Method and System for Selecting Passenger Flow Monitoring Points at Stations Based on Complex Networks

Abstract

The present invention provides a method and system for selecting passenger flow monitoring points at stations based on complex networks, belonging to the technical field of safety management of rail transit stations. A passenger flow distribution network of the station is constructed; based on the constructed passenger flow distribution network of the station, centrality indexes of network nodes are calculated, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality; based on the constructed passenger flow distribution network of the station, combined with the calculated centrality indexes of network nodes, an optimization model for selecting passenger flow monitoring nodes is constructed; the constructed optimization model for selecting passenger flow monitoring nodes is solved to obtain a selection scheme for passenger flow monitoring points at the station. By analyzing the passenger flow distribution network of the station, the present invention realizes indexes representing the differences in passenger flow distribution monitoring requirements, constructs a model and method for selecting passenger flow monitoring points at the station, and helps to establish a scientific and effective passenger flow monitoring system for the station.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit station safety management, and particularly relates to a method and system for selecting passenger flow monitoring points in a station based on complex networks. Background Art

[0002] Passenger flow monitoring devices play an important role in ensuring passenger safety and improving the operation efficiency of stations. Passenger flow monitoring devices first provide key data support for the work arrangement of station staff by monitoring the passenger flow situation of the station in real time, helping the staff make reasonable and correct decisions. However, there are still some problems in the layout of passenger flow monitoring devices:

[0003] (1) Incomplete monitoring range: At present, there are obvious limitations in the layout and coverage range of passenger flow monitoring devices in some stations. The layout of monitoring devices often only targets individual entrances and exits and other areas, so not all areas and channels can be monitored for real-time and accurate passenger flow data, thus affecting the comprehensive analysis and accurate judgment of the overall passenger flow situation;

[0004] (2) Low data accuracy: The effect of passenger flow monitoring data is affected by the monitoring range and the accuracy of monitoring devices. The detection range refers to whether the covered area can specifically reflect the passenger flow situation in that area, and the detection accuracy refers to that when the coverage range is within the device's capabilities, the detection accuracy is relatively high, otherwise it is relatively low. Therefore, if better monitoring effects are desired, both the detection range and the monitoring accuracy need to be considered;

[0005] (3) Chaotic layout: The positions of monitoring devices are not reasonably planned, resulting in occlusion or overlap between devices, affecting the accuracy and efficiency of data collection. Due to uneven distribution and chaotic layout of devices, blind spots in monitoring may occur, and it is impossible to comprehensively obtain the passenger flow information in the station. To solve this problem, the positions of devices should be scientifically planned to ensure that the coverage ranges of each monitoring point are complementary and do not overlap, improving the efficiency and accuracy of data collection;

[0006] The function of monitoring devices is to monitor the basic situations such as the passenger flow situation in the station and whether there are emergencies. For different monitoring situations with different emphases, the layout of monitoring devices is also different. The location selection of monitoring devices should be based on the differences in passenger flow monitoring requirements to obtain different layout schemes for passenger flow monitoring devices. Summary of the Invention

[0007] The purpose of the present invention is to provide a method for selecting passenger flow monitoring points in a station based on complex networks to solve at least one of the technical problems existing in the above background art.

[0008] To achieve the above purpose, the present invention adopts the following technical solutions:

[0009] In a first aspect, the present invention provides a method for selecting passenger flow monitoring points based on complex networks, including:

[0010] Construct a passenger flow concentration and dispersion network based on the passenger flow streamline of the station;

[0011] Based on the constructed passenger flow concentration and dispersion network of the station, calculate the centrality indicators of the network nodes, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality;

[0012] Based on the constructed passenger flow concentration and dispersion network of the station, and in combination with the calculated centrality indicators of the network nodes, construct an optimization model for selecting passenger flow monitoring nodes;

[0013] Solve the constructed optimization model for selecting passenger flow monitoring nodes to obtain a selection plan for passenger flow monitoring points of the station.

[0014] Further, the passenger flow degree centrality is obtained by weighted calculation considering the influence of passenger flow volume on the basis of the calculation method of the degree centrality of ordinary node structures. The calculation formula for the passenger flow degree centrality D(i) of node i in the passenger flow concentration and dispersion network of the station is as follows:

[0015] D(i) = ∑ i≠j x ij Q(i);

[0016] Wherein, D(i) is the passenger flow degree centrality of node i; Q(i) is the passenger flow volume of node i that can be obtained by monitoring; i, j are nodes in the passenger flow concentration and dispersion network of the station; x ij - Connection variable, taking 1 if i and j are connected, and 0 otherwise.

[0017] Further, the passenger flow betweenness centrality is obtained by considering the influence of passenger flow volume on the basis of the betweenness centrality of the network structure. The calculation formula for the passenger flow betweenness centrality of node i is as follows:

[0018]

[0019] B(i) = B'(i)Q(i)

[0020] In the formula, B'(i) represents the structure betweenness centrality of node i; B(i) represents the betweenness centrality of node i after weighting by passenger flow volume; Q(i) represents the passenger flow volume of node i that can be obtained by monitoring equipment; i, t, s represent nodes in the passenger flow concentration and dispersion network diagram of the station; I represents the set of all nodes in the passenger flow concentration and dispersion network diagram of the station; σ st represents the number of shortest paths from node s to node t; σ st (i) represents the number of shortest paths from node s to node t that pass through point i.

[0021] Further, the closeness centrality value of a node represents the degree of the node being "close to the central position" in the network structure. Considering the influence of passenger flow, the calculation formula for the passenger flow closeness centrality of a node is as follows:

[0022] C′(i) = (N - 1) / ∑d(i, j)

[0023] C(i) = C′(i)Q(i)

[0024] In the formula, C′(i) represents the structural closeness centrality value of node i; C(i) represents the closeness centrality of node i after weighted by passenger flow; Q(i) represents the passenger flow of node i that can be obtained by the monitoring device; i represents a node in the network diagram; N represents the number of nodes; d(i, j) represents the shortest path length between node i and node j; ∑d(i, j) represents the sum of the shortest path lengths from node i to all other nodes (j) in the network.

[0025] Further, combining the passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality, the specific evaluation calculation formula for the passenger flow monitoring effect is as follows:

[0026]

[0027] In the formula, M represents the passenger flow monitoring effect; N represents the number of nodes; represents the weight parameter of the passenger flow degree centrality; represents the weight parameter of the passenger flow betweenness centrality; represents the weight parameter of the passenger flow closeness centrality; In order to be able to measure on the same scale, are respectively the normalized passenger flow degree centrality, betweenness centrality, and closeness centrality.

[0028] Further, the established optimization model for the location selection of passenger flow monitoring nodes is:

[0029] Objective function: max M

[0030] Constraint condition: y i p i ≤H

[0031] In the formula, y i represents the decision variable. If node i is selected to install the monitoring facility, then y i = 1, otherwise it takes 0; p i - the cost of installing the passenger flow monitoring device at node i; H - the total budget for the installation of the passenger flow monitoring device.

[0032] In the second aspect, the present invention provides a system for the location selection of passenger flow monitoring points based on a complex network, including:

[0033] The first construction module is used to construct the passenger flow distribution network of the station;

[0034] A first calculation module, configured to calculate centrality indexes of network nodes based on the constructed passenger flow distribution network at stations, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality;

[0035] A second construction module, configured to construct an optimization model for the location selection of passenger flow monitoring nodes based on the constructed passenger flow distribution network at stations and in combination with the calculated centrality indexes of network nodes;

[0036] A second calculation module, configured to solve the constructed optimization model for the location selection of passenger flow monitoring nodes to obtain a location selection scheme for passenger flow monitoring points at stations.

[0037] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the method for the location selection of passenger flow monitoring points at stations based on a complex network as described in the first aspect is implemented.

[0038] In a fourth aspect, the present invention provides a computer device, including a memory and a processor. The processor and the memory communicate with each other. The memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for the location selection of passenger flow monitoring points at stations based on a complex network as described in the first aspect.

[0039] In a fifth aspect, the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the method for the location selection of passenger flow monitoring points at stations based on a complex network as described in the first aspect.

[0040] Advantages of the present invention: By analyzing the passenger flow distribution network at stations, indexes representing the differences in passenger flow distribution monitoring requirements are realized, and an optimization model and method for the location selection of passenger flow monitoring points at stations are constructed, which helps to establish a scientific and effective passenger flow monitoring system at stations.

[0041] Advantages of additional aspects of the present invention will be more clearly given in the following description part, or can be understood through the practice of the present invention. Description of the Drawings

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 Flowchart of the method for selecting passenger flow monitoring points at stations based on complex networks according to the embodiments of the present invention.

[0044] Figure 2 Schematic diagram of the CQDZ outbound transfer layer network according to the embodiments of the present invention.

[0045] Figure 3 Schematic diagram of the site selection scheme mainly for monitoring passenger flow conflicts according to the embodiments of the present invention.

[0046] Figure 4 Schematic diagram of the site selection scheme mainly for monitoring passenger flow directions according to the embodiments of the present invention.

[0047] Figure 5 Schematic diagram of the site selection scheme mainly for evaluating network convenience according to the embodiments of the present invention. Detailed implementation manners

[0048] The following details the implementation manners of the present invention. Examples of the implementation manners are shown in the drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The implementation manners described through the drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0049] Those skilled in the art of the present technology can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the art in the field to which the present invention belongs.

[0050] It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art and will not be interpreted with an idealized or overly formal meaning unless defined as such herein.

[0051] Those skilled in the art of the present technology can understand that, unless specifically stated, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the description of the present invention means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or their groups.

[0052] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. Without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0053] For ease of understanding the present invention, the following will further explain the present invention with specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation to the embodiments of the present invention.

[0054] Those skilled in the art should understand that the drawings are only schematic diagrams of the embodiments, and the components in the drawings are not necessarily essential for implementing the present invention.

[0055] Embodiment 1

[0056] In this Embodiment 1, first, a station passenger flow monitoring point location system based on a complex network is provided. The system includes: a first construction module for constructing a station passenger flow distribution network; a first calculation module for calculating the centrality indexes of network nodes based on the constructed station passenger flow distribution network, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality; a second construction module for constructing an optimization model for the location of passenger flow monitoring nodes based on the constructed station passenger flow distribution network and in combination with the calculated centrality indexes of network nodes; and a second calculation module for solving the constructed optimization model for the location of passenger flow monitoring nodes to obtain a location plan for station passenger flow monitoring points.

[0057] In this embodiment, using the above system, a method for locating station passenger flow monitoring points based on a complex network is realized, including: using the first construction module to construct a station passenger flow distribution network; using the first calculation module to calculate the centrality indexes of network nodes based on the constructed station passenger flow distribution network, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality; using the second construction module to construct an optimization model for the location of passenger flow monitoring nodes based on the constructed station passenger flow distribution network and in combination with the calculated centrality indexes of network nodes; and using the second calculation module to solve the constructed optimization model for the location of passenger flow monitoring nodes to obtain a location plan for station passenger flow monitoring points.

[0058] Constructing the passenger flow concentration and distribution network of the station plays a key role in the layout of passenger flow monitoring facilities. First of all, the passenger flow concentration and distribution network of the station can provide a comprehensive perspective when analyzing the flow lines and selecting monitoring nodes, and can accurately grasp the overall structure and spatial layout of the station. By analyzing the passenger flow lines of the station through the passenger flow concentration and distribution network, the path planning of passengers' activities such as entering the station, leaving the station, and transferring can be better understood, and then the reasonable positions of monitoring facilities can be determined. The passenger flow concentration and distribution network of the station clearly shows the relationships and connection methods of various internal areas of the station, providing a basis for effectively planning the layout of monitoring facilities. Secondly, the passenger flow concentration and distribution network of the station helps to deeply study the activity trajectories and behavioral characteristics of passengers, so as to better understand the needs and characteristics of different passenger flow monitoring.

[0059] In this embodiment, the passenger flow degree centrality is calculated by weighted calculation considering the influence of passenger flow on the basis of the calculation method of the degree centrality of ordinary node structures. The calculation formula for the passenger flow degree centrality D(i) of node i in the passenger flow concentration and distribution network of the station is as follows:

[0060] D(i) = ∑ i≠j x ij Q(i);

[0061] where D(i) is the passenger flow degree centrality of node i; Q(i) is the passenger flow volume of node i that can be obtained by monitoring; i, j are nodes in the passenger flow concentration and distribution network of the station; x ij is the connection variable, taking 1 if i and j are connected, and 0 otherwise.

[0062] The passenger flow betweenness centrality is obtained by considering the influence of passenger flow on the basis of the betweenness centrality of the network structure. The calculation formula for the passenger flow betweenness centrality of node i is as follows:

[0063]

[0064] B(i) = B′(i)Q(i)

[0065] In the formula, B′(i) represents the structural betweenness centrality of node i; B(i) represents the betweenness centrality of node i after weighting by passenger flow; Q(i) represents the passenger flow volume of node i that can be obtained by monitoring equipment; i, t, s represent nodes in the passenger flow concentration and distribution network diagram of the station; I represents the set of all nodes in the passenger flow concentration and distribution network diagram of the station; σ st represents the number of shortest paths from node s to node t; σ st (i) represents the number of shortest paths from node s to node t that pass through point i.

[0066] The closeness centrality value of a node represents the degree of "proximity to the central position" of the node in the network structure. Considering the influence of passenger flow, the calculation formula for the passenger flow closeness centrality of the node is as follows:

[0067] C(i) = (N - 1) / ∑d(i, j)

[0068] C(i) = C′(i)Q(i)

[0069] Wherein, C′(i) represents the structural closeness centrality value of node i; C(i) represents the closeness centrality of node i after weighting by passenger flow; Q(i) represents the passenger flow of node i that can be obtained by the monitoring device; i represents a node in the network diagram; N represents the number of nodes; d(i, j) represents the shortest path length between node i and node j; ∑d(i, j) represents the sum of the shortest path lengths from node i to all other nodes (j) in the network.

[0070] Combining the passenger flow degree centrality, passenger flow betweenness centrality and passenger flow closeness centrality, the specific evaluation calculation formula for the passenger flow monitoring effect is as follows:

[0071]

[0072] Wherein, M represents the passenger flow monitoring effect; N represents the number of nodes; represents the weight parameter of the passenger flow degree centrality; represents the weight parameter of the passenger flow betweenness centrality; represents the weight parameter of the passenger flow closeness centrality; In order to be able to measure on the same field scale, are respectively the normalized passenger flow degree centrality, betweenness centrality and closeness centrality.

[0073] The established optimization model for the location selection of passenger flow monitoring nodes is as follows:

[0074] Objective function: max M

[0075] Constraint condition: y i p i ≤H

[0076] Wherein, y i represents the decision variable. If node i is selected to install the monitoring facility, then y i = 1; otherwise, it takes 0; p i - The cost of installing the passenger flow monitoring device at node i; H - The total budget for the installation of the passenger flow monitoring device.

[0077] If it is necessary to focus on monitoring the conflict situation of the passenger flow at the station, the weight parameter of the passenger flow degree centrality can be set to a relatively high value, that is If it is necessary to focus on monitoring the flow direction and propagation path of the passenger flow at the station, the weight parameter of the passenger flow betweenness centrality can be set to a relatively high value, that is If you want to focus on monitoring the average walking distance and path selection of the passenger flow in the station to evaluate the convenience and efficiency of the network, you can use the passenger flow closeness centrality weight parameter

[0078] Example 2

[0079] In this Example 2, a method for locating passenger flow monitoring points in a station based on complex networks is provided. The problem to be solved is the problem of locating passenger flow monitoring points in a station considering the differences in passenger flow monitoring requirements.

[0080] The station passenger flow monitoring system realizes the monitoring of the passenger flow state in the station. However, the passenger flow state is reflected by different indicators, such as passenger flow conflicts, passenger flow OD flow, and passenger flow passage efficiency, etc. The layout schemes of the station passenger flow monitoring system obtained from different passenger flow monitoring requirements are also different. Therefore, it is necessary to analyze the passenger flow distribution network in the station, propose indicators representing the differences in passenger flow distribution monitoring requirements, and construct a model and method for locating passenger flow monitoring points in the station to help establish a scientific and effective station passenger flow monitoring system.

[0081] The method for locating passenger flow monitoring points in a station based on complex networks described in this embodiment first constructs a passenger flow distribution network in the station according to the passenger flow streamline; then calculates the centrality indicators of network nodes, including; then, constructs an optimization model for locating passenger flow monitoring nodes; finally, proposes a heuristic algorithm for solving the model.

[0082] Step 1: Construct a passenger flow distribution network in the station

[0083] Constructing a passenger flow distribution network in the station plays a key role in the layout of passenger flow monitoring facilities. First of all, the passenger flow distribution network in the station can provide a comprehensive perspective when analyzing the streamline and selecting monitoring nodes, and can accurately grasp the overall structure and spatial layout of the station. By analyzing the passenger flow streamline in the station through the passenger flow distribution network, it is possible to better understand the path planning of passengers in activities such as entering the station, leaving the station, and transferring, and then determine the reasonable positions of monitoring facilities. The passenger flow distribution network in the station clearly shows the relationships and connection methods of various regions inside the station, providing a basis for effectively planning the layout of monitoring facilities. Secondly, the passenger flow distribution network in the station helps to deeply study the activity trajectories and behavior characteristics of passengers, so as to better understand the requirements and characteristics of different passenger flow monitoring.

[0084] Step 2: Evaluation of passenger flow monitoring effect

[0085] According to the passenger flow distribution network, converting the problem of locating passenger flow monitoring facilities into the problem of selecting passenger flow monitoring points is conducive to analyzing the problem and finding the key points. The selection of passenger flow monitoring points mainly considers the differences in indicators such as the passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality of nodes, and proposes a comprehensive evaluation method for passenger flow monitoring effect.

[0086] 2.1 Passenger flow degree centrality

[0087] Degree centrality can also be understood as connection centrality. As the name implies, it is the sum of the direct connections of a node with other nodes in the network diagram. Passenger flow degree centrality is calculated by weighted calculation considering the influence of passenger flow on the basis of the calculation method of the degree centrality of ordinary node structures. The calculation formula for the passenger flow degree centrality D(i) of node i in the station passenger flow distribution network is as follows:

[0088] D(i) = ∑ i≠j x ij Q(i) (1)

[0089] In the formula, D(i) is the passenger flow degree centrality of node i; Q(i) is the passenger flow of node i that can be obtained by monitoring; i, j are nodes in the station passenger flow distribution network; x ij is the connection variable, taking 1 if i and j are connected, and 0 otherwise;

[0090] Since the node passenger flow degree centrality is a comprehensive index to measure the number of connecting edges and passenger flow around the node, arranging monitoring facilities at nodes with high node passenger flow degree centrality helps to monitor the conflict situation of passenger flow in different areas of the station distribution network.

[0091] 2.2 Passenger flow betweenness centrality

[0092] In network analysis, betweenness centrality is an important metric used to measure the control and propagation ability of a node in the network. Similarly, passenger flow betweenness centrality is obtained by considering the influence of passenger flow on the basis of the betweenness centrality of the network structure. The calculation formula for the passenger flow betweenness centrality of node i is as follows:

[0093]

[0094] B(i) = B′(i)Q(i) (3)

[0095] In the formula, B′(i) is the structural betweenness centrality of node i;

[0096] B(i) is the betweenness centrality of node i after weighting by passenger flow;

[0097] Q(i) is the passenger flow of node i that can be obtained by the monitoring equipment;

[0098] i, t, s are nodes in the network diagram;

[0099] I is the set of all nodes in the network diagram;

[0100] σ st is the number of the shortest paths from node s to node t;

[0101] σst (i) - The number of shortest paths from node s to node t passing through point i.

[0102] As can be seen from the calculation method of betweenness centrality, installing passenger flow detection equipment at nodes with relatively high betweenness centrality in terms of passenger flow volume of nodes can better monitor the flow direction and spread of passenger flow. After obtaining the passenger flow volume data of these nodes, the decoupling or passenger flow OD data can be used to further monitor the passenger flow state of the entire passenger flow distribution network of the station.

[0103] 2.3 Passenger Flow Closeness Centrality

[0104] Closeness centrality is an index used to measure the importance of nodes in a network, which takes into account the average shortest distance from a node to other nodes in the network. The closeness centrality value of a node represents the degree of "proximity to the central position" of the node in the network structure. Considering the influence of passenger flow volume, the calculation formula for the passenger flow closeness centrality of a node is as follows:

[0105] C′(i) = (N - 1) / ∑d(i, j) (4)

[0106] C(i) = C′(i)Q(i) (5)

[0107] Where C′(i) - the structural closeness centrality value of node i;

[0108] C(i) - the closeness centrality of node i after weighting by passenger flow volume;

[0109] Q(i) - the passenger flow volume of node i that can be obtained by the monitoring equipment;

[0110] i - a node in the network diagram;

[0111] N - the number of nodes;

[0112] d(i, j) - the shortest path length between node i and node j;

[0113] ∑d(i, j) - the sum of the shortest path lengths from node i to all other nodes (j) in the network.

[0114] The larger the passenger flow degree centrality, the more passenger flow passes through the geometric center node in the distribution network, that is, the closer the average distance of more passenger flow is to other nodes. Therefore, installing monitoring equipment at nodes with high passenger flow closeness centrality can be used to monitor and evaluate the convenience of the passenger flow distribution network of the station.

[0115] 2.4 Passenger Flow Monitoring Effect Evaluation Method

[0116] Based on the above three indicators, the specific evaluation calculation formula for the passenger flow monitoring effect is as follows:

[0117]

[0118] Where M is the passenger flow monitoring effect; N is the number of nodes; - Passenger flow degree centrality weight parameter; - Passenger flow betweenness centrality weight parameter; - Passenger flow closeness centrality weight parameter. In order to be able to measure on the same field scale, are the normalized passenger flow degree centrality, betweenness centrality, and closeness centrality respectively. The calculation methods are as follows:

[0119]

[0120] Step 3: Model establishment

[0121] The selection of passenger flow monitoring points not only considers the passenger flow monitoring effect but is also limited by the construction cost of the passenger flow monitoring system. Therefore, the optimization model for the location selection of passenger flow monitoring nodes established in this paper is as follows:

[0122] Objective function: max M (10)

[0123] Constraint condition: y i p i ≤H (11)

[0124] Where y i - Decision variable. If node i is selected to install monitoring facilities, then y i = 1; otherwise, it takes 0; p i - The cost of installing passenger flow monitoring equipment at node i; H - The total budget for the installation of passenger flow monitoring equipment.

[0125] If it is necessary to focus on monitoring the conflict situation of passenger flow at the station, the value of the passenger flow degree centrality weight parameter can be set relatively high, that is If it is necessary to focus on monitoring the flow direction and propagation path of passenger flow at the station, the value of the passenger flow betweenness centrality weight parameter can be set relatively high, that is If you want to focus on monitoring the average walking distance of passenger flow at the station, the path selection situation, etc., and evaluate the convenience and efficiency of the network, the value of the passenger flow closeness centrality weight parameter

[0126] Case verification

[0127] In this embodiment, a certain city east station (CQDZ) was selected to study the deployment plan of passenger flow monitoring equipment. The study specifically took the CQDZ exit transfer layer as an example for verification. This layer has a total of six exits to the transfer hall. There are four subway entrances in the hall for subway transfers. From the hall, you can transfer to a taxi to the north; to the south, you can transfer to a bus, a long-distance coach, and a direct airport link; to the west, you can go to Kaicheng Road; to the east, you can go to Shujie Road. When drawing the passenger flow distribution network of the exit transfer layer, you first need to determine the relative positions of important nodes such as each exit, subway station entrance, etc. Since this plan will serve as the centrality index of the nodes in the study station and the basic map for the selection of passenger flow monitoring points, it is necessary to draw the paths where there may be passenger flow lines between the nodes in the network diagram. The passenger flow distribution network diagram of the CQDZ exit transfer layer is shown below. Figure 2 shown.

[0128] The nodes represented by the numbers in the boxes in the figure are all at the intersections of passenger flow lines or road forks, etc. The numbers 5, 7, 15, 17, 25, and 27 in the boxes represent the railway passenger exits, and the numbers in the circles represent the passengers' destinations, of which 1, 2, 3, 4, and 5 represent arrival at Shujie Road; 14, 15, 16, 17, and 18 represent arrival at Kaicheng Road; 12, 22, and 32 represent transfer to taxis; 18 and 28 represent transfer to buses; and 0 and 8 represent arrival at city terminals and long-distance bus yards, all of which are classified as long-distance passenger transport. At this point, the station passenger flow distribution network is complete.

[0129] The passenger flow centrality index of each node can be calculated through the adjacency matrix of the station passenger flow distribution network graph. The passenger flow point degree centrality index, betweenness centrality index and proximity centrality index will be calculated respectively below. Tables 1 to 3 are the calculation results of the passenger flow point degree centrality index, passenger flow betweenness centrality index and passenger flow proximity centrality index of different nodes respectively.

[0130] Table 1 Node passenger flow point degree centrality values

[0131]

[0132]

[0133] Table 2 Node betweenness centrality values ​​after passenger flow weighting

[0134]

[0135]

[0136]

[0137] Table 3 Node proximity centrality values ​​after passenger flow weighting

[0138]

[0139]

[0140] According to the tabular data, it can be seen that the closeness centrality of nodes 16, 20, 10, 15, and 17 is relatively high. According to the definition of closeness centrality, the closer the average distance from a node to the remaining nodes in the network, the higher the closeness centrality. On the contrary, the positions of the above nodes in the network are located in the central position of the station, so the calculation results are in line with the actual situation.

[0141] The average price of passenger flow monitoring equipment is 4000 yuan per unit, and the budget for building passenger flow monitoring equipment in the CQDZ outbound transfer layer is 60000 yuan, that is, C' = 60000. According to the objective function and constraint conditions, the node selection for monitoring different passenger flow characteristics can be obtained. The following is the layout plan of passenger flow monitoring equipment calculated for the purpose of focusing on monitoring passenger flow conflicts at the station, that is According to the passenger flow monitoring equipment layout selection model, it is calculated that the passenger flow monitoring nodes include 9, 15, 17, 11, 25, 16, 27, 7, 5, 26, 19, 21, 23, 13, 14. The site selection plan is as Figure 3 shown.

[0142] If you want to focus on monitoring the flow direction of passenger flow in the station, you can set the weight of the betweenness centrality parameter of the node to the highest, that is According to the passenger flow monitoring equipment layout selection model, it is calculated that the passenger flow monitoring nodes include 9, 15, 16, 11, 17, 26, 19, 21, 10, 20, 25, 27, 13, 7, 5. The site selection plan is as Figure 4 shown.

[0143] If you want to evaluate indicators such as the convenience and accessibility of the passenger flow streamline network on this layer by monitoring the passenger flow situation, you need to give priority to the points with relatively high closeness centrality after passenger flow weighting, and you can set the weight of the closeness centrality parameter of the node to the highest, that is According to the passenger flow monitoring equipment layout selection model, it is calculated that the passenger flow monitoring nodes include 15, 9, 17, 11, 25, 16, 27, 13, 26, 7, 14, 23, 5, 19, 21. The site selection plan is as Figure 5 shown.

[0144] Example 3

[0145] This Example 3 provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the above-mentioned method for selecting passenger flow monitoring points in a station based on a complex network is implemented. The method includes:

[0146] Based on the passenger flow streamline of the station, construct a passenger flow distribution network of the station;

[0147] Based on the constructed passenger flow distribution network of the station, calculate the centrality indexes of the network nodes, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality;

[0148] Based on the constructed passenger flow distribution network of the station, combined with the calculated centrality indexes of the network nodes, construct an optimization model for the location selection of passenger flow monitoring nodes;

[0149] Solve the constructed optimization model for the location selection of passenger flow monitoring nodes to obtain the location selection plan for the passenger flow monitoring points of the station.

[0150] Embodiment 4

[0151] This Embodiment 4 provides a computer device, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the above-mentioned method for the location selection of passenger flow monitoring points of the station based on complex networks, and this method includes:

[0152] Construct a passenger flow distribution network of the station;

[0153] Based on the constructed passenger flow distribution network of the station, calculate the centrality indexes of the network nodes, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality;

[0154] Based on the constructed passenger flow distribution network of the station, combined with the calculated centrality indexes of the network nodes, construct an optimization model for the location selection of passenger flow monitoring nodes;

[0155] Solve the constructed optimization model for the location selection of passenger flow monitoring nodes to obtain the location selection plan for the passenger flow monitoring points of the station.

[0156] Embodiment 5

[0157] This Embodiment 5 provides an electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes the instructions for implementing the above-mentioned method for the location selection of passenger flow monitoring points of the station based on complex networks, and this method includes:

[0158] Construct a passenger flow distribution network of the station;

[0159] Based on the constructed passenger flow distribution network of the station, calculate the centrality indexes of the network nodes, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality;

[0160] Based on the constructed passenger flow distribution network of the station, combined with the calculated centrality indexes of the network nodes, construct an optimization model for the location selection of passenger flow monitoring nodes;

[0161] Solve the optimized model for the location selection of the passenger flow monitoring nodes constructed to obtain the location selection plan for the passenger flow monitoring points at the station.

[0162] 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 completely hardware embodiment, a completely 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.

[0163] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (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. 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 a machine for implementing the functions specified in one Figure 1 one or more flows and / or blocks Figure 1 device for the functions specified in one or more blocks.

[0164] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in one Figure 1 one or more flows and / or blocks Figure 1 device for the functions specified in one or more blocks.

[0165] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one or more flows and / or blocks Figure 1 device for the functions specified in one or more blocks.

[0166] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present invention. Those skilled in the art should understand that, based on the technical solutions disclosed in the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts should be covered within the protection scope of the present invention.

Claims

1. A method for selecting passenger flow monitoring points at stations based on complex networks, characterized in that including: constructing a passenger flow distribution network of a station based on the passenger flow streamline of the station; calculating the centrality indexes of network nodes based on the constructed passenger flow distribution network of the station, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality; constructing an optimized model for the location selection of passenger flow monitoring nodes based on the constructed passenger flow distribution network of the station and in combination with the calculated centrality indexes of network nodes; wherein, by combining the passenger flow degree centrality, the passenger flow betweenness centrality, and the passenger flow closeness centrality, the specific evaluation calculation formula for the passenger flow monitoring effect is as follows: In the formula, represents the passenger flow monitoring effect; represents the number of nodes; represents the passenger flow degree centrality weight parameter; represents the passenger flow betweenness centrality weight parameter; represents the passenger flow closeness centrality weight parameter; In order to be able to measure on the same field scale, are respectively the normalized passenger flow degree centrality, passenger flow betweenness centrality and passenger flow closeness centrality; the established optimized model for the location selection of passenger flow monitoring nodes is: Objective function: Constraints: In the formula, represents the decision variable, and selecting a node to install monitoring facilities will result in 1, otherwise 0; represents the node cost of deploying passenger flow monitoring equipment; represents the total budget for deploying passenger flow monitoring equipment; solving the constructed optimized model for the location selection of passenger flow monitoring nodes to obtain the location selection scheme of the passenger flow monitoring points of the station.

2. The method for selecting passenger flow monitoring points at stations based on complex networks according to claim 1, wherein The passenger flow degree centrality is obtained by weighted calculation considering the influence of passenger flow on the basis of the calculation method of the degree centrality of ordinary node structures. The nodes of the passenger flow distribution network of the station of the passenger flow degree centrality The calculation formula is as follows: ； Among them, represents the passenger flow point degree centrality of the node ; represents the passenger flow volume of the node that can be obtained by monitoring; represents the node in the passenger flow distribution network of the station; represents the connection variable, taking 1 if connected, and 0 otherwise.

3. The method for selecting passenger flow monitoring points at stations based on complex networks according to claim 2, wherein The passenger flow betweenness centrality is obtained by considering the influence of passenger flow on the basis of the betweenness centrality of the network structure. The formula for calculating the passenger flow betweenness centrality of a node is as follows: In the formula, represents the betweenness centrality of node ; represents the betweenness centrality of node after weighted by passenger flow; represents the passenger flow of node obtainable by monitoring equipment; represents a node in the network diagram of passenger flow concentration and dispersion at the station; represents the set of all nodes in the network diagram of passenger flow concentration and dispersion at the station; represents the number of the shortest paths from node to node ; represents the number of the shortest paths from node to node that pass through point .

4. The method for selecting passenger flow monitoring points at stations based on complex networks according to claim 3, wherein The passenger flow closeness centrality value represents the degree of "being close to the central position" of the node passenger flow in the network structure. Considering the influence of the passenger flow volume, the calculation formula for the passenger flow closeness centrality is as follows: In the formula, represents the closeness centrality value of node ; represents the closeness centrality of node after passenger flow weighting; represents the passenger flow of node that can be obtained by the monitoring device; represents a node in the network diagram; represents the number of nodes; represents node and node the shortest path length between them; represents node to all other nodes in the network the sum of the shortest path lengths.

5. A station passenger flow monitoring point location system based on complex networks, characterized in that, including: a first construction module for constructing a passenger flow distribution network of a station based on the passenger flow streamline of the station; a first calculation module for calculating the centrality indexes of network nodes based on the constructed passenger flow distribution network of the station, including passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality; a second construction module for constructing an optimized model for the location selection of passenger flow monitoring nodes based on the constructed passenger flow distribution network of the station and in combination with the calculated centrality indexes of network nodes; wherein, by combining the passenger flow degree centrality, the passenger flow betweenness centrality, and the passenger flow closeness centrality, the specific evaluation calculation formula for the passenger flow monitoring effect is as follows: In the formula, represents the passenger flow monitoring effect; represents the number of nodes; represents the passenger flow degree centrality weight parameter; represents the passenger flow betweenness centrality weight parameter; represents the passenger flow closeness centrality weight parameter; In order to be able to measure on the same field scale, are the normalized passenger flow degree centrality, passenger flow betweenness centrality, and passenger flow closeness centrality respectively; the established optimized model for the location selection of passenger flow monitoring nodes is: Objective function: Constraints: In the formula, represents the decision variable, and selecting a node to install monitoring facilities will be 1; otherwise, it will be 0; represents the node cost of deploying passenger flow monitoring equipment; represents the total budget for deploying passenger flow monitoring equipment; a second calculation module for solving the constructed optimized model for the location selection of passenger flow monitoring nodes to obtain the location selection scheme of the passenger flow monitoring points of the station.

6. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method for the location selection of passenger flow monitoring points of a station based on a complex network as described in any one of claims 1-4 is implemented.

7. A computer device, characterized in that, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for the location selection of passenger flow monitoring points of a station based on a complex network as described in any one of claims 1-4.

8. An electronic device, characterized in that, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes the instructions for implementing the method for the location selection of passenger flow monitoring points of a station based on a complex network as described in any one of claims 1-4.

Images