Rail transit connection line design method and device

Abstract

The present invention discloses a rail transit shuttle line design method and device, wherein the method comprises: obtaining user OD trajectory information; screening the user OD trajectory information to obtain the user's private transportation travel information; collecting user multi-dimensional data corresponding to the user's private transportation travel information, and predicting the public transportation travel acceptance according to the user multi-dimensional data, and determining the target user's private transportation travel information corresponding to the target user whose public transportation travel acceptance is higher than a preset threshold; screening out the rail transit shuttle target area and constructing the public transportation passenger capacity target function according to the target user's private transportation travel information, and using a graph database to process the public transportation passenger capacity target function to obtain the rail transit shuttle line in the rail transit shuttle target area.

Description

Technical Field

[0001] The present invention relates to the technical field of data statistics, and in particular to a method and device for designing a rail transit connection line. Background Art

[0002] The existing methods for designing or optimizing rail transit connection routes are as follows:

[0003] 1. Analyze the spatiotemporal aggregation points of residents' travel through mobile phone signaling data and GIS. Then, based on the spatiotemporal aggregation characteristics of passengers' travel, according to the topological structure and operating status of the transportation network, select the location of the best bus stop, allocate the demand points to the selected transfer stations, and reasonably determine the route direction and departure frequency.

[0004] 2. Determine the passenger flow demand for conventional bus distribution at the hub based on traffic surveys or traffic models, establish an optimal configuration model for conventional bus shuttle routes in the hub area, and combine other shuttle route evaluation indicators to obtain a plan for setting up shuttle bus stations in the hub area.

[0005] 3. Based on data such as passenger reservation time and location, conduct in-depth analysis of the mutual constraints between passengers on the same bus, fully consider the time windows at the beginning and end of passenger travel in the shuttle bus route planning, vehicle multi-path issues, and design the shuttle bus route according to demand.

[0006] 4. By constructing a virtual network model of the urban integrated transportation system and estimating the parameters of the emergency state, a bus connection network model under deterministic bus running time is established. The column generation algorithm is used to solve the bus connection network design model after robust transformation to obtain the optimal bus connection network design scheme.

[0007] However, the above prior art has the following disadvantages:

[0008] 1. In the process of estimating public transportation demand: methods based on traffic surveys and traffic models are prone to inaccurate estimates of public transportation demand due to sample randomness / model bias, and most methods optimize the deployment of existing public transportation users and do not actually solve the problem of traffic congestion.

[0009] 2. In the process of connecting line design: the method of finding the optimal solution by constructing the road network topology relationship requires too much manual intervention, and often does not consider the problem of computational complexity. Many methods are only feasible in theory, but some actual parameters are difficult to obtain / estimate, or the calculation process needs to be optimized through complex algorithms. There are relatively few methods that can be actually configured for application. Summary of the invention

[0010] In view of the above problems, the present invention is proposed to provide a rail transit connection line design method and device that overcomes the above problems or at least partially solves the above problems.

[0011] According to one aspect of the present invention, a rail transit connection line design method is provided, which includes:

[0012] Get user OD trajectory information;

[0013] Filter the user's OD trajectory information to obtain the user's private transportation information;

[0014] Collect multi-dimensional data of users corresponding to their private transportation information, and make public transportation acceptance predictions based on the multi-dimensional data, to determine the private transportation information of target users corresponding to target users whose public transportation acceptance is higher than a preset threshold;

[0015] According to the target departure point information and target destination information in the target user's private transportation travel information, the rail transit connection target area is screened out and the public transportation passenger capacity objective function is constructed. The public transportation passenger capacity objective function is processed using the graph database to obtain the rail transit connection lines within the rail transit connection target area; among them, the public transportation passenger capacity objective function is constructed based on the rail transit connection target area and public transportation data.

[0016] According to another aspect of the present invention, a rail transit connection line design device is provided, comprising:

[0017] An acquisition module, adapted to acquire user OD trajectory information;

[0018] A screening module is suitable for screening the user's OD trajectory information to obtain the user's private transportation information;

[0019] A prediction module, adapted to collect multi-dimensional data of users corresponding to their private transportation information, and predict the public transportation acceptance according to the multi-dimensional data of users, and determine the private transportation information of target users corresponding to the target users whose public transportation acceptance is higher than a preset threshold;

[0020] The solution module is suitable for screening out the rail transit connection target area and constructing the public transportation passenger capacity target function according to the target departure point information and the target destination information in the target user's private transportation travel information, and using the graph database to process the public transportation passenger capacity target function to obtain the rail transit connection lines within the rail transit connection target area; wherein, the public transportation passenger capacity target function is constructed based on the rail transit connection target area and public transportation data.

[0021] According to another aspect of the present invention, there is provided an electronic device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0022] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned rail transit connection line design method.

[0023] According to another aspect of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a processor to perform operations corresponding to the above-mentioned rail transit shuttle line design method.

[0024] According to the rail transit shuttle line design method and device of the present invention, the user OD trajectory information is obtained; the user OD trajectory information is screened to obtain the user's private transportation travel information; the user multi-dimensional data corresponding to the user's private transportation travel information is collected, and the public transportation travel acceptance is predicted according to the user multi-dimensional data, and the target user's private transportation travel information corresponding to the target user whose public transportation travel acceptance is higher than the preset threshold is determined; according to the target departure point information and the target destination information in the target user's private transportation travel information, the rail transit shuttle target area is screened and the public transportation passenger capacity objective function is constructed, and the public transportation passenger capacity objective function is processed using the graph database to obtain the rail transit shuttle line in the rail transit shuttle target area; wherein the public transportation passenger capacity objective function is constructed according to the rail transit shuttle target area and public transportation data. The user's private transportation travel information is obtained by screening the user's OD trajectory information. Based on the user's private transportation travel information, guidance is carried out, the target user who intends to choose public transportation travel is identified, the target user's private transportation travel information is designed, and the rail transit shuttle line is determined, which can maximize the conversion of private transportation travel to public transportation travel and ensure the passenger capacity of the rail transit shuttle line. Furthermore, the public transportation passenger capacity objective function is processed using the graph model of the graph database, which greatly reduces the time complexity of the calculation and obtains the rail transit connection lines more accurately.

[0025] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0027] Figure 1 A flow chart of a rail transit connection line design method according to an embodiment of the present invention is shown;

[0028] Figure 2 A schematic diagram showing determination of a rail transit connection target area according to an embodiment of the present invention is shown;

[0029] Figure 3 A schematic diagram showing a graph database establishing a graph model according to an embodiment of the present invention is shown;

[0030] Figure 4 A functional block diagram of a rail transit connection line design device according to an embodiment of the present invention is shown;

[0031] Figure 5 A schematic structural diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0032] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0033] Figure 1 FIG. 1 is a flow chart showing a method for designing a rail transit connection line according to an embodiment of the present invention. Figure 1 As shown in FIG. 1 , the rail transit connection line design method specifically includes the following steps:

[0034] Step S101, obtaining user OD trajectory information.

[0035] The user's OD trajectory information (Origin-Destination) can be obtained based on the signaling data of the user's mobile device. Specifically, the signaling data of the user's mobile device is obtained. For example, the signaling data of the user's mobile phone. The temporal and spatial continuity of mobile phone signaling data is high, and it has extremely high superiority in the accuracy of restoring the user's travel behavior. The mobile phone signaling data reflects that the user's OD trajectory is based on the base station. The base station locations can be connected in chronological order to obtain the user's OD trajectory information.

[0036] Taking into account the possible existence of signal drift and other problems in the signaling data, which may lead to inaccurate signaling data, the signaling data needs to be preprocessed. Preprocessing includes trajectory angle filtering, trajectory dynamic interpolation, and base station trajectory grid mapping. The above preprocessing can be achieved by technical means such as trajectory cleaning and trajectory interpolation, which will not be explained in detail here. After the signaling data is preprocessed, the preprocessed signaling data is filtered based on the grid continuous residence time threshold to obtain the user residence trajectory sequence. The grid continuous residence time threshold is related to the size of the grid area. For example, a grid with a side length of 250m can set the grid continuous residence time threshold to 30 minutes. The specific setting is based on the implementation situation and is not limited here. The user residence trajectory sequence is sorted according to the time order of the signaling data to obtain the user OD trajectory information. The user OD trajectory information contains a series of sequence values ​​of the user OD trajectory.

[0037] Step S102, filtering the user's OD trajectory information to obtain the user's private transportation travel information.

[0038] The user OD trajectory information includes a variety of travel information, such as user walking trajectory information, user public transportation travel information, user private transportation travel information, etc. For user walking information, there is no need to set up public transportation connecting routes. For user public transportation travel information, there is already existing public transportation, and there is no need to set it up again. Therefore, in this embodiment, it is necessary to filter out the user's private transportation travel information from the user OD trajectory information, so as to design rail transit connecting routes according to the user's private transportation travel information, so as to guide users to travel by public transportation.

[0039] For the user's private transportation travel information, the moving distance, speed, etc. in the user's OD trajectory information can be first extracted, and the user's private transportation travel information can be obtained according to the moving distance and / or speed, combined with the public transportation data. Specifically, the extracted moving distance and speed are detected. When the moving distance is less than or equal to the walking distance threshold, or the average speed calculated according to the speed is less than or equal to the standard walking speed, it can be determined that the trajectory information corresponding to the moving distance or the speed is walking trajectory information, and the walking trajectory information is removed. Then, according to the public transportation data, such as bus station information, subway base station information, bus GPS data, etc., the user trajectory information is identified by time-space matching, and the specific travel mode, boarding and alighting stations, etc. of the user when traveling by public transportation can be identified, and the public transportation travel information can be obtained, so that the public transportation travel information can be removed from the user's OD trajectory information, and the user's private transportation travel information in the user's OD trajectory information can be obtained. Alternatively, the speed in the user's OD trajectory information can be compared with the maximum speed threshold of the bus. When the speed is greater than the maximum speed threshold of the bus, the user's OD trajectory information corresponding to the speed should be the user's private transportation travel information.

[0040] The user OD trajectory information includes the user's walking trajectory information, the user's public transportation travel information, and the user's private transportation travel information, wherein the user's public transportation travel information may also include bus travel information and subway travel information. By removing the user's walking trajectory information and the user's public transportation travel information from the user's OD trajectory information, the user's private transportation travel information can be obtained, so as to set up a rail transit connection line for the user's private transportation travel information and attract the user to public transportation travel.

[0041] Step S103, collecting user multi-dimensional data corresponding to the user's private transportation travel information, and predicting public transportation travel acceptance based on the user multi-dimensional data, and determining the target user's private transportation travel information corresponding to the target user whose public transportation travel acceptance is higher than a preset threshold.

[0042] Although all users of private transportation information are potential targets for guidance to public transportation, due to the different characteristics of different users, there are great differences between them, resulting in different possibilities for different users to be successfully guided to public transportation. Therefore, further analysis is needed for the private transportation information of users. Collect multi-dimensional data of users corresponding to the private transportation information of users. The multi-dimensional data of users include: user identity data, user communication data, user social data, user consumption data, user network data, etc. The above data is collected after the user authorizes and allows. Based on the above multi-dimensional data of users, the user's income level, social status, personal preferences, etc. can be determined, and the user can be analyzed and predicted from multiple dimensions. In order to ensure the accuracy of the prediction, this embodiment uses a regression model to predict the acceptance of public transportation according to the multi-dimensional data of users. Specifically, if a logistic regression model is used to predict the acceptance of public transportation (the training of the regression model can be adjusted according to the characteristics of the sample data, such as using the Random-Froest ensemble learning method, with the model ROC curve / AUC value / F1 value as the evaluation criteria, etc.), the acceptance of public transportation p is predicted. According to the predicted public transportation acceptance, the target users whose public transportation acceptance is higher than the preset threshold are determined, and the target users' private transportation travel information is determined. Specifically, the target users predicted by the regression model can be changed by adjusting the p-value (such as setting the p-value to 0.5). Considering that the cost of two transfers for the target user is relatively high, this embodiment assumes that only rail transit transfer lines with a single transfer are provided to filter the target users' private transportation travel information. When filtering, the target users' private transportation travel information with only one end within the coverage of the subway station is selected. The following formula can be used for the regression model:

[0043]

[0044] Where X = (x1, x2, x3, ..., x p ) represents the different dimensions of the user's multi-dimensional data, g(X) = β T X,β=(β1,β2,β3,…,β p ) represents the specific data value of the user's multi-dimensional data.

[0045] Step S104, based on the target departure point information and the target destination information in the target user's private transportation information, the target rail transit connection area is screened out and the public transportation passenger capacity target function is constructed, and the public transportation passenger capacity target function is processed using the graph database to obtain the rail transit connection lines within the target rail transit connection area.

[0046] According to the target user's private transportation information, visualization tools can be used to display the target user's private transportation information in geographic space, determine the target area for rail transit connection, and narrow the route selection range involved in the rail transit connection line, so as to better realize the design of the rail transit connection line. Specifically, according to the target departure point information and target destination information in the target user's private transportation information, the distance to the station in the public transportation data is determined, such as determining the distance through the grid in geographic space, such as Figure 2 As shown, by screening the grid, the target is screened out for deletion. The grid can be selected as a grid with a side length of 250m. Among them, the target grid is the grid whose straight-line distance to the nearest station such as a subway station is within the preset minimum distance and maximum distance range, and its total flow reaches the preset flow threshold and has the largest total flow. The preset minimum distance can be set to 2km, the preset maximum distance can be set to 5km, the preset flow threshold can be set to 100 people, etc. The above settings are set according to the implementation situation and are not limited here. Figure 2 In addition to determining the target grid based on the target departure point information and the distance between the target destination information and the station, a spatial rectangle is formed based on the straight-line distance and extended distance between the target grid and the nearest station, such as a subway station (i.e., the maximum range of the track connection line, where the extended path can be set in combination with the specific actual geographical area characteristics), and the ray algorithm is used to determine the positional relationship between each grid center point and the spatial rectangle. All grids with center points inside the grid are determined as covered grids. The target grid and its covered grid constitute the target area for rail transit connection.

[0047] On the basis of determining the target area for rail transit connection, the flow rate in the target area for rail transit connection, and the private transportation information of the target users, the public transportation passenger capacity objective function can be constructed in combination with the road network data and its topological relationship in the public transportation data. The public transportation passenger capacity objective function maximizes the passenger capacity per unit mileage of the rail transit connection line. By iteratively solving the public transportation passenger capacity objective function, the rail transit connection lines in the target area for rail transit connection are obtained. The public transportation passenger capacity objective function is directly related to the change in the travel time cost of the target users. If the rail transit connection line causes a significant increase in the travel time of the target users, the target users will not choose to travel on the rail transit connection line. Based on the calculation and evaluation of the original travel time of each target user and the travel time using the rail transit connection line, the passenger capacity per unit mileage is finally maximized. The obtained public transportation passenger capacity objective function is as follows:

[0048]

[0049]

[0050] Where n is the total number of target users, s walk is the walking distance of the target user, v walk Evaluate walking speed for target users, s bus is the distance travelled by the bus, v bus is the average speed of the bus, s metro is the subway travel distance, v metro is the average speed of the subway, s is the total length of the rail transit connecting line, t wait-bus is the average waiting time for the shuttle bus, t wait-metro The average waiting time for connecting to the subway, is the historical average travel time of the target user, t k is the time cost tolerance coefficient of the target user.

[0051] By iteratively solving the above public transportation passenger capacity objective function, the maximum passenger capacity is obtained. The total length of the track connection line, the bus driving distance, the subway driving distance, etc. obtained in the iterative solution process determine the driving distance of each public transportation of the rail transit connection line. The average speed of the bus, the average speed of the subway, the average waiting time of the connecting bus, the average waiting time of the connecting subway, etc. can be obtained based on public transportation data.

[0052] The prior art usually uses a relational database to iteratively solve the above public transportation passenger capacity objective function. However, once the route is too long during the route iteration process, problems such as large amount of calculation and low efficiency will occur. A graph database is a non-relational (NoSQL) database that uses graph theory to store relationship information between entities. For example, the Neo4j graph database stores structured data on a network instead of a table. The basic elements include: node nodes and relation relationships. Node nodes can add labels and attributes, and relation relationships can add types and attributes. The performance of a relational database will drop sharply when processing a large number of associations; while the graph database has very high performance and flexibility when processing data connections. The query is always related to a part of the graph, and the overall performance tends to remain unchanged. In this embodiment, since roads are naturally connected, the path is a combination of interconnected roads. Therefore, when the route becomes longer and the amount of data increases, the performance of using a graph database for solving can still remain relatively stable. In the graph database, the public transportation passenger capacity objective function is part of the query graph. The execution time of each query is only proportional to the size of the graph that meets the conditions, not the size of the entire graph. Therefore, this embodiment uses a graph database to obtain and store public road network data, and constructs a graph model based on the graph database for solving. Public road network data includes two main types of data: road way and location node. A way is composed of multiple nodes, and intersecting roads have the same node. Combined with data such as bus routes and stations, a graph model can be constructed. The graph model includes four types of label nodes and five types of relationships. Nodes: 1. Way node (including road id, road name, road length and other attributes); 2. Node node (including node_id, node longitude and latitude coordinates and other attributes); 3. Station node (including station_id, station name, station longitude and latitude coordinates and other attributes); 4. Route node (including bus route id, bus route name). Relationships: 1. (way)-[:own_1]->(node): a one-to-many relationship between roads and nodes; 2. (way)-[:have]->(station): a one-to-many relationship between roads and bus stations; 3. (way)-[:connect]->(way): a connection relationship between roads; 4. (route)-[:track]->(way): a one-to-many relationship between bus routes and roads; 5. (route)-[:own_2]->(node): a one-to-many relationship between bus routes and stations. For details, see Figure 3As shown. In addition to using the graph database to build a graph model, the public transportation passenger capacity objective function is iteratively solved according to the preset constraint rules to obtain the rail transit shuttle line in the rail transit shuttle target area. The preset constraint rules include: the rail transit shuttle line starts from the target grid and arrives at the subway station. The target grid is determined according to the distance from the station in the public transportation data; the rail transit shuttle line route is within the rail transit shuttle target area; there are no duplicate roads in the rail transit shuttle line route; the rail transit shuttle line route itself does not intersect; the length of the rail transit shuttle line route is less than the preset length threshold; the non-linear coefficient of the rail transit shuttle line route is less than the preset coefficient threshold; the non-linear coefficient = the length of the rail transit shuttle line route / the straight-line distance to the nearest station. The maximum similarity between the rail transit shuttle line route and the existing bus route is less than the preset similarity threshold; the maximum similarity = the maximum proportion of the intersection of the rail transit shuttle line route and the existing bus route and the union of the rail transit shuttle line route and the existing bus route; the number of bus stops passed by the rail transit shuttle line route is within the preset stop threshold range; the average distance between stops in the rail transit shuttle line route is within the preset distance threshold range; the maximum distance between stops in the rail transit shuttle line route does not exceed the preset stop distance threshold, etc. The above various thresholds are set according to the specific implementation situation and are not limited here. The graph model constructed using the graph database directly expresses the solution of the public transportation passenger capacity objective function as an iterative query of the path relationship, and the preset constraint rules are converted into restriction conditions for the iterative query. For example, if the preset constraint rule states that the rail transit shuttle line starts from the target grid and arrives at the subway station, this can be achieved by using the node longitude and latitude, as well as the own relationship between the way and the node; if the preset constraint rule states that the length of the rail transit shuttle line is less than the preset length threshold, this can be achieved by using the line length constraint of the attribute value of the way contained in the rail transit shuttle line. There is no need to use other planning algorithms, and the public transportation passenger capacity objective function can be directly solved iteratively for the lines that meet the requirements. This reduces the time complexity and overcomes the problem that the algorithm result is only a local optimal solution, thus truly providing the global optimal solution for the rail transit shuttle line. The iterative solution code for the public transportation passenger capacity objective function is as follows:

[0053] --Preset constraint rules: The rail transit connection line starts from the target grid and arrives at the subway station

[0054] MATCH(a:node),(b:node)

[0055] WHERE a.lng>lng1_min AND a.lng <lng2_max

[0056] AND a.lat>lat1_min AND a.lat <lat1_max

[0057] AND b.lng>lng2_min AND b.lng <lng2_max

[0058] AND b.lat>lat2_min AND b.lat <lat2_max

[0059] WITH a,b

[0060] MATCH(o:way)-[:own]->(a), (d:way)-[:own]->(b)

[0061] --Preset constraint rule: The length of the rail transit connection line is less than the preset length threshold

[0062] MATCH path=(o:way)-[:connect*1..10]->(d:way)

[0063] UNWIND NODES(path)AS n

[0064] WITH path,sum(n.dis)as way_dis

[0065] WHERE way_dis>=S

[0066] The above is an example for explanation. The corresponding code is used according to the specific implementation situation and is not limited here.

[0067] The rail transit shuttle line design of this embodiment is to maximize the passenger capacity per unit mileage of the rail transit shuttle line, and each time a single rail transit shuttle line is taken as the object. If the existing resources can design multiple rail transit shuttle lines or multiple rail transit shuttle lines are designed at the same time according to the needs, multiple screening and design can be performed, and each time the flow prediction results of the designed rail transit shuttle line are added to the bus lines / flows of the existing public transportation data to obtain the optimal rail transit shuttle line design plan under the current conditions in each round, and finally multiple rail transit shuttle lines with priority sorting are obtained.

[0068] According to the rail transit shuttle line design method provided by the present invention, the user OD trajectory information is obtained; the user OD trajectory information is screened to obtain the user's private transportation travel information; the user multi-dimensional data corresponding to the user's private transportation travel information is collected, and the public transportation travel acceptance is predicted according to the user multi-dimensional data, and the target user's private transportation travel information corresponding to the target user whose public transportation travel acceptance is higher than the preset threshold is determined; according to the target departure point information and the target destination information in the target user's private transportation travel information, the rail transit shuttle target area is screened and the public transportation passenger capacity objective function is constructed, and the public transportation passenger capacity objective function is processed using a graph database to obtain the rail transit shuttle line in the rail transit shuttle target area; wherein the public transportation passenger capacity objective function is constructed according to the rail transit shuttle target area and public transportation data. The user's private transportation travel information is obtained by screening the user's OD trajectory information. Based on the user's private transportation travel information, guidance is carried out, the target user who intends to choose public transportation travel is identified, the target user's private transportation travel information is designed, and the rail transit shuttle line is determined, which can maximize the conversion of private transportation travel to public transportation travel and ensure the passenger capacity of the rail transit shuttle line. Furthermore, the public transportation passenger capacity objective function is processed using the graph model of the graph database, which greatly reduces the time complexity of the calculation and obtains the rail transit connection lines more accurately.

[0069] Figure 4 FIG. 4 shows a functional block diagram of a rail transit connection line design device according to an embodiment of the present invention. Figure 4 As shown, the rail transit connection line design device includes the following modules:

[0070] An acquisition module 410, adapted to acquire user OD trajectory information;

[0071] A screening module 420 is adapted to screen the user's OD trajectory information to obtain the user's private transportation information;

[0072] The prediction module 430 is adapted to collect multi-dimensional user data corresponding to the user's private transportation information, and perform public transportation acceptance prediction based on the multi-dimensional user data to determine the target user's private transportation information corresponding to the target user whose public transportation acceptance is higher than a preset threshold;

[0073] The solution module 440 is suitable for screening out the rail transit connection target area and constructing the public transportation passenger capacity target function according to the target departure point information and the target destination information in the target user's private transportation travel information, and using the graph database to process the public transportation passenger capacity target function to obtain the rail transit connection lines within the rail transit connection target area; wherein the public transportation passenger capacity target function is constructed based on the rail transit connection target area and public transportation data.

[0074] Optionally, the acquisition module 410 is further adapted to: acquire user OD trajectory information according to signaling data of a user's mobile device.

[0075] Optionally, the acquisition module 410 is further suitable for: acquiring signaling data of a user's mobile device; preprocessing the signaling data; the preprocessing includes: trajectory angle filtering, trajectory dynamic interpolation, and base station trajectory grid mapping; filtering the preprocessed signaling data based on a grid continuous stay time threshold, sorting the signaling data according to the time, and acquiring the user's OD trajectory information.

[0076] Optionally, the screening module 420 is further adapted to: extract the moving distance and / or speed in the user's OD trajectory information; and screen the user's private transportation travel information according to the moving distance and / or speed in combination with public transportation data.

[0077] Optionally, the filtering module 420 is further adapted to: detect the moving distance and / or speed to remove the walking trajectory information; detect according to the station information and / or GPS data contained in the public transportation data, remove the public transportation travel information, and filter out the user's private transportation travel information in the user's OD trajectory information.

[0078] Optionally, the prediction module 430 is further adapted to: collect user multi-dimensional data corresponding to the user's private transportation travel information; the user multi-dimensional data includes: user identity data, user communication data, user social data, user consumption data and / or user network data; use a regression model to predict public transportation travel acceptance based on the user's multi-dimensional data; determine the target users whose public transportation travel acceptance is higher than a preset threshold based on the predicted public transportation travel acceptance, and determine the target user's private transportation travel information.

[0079] Optionally, the solution module 440 is further adapted to: determine the distance from the station in the public transportation data according to the target departure point information and the target destination information in the private transportation information of the target user; determine the rail transit connection target area according to the distance from the station in the public transportation data; construct a public transportation passenger capacity objective function according to the rail transit connection target area and the public transportation data; use the public road network data stored in the graph database, and iteratively solve the public transportation passenger capacity objective function according to the preset constraint rules to obtain the rail transit connection line in the rail transit connection target area; wherein the preset constraint rules include: the rail transit connection line starts from the target grid and arrives at the subway station point, the target grid is determined according to the distance from the station in the public transportation data; the rail transit shuttle line route is within the rail transit shuttle target area; there are no duplicate roads in the rail transit shuttle line route; the rail transit shuttle line route itself does not intersect; the length of the rail transit shuttle line route is less than the preset length threshold; the non-linear coefficient of the rail transit shuttle line route is less than the preset coefficient threshold; the maximum similarity between the rail transit shuttle line route and the existing bus routes is less than the preset similarity threshold; the number of bus stops passed by the rail transit shuttle line route is within the preset station threshold range; the average distance between stations in the rail transit shuttle line route is within the preset distance threshold range; and / or the maximum distance between stations in the rail transit shuttle line route does not exceed the preset station distance threshold.

[0080] The description of each module above refers to the corresponding description in the method embodiment and will not be repeated here.

[0081] The present application also provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the rail transit connection line design method in any of the above method embodiments.

[0082] Figure 5 A schematic structural diagram of an electronic device according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the electronic device.

[0083] like Figure 5 As shown, the electronic device may include: a processor (processor) 502 , a communication interface (Communications Interface) 504 , a memory (memory) 506 , and a communication bus 508 .

[0084] in:

[0085] The processor 502 , the communication interface 504 , and the memory 506 communicate with each other via a communication bus 508 .

[0086] The communication interface 504 is used to communicate with other devices such as clients or other servers.

[0087] The processor 502 is used to execute the program 510, and specifically can execute the relevant steps in the above-mentioned rail transit connection line design method embodiment.

[0088] Specifically, the program 510 may include program codes, which include computer operation instructions.

[0089] The processor 502 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0090] The memory 506 is used to store the program 510. The memory 506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0091] The program 510 can be specifically used to enable the processor 502 to execute the rail transit shuttle line design method in any of the above-mentioned method embodiments. The specific implementation of each step in the program 510 can refer to the corresponding descriptions in the corresponding steps and units in the above-mentioned rail transit shuttle line design embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described devices and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0092] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0093] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0094] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all of the features of the individual embodiments previously disclosed. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0095] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0096] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0097] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the rail transit connection line design device according to an embodiment of the present invention. The present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0098] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A rail transit connection line design method, characterized in that: Methods include: Get user OD trajectory information; Filtering the user's OD trajectory information to obtain the user's private transportation information; Collect multi-dimensional data of users corresponding to their private transportation information; The user multi-dimensional data includes: user identity data, user communication data, user social data, user consumption data and / or user network data; using a regression model to predict public transportation travel acceptance based on the user multi-dimensional data; determining target users whose public transportation travel acceptance is higher than a preset threshold based on the predicted public transportation travel acceptance, and determining the target user's private transportation travel information; According to the target departure point information and the target destination information in the private transportation travel information of the target user, the rail transit connection target area is screened out and the public transportation passenger capacity target function is constructed, and the public transportation passenger capacity target function is processed using a graph database to obtain the rail transit connection lines within the rail transit connection target area; wherein the public transportation passenger capacity target function is constructed based on the rail transit connection target area and public transportation data.

2. The method according to claim 1, characterized in that The obtaining of user OD trajectory information further includes: Obtain user OD trajectory information based on the signaling data of the user's mobile device.

3. The method according to claim 2, characterized in that The obtaining of user OD trajectory information according to the signaling data of the user's mobile device further includes: Obtain signaling data from the user's mobile device; Preprocessing the signaling data; the preprocessing includes: trajectory angle filtering, trajectory dynamic interpolation and base station trajectory grid mapping; The pre-processed signaling data is filtered based on the grid continuous residence time threshold, and the signaling data is sorted according to the time to obtain the user OD trajectory information.

4. The method according to claim 1, characterized in that: The filtering of the user's OD trajectory information to obtain the user's private transportation information further includes: Extracting the moving distance and / or speed in the user OD trajectory information; The user's private transportation travel information is obtained by screening according to the moving distance and / or speed in combination with public transportation data.

5. The method according to claim 4, characterized in that The obtaining of the user's private transportation information by screening according to the moving distance and / or speed in combination with public transportation data further includes: Detecting the moving distance and / or speed and removing walking track information; According to the station information and / or GPS data contained in the public transportation data, the public transportation travel information is removed, and the user's private transportation travel information in the user's OD trajectory information is screened out.

6. The method according to claim 1, characterized in that The method further comprises: screening out a rail transit connection target area and constructing a public transportation passenger capacity target function according to the target departure point information and the target destination information in the private transportation travel information of the target user, and processing the public transportation passenger capacity target function by using a graph database to obtain a rail transit connection line in the rail transit connection target area. Determine the distance from the station in the public transportation data according to the target departure point information and the target destination information in the private transportation travel information of the target user; Determine the target area for rail transit connection according to the distance from the station in the public transportation data; Constructing a public transportation passenger volume objective function based on the rail transit connection target area and public transportation data; The public road network data stored in the graph database is used, and the public transportation passenger capacity objective function is iteratively solved according to the preset constraint rules to obtain the rail transit shuttle line in the rail transit shuttle target area; wherein the preset constraint rules include: the rail transit shuttle line starts from the target grid and arrives at the subway station, and the target grid is determined according to the distance from the station in the public transportation data; the rail transit shuttle line route is within the rail transit shuttle target area; there are no repeated roads in the rail transit shuttle line route; the rail transit shuttle line route itself does not intersect; the length of the rail transit shuttle line route is less than the preset length threshold; the non-linear coefficient of the rail transit shuttle line route is less than the preset coefficient threshold; the maximum similarity between the rail transit shuttle line route and the existing bus route is less than the preset similarity threshold; the number of bus stops passed in the rail transit shuttle line route is within the preset station threshold range; the average distance between stations in the rail transit shuttle line route is within the preset distance threshold range; and / or the maximum distance between stations in the rail transit shuttle line route does not exceed the preset station distance threshold.

7. A rail transit connection line design device, characterized in that: The device includes: An acquisition module, adapted to acquire user OD trajectory information; A screening module, adapted to screen the user's OD trajectory information to obtain the user's private transportation information; A prediction module, suitable for collecting multi-dimensional data of users corresponding to their private transportation information; The user multi-dimensional data includes: user identity data, user communication data, user social data, user consumption data and / or user network data; using a regression model to predict public transportation travel acceptance based on the user multi-dimensional data; determining target users whose public transportation travel acceptance is higher than a preset threshold based on the predicted public transportation travel acceptance, and determining the target user's private transportation travel information; The solution module is suitable for screening out the rail transit connection target area and constructing the public transportation passenger capacity target function according to the target departure point information and the target destination information in the private transportation travel information of the target user, and using the graph database to process the public transportation passenger capacity target function to obtain the rail transit connection line within the rail transit connection target area; wherein, the public transportation passenger capacity target function is constructed according to the rail transit connection target area and public transportation data.

8. An electronic device, comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the rail transit connection line design method according to any one of claims 1-6.

9. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute operations corresponding to the rail transit connection line design method as described in any one of claims 1 to 6.

Images