Method and device for evaluating highway service level based on toll data

Abstract

This application belongs to the field of computer science and specifically relates to a method and apparatus for evaluating highway service levels based on toll data. The method comprises: obtaining toll data for a target section of a highway to be evaluated; cleaning the toll data to extract valid data; obtaining traffic parameters for each valid data; calculating, using a set time period as a time granularity, a travel time reliability index and a driving comfort index for each set time period in the upstream and downstream directions based on the traffic parameters, and plotting the results as a scatter plot; and performing cluster analysis on the travel time reliability index and driving comfort index for each set time period in the upstream and downstream directions using fuzzy C-means clustering, with the clustering results serving as the basis for categorizing different types of service levels. This method can accurately evaluate highway service levels based on toll data.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for evaluating the service level of a highway based on toll data. Background Art

[0002] With the increase in expressway mileage and the growth in car ownership, the complexity of expressway vehicle operations has increased, and some expressways have gradually begun to experience traffic congestion. Alleviating traffic congestion and improving expressway operational efficiency can be achieved by regulating traffic demand and optimizing traffic supply. Traffic demand management, however, presupposes an understanding of traffic resource utilization—that is, the travel characteristics of expressway travelers. Furthermore, service level (LSI) reflects the relationship between traffic demand and traffic supply and serves as a qualitative assessment of service quality. Therefore, service level evaluation is crucial in operational management. Summary of the Invention

[0003] The embodiments of the present application provide a method and device for evaluating the service level of a highway based on toll data, which can accurately evaluate the service level of a highway based on toll data.

[0004] In a first aspect, an embodiment of the present application provides a method for evaluating the service level of a highway based on toll data, comprising:

[0005] Obtain toll data for the target section of the highway to be evaluated;

[0006] Cleaning the charging data to extract valid data;

[0007] Obtaining traffic parameters of each of the valid data;

[0008] Taking a set time period as the time granularity, calculate the travel time reliability index and the driving comfort index for each set time period in the upbound direction and the downbound direction respectively according to the traffic parameters, and plot the results into a scatter plot;

[0009] Fuzzy C-means clustering is used to perform cluster analysis on the travel time reliability index and driving comfort index of each set time period for both uplink and downlink. The clustering results are used as the basis for dividing different types of service levels.

[0010] In a second aspect, an embodiment of the present application provides a highway service level evaluation device based on toll data, comprising:

[0011] An acquisition module is used to obtain toll data of a target section of the expressway to be evaluated;

[0012] A cleaning module, used for cleaning the charging data to extract valid data;

[0013] An analysis module is configured to obtain traffic parameters for each valid data; calculate the travel time reliability index and the driving comfort index for each set time period in the uplink and downlink directions based on the traffic parameters, using a set time period as a time granularity, and plot the results into a scatter plot; and perform cluster analysis on the travel time reliability index and the driving comfort index for each set time period in the uplink and downlink directions using fuzzy C-means clustering, with the clustering results serving as the basis for categorizing different types of service levels.

[0014] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements any of the methods described above when executed by a processor.

[0015] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described methods when executing the computer program. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A schematic diagram showing a flow chart of a method for evaluating a highway service level based on toll data according to an embodiment of the present application;

[0018] Figure 2 A schematic diagram showing the reliability of hourly travel time in two directions obtained by the highway service level evaluation method based on toll data in an embodiment of the present application;

[0019] Figure 3 A schematic diagram showing the hourly driving comfort in two directions obtained by the highway service level evaluation method based on toll data according to an embodiment of the present application;

[0020] Figure 4 A scatter plot showing the travel time reliability index and the driving comfort index obtained by the highway service level evaluation method based on toll data in an embodiment of the present application;

[0021] Figure 5 A graph showing the relationship between the sum of squared errors and the number of clusters in the highway service level evaluation method based on toll data according to an embodiment of the present application is shown;

[0022] Figure 6A graph showing the relationship between the silhouette coefficient and the number of clusters in the highway service level evaluation method based on toll data according to an embodiment of the present application is shown;

[0023] Figure 7 A schematic diagram showing a clustering structure of a highway service level evaluation method based on toll data according to an embodiment of the present application is shown;

[0024] Figure 8 A box plot showing travel time reliability indicators for various service levels obtained by the highway service level evaluation method based on toll data according to an embodiment of the present application;

[0025] Figure 9 A box plot showing driving comfort indicators for various service levels obtained by the highway service level evaluation method based on toll data according to an embodiment of the present application;

[0026] Figure 10 A schematic diagram showing the classification accuracy of a classification and regression tree using a confusion matrix in a method for evaluating a highway service level based on toll data according to an embodiment of the present application;

[0027] Figure 11 A schematic diagram showing a decision tree for generating five types of service levels using a classification regression tree in a highway service level evaluation method based on toll data according to an embodiment of the present application;

[0028] Figure 12 A schematic diagram showing the structure of a highway service level evaluation device based on toll data according to an embodiment of the present application;

[0029] Figure 13 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0032] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0033] See also Figure 1 , an embodiment of the present application provides a highway service level evaluation method based on toll data, comprising:

[0034] Obtain toll data for the target section of the highway to be evaluated;

[0035] Clean the charging data to extract valid data;

[0036] Obtain traffic parameters of each valid data;

[0037] Taking the set time period as the time granularity, the travel time reliability index and driving comfort index of each set time period in the up and down directions are calculated according to the traffic parameters, and the results are plotted as a scatter plot;

[0038] Fuzzy C-means clustering is used to perform cluster analysis on the travel time reliability index and driving comfort index of each set time period for both uplink and downlink. The clustering results are used as the basis for dividing different types of service levels.

[0039] The method of the embodiment of the present application is based on traffic parameters such as vehicle travel time and interval speed. From the perspective of user needs, two evaluation indicators, travel time reliability and driving comfort, are designed to evaluate the service level of highways. Cluster analysis is used to classify the service levels, thereby accurately evaluating the service level of highways.

[0040] The toll collection data for the target highway section in this application can be obtained from the toll collection system of the highway operation and management department. Valid toll collection data generally includes relevant information such as the time when the vehicle enters and exits the highway, the name of the toll station, the vehicle model, and traffic parameters such as the vehicle's origin and destination (OD).

[0041] To eliminate the impact of noisy data, data cleaning is necessary to remove invalid data and retain only valid data. Typical data cleaning involves removing incomplete data at the start and end points to retain valid data. However, for toll collection data on target highway sections, many factors can lead to missing information about entry and exit points. Using the lack of entry and exit information as a criterion for invalid data can lead to the mistaken deletion of valid data, causing bias in subsequent clustering. For example, highways run through multiple provinces and interconnect with other highways. Therefore, when studying highway data within a specific province, vehicles may exit or enter the target highway section through the highway interchange, resulting in missing entry and / or exit information. Deleting this toll collection data will result in missing data for this type of trip.

[0042] In the embodiment of the present application, data cleaning is performed by extracting valid data to avoid mistakenly deleting valid data by judging the missing toll station information of the starting and ending points as erroneous data.

[0043] In some embodiments, cleaning the charging data to extract valid data includes:

[0044] (1) Record the toll collection data with complete entry and exit times as valid data. The entry and exit times are the time of entering and exiting the toll station;

[0045] (2) At least one of the entry and exit times of the toll data is missing. If the exit node and / or entry node can be determined based on the toll data from the toll gantry, the toll data will be recorded as valid data. The exit node and entry node are the nodes entering or exiting the target section outside the toll station in the target section.

[0046] According to the above two situations, the valid data is determined respectively, and the valid data is retained. Other charging data other than the valid data is deleted as abnormal data to achieve the purpose of accurate data cleaning.

[0047] In the embodiments of the present application, the exit node and the entry node are nodes in the target section that enter or exit the target section outside of a toll station. Nodes that enter or exit the target section outside of a toll station include highway interchange nodes and provincial boundary nodes in the target section. For example, a vehicle may enter or exit the target section from a highway interchange node, thereby preventing the toll station in the target section from recording the corresponding information. Alternatively, a vehicle may enter or exit the target section from a provincial boundary node, thereby preventing the toll station in the target section from recording the corresponding information.

[0048] For example, if a vehicle enters the Beijing section of the expressway from Tianjin, the toll collection data for the Beijing section will be missing information about the vehicle entering the toll booth. If the vehicle then exits the expressway at an interchange after entering the Beijing section, the toll collection data for the Beijing section will also be missing information about the vehicle exiting the toll booth.

[0049] Alternatively, if a vehicle leaves the Beijing section of the highway and enters Tianjin, the toll collection data for the Beijing section of the highway will be missing information about the vehicle exiting the toll station. If the vehicle enters the highway from an interchange, the toll collection data for the Beijing section of the highway will also be missing information about the vehicle entering the toll station.

[0050] There are also toll gantries on the highway. In order to facilitate non-stop billing, toll gantries are set up near nodes such as highway interchanges and provincial borders. For valid data, the vehicle's entry node or exit node can be determined based on the toll information of the toll gantries. Therefore, if the exit node and / or entry node can be determined based on the toll data of the toll gantries, then the toll data is valid data.

[0051] In some embodiments, at least one of the entry and exit times of the toll data is missing. If the exit node and / or entry node can be determined based on the toll data of the toll gantry, the toll data will be recorded as valid data, including: the toll data has the time of entering the toll station. When the time of exiting the toll station is missing, if the last gantry in the toll data is the gantry closest to the highway interchange node or provincial boundary node in front, then the highway interchange node or provincial boundary node closest to the last gantry is the exit node of the toll data, and the toll data is valid data. The toll data with missing entry and exit times includes at least one gantry information, that is, the vehicle passes through at least one gantry in the target section and is recorded by the gantry. After the vehicle enters the target section from the toll station, if it exits the target section from the highway interchange node or provincial boundary node, the highway interchange node or provincial boundary node that the vehicle exits will be recorded by the gantry, and the last gantry in the toll data of the vehicle is the gantry closest to the highway interchange node or provincial boundary node to exit.

[0052] In some embodiments, when the toll data has the time of entering the toll station but lacks the time of exiting the toll station, if there are other gantries between the last gantry in the toll data and the nearest highway interchange node or provincial boundary node in front, the toll data is abnormal data.

[0053] In this application, the front refers to the direction of the front of the vehicle, and the rear refers to the direction of the rear of the vehicle.

[0054] In some embodiments, at least one of the entry and exit times of the toll data is missing. If the exit node and / or entry node can be determined based on the toll data of the toll gantry, the toll data will be recorded as valid data, including: when the toll data has the time of exiting the toll station and the time of entering the toll station is missing, if the first gantry in the toll data is the gantry closest to the highway interchange node or provincial boundary node behind it, then the highway interchange node or provincial boundary node closest to the first gantry is the entry node of the toll data, and the toll data is valid data. The toll data with missing entry and exit times includes at least one gantry information, that is, the vehicle passes through at least one gantry in the target section and is recorded by the gantry. After the vehicle enters the target section from the highway interchange node or provincial boundary node, the vehicle will be recorded by the gantry, and the first gantry in the toll data of the vehicle is the gantry closest to the highway interchange node or provincial boundary node after entering the target section.

[0055] In some embodiments, when toll collection data includes the time of exiting a toll station but lacks the time of entering a toll station, if there are other gantries between the first gantry in the toll collection data and the nearest highway interchange or provincial boundary node behind, the toll collection data is considered abnormal. Alternatively, if there are other gantries between the last gantry in the toll collection data and the nearest highway interchange or provincial boundary node ahead, the toll collection data is considered abnormal.

[0056] In some embodiments, if at least one of the entry and exit times in the toll data is missing, and if the exit node and / or entry node can be determined based on the toll data from the toll gantry, the toll data will be recorded as valid data, including: when the toll data is missing the time of exiting the toll station and the time of entering the toll station, if the toll data only includes one gantry, and the gantry is the only gantry between two adjacent nodes, and the nodes include highway interchange nodes and provincial boundary nodes, then the adjacent nodes on both sides of the gantry are the entry node and exit node of the toll data, and the toll data is valid; otherwise, the toll data is abnormal data. The target road section is generally equipped with multiple gantries. If the toll data of the target road section only includes one gantry for a vehicle, and the gantry is the only gantry between two adjacent nodes, it can be considered that the vehicle entered from one of the two adjacent nodes and exited from the other. For example, there is only the first gantry between the provincial boundary node and the first highway interchange node. If the vehicle's charging data only includes the first gantry, that is, it is only recorded by the first gantry, and not recorded by other gantries on the target section, such as the second gantry, the third gantry, etc., then it can be considered that the vehicle enters the target section from one of the provincial boundary node and the first highway interchange node, and exits the target section from the other. The vehicle's driving direction can be determined based on the gantry's charging data, so the entry node and exit node can be determined. For example, if the charging data of the first gantry determines that the vehicle enters the target section from the provincial boundary, then the vehicle enters from the provincial boundary node and exits from the first highway interchange node. Conversely, the vehicle enters the target section from the provincial boundary node and exits from the first highway node.

[0057] In some embodiments, when the toll data lacks the time of exiting and entering a toll station, if the toll data includes at least two gantries, and the first gantry in the toll data is the gantry closest to the subsequent highway interchange or provincial boundary node, and the last gantry in the toll data is the gantry closest to the preceding highway interchange or provincial boundary node, then the nearest highway interchange or provincial boundary node behind the first gantry is the entry node of the toll data, and the nearest highway interchange or provincial boundary node in front of the last gantry is the exit node of the toll data, and the toll data is valid; otherwise, the toll data is abnormal. The target road section generally has multiple gantries. When the toll data of a vehicle on the target road section includes at least two gantries, if the first gantry in the toll data is the gantry closest to the subsequent highway interchange or provincial boundary node, it can be assumed that the vehicle entered from the highway interchange or provincial boundary node behind the first gantry. This node can be used as the vehicle's starting point on the target road section. After the vehicle enters from this node, it is recorded by the first gantry. If the last gantry in the toll data is the gantry closest to the highway interchange node or provincial boundary node in front, it can be considered that the vehicle exited from the highway interchange node or provincial boundary node in front of the last gantry, and this node can be used as the end point of the vehicle in the target section.

[0058] For example, if there is a first gantry and a second gantry between the provincial boundary node and the first highway interchange node, with the first gantry closer to the provincial boundary node and the second gantry closer to the first highway interchange node, and if the first gantry in the vehicle's toll collection data is the first gantry and the last gantry is the second gantry, then it can be assumed that the vehicle entered the target section from the provincial boundary node and exited the target section from the first highway interchange node. If the first gantry in the vehicle's toll collection data is the second gantry and the last gantry is the first gantry, then it can be assumed that the vehicle entered the target section from the first highway interchange node and exited the target section from the provincial boundary node.

[0059] In some embodiments, the method of the present invention further includes determining the starting and ending points of each valid data. The valid data can determine the nodes where the vehicle enters or exits the target road section, thereby determining the starting and ending points of the vehicle on the target road section.

[0060] The starting and ending points of toll collection data with complete entry and exit times are the toll stations for entering and exiting the target road section, respectively. If the toll collection data includes toll stations for both entering and exiting the target road section, the starting point is the toll station for entering the target road section, and the ending point is the toll station for exiting the target road section.

[0061] Valid data with toll station entry times but missing toll station exit times starts at the toll station that entered the target road section, and ends at the exit node immediately preceding the last gantry in the valid data. For data missing from a toll station exit, the node at which the vehicle exited the target road section can be determined based on the gantry. This node is the end point of the vehicle's journey on the target road section. The exit node can be a highway interchange or a provincial boundary.

[0062] For valid data with toll station exit times but missing toll station entry times, the starting point is the nearest entry node behind the first gantry in the valid data, and the end point is the toll station exiting the target road section. For valid data missing from a toll station entry, the node at which the vehicle entered the target road section can be determined based on the gantry. This node is the starting point of the vehicle's journey on the target road section. The node entered by the vehicle can be a highway interchange or a provincial boundary node.

[0063] For valid data with missing entry and exit times, if the data includes at least two gantries, the starting point is the nearest entry node behind the first gantry, and the end point is the nearest exit node in front of the last gantry. For valid data missing for both entry and exit toll stations, the node at which the vehicle enters the target section can be determined based on the first gantry in the valid data. This node is the starting point of the vehicle's journey on the target section. The node at which the vehicle exits the target section can be determined based on the last gantry in the valid data. This node is the end point of the vehicle's journey on the target section. The vehicle's entry and exit nodes can be highway interchange nodes or provincial boundary nodes.

[0064] For valid data with missing entry and exit times, if only one gantry is included, the starting point is the nearest entry node behind the gantry, and the end point is the nearest exit node in front of the gantry. For valid data with missing entry and exit times for a toll station, the nodes at which the vehicle enters and exits the target road section can be determined based on the unique gantry, serving as the starting and end points of the vehicle's journey on the target road section, respectively. The entry node can be a highway interchange or a provincial boundary.

[0065] For valid data missing from entry and exit times, the time a vehicle enters and / or leaves the target road section can be determined based on the time information in the toll collection data recorded by the corresponding gantry. For example, the time recorded by the corresponding gantry can be directly used as the time the vehicle enters and / or leaves the target road section. Alternatively, the time from the gantry to the entry or exit node can be calculated based on the distance from the gantry to the entry or exit node and the vehicle's speed. The calculated time can then be subtracted from or added to the time recorded by the corresponding gantry to determine the entry or exit time.

[0066] In some embodiments, the travel time reliability index is calculated using the following formula (1):

[0067] R(t)=P{t<(t median +θ*t median )} (1)

[0068] Among them, R(t) is the travel time reliability index, t median is the median of the vehicle travel time on the road section within a specific time period, and θ is a reliability threshold parameter; θ is generally set to 5%, 10%, 15% or 20%, etc. In the embodiment of the present application, θ=20% is taken as an example.

[0069] The travel time reliability index ranges from 0 to 1. The closer it is to 1, the higher the travel time reliability. When the value is 1, it means that all vehicles can complete the trip within the acceptable travel time threshold.

[0070] Travel time reliability is one of the important indicators for evaluating the operating efficiency and travel quality of the transportation system. It reflects the probability that travelers can complete their trip from the starting point to the destination within an acceptable travel time threshold.

[0071] In some embodiments, the travel time reliability index of each set time period in the uplink direction and the downlink direction is calculated based on the traffic parameters, including: dividing the target road section into a plurality of sections according to the toll gantries, and calculating the travel time reliability index of each section according to formula (1); calculating the travel time reliability index of the target road section according to the following formula (2):

[0072]

[0073] Among them, R represents the travel time reliability index of the target road section, R i represents the travel time reliability index of the i-th interval, and n is the number of intervals on the target section.

[0074] The toll gates on the target road section divide the target road section into several sections. The travel time reliability of each section can be calculated using formula (1). The travel time reliability of the entire target road section can be calculated using formula (2). The following is a schematic diagram of the travel time reliability of the entire road section in each period.

[0075] In the embodiment of the present application, the method of the present application is described by taking the Beijing section of a certain highway as the target section as an example.

[0076] The reliability of travel time in both the up and down directions of the target road section is analyzed with the hourly granularity. The reliability of travel time in both directions per hour is as follows: Figure 2 As shown in the figure, travel time reliability in both directions during the night (00:00-6:00) is close to 1, meaning all travelers can complete their trips within the acceptable travel time threshold. Travel time reliability throughout the day also remains high. Overall, travel time reliability in the upward direction is slightly lower than that in the downward direction, and trip quality assurance is inferior to that in the downward direction.

[0077] In some embodiments, a driving comfort index for each set time period in the up and down directions is calculated based on traffic parameters, including: the driving comfort index is used to describe the passenger's feeling of the vehicle speed change when the vehicle passes through each section of the target road section. The larger the driving comfort index, the greater the vehicle speed fluctuation and the worse the driving comfort; the smaller the driving comfort index, the smaller the vehicle speed fluctuation and the better the driving comfort. The driving comfort index is calculated by the following formula (3):

[0078]

[0079] Among them, C v is the driving comfort index of the target road section, vi represents the spatial average speed of the i-th interval in a specific time period, It represents the mean of the spatial average vehicle speed in each interval of the target road section, and N represents the number of intervals in the target road section.

[0080] When traveling, people care not only about arriving at their destination on time but also about the overall travel experience. For example, if the travel time remains the same, large speed fluctuations result in a bumpy ride, a poor ride experience, and even motion sickness. Smaller speed fluctuations lead to a smoother ride and a better passenger experience. The ride comfort index describes how passengers experience speed fluctuations when the vehicle passes through these intervals. This index can be represented by the coefficient of variation. A larger coefficient of variation indicates greater speed fluctuations and poorer ride comfort; a smaller coefficient of variation indicates less speed fluctuations and better ride comfort.

[0081] The driving comfort of the target road section in both the up and down directions is analyzed with the hourly granularity. The driving comfort of each direction per hour is as follows: Figure 3 As shown. Downward driving comfort fluctuates little throughout the day, with nighttime comfort being higher than daytime. Upward driving comfort is worse at night than during the day, due to the higher number of large trucks entering Beijing at night. Overall, upward driving comfort fluctuates more than downward driving comfort. A key turning point is between 5:00 and 6:00 a.m.; before this point, downward driving comfort consistently outperforms upward driving. After this point, downward driving comfort is almost always inferior to upward driving comfort.

[0082] In the embodiment of the present application, the travel time reliability index and the driving comfort index of the up and down directions can be calculated every 15 minutes with a time granularity of 15 minutes, and the results can be plotted as a scatter plot, such as Figure 4 As shown in the figure, throughout the day, the travel time reliability and ride comfort in the upward direction fluctuate more than in the downward direction. Next, we apply fuzzy C-means clustering to the 15-minute travel time reliability and ride comfort indicators for both the upward and downward directions. The clustering results will serve as the basis for categorizing different service levels. Before clustering begins, we first need to determine the number of clusters.

[0083] In some embodiments, cluster analysis is performed using fuzzy C-means clustering, including determining the number of clusters. In a specific implementation, determining the number of clusters includes: using the elbow rule and / or silhouette coefficient to determine the number of clusters for clustering the travel time reliability index and the driving comfort index.

[0084] In some embodiments, the expression of the sum of squared errors and the number of clusters is shown in formula (4),

[0085]

[0086] Among them, C i represents the i-th cluster, p is C i The sample points in, k is the number of clusters, m is the number of clusters, i It is C i The mean of all samples in ;

[0087] According to the expression, a relationship graph between the sum of squared errors and the number of clusters is plotted. The relationship graph between the sum of squared errors and the number of clusters presents an elbow shape. The optimal number of clusters corresponding to the elbow is the number of clusters for clustering the travel time reliability index and the driving comfort index.

[0088] As the number of clusters gradually increases, the sample division becomes more refined, the degree of aggregation of each cluster gradually increases, and the sum of squared errors also decreases. When the number of clusters is less than the optimal number of clusters, the degree of aggregation of each cluster increases significantly as the number of clusters increases, so the decrease in the sum of squared errors will be large; and when the number of clusters is greater than the actual number of clusters, the decrease in the degree of aggregation brought about by each increase in the number of clusters will rapidly decrease, so the decrease in the sum of squared errors will decrease sharply, and finally tend to be flat as the number of clusters increases, that is, the relationship graph of the sum of squared errors and the number of clusters presents the shape of an elbow, and the optimal number of clusters is the number of clusters corresponding to the elbow, and the optimal number of clusters is used as the number of clusters in the embodiment of the present application.

[0089] In the specific implementation, the relationship between the sum of squared errors and the number of clusters is shown in the figure below: Figure 5 As shown in Figure 2, the elbow method can be used to determine that the optimal number of clusters is 5.

[0090] In some embodiments, the silhouette coefficient is used to determine the number of clusters, including: the expression of the silhouette coefficient of the sample point is as follows (5):

[0091]

[0092] Among them, S represents the silhouette coefficient, a represents the average distance between the sample point and other sample points in the same cluster, and b represents the average distance between the sample point and all sample points in the nearest cluster;

[0093] The silhouette coefficient of the cluster is the average of the silhouette coefficients of all sample points, and its value range is [-1, 1]. The closer it is to 1, the better the clustering effect. The cluster with the largest silhouette coefficient is the number of clusters for clustering the travel time reliability index and the driving comfort index.

[0094] In the specific implementation, the relationship between the silhouette coefficient and the number of clusters is shown in the figure below: Figure 6 As shown, the number of clusters corresponding to the maximum silhouette coefficient is 5. In summary, in the embodiment of the present application, the number of clusters of the fuzzy C-means clustering is set to 5.

[0095] In some embodiments, the method further includes: performing normalization processing on the travel time reliability index and the driving comfort index before clustering; the normalization processing formula is as follows:

[0096]

[0097] By normalizing them, the value ranges of the travel time reliability index and the driving comfort index used for clustering can be made the same.

[0098] In some embodiments, the clustering results are used as the basis for dividing different types of service levels, including: classifying and defining the travel time reliability and driving comfort of each service level according to the clustering results; and defining different types of service levels according to the travel time reliability definition and driving comfort definition of the same type of service level.

[0099] In the specific implementation, the number of clusters of fuzzy C-means clustering is set to 5, the fuzzy weighted index is set to 2, and the samples are clustered. The membership of some samples is shown in Table 1, and the clustering results are shown in Figure 7 As shown in Table 2, the clustering results are good. The obtained cluster centers are shown in Table 2. The largest number of samples are classified into Class 2, while the smallest number are classified into Class 4. Among them, Class 2 accounts for 36.98%, Class 4 accounts for 5.73%, Class 1 accounts for 21.88%, and Classes 3 and 5 each account for 17.71%.

[0100] Table 1 Membership degree of some samples

[0101]

[0102]

[0103] Table 2 Cluster centers and results

[0104] category Travel time reliability Driving comfort quantity Proportion Category 1 0.96 0.19 42 21.88％ Category 2 0.84 0.07 71 36.98％ Category 3 0.91 0.12 34 17.71％ Category 4 0.99 0.11 11 5.73％ Category 5 0.99 0.34 34 17.71％

[0105] In the specific implementation, the box plot of travel time reliability index of various service levels is as follows Figure 8As shown. The median travel time reliability of the 1st, 4th and 5th service levels is relatively high, greater than 0.95, which means that when traveling under the traffic conditions corresponding to these three service levels, less than 5% of vehicles cannot reach the destination within the acceptable time threshold. The median travel time of the 3rd service level is also above 0.9, but it is slightly worse than the above three reliability levels. The median travel time of the 2nd service level is less than 0.85, and the minimum value is less than 0.8, which is the worst reliability among the 5 service levels. Therefore, the travel time reliability corresponding to the 1st, 4th and 5th service levels can be defined as high reliability; the travel time reliability corresponding to the 3rd service level is defined as medium reliability; and the travel time reliability corresponding to the 2nd service level is defined as medium reliability.

[0106] The box diagram of driving comfort of various service levels is shown in the figure below. Figure 9 As shown. The driving comfort index is characterized by the coefficient of variation. The larger the value, the greater the speed fluctuation and the worse the comfort; the closer the value is to 0, the better the driving comfort. The driving comfort corresponding to the second service level is the highest, and the driving comfort corresponding to the third and fourth service levels is second, but the gap with the second level is not too large. The driving comfort corresponding to the first service level is medium, and the driving comfort corresponding to the fifth service level is the worst. The travel experience is the worst under the corresponding traffic conditions. Therefore, the driving comfort corresponding to the second, third, and fourth service levels can be defined as high driving comfort; the driving comfort corresponding to the first service level is defined as medium driving comfort; and the driving comfort corresponding to the fifth service level is defined as low driving comfort.

[0107] The service levels are divided into five categories through fuzzy C-means clustering: low reliability and high comfort, medium reliability and high comfort, high reliability and high comfort, high reliability and medium comfort, and high reliability and low comfort.

[0108] A 10-fold cross-validation test was used to test the accuracy of the service level classification by the classification and regression tree. Precision, accuracy, recall, and F1 score were used for evaluation. The formulas are defined as follows: the closer the value of each indicator is to 1, the better the classification effect.

[0109]

[0110] Here, TP indicates that a positive class is predicted as positive, FP indicates that a negative class is predicted as positive, TN indicates that a negative class is predicted as negative, and FN indicates that a positive class is predicted as negative. Table 3 shows the evaluation of the classification and regression tree for service level classification. All indicators are around 0.95, indicating that the generated classification and regression tree has high classification accuracy.

[0111] Table 3 Summary of evaluation indicators

[0112]

[0113] Use confusion matrix to show the classification accuracy of classification and regression tree, such as Figure 10 As shown in the figure, the darker the diagonal square, the lighter the other squares, the better the classification effect. Among the 39 samples in the test set, the model only misclassified two samples, indicating that the model has good classification performance.

[0114] Using travel time reliability and driving comfort as predictor variables and service level categories as corresponding variables, a classification regression tree is applied to learn the service level classification rules. To prevent overfitting, a grid search is first used to search for the optimal maximum depth of the classification regression tree, and the optimal maximum depth is 4. The classification regression tree is used to generate a five-category service level classification decision tree, as shown in the following example: Figure 11 shown.

[0115] In some embodiments, the basis for different types of service levels includes:

[0116] Driving comfort ≤ 0.1459, and travel time reliability ≤ 0.8753, the service level is low reliability and high comfort;

[0117] Driving comfort ≤ 0.1459, and 0.8753 < travel time reliability ≤ 0.8865, the service level is medium reliability and high comfort;

[0118] Driving comfort ≤ 0.1459, and 0.8865 < travel time reliability ≤ 0.945, the service level is medium reliability and high comfort;

[0119] Driving comfort ≤ 0.1392, and travel time reliability > 0.945, the service level is high reliability and high comfort;

[0120] 0.1392<Driving Comfort≤0.1459, and 0.945<Travel Time Reliability≤0.9793, the service level is high reliability and medium comfort;

[0121] 0.1392<Driving Comfort≤0.1459, and Travel Time Reliability>0.9793, the service level is high reliability and high comfort;

[0122] 0.1459<Driving Comfort≤0.2252, and Travel Time Reliability≤0.9243, the service level is medium reliability and high comfort;

[0123] 0.2252<Driving Comfort≤0.2669, and Travel Time Reliability≤0.9243, the service level is high reliability and medium comfort;

[0124] 0.1459<Driving Comfort≤0.2669, and Travel Time Reliability>0.9243, the service level is high reliability and medium comfort;

[0125] 0.2669<Driving comfort, the service level is high reliability and low comfort.

[0126] Based on these rules, different levels of service are defined based on different thresholds for travel time reliability and ride comfort. Simply calculate the reliability and ride comfort of a road's travel time over a specific time period and compare the above classification rules to determine the corresponding level of service for that road.

[0127] An embodiment of the present application provides a highway service level evaluation device based on toll data. The device of the embodiment of the present application can implement the method of the above embodiment. The above method embodiment can be used to understand the device of the embodiment of the present application, and the description part of the embodiment of the following device can also be used to understand the method of the above embodiment.

[0128] See also Figure 12 The highway service level evaluation device based on toll data of the embodiment of the present application includes an acquisition module, a cleaning module and an analysis module. The acquisition module is used to obtain the toll data of the target section of the highway to be evaluated; the cleaning module is used to clean the toll data to extract valid data; the analysis module is used to obtain the traffic parameters of each valid data; with a set time period as the time granularity, the travel time reliability index and the driving comfort index of each set time period in the uplink and downlink directions are calculated according to the traffic parameters, and the results are plotted into a scatter plot; the travel time reliability index and the driving comfort index of each set time period in the uplink and downlink directions are clustered and analyzed using fuzzy C-means clustering, and the clustering results are used as the basis for dividing different types of service levels.

[0129] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above methods when executing the computer program.

[0130] See Figure 13 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 13 As shown, the electronic device 600 may include: at least one processor 601 , at least one network interface 604 , a user interface 603 , a memory 605 , and at least one communication bus 602 .

[0131] The communication bus 602 is used to implement the connection and communication between these components.

[0132] The user interface 603 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 603 may also include a standard wired interface and a wireless interface.

[0133] The network interface 604 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0134] The processor 601 may include one or more processing cores. The processor 601 utilizes various interfaces and circuits to connect various components within the electronic device 600. It executes instructions, programs, code sets, or instruction sets stored in the memory 605, and accesses data stored in the memory 605 to perform various functions and process data within the electronic device 600. Optionally, the processor 601 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 601 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may not be integrated into the processor 601 and may be implemented as a separate chip.

[0135] Among them, the memory 605 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 605 includes a non-transitory computer-readable storage medium. The memory 605 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 605 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 605 may also be optionally at least one storage device located away from the aforementioned processor 601. As Figure 13 As shown, the memory 605 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program.

[0136] exist Figure 13 In the electronic device 600 shown, the user interface 603 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 601 can be used to call the application stored in the memory 605 and specifically perform the operations of any of the above method embodiments.

[0137] The present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above method. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a microdrive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0138] An embodiment of the present application also provides 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 part or all of the steps of any one of the methods described in the above method embodiments.

[0139] Those skilled in the art will clearly understand that the technical solution of the present application can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0140] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0141] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0143] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0145] 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 memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0146] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0147] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A highway service level evaluation method based on toll data, characterized in that: include: Obtain toll data for the target section of the highway to be evaluated; Cleaning the charging data to extract valid data; Obtaining traffic parameters of each of the valid data; Taking a set time period as the time granularity, calculate the travel time reliability index and the driving comfort index for each set time period in the upbound direction and the downbound direction respectively according to the traffic parameters, and plot the results into a scatter plot; Cluster analysis is performed on the travel time reliability index and driving comfort index of each set time period for both uplink and downlink by applying fuzzy C-means clustering. The clustering results are used as the basis for classifying different types of service levels. The travel time reliability index is calculated by the following formula (1): R(t)=P{t<(t median +θ*t median )}(1) Among them, R(t) is the travel time reliability index, t median is the median of vehicle travel time on the road segment within a specific time period, and θ is the reliability threshold parameter; The travel time reliability index has a value between 0 and 1, where the closer it is to 1, the higher the travel time reliability. When the value is 1, it means that all vehicles can complete the trip within the acceptable travel time threshold. Calculating the driving comfort index for each set time period in the upward direction and the downward direction according to the traffic parameters, including: The driving comfort index is used to describe the passenger's feeling of vehicle speed changes when the vehicle passes through each section of the target road section. The larger the driving comfort index, the greater the vehicle speed fluctuation and the worse the driving comfort; the smaller the driving comfort index, the smaller the vehicle speed fluctuation and the better the driving comfort. The driving comfort index is calculated by the following formula (3): Among them, C v is the driving comfort index of the target road section, v i represents the spatial average speed of the i-th interval in a specific time period, It represents the mean of the spatial average vehicle speed in each interval of the target road section, and N represents the number of intervals in the target road section.

2. The method according to claim 1, characterized in that Calculating the travel time reliability index for each set time period in the up direction and the down direction according to the traffic parameters, including: The target road section is divided into several sections according to the toll gantries, and the travel time reliability index of each section is calculated by formula (1); The travel time reliability index of the target road section is calculated according to the following formula (2): Among them, R represents the travel time reliability index of the target road section, R i represents the travel time reliability index of the i-th interval, and n is the number of intervals on the target section.

3. The method according to claim 1, characterized in that Cluster analysis is performed using fuzzy C-means clustering, including: The number of clusters for clustering the travel time reliability index and the driving comfort index is determined by using the elbow rule and / or silhouette coefficient; The expression of the sum of squared errors and the number of clusters is shown in formula (4). Among them, C i represents the i-th cluster, p is C i The sample points in, k is the number of clusters, m is the number of clusters, i It is C i The mean of all samples in ; A relationship graph between the sum of squared errors and the number of clusters is drawn according to the expression. The relationship graph between the sum of squared errors and the number of clusters presents an elbow shape. The optimal number of clusters corresponding to the elbow is the number of clusters for clustering the travel time reliability index and the driving comfort index. The silhouette coefficient is used to determine the number of clusters, including: The expression of the silhouette coefficient of the sample point is as follows (5): Among them, S represents the silhouette coefficient, a represents the average distance between the sample point and other sample points in the same cluster, and b represents the average distance between the sample point and all sample points in the nearest cluster; The silhouette coefficient of the cluster is the average of the silhouette coefficients of all sample points, and its value range is [-1, 1]. The closer it is to 1, the better the clustering effect. The cluster with the largest silhouette coefficient is the number of clusters for clustering the travel time reliability index and the driving comfort index.

4. The method according to claim 1, wherein include: Before clustering, the travel time reliability index and driving comfort index were normalized respectively; The normalization formula is as follows (6):

5. The method according to claim 3, characterized in that The clustering results serve as the basis for different types of service levels, including: Based on the clustering results, the travel time reliability and driving comfort of each service level are classified and defined respectively; According to the definition of travel time reliability and driving comfort of the same type of service level, different types of service levels are defined separately.

6. The method according to claim 5, characterized in that The number of clusters is 5, and the travel time reliability and driving comfort of each service level are defined as follows: The travel time reliability corresponding to category 1, category 4, and category 5 is defined as high reliability; the travel time reliability corresponding to category 3 service level is defined as medium reliability; the travel time reliability corresponding to category 2 service level is defined as medium reliability; The driving comfort corresponding to the second, third and fourth service levels is defined as high driving comfort; the driving comfort corresponding to the first service level is defined as medium driving comfort; and the driving comfort corresponding to the fifth service level is defined as low driving comfort.

7. The method according to claim 6, characterized in that The basis for different types of service levels includes: Driving comfort ≤ 0.1459, and travel time reliability ≤ 0.8753, the service level is low reliability and high comfort; Driving comfort ≤ 0.1459, and 0.8753 < travel time reliability ≤ 0.8865, the service level is medium reliability and high comfort; Driving comfort ≤ 0.1459, and 0.8865 < travel time reliability ≤ 0.945, the service level is medium reliability and high comfort; Driving comfort ≤ 0.1392, and travel time reliability > 0.945, the service level is high reliability and high comfort; 0.1392<Driving Comfort≤0.1459, and 0.945<Travel Time Reliability≤0.9793, the service level is high reliability and medium comfort; 0.1392<Driving Comfort≤0.1459, and Travel Time Reliability>0.9793, the service level is high reliability and high comfort; 0.1459<Driving Comfort≤0.2252, and Travel Time Reliability≤0.9243, the service level is medium reliability and high comfort; 0.2252<Driving Comfort≤0.2669, and Travel Time Reliability≤0.9243, the service level is high reliability and medium comfort; 0.1459<Driving Comfort≤0.2669, and Travel Time Reliability>0.9243, the service level is high reliability and medium comfort; 0.2669<Driving comfort, the service level is high reliability and low comfort.

8. A highway service level evaluation device based on toll data, characterized in that: include: An acquisition module is used to obtain toll data of a target section of the expressway to be evaluated; A cleaning module, used for cleaning the charging data to extract valid data; An analysis module, configured to obtain traffic parameters of each of the valid data; Taking the set time period as the time granularity, the travel time reliability index and the driving comfort index of each set time period in the up and down directions are calculated according to the traffic parameters, and the results are plotted as a scatter plot; the travel time reliability index and the driving comfort index of each set time period in the up and down directions are clustered and analyzed using fuzzy C-means clustering, and the clustering results are used as the basis for the classification of different types of service levels; the travel time reliability index is calculated by the following formula (1): R(t)=P{t<(t median +θ*t median )}(1) Among them, R(t) is the travel time reliability index, t median is the median of vehicle travel time on the road segment within a specific time period, and θ is the reliability threshold parameter; The travel time reliability index has a value between 0 and 1, where the closer it is to 1, the higher the travel time reliability. When the value is 1, it means that all vehicles can complete the trip within the acceptable travel time threshold. The driving comfort index is used to describe the passenger's feeling of vehicle speed changes when the vehicle passes through each section of the target road section. The larger the driving comfort index, the greater the vehicle speed fluctuation and the worse the driving comfort; the smaller the driving comfort index, the smaller the vehicle speed fluctuation and the better the driving comfort. The driving comfort index is calculated by the following formula (3): Among them, C v is the driving comfort index of the target road section, v i represents the spatial average speed of the i-th interval in a specific time period, It represents the mean of the spatial average vehicle speed in each interval of the target road section, and N represents the number of intervals in the target road section.

Images