressway section and the number of vehicles in the area passing through the expressway section is calculated to obtain a traffic ratio within the area; The calculation of the long-distance traffic ratio of each highway section in the target area based on the trajectories of all vehicles and all long-distance vehicles includes: For each of the expressway sections, the number of long-distance vehicles passing through the expressway section is counted based on the trajectories of all long-distance vehicles, and the ratio between the total number of vehicles passing through the expressway section and the number of long-distance vehicles passing through the expressway section is calculated to obtain the long-distance traffic ratio of the expressway section.

4. The method for generating a highway section label according to claim 3, wherein: The calculating of the traffic flow of each highway section in the target area in a historical time period based on the trajectories of all vehicles includes: For each of the expressway sections, the total number of vehicles passing through the expressway section is used as the traffic flow of the expressway section in the historical time period.

5. The method for generating a highway section label according to claim 4, characterized in that: Said vehicle types include various trucks; The calculating of the truck traffic ratio of each highway section in the target area based on the trajectories of all vehicles and all vehicle types includes: For each expressway section, the number of trucks passing through the expressway section is counted based on the trajectories of all truck vehicles, and the ratio between the number of trucks passing through the expressway section and the total number of vehicles passing through the expressway section is calculated to obtain the truck traffic ratio; The calculating the average vehicle speed of each highway section in the target area based on the trajectories of all vehicles includes: For each of the expressway sections, perform the following steps: The vehicle passing through the highway section in each trajectory is regarded as a target vehicle; For each target vehicle, calculate the time it takes for the target vehicle to pass through adjacent gantries in the highway section, and calculate the ratio between the length of the adjacent gantries in the highway section and the time to obtain the speed of the target vehicle in the adjacent gantries in the highway section; If the speed of the target vehicle between adjacent gantries on the expressway section is within a preset speed threshold range, the vehicle's journey between adjacent gantries on the expressway section is regarded as a normal journey without stopping, and the average driving speed of all target vehicles whose journey between adjacent gantries on the corresponding expressway section is a normal journey is calculated to obtain the average vehicle speed of the expressway section.

6. A device for generating labels for highway sections, characterized in that: include: Acquisition module, to obtain highway gantry traffic data in the target area; The highway gantry traffic data includes the time when each vehicle passing through the gantry in the target area passes through the gantry and the entrance toll station and exit toll station passed by the vehicle within a historical time period, and the multiple vehicles passing through the gantry in the target area include vehicles of multiple different types; A statistics module, based on the highway gantry traffic data, obtains the regional traffic ratio, long-distance traffic ratio, traffic flow in a historical time period, truck traffic ratio, and average vehicle speed of each highway section in the target area; The clustering module clusters all highway sections into multiple clusters based on their regional traffic ratio, long-distance traffic ratio, traffic volume in historical time periods, truck traffic ratio, and average vehicle speed. a calculation module for calculating, for each of the expressway sections, a freight function value of the expressway section based on the traffic flow and all vehicle types of the expressway section in a historical time period; the freight function value is used to describe the truck traffic efficiency of the expressway section; a label generation module, generating a freight label based on all freight function values to obtain a freight label for each expressway section, and generating a section label based on all clusters to obtain a section label for each expressway section; the freight label is used to describe the traffic conditions of freight vehicles on the expressway section, and the section label is used to describe the traffic conditions of all types of vehicles on the expressway section; The clustering module is specifically used to implement: Combining the regional traffic ratio, long-distance traffic ratio, traffic volume in a historical time period, truck traffic ratio, and average vehicle speed of each highway section into one data point; Clustering algorithms are used to cluster all data points to obtain multiple clusters; The calculation module is specifically used to implement: By formula: ； Calculating freight function value ; in, Indicates the number of vehicles passing through the expressway section. The proportion of trucks Indicates the The total number of axles of the truck, Indicates the number of truck types. Indicates the traffic flow of the expressway section in the historical time period, Indicates the average vehicle speed on the expressway section.

7. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for generating a highway section label according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for generating a highway section label according to any one of claims 1 to 5 is implemented.

Images