Site Importance Assessment Methods and Devices

Abstract

This invention discloses a method and apparatus for assessing the importance of stations, belonging to the field of transportation networks and propagation dynamics technology. It addresses the problem that existing methods for assessing station importance fail to fully reflect operating routes and rely on global network topology information based on shortest paths, leading to relatively time-consuming calculations of the impact of distant stations on station importance. The method includes: constructing a bus-metro dual-layer network, a node network, a route network, and a bipartite graph network based on the bus and metro networks; determining the community structure and community center nodes of the node network using a community mining algorithm to form an enhanced node network; determining the preliminary importance of each second node based on the enhanced node network, and determining the preliminary importance of each third node based on the route network; and determining the final importance of the second nodes included in the node network based on the bipartite graph network, the preliminary importance of each second node, and the preliminary importance of each third node.

Description

Technical Field

[0001] This invention belongs to the field of transportation network and propagation dynamics technology, and more specifically, to a method and apparatus for assessing the importance of stations. Background Technology

[0002] With the continuous development of the social economy and urban construction, urban public transportation, providing convenient services for urban residents' daily commutes, has become increasingly diversified. It primarily utilizes subways and buses, supplemented by bicycles and taxis. Subways, due to their environmental friendliness, convenience, speed, and affordability, have become a fundamental transportation infrastructure. Buses, with their large passenger capacity, high efficiency, and wide coverage, have also become important travel options. Bicycles and taxis, however, offer personalized transportation options that combine private and public transport functions, lacking fixed stops. In the daily operation of urban public transportation, some subway or bus stops may experience widespread traffic congestion after extreme weather or traffic accidents, leading to a decline in the connectivity and network efficiency of the transportation system, becoming a key factor restricting the normal operation of urban public transportation. Simultaneously, the urban public transportation system exhibits unbalanced development, with some subway and bus stops carrying the majority of the system's passenger volume. To avoid station malfunctions significantly reducing travel efficiency and disrupting the network structure, it is necessary to understand the importance of urban public transportation network stations to provide decision-making support for traffic managers. For example, allocating more resources to key stations can improve the resilience of urban public transportation; key stations can be designated as transfer stations for new lines to optimize the transportation network structure.

[0003] Subways and buses are two major modes of transportation for residents' daily travel, playing a complementary role in improving urban traffic efficiency. They are not isolated within the urban public transportation system but are interconnected through transfer stations, jointly meeting residents' daily travel needs and effectively improving the system's efficiency. In fact, the urban public transportation system should be viewed as a multi-layered network with interconnected connections. Because a single network is often influenced by others, a node failure in a single network not only affects itself but also the structure and function of other networks within the multi-layered network. Therefore, it is difficult to detect the overall characteristics of the urban public transportation system from a single network perspective. Furthermore, in the daily operation of urban rail transit, managers often suspend the operation of an entire line due to a fault at a specific point (such as a fire at a station or a power outage on a section) to minimize subsequent damage. Traditional station importance assessment algorithms mainly focus on network topology and static passenger flow; methods based on network topology primarily focus on the network structure attributes of the transportation system; while methods based on static passenger flow combine network topology and passenger flow characteristics to measure station importance.

[0004] Furthermore, the operational trajectories of vehicles are increasingly being considered an important factor in assessing station importance. However, existing methods fail to fully reflect the role of operational routes when evaluating station importance. Additionally, current methods often rely on global network topology information based on shortest paths, making the calculation of the impact of distant stations on station importance relatively time-consuming. Moreover, existing research rarely considers the interactions between different transportation systems.

[0005] In summary, existing methods for assessing site importance fail to fully reflect operational routes. They rely on global network topology information based on the shortest path, which results in relatively time-consuming calculations of the impact of distant sites on site importance. Summary of the Invention

[0006] This invention provides a site importance assessment method and apparatus to address the problem that existing site importance assessment methods fail to fully reflect operational routes and rely on global network topology information based on the shortest path, resulting in relatively time-consuming calculations of the impact of distant sites on site importance.

[0007] This invention provides a method for assessing site importance, including:

[0008] Construct a bus-subway dual-layer network based on the bus network and subway network, and then construct a node network, a route network, and a bipartite graph network based on the bus-subway dual-layer network.

[0009] The community structure and community center nodes of the node network are determined according to the community mining algorithm. Multiple newly added community center nodes in the node network are connected to form an enhanced node network. Based on the authority value and hub value of the second nodes included in the node network, the preliminary importance of each second node is determined based on the enhanced node network.

[0010] The initial importance of each third node is determined based on its authority and hub values ​​within the network.

[0011] Based on the bipartite graph network, the initial importance of each second node, and the initial importance of each third node, the final importance of the second nodes included in the node network is determined.

[0012] Preferably, the bus-subway dual-layer network is The first set of nodes is The first set of edges is The first node's attribute set is The first set of routes is ;

[0013] in, , , , , , For bus stops; , , , , It is a subway node.

[0014] Preferably, the community center node is determined using the following formula:

[0015]

[0016] in, Represents a node network Second node The attributes, Indicates club The average value of the attributes of each second node within the node. , This represents the q-th club. q represents the community structure of the node network, where each community structure includes multiple second nodes, and q represents the number of community structures.

[0017] Preferably, the initial importance of each second node is determined using the following formula: ;

[0018] The initial importance of each third node is determined using the following formula: ;

[0019] in, , , Indicates the second node The pivot value in the (t-1)th iteration, Indicates the second node The authority value in the t-th iteration, Indicates the second node The pivot value in the t-th iteration, This represents the total number of second nodes included in the node network. Represents the second edge in a node network. The first weight; , ,

[0020] Indicates the third node The pivot value in the (t-1)th iteration, This indicates the total number of third nodes included in the network. Indicates the third node The authority value in the t-th iteration, Indicates the third node The pivot value in the t-th iteration, Indicates the third edge in the circuit network The second weight.

[0021] Preferably, the final importance of the second node included in the node network is determined by the following formula: ;

[0022] in, This represents the second node at the t-th iteration. Ultimate importance, Indicates the second node in the node network The second importance in the (t-1)th iteration It is a hyperparameter that balances the tightness of connections and mutual reinforcement between the second nodes. Represents the fourth edge in a bipartite graph network. The third weight, This represents the third node in the (t-1)th iteration. The second importance, , Indicates the third node in the line network. Second importance in the (t-2)th iteration; This represents the total number of third nodes in the network. This represents the total number of second nodes included in the node network. This represents the second node in the (t-1)th iteration. Second importance.

[0023] This invention provides a site importance assessment apparatus, comprising:

[0024] The construction unit is used to construct a bus-subway dual-layer network based on the bus network and the subway network, and to construct a node network, a route network and a bipartite graph network in sequence based on the bus-subway dual-layer network.

[0025] The first determining unit is used to determine the community structure and community center nodes of the node network according to the community mining algorithm, connect the multiple newly added community center nodes in the node network to form an enhanced node network, and determine the preliminary importance of each second node based on the authority value and hub value of the second nodes included in the node network.

[0026] The second determining unit is used to determine the preliminary importance of each third node based on the authority value and hub value of the third nodes included in the line network.

[0027] The third determining unit is used to determine the final importance of the second nodes included in the node network based on the bipartite graph network, the preliminary importance of each second node, and the preliminary importance of each third node.

[0028] Preferably, the bus-subway dual-layer network is The first set of nodes is The first set of edges is The first node's attribute set is The first set of routes is ;

[0029] in, , , , , , For bus stops; , , , , It is a subway node.

[0030] Preferably, the community center node is determined using the following formula:

[0031]

[0032] in, Represents a node network Second node The attributes, Indicates club The average value of the attributes of each second node within the node. , This represents the q-th club. q represents the community structure of the node network, where each community structure includes multiple second nodes, and q represents the number of community structures.

[0033] Preferably, the initial importance of each second node is determined using the following formula: ;

[0034] The initial importance of each third node is determined using the following formula: ;

[0035] in, , , Indicates the second node The pivot value in the (t-1)th iteration, Indicates the second node The authority value in the t-th iteration, Indicates the second node The pivot value in the t-th iteration, This represents the total number of second nodes included in the node network. Represents the second edge in a node network. The first weight; , ,

[0036] Indicates the third node The pivot value in the (t-1)th iteration, This indicates the total number of third nodes included in the network. Indicates the third node The authority value in the t-th iteration, Indicates the third node The pivot value in the t-th iteration, Indicates the third edge in the circuit network The second weight.

[0037] Preferably, the final importance of the second node included in the node network is determined by the following formula: ;

[0038] in, This represents the second node at the t-th iteration. Ultimate importance, Indicates the second node in the node network The second importance in the (t-1)th iteration It is a hyperparameter that balances the tightness of connections and mutual reinforcement between the second nodes. Represents the fourth edge in a bipartite graph network. The third weight, This represents the third node in the (t-1)th iteration. The second importance, , Indicates the third node in the line network. Second importance in the (t-2)th iteration; This represents the total number of third nodes in the network. This represents the total number of second nodes included in the node network. This represents the second node in the (t-1)th iteration. Second importance.

[0039] This invention provides a method and apparatus for assessing the importance of stations. The method includes: constructing a bus-subway dual-layer network based on a bus network and a subway network; sequentially constructing a node network, a route network, and a bipartite graph network based on the bus-subway dual-layer network; determining the community structure and community center nodes of the node network using a community mining algorithm; connecting multiple newly added community center nodes in the node network to form an enhanced node network; determining the preliminary importance of each second node based on the authority and hub values ​​of the second nodes included in the node network; determining the preliminary importance of each third node based on the authority and hub values ​​of the third nodes included in the route network; and determining the final importance of the second nodes included in the node network based on the bipartite graph network, the preliminary importance of each second node, and the preliminary importance of each third node. To address the issue that existing methods often neglect the coupling relationships between different transportation systems, this invention constructs a two-layer bus-subway network for urban public transportation systems. Inter-layer edges characterize the interaction relationships between different transportation systems, and node attributes record historical passenger flow totals for different dates. Edge attributes also record the operating routes passing through those edges. Furthermore, to address the issue of existing methods rarely focusing on operating routes, this invention uses the number of operating routes to characterize the importance influence between neighboring stations and uses a bipartite graph network to characterize the mutual reinforcement relationships between operating routes and stations. Finally, to address the issue that existing methods typically rely on time-consuming shortest path algorithms to characterize the influence of distant nodes, this invention first identifies the network community structure using community mining technology, then determines the community center node that represents all nodes within the community based on node attributes, and finally uses a small number of community center nodes to quickly obtain the importance influence of distant nodes. This solves the problem that existing methods for assessing station importance fail to fully reflect operating routes and rely on global network topology information based on shortest paths, leading to relatively time-consuming calculations of the influence of distant stations on station importance. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of the site importance assessment method provided in an embodiment of the present invention;

[0042] Figure 2a This is a schematic diagram of a public transport network structure provided in an embodiment of the present invention;

[0043] Figure 2bA schematic diagram of a subway network structure provided in an embodiment of the present invention;

[0044] Figure 2c This is a schematic diagram of a bus-subway dual-layer network structure provided in an embodiment of the present invention;

[0045] Figure 3a This is a schematic diagram of the node network structure provided in an embodiment of the present invention;

[0046] Figure 3b This is a schematic diagram of the line network structure provided in an embodiment of the present invention;

[0047] Figure 3c This is a schematic diagram of a bipartite graph network structure provided in an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of the node network community division and community center node selection structure provided in an embodiment of the present invention;

[0049] Figure 5 This is a schematic diagram of the site importance assessment method provided in Embodiment 1 of the present invention;

[0050] Figure 6 This is a schematic diagram of the algorithm flow included in the site importance assessment method provided in Embodiment 1 of the present invention;

[0051] Figure 7 This is a schematic diagram of the site importance assessment device provided in an embodiment of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Figure 1 An exemplary schematic diagram of the site importance assessment method provided in an embodiment of the present invention is shown, such as... Figure 1 As shown, the method mainly includes the following steps:

[0054] Step 101: Construct a bus-subway dual-layer network based on the bus network and the subway network, and then construct a node network, a route network, and a bipartite graph network in sequence based on the bus-subway dual-layer network.

[0055] Step 102: Determine the community structure and community center nodes of the node network according to the community mining algorithm; connect the newly added community center nodes in the node network to form an enhanced node network; determine the preliminary importance of each second node based on the authority value and hub value of the second nodes included in the node network;

[0056] Step 103: Determine the preliminary importance of each third node based on its authority and hub values.

[0057] Step 104: Based on the bipartite graph network, the preliminary importance of each second node, and the preliminary importance of each third node, determine the final importance of the second nodes included in the node network.

[0058] Urban public transportation is a crucial component of urban infrastructure, playing a decisive role in stable traffic operation and sustained economic development. Urban rail transit and urban buses, as major components of urban public transportation, are not isolated systems but are interconnected through transfer stations. They typically complement each other in meeting residents' daily travel needs, effectively improving the transmission efficiency of the transportation system. Therefore, in this embodiment of the invention, a two-layer bus-subway network is constructed based on transfer stations, operating routes, and passenger flow information. This network characterizes the interaction between urban buses and urban rail transit, delineates the connection density of stations based on route information, and describes the time-varying characteristics of station passenger flow.

[0059] Before step 101, it is necessary to introduce the bus and subway networks. Specifically, Table 1 shows examples of Shanghai Transportation Smart Card swipe data for the subway used in the test, and Table 2 shows examples of Shanghai Transportation Smart Card swipe data for buses. Table 3 shows the scale of the Shanghai subway and bus networks used in the test.

[0060] Table 1. Example of Shanghai Transportation Smart Card Swiping Data (Metro).

[0061]

[0062] Table 2. Example of Shanghai Transportation Smart Card Swiping Data (Bus).

[0063]

[0064] Table 3. Scale of Shanghai's subway and bus networks.

[0065]

[0066] Furthermore, based on the input bus route map and card swipe data, the bus network can be determined. For example, such as... Figure 2aAs shown in the diagram, the public transportation network consists of 5 stops and 3 operating routes. Specifically, the multiple bus stops included in the diagram are abstracted into bus nodes with a total number of stops. The public transportation network, in which the public transportation network is The set of bus nodes is It corresponds to a bus stop, such as a bus stop. With bus nodes Correspondingly; the bus stop is the gathering point.

[0067] It represents the connection relationship between adjacent bus nodes on the same route, such as bus nodes and There are lines Therefore, there is a bus stop. The set of attributes for bus nodes is: n-dimensional node load vector Different dimensions record the nodes Historical passenger flow totals on different dates; bus node attribute data is derived from card swipe data; bus route attribute set is... Bus route attributes Indicates from the bus side Connected bus nodes and bus nodes A collection of bus routes between them. For example, bus routes and Also serves as a bus stop and public transportation Providing travel services, therefore, bus route attributes .

[0068] Furthermore, based on the input subway map and card swipe data, the subway network can be determined. For example, Figure 2b The subway system shown consists of 5 stations and 2 lines. Specifically, the multiple subway stations included in the diagram are abstracted into a number of subway nodes. The subway network, in which the subway network is The set of subway nodes is It corresponds to subway stations, such as subway stations. With bus nodes Correspondingly; the meeting point is located next to the subway. It represents the connection relationship between adjacent subway nodes on the same line, such as subway nodes. and There are lines Therefore, there is a bus stop. ;

[0069] Metro node attribute set n-dimensional node load vector Different dimensions record the nodes The historical passenger flow totals for different dates, and the subway node attribute data are derived from passenger card swiping data;

[0070] The set of subway line attributes is Subway line attributes Indicates from the subway side Connected subway nodes and subway nodes A collection of bus routes between them. For example, subway routes. and Also serves as a bus stop and public transportation Providing travel services, therefore, bus route attributes .

[0071] In step 101, based on the already constructed bus network and subway network, a bus-subway dual-layer network is further constructed. The number of first nodes included in the bus-subway dual-layer network is equal to the sum of the number of bus nodes and the number of subway nodes, i.e., the set of first nodes is represented as... The set of first edges, after the number of edges equals the number of bus edges, subway edges, and transfer edges, is represented as: , and These are the bus edge set included in the public transport network and the subway edge set included in the subway network. This represents the set of transfer edges, recording inter-layer connections to characterize the interaction relationships between different transportation systems. Further, in this embodiment of the invention, it is defined that when the geographical distance between a bus node in the public transport network and a subway node in the subway network is less than a threshold D = 200m, an inter-layer connection between the public transport network and the subway network can be determined. The number of attributes of the first node is equal to the sum of the attributes of the bus node and the subway node, i.e., the first node set is represented as... The number of first-line attributes is equal to the sum of bus route attributes and subway route attributes; that is, the first-line set is represented as... In this embodiment of the invention, the bus-subway two-layer network is represented as follows: .

[0072] In practical applications, the bus-subway dual-layer network has various node types, making it difficult to describe the calculation process for node importance. Therefore, while maintaining the dual-layer network topology, the nodes are renumbered to form a node network. In this embodiment of the invention, as... Figure 3a The node network is represented as follows: The second set of nodes is represented as It is relative to the first node included in the bus-subway dual-layer network; the second edge set is represented as It includes the second edge corresponding to the set of first edges included in the bus-subway two-layer network; the second node attribute set is represented as It includes the second node attributes corresponding to the first node attributes included in the bus-subway two-layer network; the first edge weight set is represented as The weight of the first edge is used to characterize the tightness of the connection between the second nodes. For example, if... The corresponding second side belongs to the set or ,So or In other words, the weight of the second side represents the number of operating lines between the second nodes.

[0073] Furthermore, to accurately characterize the synergistic effect between the first line and the first station in the bus-metro dual-layer network, the importance of the first line is first measured based on the line connectivity. Specifically, such as... Figure 3b As shown, the C-space method is used to extract data from a two-layer bus-subway network. The network of lines with three third nodes, i.e., the network of lines is represented as follows: The set of third nodes is represented as For example, nodes Corresponding route The third side set is represented as If the operating line and If at least one service is provided to the same site, then an edge exists. In addition, if the operating line and If two or more vehicles belong to different transportation systems but have transfer stations, then there is also a boundary. The set of weights on the second side is represented as follows: , Indicates the line and The number of shared sites.

[0074] Furthermore, such as Figure 3c As shown, a bipartite graph network, including the first node and the first line, is constructed based on the B-space method in a two-layer bus-subway network. The bipartite graph network is represented as follows: The set of fourth nodes is represented as It contains two types of nodes: second nodes and third nodes. The second nodes correspond to bus stops or subway stations, and the third nodes correspond to operating routes. The fourth edge set is represented as... The third weight set is represented as For example, if an operational route passes through a fourth node, then there is an edge connecting the corresponding third node and the second node. In other words, if the third node... Passing through the second node Or through the second node If one can transfer to another transportation system, then there exists an edge. and ,otherwise .

[0075] In step 102, after determining the node network and the path network through the above steps, the iterative process of the second node and its direct neighbors is utilized for the node network. Although the importance of the second node is indirectly affected by distant second nodes due to the iterative process, this influence is not fully characterized. To fully reveal the role of the global structure of the node network, making the importance of the second node more susceptible to the influence of distant second nodes, and avoiding characterizing the role of distant second nodes based on time-consuming shortest path algorithms, this embodiment of the invention enhances the influence of distant second nodes on the evaluation of the importance of the second node by adding a small number of edges to the node network. Therefore, the node network is determined using the Louvain community mining algorithm. The community structure is shown in formula (1):

[0076] (1)

[0077] in, Let q represent the q-th community, where q represents the number of community structures. In practical applications, each community may include several second nodes.

[0078] After determining the community structure, in this embodiment of the invention, the community center node that can represent the entire community is calculated based on the attributes of the second nodes. Specifically, firstly, the average value of the attributes of all second nodes within the community is used as the community vector of the community, and then the second node closest to the community vector, i.e., the community center node, is determined based on similarity. The community center node is determined by the following formula (2):

[0079] (2)

[0080] in, Represents a node network Second node The attributes, Indicates club The average value of the attributes of each second node within the node. , This represents the q-th club. q represents the community structure of the node network, where each community structure includes multiple second nodes, and q represents the number of community structures.

[0081] It should be noted that, since the second node attribute characterizes the time-varying passenger flow features of each corresponding station, the community center node is the node that best represents the average passenger flow of the community, and can well represent the entire community from a passenger flow perspective. Finally, the community center nodes are interconnected to obtain an enhanced node network.

[0082] Furthermore, the enhanced node network determines the initial importance of each second node. In determining the initial importance of the second node, the importance of the second node is divided into an authority value and a hub value. The authority value and hub value of the second node are shown in the following formula (3):

[0083] (3)

[0084] In formula (3), Indicates the second node The authority value in the t-th iteration, Indicates the second node In the t-th iteration, the initial values ​​of the pivot value, authority value, and pivot value are all 1; Indicates the second node The pivot value in the (t-1)th iteration, This represents the total number of second nodes included in the node network. Represents the second edge in a node network. The first weight;

[0085] After the authority value and hub value of the second node are completed in the t-th iteration, the second node... The initial importance As shown in formula (4):

[0086] (4)

[0087] like Figure 4 As shown, the node network is divided into , and Three clubs, at the central node connecting their clubs , and Then, the second node It only takes 2 iterations to process the nodes. It has an effect, whereas previously it would take four iterations to affect a node. The importance of.

[0088] In step 103, based on the above method of determining the preliminary importance of the second node included in the node network, the importance of the third node included in the line network is also divided into authority value and hub value. The authority value and hub value of the third node are shown in the following formula (5):

[0089] (5)

[0090] In formula (5), Indicates the third node The authority value in the t-th iteration, Indicates the third node In the t-th iteration, the initial values ​​of the pivot value, authority value, and pivot value are all 1; Indicates the third node The pivot value in the (t-1)th iteration, This indicates the total number of third nodes included in the network. Indicates the third node The pivot value in the t-th iteration, Indicates the third edge in the circuit network The second weight.

[0091] After the third node's authority value and hub value have completed the t-th iteration, the third node... The initial importance As shown in formula (6):

[0092] (6)

[0093] In step 104, based on the initial importance of the second node, the final importance of the second node in the node network is determined through the mutual reinforcement relationship between the second node included in the node network and the third node included in the line network, as shown in formula (7):

[0094] (7)

[0095] in, This represents the second node at the t-th iteration. Ultimate importance, Indicates the second node in the node network The second importance in the (t-1)th iteration It is a hyperparameter that balances the tightness of connections and mutual reinforcement between the second nodes. Represents the fourth edge in a bipartite graph network. The third weight, This represents the third node in the (t-1)th iteration. The second importance, , Indicates the third node in the line network. Second importance in the (t-2)th iteration; This represents the total number of third nodes in the network. This represents the total number of second nodes included in the node network. This represents the second node in the (t-1)th iteration. Second importance.

[0096] Figure 5 This is a schematic diagram of the site importance assessment method provided in Embodiment 1 of the present invention; Figure 6 This is a schematic diagram of the algorithm flow included in the site importance assessment method provided in Embodiment 1 of the present invention; to more clearly introduce the site importance assessment method provided in the embodiments of the present invention, the following will use... Figure 5 Example combination Figure 6 This method will be described in detail.

[0097] like Figure 5 As shown, the method includes the following steps:

[0098] S1: Input bus and subway route maps and card swipe data; In this embodiment of the invention, the importance of all stations in Shanghai Rail Transit has been assessed, so the input card swipe data is Shanghai Transportation Smart Card swipe data.

[0099] S2: Construct a two-tier bus-subway network; first, construct the number of bus nodes based on the bus network. The public transportation network, in which the public transportation network is The set of bus nodes is Meet at the bus stop The set of attributes for bus nodes is The set of bus route attributes is .

[0100] Then, construct the subway node number as follows: The subway network, in which the subway network is The set of subway nodes is The set of attributes for subway nodes is Meet at the subway station The set of subway line attributes is .

[0101] Finally, based on the existing bus and subway networks, a two-tiered bus-subway network will be further constructed, such as... Figure 6 This includes a double-decker bus-subway network. The double-decker bus-subway network is... The first node set is represented as The first edge set is represented as The first node's attribute set is represented as The first set of line attributes is represented as .

[0102] S3: Build a node network, such as Figure 6 The included node network is represented as The second set of nodes is represented as The second side set is represented as The second node attribute set is represented as The first edge weight set is represented as .

[0103] S4: Construct a bipartite graph network. Based on the B-space method, construct a bipartite graph network including the first node and the first line in a two-layer bus-subway network, such as... Figure 6 Includes bipartite graph networks, which are represented as follows: The fourth node set is represented as The fourth side set is represented as The third weight set is represented as .

[0104] S5: Construct the route network and use the C-space method to extract the relevant information from the bus-subway two-layer network. The network of lines for a third node, i.e., constructing the network of lines, such as Figure 6 The included line network is represented as The set of third nodes is represented as The third side set is represented as .

[0105] S6: Computational node network community structure. The node network is determined using the Louvain community mining algorithm. The community structure is shown in formula (1).

[0106] S7: Calculate and connect the community center node. First, use the average attribute of all second nodes within the community as the community vector. Then, determine the second node closest to the community vector based on similarity; this is the community center node. In other words, the community... Community Center Node The node most similar to the average attribute of all nodes within the community is the solution to formula (2). After determining the community's central node, they are connected to each other to quickly obtain the importance influence of distant nodes. The reason why the method provided in this embodiment of the invention can quickly obtain the importance influence of distant nodes is that it no longer relies on the traditional shortest path algorithm with a time complexity of O(n³), but uses the Louvain algorithm with a time complexity of only O(m), where n and m represent the number of nodes and the number of edges in the network, respectively.

[0107] S8: Calculate the initial importance of nodes based on the node network. The importance of a node is determined by its direct neighbors based on the local information of the network topology, and the influence of different neighbors on the importance of a node is evaluated based on the connection density between nodes characterized by the operating route. Similar to the HITs algorithm, in this embodiment of the invention, the importance value of the second node is divided into an authority value and a hub value, and then the importance of the second node is finally determined by the mutual iteration process of these two values. The authority value and hub value of each second node are shown in formula (3), and then the importance of the second nodes included in the node network is determined by the iterative process, and the iterative formula is shown in formula (4).

[0108] S9: Calculate the importance of a route based on the route network. Similar to the preliminary calculation of the importance of the second node included in the station network, the importance value of the third node included in the route network is divided into an authority value and a hub value as shown in formula (5). Then, the importance of the third node included in the route network is determined by an iterative process, and the iterative formula is shown in formula (6).

[0109] S10: Calculate the final importance of the second node based on the bipartite graph. Based on the preliminary importance of the second node and the preliminary importance of the third node, the final importance of the second node is determined by the mutual reinforcement relationship between the node network and the line network. The determination formula is shown in (7).

[0110] S11: Output the final importance of the second node. After determining the final importance of the second node according to formula (7), it is necessary to determine whether the convergence condition has been met. If the convergence condition has been met, the final importance of the second node determined by formula (7) will be output. If the convergence condition has not been met, further iteration is required until the convergence condition is met.

[0111] In summary, this invention provides a method and apparatus for assessing the importance of stations. It constructs a two-layer bus-subway network for urban public transportation systems, characterizes the interaction relationships between different transportation systems through inter-layer edges, records historical passenger flow totals for different dates using node attributes, and records operating routes passing through those edges using edge attributes. Addressing the issue that existing methods often focus less on operating routes, this invention uses the number of operating routes to characterize the importance influence between neighboring stations and uses a bipartite graph network to characterize the mutual reinforcement relationship between operating routes and stations. Addressing the problem that existing methods typically rely on time-consuming shortest path algorithms to characterize the influence of distant nodes, this invention first identifies network community structures using community mining technology, then determines community center nodes that represent all nodes within the community based on node attributes, and finally uses a small number of community center nodes to quickly obtain the importance influence of distant nodes. This solves the problem that existing methods for assessing station importance fail to fully reflect operating routes and rely on global network topology information based on shortest paths, leading to relatively time-consuming calculations of the influence of distant stations on station importance.

[0112] Based on the same inventive concept, this invention provides a site importance assessment device. Since the principle of this device in solving the technical problem is similar to that of the site importance assessment method, the implementation of this device can refer to the implementation of the method, and the repeated parts will not be described again.

[0113] Figure 7 This is a schematic diagram of the site importance assessment device provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the device mainly includes: a construction unit 201, a first determination unit 202, a second determination unit 203 and a third determination unit 204.

[0114] Construction unit 201 is used to construct a bus-subway dual-layer network based on the bus network and the subway network, and to construct a node network, a route network and a bipartite graph network in sequence based on the bus-subway dual-layer network.

[0115] The first determining unit 202 is used to determine the community structure and community center nodes of the node network according to the community mining algorithm, connect the multiple newly added community center nodes in the node network to form an enhanced node network, and determine the preliminary importance of each second node based on the authority value and hub value of the second nodes included in the node network.

[0116] The second determining unit 203 is used to determine the preliminary importance of each third node based on the authority value and hub value of the third nodes included in the line network.

[0117] The third determining unit 204 is used to determine the final importance of the second nodes included in the node network based on the bipartite graph network, the preliminary importance of each second node, and the preliminary importance of each third node.

[0118] Preferably, the bus-subway dual-layer network is The first set of nodes is The first set of edges is The first node's attribute set is The first set of routes is ;

[0119] in, , , , , , For bus stops; , , , , It is a subway node.

[0120] Preferably, the community center node is determined using the following formula:

[0121]

[0122] in, Represents a node network Second node The attributes, Indicates club The average value of the attributes of each second node within the node. , This represents the q-th club. q represents the community structure of the node network, where each community structure includes multiple second nodes, and q represents the number of community structures.

[0123] Preferably, the initial importance of each second node is determined using the following formula: ;

[0124] The initial importance of each third node is determined using the following formula: ;

[0125] in, , , Indicates the second node The pivot value in the (t-1)th iteration, Indicates the second node The authority value in the t-th iteration, Indicates the second node The pivot value in the t-th iteration, This represents the total number of second nodes included in the node network. Represents the second edge in a node network. The first weight; , ,

[0126] Indicates the third node The pivot value in the (t-1)th iteration, This indicates the total number of third nodes included in the network. Indicates the third node The authority value in the t-th iteration, Indicates the third node The pivot value in the t-th iteration, Indicates the third edge in the circuit network The second weight.

[0127] Preferably, the final importance of the second node included in the node network is determined by the following formula: ;

[0128] in, This represents the second node at the t-th iteration. Ultimate importance, Indicates the second node in the node network The second importance in the (t-1)th iteration It is a hyperparameter that balances the tightness of connections and mutual reinforcement between the second nodes. Represents the fourth edge in a bipartite graph network. The third weight, This represents the third node in the (t-1)th iteration. The second importance, , Indicates the third node in the line network. Second importance in the (t-2)th iteration; This represents the total number of third nodes in the network. This represents the total number of second nodes included in the node network. This represents the second node in the (t-1)th iteration. Second importance.

[0129] It should be understood that the units included in the above site importance assessment device are only a logical division based on the functions implemented by the device. In practical applications, the above units can be superimposed or split. Furthermore, the functions implemented by the site importance assessment device provided in this embodiment correspond one-to-one with the site importance assessment methods provided in the above embodiments. The more detailed processing flow implemented by the device has been described in detail in the first embodiment of the method above, and will not be described in detail here.

[0130] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0131] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method of assessing the importance of a site, characterized by, Comprise: According to the input bus line map and the card swiping data, a bus network is determined; according to the input subway line map and the card swiping data, a subway network is determined; a bus-subway double-layer network is constructed according to the bus network and the subway network, wherein the bus-subway double-layer network is , the first node set is , the first edge set is , the first node attribute set is , the first line set is ; wherein , , , , , is a bus node; , , , , is a subway node; According to the bus-metro double-layer network, a node network is formed after renumbering the nodes under the premise of keeping the double-layer network topology unchanged; the node network is represented as wherein the second node set is represented as which is opposite to the first node included in the bus-metro double-layer network; the second edge set is represented as which includes the second edge corresponding to the first edge set included in the bus-metro double-layer network; the second node attribute set is represented as which includes the second node attribute corresponding to the first node attribute included in the bus-metro double-layer network; and the first edge weight set is represented as the first edge weight is used to depict the closeness degree of the connection between the second nodes. A line network with third nodes is extracted from the bus-metro double-deck network using the C-space method The line network is represented as where the third node set is represented as ; constructing a bipartite network including the first node and the first line in the bus-metro double-layer network based on a B-space method; the bipartite network is represented as , wherein a fourth node set is represented as , including two types of second nodes and third nodes, the second nodes corresponding to bus stations or subway stations, and the third nodes corresponding to operating lines, a fourth edge set is represented as , and a third weight set is represented as ; Determine the community structure of the node network through a community mining algorithm, and determine the community center node through the following formula: in, Represents a node network Second node The attributes, Indicates club The average value of the attributes of each second node within the node. , This represents the q-th club. The node network represents a community structure, where each community structure includes multiple second nodes, and q represents the number of community structures. Multiple newly added community center nodes are connected to form an enhanced node network. Based on the authority and hub values ​​of the second nodes in the node network, the initial importance of each second node is determined using the enhanced node network. The initial importance of each second node is determined using the following formula: ; The preliminary importance of each third node is determined by the following equation: ; wherein , , denotes a second node pivot value at iteration t-1, denotes a second node authority value at iteration t, denotes a second node pivot value at iteration t, denotes the total number of second nodes comprised by the network of nodes, denotes a first weight of a second edge in the network of nodes; , , denotes a third node the pivot value at iteration t-1, denotes the total number of third nodes comprised by the line network, denotes a third node the authority value at iteration t, denotes a third node the pivot value at iteration t, denotes a second weight of a third edge in the line network; determining a final importance of the second nodes comprised in the network of nodes according to the bipartite network, the preliminary importance of each second node and the preliminary importance of each third node; the final importance of the second nodes comprised in the network of nodes is determined by the following formula: ; in, This represents the second node in the t-th iteration. Ultimate importance, Indicates the second node in the node network The second importance in the (t-1)th iteration It is a hyperparameter that balances the tightness of connections and mutual reinforcement between the second nodes. Represents the fourth edge in a bipartite graph network. The third weight, This represents the third node in the (t-1)th iteration. The second importance, , Indicates the third node in the line network. Second importance in the (t-2)th iteration; This represents the total number of third nodes in the network. This represents the total number of second nodes included in the node network. This represents the second node in the (t-1)th iteration. Second importance.

2. The station importance evaluation apparatus characterized by comprising: Comprise: The constructing unit is configured to determine a bus network according to an input bus line map and card swiping data, determine a subway network according to an input subway line map and card swiping data, and construct a bus-subway double-layer network according to the bus network and the subway network, wherein the bus-subway double-layer network is , the first node set is , the first edge set is , the first node attribute set is , the first line set is ; wherein , , , , , is a bus node; , , , , is a subway node; according to the bus-subway double-layer network, a node network is formed after renumbering the nodes under the premise of keeping the double-layer network topology unchanged; the node network is represented as , wherein the second node set is represented as , which is opposite to the first node included in the bus-subway double-layer network; the second edge set is represented as , which includes the second edge corresponding to the first edge set included in the bus-subway double-layer network; the second node attribute set is represented as , which includes the second node attribute corresponding to the first node attribute included in the bus-subway double-layer network; the first edge weight set is represented as , the first edge weight is used to depict the closeness degree of connection between the second nodes; a line network with third nodes is extracted from the bus-subway double-layer network by using a C-space method; the line network is represented as , wherein the third node set is represented as ; a bipartite graph network including the first node and the first line in the bus-subway double-layer network is constructed based on a B-space method; the bipartite graph network is represented as , wherein the fourth node set is represented as , containing two types of second nodes and third nodes, the second nodes corresponding to bus stations or subway stations, and the third nodes corresponding to operating lines; the fourth edge set is represented as , and the third weight set is represented as ; The first determination unit is configured to determine the community structure of the node network through a community mining algorithm, and determine the community center node through the following formula: in, Represents a node network Second node The attributes, Indicates club The average value of the attributes of each second node within the node. , This represents the q-th club. The node network represents a community structure, where each community structure includes multiple second nodes, and q represents the number of community structures. Multiple newly added community center nodes are connected to form an enhanced node network. Based on the authority and hub values ​​of the second nodes in the node network, the initial importance of each second node is determined using the enhanced node network. The initial importance of each second node is determined using the following formula: ; The second determining unit is configured to determine the preliminary importance of each third node according to the following formula: ; wherein, , , denotes a second node pivot value at iteration t-1, denotes a second node authority value at iteration t, denotes a second node pivot value at iteration t, denotes the total number of second nodes comprised by the network of nodes, denotes a first weight of a second edge in the network of nodes; , , denotes a third node the pivot value at iteration t-1, denotes the total number of third nodes comprised by the line network, denotes a third node the authority value at iteration t, denotes a third node the pivot value at iteration t, denotes a second weight of a third edge in the line network; The third determining unit is configured to determine the final importance of the second nodes included in the node network according to the bipartite network, the preliminary importance of each second node and the preliminary importance of each third node; and the final importance of the second nodes included in the node network is determined by the following formula: ; in, This represents the second node in the t-th iteration. Ultimate importance, Indicates the second node in the node network The second importance in the (t-1)th iteration It is a hyperparameter that balances the tightness of connections and mutual reinforcement between the second nodes. Represents the fourth edge in a bipartite graph network. The third weight, This represents the third node in the (t-1)th iteration. The second importance, , Indicates the third node in the line network. Second importance in the (t-2)th iteration; This represents the total number of third nodes in the network. This represents the total number of second nodes included in the node network. This represents the second node in the (t-1)th iteration. Second importance.

Images