Public transportation network key road section identification method, electronic equipment and storage medium

Abstract

The invention discloses a public transportation network key road section identification method, an electronic device and a storage medium, and the method comprises the steps: extracting the moving trajectory of each public transportation line based on the GPS data of public transportation vehicles in a research range; acquiring an urban road network in a research range, and constructing a map matching algorithm based on a hidden Markov model; the constructed map matching algorithm is used for matching the bus running track of each line with the actual road network, and the route bus route information of each road section in the road network is obtained; and according to the extracted route bus route information, lane information, surrounding population and POI information of each road section and the departure frequency of each bus route, calculating a key index of each road section in the road network, and identifying a key road section in the bus network. According to the method, time-space fusion of the public transportation network and the urban road network is considered, the key road sections in the public transportation network are accurately identified from the road network level, and decision support is provided for network planning, station layout and transport capacity configuration of the public transportation.

Description

Technical Field

[0001] The present invention relates to a method for identifying key sections of a bus network, an electronic device, and a storage medium, belonging to the technical field of traffic control systems for road vehicles. Background Art

[0002] The density of bus lines on some sections of the bus network is relatively high. Once an emergency (such as natural disasters or congestion) occurs, it will have a greater impact on the normal operation of the entire bus system. The population density around some sections is relatively large, and the operation status of bus lines on these sections has an important impact on the daily travel of residents. In addition, the number of lanes on some sections is limited. Due to the fixity of bus lines, when the road on this section needs to be repaired or traffic control is implemented, it is extremely easy to cause the paralysis of the bus network. The impact of emergencies on these key sections on bus operation makes it difficult to guarantee the travel timeliness of passengers, prompting more citizens to choose private cars as travel tools, further exacerbating the congestion of urban roads.

[0003] Currently, the research on identifying key sections of the bus network mainly focuses on the station level, and relatively few studies focus on the road network level. Only a few studies use the running speed of bus vehicles on a section as the basis for identifying whether the section is a key section of the bus network, which leads to unreasonable bus network planning.

[0004] Therefore, how to identify key sections in the bus network is of crucial significance for bus network planning. Summary of the Invention

[0005] Objective: To overcome the deficiencies in the prior art, the present invention provides a method for identifying key sections of a bus network, an electronic device, and a storage medium. Considering the spatio-temporal fusion of the bus network and the urban road network, it accurately identifies key sections in the bus network from the road network level, providing decision-making support for bus network planning, station layout, and transport capacity allocation.

[0006] Technical Solution: To solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0007] In the first aspect, a method for identifying key sections of a bus network specifically includes:

[0008] Step 1: Obtain the geographical information of bus vehicles within the research scope, and based on the location data of the starting and ending stations of bus lines, extract the up and down running trajectories of each bus line.

[0009] Step 2: Obtain the urban road network data within the research scope and establish an urban road network.

[0010] Step 3: Construct a map matching algorithm based on the Hidden Markov Model, and calculate the matching probabilities between the trajectory points of the up and down running trajectories of each bus line and the road segments in the urban road network.

[0011] Step 4: Consider the vector relationship between adjacent trajectory points in the bus line trajectory, and calculate the transition probability of the vehicle traveling from one road segment to another at the intersection.

[0012] Step 5: Based on the matching probability and the transition probability, set the parameters in the Hidden Markov Model to construct a map matching algorithm for the bus line and the urban road network, and obtain the bus line information passing through each road segment in the urban road network.

[0013] Step 6: Use the spatial join method to obtain the population and POI information around each road segment.

[0014] Step 7: According to the bus line information, lane information, surrounding population and POI information passing through each road segment extracted, and the departure frequency of each bus line, calculate the key index of each road segment in the road network, and identify the key road segments in the bus network according to the key index of each road segment.

[0015] Optionally, step 1 specifically includes:

[0016] Step 1.1: Read the bus line information data within the research scope for a certain period of time. The bus line information data includes but is not limited to: line name, number of vehicles, and number of running trips.

[0017] Step 1.2: Read the bus trajectory information within the research scope. The bus trajectory information data includes but is not limited to: line name, up and down directions, starting station, ending station, and trajectory coordinates.

[0018] Step 1.3: According to the bus line information data, extract the running trajectories G t of each bus line in the up and down directions from the bus trajectory information data, and count the total number of running trips p of each line during this period to obtain the bus line geographic information within the research scope. The bus line geographic information includes line name, up and down directions, starting station, ending station, total number of running trips, and longitude and latitude information.

[0019] Optionally, step 2 specifically includes:

[0020] Step 2.1: Based on the running trajectory G t of the bus, extract the longitude range [lon min , lon max , and the latitude range [lat min , lat max , and define this range as the research area, where lon min, lon max It is the minimum and maximum longitude among all bus trajectory points, lat min , lat max They are respectively the minimum and maximum latitude among all bus trajectory points.

[0021] Step 2.2: Download map data according to the research area, and extract information on map edges and nodes. Among them, a node is the endpoint of two adjacent roads in the map, and the information of the endpoint includes the node number and node coordinates; an edge is a road in the map, and the information of the road includes the start point number, end point number, road name, number of lanes, and edge coordinates.

[0022] Step 2.3: Create a map object G nodes based on the set of node coordinates G edges and the set of edge coordinates G o as the urban road network, where G o ={G nodes ,G edges}.

[0023] Optionally, step 3 specifically includes:

[0024] Step 3.1: Perform rasterization processing on the road network data of the urban road network, use a circular area within a certain range centered on the nodes in the set of node coordinates G nodes as the error area, set the radius of the circumference to ir meters, and eliminate the road segments with a distance greater than ir meters.

[0025] Step 3.2: Use the projection method to determine candidate points, calculate the actual distance d between the trajectory points in the bus trajectory information and all the to-be-matched road segments within i meters of the node, and compare the calculation results to find the to-be-matched road segment closest to the trajectory point.

[0026] Step 3.3: Set the positioning error E d in the map matching algorithm, and the expression of the positioning error E d is as follows:

[0027] ,

[0028] where is the standard deviation of the bus trajectory points, is the pi, is the natural constant.

[0029] Step 3.4: Extract the driving direction information of the bus according to the up and down information of the bus, and calculate the direction error E α , and the expression of the direction error E α is as follows:

[0030] ,

[0031] Among them, α represents the included angle between the orientation of the bus trajectory point in its trajectory and the direction of the road section to be matched.

[0032] Step 3.5: According to the bus positioning error E d and the direction error between the bus GPS trajectory and the road section to be matched , calculate the matching probability E that the bus trajectory point and its road section to be matched are the actual driving road section of the bus. The expression of E is as follows:

[0033] .

[0034] Optionally, the specific steps of step 4 include:

[0035] Step 4.1: Obtain the Euclidean distance d between two adjacent trajectory points in the bus trajectory n-1，n and the shortest distance D between the candidate points corresponding to the two trajectory points n-1，n , and calculate the similarity degree S between the bus trajectory and the road section to be matched r . The similarity degree S r is expressed as follows:

[0036] ,

[0037] Step 4.2: Calculate the positioning change trend C between two adjacent trajectory points p . The positioning change trend C p is expressed as follows:

[0038] ,

[0039] Among them, d n-1 and d n are respectively the distances between two adjacent bus trajectory points and their corresponding matched road sections.

[0040] Step 4.3: According to the similarity degree S between the bus trajectory and the road section to be matched r and the positioning change trend C between two adjacent trajectory points p , calculate the transfer probability T that the bus travels from one road section to another at the intersection. The expression of the transfer probability T is as follows:

[0041] ,

[0042] Among them, t r is the coefficient of the similarity degree S between the bus trajectory and the road section to be matched r , t p is the positioning change trend C between two adjacent trajectory points pCoefficient.

[0043] Optionally, step 5 specifically includes:

[0044] Step 5.1: Set the parameter id to specify the maximum distance between the bus trajectory and the section to be matched, and set the parameter di max to specify the maximum distance of each trajectory point from the corresponding starting position, and set the parameter to specify the standard deviation value of the bus trajectory points, and set the parameter st n to specify whether to allow parts of the bus trajectory that do not directly correspond to the road network, and set the parameter p stn to specify the proportion of the bus trajectory that does not directly correspond to the road network, and construct a map matching algorithm for bus lines and the actual road network based on the hidden Markov model.

[0045] Step 5.2: Randomly select a bus trajectory sample, divide it into multiple small segments, project the extracted bus trajectory coordinates and the urban road network G o onto the same coordinate system, and use the map matching algorithm for bus lines and the actual road network to match the trajectory with the actual path in the urban road network G o and extract the path matching result to complete the path matching of one bus trajectory.

[0046] Step 5.3: Repeat step 5.2 to match all bus trajectories in the study area with the actual road network, and obtain the bus line information of each section in the urban road network G o The information on the sections passed by each bus line in the obtained urban road network includes the line name, up and down directions, departure times, road name, road starting point number, road ending point number, and number of lanes.

[0047] Step 5.4: Link the information on the bus lines passing through each section in the urban road network with the information on the bus lines in the study area during the time period q, and calculate the number of trips p m of all bus lines on section m during the time period q, as well as the bus traffic situation B m of section m.

[0048] Among them, the expression of the number of trips p m is as follows:

[0049]

[0050] Among them, I is the total number of bus lines passing through a certain section m, and p id is the total departure times of bus line id during the time period q.

[0051] The expression of the bus traffic situation B m is as follows:

[0052]

[0053] Among them, l m is the number of lanes of road section m.

[0054] Optionally, step 6 specifically includes:

[0055] Step 6.1: Taking the trajectory points of each road section in the actual road network as the centers, setting the road influence radius as θ meters, and constructing a road buffer zone.

[0056] Step 6.2: Reading the POI data within the research scope, projecting the POI data and the buffer zones of each road section in a unified coordinate system to obtain the POI information within the buffer zones of each road section, statistically analyzing the quantity of the POI information within each buffer zone, and counting the number of POIs within the buffer zone corresponding to road section m as poi m .

[0057] Step 6.3: Reading the population data of each traffic zone within the research area, calculating the residential population and working population data within the buffer zones according to the proportional relationship between the area of each road buffer zone and the area of the corresponding traffic zone, and counting the residential population within the buffer zone corresponding to road section m as lp m , and the number of working population as wp m .

[0058] Optionally, step 7 specifically includes:

[0059] Step 7.1: Linking the bus line information passing through each road section in the road network with various POI data and residential population and working population data around each road section, taking the bus traffic conditions of each road section as the first column, the number of POIs within the corresponding buffer area as the second column, the residential population within the corresponding buffer area as the third column, and the working population within the corresponding buffer area as the fourth column, establishing a judgment matrix X, and performing normalization processing on the judgment matrix X to obtain the elements of the normalized judgment matrix X .

[0060] Among them, the expression of the judgment matrix X is:

[0061] ,

[0062] Among them, x ij represents the element in the i-th row and j-th column of the judgment matrix X, m is the number of road sections within the research area, i represents the i-th road section, and j represents the serial number of the column.

[0063] Step 7.2: Calculating the dimensional entropy H j , and its calculation formula is:

[0064] ,

[0065] Define the weights of each index using the dimensional entropy of each index , and its expression is:

[0066] ,

[0067] And calculate the weighted matrix R to determine the optimal solution and the worst solution , and the expression of the weighted matrix R is:

[0068] .

[0069] Among them, r ij represents the element in the i-th row and j-th column of the matrix R, .

[0070] Step 7.3: Calculate the key index C of each section in the road network according to the optimal solution and the worst solution of the weighted matrix R i , and the key index C i The calculation formula of is:

[0071] .

[0072] C i The larger the value of, the more critical the section is in the bus network.

[0073] Second aspect, a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a method for identifying key sections of a bus network as described in any one of the first aspects.

[0074] Third aspect, a computer device, including:

[0075] A memory for storing instructions.

[0076] A processor for executing the instructions, so that the computer device executes the operations of a method for identifying key sections of a bus network as described in any one of the first aspects.

[0077] Beneficial effects: A method, an electronic device, and a storage medium for identifying key sections of a bus network provided by the present invention extract the operating trajectories of each bus line based on the GPS data of buses within the research scope; obtain the urban road network within the research scope and construct a map matching algorithm based on the Hidden Markov Model; apply the constructed map matching algorithm to match the operating trajectories of each bus line and the actual road network to obtain the information of the bus lines passing through each section of the road network; use the spatial join method to identify and obtain various types of POI (Point of Interest) data and population data around each section; based on the information of the bus lines passing through each road section, lane information, surrounding population and POI information, and the departure frequencies of each bus line, calculate the key index of each section in the road network using the entropy weight TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) method, so as to identify the key sections in the bus network. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 is a flowchart of a method for identifying key sections of a bus network according to the present invention.

[0079] Figure 2 is a schematic diagram of a bus trajectory in an embodiment of the method of the present invention.

[0080] Figure 3 is a schematic diagram of a road network created in an embodiment of the method of the present invention.

[0081] Figure 4 is a visualization schematic diagram of the importance of each road in an embodiment of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0082] The following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

[0083] The following further describes the present invention with reference to specific embodiments.

[0084] Embodiment 1:

[0085] This embodiment introduces a method for identifying key sections of a bus network. As Figure 1 shown, it specifically includes:

[0086] Step 1: Obtain the geographical information of bus vehicles within the research scope. Based on the location data of the starting and ending stations of bus lines, extract the up and down running trajectories of each bus line.

[0087] Step 2: Obtain the urban road network data within the research scope and establish an urban road network.

[0088] Step 3: Construct a map matching algorithm based on the Hidden Markov Model, and calculate the matching probability between the trajectory points of the up and down running trajectories of each bus line and the road segments in the urban road network.

[0089] Step 4: Consider the vector relationship between adjacent trajectory points in the bus line trajectory, and calculate the transition probability of the vehicle traveling from one road segment to another at the intersection.

[0090] Step 5: Based on the obtained matching probability and transition probability, set the parameters in the Hidden Markov Model to construct a map matching algorithm for the bus line and the urban road network, and obtain the bus line information passing through each road segment in the urban road network.

[0091] Step 6: Use the spatial join method to obtain various types of POI data and population data around each road segment.

[0092] Step 7: According to the bus line information, lane information, surrounding population and POI information passing through each road segment extracted, and the departure frequency of each bus line, calculate the key index of each road segment in the road network based on the entropy weight TOPSIS method, so as to identify the key road segments in the bus network.

[0093] As an optimal solution, Step 1 specifically includes:

[0094] Step 1.1: Read the bus line information data within the research scope for a certain period (such as: one month). The bus line information data includes but is not limited to: three fields of line name, number of vehicles, and number of running trips.

[0095] Step 1.2: Read the bus trajectory information within the research scope. The bus trajectory information data includes but is not limited to: five fields of line name, up and down directions, starting station, ending station, and trajectory coordinates (a set of trajectory points).

[0096] Step 1.3: According to the bus line information data obtained in Step 1.1, extract the running trajectories G of each bus line in the up and down directions from the bus trajectory information data obtained in Step 1.2 t , and count the total number of running trips p of each line during this period to obtain the geographical information of the bus lines within the research scope, where G tIt is a set of bus trajectory points, and its data form is LINESTRING (lon.lat,...), where lon is the longitude coordinate of the trajectory point and lat is the latitude coordinate of the trajectory point. The obtained geographical information of the bus line includes 6 fields: line name, up and down directions, starting station, ending station, total number of running trips, and longitude and latitude information.

[0097] As an optimal solution, step 2 specifically includes:

[0098] Step 2.1: According to the bus running trajectory G obtained in step 1 t , extract the longitude range [lon min , lon max , and the latitude range [lat min , lat max , and define this range as the research area, where lon min , lon max are respectively the minimum and maximum longitudes among all bus trajectory points, and lat min , lat max are respectively the minimum and maximum latitudes among all bus trajectory points.

[0099] Step 2.2: According to the research area obtained in step 2.1, download map data and extract information on map edges and nodes. Among them, a node is the endpoint of two adjacent roads in the map, and its information includes 2 fields: node number and node coordinates; an edge is a road in the map, and its information includes 5 fields: starting point number, ending point number, road name, number of lanes, and edge coordinates.

[0100] Step 2.3: According to the set G nodes of node coordinates and the set G edges of edge coordinates obtained in step 2.2, create a map object G o as the urban road network, where G o = {G nodes , G edges}. Project the created map object G o into the Mercator coordinate system to precisely control parameters. G nodes represents the set of nodes, and G edges represents the set of edges.

[0101] As an optimal solution, step 3 specifically includes:

[0102] Step 3.1: Perform rasterization processing on the road network data of the obtained urban road network, using the set G nodesThe nodes in it are circular regions within a certain range centered on the node as the error region. According to the actual complexity of the bus line, the circumferential radius is set to ir meters, and the sections with a distance greater than ir meters are removed to reduce the candidate sections and improve the matching efficiency.

[0103] Step 3.2: Use the projection method to determine the candidate points. Calculate the actual distances between the trajectory points in the bus trajectory information obtained in Step 1.2 and all the to-be-matched sections within a distance of i meters from the node, and compare the calculation results to find the to-be-matched section with the closest distance to the trajectory point, so as to obtain the actual running trajectory of the bus in the road network. The calculation formula for the actual distance d between a certain trajectory point G in the bus trajectory information and the to-be-matched section is:

[0104] ,

[0105] where x l , y l are the abscissa and ordinate of the projection point L of the trajectory point G to the to-be-matched section in the coordinate system, and x g , y g are the abscissa and ordinate of the trajectory point G in the coordinate system. The calculation formula for the coordinates of the projection point L of the trajectory point G to the to-be-matched section AB is:

[0106] ,

[0107] where x a , y a are the abscissa and ordinate of the vertex A of the to-be-matched section AB in the coordinate system, and k is the slope of the to-be-matched section AB in the coordinate system. x b , y b are the abscissa and ordinate of the vertex B of the to-be-matched section AB in the coordinate system.

[0108] Step 3.3: According to the GPS positioning error principle, the closer the to-be-matched section is to the trajectory point position, the higher the probability that this section is the actual running trajectory of the bus. Set the positioning error E d in this map matching algorithm to satisfy the normal distribution, and its expression is:

[0109] ,

[0110] where is the standard deviation of the bus trajectory point. By setting the parameter to optimize the matching degree between the bus trajectory and the road network, is the pi.

[0111] Step 3.4: According to the bus up / down information obtained in Step 1.3, extract the driving direction information of the bus, introduce the direction deviation in the map matching tool to improve the matching degree between the bus trajectory and the road network, and the direction error Eα The calculation formula is as follows:

[0112] ,

[0113] where α represents the angle between the orientation of the bus trajectory point in its trajectory and the direction of the road segment to be matched. Taking the trajectory point G and its road segment AB to be matched as an example, its calculation formula is:

[0114] ,

[0115] where k g is the orientation of the trajectory point G in its trajectory.

[0116] Step 3.5: According to the bus positioning error E d obtained in Step 3.3 and Step 3.4 and the direction error between the bus GPS trajectory and the road segment to be matched

[0117] .

[0118] As an optimal solution, the said Step 4 specifically includes:

[0119] Step 4.1: Obtain the Euclidean distance d n-1，n between two adjacent trajectory points in the bus trajectory n-1，n and the shortest distance D r between the candidate points corresponding to these two points r , and calculate the similarity degree S

[0120] .

[0121] Step 4.2: Calculate the positioning change trend C p between two adjacent trajectory points, and ensure that the two adjacent trajectory points in the bus trajectory described in Step 4.1 are two adjacent points in the actual driving trajectory. The calculation formula of C p is as follows:

[0122] ,

[0123] where d n-1 and d n are the distances between two adjacent bus trajectory points and their corresponding matched road segments.

[0124] Step 4.3: According to the similarity degree S r between the bus trajectory and the road segment to be matched obtained in Step 4.1 and Step 4.2p , calculate the transfer probability T of the bus traveling from one section to another at the intersection. The calculation formula of T is as follows:

[0125] ,

[0126] where t r is the coefficient of the similarity degree S r between the bus trajectory and the section to be matched, t p is the coefficient of the positioning change trend C p between adjacent two trajectory points, and t r +t p = 1. By adjusting the map matching tool, increase the size of the probability T that the matching path is the actual driving path, and improve the matching degree between the actual driving trajectory of the bus and the road network when the bus enters the intersection.

[0127] As an optimal solution, step 5 specifically includes:

[0128] Step 5.1: According to the method of rasterization and determination of candidate points in step 3, set the parameter id to specify the maximum distance between the bus trajectory and the section to be matched, set the parameter di max to specify the maximum distance of each trajectory point from the corresponding starting position, and set the parameter to specify the standard deviation value of the bus trajectory points; according to the method of improving the matching degree between the actual driving trajectory of the bus and the road network in step 4, set the parameter st n to specify whether to allow the part of the bus trajectory that does not directly correspond to the road network, and set the parameter p stn to specify the proportion of the bus trajectory that does not directly correspond to the road network. By setting the above parameters, create the map matching tool distancemacther, and construct the map matching algorithm between the bus line and the actual road network to enhance the matching accuracy between the trajectory and the actual road network.

[0129] Step 5.2: Randomly select a bus trajectory sample, divide it into multiple small segments, project the taken bus trajectory coordinates and the road network G o created in step 2.3 into the same coordinate system, use the map matching algorithm constructed in step 5.1 to match the trajectory with the actual path in the road network, extract the result of the path matching, and complete the path matching of a bus trajectory.

[0130] Step 5.3: According to the matching method of a bus trajectory in step 5.2, match all bus trajectories in the research scope with the actual road network, obtain the bus line information of each section in the road network, and the obtained information of the sections passed by each bus line in the road network includes 6 fields: line name, up and down directions, departure times, road name, road starting point number, road ending point number, and number of lanes.

[0131] Step 5.4: Link the bus line information passing through each section in the road network obtained in Step 5.3 with the bus line information within the time period q in the research scope obtained in Step 1.1, and the passing times p of all bus lines on section m within the time period q can be calculated. m , p m The calculation formula of is:

[0132]

[0133] Among them, I is the total number of bus lines passing through a certain section m, and p id is the total departure times of the id bus within the time period q. Further, the bus passing situation B of section m can be calculated m , B m The calculation formula of is:

[0134]

[0135] Among them, l m is the number of lanes of section m.

[0136] As a preferred solution, Step 6 specifically includes:

[0137] Step 6.1: Taking the trajectory points of each section in the actual road network as the center, setting the road influence radius as θ meters, constructing a road buffer zone, and using this buffer zone as the influence range for evaluating whether each section is congested.

[0138] Step 6.2: Read the POI data within the research scope, project the POI and the buffer zones of each section in a unified coordinate system to obtain the POI information within the buffer zones of each section, and conduct statistical analysis on the number of POIs within each buffer zone. The number of POIs within the buffer zone corresponding to section m is recorded as poi m .

[0139] Step 6.3: Read the population data of each traffic zone within the research area, and calculate the residential population and working population data within the buffer zones according to the proportional relationship between the area of each road buffer zone and the area of the traffic zone where it is located. The residential population within the buffer zone corresponding to section m is recorded as lp m , and the number of working population is recorded as wp m .

[0140] As a preferred solution, Step 7 specifically includes:

[0141] Step 7.1: Link the bus line information of each section in the road network obtained in Step 5.4 with the various types of POI data around each section obtained in Step 6.2 and the resident population and working population data obtained in Step 6.3. Take the bus traffic situation of each section as the first column, the number of POIs in the corresponding buffer area as the second column, the number of resident population in the corresponding buffer area as the third column, and the number of working population in the corresponding buffer area as the fourth column to establish a judgment matrix X, and its expression is:

[0142] ,

[0143] where, x ij represents the element in the i-th row and j-th column of matrix X, and m is the number of roads in the research area.

[0144] Perform normalization processing on the judgment matrix, and the normalization calculation formula is:

[0145] ,

[0146] where, x max is the maximum value under the same index.

[0147] Step 7.2: Calculate the dimension entropy H j of each index, and its calculation formula is:

[0148] ,

[0149] where, j is the number of each index.

[0150] Define the weight of each index using the dimension entropy of each index , and its expression is:

[0151] ,

[0152] And calculate the weighted matrix R, determine the optimal solution and the worst solution , and the expression of the weighted matrix R is:

[0153] .

[0154] where, r ij represents the element in the i-th row and j-th column of matrix R.

[0155] Step 7.3: According to the optimal solution and the worst solution of the weighted matrix R obtained in Step 7.2, calculate the key index C i of each section in the road network, and the calculation formula of the key index C i is:

[0156] .

[0157] C i The larger the value of, the more critical the section is in the bus network. Finally, the criticality index C of each section i is visualized.

[0158] Example 2:

[0159] This example is used to further illustrate the technical solution of the present invention. The initial research object of this example is 440 bus lines in a certain city. After screening the running track ranges and the up and down directions of these 440 bus lines, finally 819 bus running tracks are selected as the final research object for the judgment of critical sections.

[0160] 1. Obtain the bus line and geographical information (line name, up and down directions, starting station, ending station, departure times, and longitude and latitude information of the running track) of 819 bus running tracks within the research scope for one month. The specific data format is shown in Table 1. The bus tracks obtained in this example are as Figure 2 shown.

[0161] Table 1 Bus Line Information

[0162]

[0163] 2. According to the longitude and latitude of 819 bus running tracks within the research scope, extract the longitude range [118.361, 119.46] and the latitude range [31.85, 32.61] as the research area, download the map data, and extract the information of map nodes and edges. In this example, 37,290 pieces of node information are extracted, as shown in Table 2; 88,514 pieces of edge information are extracted, as shown in Table 3. Create a map object based on the extracted node and edge information, form a road network model, and establish an urban road network. The road network created in this example is as Figure 3 shown.

[0164] Table 2 Road Network Node Information

[0165]

[0166] Table 3 Road Network Edge Information

[0167]

[0168] 3. According to the rasterization and candidate point determination method, set the maximum distance between the bus trajectory and the section to be matched to 500 meters, set the maximum distance of each trajectory point from its corresponding starting position to 170 meters, and set the standard deviation value of the bus trajectory points to 50; set the part where the bus trajectory is not directly corresponding to the road network according to the method of improving the matching degree between the actual driving trajectory of the bus and the road network when entering the intersection. By setting the above parameters, construct a map matching algorithm for the bus line and the actual road network to enhance the matching accuracy between the trajectory and the actual road network. The parameter settings of the map matching tool created in this example are shown in Table 4.

[0169] Table 4 Map Matching Tool Parameters

[0170]

[0171] 4. Match all bus trajectories within the research scope with the actual road network to obtain the bus line information passing through each section of the road network. The sections passed by the bus lines obtained in this example are shown in Table 5.

[0172] Table 5 Information on Sections Passed by Bus Lines

[0173]

[0174] 5. Link the information on the sections passed by the bus lines with the bus operation record information for one month to obtain the number of passes of all bus lines on each section. Combine the number of lanes of each section to calculate the bus traffic conditions on each section. Set the road influence radius to 200 meters, construct a road buffer, and count the number of POIs, resident population, and working population within each buffer. The bus traffic conditions on 13,857 roads within the research scope obtained in this example, as well as the number of POIs, resident population, and working population within the buffer, are shown in Table 6.

[0175] Table 6 Bus Traffic Conditions on Each Road and Buffer Area Information

[0176]

[0177] 6. According to the bus traffic conditions on each road and buffer area information shown in Table 3, calculate the key index of each section in the road network based on the entropy weight TOPSIS method, and sort the obtained key indexes from largest to smallest. The judgment values for whether the roads obtained in this example are key sections are shown in Table 7. Visualize the obtained judgment values, as Figure 4 shown, and it can be found that the key index of the road reaches the peak in some sections of Zhujiang Road.

[0178] Table 7 Road Key Index

[0179]

[0180] 7. After obtaining the key indices of each road section, query the bus line information passing through this road section in Table 5 according to the road starting point and ending point numbers, evaluate whether there are duplicate functions of these bus routes on the key road sections in combination with the actual situation, and then adjust and optimize the existing bus network to minimize the impact of emergencies on the key road sections on the bus network.

[0181] Example 3:

[0182] This example introduces a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a method for identifying key road sections of a bus network as described in any one of Example 1.

[0183] Example 4:

[0184] This example introduces a computer device, including:

[0185] A memory for storing instructions.

[0186] A processor for executing the instructions, so that the computer device performs the operations of a method for identifying key road sections of a bus network as described in any one of Example 1.

[0187] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0189] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means embodying the functionality specified in one or more of the flowchart Figure 1 flowcharts and / or block Figure 1 diagrams or blocks.

[0190] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functionality specified in one or more of the flowchart Figure 1 flowcharts and / or block Figure 1 diagrams or blocks.

[0191] The above are only the preferred embodiments of the present invention, and it should be noted that: for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for identifying key sections of a bus network, characterized in that: Specifically, it includes: Step 1: Obtain the geographical information of bus vehicles within the research scope, and extract the up and down running trajectories of each bus line based on the location data of the starting and ending stations of the bus lines. Step 2: Obtain the urban road network data within the research scope and establish an urban road network. Step 3: Construct a map matching algorithm based on the Hidden Markov Model, and calculate the matching probability between the trajectory points of the up and down running trajectories of each bus line and the road segments in the urban road network. Step 4: Consider the vector relationship between adjacent trajectory points in the bus line trajectory, and calculate the transfer probability of the vehicle traveling from one road segment to another at the intersection. Step 5: Based on the matching probability and transfer probability, set the parameters in the Hidden Markov Model to construct a map matching algorithm for the bus line and the urban road network, and obtain the information of the bus lines passing through each road segment in the urban road network. Step 6: Use the spatial join method to obtain the population and POI information around each road segment. Step 7: According to the information of the bus lines passing through each road segment, lane information, surrounding population and POI information extracted, and the departure frequency of each bus line, calculate the key index of each road segment in the road network, and identify the key road segments in the bus network according to the key index of each road segment.

2. The method for identifying key sections of a bus network according to claim 1, characterized in that: The specific content of step 1 includes: Step 1.1: Read the bus line information data within the research scope for a certain period of time. The bus line information data includes but is not limited to: line name, number of vehicles, and number of running trips. Step 1.2: Read the bus trajectory information within the research scope. The bus trajectory information data includes but is not limited to: line name, up and down directions, starting station, ending station, and trajectory coordinates. Step 1.3: According to the bus line information data, extract the driving trajectories G of each bus line in the upward and downward directions from the bus trajectory information data, and count the total number of trips p of each line during this time period to obtain the geographical information of the bus lines within the research scope. The geographical information of the bus lines includes the line name, up and down directions, starting station, ending station, total number of trips, and longitude and latitude information. t , and count the total number of trips p of each line during this time period to obtain the geographical information of the bus lines within the research scope. The geographical information of the bus lines includes the line name, up and down directions, starting station, ending station, total number of trips, and longitude and latitude information.

3. A method for identifying key sections of a bus network according to claim 1, characterized in that: The specific content of step 2 includes: Step 2.1: According to the driving trajectory G of the bus t , extract the longitude range [lon min , lon max , and the latitude range [lat min , lat max , and define this range as the research area, where lon min , lon max are the minimum and maximum longitudes among all bus trajectory points, and lat min , lat max are the minimum and maximum latitudes among all bus trajectory points respectively; Step 2.2: Download the map data according to the research area, and extract the information of the map edges and nodes. Among them, the node is the endpoint of two adjacent roads in the map, and the information of the endpoint includes the node number and node coordinates; the edge is the road in the map, and the information of the road includes the starting point number, ending point number, road name, number of lanes, and edge coordinates. Step 2.3: According to the node coordinate set G nodes and the edge coordinate set G edges , create a map object G o as the urban road network, where G o ={G nodes ,G edges}.

4. A method for identifying key sections of a bus network according to claim 1, characterized in that: The specific content of step 3 includes: Step 3.1: Rasterize the road network data of the urban road network to obtain the node coordinate set G nodes The circle area within a certain range of the node in the center is taken as the error area, the radius of the circle is set to ir meters, and the road sections with a distance greater than ir meters are eliminated; Step 3.2: Use the projection method to determine the candidate points, calculate the actual distance d between the trajectory points in the bus trajectory information and all the to-be-matched road segments within i meters of the node, and compare the calculation results to find the to-be-matched road segment closest to the trajectory point. Step 3.3: Set the positioning error E in the map matching algorithm d , the positioning error E d The expression is as follows: ； Among them, is the standard deviation of bus trajectory points, is the ratio of the circumference of a circle to its diameter, is the natural constant; Step 3.4: Extract the driving direction information of the bus according to the up / down information of the bus, and calculate the direction error E α , the direction error E α The expression of is as follows: ； Among them, α represents the angle between the orientation of the bus trajectory point in its trajectory and the direction of the to-be-matched road segment. Step 3.5: According to the positioning error E of the bus d and the direction error between the bus GPS trajectory and the road section to be matched , calculate the matching probability E that the bus trajectory point and the road section to be matched are the actual driving road section of the bus. The expression of E is as follows: 。 5. A method for identifying key sections of a bus network according to claim 1, characterized in that: The specific content of step 4 includes: Step 4.1: Obtain the Euclidean distance d between two adjacent trajectory points in the bus trajectory n-1，n The shortest distance D between the candidate points corresponding to the two trajectory points n-1，n , and calculate the similarity degree S between the bus trajectory and the section to be matched r The similarity degree S r has the following expression: ； Step 4.2: Calculate the positioning change trend C between two adjacent trajectory points p , the positioning change trend C p has the following expression: ； where d n-1 and d n are respectively the distances between two adjacent bus trajectory points and their corresponding matched road segments; Step 4.3: According to the similarity degree S between the bus trajectory and the section to be matched r and the positioning change trend C between two adjacent trajectory points p , calculate the transfer probability T of the bus traveling from one section to another at the intersection; the expression of the transfer probability T is as follows: ； Among them, t r is the coefficient of the similarity degree S r between the bus trajectory and the section to be matched, and t p is the coefficient of the positioning change trend C p between two adjacent trajectory points.

6. A method for identifying key sections of a bus network according to claim 1, characterized in that: The specific content of step 5 includes: Step 5.1: Set the parameter id to specify the maximum distance between the bus trajectory and the section to be matched, and set the parameter di max to specify the maximum distance of each trajectory point from the corresponding starting position, and set the parameter to specify the standard deviation value of the bus trajectory points, and set the parameter st n to specify whether it is allowed that there are parts of the bus trajectory that do not directly correspond to the road network, and set the parameter p stn to specify the proportion of the bus trajectory that does not directly correspond to the road network, and construct a map matching algorithm for bus lines and the actual road network based on the hidden Markov model; Step 5.2: Randomly select a bus trajectory sample, divide it into multiple small segments, project the extracted bus trajectory coordinates and the urban road network G o onto the same coordinate system, and use the map matching algorithm for bus lines and the actual road network to match the trajectory with the actual path in the urban road network G o to extract the result of path matching and complete the path matching of one bus trajectory; Step 5.3: Repeat Step 5.2 to match all bus trajectories within the research scope with the actual road network, and obtain the bus line information of each section in the urban road network G o The information on the sections passed by each bus line in the obtained urban road network includes the line name, up and down directions, departure frequency, road name, road start point number, road end point number, and number of lanes; Step 5.4: Link the bus line information passing through each section in the urban road network with the bus line information within the time period q in the research scope, and calculate the number of passes p of all bus lines on section m within the time period q m , and the bus traffic situation B of section m m ; Among them, the number of passages p m has the following expression: ； Among them, I is the total number of bus lines passing through a certain section m, and p id is the total number of departures of the bus on route id during time period q; Bus traffic condition B m The expression is as follows: ； where l m is the number of lanes of road segment m.

7. A method for identifying key sections of a bus network according to claim 1, characterized in that: The specific content of step 6 includes: Step 6.1: Take the trajectory points of each road segment in the actual road network as the center, set the road influence radius to θ meters, and construct a road buffer zone. Step 6.2: Read the POI data within the research scope, project the POI data and the buffer zones of each road section in a unified coordinate system to obtain the POI information within the buffer zones of each road section, statistically analyze the quantity of the POI information within each buffer zone, and count the number of POIs within the buffer zone corresponding to road section m as poi m ; Step 6.3: Read the population data of each traffic zone in the study area. Based on the proportional relationship between the area of each road buffer and the area of the corresponding traffic zone, calculate the residential and working population data within the buffer. Denote the residential population within the buffer corresponding to section m as lp m , and denote the working population as wp m .

8. A method for identifying key sections of a bus network according to claim 1, characterized in that: The specific content of step 7 includes: Step 7.1: Link the bus line information of each section in the road network with various types of POI data, residential population, and working population data around each section. Take the bus traffic situation of each section as the first column, the number of POIs in the corresponding buffer area as the second column, the number of residential population in the corresponding buffer area as the third column, and the number of working population in the corresponding buffer area as the fourth column to establish a judgment matrix X, and perform normalization processing on the judgment matrix X to obtain the elements of the normalized judgment matrix X ; Among them, the expression of the judgment matrix X is: ； where x ij represents the element in the \(i\)-th row and \(j\)-th column of the judgment matrix \(X\), \(m\) is the number of road segments in the study area, \(i\) represents the \(i\)-th road segment, and \(j\) represents the column number; Step 7.2: Calculate the dimensional entropy H of the four columns of indicators j , and its calculation formula is as follows: ； Define the weights of each indicator using the dimensional entropy of each indicator , and its expression is: ； And calculate the weighted matrix \(R\) to determine the optimal solution and the worst solution , and the expression of the weighted matrix \(R\) is: ； where r ij represents the element in the i-th row and j-th column of matrix R, ; Step 7.3: Calculate the critical index C of each section in the road network according to the optimal solution and the worst solution of the weighted matrix R i , the critical index C i is calculated by the formula: ； C i The larger the value, the more critical the road section is in the bus network.

9. A computer-readable storage medium, characterized in that: It stores a computer program, and when the computer program is executed by a processor, it implements a method for identifying key road segments in a bus network as described in any one of claims 1 to 8.

10. A computer device, characterized in that: It includes: A memory for storing instructions; A processor for executing the instructions, so that the computer device performs the operations of a method for identifying key road segments in a bus network as described in any one of claims 1 to 8.

Images