Method and device for determining vehicle driving route, storage medium and electronic equipment

Abstract

Embodiments of the present application provide a vehicle driving route determination method and device, a storage medium and an electronic device, wherein the method comprises: determining a demand matrix, wherein the demand matrix comprises a time sequence, a station set and a demand set, the time sequence is a time interval in which an object has a demand for a ride, the station set comprises stations in a predetermined area that allow a target vehicle to arrive, and the demand set comprises a plurality of objects issuing a demand for a ride that meets the time sequence and a demand quantity with the same demand for a ride; extracting a demand for a ride between any two stations within a sliding time window from the demand matrix; determining a line search queue based on the demand for a ride between any two stations; and determining a target driving route from the line search queue. Through the present application, the problem of low planning efficiency and poor flexibility of the vehicle driving route in the related art is solved, and the effect of flexibly and efficiently planning the driving route of the vehicle is achieved.

Description

Technical Field

[0001] This application relates to the field of computers, and more specifically, to a method and apparatus for determining a vehicle's driving route, a storage medium, and an electronic device. Background Technology

[0002] Traditional public transportation (e.g., buses) has drawbacks for users, such as frequent stops, lack of seating, unpredictable schedules, and the need for transfers. For operators, traditional buses have high operating costs and it's difficult to accurately schedule appropriate frequencies for specific routes. Adhering to the principles of adapting to urban development, meeting user needs, and balancing the interests of operators, and from the perspective of minimizing social costs and maximizing social benefits, public transportation network optimization models are gradually shifting from single-objective models to multi-objective models.

[0003] Current technologies, such as genetic algorithms and ant colony algorithms, plan vehicle routes based on specific time points and inherent needs, configuring vehicle operation schemes accordingly. However, the origin and destination of vehicle operations are relatively fixed, failing to consider both operating costs and diverse user needs. This approach has poor practical application, generally neglects user requirements, lacks real-time capability, and offers little response to actual traffic conditions. Summary of the Invention

[0004] This application provides a method and apparatus for determining vehicle driving routes, a storage medium, and an electronic device, to at least solve the problems of low efficiency and poor flexibility in planning vehicle driving routes in related technologies.

[0005] According to one embodiment of this application, a method for determining a vehicle travel route is provided, comprising: determining a demand matrix, wherein the demand matrix includes a time series, a station set, and a demand set, wherein the time series is a time interval in which an object has a travel demand, the station set includes stations in a preset area that the target vehicle is allowed to reach, and the demand set includes multiple travel demands issued by the object that satisfy the time series and the number of demands with the same travel demand; extracting travel demands between any two stations within a sliding time window from the demand matrix, wherein the sliding time window is a time interval in the time series, and the any two stations are stations in the station set; determining a route search queue based on the travel demands between the any two stations, wherein the stations included in the route search queue satisfy the requirement that the travel time of the object between the any two stations is greater than a preset time; and determining a target travel route from the route search queue, wherein the target travel route is the shortest route that satisfies the travel demands within the sliding time window.

[0006] In one exemplary embodiment, determining a target driving route from the route search queue includes: sorting multiple driving routes in the route search queue using a fully connected matrix, determining the longest driving route among the multiple driving routes, wherein the longest driving route is the route with the greatest distance between any two stations, and the fully connected matrix includes the shortest distance between any two of the stations; and searching the route search queue using the longest driving route to determine the target driving route.

[0007] In one exemplary embodiment, determining the target travel route by searching the route search queue using the longest possible travel route includes: deleting the longest possible travel route from the route search queue to obtain a target route search queue; determining the target start station and target end station of the travel demand from the target route search queue; constructing a search tree using the target start station and the target end station, wherein the target end station is the root node of the search tree and the target start station is the end node of the search tree; and searching for the target travel route in the search tree.

[0008] In an exemplary embodiment, constructing a search tree using the target starting station and the target ending station includes: sliding the sliding time window to search for intermediate stations in the demand matrix that satisfy the target ending node and the target starting node; determining child nodes between the target ending node and the target starting node, wherein the child nodes satisfy preset constraints, the preset constraints including at least one of the following: the maximum capacity of the target vehicle, the number of stops for the target vehicle, the time for the target vehicle to arrive at the target ending station is less than the time for the object to arrive at the target ending station, and the ride demand includes the intermediate stations; and constructing the search tree using the target ending node, the target starting node, and the child nodes.

[0009] In an exemplary embodiment, searching for the target driving route in the search tree includes: calculating a score for each path in the search tree, wherein each path includes a target termination node, a target start node, and corresponding child nodes, and the score for each path is calculated in reverse from the target termination node to the target start node, and the score of each path is used to represent each path; determining the target driving route based on the score of each path, wherein the demand quantity corresponding to the target driving route satisfies a preset quantity.

[0010] In an exemplary embodiment, before sorting multiple driving routes in the route search queue using a fully connected matrix and determining the farthest driving route among the multiple driving routes, the method further includes: constructing a vertex set using the location information of each of the stations in the acquired station set, wherein the vertex set includes a station vertex set and an intersection vertex set, the station vertex set is used to determine the driving route, and the intersection vertex set is used to determine the stations in the driving route; determining the directed connection relationships between the multiple stations to obtain an edge set; constructing a station map in the preset area using the vertex set and the edge set; and determining an adjacency matrix and the fully connected matrix based on the station map, wherein the adjacency matrix is ​​used to determine the child nodes in the route search queue, and the fully connected matrix includes the shortest distance between two stations.

[0011] In an exemplary embodiment, before determining the demand matrix, the method further includes: obtaining ride information sent by the object, wherein the ride information includes the object's identification information, the object's boarding station, the object's alighting station, and the time of arrival at the alighting station; determining the demand set according to the ride information; and selecting the target vehicle if the number of demands in the demand set is less than a first preset threshold and the peak number of objects within the time interval is less than a second preset threshold.

[0012] In an exemplary embodiment, before determining the demand matrix, the method further includes: determining constraints, wherein the constraints include at least one of the following: the time it takes for the object to arrive at the station, the maximum capacity of the vehicle, the number of stations the vehicle stops at, the vehicle fare, the number of objects on the route the vehicle operates, the ratio between the vehicle's speed and the object's speed, the time interval, the number of objects allowed to get on and off the vehicle at the station within a preset time period, the peak number of objects in the vehicle, the time it takes for the object to arrive at the destination station; the time it takes for the vehicle to arrive at the station is less than the time it takes for the object to arrive at the station, the conditions for the vehicle to stop at the station, and multiple objects with the same travel demand being assigned to the same vehicle.

[0013] According to another embodiment of this application, a vehicle route determination device is provided, comprising: a first determining module, configured to determine a demand matrix, wherein the demand matrix includes a time series, a station set, and a demand set, wherein the time series is a time interval in which an object has a travel demand, the station set includes stations in a preset area that the target vehicle is allowed to reach, and the demand set includes multiple travel demands issued by the object that satisfy the time series and the number of demands with the same travel demand; a first extraction module, configured to extract travel demands between any two stations within a sliding time window from the demand matrix, wherein the sliding time window is a time interval in the time series, and the any two stations are stations in the station set; a second determining module, configured to determine a route search queue based on the travel demands between the any two stations, wherein the stations included in the route search queue satisfy the requirement that the travel time of the object between the any two stations is greater than a preset time; and a third determining module, configured to determine a target travel route from the route search queue, wherein the target travel route is the shortest route that satisfies the travel demand within the sliding time window.

[0014] In an exemplary embodiment, the first determining module includes: a first determining submodule, configured to sort multiple driving routes in the route search queue using a fully connected matrix, and determine the longest driving route among the multiple driving routes, wherein the longest driving route is the route with the greatest distance between any two stations, and the fully connected matrix includes the shortest distance between any two stations; and a second determining submodule, configured to search the route search queue using the longest driving route to determine the target driving route.

[0015] In one exemplary embodiment, the second determining submodule includes: a first deletion unit, configured to delete the longest travel route from the route search queue to obtain a target route search queue; a first determining unit, configured to determine the target starting station and target ending station of the travel demand from the target route search queue; a first constructing unit, configured to construct a search tree using the target starting station and the target ending station, wherein the target ending station is the root node of the search tree and the target starting station is the end node of the search tree; and a first searching unit, configured to search for the target travel route in the search tree.

[0016] In an exemplary embodiment, the first construction unit includes: a first determining subunit, configured to slide the sliding time window, search in the demand matrix for intermediate stations that satisfy the target termination node and the target starting node, and determine child nodes between the target termination node and the target starting node, wherein the child nodes satisfy preset constraints, the preset constraints including at least one of the following: the maximum capacity of the target vehicle, the number of stops for the target vehicle, the time for the target vehicle to arrive at the target termination station is less than the time for the object to arrive at the target termination station, and the ride demand includes the intermediate stations; the first construction subunit is configured to construct the search tree using the target termination node, the target starting node, and the child nodes.

[0017] In an exemplary embodiment, the first search unit includes: a first calculation subunit, configured to calculate a score for each path in the search tree, wherein each path includes a target termination node, a target start node, and corresponding child nodes, and the score for each path is calculated in reverse from the target termination node to the target start node, and the score for each path represents each path; and a second determination subunit, configured to determine the target driving route based on the score for each path, wherein the number of requirements corresponding to the target driving route meets a preset number.

[0018] In an exemplary embodiment, the apparatus further includes: a first construction submodule, configured to sort multiple driving routes in the route search queue using a fully connected matrix, and before determining the farthest driving route among the multiple driving routes, construct a vertex set using the location information of each of the stations in the acquired station set, wherein the vertex set includes a station vertex set and an intersection vertex set, the station vertex set being used to determine the driving route, and the intersection vertex set being used to determine the stations in the driving route; a third determination submodule, configured to determine the directed connection relationships between the multiple stations to obtain an edge set; a second construction submodule, configured to construct a station map in the preset area using the vertex set and the edge set; and a fourth determination submodule, configured to determine an adjacency matrix and the fully connected matrix based on the station map, wherein the adjacency matrix being used to determine child nodes in the route search queue, and the fully connected matrix including the shortest distance between two stations.

[0019] In one exemplary embodiment, the apparatus further includes: a first acquisition module, configured to acquire ride information sent by the object before determining the demand matrix, wherein the ride information includes the object's identification information, the object's boarding station, the object's alighting station, and the time point of arrival at the alighting station; a fourth determination module, configured to determine the demand set according to the ride information; and a first selection module, configured to select the target vehicle when the number of demands in the demand set is less than a first preset threshold and the peak number of objects within the time interval is less than a second preset threshold.

[0020] In an exemplary embodiment, the apparatus further includes a fifth determining module, configured to determine constraints before determining the demand matrix, wherein the constraints include at least one of the following: the time it takes for the object to arrive at the station, the maximum capacity of the vehicle, the number of stations the vehicle stops at, the vehicle fare, the number of objects on the route the vehicle operates, the ratio between the vehicle's speed and the object's speed, the time interval, the number of objects allowed to get on and off the vehicle at the station within a preset time period, the peak number of objects in the vehicle, the time it takes for the object to arrive at the destination station; the time it takes for the vehicle to arrive at the station being less than the time it takes for the object to arrive at the station, the conditions for the vehicle to stop at the station, and multiple objects with the same travel demand being assigned to the same vehicle.

[0021] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and the computer program is configured to perform the steps in any of the above method embodiments when it is run.

[0022] According to yet another embodiment of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0023] This application addresses the issue that the determined demand matrix includes the three essential elements for route planning: time series, station set, and demand set. Based on this matrix, a sliding time window approach is used to determine the travel demand between any two stations. A route search queue is then established according to the travel demand. A fully connected matrix is ​​used to sort the multiple routes in the route search queue, and a search tree is used to score and remove constraints from these routes. This allows for the efficient and accurate determination of the target vehicle's route within the sliding time window. Therefore, this solution overcomes the problems of low efficiency and poor flexibility in related technologies for vehicle route planning, achieving a more flexible and efficient approach to vehicle route planning. Attached Figure Description

[0024] Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of determining a vehicle driving route according to an embodiment of this application.

[0025] Figure 2 This is a flowchart of a method for determining a vehicle driving route according to an embodiment of this application;

[0026] Figure 3 This is a sliding time window diagram of a method for determining a vehicle driving route according to an embodiment of this application;

[0027] Figure 4 This is a functional module diagram for determining the bus route in this specific embodiment;

[0028] Figure 5 This is an interaction diagram of the functional modules in a specific embodiment of this application;

[0029] Figure 6 It is a graph showing the shortest Euclidean distance for determining bus routes;

[0030] Figure 7 This is a flowchart of the map module constructing a map in this specific embodiment;

[0031] Figure 8 This is a flowchart illustrating the selection of a vehicle in a specific embodiment of this application;

[0032] Figure 9 These are time window graphs of the search sliding in different directions;

[0033] Figure 10 This is a search example diagram of a specific embodiment of this application;

[0034] Figure 11 This is a backtracking score graph of each route in a specific embodiment of this application;

[0035] Figure 12 This is a structural block diagram of a vehicle driving route determination according to an embodiment of this application. Detailed Implementation

[0036] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples.

[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0038] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1This is a hardware structure block diagram of a mobile terminal for a method of determining a vehicle driving route according to an embodiment of this application. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0039] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the vehicle route determination method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the aforementioned method. The memory 104 may include high-speed random access memory and 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 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0040] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0041] This embodiment provides a method that runs on the aforementioned mobile terminal. Figure 2 This is a flowchart of a method for determining a vehicle driving route according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0042] Step S202: Determine the demand matrix, wherein the demand matrix includes a time series, a set of stations, and a set of demands. The time series is the time interval during which the object has a travel demand. The set of stations includes stations in a preset area that the target vehicle is allowed to reach. The set of demands includes multiple travel demands issued by the object that satisfy the time series and the number of demands with the same travel demand.

[0043] Step S204: Extract the travel demand between any two stations within the sliding time window from the above demand matrix, wherein the above sliding time window is a time interval in the above time series, and the above any two stations are stations in the above set of stations.

[0044] Step S206: Determine a route search queue based on the travel demand between any two stations, wherein the stations included in the route search queue satisfy the requirement that the travel time of the object between any two stations is greater than a preset time.

[0045] Step S208: Determine the target travel route from the above-mentioned route search queue, wherein the target travel route is the shortest route that satisfies the travel demand within the above-mentioned sliding time window.

[0046] The entity performing the above steps may be a terminal, a server, a specific processor set in the terminal or server, or a processor or processing device set up relatively independently of the terminal or server, but is not limited to these.

[0047] Optionally, the time series in this embodiment can be in minutes. The preset area can be a road segment where public vehicles need to be deployed, for example, an area from the city center to the suburbs of a city.

[0048] Optionally, travel requests include, but are not limited to, departure point, destination, departure time, and preset arrival time. The request set includes travel requests from multiple objects within the time interval.

[0049] Optionally, the sliding time window can be any period within a time interval. For example, if object A's travel request includes a preset arrival time at the travel station of 14:00, and they need to arrive at the travel station 20 minutes in advance, then the sliding time window can be 14:00-14:20. The larger the sliding time window, the more travel requests it can satisfy, the more people can travel on the route, and the fewer vehicles will be running simultaneously. Figure 3 The diagram shown is a sliding time window diagram of a method for determining a vehicle driving route according to an embodiment of this application. The sliding time window can be a time period between t0 and t20, where t0 is the demand that needs to be considered at the moment.

[0050] Optionally, the demand matrix uses a sliding time window to add the set of stations that meet the current urgent travel needs to the route search queue.

[0051] Through the above steps, since the determined demand matrix includes the three elements needed for route planning: time series, station set, and demand set; based on the demand matrix, the travel demand between any two stations is determined using a sliding time window method; a route search queue is determined based on travel demand; multiple routes in the route search queue are sorted using a fully connected matrix, and multiple routes are scored and constraints removed according to the search tree, thus efficiently and accurately determining the target travel route of the target vehicle within the sliding time window. Therefore, the problems of low efficiency and poor flexibility in vehicle route planning of related technologies can be solved, thereby achieving the effect of flexible and efficient vehicle route planning.

[0052] In one exemplary embodiment, determining a target driving route from the route search queue includes: sorting multiple driving routes in the route search queue using a fully connected matrix, determining the longest driving route among the multiple driving routes, wherein the longest driving route is the route with the greatest distance between any two stations, and the fully connected matrix includes the shortest distance between any two of the stations; and searching the route search queue using the longest driving route to determine the target driving route.

[0053] Optionally, in this embodiment, the fully connected matrix can be constructed based on a site map and Dijkstra's algorithm, with the elements in the fully connected matrix representing the shortest distance values ​​between each site. This embodiment achieves the goal of quickly obtaining the starting and ending sites of all reachable routes by sorting the route search queue using the fully connected matrix.

[0054] In one exemplary embodiment, determining the target travel route by searching the route search queue using the longest possible travel route includes: deleting the longest possible travel route from the route search queue to obtain a target route search queue; determining the target start station and target end station of the travel demand from the target route search queue; constructing a search tree using the target start station and the target end station, wherein the target end station is the root node of the search tree and the target start station is the end node of the search tree; and searching for the target travel route in the search tree.

[0055] Optionally, in this embodiment, the longest driving route is removed from the route search queue, and the requirements satisfied by the longest driving route are removed from the requirement matrix, while the requirements not satisfied are retained. This embodiment achieves the purpose of avoiding blindly searching for starting points and reducing the search range by removing the longest driving route from the route search queue.

[0056] In an exemplary embodiment, constructing a search tree using the target starting station and the target ending station includes: sliding the sliding time window to search for intermediate stations in the demand matrix that satisfy the target ending node and the target starting node; determining child nodes between the target ending node and the target starting node, wherein the child nodes satisfy preset constraints, and the preset constraints include at least one of the following: the maximum capacity of the target vehicle, the number of stops for the target vehicle, the time for the target vehicle to arrive at the target ending station is less than the time for the object to arrive at the target ending station, and the travel demand includes the intermediate stations; and constructing the search tree using the target ending node, the target starting node, and the child nodes. Optionally, in this embodiment, the intermediate stations constitute child nodes between the target ending node and the target starting node, thereby enabling rapid construction of the search tree.

[0057] In an exemplary embodiment, searching for the target driving route in the search tree includes: calculating a score for each path in the search tree, wherein each path includes a target termination node, a target start node, and corresponding child nodes, and the score for each path is calculated in reverse from the target termination node to the target start node, and the score of each path is used to represent each path; determining the target driving route based on the score of each path, wherein the demand quantity corresponding to the target driving route satisfies a preset quantity.

[0058] Optionally, in this embodiment, a reverse station search (from the target termination station to the target origin station) is used to calculate the score of each path. The score can be calculated using a dynamic programming strategy: score function = path benefit - travel time - number of path nodes, constructing an iterative deepening backtracking algorithm. This embodiment calculates the path score through reverse backtracking, achieving the goal of efficiently searching for the target travel route.

[0059] In an exemplary embodiment, before sorting multiple driving routes in the route search queue using a fully connected matrix and determining the farthest driving route among the multiple driving routes, the method further includes: constructing a vertex set using the location information of each of the stations in the acquired station set, wherein the vertex set includes a station vertex set and an intersection vertex set, the station vertex set is used to determine the driving route, and the intersection vertex set is used to determine the stations in the driving route; determining the directed connection relationships between the multiple stations to obtain an edge set; constructing a station map in the preset area using the vertex set and the edge set; and determining an adjacency matrix and the fully connected matrix based on the station map, wherein the adjacency matrix is ​​used to determine the child nodes in the route search queue, and the fully connected matrix includes the shortest distance between two stations.

[0060] Optionally, in this embodiment, the site map is a manually drawn directed graph, including stations and intersections, used to simulate actual driving routes. The constructed directed graph can store the vertex set in a document, allowing for expansion and modification at any time. Simultaneously, the vertex set data document can be exported in reverse, enabling modifications to the vertex set relationships within the program. The main form is V=<ID,N,P,C>, where ID is the unique identifier index of the vertex, N is the vertex name, P is the vertex position coordinates, and C is the set of IDs of reachable adjacent vertices. A vertex can be represented as: The set of edges E can be represented as: e ij =Euclidean(p i ,p j The shortest distance is calculated using Euclidean distance, which exhibits trigonometric properties, meaning the target route is always the shortest path. This embodiment improves the scalability of route planning by digitizing a graphical map.

[0061] In an exemplary embodiment, before determining the demand matrix, the method further includes: obtaining ride information sent by the object, wherein the ride information includes the object's identification information, the object's boarding station, the object's alighting station, and the time of arrival at the alighting station; determining the demand set according to the ride information; and selecting the target vehicle if the number of demands in the demand set is less than a first preset threshold and the peak number of objects within the time interval is less than a second preset threshold.

[0062] Optionally, in this embodiment, the passenger information can be obtained from the ride-hailing platform, and the identification information of the object can be the account ID of the passenger. The first preset threshold is the maximum capacity of the shuttle bus, which is a vehicle that runs directly from the starting station to the ending station. The second preset threshold is the maximum capacity of the target vehicle, for example, a bus with a passenger capacity of 30 people. This embodiment achieves the purpose of accurately allocating vehicles by determining the demand set according to the passenger information.

[0063] In an exemplary embodiment, before determining the demand matrix, the method further includes: determining constraints, wherein the constraints include at least one of the following: the time it takes for the object to arrive at the station, the maximum capacity of the vehicle, the number of stations the vehicle stops at, the vehicle fare, the number of objects on the route the vehicle operates, the ratio between the vehicle's speed and the object's speed, the time interval, the number of objects allowed to get on and off the vehicle at the station within a preset time period, the peak number of objects in the vehicle, the time it takes for the object to arrive at the destination station; the time it takes for the vehicle to arrive at the station is less than the time it takes for the object to arrive at the station, the conditions for the vehicle to stop at the station, and multiple objects with the same travel demand being assigned to the same vehicle.

[0064] Optionally, the above constraints can be specifically as follows: passengers arrive at their destination no earlier than a preset time by 20 minutes; the maximum vehicle capacity is 50 people; the route stops at a maximum of 6 stations (including the starting and ending stations); the fare is 5 yuan; the route can be opened if it meets the needs of 10 people; the ratio of bus speed to walking speed is used to adjust the curvature of the route; the time range for passenger travel demand is from 8:00 AM to 10:00 PM; 20 people can get on and off the bus per minute after it arrives at a station; the peak number of passengers on the bus does not exceed 50; the time to reach the destination by bus must be less than the time to reach the destination by walking; no buses will operate between two stations within a 10-minute walk; no stops will be made at stations without passenger demand; passengers with the same needs will not be split between two buses (except for shuttle buses). Among these, the ratio of vehicle speed to passenger speed is such that the closer the ratio is to 0, the more likely the bus is to visit previously passed stops; the closer the ratio is to 1, the straighter the route. This embodiment, through the above constraints, can meet the passenger demand and quickly obtain the target route.

[0065] The present invention will now be described in conjunction with specific embodiments:

[0066] This specific embodiment is illustrated by determining the bus's route, such as... Figure 4 The diagram shown is a functional block diagram for determining the bus route in this specific embodiment, including: a map module, a user module, a vehicle module, a demand processing module, and a route module. Among them,

[0067] The map module is used to build a directed graph of stations and intersections to simulate actual driving routes;

[0068] The user module is used to collect basic information and travel information of users (e.g., passengers who need to take a bus) and distribute the received target travel routes to specific users.

[0069] The vehicle module is used to determine the type of vehicle, that is, to store vehicle information and vehicle quantity information, and to provide constraints for finding the target driving route;

[0070] The demand processing module is used to process a large number of user demands (i.e., travel demands), collect constraints, construct a sliding time window and a target route search queue, thereby determining the target origin station and the target destination station.

[0071] The route module is used to perform route search using the improved IDA* algorithm. Under the constraints and assistance of the demand processing module, it finds the optimal solution that satisfies the constraints as the target driving route.

[0072] In this embodiment, the interaction process between the map module, user module, vehicle module, demand processing module, and route module is as follows: Figure 5 As shown, Figure 5 This is an interaction diagram of the functional modules of a specific embodiment of this application, specifically including:

[0073] To adapt to varying road conditions and expanding coverage within the preset area, the map module constructs a directed graph G from the station maps within that area.<V,E> Where V is the set of vertices and E is the set of edges. The vertex set V includes the site vertex set Vi. S and intersection vertex V C Two parts. The reason why the vertex set V includes two parts is that buses can operate across stops and also have a route recommendation function, so it is necessary to store two types of vertices. Station vertex set V S Used to determine the route of buses within a preset area, the set of intersection vertices V C Used to determine the stations along the driving route. The map module needs to be based on the directed graph G =<V,E> Complete the adjacency matrix A and the fully connected matrix A all The construction, in which:

[0074] The adjacency matrix A is used to expand the child nodes when the target driving route is obtained later.

[0075] Due to the unique nature of buses, any stop not yet visited could theoretically be the next stop. Therefore, when determining the target route, expanding the child nodes ensures that the target route is the shortest path, which helps in time estimation and cost calculation. Therefore, Euclidean distance is used for distance calculation, and finally, based on A...all The obtained travel route must be the shortest path. The Euclidean distance shortest distance diagram for determining the bus travel route is specifically as Figure 6 shown, which is a Euclidean distance shortest distance diagram for determining the bus travel route, d(V0,VN)=d(V0,V1)+d(V1,VN), indicating that V1 is on the shortest path from V0 to VN or on another path of equal length. d(V0,VN)<d(V0,V1)+d(V1,VN), indicating that V2 causes a detour.

[0076] As Figure 7 shown, it is a flow chart of map construction by the map module in this specific embodiment, specifically including the following steps:

[0077] S702, start;

[0078] S704, acquire station and intersection data information in the map module;

[0079] S706, construct some simulated station information;

[0080] S708, generate an adjacency matrix according to the directed graph G=<V, E> constructed from station and intersection data information;

[0081] S710, obtain the full connection matrix A using Dijkstra's algorithm all ;

[0082] S712, store the generated adjacency matrix and full adjacency matrix into variables of a database file;

[0083] S714, end.

[0084] Optionally, the full connection matrix A all can be obtained by Dijkstra's algorithm, and records the distance d of the shortest path between all vertices in the vertex set V ij . The initialization data of vertex set V is recorded in the variables of the file, the main form is V=<ID,N,P,C>, where ID is the unique identification index of the vertex, N is the vertex name, P is the position coordinate of the vertex, and C is the ID set of reachable adjacent vertices. Vertices can be expressed as: Edge set E can be expressed as: e ij =Euclidean(p i ,p j ). All vertex information in this embodiment is collected and recorded manually, stored in the database according to the format shown by v i , can be expanded and modified at any time, and the vertex data document can be exported in reverse, and the vertex relationship can be modified by a computer program, which has extremely high scalability.

[0085] The user module is used to collect users' basic information and travel information. In this embodiment, the user's basic information is used to uniquely identify the user and improve the travel schedule; the user's travel information... i = <id,v start ,v end ,t exp bus num ,t up ,t down >, which is entered by the user, where id is the unique identifier of user u; v start It is the starting station; v end It is the terminal station; t exp It refers to the expected arrival time no later than a specific point in time; bus num It is the bus number you took; t up For boarding time; t down This refers to the alighting time. This embodiment requires users to directly enter their alighting and boarding stations, without considering passengers' travel needs outside of designated stations; therefore, cluster analysis for station selection is unnecessary. Since there is no travel plan information initially, the bus... num t up t down These three values ​​are initialized to empty, and will be assigned values ​​once the target driving route is determined.

[0086] In this embodiment, the vehicle module handles different types of buses, each with varying passenger capacity and operating costs. The module is responsible for automatically selecting vehicles and choosing bus schedules.

[0087] bus i =<num,capacity,price,schedule>;

[0088] schedule = dict(stop:(time) in ,time out )),stop∈V S ;

[0089] Where num is the vehicle number, which is the unique identifier of the vehicle; capacity is the capacity, which records the current number of passengers in the vehicle; price is the fare, which is a fixed fare for this problem; and schedule stores the timetable, which records the arrival and departure times of the target route.

[0090] Optionally, in this embodiment, the vehicle type is automatically selected based on the number of passengers on the target route. Therefore, during the search for the target route, passenger boarding and alighting records are generated to assist the automatic selection function in calculating the peak passenger number. Vehicles are automatically allocated based on the peak passenger number (corresponding to the first preset threshold mentioned above). Simultaneously, the vehicle module has a counting function; when allocating vehicles, it checks the vehicle inventory. If no vehicle meets the standard, other vehicle types are selected as substitutes. If no suitable vehicle is available, stops along the route are removed to reduce the peak passenger number. The removed requests are then added back to the request list to await route scheduling. The shuttle bus selection process is as follows: when the number of point-to-point passengers exceeds the vehicle capacity (corresponding to the second preset threshold mentioned above), a point-to-point shuttle bus can be arranged without additional stops along the way. Passengers are arranged to board the shuttle bus according to the order in which requests are submitted.

[0091] Specifically, the vehicle module selects vehicles in the following ways: Figure 8 As shown, Figure 8 This is a flowchart illustrating the selection of a vehicle in a specific embodiment of this application, which includes the following steps:

[0092] S802, Start;

[0093] S804, obtain the travel information sent by the object, wherein the travel information includes the object's identification information, the object's boarding station, the object's alighting station, and the time of arrival at the alighting station;

[0094] S806, determine the demand set based on passenger information;

[0095] S808, determine whether the number of demands in the demand set is less than the first preset threshold. If yes, go to S810; otherwise, go to S812.

[0096] S810, determine whether the peak number of objects in the time interval is less than the second preset threshold. If yes, go to S816; otherwise, go to S812.

[0097] S812, choose your bus first;

[0098] S814, Select target vehicle.

[0099] S816, End.

[0100] The requirements processing module is mainly used to process constraints and prepare requirements before searching for the target driving route. It centrally processes some constraints and needs to continuously interact with the search process during the target driving route search to quickly adjust the requirement set and select possible starting and ending stations. The constraints required in this embodiment include: (1) the time for passengers to arrive at their destination is no earlier than 20 minutes before the preset time; (2) the maximum capacity of the vehicle is 50 people; (3) the route stops at a maximum of 6 stations (including the starting station and the ending station); (4) the fare is 5 yuan; (5) the route can be opened if it meets the needs of 10 people; (6) the ratio of bus speed to walking speed is used to adjust the curvature of the route; (7) the time interval for passenger travel demand is from 8:00 am to 10:00 pm; (8) 20 people can get on and off the bus per minute after the bus arrives at the station; (9) the peak number of passengers on the bus does not exceed 50; (10) the time to reach the destination by bus is less than the time to reach the destination by walking; (11) no bus service is opened between two stations within a 10-minute walk; (12) no bus stops are opened at stations where there is no need to get on or off; (13) passengers with the same needs will not be spread out between two buses (except for shuttle buses).

[0101] Constraint (1) determines the size of the sliding time window during the subsequent rapid demand extraction process. The longer the preset time, the more passenger demand can be met, the more people will take the route, and the fewer vehicles will be running at the same time. Constraint (2) specifies the maximum passenger capacity and limits the maximum vehicle type to assist in vehicle selection. Constraint (3) limits the depth of the search tree expansion in the subsequent target route search. That is, the deeper the depth, the greater the search pressure may be. However, by ensuring the pruning strategy through other constraints, the complexity of the search may decrease sharply if the depth is too large. For example, constraints (6), (10), and (11) can quickly reduce the subsequent value range. Constraint (4) will affect the heuristic results, thereby indirectly affecting the search priority. Constraint (5) will affect the number of vehicles running. The fewer passengers who need to depart, the more routes there will be, and the more demand can be met. Usually, in this case, the number of stations the route passes through will be significantly less than the depth specified in constraint (3). The more passengers who need to depart, the fewer routes there will be, and a large number of off-peak demand will be abandoned. Constraint (6) is the route adjustment constraint. The closer the ratio is to 0, the more likely it is to go to a stop that has already been passed (backtracking); the closer the ratio is to 1, the straighter the route is. Constraint (7) determines the total demand. Constraint (8) can more accurately simulate the time during the route journey and calculate the estimated parking time based on this constraint. Constraint (9) can reserve empty seats for vehicles based on actual operating conditions or impose maximum passenger limits based on the available vehicle models to meet most scheduling needs. Constraint (10) is used to prune during the expansion of the search tree, which greatly improves search efficiency. Constraint (11) reduces the number of potential routes to be opened, and stations that are too close are not suitable for opening routes. Constraint (12) is used to prune during the expansion of the search tree to reduce the number of expanded nodes. Constraint (13) binds passengers with the same demand into a set. Therefore, when processing demand during the route search process, the demand can be counted and only numbers need to be processed. Only the demand name needs to be marked, and the route arrangement can be distributed to users based on the demand name after the route is found.

[0102] Optionally, the demand processing module extracts travel demands specifically by: based on the three-dimensional demand matrix D=V S ×V S ×T is used for rapid demand extraction, where T is the time series in minutes in constraint (7), and u is the user's expected arrival time. i .texp, and then, based on constraint (13), count the identical requirements and fill them into D. During the requirement extraction process, a time baseline t0 is set, where t0 is the current time, representing the most pressing requirement at that moment. For example... Figure 3The diagram shown is a sliding time window diagram of a method for determining a vehicle travel route according to an embodiment of this application. Based on the time specified in constraint (1), a window of a specified duration is drawn in matrix D, which is the time sliding window. By sliding the time sliding window, the demand between any two stations can be extracted at any time, thus realizing the rapid extraction of travel demand.

[0103] The route module searches for the target driving route and interacts with the demand processing module in real time. It employs technologies such as artificial intelligence problem-solving agents, combining IDA* and game theory algorithms, and using a propagation constraint pruning strategy to obtain optimized results by modifying heuristics. Specifically, it includes:

[0104] When expanding the search tree with the destination terminal as the root node, the demand can be managed using a dynamic programming strategy according to the following formula. Assuming there is already a path l, the route demand is D. l The new exploration node is v new The total demand for the route is D. new :

[0105]

[0106] A search tree rooted at the destination station can slide the sliding time window in the negative direction of the demand matrix T-axis during the search process, keeping the time window on both sides of the t0 baseline. This is because child nodes in the reverse search will arrive earlier than their parent nodes in the route, thus the expected arrival time will shift in the negative direction of the T-axis. However, this does not conflict with actual demand and instead has high interpretability. This approach ensures that the demand of all passengers is traversed at least once or more, guaranteeing fairness to a certain extent. Figure 9 The diagram shows the search sliding time window in different directions. If the starting point is taken as the root node, sliding in the positive direction of the T-axis will cause some requirements to be discarded without being considered, because the baseline is also moving in the positive direction, so the requirements that the baseline moves through will no longer be considered. In summary, this application creates a search tree with the target termination site as the root node.

[0107] like Figure 10 The diagram shown is a search example diagram of a specific embodiment of this application. After the root node is constructed, a deepening iteration method similar to IDA* is used to search at different depths with v start To find the terminating node, expand all possible solutions. During this process, constraints (2)(3)(10)(11)(12) play a pruning role. Because the pruned value range is propagable—that is, the value range of a child node in the search tree is always a subset of the value range of its parent node—the pruning efficiency increases progressively. This differs from the conventional IDA* algorithm. Heuristic H is used during the search for child nodes:

[0108] Where l represents the path that has been backtracked to so far, including node information v n D l The bus.speed is the simulated speed, which is the initial preset value, representing the requirements of the current path.

[0109] Since heuristics cannot directly determine the impact of the next site on the selection of subsequent sites, all sites within the value range are expanded at the next level. After the search is complete, the heuristic H is set as a scoring function Score:

[0110] The score function will be calculated backwards from the target termination node to the target start node, ultimately obtaining the path with the highest score at the target start node (root node). If this path satisfies constraint (5), it can be considered a reasonable path, and subsequent demand removal and user distribution work can begin. Furthermore, since the score function conforms to the dynamic programming strategy, optimizing it can improve the efficiency of subsequent scoring. Wherein, Score(l') = Score(l) + D'*price - A all (v',v l0 ) / bus.speed-1, l' is the path sequence to add the new station v', D' is the demand associated with station v', and vl0 is the latest station of l, which is the adjacent station of v'. The purpose of the final decrement operation is to strengthen the constraint condition (12) so that stations without demand on the shortest path will not stop, because this would lower the score for no reason.

[0111] like Figure 11 The diagram shown is a backtracking score graph for each route in a specific embodiment of this application. When determining the target driving route, it is only necessary to compare the value of Score(l) at the parent node, without having to repeatedly calculate Score(l') for all cases, thus improving backtracking efficiency.

[0112] In summary, this embodiment utilizes a sliding window to dynamically extract demands from the demand matrix, enabling dynamic changes in expanded nodes during search tree construction and achieving real-time demand processing and route planning. This embodiment employs a reverse station search (from the destination to the origin) approach, using heuristic estimation of travel time, cost, and user demand to construct an iterative deepening backtracking algorithm, which can accurately determine the target route. This embodiment can also distribute specific user travel information to individual users, improving the user experience.

[0113] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0114] This embodiment also provides a vehicle route determination device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0115] Figure 12 This is a structural block diagram illustrating the determination of a vehicle driving route according to an embodiment of this application, such as... Figure 12 As shown, the device includes:

[0116] The first determining module 122 is used to determine a demand matrix, wherein the demand matrix includes a time series, a set of stations, and a demand set. The time series is the time interval during which the object has a travel demand. The set of stations includes stations in a preset area that the target vehicle is allowed to reach. The demand set includes multiple travel demands issued by the object that satisfy the time series and the number of demands with the same travel demand.

[0117] The first extraction module 124 is used to extract the travel demand between any two stations within the sliding time window from the above demand matrix, wherein the above sliding time window is a time interval in the above time series, and the above any two stations are stations in the above set of stations.

[0118] The second determining module 126 is used to determine a route search queue based on the travel demand between any two stations, wherein the stations included in the route search queue satisfy the requirement that the travel time of the object between any two stations is greater than a preset time.

[0119] The third determining module 128 is used to determine the target travel route from the above-mentioned route search queue, wherein the target travel route is the shortest route that satisfies the travel demand within the above-mentioned sliding time window.

[0120] In an exemplary embodiment, the first determining module (corresponding to the route module) includes: a first determining submodule, configured to sort multiple driving routes in the route search queue using a fully connected matrix, and determine the longest driving route among the multiple driving routes, wherein the longest driving route is the route with the greatest distance between any two stations, and the fully connected matrix includes the shortest distance between any two stations; and a second determining submodule, configured to search the route search queue using the longest driving route to determine the target driving route.

[0121] In an exemplary embodiment, the second determining submodule (corresponding to the route module) includes: a first deletion unit, configured to delete the longest travel route from the route search queue to obtain a target route search queue; a first determining unit, configured to determine the target starting station and target ending station of the travel demand from the target route search queue; a first constructing unit, configured to construct a search tree using the target starting station and the target ending station, wherein the target ending station is the root node of the search tree and the target starting station is the end node of the search tree; and a first searching unit, configured to search for the target travel route in the search tree.

[0122] In an exemplary embodiment, the first construction unit (corresponding to the route module) includes: a first determining subunit, configured to slide the sliding time window, search the demand matrix for intermediate stations that satisfy the target termination node and the target starting node, and determine child nodes between the target termination node and the target starting node, wherein the child nodes satisfy preset constraints, the preset constraints including at least one of the following: the maximum capacity of the target vehicle, the number of stops for the target vehicle, the time for the target vehicle to reach the target termination node is less than the time for the object to reach the target termination node, and the ride demand includes the intermediate stations; and a first construction subunit, configured to construct the search tree using the target termination node, the target starting node, and the child nodes.

[0123] In an exemplary embodiment, the first search unit (corresponding to the route module) includes: a first calculation subunit, configured to calculate the score of each path in the search tree, wherein each path includes a target termination node, a target start node, and corresponding child nodes, and the score of each path is calculated in reverse from the target termination node to the target start node of each path, and the score of each path is used to represent each path; and a second determination subunit, configured to determine the target driving route based on the score of each path, wherein the demand quantity corresponding to the target driving route meets a preset quantity.

[0124] In an exemplary embodiment, before sorting multiple driving routes in the route search queue using a fully connected matrix and determining the longest driving route among the multiple driving routes, the apparatus further includes: a first construction submodule (corresponding to the map module), configured to construct a vertex set using the location information of each of the stations in the acquired station set, wherein the vertex set includes a station vertex set and an intersection vertex set, the station vertex set being used to determine the driving route, and the intersection vertex set being used to determine the stations in the driving route; a third determination submodule (corresponding to the map module), configured to determine the directed connection relationships between the multiple stations to obtain an edge set; a second construction submodule (corresponding to the map module), configured to construct a station map in the preset area using the vertex set and the edge set; and a fourth determination submodule (corresponding to the map module), configured to determine an adjacency matrix and the fully connected matrix based on the station map, wherein the adjacency matrix is ​​used to determine child nodes in the route search queue, and the fully connected matrix includes the shortest distance between two stations.

[0125] In an exemplary embodiment, before determining the demand matrix, the apparatus further includes: a first acquisition module (corresponding to the user module), configured to acquire ride information sent by the object, wherein the ride information includes the object's identification information, the object's boarding station, the object's alighting station, and the time point of arrival at the alighting station; a fourth determination module (corresponding to the vehicle module), configured to determine the demand set according to the ride information; and a first selection module, configured to select the target vehicle when the number of demands in the demand set is less than a first preset threshold and the peak number of objects within the time interval is less than a second preset threshold.

[0126] In an exemplary embodiment, before determining the demand matrix, the apparatus further includes a fifth determining module (corresponding to the demand processing module) for determining constraints, wherein the constraints include at least one of the following: the time it takes for the object to arrive at the station, the maximum capacity of the vehicle, the number of stations the vehicle stops at, the vehicle fare, the number of objects on the route the vehicle operates, the ratio between the vehicle's speed and the object's speed, the time interval, the number of objects allowed to get on and off the vehicle at the station within a preset time period, the peak number of objects in the vehicle, the time it takes for the object to arrive at the destination station; the time it takes for the vehicle to arrive at the station is less than the time it takes for the object to arrive at the station, the conditions for the vehicle to stop at the station, and multiple objects with the same travel demand being assigned to the same vehicle.

[0127] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0128] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when run.

[0129] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0130] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0131] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0132] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0133] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular hardware and software combination.

[0134] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining a vehicle's driving route, characterized in that, include: A demand matrix is ​​determined, wherein the demand matrix includes a time series, a set of stations, and a set of demands. The time series is the time interval during which an object has a travel demand. The set of stations includes stations in a preset area that the target vehicle is allowed to reach. The set of demands includes multiple travel demands issued by the object that satisfy the time series and the number of demands with the same travel demand. Extract the travel demand between any two stations within a sliding time window from the demand matrix, wherein the sliding time window is a time interval in the time series, and the any two stations are stations in the station set; A route search queue is determined based on the travel demand between any two stations, wherein the stations included in the route search queue satisfy the requirement that the travel time of the object between any two stations is greater than a preset time. A target travel route is determined from the route search queue, wherein the target travel route is the shortest route that satisfies the travel demand within the sliding time window; Determining a target driving route from the route search queue includes: sorting multiple driving routes in the route search queue using a fully connected matrix, determining the longest driving route among the multiple driving routes, wherein the longest driving route is the route with the greatest distance between any two stations, and the fully connected matrix includes the shortest distance between any two stations; and searching the route search queue using the longest driving route to determine the target driving route. Determining the target travel route by searching the route search queue using the longest possible route includes: deleting the longest possible route from the route search queue to obtain a target route search queue; determining the target start station and target end station of the travel demand from the target route search queue; constructing a search tree using the target start station and the target end station, wherein the target end station is the root node of the search tree and the target start station is the end node of the search tree; and searching for the target travel route in the search tree.

2. The method according to claim 1, characterized in that, Constructing a search tree using the target starting site and the target ending site includes: Slide the sliding time window to search the demand matrix for intermediate stations that satisfy the target termination station and the target origin station, and determine the sub-stations between the target termination station and the target origin station. The sub-stations satisfy preset constraints, which include at least one of the following: the maximum capacity of the target vehicle, the number of stops of the target vehicle, the time for the target vehicle to arrive at the target termination station is less than the time for the object to arrive at the target termination station, and the travel demand includes the intermediate stations. The search tree is constructed using the target termination site, the target starting site, and the sub-sites.

3. The method according to claim 1, characterized in that, Searching for the target driving route in the search tree includes: In the search tree, a score is calculated for each path, wherein each path includes the target termination station, the target starting station, and the corresponding sub-stations. The score for each path is calculated in reverse from the target termination station to the target starting station. The score for each path is used to represent each path. The target driving route is determined based on the score of each path, wherein the required quantity corresponding to the target driving route meets a preset quantity.

4. The method according to claim 1, characterized in that, Before sorting multiple driving routes in the route search queue using a fully connected matrix and determining the longest driving route among the multiple driving routes, the method further includes: A vertex set is constructed using the location information of each station in the acquired station set, wherein the vertex set includes a station vertex set and an intersection vertex set. The station vertex set is used to determine the driving route, and the intersection vertex set is used to determine the stations in the driving route. Determine the directed connections between the multiple sites to obtain an edge set; A site map in the preset region is constructed using the vertex set and the edge set; The adjacency matrix and the fully connected matrix are determined based on the site map, wherein the adjacency matrix is ​​used to determine the sub-sites in the route search queue, and the fully connected matrix includes the shortest distance between two sites.

5. The method according to claim 1, characterized in that, Before determining the demand matrix, the method further includes: Obtain the travel information sent by the object, wherein the travel information includes the object's identification information, the object's boarding station, the object's alighting station, and the time of arrival at the alighting station; The demand set is determined based on the travel information; If the number of demands in the demand set is less than a first preset threshold, and the peak number of objects within the time interval is less than a second preset threshold, then the target vehicle is selected.

6. The method according to claim 1, characterized in that, Before determining the demand matrix, the method further includes: Define constraints, wherein the constraints include at least one of the following: the time it takes for the object to arrive at the station, the maximum capacity of the vehicle, the number of stations the vehicle stops at, the vehicle fare, the number of objects on the route the vehicle operates, the ratio between the vehicle's speed and the object's speed, the time interval, the number of objects allowed to get on and off the vehicle at the station within a preset time period, the peak number of objects in the vehicle, the time it takes for the object to arrive at the destination station; the time it takes for the vehicle to arrive at the station is less than the time it takes for the object to arrive at the station, the conditions for the vehicle to stop at the station, and multiple objects with the same travel needs being assigned to the same vehicle.

7. A device for determining a vehicle's driving route, characterized in that, include: The first determining module is used to determine a demand matrix, wherein the demand matrix includes a time series, a station set, and a demand set. The time series is the time interval during which an object has a travel demand. The station set includes stations in a preset area that the target vehicle is allowed to reach. The demand set includes multiple travel demands issued by the object that satisfy the time series and the number of demands with the same travel demand. The first extraction module is used to extract the travel demand between any two stations within a sliding time window from the demand matrix, wherein the sliding time window is a time interval in the time series, and the any two stations are stations in the station set. The second determining module is used to determine a route search queue based on the travel demand between any two stations, wherein the stations included in the route search queue satisfy the requirement that the travel time of the object between any two stations is greater than a preset time. The third determining module is used to determine the target driving route from the route search queue, wherein the target driving route is the shortest route that satisfies the travel demand within the sliding time window; The first determining module includes: a first determining submodule, configured to sort multiple driving routes in the route search queue using a fully connected matrix, and determine the longest driving route among the multiple driving routes, wherein the longest driving route is the route with the greatest distance between any two stations, and the fully connected matrix includes the shortest distance between any two stations; and a second determining submodule, configured to search the route search queue using the longest driving route to determine the target driving route; The second determining submodule includes: a first deletion unit, configured to delete the longest travel route from the route search queue to obtain a target route search queue; a first determining unit, configured to determine the target starting station and target ending station of the travel demand from the target route search queue; a first construction unit, configured to construct a search tree using the target starting station and the target ending station, wherein the target ending station is the root node of the search tree and the target starting station is the end node of the search tree; and a first search unit, configured to search for the target travel route in the search tree.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 6.

Images