CN112129306A

CN112129306A - Route generation method and device, computer equipment and storage medium

Info

Publication number: CN112129306A
Application number: CN202011015613.4A
Authority: CN
Inventors: 李大韦; 宋玉晨; 杨敏; 刘向龙
Original assignee: Tencent Technology Shenzhen Co Ltd; Southeast University
Current assignee: Tencent Technology Shenzhen Co Ltd; Southeast University
Priority date: 2020-09-24
Filing date: 2020-09-24
Publication date: 2020-12-25

Abstract

The application relates to a route generation method, a route generation device, a computer device and a storage medium. The method relates to a path planning technology integrating multiple travel modes, and comprises the following steps: acquiring travel information and travel preference information; determining a multi-layer transportation network corresponding to the geographic position related to the travel information, wherein the multi-layer transportation network comprises a road sub-network, a walking sub-network and a public transportation sub-network; inquiring the passing time length between each network node in different sub-networks of the multi-layer traffic network; and generating a travel route matched with the travel information according to the travel preference information and the travel duration based on the multilayer traffic network, wherein a sequence formed by travel mode identifications corresponding to various travel modes adopted by the travel route is a feasible sequence in a travel mode state transition model. By adopting the method, the travel route considering various travel modes can be generated.

Description

Route generation method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a route generation method and apparatus, a computer device, and a storage medium.

Background

With the rapid development of intelligent transportation technology, some map software on the market can generate travel routes based on user demands. Specifically, the user can set a starting point and an end point according to the needs of the user, and the path planning algorithms adopted by the map software can generate corresponding travel paths for the user according to the shortest transit time, the shortest route or the minimum transfer times.

However, the path generated by the above method only relates to a single travel mode, and the combination of multiple travel modes which people can adopt in real life is ignored. The above method does not consider that the user can combine multiple travel modes, so that an optimal path with better passing efficiency cannot be provided for the user.

Disclosure of Invention

In view of the above, it is necessary to provide a route generation method, apparatus, computer device and storage medium capable of considering a plurality of travel modes in view of the above technical problems.

A route generation method, the method comprising:

acquiring travel information and travel preference information;

determining a multi-layer transportation network corresponding to the geographic position related to the travel information, wherein the multi-layer transportation network comprises a road sub-network, a walking sub-network and a public transportation sub-network;

inquiring the passing time length between each network node in different sub-networks of the multi-layer traffic network;

and generating a travel route matched with the travel information according to the travel preference information and the travel duration based on the multilayer traffic network, wherein a sequence formed by travel mode identifications corresponding to various travel modes adopted by the travel route is a feasible sequence in a travel mode state transition model.

A route generation apparatus, the apparatus comprising:

the acquisition module is used for acquiring the travel information and the travel preference information;

the determining module is used for determining a multi-layer transportation network corresponding to the geographic position related to the travel information, and the multi-layer transportation network comprises a road sub-network, a walking sub-network and a public transportation sub-network;

the query module is used for querying the passing time length between each network node in different sub-networks of the multi-layer traffic network;

and the generating module is used for generating a travel route matched with the travel information according to the travel preference information and the travel duration based on the multilayer traffic network, wherein a sequence formed by travel mode identifications corresponding to multiple travel modes adopted by the travel route is a feasible sequence in a travel mode state transition model.

A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

acquiring travel information and travel preference information;

A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

acquiring travel information and travel preference information;

According to the route generation method, the route generation device, the computer equipment and the storage medium, the multilayer transportation network comprises a road sub-network, a walking sub-network and a public transportation sub-network, and can provide support for generating the travel route comprising a plurality of different travel modes; the travel mode state transition model defines a reasonable and feasible combination sequence corresponding to multiple travel modes, and the generated travel route comprising the multiple travel modes is ensured to be in accordance with the travel habits of people. After the travel information and the travel preference information of the user are obtained, the travel time between network nodes in different sub-networks of the multilayer traffic network is inquired, so that the path planning can be carried out according to the travel time between the network nodes based on the multilayer traffic network, the travel preference information of the user is considered during the path planning, various travel modes and the feasibility of transformation among the various travel modes are also considered, and the generated route matched with the travel information is enabled to be in line with the preference of the user and to be efficient and feasible.

Drawings

FIG. 1 is a diagram of an application environment of a route generation method in one embodiment;

FIG. 2 is a flow diagram of a route generation method in one embodiment;

FIG. 3 is a schematic illustration of a traffic network in one embodiment;

FIG. 4 is a schematic illustration of a multi-layer traffic network generated in one embodiment;

FIG. 5 is a schematic illustration of a hyperlink section defined in one embodiment;

FIG. 6 is a diagram illustrating a travel mode state transition model in one embodiment;

FIG. 7 is a diagram illustrating path planning using label correction in one embodiment;

FIG. 8 is a schematic illustration of a link list update process in one embodiment;

FIG. 9 is a schematic diagram of a frame of a method for generating a travel route in one embodiment

FIG. 10 is a schematic illustration of a multi-layer traffic network generated in one particular embodiment;

FIG. 11 is a block diagram showing the construction of a route generation apparatus;

FIG. 12 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The route generation method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 can obtain travel information and travel preference information input by a user and then send the travel information and the travel preference information to the server 104, the server 104 receives the travel information and the travel preference information sent by the terminal 102 and determines a multilayer transportation network corresponding to a geographic position related to the travel information, and the multilayer transportation network comprises a road sub-network, a walking sub-network and a public transportation sub-network; inquiring the passing time length between each network node in different sub-networks of the multi-layer traffic network; based on the multilayer traffic network, a travel route matched with the travel information is generated according to the travel preference information and the travel duration, wherein a sequence formed by travel mode identifications corresponding to various travel modes adopted by the travel route is a feasible sequence in a travel mode state transition model. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers. The server 104 may be a server of a MaaS (Mobility as a Service) platform.

In a specific application scenario, a user can input travel information and travel preference information of the user through a map client, and after the map client sends the travel information and the travel preference information input by the user to a server, the server returns a corresponding travel route.

It can be understood that before the server performs route planning, a traffic network needs to be generated, and a passing distance, a passing duration, travel fees corresponding to different travel modes, and the like corresponding to road segments between network nodes in the traffic network are acquired, so that a reasonable travel route can be planned for the user based on the information.

In one embodiment, as shown in fig. 2, a route generation method is provided, which is described by taking the method as an example applied to the computer device (terminal 102 or server 104) in fig. 1, and includes the following steps:

step 202, obtaining travel information and travel preference information.

The trip information is information including at least one set of trip data, and the trip data includes a start point and an end point of a trip. The travel information may include only one set of travel data including a start point and an end point of the user's travel plan. The trip information can also be the trip information of user all day, and the trip information of all day includes multiunit trip data, and this multiunit trip data concatenates and constitutes user all day's trip process, and the terminal point of the outgoing data in the front is the starting point of the outgoing data in the back promptly, and for example, first group's outgoing data is: from the place A to the place B, the second group of travel data is from the place B to the place C, and the third group of travel data is from the place C to the place A. In order to be able to more accurately plan a travel route for a user, the travel information may further include a time window corresponding to the travel data, i.e. a start-stop time, i.e. a start time from a start point in the travel data and an arrival time to an end point of the travel data. The starting point and the ending point of the travel data can be represented by longitude and latitude.

The travel preference information is information related to a user's travel preference. The travel preference information can include whether the user uses a private car, whether the user rides a private bicycle, whether the user needs to go to a parking lot to pick up the car when starting, whether the user needs to go to a parking spot to park when returning, and the like. The travel preference information may further include at least one of an upper limit of transfer times, an upper limit of travel cost, an upper limit of walking distance, and an upper limit of riding distance acceptable to the user, and such travel preference information may be used to generate a travel route that meets travel requirements of the user. It should be noted that the above-mentioned travel preference information may be set for the overall travel information, for example, the user may request that the travel fee all day cannot exceed the set upper limit value of the travel fee; the travel preference information may also be set for each piece of travel data in the travel information, for example, a user may request that travel fees of a certain set of travel data in the travel information cannot exceed a set upper limit value of the travel fees.

Specifically, the computer device may obtain travel information and travel preference information input by a user, and may also obtain travel information and travel preference information sent by other computer devices. The computer equipment can also acquire the current position of the user through the positioning device, and then acquire the terminal point input by the user by taking the current position of the user as the starting point in the travel information. And the computer equipment carries out subsequent path planning according to the obtained travel information and the travel preference information of the user.

And step 204, determining a multi-layer transportation network corresponding to the geographic position related to the travel information, wherein the multi-layer transportation network comprises a road sub-network, a walking sub-network and a public transportation sub-network.

When the embodiment of the application is applied to route planning in cities, the geographic position related to the travel information may be a target city, and the corresponding multilayer traffic network is a road network corresponding to the target city. When the embodiment of the application is applied to route planning across cities, the geographic position related to the travel information may be a target province, the corresponding multilayer traffic network is a road network corresponding to the target province, and the multilayer traffic network corresponding to the target province may be obtained by connecting the multilayer traffic networks corresponding to a plurality of cities in the province. The embodiments of the present application mainly take the urban route planning as an example for explanation.

The multi-layer traffic network in the application considers the road networks required by various travel modes, so that all travel modes can be considered during path planning. The multi-layer transportation network includes a road sub-network, a walking sub-network, and a public transportation sub-network. The public transportation sub-network may include a bus sub-network and a subway sub-network. The network nodes in the road sub-network are road nodes, the road nodes comprise road stopping points and parking points, and the road nodes are connected with the road nodes through road sections. The network nodes in the walking sub-network are walking nodes, the walking nodes comprise road stop points, parking points and public transportation stations, and the walking nodes are connected with the walking nodes through road sections. The network nodes in the public transportation sub-network are public transportation nodes, the public transportation nodes comprise public transportation stations such as bus stations and subway stations, and the public transportation nodes are connected with the public transportation nodes through road sections.

Before a travel route is generated according to travel information of a user, a multilayer traffic network corresponding to a geographic position related to the travel information needs to be constructed in advance, and the generated multilayer traffic network can provide support for generating the travel route comprising a plurality of different travel modes. In one embodiment, the route generation method further comprises the step of constructing a multi-layer traffic network, the step comprising:

acquiring map data of a geographic position; generating a road sub-network according to the map data, wherein the road sub-network comprises road nodes and road sections among the road nodes, and the road nodes comprise road stopping points and parking points; generating a walking sub-network according to the map data, wherein the walking sub-network comprises walking nodes and road sections among the walking nodes, and the walking nodes comprise road stop points, parking points and public transportation stations; generating a public transportation sub-network according to the map data and the public transportation line data, wherein the public transportation sub-network comprises public transportation nodes and road sections among the public transportation nodes, and the public transportation nodes comprise public transportation stations; the multi-layer transportation network is obtained by connecting a road sub-network with a walking sub-network according to road stops and parking points, and connecting the walking sub-network with a public transportation sub-network according to public transportation stations.

The computer device can acquire map data of the target geographic position, and obtain the connection relation presented by the positions of all places and roads on the map according to the map data, so that the multilayer traffic network is generated. Specifically, the road sub-network may be generated according to a connection relationship between road stops and parking points in the map data, the walking sub-network may be generated according to a connection relationship between two of the road stops, parking points, and public transportation stations in the map data, and the public transportation sub-network may be generated according to a connection relationship between the public transportation stations presented in the map data and the public transportation line data. The walking subnetwork is generated on the basis of a road subnetwork, and a user can walk in any closed loop formed by a road stop, a parking spot and a public transport station, and the public transport subnetwork needs to be matched with the road subnetwork. In one embodiment, the computer device may obtain Map data for the target geographic location according to an Open source Map service of an Open Street Map.

In one embodiment, generating a public transportation sub-network from map data and public transportation line data comprises: acquiring the sequence of public transport stations of the public transport line according to the public transport line data; acquiring geographic coordinates of public transportation stations of public transportation lines according to the map data; and matching the public transport stops with the road sub-networks according to the sequence and the geographic coordinates to generate the public transport sub-networks comprising the public transport stops and the road sections between the public transport stops.

The geographic coordinates of the public transportation stations can be represented by longitude and latitude coordinates, the computer device can acquire public transportation line data from a network, the public transportation line data comprise the longitude and latitude of the public transportation stations and the sequence of the public transportation stations on the public transportation lines, the computer device needs to match the public transportation stations with corresponding places in a road sub-network, namely after the public transportation stations are mapped to the corresponding road nodes in the road sub-network, an actual public transportation line is generated, and the public transportation sub-network is generated according to the actual public transportation line and the actual public transportation stations. It should be noted that, for a bus line, the transit time length between public transportation stations may not be fixed, and for a subway line, the transit time length between subway stations is usually a fixed value.

Referring to fig. 3, which is a schematic diagram of a transportation network in one embodiment, the transportation network includes six road stops 1 to 6, one parking spot 7, six public transportation stations a1, a2, b1, b2, c1, and c2, wherein the six public transportation stations correspond to two public transportation lines a-b and a-c.

As shown in fig. 4, which is a schematic diagram of a multi-layer transportation network generated according to the transportation network in fig. 3, a road sub-network is first generated according to the road stops 1 to 6, the parking point 7 and the links therebetween, a walking sub-network is generated according to the road stops 1 to 6, the parking point 7, the six public transportation sites and the links therebetween, a public transportation sub-network is generated according to the six public transportation sites and the links therebetween, then the road sub-network is connected with the walking sub-network through the road stops 1 to 6 and the parking point 7, and the multi-layer transportation network is obtained after the walking sub-network is connected with the public transportation sub-network through the public transportation sites a1, a2, b1, b2, c1 and c 2.

In this embodiment, the multi-layer transportation network considers road networks required to be used by a plurality of travel modes, including a road sub-network, a walking sub-network and a public transportation sub-network, so that the various travel modes can be considered when planning a path.

In the above-described embodiment, the multi-layer transportation network includes sub-networks corresponding to travel modes such as public transportation, private transportation, walking, and the like, that is, a public transportation sub-network, a road sub-network, and a walking sub-network. In other embodiments, the multi-layer transportation network may further include sub-networks corresponding to private travel services (private transport services) provided by other companies, called private transportation sub-networks, which are connected to the walking sub-network. The private traffic nodes of the private sub-network also belong to walking nodes in a walking sub-network, which can be connected to the walking sub-network via private traffic nodes, similar to the road sub-network, or via public traffic stations, similar to the public traffic sub-network.

In one embodiment, the walking nodes in the walking sub-network further comprise private transportation nodes, and the method further comprises: acquiring private traffic road data corresponding to a private traffic service; generating a private traffic sub-network according to the private traffic road data, wherein the private traffic sub-network comprises private traffic nodes and road sections between the private traffic nodes; connecting a road sub-network with a walking sub-network according to road stops and parking points, and connecting the walking sub-network with a public transportation sub-network according to public transportation stations, obtaining a multi-layer transportation network, comprising: the multi-layer traffic network is obtained by connecting the road sub-network with the walking sub-network according to the road stopping points and the parking points, connecting the walking sub-network with the public traffic sub-network according to the public traffic stopping points, and connecting the private traffic sub-network with the walking sub-network according to the private traffic nodes.

The private transportation service data is data related to a private travel service process and is used for generating a private transportation sub-network. For example, when the private transportation service is a private car rental service, the private transportation service data includes a geographic location of a car rental point and a car rental fee, and specifically, the private car rental service can provide a car rental service for a user, when the user needs to travel in a car rental mode, the user needs to go to the rental point of the private car rental service to rent a car, so that the computer device can use the rental points as the private transportation nodes, generate a private transportation sub-network corresponding to the private car rental service according to the geographic location of the private transportation nodes, and connect the generated private transportation sub-network with the walking sub-network through the rental points, wherein the car rental fee is used for calculating the travel fee corresponding to the travel mode.

As another example, when the private transportation service is a private taxi-taking service, the private transportation service data includes road waypoints and parking points within a service range of the private taxi-taking service, and also includes pricing rules, and particularly, the private taxi-taking service can provide taxi-taking services for the user, when a user needs to travel by driving, he or she needs to walk to a road stop or a parking spot to drive, and therefore, the private traffic sub-network is similar to the road sub-network, and the computer device can use the road parking points and parking points in the service range as the private traffic nodes, and generating a private traffic sub-network corresponding to the private taxi-taking service according to the geographic position of the private traffic node, and connecting the private traffic sub-network with a walking sub-network through a road parking point and a parking point, wherein the pricing rule is used for calculating the travel cost corresponding to the travel mode.

For another example, when the private transportation service is a customized shift car service provided to the user, the private transportation service data includes a route and a fee corresponding to the customized shift car, and a stop point and a road segment in the route are used for generating a corresponding private transportation sub-network, which is linked with the walking sub-network through the stop point in the route.

In this embodiment, by acquiring private transportation service data provided by different private transportation services to generate corresponding private transportation subnetworks and connecting the generated private transportation subnetworks with a road subnetwork or a walking subnetwork, a multi-layer transportation network including rich travel modes can be obtained, so that when planning a path, the rich travel modes can be considered to provide as many travel choices for a user as possible.

The multi-layer traffic network comprises network nodes and road sections between the network nodes, wherein the road sections can be understood as edges between the network nodes, and when two network nodes are connected through the edges, the two network nodes are adjacent. In the embodiment of the present application, although many limiting conditions are considered when performing path planning, path planning is mainly performed with the shortest transit time as a target, so that the weights of the edges between the network nodes are represented by the transit times in different corresponding manners. For example, in the road sub-network, the weight of the edge between the road stop point and the road stop point may be a corresponding passage time length when the vehicle is driven, or a corresponding passage time length when the vehicle is driven.

In one embodiment, a data structure such as an adjacency matrix, an adjacency list or a linked list may be used to store the connection relationship between network nodes and the weights of the road segments between the network nodes in the multi-layer traffic network. For example, a two-dimensional matrix may be used to represent the topological relationship of the multi-layer traffic network, where both rows and columns of the two-dimensional matrix represent network nodes in the multi-layer traffic network, and if there is a value at the intersection of a row pm of the matrix and a column pn of the matrix, it indicates that the network node pm and the network node pn are adjacent network nodes, and the value represents the weight of the edge from the network node v to the network node w; if no value exists at the intersection point of the row pm of the matrix and the column pn of the matrix, the network node pm and the network node pn are non-adjacent network nodes. For another example, an adjacency list may be used to implement the topological relationship of the multi-layer traffic network, and if the network node a corresponding to the header has an adjacent network node b, the adjacent network nodes b are sequentially stored in the one-way linked list pointed by the header, and the weight of the edge between the network node a and the network node b is recorded in the one-way linked list.

In step 206, the transit time between each network node in different sub-networks of the multi-layer transportation network is inquired.

As mentioned above, in the embodiment of the present application, although many limiting conditions are considered when performing path planning, the path planning is mainly performed with the shortest transit time as a target, so that when performing path planning by using a planning algorithm, the transit time between each network node in a multi-layer traffic network needs to be obtained, so as to find a travel route with the shortest transit time on the premise of meeting travel preferences of a user.

It should be noted that the passing time duration may be a generalized passing time duration obtained according to data statistics, for example, for a driving mode, the passing time duration of a road segment may be a value determined according to an average passing time of the road segment, for a walking mode, the passing time duration may be a value determined based on an average pace speed of a large number of users, and for a riding mode, the passing time duration may be a value determined based on an average riding speed of a large number of users. In other embodiments, for the driving mode, the passing time duration may also be a real-time passing time duration queried according to a real-time road passing condition, for the walking mode, the passing time duration may be a value determined according to a length of a road section after the pace speed of the current user is determined according to historical walking data of the current user, and for the riding mode, the passing time duration may be a value determined according to a length of a road section after the pace speed of the current user is determined according to historical riding data of the current user.

In one embodiment, the querying of the transit time between network nodes in different sub-networks of the multi-layer transportation network comprises: inquiring the passing time length between each road node in a road sub-network of the multi-layer traffic network; inquiring the passing time length between each walking node in the walking sub-network of the multi-layer traffic network; and inquiring the running time length between the public transportation nodes in the public transportation sub-network of the multi-layer transportation network and the vehicle frequency of each public transportation line, and calculating the passing time length between the public transportation nodes according to the running time length and the vehicle frequency of each public transportation line.

Specifically, the computer device may obtain the passage time length between road nodes in the road sub-network through some map real-time services, for example, the passage time length corresponding to the current time or the travel time in the user's travel information may be obtained through a Web API service provided by a gold open platform, and the passage time length of the road may be stored or calculated through a database of the open platform. The passing time length between each walking node in the walking sub-network can be calculated according to the walking distance and the generalized walking speed, and then the passing time length is recorded into the walking sub-network as the weight of the edge between the walking nodes.

When the public transportation sub-network is a subway track sub-network, the public transportation nodes are subway stations, the passage time between the public transportation nodes, namely the subway stations, is usually a fixed value, and the computer equipment can be used for recording the passage time between the stations of the subway line as the weight of the edges between the public transportation nodes into the subway track sub-network after inquiring the passage time between the stations of the subway line from the network.

When the public transportation sub-network is a bus route sub-network, due to the fact that various bus routes can be reached between a bus stop and a bus stop, a user usually takes a bus route which is preferentially reached when waiting at the bus stop, but the specific bus route which is preferentially reached to the bus stop is uncertain, so that the passing time between the bus stop and the bus stop is uncertain, and the passing time between the bus stops in the bus route sub-network needs to be redefined.

For the case that a plurality of reachable public transportation lines exist between two public transportation stations, the computer device defines the type of the road section between the two public transportation stations as a super road section, namely when a plurality of reachable public transportation lines exist on a road section ei starting from a public transportation station i to another public transportation station j, the passing time of the road section ei is uncertain, and the road section ei is defined as the super road section. As shown in fig. 5, which is a schematic diagram of a highway segment defined in one embodiment, there are three bus routes j1, j2, and j3 at bus stop i that can travel to the user's destination point j.

In one embodiment, calculating a transit time period between public transportation nodes from a travel time period and a vehicle frequency of each public transportation line includes: when a plurality of public transportation lines exist between a first station in the public transportation sub-network and a second station in the public transportation sub-network, marking a road section from the first station to the second station in the public transportation sub-network as a road section; acquiring the vehicle frequency of each public transport line in a plurality of public transport lines; acquiring the running time of each public transport line from a first station to a second station; obtaining the combined vehicle frequency of the super road section according to the vehicle frequency of each public transport line; determining the average waiting time corresponding to the first station according to the frequency of the combined vehicle; determining the probability of each public transport line as a first line reaching the first station according to the vehicle frequency of each public transport line and the combined vehicle frequency; and calculating the passing time of the super road section from the first station to the second station according to the average waiting time, the probability and the driving time.

Specifically, when there are a plurality of public transportation lines between the first station and the second station, the computer device may determine the transit time period of the super road section between the two stations according to the frequency of vehicles combined with each public transportation line and the travel time period from the first station to the second station through each public transportation line. Defining a road section starting from a first stop i to a second stop j as ei, wherein ei is (i, j), a plurality of public transportation lines exist between the first stop i and the second stop j, and assuming that a user randomly arrives at each public transportation station and the user arrives at the public transportation line of the public transportation station in a first way in the process of taking a bus by the user, and the public transportation lines are independent from each other, the arrival of the public transportation lines at the public transportation station obeys exponential distribution.

Let ei denote the path of the road covered between the first station i to the second station j, θ_kRepresenting the vehicle frequency of the public transport link k, c (i, j)_k) Representing the travel time of the vehicle of the public transport line k from the first station i to the second station j

f(ei)＝∑θ_k；

w(ei)＝1/f(ei)；

p(ei,k)＝θ_k/f(ei)；

Wherein f (ei) represents the joint vehicle frequency of the plurality of reachable public transportation links between the first station i and the second station i, and w (ei) represents the average waiting time of the user waiting at the first station i for vehicles to reach the second station j; p (ei, k) represents the probability that the public transportation link k is the first link to reach the first stop i;

representing a desired transit time for a section ei of the highway between the first station i and the second station j; vj denotes the shortest passage time from the second station j to the destination, and Vi denotes the shortest passage time from the first station i to the destination. When the computer device performs path planning, after the shortest passing time Vj from the second station j to the terminal is obtained, the shortest passing time Vi from the first station i to the terminal can be obtained by inquiring the passing time of a super road section between the first station i and the second station j.

In one embodiment, calculating a transit time period between public transportation nodes from a travel time period and a vehicle frequency of each public transportation line includes: when only one public transportation line exists between a first station in the public transportation sub-network and a second station in the public transportation sub-network, marking a road section from the first station to the second station in the public transportation sub-network as a common road section; acquiring the running time from a first station to a second station; and taking the running time as the passing time of the ordinary road section between the first station and the second station.

Specifically, for a case where there is only one reachable public transportation line between two public transportation stations, the computer device defines the type of the road segment between the two public transportation stations as a normal road segment, in which case the passage duration of the road segment between the first station to the second station can be directly expressed by the travel duration C (i, j) of the vehicle of the public transportation line, and then the shortest passage duration Vi from the first station i to the end point can be expressed by the following formula:

Vi＝Vj+C(i，j)。

in the above embodiment, the passing time length between the first stop and the second stop is determined by combining the vehicle frequency and the driving time length of the plurality of bus routes corresponding to the overtaking road section between the first stop and the second stop, so that the weight of the edge between the public transportation nodes in the public transportation sub-network can be more accurately represented, and support is provided for generating a more reasonable travel route.

And 208, generating a travel route matched with the travel information according to the travel preference information and the travel duration based on the multilayer traffic network, wherein a sequence formed by travel mode identifications corresponding to the various travel modes adopted by the travel route is a feasible sequence in the travel mode state transition model.

The travel mode state transition model is used for constraining the transformation among different travel modes, and is essentially a possible sequence formed by identifiers corresponding to multiple feasible travel modes. In order to support the generation of the travel route by adopting a plurality of travel modes, the computer device may construct the travel mode state transition model in advance. After the travel mode state transition model is constructed, a path can be planned based on a multi-layer traffic network generated in advance, the travel mode state transition model, travel information of a user and travel preference information by taking the shortest travel time as a target, and a travel route matched with the travel information is generated.

In one embodiment, the method further includes the step of generating a travel mode state transition model: acquiring travel mode identifications corresponding to various preset travel modes; acquiring a transfer limiting condition for restricting the change of a travel mode in the travel process; taking the travel mode identification sequence meeting the transfer limiting condition as a feasible sequence; and generating a travel mode state transition model according to the feasible sequence.

The preset various travel modes are common travel modes when people travel, and can include travel modes such as walking, private cars, shared cars, subway rail transit, road bus, private cars, shared cars and transfer, wherein the transfer refers to transfer between stations of subway rail transit, transfer between stations of road bus or transfer between stations of subway rail transit and stations of road bus. Theoretically, there may be many combinations between the travel modes, but according to the travel habits of the user, in order to generate a reasonable travel route, there are transition restrictions between the preset travel modes, and the transition restrictions are used to exclude some unreasonable combinations of travel modes. The transfer limiting condition may include at least one of: private single cars and private cars can only start to be used or parked at starting points, end points or parking points, and one trip data can only be used for one time; shared cars, shared bikes can only be used or parked at a designated place; the private bicycle and the shared bicycle cannot be continuously used.

The travel mode identification is used for representing corresponding travel modes, and the travel mode identifications corresponding to different travel modes are different. The sequence obtained by arranging the travel mode identifications corresponding to the various travel modes in sequence represents that the user uses the various travel modes to travel in sequence. The computer equipment takes the travel mode identification sequence meeting the transfer limiting conditions as a feasible sequence, and generates a travel mode state transfer model according to the feasible sequence, wherein the combination of the travel modes adopted by the user for traveling needs to meet any feasible sequence in the travel mode state transfer model. Referring to fig. 6, which is a schematic diagram of a travel mode state transition model in an embodiment, referring to fig. 6, numbers in the diagram represent a travel mode, alphabets show row states, and a travel state marks a type and an order of a travel mode currently used by a user, and is a subset of a feasible sequence. For example, the trip state corresponding to the letter f indicates that the user walks (1) first and then rides the sharing bicycle (3); the trip state corresponding to the letter g represents that the user walks (1) first and then takes the subway rail transit (4), can also represent that the user walks (1) first and then takes the road bus (5), can also represent that the user walks (1) first and then rides the shared bicycle (3) and then takes the subway rail transit (4), and can also represent that the user walks (1) first and then rides the shared bicycle (3) and then takes the road bus (5). It can be understood that the travel state corresponding to the letter a is an initial state of the path plan.

In one embodiment, based on a multi-layer transportation network, a travel route matched with travel information is generated according to travel preference information and travel duration, and the method comprises the following steps: acquiring starting and stopping points and starting and stopping times of each group of travel data in the travel information; for each group of travel data, performing path planning based on a multilayer traffic network and with the shortest travel time as a target to obtain a travel route with a travel path according with a start-stop place, a travel time according with a start-stop time, a travel process according with travel preference information and a travel mode according with a travel mode state transition model; the travel preference information comprises an upper limit value of transfer times, an upper limit value of riding cost, an upper limit value of walking distance and an upper limit value of riding distance; and connecting the travel routes corresponding to each group of travel data to obtain the travel routes of the whole day.

Specifically, the computer device may determine network nodes corresponding to the starting point and the ending point from the multi-layer transportation network according to the starting point and the ending point, namely the starting point and the ending point, in the travel data, so that a travel route from the starting point to the ending point can be determined from the multi-layer transportation network. The computer device further needs to determine an upper limit value of the passage duration of the travel data according to the start-stop time in the travel data, where the upper limit value is used to constrain the passage duration of the travel route during path planning, that is, the passage duration of the generated travel route needs to be smaller than the passage duration determined according to the start-stop time. The computer device also needs to consider travel preference information of the user in the path planning process, if the user does not want to ride, the travel route generated for the user does not use the riding travel mode, if the user needs to park in a return trip, the travel route including the parking path needs to be generated for the user, and if the user does not want to transfer, the travel route not including the transfer needs to be generated for the user. The computer device also needs to consider a travel mode state transition model during path planning, and ensure that a sequence formed by travel mode identifiers corresponding to travel modes adopted by a travel route is a feasible sequence in the travel mode transition model. That is to say, the travel data, the travel preference information and the travel mode state transition model will affect the generated travel route together, so as to ensure that the travel route not only meets the requirements of the user, but also is reasonable and feasible, and has better traffic efficiency.

In one embodiment, the travel information includes a plurality of sets of travel data related to all-day travel of the user, and then the computer device may obtain a travel route corresponding to each set of travel data according to the above method, and connect the corresponding travel routes according to the starting and stopping points of the travel data to obtain an all-day travel route corresponding to all-day travel information.

When a travel route needs to be generated, the computer device acquires a multi-layer traffic network which is constructed in advance, network nodes in the multi-layer traffic network represent all places, two adjacent network nodes represent that a passable road section exists between two corresponding places, and the weight of an edge between each network node and each network node represents the passage time length between the two corresponding places. The computer equipment also acquires a previously constructed travel mode state transition matrix. The computer device also acquires data determined in advance for indicating a route type (a super link or a normal link) of a link in the multi-layer traffic network. The computer equipment also acquires the travel information and the travel preference information of the user. And the computer equipment takes the obtained multilayer traffic network, the travel mode state transition matrix, the road section types of all road sections in the multilayer traffic network, the travel information and the travel preference information as input, then adopts a path planning algorithm to plan a path based on the input information, and outputs a corresponding travel route.

The computer device may employ Label correction (Label correction Algorithm) to perform path planning with the shortest transit time being the target in view of the above input information. Referring to fig. 7, which is a schematic diagram of performing route planning with shortest transit time by using the label correction method in an embodiment, referring to fig. 7, a multi-layer traffic network includes 6 nodes ABCDEF, and weights of edges between the nodes represent transit time durations, i.e., numbers on the edges in the diagram. Assuming that the end point is node a and the starting point is node F, the computer device needs to plan the shortest transit time path from the end point a to the starting point F. Defining the shortest passing time length from a node stored in a road section list to a starting point, firstly, determining road sections taking A as a head node, namely AB, AC and AD from the multilayer traffic network, and recording the path in a node-passing time length pair mode, namely adding B-7, C-9 and D-11 into the road section list; then, selecting a node-passage time length pair with the shortest passage time length, namely a node B, from the road section list, wherein the path with the shortest passage time length from the multilayer traffic network to the terminal A is from the node A to the node B, so that the computer equipment marks the node A as a processed node; and then the computer device continues iteration, a road section taking the starting point B as a head node, namely BC and BF, is determined from the multilayer traffic network, the tail node F of the road section BF is connected with A through the node B, the shortest transit time from the node F to the node A is AB + BC at the moment and F-27 is added into the road section list, the tail node C of the road section BC is directly connected with the starting point A, the transit time corresponding to the AC is shorter after comparing the tail node AB + BC with the AC recorded in the road section list, and C-9 is not updated, and the shortest transit time from the node B as a middle node in the multilayer traffic network to all nodes of the terminal A is determined, so the computer device marks B as a processed node. And then the computer equipment continues iteration, the node which is not marked currently and has the shortest transit time to the node A is C, the road section which takes the starting point C as the head node, namely the CE, is determined from the multilayer traffic network, and E-15 is added into the road section list, at the moment, the shortest transit time of all nodes which take the node C as the middle node to reach the end point A in the multilayer traffic network is determined, so that the computer equipment marks the node C as the processed node. By analogy, the computer equipment continuously updates the road section list, updates E-15 to E-14 and updates F-27 to F-15, all nodes are marked at this time, the shortest passing time of the distance A from the F recorded in the road section list is 15 directly according to the fact that the shortest passing time of the distance A from the F is 15, the corresponding path is ADEF, and the path from the starting point F to the end point A is determined to be FEDA.

In one embodiment, the road segments in the multi-layer transportation network are represented by head nodes and tail nodes, and for each set of travel data, the path planning is performed based on the multi-layer transportation network and with the shortest transit time as a target, including: acquiring a starting point and an end point in travel data; determining all road sections taking the terminal points as head nodes from the multilayer traffic network; traversing each determined road section, acquiring a travel state Si of a tail node i of the currently traversed road section according to a travel mode state transition model, determining a travel mode of the currently traversed road section according to the travel state Si, and adding a node state pair [ i, Si ] formed by the tail node i of the currently traversed road section and the travel state Si of the tail node i into a road section list when travel parameters corresponding to the travel mode accord with travel preference information; after traversing is finished, the following steps are executed in an iterative mode until the road section list is empty: selecting a node state pair [ k, Sk ] corresponding to a tail node k with the shortest passing time to reach a terminal point d from the road section list, removing the selected node state pair [ k, Sk ] from the road section list, and storing the passing time from the node k to the terminal point d by adopting a passing mode corresponding to a trip state Sk; determining all road sections with the node k as a head node from the multilayer traffic network; traversing each determined road section, and acquiring a travel state Si of a tail node i of the currently traversed road section according to a travel mode state transition model; determining a trip mode of the current traversed road section according to the trip state Si, and adding a node state pair [ i, Si ] formed by a tail node i of the current traversed road section and the trip state Si of the tail node i into a road section list when a trip parameter corresponding to the trip mode accords with trip preference information; and after the iteration is finished, obtaining the travel state corresponding to the starting point, backtracking from the starting point to the end point according to the travel state corresponding to the starting point, and obtaining a travel route matched with the travel data.

In this embodiment, a link in the multi-layer traffic network may be defined as e ═ i, j, where i denotes a tail node of the link e and j denotes a head node of the link e. After a starting point a and an end point d in the travel data are obtained, path planning is carried out from the end point d in the travel data, the shortest passing time from each node in the multilayer traffic network to the end point d is sequentially determined, and when the shortest passing time from the starting point a to the end point d is determined, the corresponding travel route is also determined. It is needless to say that the route planning may be performed from the start point a in the travel data, and the embodiment of the present application is mainly described by taking the route planning from the end point in the travel data as an example. Before the path planning starts, the computer device needs to initialize various items of data, for example, the travel time of all network nodes in the multi-layer transportation network to the end point in all travel states may be initialized to infinity, the travel cost is initialized to infinity, the transfer number is initialized to 0, and the travel state is initialized to a, that is, a.

The shortest passing time from the node j to the terminal d can be represented by Vj, and in the planning process, the node j is any node which changes constantly in the multilayer traffic network; and a node state pair [ i, Si ] is stored in the road section list, the node i in the node state pair is a node which is not determined to have the shortest transit time with the terminal point d in the multilayer traffic network, and the state Si in the node state pair is the travel state of the node i.

The computer device determines all road segments with the end point d as a head node from the multi-layer traffic network, so as to find the determined tail node i of each road segment, for example, the number of the determined tail nodes is m, and the m road segments are determined by traversing in sequence. Since the travel state of the end point d is an initial state a (as shown in fig. 6, a represents an initial travel state), the travel state Si of the end point i of the currently traversed road segment is obtained according to the travel mode state transition model, as shown in fig. 6, in the travel mode state transition model, the travel state adjacent to the travel state may include b, c, d, e, the travel mode of the currently traversed road segment is determined according to the travel state Si, and is sequentially a walking mode, a private bicycle, a private car and a shared car, when the travel parameter corresponding to the travel mode corresponds to the travel preference information, for example, if the walking mode is adopted and the walking distance is less than the maximum walking distance value set by the user, for example, if the private bicycle mode is adopted and the riding distance is less than the upper limit riding distance value set by the user, for example, if the user allows the driving mode to be adopted, then, a node state pair [ i, Si ] formed by the end node i of the currently traversed road segment and the travel state Si of the end node i may be added to the road segment list, that is, a feasible travel path and a travel mode may be retained. Of course, the travel modes that different end nodes can adopt are different, for example, if it is determined that the end node i is a bus stop, the user needs to walk to the bus stop, the corresponding travel mode is walking, if the end node i of the determined road section is a parking lot, the user needs to walk to the parking lot, the corresponding travel mode is walking, and if the end node of the determined road section is a certain road stop, the corresponding travel mode may be a private single car, a private car or a shared car.

According to the above steps, the computer device determines all feasible paths and travel modes from the terminal, then, the computer device selects the node state pair [ k, Sk ] corresponding to the tail node k with the shortest transit time to reach the terminal d from the road section list, and eliminates the selected node state pair [ k, Sk ] from the road section list, and stores the transit time from the node k to the terminal d by adopting the transit mode corresponding to the travel state Sk. Next, the computer device needs to determine a node, which has the shortest transit time and meets the travel preference information of the user, among all network nodes adjacent to the end node k in the multi-layer traffic network, so as to update the road section list after determining the next node.

In particular, the computer device iteratively performs the steps of: determining all road segments with a node k as a head node from a multilayer traffic network, traversing each determined road segment, and acquiring a travel state Si of a tail node i of a currently traversed road segment according to a travel mode state transition model, for example, if the travel state of the node k is determined as b in the foregoing steps, referring to fig. 6, theoretically, the state of the tail node i of the currently traversed road segment may be at least one of f, g, l, and m, but the computer device not only needs to exclude some travel states which do not conform to the type of the tail node i from the travel states, but also needs to exclude travel preference information of a user according to the travel preference information, that is, determining the travel mode of the currently traversed road segment according to the travel state Si, and when the travel parameters corresponding to the travel mode conform to the travel preference information, that is, the travel mode relates to travel distance, walking distance, transfer times, travel preference information, and travel preference information, When the trip cost is consumed, the computer equipment needs to judge the trip mode of the tail node to update the trip parameters, judge whether the updated trip parameters meet the upper limit value set in the trip preference information of the user, if so, add a node state pair [ i, Si ] formed by a tail node i of the currently traversed road section and the trip state Si of the tail node i into the road section list, and continuously update the node state pair in the road section list. The iteration stop condition may be that all nodes in the multilayer traffic network traverse, or the road section list is empty, and after the iteration is finished, the computer device acquires the travel state corresponding to the starting point, and backtracks from the starting point to the end point according to the travel state corresponding to the starting point to acquire the travel route matched with the travel data.

In addition, in the iterative process, the computer device also judges the type of the road section, determines the overtaking road section or the common road section according to the type, and if the overtaking road section exists, the computer device needs to update the transfer times.

As shown in fig. 8, which is a schematic diagram of a link list updating process in an embodiment, referring to fig. 7, a computer device selects a node-state pair [ k, Sk ] with the shortest transit time length from a link list, records the shortest transit time length from the node k to a terminal, and then removes the node-state pair [ k, Sk ] from the link list; selecting m road sections [ i, k ] with k as a head node from a multilayer traffic network, traversing tail nodes of the m road sections, obtaining a trip state Si of the tail nodes i according to a trip mode state transfer model, updating trip parameters according to a trip mode corresponding to the trip state Si, judging whether the updated trip parameters meet user trip preference information, if so, adding the tail nodes i and the corresponding trip states Si into a road section queue, if not, traversing the tail nodes i of the next road section in the m road sections, and returning to select the node-state pairs [ k, Sk ] with the shortest transit time from the road section list to continue execution until the road section list is empty.

Fig. 9 is a schematic diagram of a frame of a method for generating a travel route in an embodiment. Referring to fig. 9, the data involved in the method includes a road sub-network, a walking sub-network, and a public transportation sub-network generated from map data, and further includes a private transportation sub-network generated from private transportation road data and service information related to travel of a private transportation service, and then the multi-layer transportation network considering a plurality of travel modes is obtained by connecting the sub-networks by using common network nodes in the networks. The model related to the method comprises a feasible sequence formed by defined combinations of the hyper-path and the travel mode and a travel mode state transition model. After the data and the model exist, a travel route is generated by using a path planning algorithm, the passing time length is obtained from the road real-time service, and the connection between the travel state and the travel mode of each travel data is considered in the planning process by adopting an improved label correction method to obtain a reasonable travel route set.

According to the route generation method, the multilayer traffic network comprises a road sub-network, a walking sub-network and a public traffic sub-network, and can provide support for generating travel routes comprising a plurality of different travel modes; the travel mode state transition model defines a reasonable and feasible combination sequence corresponding to multiple travel modes, and the generated travel route comprising the multiple travel modes is ensured to be in accordance with the travel habits of people. After the travel information and the travel preference information of the user are obtained, the travel time between network nodes in different sub-networks of the multilayer traffic network is inquired, so that the path planning can be carried out according to the travel time between the network nodes on the basis of the multilayer traffic network, the travel preference information of the user is considered during the path planning, various travel modes and the feasibility of transformation among the various travel modes are also considered, and the generated route matched with the travel information is in accordance with the preference of the user and is efficient and feasible.

The route generation method provided by the embodiment of the application is verified by taking Nanjing as an example: firstly, a multi-layer traffic network is generated, only services provided by public transport companies, namely buses and subways, are considered due to data limitation, and some private traffic services are not considered. As shown in fig. 10, in the generated visualized multi-layer transportation network, the road sub-network has 40710 roads and 16427 nodes, the transit sub-network has 1321 lines, 30443 stations, and the subway line has 10 lines. Setting the travel preference information of the user as follows: the maximum walking distance is 3km, the maximum riding distance is 10km, the maximum multiplier is 3, and the travel information is as follows: 8:00 in the morning from a residential area (longitude and latitude: 118.797385, 32.053281) of east school of the four-brand building, 10:00-10:20 in the morning to a Jiulong lake school area (longitude and latitude: 118.8269, 31.892234) of southeast university; in the afternoon, the vehicle starts from 19:00 of the university of southeast, Jiulong lake school district to the east valley (longitude and latitude: 118.828123, 31.867818) of the week of the fodder, and returns to the residential district of the east school of the four brands before 22:00 of the evening, so that a private car can be driven and the vehicle needs to be taken back. The generated travel route has two schemes:

the first scheme is as follows: in the first section, walking to the northern Taiping road, driving to the northern gate of the Jiulong lake school of southeast university, and walking to the destination, the walking cost is 65 yuan in 46 min. And in the second stage, walking to the north gate of the Jiulong lake school district of the southeast university, driving to the terminal, spending 11 yuan and consuming 12 min. And in the third section, driving the vehicle to return to the Taiping north road and stopping the vehicle. It takes 65min, and takes 80 yuan.

Scheme II: in the first stage, the user walks to a floating bridge subway station, gets on a 3B port to ride a third line to a Jiulong lake school station of southeast university, gets off a2 port and walks to a terminal point, and the total time is 102min, and the cost is 5 yuan. Second, walking to a Jiulong lake school station of southeast university, getting on a vehicle at a No. 2 port, taking a No. 3 wire to a No. 3 port of an east station of the silo, walking to a terminal point, spending 2 yuan, and consuming 32 min; or in the second stage, walking to the east gate of the Jiulong lake school district of southeast university, taking 838 routes to a tombstone station, walking to the terminal point by getting off, spending 2 yuan, and using 38 min. And a third stage, walking to a road station in the middle east of the fodder, getting off the vehicle from a third line to a floating bridge station, walking to the terminal point, taking 93min, and spending 5 yuan.

It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

In one embodiment, as shown in fig. 11, there is provided a route generating apparatus 1100, which may be a part of a computer device using a software module or a hardware module, or a combination of the two, and specifically includes: an obtaining module 1102, a determining module 1104, a querying module 1106, and a generating module 1108, wherein:

an obtaining module 1102, configured to obtain travel information and travel preference information;

a determining module 1104, configured to determine a multi-layer transportation network corresponding to a geographic location related to travel information, where the multi-layer transportation network includes a road sub-network, a walking sub-network, and a public transportation sub-network;

a query module 1106, configured to query a passage time length between network nodes in different subnetworks of the multi-layer traffic network;

a generating module 1108, configured to generate a travel route matched with the travel information according to the travel preference information and the travel duration based on the multi-layer traffic network, where a sequence formed by travel mode identifiers corresponding to multiple travel modes adopted by the travel route is a feasible sequence in the travel mode state transition model.

In one embodiment, the device further comprises a road network construction module for acquiring map data of the geographic location; generating a road sub-network according to the map data, wherein the road sub-network comprises road nodes and road sections among the road nodes, and the road nodes comprise road stopping points and parking points; generating a walking sub-network according to the map data, wherein the walking sub-network comprises walking nodes and road sections among the walking nodes, and the walking nodes comprise road stop points, parking points and public transportation stations; generating a public transportation sub-network according to the map data and the public transportation line data, wherein the public transportation sub-network comprises public transportation nodes and road sections among the public transportation nodes, and the public transportation nodes comprise public transportation stations; the multi-layer transportation network is obtained by connecting a road sub-network with a walking sub-network according to road stops and parking points, and connecting the walking sub-network with a public transportation sub-network according to public transportation stations.

In one embodiment, the road network construction module is further configured to obtain an order of public transportation stations of the public transportation line according to the public transportation line data; acquiring geographic coordinates of public transportation stations of public transportation lines according to the map data; and matching the public transport stops with the road sub-networks according to the sequence and the geographic coordinates to generate the public transport sub-networks comprising the public transport stops and the road sections between the public transport stops.

In one embodiment, the walking nodes in the walking sub-network further comprise private traffic nodes, and the road network construction module is further used for acquiring private traffic road data corresponding to the private traffic service; generating a private traffic sub-network according to the private traffic road data, wherein the private traffic sub-network comprises private traffic nodes and road sections between the private traffic nodes; the multi-layer traffic network is obtained by connecting the road sub-network with the walking sub-network according to the road stopping points and the parking points, connecting the walking sub-network with the public traffic sub-network according to the public traffic stopping points, and connecting the private traffic sub-network with the walking sub-network according to the private traffic nodes.

In one embodiment, the device further comprises a travel mode state transition model generation module, configured to obtain travel mode identifiers corresponding to various preset travel modes; acquiring a transfer limiting condition for restricting the change of a travel mode in the travel process; taking the travel mode identification sequence meeting the transfer limiting condition as a feasible sequence; and generating a travel mode state transition model according to the feasible sequence.

In one embodiment, the query module 1106 is further configured to query a transit time between road nodes in a road sub-network of the multi-layer traffic network; inquiring the passing time length between each walking node in the walking sub-network of the multi-layer traffic network; and inquiring the running time length between the public transportation nodes in the public transportation sub-network of the multi-layer transportation network and the vehicle frequency of each public transportation line, and calculating the passing time length between the public transportation nodes according to the running time length and the vehicle frequency of each public transportation line.

In one embodiment, the query module 1106 is further configured to mark a road segment from a first station to a second station in the public transportation sub-network as a road segment for overtaking when there are multiple public transportation lines from the first station to the second station in the public transportation sub-network; acquiring the vehicle frequency of each public transport line in a plurality of public transport lines; acquiring the running time of each public transport line from a first station to a second station; obtaining the combined vehicle frequency of the super road section according to the vehicle frequency of each public transport line; determining the average waiting time corresponding to the first station according to the frequency of the combined vehicle; determining the probability of each public transport line as a first line reaching the first station according to the vehicle frequency of each public transport line and the combined vehicle frequency; and calculating the passing time of the super road section from the first station to the second station according to the average waiting time, the probability and the driving time.

In one embodiment, the query module 1106 is further configured to mark a road segment from a first station to a second station in the public transportation sub-network as a normal road segment when there is only one public transportation line from the first station to the second station in the public transportation sub-network; acquiring the running time from a first station to a second station; and taking the running time as the passing time of the ordinary road section between the first station and the second station.

In one embodiment, the generating module 1108 is further configured to obtain start and stop locations and start and stop times of each set of travel data in the travel information; for each group of travel data, performing path planning based on a multilayer traffic network and with the shortest travel time as a target to obtain a travel route with a travel path according with a start-stop place, a travel time according with a start-stop time, a travel process according with travel preference information and a travel mode according with a travel mode state transition model; the travel preference information comprises an upper limit value of transfer times, an upper limit value of riding cost, an upper limit value of walking distance and an upper limit value of riding distance; and connecting the travel routes corresponding to each group of travel data to obtain the travel routes of the whole day.

In one embodiment, the generating module 1108 is further configured to obtain a starting point and an ending point in the travel data; determining all road sections taking the terminal points as head nodes from the multilayer traffic network; traversing each determined road section, acquiring a travel state Si of a tail node i of the currently traversed road section according to a travel mode state transition model, determining a travel mode of the currently traversed road section according to the travel state Si, and adding a node state pair [ i, Si ] formed by the tail node i of the currently traversed road section and the travel state Si of the tail node i into a road section list when travel parameters corresponding to the travel mode accord with travel preference information; after traversing is finished, the following steps are executed in an iterative mode until the road section list is empty: selecting a node state pair [ k, Sk ] corresponding to a tail node k with the shortest passing time to reach a terminal point d from the road section list, removing the selected node state pair [ k, Sk ] from the road section list, and storing the passing time from the node k to the terminal point d by adopting a passing mode corresponding to a trip state Sk; determining all road sections with the node k as a head node from the multilayer traffic network; traversing each determined road section, and acquiring a travel state Si of a tail node i of the currently traversed road section according to a travel mode state transition model; determining a trip mode of the current traversed road section according to the trip state Si, and adding a node state pair [ i, Si ] formed by a tail node i of the current traversed road section and the trip state Si of the tail node i into a road section list when a trip parameter corresponding to the trip mode accords with trip preference information; and after the iteration is finished, obtaining the travel state corresponding to the starting point, backtracking from the starting point to the end point according to the travel state corresponding to the starting point, and obtaining a travel route matched with the travel data.

The route generating device 1100, which includes a road sub-network, a walking sub-network, and a public transportation sub-network, can provide support for generating travel routes including a plurality of different travel modes; the travel mode state transition model defines a reasonable and feasible combination sequence corresponding to multiple travel modes, and the generated travel route comprising the multiple travel modes is ensured to be in accordance with the travel habits of people. After the travel information and the travel preference information of the user are obtained, the travel time between network nodes in different sub-networks of the multilayer traffic network is inquired, so that the path planning can be carried out according to the travel time between the network nodes on the basis of the multilayer traffic network, the travel preference information of the user is considered during the path planning, various travel modes and the feasibility of transformation among the various travel modes are also considered, and the generated route matched with the travel information is in accordance with the preference of the user and is efficient and feasible.

For the specific definition of the route generation device, reference may be made to the above definition of the route generation method, which is not described herein again. The respective modules in the route generation apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 12. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data of the multi-layer traffic network and data of the transit time. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a route generation method.

Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer-readable storage medium. The computer instructions are read by a processor of a computer device from a computer-readable storage medium, and the computer instructions are executed by the processor to cause the computer device to perform the steps in the above-mentioned method embodiments.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A route generation method, characterized in that the method comprises:

acquiring travel information and travel preference information;

and generating a travel route matched with the travel information according to the travel preference information and the travel duration based on the multilayer traffic network, wherein the travel route is generated by adopting a plurality of travel modes, and a sequence formed by travel mode identifications corresponding to the travel modes is a feasible sequence in a travel mode state transition model.

2. The method of claim 1, further comprising:

obtaining map data of the geographic location;

generating a road sub-network according to the map data, wherein the road sub-network comprises road nodes and road sections among the road nodes, and the road nodes comprise road parking points and parking points;

generating a walking sub-network according to the map data, wherein the walking sub-network comprises walking nodes and road sections among the walking nodes, and the walking nodes comprise road stop points, parking points and public transportation stations;

generating a public transportation sub-network according to the map data and the public transportation line data, wherein the public transportation sub-network comprises public transportation nodes and road sections among the public transportation nodes, and the public transportation nodes comprise public transportation stations;

and connecting the road sub-network with the walking sub-network according to the road parking points and the parking points, and connecting the walking sub-network with the public transportation sub-network according to the public transportation station to obtain the multi-layer transportation network.

3. The method of claim 2, wherein generating a public transportation sub-network from the map data and public transportation line data comprises:

acquiring the sequence of public transport stations of the public transport line according to the public transport line data;

acquiring geographic coordinates of public transportation stations of public transportation lines according to the map data;

and matching the public transportation station with the road sub-network according to the sequence and the geographic coordinates to generate the public transportation sub-network comprising the public transportation station and the road section between the public transportation stations.

4. The method of claim 2, wherein the walking nodes in the walking subnetwork further comprise private traffic nodes, the method further comprising:

acquiring private traffic road data corresponding to a private traffic service;

generating a private traffic sub-network according to the private traffic road data, wherein the private traffic sub-network comprises private traffic nodes and a road section between the private traffic nodes;

the connecting the road sub-network with the walking sub-network according to the road stopping points and the parking points, and connecting the walking sub-network with the public transportation sub-network according to the public transportation station to obtain the multi-layer transportation network, comprising:

and connecting the road sub-network with the walking sub-network according to the road parking points and the parking points, connecting the walking sub-network with the public transportation sub-network according to the public transportation sites, and connecting the private transportation sub-network with the walking sub-network according to the private transportation nodes to obtain the multilayer transportation network.

5. The method of claim 1, further comprising:

acquiring travel mode identifications corresponding to various preset travel modes;

acquiring a transfer limiting condition for restricting the change of a travel mode in the travel process;

taking the travel mode identification sequence meeting the transfer limiting condition as the feasible sequence;

and generating the travel mode state transition model according to the feasible sequence.

6. The method of claim 1, wherein the querying a transit time between network nodes in different sub-networks of the multi-layer transportation network comprises:

inquiring the passing time length between each road node in the road sub-network of the multi-layer traffic network;

inquiring the passing time length between each walking node in the walking sub-network of the multi-layer traffic network;

and inquiring the running time between the public transportation nodes in the public transportation sub-network of the multi-layer transportation network and the vehicle frequency of each public transportation line, and calculating the passing time between the public transportation nodes according to the running time and the vehicle frequency of each public transportation line.

7. The method of claim 6, wherein said calculating a transit time period between public transportation nodes from said travel time period and a vehicle frequency of each public transportation line comprises:

when a plurality of public transportation lines exist between a first station in the public transportation sub-network and a second station in the public transportation sub-network, marking a road section from the first station to the second station in the public transportation sub-network as a super road section;

obtaining a vehicle frequency of each public transportation line in the plurality of public transportation lines;

acquiring the running time of each public transport line from the first station to the second station;

obtaining the combined vehicle frequency of the super road section according to the vehicle frequency of each public transport line;

determining the average waiting time corresponding to the first station according to the frequency of the combined vehicle;

determining the probability of each public transport line as a first line reaching the first station according to the vehicle frequency of each public transport line and the combined vehicle frequency;

and calculating the passing time of the super road section from the first station to the second station according to the average waiting time, the probability and the running time.

8. The method of claim 6, wherein said calculating a transit time period between public transportation nodes from said travel time period and a vehicle frequency of each public transportation line comprises:

when only one public transportation line exists between a first station in the public transportation sub-network and a second station in the public transportation sub-network, marking a road section from the first station to the second station in the public transportation sub-network as a common road section;

acquiring the running time from the first station to the second station;

and taking the running time as the passing time of the common road section between the first station and the second station.

9. The method according to any one of claims 1 to 8, wherein the generating a travel route matching the travel information according to the travel preference information and the transit time based on the multi-layer transportation network comprises:

acquiring starting and stopping points and starting and stopping times of each group of travel data in the travel information;

for each group of travel data, based on the multilayer traffic network, performing path planning by taking the shortest travel time as a target, and obtaining a travel route of which the travel path meets the start-stop place, the travel time meets the start-stop time, the travel process meets the travel preference information and the travel mode meets the travel mode state transition model; the travel preference information comprises an upper limit value of transfer times, an upper limit value of riding cost, an upper limit value of walking distance and an upper limit value of riding distance;

and connecting the travel routes corresponding to each group of travel data to obtain the travel routes of the whole day.

10. The method of claim 9, wherein the road segments in the multi-layer transportation network are represented by head nodes and tail nodes, and the performing route planning based on the multi-layer transportation network and with the shortest transit time as a target for each set of travel data comprises:

acquiring a starting point and an end point in travel data;

determining all road sections with the terminal point as a head node from the multilayer traffic network;

traversing each determined road section, acquiring a travel state Si of a tail node i of the currently traversed road section according to a travel mode state transition model, determining a travel mode of the currently traversed road section according to the travel state Si, and adding a node state pair [ i, Si ] formed by the tail node i of the currently traversed road section and the travel state Si of the tail node i into a road section list when travel parameters corresponding to the travel mode accord with the travel preference information;

after traversing, iteratively executing the step of updating the road section list until the road section list is empty; the link list updating step includes: selecting a node state pair [ k, Sk ] corresponding to a tail node k with the shortest passing time length reaching the terminal point d from the road section list, and the selected node state pair [ k, Sk ] is removed from the road section list, the passing time from the node k to the terminal point d by adopting the passing mode corresponding to the travel state Sk is stored, all road sections with the node k as a head node are determined from the multilayer traffic network, each determined road section is traversed, obtaining the travel state Si of the tail end point i of the currently traversed road section according to the travel mode state transition model, determining a travel mode of the currently traversed road section according to the travel state Si, when the travel parameters corresponding to the travel mode accord with the travel preference information, adding a node state pair [ i, Si ] formed by a tail node i of a currently traversed road section and a travel state Si of the tail node i into a road section list;

and after iteration is finished, obtaining the travel state corresponding to the starting point, backtracking from the starting point to the end point according to the travel state corresponding to the starting point, and obtaining a travel route matched with the travel data.

11. A route generation apparatus, characterized in that the apparatus comprises:

and the generating module is used for generating a travel route matched with the travel information according to the travel preference information and the travel duration based on the multilayer traffic network, wherein the travel route is generated by adopting a plurality of travel modes, and a sequence formed by travel mode identifications corresponding to the travel modes is a feasible sequence in a travel mode state transition model.

12. The apparatus of claim 11, further comprising a road network construction module for obtaining map data of said geographic location; generating a road sub-network according to the map data, wherein the road sub-network comprises road nodes and road sections among the road nodes, and the road nodes comprise road parking points and parking points; generating a walking sub-network according to the map data, wherein the walking sub-network comprises walking nodes and road sections among the walking nodes, and the walking nodes comprise road stop points, parking points and public transportation stations; generating a public transportation sub-network according to the map data and the public transportation line data, wherein the public transportation sub-network comprises public transportation nodes and road sections among the public transportation nodes, and the public transportation nodes comprise public transportation stations; and connecting the road sub-network with the walking sub-network according to the road parking points and the parking points, and connecting the walking sub-network with the public transportation sub-network according to the public transportation station to obtain the multi-layer transportation network.

13. The device according to claim 11, further comprising a travel mode state transition model generation module, configured to obtain travel mode identifiers corresponding to preset various travel modes; acquiring a transfer limiting condition for restricting the change of a travel mode in the travel process; taking the travel mode identification sequence meeting the transfer limiting condition as the feasible sequence; and generating the travel mode state transition model according to the feasible sequence.

14. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 12.

15. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 12.