Site importance evaluation method and device, storage medium, and electronic device

Abstract

The present application discloses a method and device for evaluating the importance of a station, a storage medium, and an electronic device. The method includes: upon receiving an evaluation request for evaluating the importance of a target station of a subway, obtaining the station code data, in-and-out passenger flow data, and driving path data of the target station; inputting the station code data, in-and-out passenger flow data, and driving path data of the target station into a pre-trained evaluation model, obtaining the importance of the target station output by the evaluation model, and constructing edges based on the real-time in-and-out passenger flow of the subway and the subway path table of the subway clearing system, comprehensively considering the number of people entering the station, the number of people passing by, and the importance of the subway station as a static network node to evaluate the importance of the station, which can solve the technical problem of low accuracy of importance evaluation in related technologies.

Description

Technical Field

[0001] The present application relates to the field of urban transportation, and more specifically, to a method and device for evaluating the importance of a site, a storage medium, and an electronic device. Background Art

[0002] With the continuous development of cities, subway rail transit has increasingly become the backbone of urban transportation, and is an important guarantee for citizens to travel smoothly and solve traffic congestion problems. While the subway network is developing, it has also brought more challenges to the effective operation of the system. On the one hand, under the bearing capacity of the existing subway system, in order to balance traffic demand and resource utilization, it is more difficult to set a reasonable departure interval; on the other hand, due to equipment failure, large passenger flow and other emergencies that may cause local stations or lines to be paralyzed, it is more difficult to evaluate the overall impact of rail transit, such as the large passenger flow caused by concerts held near subway stations. In order to solve these problems, an effective means is to reasonably evaluate the importance of subway stations (i.e. importance) based on the subway network and real-time subway passenger flow, and then balance the importance of each station by reasonably setting the departure interval to ensure the circulation efficiency of the subway network. The accuracy of the existing importance evaluation scheme is low.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for evaluating the importance of a site, a storage medium, and an electronic device, so as to at least solve the technical problem of low accuracy of importance evaluation in the related art.

[0005] According to one aspect of an embodiment of the present application, a method for evaluating the importance of a station is provided, comprising: receiving an evaluation request, wherein the evaluation request is used to request an evaluation of the importance of a target station of a subway; in response to the evaluation request, obtaining station code data, in-and-out passenger flow data, and driving path data of the target station; inputting the station code data, in-and-out passenger flow data, and driving path data of the target station into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model.

[0006] Optionally, the station coding data, in-and-out passenger flow data and driving path data of the target site are input into a pre-trained evaluation model, including: inputting the station coding data, in-and-out passenger flow data and driving path data of the target site into a pre-trained first evaluation model, and obtaining the first importance of the target site output by the first evaluation model, wherein the first importance is the objective importance of the target site; and / or, inputting the station coding data, in-and-out passenger flow data, driving path data, departure interval data and vehicle capacity data of the target site into a pre-trained second evaluation model, and obtaining the second importance of the target site output by the second evaluation model, wherein the second importance is the importance of the target site after regulation.

[0007] Optionally, before inputting the station code data, in-and-out passenger flow data, and driving path data of the target station into the pre-trained first evaluation model, the method further includes: obtaining station data of each station in the subway, wherein the station data includes the station code data, in-and-out passenger flow data, and driving path data of the station; and iterating the original model represented by the following formula using the station data of each station to obtain the first evaluation model: Among them, P is an N-dimensional column vector, which represents the PR value of each node, S is an N*N-dimensional matrix with all elements non-negative and the sum of each column being 1, α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1.

[0008] Optionally, before iterating the original model represented by the following formula using the site data of each site, the method further includes:

[0009] Construct a matrix A with n columns and n rows using the site data of each site.

[0010]

[0011] Among them, a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in rd jk When I(i∈rd jk ) is equal to 1, otherwise I(i∈rd jk ) is equal to 0;

[0012] Construct matrix S using matrix A:

[0013]

[0014] Among them, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i.

[0015] Optionally, the matrix S satisfies the following requirements: In this case, the matrix S satisfies: The more people enter station i, the greater the number of s ii The larger the number, the more people who enter from station j pass through station i, then s ji The bigger.

[0016] Optionally, before inputting the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the target station into the pre-trained second evaluation model, the method further includes: obtaining station data of each station in the subway, wherein the station data includes the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the station; and iterating the original model represented by the following formula using the station data of each station to obtain the second evaluation model:

[0017]

[0018] Among them, P is an N-dimensional column vector, which represents the PR value of each node, S is an N*N-dimensional matrix with all elements non-negative and the sum of each column being 1, α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1.

[0019] Optionally, before iterating the original model represented by the following formula using the site data of each site, the method further includes: constructing a matrix A having n columns and n rows using the site data of each site,

[0020]

[0021] Among them, a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in the time slice, time_slice represents the length of the time slice, t i,jk It represents the departure interval of station i in the path direction from station j to station k, c i,jk It represents the passenger capacity of a single train from station i in the path direction from j to k. It represents the subway capacity of station i in the path direction from station j to station k within the time slice time_;

[0022] Construct matrix S using matrix A:

[0023]

[0024] Among them, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i.

[0025] According to another aspect of an embodiment of the present application, a station importance evaluation device is also provided, including: a receiving unit, used to receive an evaluation request, wherein the evaluation request is used to request an evaluation of the importance of a target station of a subway; an acquisition unit, used to obtain the station code data, in-and-out passenger flow data, and driving path data of the target station in response to the evaluation request; an evaluation unit, used to input the station code data, in-and-out passenger flow data, and driving path data of the target station into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model.

[0026] Optionally, the evaluation unit is also used to: input the station coding data, inbound and outbound passenger flow data and driving path data of the target site into a pre-trained first evaluation model to obtain a first importance of the target site output by the first evaluation model, wherein the first importance is the objective importance of the target site; and / or, input the station coding data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the target site into a pre-trained second evaluation model to obtain a second importance of the target site output by the second evaluation model, wherein the second importance is the importance of the target site after regulation.

[0027] Optionally, the apparatus of the present application may further include: a training unit, which is used to input the station code data, in-and-out passenger flow data, and driving path data of the target station into the pre-trained first evaluation model before the method further includes: obtaining the station data of each station in the subway, wherein the station data includes the station code data, in-and-out passenger flow data, and driving path data of the station; and iterating the original model represented by the following formula using the station data of each station to obtain the first evaluation model: Among them, P is an N-dimensional column vector, which represents the PR value of each node, S is an N*N-dimensional matrix with all elements non-negative and the sum of each column being 1, α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1.

[0028] Optionally, the training unit is further used to: construct a matrix A with n columns and n rows using the site data of each site before iterating the original model represented by the following formula using the site data of each site,

[0029]

[0030] Among them, a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in rd jk When I(i∈rd jk ) is equal to 1, otherwise I(i∈rd jk ) is equal to 0;

[0031] Construct matrix S using matrix A:

[0032]

[0033] Among them, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i.

[0034] Optionally, the matrix S satisfies the following requirements: In this case, the matrix S satisfies: The more people enter station i, the greater the number of s ii The larger the number, the more people who enter from station j pass through station i, then s ji The bigger.

[0035] Optionally, the training unit is further used to: before inputting the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the target station into the pre-trained second evaluation model, obtain the station data of each station in the subway, wherein the station data includes the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the station; and iterate the original model represented by the following formula using the station data of each station to obtain the second evaluation model:

[0036]

[0037] Among them, P is an N-dimensional column vector, which represents the PR value of each node, S is an N*N-dimensional matrix with all elements non-negative and the sum of each column being 1, α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1.

[0038] Optionally, the training unit is further used to: construct a matrix A with n columns and n rows using the site data of each site before iterating the original model represented by the following formula using the site data of each site,

[0039]

[0040] Among them, a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in the time slice, time_slice represents the length of the time slice, t i,jk It represents the departure interval of station i in the path direction from station j to station k, c i,jk It represents the passenger capacity of a single train from station i in the path direction from j to k. It represents the subway capacity of station i in the path direction from station j to station k within the time slice time_slice;

[0041] Construct matrix S using matrix A:

[0042]

[0043] Among them, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i.

[0044] According to another aspect of an embodiment of the present application, a storage medium is further provided, which includes a stored program, and the above method is executed when the program is run.

[0045] According to another aspect of an embodiment of the present application, an electronic device is further provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above method through the computer program.

[0046] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any one of the embodiments of the above method.

[0047] The present application can be applied to data mining in the field of data capabilities. In an embodiment of the present application, when an evaluation request for evaluating the importance of a target station of a subway is received, the station code data, in-and-out passenger flow data, and driving path data of the target station are obtained; the station code data, in-and-out passenger flow data, and driving path data of the target station are input into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model. Edges can be constructed based on the real-time in-and-out passenger flow of the subway and the subway path table of the subway clearing system. The importance of the station is evaluated by comprehensively considering the number of people entering the station, the number of people passing through, and the importance of the subway station as a static network node, which can solve the technical problem of low accuracy of importance evaluation in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0049] Figure 1 is a flowchart of an optional method for evaluating site importance according to an embodiment of the present application;

[0050] Figure 2 is a schematic diagram of an optional site importance evaluation scheme according to an embodiment of the present application;

[0051] Figure 3 is a schematic diagram of an optional site importance evaluation device according to an embodiment of the present application; and,

[0052] Figure 4 It is a structural block diagram of a terminal according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] In order to evaluate the importance of subway stations, the following two types of solutions can be used. One is a method based on the importance of network nodes, such as betweenness centrality, PageRank, LeaderRank and other algorithms. Based on the subway network diagram, the importance of the station is calculated using the real-time subway in and out passenger flow as the relevant weight. However, this type of algorithm does not reasonably evaluate the impact of passenger flow on the passing stations. It will give too high importance to neighboring stations with large passenger flow, and too low importance to other passing stations. The other is based on subway passenger flow. The clearing system calculates the number of people affected by each station to evaluate the importance of the station. This method evaluates the importance of each station separately and does not consider the mutual influence between stations.

[0056] According to one aspect of the embodiments of the present application, a method embodiment of a method for evaluating the importance of a site is provided. The subway site importance evaluation method provided in this scheme, which combines the advantages of two types of methods, is an application of an improved PageRank algorithm. Different from the general PageRank algorithm that constructs edges based on the subway line network, this method constructs edges based on the real-time inbound and outbound passenger flow of the subway and the subway path table of the subway clearing system, and comprehensively considers the number of people entering the station, the number of people passing through, and the importance of the subway station as a static network node to evaluate the importance of the station. The present invention first calculates the objective importance of the subway station based on real-time passenger flow data, and then adds the departure interval and subway capacity data training to obtain the smoothness of the subway station to evaluate the effectiveness of the control measures.

[0057] Figure 1 is a flow chart of an optional method for evaluating the importance of a site according to an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps:

[0058] Step S102: receiving an evaluation request, the evaluation request is used to request an evaluation of the importance of a target subway station. Importance is a parameter commonly used in the field of subways to evaluate the status of subway stations.

[0059] Step S104, in response to the evaluation request, obtaining the station code data, inbound and outbound passenger flow data, and driving path data of the target station.

[0060] Step S106, input the station code data, in-and-out passenger flow data and driving path data of the target station into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model.

[0061] Through the above steps, when an evaluation request for evaluating the importance of a target station of a subway is received, the station code data, in-and-out passenger flow data, and driving path data of the target station are obtained; the station code data, in-and-out passenger flow data, and driving path data of the target station are input into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model. Edges can be constructed based on the real-time in-and-out passenger flow of the subway and the subway path table of the subway settlement system. The importance of the station is evaluated by comprehensively considering the number of people entering the station, the number of people passing through, and the importance of the subway station as a static network node, which can solve the technical problem of low accuracy of importance evaluation in related technologies.

[0062] As an optional implementation, the following is combined with Figure 2 The technical solution of this application is further described in detail with specific implementation methods:

[0063] 1) Data collection module, which collects station code data of subway stations, real-time in-and-out passenger flow data, subway driving path data, subway departure interval data, subway vehicle capacity data, and subway station data. These data can be provided by the subway data center; passenger flow data can be counted hourly:

[0064] Taking Shanghai Metro as an example, the data in the following format can be obtained (the specific data is not real data). Table 1 is the station code data, Table 2 is the in and out passenger flow data, Table 3 is the driving path data, Table 4 is the departure interval data, and Table 5 is the subway vehicle capacity data:

[0065] Table 1

[0066] Station Code Station name 0101 Xinzhuang 0102 Outer Ring Road 0103 Lotus Road 0104 Jinjiang Amusement Park

[0067] Table 2

[0068] date Hour Inbound station code Departure station code Flow 20181225 8 0101 0102 5 20181225 8 0101 0103 10

[0069] Table 3

[0070] Inbound station code Departure station code Station code 0101 0104 0101 0101 0104 0102 0101 0104 0103 0101 0104 0104

[0071] Table 4

[0072] date Hour SUBWAY LINE Interval time (minutes) direction 20181225 8 1 3 0 20181225 8 1 3 1 20181225 8 2 4 0 20181225 8 2 4 1

[0073] Table 5

[0074] SUBWAY LINE capacity direction 1 1000 0 1 1000 1 2 800 0 2 800 1

[0075] 2) Data processing module. The data processing module contains two functions. One is to calculate the flow weights between subway stations based on the passenger flow in and out of the station and the subway driving path data. The other is to add the departure interval data and subway transportation capacity data to the original data to update the new flow weights between stations.

[0076] 3) Model training module. The model training module includes some functions. First, based on the original flow data between stations, a converged model is trained to obtain the objective importance of the station. Second, the importance of the station is obtained by training the flow data between stations after adding the departure interval and subway capacity data.

[0077] 4) Data customization module, which includes functions such as customized departure interval, customized passenger flow entering the station, customized cancellation of station transfer, customized closed station, and customized closed line;

[0078] 5) Evaluation and display module: Based on the model results, it evaluates the importance of the site and the effectiveness of human control measures, and displays the results on the web page to intuitively reflect the importance of the site.

[0079] The above modules work as follows:

[0080] Step 1: Collect data. The data is obtained directly from the subway data center. All data can be sliced ​​by hour. Among them, the station code data includes the station code and the Chinese name corresponding to the station. For transfer stations, there is only one Chinese name, but there are multiple codes; the in-and-out passenger flow data includes date, hour, in-station code, out-station code, and passenger flow; the driving path data includes in-station code, out-station code, and path station code; the departure interval data includes date, hour, line number, departure interval, and direction; the subway vehicle capacity data includes line number, basic capacity (the number of subway passengers under comfortable conditions), and direction.

[0081] Step 2: Data processing. This solution is based on the site importance evaluation of the classic PageRank algorithm. The model iteration formula is as follows:

[0082]

[0083] Where P (i.e. P0 to Pm, m is the maximum positive integer of (n+1)) is an N-dimensional column vector, which represents the PR value of each node. S is an N*N-dimensional matrix with all elements non-negative and the sum of each column equal to 1. α is a manually set hyperparameter. e is an N-dimensional column vector with all values ​​1. N and n are positive integers. Pj The j (ranging from 0 to m) in is the subscript of P.

[0084] In the classic PageRank algorithm, the elements of S are determined by the outbound links between nodes. Assuming that there are only four sites, 0101, 0102, 0103, and 0104, the matrix S is shown in Table 6 below:

[0085] Table 6

[0086] Station Code 0101 0102 0103 0104 0101 p11 p21 0 0 0102 p12 p22 p32 0 0103 0 p23 p33 p43 0104 0 0 p34 p44

[0087] The sum of the numbers in each column of the matrix is ​​1. The only station connected to station 0101 is station 0102, so the probability of 0101 to 0103 and 0104 is 0. The probabilities of 0101 to 0101 and 0102 are p11 and p12 respectively, where p11+p12=1. The specific data can be determined by the flow of people data.

[0088] In this scheme, the difference from the classic PageRank algorithm is that the construction method of the matrix S is different. The classic method of constructing the transition probability matrix cannot effectively utilize the driving path data. In this scheme, the data processing part is divided into two different processes, one is only using passenger flow and path data, and the other is including departure intervals and vehicle basic capacity data. This application constructs the matrix S based on passenger flow, rather than simply based on the subway network, assuming that the total number of subway stations is n.

[0089] Step 2.1, only use passenger flow and path data (the subscripts of the parameters mentioned in the text are natural numbers). First construct an n*n matrix A, the element a in the matrix ij satisfy:

[0090]

[0091] Among them, a ij Represents the element value of the i-th row and j-th column of matrix A; od jk represents the number of passengers entering from station j and leaving from station k; rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k (excluding station j but including station k); len(rd jk ) represents rd jk The number of sites in rd jk When I(i∈rd jk ) is equal to 1, otherwise I(i∈rd jk ) is equal to 0.

[0092] Matrix A is constructed based on passenger flow and subway routes. On the basis of A, matrix S is constructed. Matrix S should not only reflect that the stations with more passengers entering the station are more important, but also reflect that the stations with more passengers passing through are more important. Based on the above two points, the following requirements are met:

[0093]

[0094] Among them, s ii is the element in the i-th row and i-th column of the matrix S; β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i, which meets the following requirements:

[0095]

[0096] Among them, j≠i.

[0097] At this time, the matrix S satisfies: The more people enter station i, the greater the number of s ii The larger the number, the more people who enter from station j and pass through station i, the larger the number of people who enter from station j and pass through station i, the larger the number of people who pass through station i ... ji The bigger.

[0098] In step 2.2, in addition to passenger flow data and route data, departure interval data and vehicle capacity data are also required.

[0099] Similar to step 2.1, first construct the matrix A to meet the following requirements:

[0100]

[0101] Among them, time_slice represents the length of the time slice; t i,jk represents the departure interval of station i in the path direction from j to k; c i,jk It represents the passenger capacity of a single train at station i in the path direction from j to k; It represents the subway capacity of station i in the path direction from j to k within the time slice time_slice.

[0102] Then construct the matrix S. The construction method of matrix S is the same as step 2.1.

[0103] Step 3: Model training.

[0104] The training method is consistent with PageRank's training method, and the iterative formula is:

[0105]

[0106] P0 is an n-dimensional vector obtained by random initialization with all elements non-negative and summed to 1. During training, in addition to setting α, you also need to set the maximum number of iterations and the convergence parameter eps. When the number of training reaches the maximum number of iterations, or P n+1 With P n When the Euclidean distance between them is less than eps, stop training.

[0107] Based on step 3.1, the obtained S can be trained to obtain a converged P value, set as P1, which can be used as the objective value of the site importance;

[0108] Based on step 3.2, the obtained S can be trained to obtain a converged P value, set as P2, and P2 is used as the value of the site importance after artificial regulation.

[0109] Data customization: When the data changes, you can modify the data through the custom module. For example, when the original data changes due to special time such as site closure, line closure, passenger flow surge, etc., you can modify the original data, reprocess the data and train the model to obtain the P value of the importance of the site after the data changes, which is set to P3.

[0110] Data customization can be in the following situations: custom departure intervals, in which case you can directly modify the departure interval data; custom inbound passenger flow, in which case the new inbound passenger flow will be distributed to each path according to the original proportion; custom cancellation of station transfers, in which case the relevant paths for transfers at the station will be deleted; custom closure of stations, in which case the data included in entering / leaving the station at the station will be deleted, and the station will be deleted from the path table; custom closure of routes, in which case all stations on the route will be closed.

[0111] When evaluating model results, the evaluation methods are diverse and not unique, including but not limited to comparing the differences in site importance at the same site at different times; comparing the differences in site importance at different sites at the same time; comparing the differences in the corresponding values ​​of P1 and P2 at the same site at the same time.

[0112] This method constructs edges based on the real-time in-and-out passenger flow of the subway and the subway path table of the subway clearing system, and comprehensively considers the number of people entering the station, the number of people passing through, and the importance of the subway station as a static network node to evaluate the importance of the station. The present invention first calculates the objective importance of the subway station based on real-time passenger flow data, and then adds the departure interval and subway capacity data training to obtain the smoothness of the subway station to evaluate the effectiveness of the control measures.

[0113] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0114] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0115] According to another aspect of the embodiments of the present application, a site importance evaluation device for implementing the above-mentioned site importance evaluation method is also provided. Figure 3 is a schematic diagram of an optional site importance evaluation device according to an embodiment of the present application, such as Figure 3 As shown, the device may include:

[0116] The receiving unit 31 is used to receive an evaluation request, wherein the evaluation request is used to request an evaluation of the importance of a target station of the subway; the acquiring unit 33 is used to obtain the station code data, in-and-out passenger flow data, and driving path data of the target station in response to the evaluation request; the evaluating unit 35 is used to input the station code data, in-and-out passenger flow data, and driving path data of the target station into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model.

[0117] It should be noted that the receiving unit 31 in this embodiment can be used to execute step S102 in the embodiment of the present application, the acquisition unit 33 in this embodiment can be used to execute step S104 in the embodiment of the present application, and the evaluation unit 35 in this embodiment can be used to execute step S106 in the embodiment of the present application.

[0118] Through the above module, when an evaluation request for evaluating the importance of a target station of the subway is received, the station code data, in-and-out passenger flow data and driving path data of the target station are obtained; the station code data, in-and-out passenger flow data and driving path data of the target station are input into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model. Edges can be constructed based on the real-time in-and-out passenger flow of the subway and the subway path table of the subway settlement system. The importance of the station is evaluated by comprehensively considering the number of people entering the station, the number of people passing by, and the importance of the subway station as a static network node, which can solve the technical problem of low accuracy of importance evaluation in related technologies.

[0119] Optionally, the evaluation unit is also used to: input the station code data, inbound and outbound passenger flow data and driving path data of the target site into a pre-trained first evaluation model, and obtain the first importance of the target site output by the first evaluation model, wherein the first importance is the objective importance of the target site; and / or, input the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the target site into a pre-trained second evaluation model, and obtain the second importance of the target site output by the second evaluation model, wherein the second importance is the importance of the target site after regulation.

[0120] Optionally, the device of the present application may further include: a training unit, which is used to input the station code data, in-and-out passenger flow data and driving path data of the target station into the pre-trained first evaluation model before the method further includes: obtaining the station data of each station in the subway, wherein the station data includes the station code data, in-and-out passenger flow data and driving path data of the station; and iterating the original model represented by the following formula using the station data of each station to obtain the first evaluation model: Among them, P is an N-dimensional column vector, which represents the PR value of each node, S is an N*N-dimensional matrix with all elements non-negative and the sum of each column being 1, α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1.

[0121] Optionally, the training unit is further used to: construct a matrix A with n columns and n rows using the site data of each site before iterating the original model represented by the following formula using the site data of each site,

[0122]

[0123] Among them, a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jkIndicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in rd jk When I(i∈rd jk ) is equal to 1, otherwise I(i∈rd jk ) is equal to 0;

[0124] Construct matrix S using matrix A:

[0125]

[0126] Among them, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i.

[0127] Optionally, the matrix S satisfies the following requirements: In this case, the matrix S satisfies: The more people enter station i, the greater the number of s ii The larger the number, the more people who enter from station j pass through station i, then s ji The bigger.

[0128] Optionally, the training unit is further used to: before inputting the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the target station into the pre-trained second evaluation model, obtain the station data of each station in the subway, wherein the station data includes the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle capacity data of the station; and iterate the original model represented by the following formula using the station data of each station to obtain the second evaluation model:

[0129]

[0130] Among them, P is an N-dimensional column vector, which represents the PR value of each node, S is an N*N-dimensional matrix with all elements non-negative and the sum of each column being 1, α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1.

[0131] Optionally, the training unit is further used to: construct a matrix A with n columns and n rows using the site data of each site before iterating the original model represented by the following formula using the site data of each site,

[0132]

[0133] Among them, a ij represents the element value of the i-th row and j-th column of matrix A, od jkrepresents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in the time slice, time_slice represents the length of the time slice, t i,jk It represents the departure interval of station i in the path direction from station j to station k, c i,jk It represents the passenger capacity of a single train from station i in the path direction from j to k. It represents the subway capacity of station i in the path direction from station j to station k within the time slice time_slice;

[0134] Construct matrix S using matrix A:

[0135]

[0136] Among them, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i.

[0137] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can be run in a corresponding hardware environment, can be implemented by software, and can also be implemented by hardware, wherein the hardware environment includes a network environment.

[0138] According to another aspect of the embodiments of the present application, a server or terminal for implementing the above-mentioned site importance evaluation method is also provided.

[0139] Figure 4 is a structural block diagram of a terminal according to an embodiment of the present application, such as Figure 4 As shown, the terminal may include: one or more ( Figure 4 (only one is shown) processor 401, memory 403, and transmission device 405, as shown in Figure 4 As shown, the terminal may also include an input and output device 407.

[0140] Among them, the memory 403 can be used to store software programs and modules, such as the program instructions / modules corresponding to the site importance evaluation method and device in the embodiment of the present application. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 403, that is, the above-mentioned site importance evaluation method is realized. The memory 403 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 403 may further include a memory remotely arranged relative to the processor 401, and these remote memories can be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0141] The above-mentioned transmission device 405 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 405 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 405 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0142] Specifically, the memory 403 is used to store application programs.

[0143] The processor 401 may call the application stored in the memory 403 through the transmission device 405 to perform the following steps:

[0144] An evaluation request is received, wherein the evaluation request is used to request an evaluation of the importance of a target station of a subway; in response to the evaluation request, station code data, in-and-out passenger flow data, and driving path data of the target station are obtained; the station code data, in-and-out passenger flow data, and driving path data of the target station are input into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model.

[0145] The processor 401 is further configured to execute the following steps:

[0146] The station code data, in-and-out passenger flow data, and driving path data of the target site are input into a pre-trained first evaluation model to obtain the first importance of the target site output by the first evaluation model, wherein the first importance is the objective importance of the target site; and / or, the station code data, in-and-out passenger flow data, driving path data, departure interval data, and vehicle capacity data of the target site are input into a pre-trained second evaluation model to obtain the second importance of the target site output by the second evaluation model, wherein the second importance is the importance of the target site after regulation.

[0147] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0148] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the terminal may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 It does not limit the structure of the above electronic device. For example, the terminal may also include Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations are shown.

[0149] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0150] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute the program code of the site importance evaluation method.

[0151] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0152] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0153] An evaluation request is received, wherein the evaluation request is used to request an evaluation of the importance of a target station of a subway; in response to the evaluation request, station code data, in-and-out passenger flow data, and driving path data of the target station are obtained; the station code data, in-and-out passenger flow data, and driving path data of the target station are input into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model.

[0154] Optionally, the storage medium is further configured to store program codes for executing the following steps:

[0155] The station code data, in-and-out passenger flow data, and driving path data of the target site are input into a pre-trained first evaluation model to obtain the first importance of the target site output by the first evaluation model, wherein the first importance is the objective importance of the target site; and / or, the station code data, in-and-out passenger flow data, driving path data, departure interval data, and vehicle capacity data of the target site are input into a pre-trained second evaluation model to obtain the second importance of the target site output by the second evaluation model, wherein the second importance is the importance of the target site after regulation.

[0156] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0157] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0158] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0159] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0160] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0161] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0163] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0164] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for evaluating the importance of a site, characterized in that: include: An evaluation request is received, wherein the evaluation request is used to request an evaluation of the importance of a target station of the subway; In response to the evaluation request, obtaining station code data, inbound and outbound passenger flow data, and driving path data of the target station; Inputting the station code data, in-and-out passenger flow data, and driving path data of the target site into a pre-trained evaluation model to obtain the importance of the target site output by the evaluation model, including: inputting the station code data, in-and-out passenger flow data, and driving path data of the target site into a pre-trained first evaluation model to obtain the first importance of the target site output by the first evaluation model, wherein the first importance is the objective importance of the target site; and, inputting the station code data, in-and-out passenger flow data, driving path data, departure interval data, and vehicle capacity data of the target site into a pre-trained second evaluation model to obtain the second importance of the target site output by the second evaluation model, wherein the second importance is the importance of the target site after regulation; Before inputting the station code data, in-and-out passenger flow data, and driving path data of the target station into the pre-trained first evaluation model, the method further includes: obtaining station data of each station in the subway, wherein the station data includes the station code data, in-and-out passenger flow data, and driving path data of the station; and iterating the original model represented by the following formula using the station data of each station to obtain the first evaluation model: P is an N-dimensional column vector, which represents the PR value of each node. S is an N*N-dimensional matrix with all elements non-negative and the sum of each column equal to 1. α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1. Before iterating the original model represented by the following formula using the site data of each site, the method further includes: constructing a matrix A having n columns and n rows using the site data of each site, a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in rd jk When I(i∈rd jk ) is equal to 1, otherwise I(i∈rd jk ) is equal to 0; Construct matrix S using matrix A: β, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i; The matrix S satisfies the following requirements: The more people enter station i, the more s ii The bigger; The more people who enter from station j pass through station i, the greater the s ji The bigger.

2. The method according to claim 1, characterized in that Before inputting the station code data, inbound and outbound passenger flow data, driving path data, departure interval data and vehicle transport capacity data of the target station into the pre-trained second evaluation model, the method further includes: Obtaining station data of each station in the subway, wherein the station data includes station code data, inbound and outbound passenger flow data, driving path data, departure interval data, and vehicle transport capacity data of the station; The original model represented by the following formula is iterated using the site data of each site to obtain the second evaluation model: Among them, P is an N-dimensional column vector, which represents the PR value of each node, S is an N*N-dimensional matrix with all elements non-negative and the sum of each column being 1, α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1.

3. The method according to claim 1, characterized in that: Before iterating the original model represented by the following formula using the site data of each site, the method further includes: Construct a matrix A with n columns and n rows using the site data of each site. Among them, a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in the time slice, time_slice represents the length of the time slice, t i,jk It represents the departure interval of station i in the path direction from station j to station k, c i,jk It represents the passenger capacity of a single train from station i in the path direction from j to k. It represents the subway capacity of station i in the path direction from station j to station k within the time slice time_slice; Construct matrix S using matrix A: Among them, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i.

4. A site importance evaluation device, characterized in that: include: A receiving unit, configured to receive an evaluation request, wherein the evaluation request is used to request an evaluation of the importance of a target station of the subway; An acquisition unit, configured to acquire station code data, inbound and outbound passenger flow data, and driving path data of the target station in response to the evaluation request; An evaluation unit, used for inputting the station code data, in-and-out passenger flow data and driving path data of the target station into a pre-trained evaluation model to obtain the importance of the target station output by the evaluation model, including: inputting the station code data, in-and-out passenger flow data and driving path data of the target station into a pre-trained first evaluation model to obtain the first importance of the target station output by the first evaluation model, wherein the first importance is the objective importance of the target station; and, inputting the station code data, in-and-out passenger flow data, driving path data, departure interval data and vehicle transport capacity data of the target station into a pre-trained second evaluation model to obtain the second importance of the target station output by the second evaluation model, wherein the second importance is the importance of the target station after regulation; Before inputting the station code data, in-and-out passenger flow data, and driving path data of the target station into the pre-trained first evaluation model, the station data of each station in the subway is obtained, and the station data includes the station code data, in-and-out passenger flow data, and driving path data of the station; the original model represented by the following formula is iterated using the station data of each station to obtain the first evaluation model: P is an N-dimensional column vector, which represents the PR value of each node. S is an N*N-dimensional matrix with all elements non-negative and the sum of each column equal to 1. α is a pre-set hyperparameter, and e is an N-dimensional column vector with all values ​​1. Before iterating the original model represented by the following formula using the site data of each site, a matrix A with n columns and n rows is constructed using the site data of each site. a ij represents the element value of the i-th row and j-th column of matrix A, od jk represents the number of passengers entering from station j and leaving from station k, rd jk Indicates the stations that need to be passed when entering from station j and exiting from station k, len(rd jk ) represents rd jk The number of sites in rd jk When I(i∈rd jk ) is equal to 1, otherwise I(i∈rd jk ) is equal to 0; Construct matrix S using matrix A: β, s ii is the element in the i-th row and i-th column of the matrix S, β is the model hyperparameter belonging to (0,1], a ii It represents the number of people entering station i; The matrix S satisfies the following requirements: The more people enter station i, the more s ii The bigger; The more people who enter from station j pass through station i, the greater the s ji The bigger.

5. A storage medium, characterized in that: The storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 3 when executed.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the method according to any one of claims 1 to 3 through the computer program.

Images