CN109949692A

CN109949692A - Road network method, apparatus, computer equipment and storage medium

Info

Publication number: CN109949692A
Application number: CN201910238205.6A
Authority: CN
Inventors: 董浩; 高树峰
Original assignee: Tencent Technology Shenzhen Co Ltd; Tencent Dadi Tongtu Beijing Technology Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd; Tencent Dadi Tongtu Beijing Technology Co Ltd
Priority date: 2019-03-27
Filing date: 2019-03-27
Publication date: 2019-06-28
Anticipated expiration: 2039-03-27
Also published as: CN109949692B

Abstract

The application is about a kind of road network method, apparatus, computer equipment and storage medium.This method comprises: carrying out path adaptation to the specified type road in the first road network, the first matching result is obtained；Path adaptation is carried out to other roads in the first road network, obtains the second matching result；According to the first matching result and the second matching result, the first road network matching result is obtained, includes the mapping relations between each road in the first road network and the second road network in the first road network matching result.The specified type road that this programme is treated first in matched two road networks is matched, then again to the specified type road not matched, and the road except specified type road is matched, the foundation of the mapping relations between road is carried out according to two matching results, path adaptation algorithm is enabled to be suitable for while including the matching between specified type road and the road network of general type road, to improve the accuracy of road network.

Description

Road network matching method and device, computer equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of map data application, in particular to a road network matching method, a road network matching device, computer equipment and a storage medium.

Background

With the continuous development of electronic map applications, how to provide the user with the road network data as accurate and detailed as possible is a problem that various large electronic map service providers are constantly dedicated to solve.

In the related art, an electronic map service provider may perform matching fusion on road network data from multiple different sources to obtain more complete road network data. For example, in one implementation scheme, for two road networks to be matched, the two road networks are respectively hierarchically divided through road attributes or geometric connectivity, and road matching is performed hierarchically through a triangulation method.

However, when the roads are matched hierarchically in a triangulation manner in the related art, the matching strategy is single, and the matching accuracy of road network data with complex road composition is low, which results in poor road network matching effect.

Disclosure of Invention

The embodiment of the application provides a road network matching method, a road network matching device, computer equipment and a storage medium, which can improve the accuracy of road network matching, and the technical scheme is as follows:

in one aspect, a road network matching method is provided, and the method includes:

acquiring road network data of a first road network and road network data of a second road network;

according to the road network data of the first road network and the road network data of the second road network, road matching is carried out on the specified type of roads in the first road network, and a first matching result is obtained; the first matching result indicates that the second road network comprises roads matched with each specified type of road in the first road network;

according to the road network data of the first road network and the road network data of the second road network, performing road matching on other roads in the first road network to obtain a second matching result; the second matching result indicates that the second road network comprises roads matched with other roads in the first road network; the other roads are all roads except the successfully matched specified type road in the first road network;

and obtaining a first road network matching result according to the first matching result and the second matching result, wherein the first road network matching result comprises a mapping relation between each road in the first road network and each road in the second road network.

In another aspect, a road network matching apparatus is provided, the apparatus including:

the first road network data acquisition module is used for acquiring road network data of a first road network and road network data of a second road network;

the first matching module is used for performing road matching on the specified type of roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a first matching result; the first matching result indicates that the second road network comprises roads matched with each specified type of road in the first road network;

the second matching module is used for matching other roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a second matching result; the second matching result indicates that the second road network comprises roads matched with other roads in the first road network; the other roads are all roads except the successfully matched specified type road in the first road network;

and the mapping module is used for obtaining a first road network matching result according to the first matching result and the second matching result, wherein the first road network matching result comprises a mapping relation between each road in the first road network and each road in the second road network.

Optionally, the first matching module is configured to,

acquiring a candidate road set of a first road, wherein the first road is any one specified type road in the first road network; the candidate road set of the first road comprises all roads in the second road network and close to the first road in position;

extracting first type features of the first road from road network data of the first road network, wherein the first type features comprise several features;

extracting first type features of a second road from the road network data of the second road network; the second road is any one of a candidate set of roads for the first road;

acquiring a similarity parameter between the first road and the second road according to the first type characteristics of the first road and the first type characteristics of the second road;

and when the similarity parameter between the first road and the second road meets a first similarity condition and the first road and the second road meet a specified type of strategy condition, determining that the first road is matched with the second road.

Optionally, when obtaining the candidate road set of the first road, the first matching module is configured to,

acquiring a parcel area of the first road, wherein the parcel area is a minimum rectangular area geographically wrapping a corresponding road;

and adding each road, in the second road network, of which the corresponding wrapping area and the wrapping area of the first road have intersection into the candidate road set of the first road.

Optionally, when the similarity parameter between the first road and the second road is obtained according to the first type feature of the first road and the first type feature of the second road, the first matching module is configured to,

acquiring spherical distances between each pair of adjacent shape points in the first road and spherical distances between each pair of adjacent shape points in the second road;

according to the spherical distance between each pair of adjacent shape points, acquiring the local matching length of each pair of adjacent shape points and the weight of each pair of adjacent shape points;

acquiring the accumulated matching length between the first road and the second road according to the local matching length of each pair of adjacent shape points in the first road;

acquiring a matching weight weighted average value between the first road and the second road according to the weight of each pair of adjacent shape points in the first road and the accumulated matching length;

acquiring the ratio of the accumulated matching length to the short road length, wherein the short road length is the road length of the shorter road in the first road and the second road;

and acquiring the matching weight weighted average value and the ratio of the accumulated matching length to the short road length as a similarity parameter between the first road and the second road.

Optionally, when the local matching length of each pair of adjacent shape points and the weight of each pair of adjacent shape points are obtained according to the spherical distance between each pair of adjacent shape points, the first matching module is configured to,

projecting the target adjacent shape points to the second road to obtain target adjacent projection points; the target adjacent shape point is any pair of adjacent shape points in the first road;

acquiring a first vector direction between the adjacent shape points of the target, a second vector direction between the adjacent projection points of the target and a spherical distance between the adjacent projection points of the target;

and acquiring the local matching length of the target adjacent shape points and the weight of the target adjacent shape points according to the angle difference between the first vector direction and the second vector direction and the spherical distance between the target adjacent projection points.

Optionally, before determining that the first road matches the second road, the first matching module is further configured to,

when the specified type road is a parallel road and the parallel road relative position relationship of the first road is the same as the parallel road relative position relationship of the second road, determining that the first road and the second road meet the specified type strategy condition;

when the specified type of road is a ramp and the difference value of the geometrical characteristics of the road between the first road and the second road is less than the difference threshold value, determining that the first road and the second road meet the specified type of policy condition; the road geometry feature difference comprises at least one of a road length difference and a shape point number difference.

Optionally, the second matching module is configured to,

acquiring a candidate road set of a third road, wherein the third road is any one of the other roads; the candidate road set of the third road comprises all roads which are close to the third road in the second road network;

extracting first type features of the third road from road network data of the first road network, wherein the first type features comprise several features;

extracting a first type feature of a fourth road from the road network data of the second road network; the fourth road is any one of a candidate road set of the third road;

acquiring a similarity parameter between the third road and the fourth road according to the first type characteristics of the third road and the first type characteristics of the fourth road;

when the similarity parameter between the third road and the fourth road meets a second similarity condition, determining that the third road and the fourth road are matched.

Optionally, the first network data obtaining module is configured to,

acquiring specified type characteristics of each road in a target road network in the target road network, wherein the target road network is any one of the first road network and the second road network;

generating n layers of road network pyramids corresponding to the target road network according to the corresponding specified type characteristics, wherein the road network pyramids are road network data which are layered according to the specified type characteristics, and n is an integer greater than or equal to 2;

and acquiring road network data of the target road network according to the n layers of road network pyramids.

Optionally, the first matching module is configured to perform road matching on a specified type of road in an ith pyramid of the first road network according to road network data corresponding to the ith pyramid of the first road network and road network data corresponding to the ith pyramid of the second road network, so as to obtain a matching result corresponding to the ith pyramid in the first matching result; i is more than or equal to 1 and less than or equal to n, and i is an integer.

Optionally, the second matching module is configured to perform road matching on other roads in the ith layer pyramid of the first road network according to the road network data corresponding to the ith layer pyramid of the first road network and the road network data corresponding to the ith layer pyramid of the second road network, so as to obtain a matching result corresponding to the ith layer pyramid in the second matching result; i is more than or equal to 1 and less than or equal to n, and i is an integer.

Optionally, when the road network data of the target road network is acquired according to the n-layer road network pyramid, the first road network data acquisition module is configured to,

merging adjacent roads, of which the road grades, the road names and the road attributes are the same and the vector angle difference is smaller than an angle difference threshold value, in each layer of pyramid in the target road network; the adjacent roads are a pair of roads with connected heads, and no intersection exists at the connected position;

and acquiring road network data of the target road network according to the merging result of the adjacent roads.

Optionally, the apparatus further comprises:

the original data acquisition module is used for acquiring original road network data of a first road network and original road network data of a second road network before the road network data of the first road network and the road network data of the second road network are acquired by the first road network data acquisition module;

the format unifying module is used for unifying the formats of the original road network data of the first road network and the original road network data of the second road network;

the first road network data acquisition module is used for acquiring road network data of the first road network and road network data of the second road network according to the original road network data of the first road network after the formats are unified and the original road network data of the second road network after the formats are unified.

Optionally, when the format of the original road network data of the first road network and the original road network data of the second road network are unified, the format unifying module is configured to unify the formats of the original road network data of the first road network and the original road network data of the second road network

Modifying the data format of the original road network data of the other road network of the first road network and the second road network into the reference format by taking the data format of the original road network data of one road network of the first road network and the second road network as the reference format;

or,

and uniformly modifying the data format of the original road network data of the first road network and the data format of the original road network data of the second road network into a reference format.

Optionally, the mapping module is configured to,

establishing a mapping relation between each pair of matched roads indicated by the first matching result to obtain a road mapping relation corresponding to the first matching result;

arranging the matched roads in each pair in the second matching result according to the sequence of the matching degrees from large to small; the mapping relation of each pair of roads which meet the matching relation in the peripheral topological roads is established in sequence from the pair of matched roads with the highest matching degree, and the road mapping relation corresponding to the second matching result is obtained;

and obtaining the first road network matching result according to the road mapping relation corresponding to the first matching result and the road mapping relation corresponding to the second matching result.

Optionally, the apparatus further comprises:

the second road network data acquisition module is used for acquiring road network data of a third road network and road network data of a fourth road network according to the first road network matching result, wherein the third road network comprises roads which are not sufficiently matched in the first road network, and the fourth road network comprises roads which are not sufficiently matched in the second road network; the road which is not fully matched is a road of which the ratio of the matching length to the length of the road is less than a proportional threshold;

a matching result obtaining module, configured to obtain a second road network matching result according to the road network data of the third road network and the road network data of the fourth road network, where the second road network matching result includes a mapping relationship between each road in the third road network and each road in the fourth road network;

and the updating module is used for updating the first road network matching result according to the second road network matching result to obtain an updated road network matching result.

Optionally, the apparatus further comprises:

the display module is used for displaying the road network matching interface according to the updated road network matching result;

the road network matching interface comprises a first type of road displayed with a first visual effect, a second type of road displayed with a second visual effect and a third type of road displayed with a third visual effect; the first road is a road successfully matched with the first road network and the second road network, the second road is a road unsuccessfully matched with the first road network, and the third road is a road unsuccessfully matched with the second road network.

In another aspect, a computer device is provided, which comprises a processor and a memory, wherein at least one instruction, at least one program, code set or instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the road network matching method as described above.

In another aspect, a computer readable storage medium is provided, in which at least one instruction, at least one program, a set of codes or a set of instructions is stored, and loaded and executed by a processor to implement the road network matching method as described above.

The technical scheme provided by the application can comprise the following beneficial effects:

the method comprises the steps of firstly matching specified type roads in two road networks to be matched to obtain a matching result of the specified type roads, then matching the specified type roads which are not matched with the specified type roads and the roads except the specified type roads to obtain a matching result except the specified type roads, establishing a mapping relation between the roads according to the two matching results to obtain a mapping relation between the roads in the two road networks, and enabling a road matching algorithm to be suitable for matching between the road networks simultaneously containing the specified type roads and the ordinary type roads, so that the accuracy of road network matching is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

FIG. 1 is a block diagram illustrating an electronic map application system in accordance with an exemplary embodiment;

FIG. 2 is a flow diagram illustrating a road network matching method in accordance with an exemplary embodiment;

FIG. 3 is an architecture diagram of a road network matching model according to the embodiment shown in FIG. 2;

FIG. 4 is a flow diagram illustrating a road network matching method in accordance with an exemplary embodiment;

FIG. 5 is a schematic diagram of a road network pyramid according to the embodiment shown in FIG. 4;

FIG. 6 is a schematic diagram of a first layer of the road network pyramid according to the embodiment shown in FIG. 4;

FIG. 7 is a schematic diagram of a second layer of the road network pyramid according to the embodiment shown in FIG. 4;

FIG. 8 is a schematic diagram of a third layer of the road network pyramid according to the embodiment shown in FIG. 4;

FIG. 9 is a graph comparing the merging effect of the super-way according to the embodiment shown in FIG. 4;

FIG. 10 is a schematic diagram of a specified type of road match involved in the embodiment shown in FIG. 4;

FIG. 11 is a diagram of a matching result presentation interface according to the embodiment shown in FIG. 4;

FIG. 12 is a flow diagram illustrating road network matching in accordance with an exemplary embodiment;

fig. 13 is a block diagram showing the structure of a road network matching apparatus according to an exemplary embodiment;

FIG. 14 is a schematic diagram illustrating a configuration of a computer device, according to an example embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

The embodiment of the application provides a road network matching scheme, and the scheme can provide a more accurate road network matching effect. For ease of understanding, several terms referred to in this application are explained below.

1) Road network data

Road network data is data that is related to geographical and spatial distribution and reflects geospatial entities and changes thereof in the real world. The road network data usually has spatial coordinates, for example, the road network data includes geometric position information, spatial form information, spatial relationship information, attribute semantic information, and the like of geospatial entities.

In the present application, the road network data may include road data of each road in an actual road network in a certain area. Each piece of road data may include coordinates (longitude and latitude) of a corresponding road, a topology (a corresponding intersection model, a road grade, a road model, a road direction, and the like), a road name, and the like.

2) Road network matching

Road network matching is a method for analyzing and calculating differences of attributes among roads and evaluating spatial similarity among the roads, so as to identify the same-name road entities appearing in the real world in different road network databases and establish the relation of related attribute elements displayed by the identified road entities in different road networks through a logical process.

In the present application, the road network matching may refer to a process of matching, for two or more road networks, roads that both exist in the two or more road networks and roads that exist in a part of the road networks but do not exist in other part of the road networks according to respective road network data of the two or more road networks, so as to subsequently fuse the two or more road networks to obtain a more complete road network.

Fig. 1 is a schematic structural diagram illustrating an electronic map application system according to an exemplary embodiment. The system comprises: a server 120 and a number of terminals 140.

The server 120 is a server, or a plurality of servers, or a virtualization platform, or a cloud computing service center.

The terminal 140 may be a terminal device with an interface display function, for example, the terminal 140 may be a mobile phone, a tablet computer, an e-book reader, smart glasses, a smart watch, an MP3 player (Moving Picture Experts group Audio Layer III, motion Picture Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts group Audio Layer IV, motion Picture Experts compression standard Audio Layer 4), a laptop portable computer, a desktop computer, and the like.

The terminal 140 and the server 120 are connected via a communication network. Optionally, the communication network is a wired network or a wireless network.

Optionally, the system may further include a management device 160, and the management device 160 is connected to the server 120 through a communication network. Optionally, the communication network is a wired network or a wireless network.

Optionally, the wireless network or wired network described above uses standard communication techniques and/or protocols. The Network is typically the Internet, but may be any Network including, but not limited to, a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a mobile, wireline or wireless Network, a private Network, or any combination of virtual private networks. In some embodiments, data exchanged over a network is represented using techniques and/or formats including Hypertext Mark-up Language (HTML), Extensible markup Language (XML), and the like. All or some of the links may also be encrypted using conventional encryption techniques such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet protocol Security (IPsec). In other embodiments, custom and/or dedicated data communication techniques may also be used in place of, or in addition to, the data communication techniques described above.

The terminal 140 includes an electronic map application program, which can provide various applications based on an electronic map, such as navigation, route query, location search, and the like.

The server 120 may be a server corresponding to an electronic map application. The server 120 may provide online map services, such as online navigation, online route query, and online location search, to the electronic map application in the terminal 140 based on the road network data; alternatively, the server 120 may provide the road network data to the terminal 140, and the electronic map application in the terminal 140 may provide the local map service based on the road network data.

The road network data may be obtained by performing matching fusion on road network data of a plurality of road networks.

In the integration and fusion of road network data, the key lies in the combination of the spatial position, the topological relation and some attribute characteristics of a road entity, and finally the advantages of a plurality of data sources are integrated together to form a complete and comprehensive road network database, so that the method has very important significance for improving the utilization rate and timeliness of data and reducing the collection cost. The road network matching algorithm is a very basic and key module in the integrated fusion of road network data.

The road network matching scheme in the related technology carries out discrete isolated processing on roads, the matching strategy is too single, the algorithm is difficult to be suitable for road data of all types aiming at different regions and different road data characteristics of different types (parallel roads, ramp roads and the like), and the problem that the complex matching relation of many-to-many roads in the multi-source road network cannot be effectively solved, so that the complex road matching cannot be effectively processed, and the defects of certain degree exist in the matching accuracy and the calculating efficiency, so that the application aims to provide a new road network matching algorithm for the integrated fusion of the multi-source road network data.

Fig. 2 is a flow chart illustrating a road network matching method according to an exemplary embodiment, which may be used in a computer device, such as the server 120 or the management device 160 of the system shown in fig. 1, or other computer devices (such as a desktop computer, a laptop computer, a personal workstation, or other servers). As shown in fig. 2, the road network matching method may include the following steps:

step 21, obtaining road network data of a first road network and road network data of a second road network.

The road network data of the first road network and the road network data of the second road network may be road network data of two road networks with different sources.

For example, the road network data of the first road network may be road network data acquired from map data provided by one map data provider (which may be the original road network data of the first road network), and the road network data of the second road network may be road network data acquired from map data provided by another map data provider (which may be the original road network data of the first road network).

And step 22, performing road matching on the specified type of roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a first matching result.

The first matching result indicates that the second road network comprises roads matched with each specified type road in the first road network.

The specified type of road may be a road corresponding to a specified road type preset by a developer or a manager. For example, in the embodiment of the present application, the specified type of road may include at least one of the following types of roads: parallel roads, ramps and access roads.

In an exemplary scheme, in the first matching result, one specified type of road in the first road network may be matched with one or more roads in the second road network, that is, the roads in the first road network and the second road network in the first matching result are not limited to a one-to-one relationship, and may also be a many-to-many matching relationship.

And step 23, performing road matching on other roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a second matching result.

Wherein the second matching result indicates that the second road network comprises roads matched with other roads in the first road network; the other roads are roads in the first road network except the specified type of road which is successfully matched.

In an exemplary scheme, in the second matching result, one road in the first road network may be matched with one or more roads in the second road network, that is, the roads in the first road network and the second road network in the second matching result are not limited to a one-to-one relationship, and may be a many-to-many matching relationship.

And 24, acquiring a first network matching result according to the first matching result and the second matching result.

The first road network matching result includes a mapping relationship between the first road network and each road in the second road network.

In summary, according to the scheme provided by the embodiment of the application, firstly, the specified type of roads in the two road networks to be matched are matched to obtain the matching result of the specified type of roads, then, the specified type of roads which are not matched and the roads except the specified type of roads are matched to obtain the matching result except the specified type of roads, the mapping relation between the roads in the two road networks is established according to the two matching results, and the mapping relation between the roads in the two road networks is obtained, so that the road matching algorithm can be suitable for matching between the road networks including the specified type of roads and the ordinary type of roads, and the accuracy of road network matching is improved.

In addition, in the scheme provided by the embodiment of the application, the matching result for road mapping can include many-to-many road matching relations, so that the many-to-many complex matching relations of roads in the multi-source road network can be effectively solved, and the accuracy of road network matching is further improved.

The embodiment of the application provides a new road network matching algorithm, and aiming at the problems of complex matching relations and insufficient algorithm accuracy caused by single matching strategy, a matching mode strategy chain is designed, so that the matching accuracy of the algorithm to different types of roads is improved.

In an exemplary scheme, the method and the device can also have the global characteristics and the local characteristics of the roads by constructing the road network pyramid and the super road, reduce the interference of local difference while simplifying the complexity of the road network, and effectively establish the many-to-many matching relationship of the road network; in addition, the method can also provide a new road network matching similarity evaluation index, and a visualization module is introduced, so that the matching effect can be conveniently and visually analyzed; the new road network matching algorithm has good universality, obviously improves the matching precision, simultaneously ensures the calculation efficiency of the matching algorithm, and can be applied to the integrated fusion of multi-source road network data.

Please refer to fig. 3, which illustrates an architecture diagram of a road network matching model related to a road network matching processing mechanism according to the present application. As shown in fig. 3, the road network matching model 30 comprises a data preprocessing component 31, a special mapping strategy chain component 32, a topological mapping strategy chain component 33, and a visualization component 34. The special mapping strategy chain component 32 and the topology mapping strategy chain component 33 further include a road network pyramid component 35, a candidate set screening component 36, a feature extraction component 37, and a similarity measurement component 38, respectively.

The input of the model shown in fig. 3 is two road networks to be matched (set as a first road network and a second road network), the first road network and the second road network are respectively subjected to data preprocessing, then the road matching of the first road network and the second road network is completed through a special mapping strategy chain and a topological mapping strategy chain, and finally, the visualization component is used for displaying so as to perform effect analysis.

Fig. 4 is a flowchart illustrating a road network matching method according to an exemplary embodiment, which may be applied to a computer device, such as the server 120 or the management device 160 of the system shown in fig. 1, or other computer devices (such as a desktop computer, a laptop computer, a personal workstation, or other servers). Taking the road network matching through the model shown in fig. 3 as an example, as shown in fig. 4, the road network matching method may include the following steps:

step 401, obtaining original road network data of a first road network and original road network data of a second road network.

The original road network data of the first road network and the original road network data of the second road network may be obtained by reading a road network matching model in a computer device from a preset database. Alternatively, the original road network data of the first road network and the original road network data of the second road network may be imported into a computer device by a manager through a data import tool, and read locally by the road network matching model in the computer device.

Step 402, unifying the format of the original road network data of the first road network and the original road network data of the second road network.

When the original road network data of the first road network and the original road network data of the second road network are unified in format, the computer device may modify the data format of the original road network data of the other one of the first road network and the second road network into the reference format by taking the data format of the original road network data of the one of the first road network and the second road network as the reference format.

In the embodiment of the present application, the original road network data of the first road network and the original road network data of the second road network may be from different road network data service providers, and the different road network data service providers may use different data formats to organize the road network data, so before matching the two road networks, the data formats of the two road networks to be matched need to be unified.

For example, the step 402 can be implemented by the data preprocessing component 31 in fig. 3, which, assuming that there is a first road network and a second road network to be matched, functions as: unifying the data formats of the first road network and the second road network so as to facilitate the subsequent algorithm calculation; the executing basis can be that the first road network is used as a reference, and the road data in the second road network is converted, including the conversion of data formats such as a coordinate system, a road grade, a road attribute, a road model (such as a parallel road and a bidirectional road), an intersection model and the like.

For example, when the road network data of the first road network is the road network data provided by the service provider a, and the road network data of the second road network is the road network data provided by the service provider b, the data preprocessing component 31 may convert the format of the road network data of the second road network into the same data format as the road network data of the first road network.

In another exemplary embodiment, when formats of the original road network data of the first road network and the original road network data of the second road network are unified, the computer device may also uniformly modify a data format of the original road network data of the first road network and a data format of the original road network data of the second road network into a reference format.

For example, taking the step implemented by the data preprocessing component 31 in fig. 3 as an example, a reference format may be uniformly set in the data preprocessing component 31, and when the data preprocessing component 31 performs data preprocessing, all the road network data to be matched are converted into the reference format.

The above feature extraction component 37 in fig. 3 has the following functions: the method is used for extracting key features of the road and participating in subsequent similarity calculation and rule auxiliary judgment. The main extracted features are: geometric characteristics such as road length, number of road shape points, start and end point angles of the road and the like; semantic features including road attributes, road grades, road names, etc.; and topological characteristics including hitching relationships between roads and intersections.

In the road network data, each road is represented by a plurality of points, that is, one road is formed by connecting every two adjacent points corresponding to the one road, and the points used for representing the road in the road network data are the shape points of the corresponding road. The number of the shape points of one road is usually related to the bending degree of the road, the more a certain road is bent, the more the number of the required shape points is, and correspondingly, the less a certain road is bent, the less the number of the required shape points is, and under an ideal condition, a completely straight road can be accurately represented by only two shape points.

The features extracted by the feature extraction component 37 are used in the road network pyramid component 35, the candidate set screening component 36 and the similarity measurement component 37 in fig. 3, so as to realize respective functions based on the above features.

Step 403, obtaining road network data of the first road network and road network data of the second road network according to the original road network data of the first road network after format unification and the original road network data of the second road network after format unification.

In an exemplary scheme, when obtaining road network data of the first road network and road network data of the second road network, for a target road network, a computer device may obtain specified type characteristics of each road in the target road network, where the target road network is any one of the first road network and the second road network; generating n layers of road network pyramids corresponding to the target road network according to the corresponding specified type characteristics, wherein the road network pyramids are road network data which are layered according to the specified type characteristics; each layer of road network pyramid in the n layers of road network pyramids comprises roads with the same specified type characteristics in the target road network, and n is an integer greater than or equal to 2; and acquiring the road network data of the target road network according to the n layers of road network pyramids.

Wherein the specific type feature may include at least one of the following features: road class (which may also be referred to as road function), and road attributes. Wherein the road attribute may comprise at least one of the following attributes: the traffic limit (such as the speed limit) of the corresponding road, the direction of the corresponding road, and the road type (such as whether it is a ramp, whether it is a tunnel, whether it is a roundabout, etc.) of the corresponding road.

Here, the step 403 may be implemented by the road network pyramid component 35 in fig. 3, where the road network pyramid component 35 functions as: the method comprises the following steps of performing spatial hierarchical division on a road network, and establishing a road network hierarchical spatial form, wherein entity roads of different levels have different specified type characteristics in the road network, so that not only is the complexity of the road network of each level reduced, but also the constraint among the levels can be used for improving the accuracy of a matching algorithm; because the information quantity borne by the roads corresponding to different specified type features in the road network is different, for example, taking the specified type features including the road grades as an example, the high-grade roads can better visually identify and determine the matching relationship than the low-grade roads, the road network pyramid is constructed by adopting the specified type features of the roads. For example, taking the example that the specified type features include road levels, the road of the highest section level (e.g., expressway from high speed to city, customizable) may be set at the highest layer of the pyramid, the road of another section level (e.g., national road to provincial road) may be set at the next layer, and so on, and the number of layers of the pyramid may be set according to the situation of the actual data source, as shown in fig. 5 to 8. Fig. 5 is a schematic diagram of a road network pyramid according to an embodiment of the present application; FIG. 6 is a schematic diagram of a first layer of a road network pyramid according to an embodiment of the present application; fig. 7 is a schematic diagram of a second layer of the road network pyramid according to an embodiment of the present application; fig. 8 is a schematic diagram of a third layer of the road network pyramid according to the embodiment of the present application.

According to the method, through the road network pyramid component, in the road matching of a multi-source heterogeneous road network (such as a multi-source multi-scale road network), different and same points among the road networks are identified, the integration efficiency of the fusion of road network data is effectively improved, a visual attention mechanism is introduced into the similarity comparison of the road networks, a visual cognition mechanism of a human is simulated to carry out spatial hierarchy division and reasoning on the complex road network, an algorithm flow from main to secondary and from stage to stage reasoning is established, and the accurate matching of the complex road network is finally realized.

In an exemplary scheme, when the road network data of the target road network is acquired according to the n layers of road network pyramids, the computer device may merge adjacent roads, which have the same road grade, road name and road attribute and have a vector angle difference smaller than an angle difference threshold value, in each layer of pyramids in the target road network; the adjacent roads are a pair of roads with head connected and no intersection at the connection position; and acquiring road network data of the target road network according to the merging result of the adjacent roads.

For example, in a first road network, a road is split into 3 roads for representation, while in a second road network, the road is split into 2 roads for representation, and if the road matching is directly performed, the matching effect is poor. Thus, in the present embodiment, for the roads assigned to each level of the pyramid, the topological relationships can be reconstructed to generate the super-roads (i.e., road merge). The implementation is based on the following: traversing each road, and if the grades of the adjacent roads at the periphery are consistent with the self road, the names of the roads are consistent, the attributes of the roads are consistent, the vector angle difference is less than a certain threshold value, and no intersection exists, merging and performing recursion; stopping until no mergeable roads exist or the length of the current super road exceeds a certain threshold; and after all roads are combined to generate the super road, recalculating the current layer of the pyramid to generate the intersection topological relation. By the super road combination, the length of each road in the two road networks to be matched is as long as possible, and the matching accuracy can be improved in the subsequent matching process.

Please refer to fig. 9, which is a comparison diagram of the merging effect of super roads according to the embodiment of the present application. In fig. 9, the left part (a) is the intersection topological relation before merging, which includes 8 roads, after super road merging, the roads 3, 4, 5 in the left part (a) are merged into the road 3 in the right part (b), and the roads 6, 7 in the left part (a) are merged into the road 6 in the right part (b).

Step 404, performing road matching on the specified type of roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a first matching result.

When obtaining the first matching result, the computer device may perform road matching on the specified type of road in the ith pyramid of the first road network according to the road network data corresponding to the ith pyramid of the first road network and the road network data corresponding to the ith pyramid of the second road network, so as to obtain a matching result corresponding to the ith pyramid in the first matching result; wherein i is more than or equal to 1 and less than or equal to n, and i is an integer.

In the embodiment of the application, when the computer device matches two road networks, the matching can be performed for each layer in the road network pyramid, so as to reduce the complexity of road network matching.

When road matching is performed on the specified type of road in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a first matching result, the computer device may obtain a candidate road set of the first road, where the first road is any one of the specified type of road in the first road network; the candidate road set of the first road comprises all roads in the second road network and close to the first road; extracting first type features of the first road from road network data of the first road network, wherein the first type features comprise several features; extracting first type features of a second road from the road network data of the second road network; the second road is any one of the road in the candidate road set of the first road; acquiring a similarity parameter between the first road and the second road according to the first type characteristics of the first road and the first type characteristics of the second road; and when the similarity parameter between the first road and the second road meets a first similarity condition and the first road and the second road meet a specified type of strategy condition, determining that the first road is matched with the second road.

In an exemplary embodiment, in obtaining the set of candidate roads for the first road, the computer device may obtain a parcel area for the first road, the parcel area being a smallest rectangular area that geographically wraps the corresponding road; and adding the roads, in the second road network, of which the corresponding wrapping areas are intersected with the wrapping area of the first road into the candidate road set of the first road.

Wherein the above steps can be implemented by the candidate set screening component 36 of fig. 3. The candidate set screening component 36 functions to: aiming at a certain super road to be matched in the first road network, screening a super road set to be matched in the second road network, wherein the accurate design of the candidate set screening component 36 can reduce the algorithm matching calculation amount and improve the algorithm execution efficiency on one hand, and also has great influence on the matching recall rate of the algorithm on the other hand; the method is characterized in that a minimum package rectangle (which can be obtained by coordinate extension according to actual data setting) is generated for each super road, and for a certain super road in the first road network, roads where all package rectangles and the super road have intersection are found in the second road network and serve as a candidate set of the super road in the first road network.

Optionally, when the similarity parameter between the first road and the second road is obtained, the computer device may obtain a spherical distance between each pair of adjacent shape points in the first road and a spherical distance between each pair of adjacent shape points in the second road; according to the spherical distance between each pair of adjacent shape points, acquiring the local matching length of each pair of adjacent shape points and the weight of each pair of adjacent shape points; acquiring the accumulated matching length between the first road and the second road according to the local matching length of each pair of adjacent shape points in the first road; acquiring a matching weight weighted average value between the first road and the second road according to the weight of each pair of adjacent shape points in the first road and the accumulated matching length; acquiring the ratio of the accumulated matching length to the short road length, wherein the short road length is the road length of the shorter road in the first road and the second road; and acquiring the weighted average value of the matching weights and the ratio of the accumulated matching length to the short road length as a similarity parameter between the first road and the second road.

When the weighted average of the matching weights is greater than a preset weighted average threshold and the ratio of the cumulative matching length to the short road length is greater than a preset ratio threshold, it may be determined that the similarity parameter between the first road and the second road satisfies a first similarity condition.

When the local matching length of each pair of adjacent shape points and the weight of each pair of adjacent shape points are obtained according to the spherical distance between each pair of adjacent shape points, the computer equipment projects the target adjacent shape points to the second road to obtain the target adjacent projection points; the target adjacent shape point is any pair of adjacent shape points in the first road; acquiring a first vector direction between the adjacent shape points of the target, a second vector direction between the adjacent projection points of the target and a spherical distance between the adjacent projection points of the target; and acquiring the local matching length of the target adjacent shape points and the weight of the target adjacent shape points according to the angle difference between the first vector direction and the second vector direction and the spherical distance between the target adjacent projection points.

Wherein the above steps can be implemented by the similarity measure component 38 of fig. 3.

The similarity calculation component 38 functions to: calculating the similarity between the road to be matched in the first road network and the candidate road in the second road network, if the similarity satisfies a certain threshold condition, putting the candidate road in the second road network into the best matching set (i.e. the first matching relationship or the second matching relationship), and then further screening. The specific calculation process is as follows:

the method comprises the steps of firstly, obtaining shape points of a road 1 to be matched in a first road network and a candidate road 2 in a second road network, sequentially obtaining two adjacent shape points in the road 1, calculating the spherical distance of the two adjacent shape points, and marking the spherical distance as dSegmentLen;

secondly, projecting the two shape points to the road 2, and calculating the angle difference (dDiffAngle) between the vector direction between the original points and the vector direction between the projection points (dProj1, dProj2), the projection distance (dProjDist1, dProjDist 2);

and thirdly, calculating the local segment matching length (dSegmentMatchLen) and the corresponding weight value (dSegmentWeight) of the two shape points based on the projection distance and the angle difference. The weight calculation formula is as follows:

the ANGLE weight dSegmentWeight of two shape points (dsdiffangleweight + dprojdisphere weight) is divided by (DIFF _ ANGLE _ FACTOR + RPOJ _ DIST _ FACTOR), where,

DIFF ANGLE weight ═ DIFF _ ANGLE _ FACTOR ═ cos (PI _ PER _ degre [ ((180-diffangle)) +1), PI _ PER _ degre is a preset parameter, which may be set to 0.01745, in one possible example, and the above-mentioned DIFF _ ANGLE _ FACTOR represents the weight coefficient of the corresponding ANGLE; dProjDistWeight represents a projection distance weight value, dProjDistWeight ═ RPOJ _ DIST _ FACTOR ((dProjDist1+ dProjDist2)/2), and RPOJ _ DIST _ FACTOR represents a projection distance weight coefficient; the weight coefficient of the angle and the weight coefficient of the projection distance may be preset coefficients by a developer or a manager.

Fourthly, sequentially traversing two adjacent shape points in the road 1, and accumulating the local section matching lengths of each pair of shape points to obtain an overall matching length dMatchLen; and accumulating the weight dSegmentWeight _ dSegmentMatchLen corresponding to each pair of shape points to obtain the matching weight of the whole segment: dMatchWeight;

and fifthly, calculating a weighted average of the matching weights of the road sections, namely dMatchweight/length of the road 1, and the ratio of the matching length to the length of the shorter road in the road 1 and the road 2:

ratio — dMatchLen/min (length of road 1, length of road 2);

and a sixth step: if the dmamchweight and the matching Ratio respectively satisfy the predetermined threshold conditions, the road 1 and the road 2 are considered to have higher similarity, and the road 2 is placed in the optimal matching set of the road 1.

In an exemplary aspect, before determining that the first road matches the second road, when the specified type of road is a parallel road and the parallel road relative positional relationship of the first road is the same as the parallel road relative positional relationship of the second road, it is determined that the first road and the second road satisfy the specified type of policy condition.

When the specified type of road is a ramp and the difference value of the geometrical characteristics of the road between the first road and the second road is less than the difference threshold value, determining that the first road and the second road meet the specified type of policy condition; the road geometry difference comprises at least one of a road length difference and a shape point number difference.

In the embodiment of the present application, the special mapping policy component 32 in fig. 3 described above functions as: because the data characteristics of roads in different areas and different types (parallel roads, ramps and the like) are different, the special mapping strategy component 32 can extract different characteristics aiming at different specified types of roads, so as to ensure that the algorithm can pertinently solve the matching problem of the specified types of roads; fig. 10 is a schematic diagram illustrating a road matching of a specified type according to an embodiment of the present application. As shown in FIG. 10, the execution steps of the special mapping policy component 32 may be as follows:

firstly, extracting specified types of roads in a first road network and a second road network, then respectively constructing a road network pyramid (one road network is generated for each road network) by adopting the roads, and after the construction is finished, sequentially performing matching calculation from the top layer to the bottom layer of the pyramid.

Step 405, performing road matching on other roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a second matching result.

When a second matching result is obtained by road matching other roads in the first road network according to the road network data of the first road network and the road network data of the second road network, the computer device performs road matching on other roads in the ith layer of pyramid of the first road network according to the road network data corresponding to the ith layer of pyramid of the first road network and the road network data corresponding to the ith layer of pyramid of the second road network, and obtains a matching result corresponding to the ith layer of pyramid in the second matching result; wherein i is more than or equal to 1 and less than or equal to n, and i is an integer.

When road matching is performed on other roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a second matching result, the computer equipment obtains a candidate road set of a third road, wherein the third road is any one of the other roads; the candidate road set of the third road comprises all roads in the second road network and close to the third road; extracting first type features of the third road from road network data of the first road network, wherein the first type features comprise several features; extracting a first type feature of a fourth road from the road network data of the second road network; the fourth road is any one of the road in the candidate road set of the third road; acquiring a similarity parameter between the third road and the fourth road according to the first type characteristics of the third road and the first type characteristics of the fourth road; and when the similarity parameter between the third road and the fourth road meets a second similarity condition, determining that the third road is matched with the fourth road.

The step 405 may be performed by the topology mapping policy chain component 33 in fig. 3, and a process of the topology mapping policy chain component 33 obtaining the second matching result through the road network pyramid component 35, the candidate set screening component 36, the feature extraction component 37 and the similarity measurement component 38 is similar to a process of obtaining the first matching result through the road network pyramid component 35, the candidate set screening component 36, the feature extraction component 37 and the similarity measurement component 38 in the step 404, except that in the step 405, only the similarity parameter between two roads needs to satisfy the second similarity condition, and the two roads can be considered to be matched.

In this step, the computer device first constructs a road network pyramid for all unsuccessfully matched roads (i.e. unsuccessfully matched roads in the unspecified type of roads and unsuccessfully matched partial roads in the specified type of roads) in the first road network and the second road network after matching calculation by the special mapping strategy chain component 32; all the super-ways of each layer in the pyramid are then matched.

In the embodiment of the present application, the special mapping policy chain component 32 and the topological mapping policy chain component 33 respectively construct a pyramid for the respective roads to be processed, that is, the special mapping policy chain component 32 constructs a road network pyramid for all the specified types of roads, while the topological mapping policy chain component 33 constructs a road network pyramid for the other roads except for the specified types of roads successfully matched, and when performing road network matching, the special mapping policy chain component 32 and the topological mapping policy chain component 33 match all the roads in the road network pyramid respectively constructed.

In another possible example, the computer device may also construct a road network pyramid for all the roads in the first road network and the second road network, and when performing road matching, the special mapping policy link component 32 performs matching according to the specified type of road in the road network pyramid, and the topological mapping policy link component 33 performs matching according to other roads in the road network pyramid except for the specified type of road that is successfully matched. For example, the special mapping policy chain component 32 first matches the specified type of road in the constructed road network pyramid, removes the successfully matched road in the road network pyramid after the matching is completed, and the subsequent topology mapping policy chain component 33 matches each road in the road network pyramid after the successfully matched specified type of road is removed.

Step 406, obtaining a first network matching result according to the first matching result and the second matching result.

Optionally, when obtaining the first road network matching result according to the first matching result and the second matching result, the computer device may establish a mapping relationship between each pair of matched roads indicated by the first matching result, and obtain a road mapping relationship corresponding to the first matching result; arranging the matched roads in each pair in the second matching result according to the sequence of the matching degrees from large to small; the method comprises the steps that mapping relations are sequentially established for each pair of roads which meet the matching relations in the peripheral topological roads from a pair of matched roads with the highest matching degree, and road mapping relations corresponding to a second matching result are obtained; and obtaining the first road network matching result according to the road mapping relation corresponding to the first matching result and the road mapping relation corresponding to the second matching result.

In this embodiment, the step of establishing the mapping relationship between each pair of matched roads indicated by the first matching result and obtaining the road mapping relationship corresponding to the first matching result may be executed by the special mapping policy chain component 32. For example, for each specified type road 1 belonging to the first road network in the first matching result, the specified type road 1 corresponds to at least one road belonging to the second road network in the first matching result (for example, corresponding to the specified type road 2 and the specified type road 3 that match), and the special mapping policy chain component 32 establishes a mapping relationship between the specified type road 1 and the specified type road 2 and the specified type road 3, respectively.

In the embodiment of the present application, the pairs of matched roads in the second matching result are arranged in the order of decreasing matching degree; the step of sequentially establishing the mapping relationship for each pair of roads satisfying the matching relationship in the peripheral topological roads from the pair of matched roads with the highest matching degree to obtain the road mapping relationship corresponding to the second matching result may be executed by the topological mapping policy component 33. For example, the topology mapping policy component may sort in descending order according to the matching similarity; then, topology mapping is started based on the super roads (road 1, road 2) with high matching degree:

a) and acquiring topological roads around the road 1, traversing each road, matching each road with each road around the road 2, and if the similarity meets a threshold condition, determining that the matching is successful.

The topological road around a certain road may be another road connected to the certain road.

b) Selecting the matching pair with the highest matching degree from all the candidate sets obtained by calculation in the step a) as the optimal subsequent result in the current topology.

c) Based on the optimal successor result, topology matching is recursively performed.

The matching degree can be obtained through a similarity parameter between two roads. For example, the similarity parameter includes a weighted average of matching weights between two roads, and a ratio of the cumulative matching length to the short road length.

For example, in an exemplary scheme, the topology mapping policy component 33 may perform weighted summation on the weighted average of the matching weights between two roads and the ratio of the cumulative matching length to the short road length to obtain the matching degree between two roads.

Alternatively, in another exemplary scheme, the topology mapping policy component 33 may also use a weighted average of the matching weights between two roads, or a ratio of the cumulative matching length to the short road length as the matching degree between two roads.

In the present application, taking a pair of matched roads (i.e. road 1 and road 2) with the highest matching degree in the first matching relationship and the second matching relationship as an example, the topology mapping policy component 33 first establishes a mapping relationship between road 1 and road 2, then obtains x1 surrounding topology roads of road 1, obtains y1 surrounding topology roads of road 2, obtains each road in x1 surrounding topology roads of road 1, and matches degrees between y1 surrounding topology roads of road 2, selects a pair of roads (such as road 3 and road 4) with the highest matching degree and the matching degree higher than a preset threshold, establishes a mapping relationship between road 3 and road 4, then obtains x2 surrounding topology roads of road 3, obtains y2 surrounding topology roads of road 4, and obtains each road in x2 surrounding topology of road 3, and respectively selecting the matching degrees between the y2 surrounding topological roads of the road 4, selecting a pair of roads (such as the road 5 and the road 6) with the highest matching degree and the matching degree higher than a preset threshold value, establishing a mapping relation between the road 5 and the road 6, and repeating the steps until no topological road meeting the condition exists. And then, the topology mapping strategy component selects a pair of matched roads with the second highest matching degree in the first matching relation and the second matching relation, and executes the topology extending process again.

Step 407, obtaining road network data of the third road network and road network data of the fourth road network according to the first road network matching result.

The third road network comprises the road which is not fully matched in the first road network, and the fourth road network comprises the road which is not fully matched in the second road network; the road which is not sufficiently matched is a road of which the ratio of the matching length to the length of the road is smaller than a proportional threshold value.

After the mapping relationship is established in step 406, there may be a case where the matching degree between two roads mapped to each other is not high enough (for example, when the ratio of the cumulative matching length between a road a and another road b in the first road network to the length of the road b is smaller than the proportional threshold, the road a and the road b may be referred to as an insufficiently matched road) although the mapping relationship is established for some roads, or there may also be a case where some roads are not successfully established with the mapping relationship, and the roads corresponding to this case may be referred to as insufficiently matched roads.

In the embodiment of the present application, matching and mapping relationship establishment may be performed again for roads that are not sufficiently matched, and at this time, it is necessary to first obtain roads that are not sufficiently matched in the first road network and the second road network, and respectively form the first road network and the fourth road network.

Step 408, obtaining a second road network matching result according to the road network data of the third road network and the road network data of the fourth road network, where the second road network matching result includes a mapping relationship between each road in the third road network and each road in the fourth road network.

In this embodiment, the process of establishing the matching and mapping relationship in step 408 may be similar to the process of performing the road matching and topology mapping by the topology mapping policy component 33 in steps 405 and 406, that is, when step 408 is executed, the road matching model in the computer device may first respectively construct a road network pyramid for the third road network and the fourth road network, then perform candidate set screening and similarity calculation on the roads in the third road network and the roads in the same layer in the fourth road network for each layer in the road network pyramid, perform matching according to the calculation result of the similarity, and finally perform topology mapping according to the matching result.

In an exemplary scenario, step 408 described above may be performed by topology mapping policy component 33.

Step 409, updating the first road network matching result according to the second road network matching result to obtain an updated road network matching result.

Through the steps 407 to 409, the computer device may further complete the mapping relationship, mainly traverse all the insufficiently matched roads in the first road network and the second road network (the ratio of the matching length to the total length of the computer device is less than a certain threshold), perform matching calculation again, further perfect the road mapping relationship in the road network, for example, modify or add a new mapping relationship in the matching result of the first road network according to the mapping relationship obtained by the matching calculation again.

And step 410, displaying a road network matching interface according to the updated road network matching result.

The road network matching interface comprises a first type of road displayed by a first visual effect, a second type of road displayed by a second visual effect and a third type of road displayed by a third visual effect; the first road is a road successfully matched with the first road network and the second road network, the second road is a road unsuccessfully matched with the first road network, and the third road is a road unsuccessfully matched with the second road network.

This step 410 can be performed by the visualization component 34 of fig. 3, the visualization component 34 functioning to: and the matching result is visually displayed, so that the effect verification is facilitated.

Please refer to fig. 11, which is a matching result display interface diagram according to an embodiment of the present application. As shown in fig. 11, the original intersection nodes of the first road network are displayed with a certain dot (for example, displayed as dark black dots), the original intersection nodes of the second road network are displayed with another dot (for example, displayed as light gray dots), and the successfully matched roads are identified with the same color, so that based on the successfully matched roads, the administrator can visually see the complex matching relationship among the roads in the two road networks, i.e., one-to-one, one-to-many, and many-to-many, and verify whether the matching relationship is correct. Based on the road with unsuccessful matching, the existence of the road in the first road network can be indicated by a line (such as a thin gray line), and the nonexistence of the road in the second road network; and indicates the presence of the road in the second road network and the absence of the road in the first road network by another line, such as a thick red line.

The method and the device can effectively improve the matching accuracy for the same entity road in the multisource multiscale road network, have better calculation efficiency, and are beneficial to improving the utilization rate of multisource road network data and reducing the data acquisition cost; on the other hand, the effectiveness of a road network can be guaranteed, and data guarantee is provided for a better navigation effect.

The special mapping policy component is described by taking only the example of processing specified types of roads such as parallel roads and ramp roads as an example, and in a possible example, the special mapping policy component may also match other types of roads, for example, matching roads such as tunnels and roundabouts.

In the similarity measurement component, the similarity parameter calculation is performed only by taking the mapping of each shape point of the road as an example, and in a possible example, the similarity measurement component may also introduce other feature row similarity parameter calculation, for example, may introduce the feature of the intersection node to perform calculation.

The visual component can also add more line colors and patterns to supplement more mapping relations.

Taking matching between road network a and road network B as an example, please refer to fig. 12, which is a schematic flow chart illustrating road network matching according to an exemplary embodiment. As shown in fig. 12, the process of road network matching may be as follows:

s1201, the road network matching model unifies the formats of the original road network data of road network a from service provider a and the original road network data of road network B from service provider B.

S1202, the road network matching model performs semantic feature extraction on the original road network data of the road network A and the original road network data of the road network B after the formats are unified, and semantic features of all the roads in the road network A and semantic features of all the roads in the road network B are obtained.

And S1203, constructing a road network pyramid for the specified type of road in the road network A and the specified type of road in the road network B respectively by the road network matching model according to the extracted semantic features, and merging super roads.

And S1204, screening out a candidate set at the same layer in the road network pyramid corresponding to the road network B by the road network matching model according to the coordinates of each road and aiming at each road in the road network pyramid corresponding to the road network A constructed in the S1203.

And S1205, the road network matching model calculates a similarity parameter between each road and each road in the corresponding candidate set aiming at each road in the road network pyramid corresponding to the road network A constructed in the S1203 according to the geometric characteristics and the topological characteristics of each road.

And S1206, the road network matching model acquires similarity parameters between each pair of roads and strategy conditions corresponding to the specified type of roads according to the S1205, and establishes a mapping relation (which can be one-to-one, one-to-many or many-to-many) between each pair of roads in the two road network pyramids constructed in the S1203.

And S1207, respectively constructing a road network pyramid for the other roads except the roads with the mapping relation established in the S1206 in the road network A, constructing a road network pyramid for the other roads except the roads with the mapping relation established in the S1206 in the road network B, and merging super roads by the road network matching model according to the extracted semantic features.

And S1208, screening out a candidate set at the same layer in the road network pyramid corresponding to the road network B according to the coordinates of each road by the road network matching model aiming at each road in the road network pyramid corresponding to the road network A constructed in the S1207.

And S1209, calculating a similarity parameter between each road and each road in the corresponding candidate set by the road network matching model according to the geometric characteristics and the topological characteristics of each road aiming at each road in the road network pyramid corresponding to the road network A constructed in the S1207.

And S1210, the road network matching model obtains similarity parameters between each pair of roads according to S1209, arranges the similarity parameters in a descending order, and performs topological mapping according to the similarity parameters to establish a mapping relation between each pair of roads in the two road network pyramids established in S1207.

And S1211, the road network matching model obtains the mapping relations respectively established in S1206 and S1210 as a first matching result.

And S1212, the road network matching model acquires road network data of the road network C and road network data of the road network D according to the first matching result.

S1213, the road network matching model respectively constructs a road network pyramid for each road in the road network C, constructs a road network pyramid for each road in the road network D and merges super roads according to the extracted semantic features.

And S1214, screening out a candidate set at the same layer in the road network pyramid corresponding to the road network D by the road network matching model according to the coordinates of each road and aiming at each road in the road network pyramid corresponding to the road network C constructed in the S1213.

And S1215, calculating a similarity parameter between each road and each road in the corresponding candidate set by the road network matching model according to the geometric characteristics and the topological characteristics of each road aiming at each road in the road network pyramid corresponding to the road network C constructed in the S1214.

And S1216, obtaining similarity parameters between each pair of roads by the road network matching model according to the S1215, arranging the similarity parameters in a descending order, and carrying out topological mapping according to the similarity parameters so as to establish the mapping relation between each pair of roads in the two road network pyramids established in the S1213.

S1217, the road network matching model updates the first matching result obtained in S1211 according to the mapping relation obtained in S1216.

And S1218, the road network matching model outputs the updated matching result to a visual interface for display.

Fig. 13 is a block diagram illustrating a structure of a road network matching apparatus according to an exemplary embodiment. The road network matching device can be used in a computer device to execute all or part of the steps in the embodiments shown in fig. 2 or fig. 4. The road network matching device may include:

a first road network data obtaining module 1301, configured to obtain road network data of a first road network and road network data of a second road network;

a first matching module 1302, configured to perform road matching on a road of a specified type in the first road network according to the road network data of the first road network and the road network data of the second road network, so as to obtain a first matching result; the first matching result indicates that the second road network comprises roads matched with each specified type of road in the first road network;

a second matching module 1303, configured to perform road matching on other roads in the first road network according to the road network data of the first road network and the road network data of the second road network, so as to obtain a second matching result; the second matching result indicates that the second road network comprises roads matched with other roads in the first road network; the other roads are all roads except the successfully matched specified type road in the first road network;

a mapping module 1304, configured to obtain a first road network matching result according to the first matching result and the second matching result, where the first road network matching result includes a mapping relationship between each road in the first road network and each road in the second road network.

Optionally, the first matching module 1302 is configured to,

Optionally, when obtaining the candidate road set of the first road, the first matching module 1302 is configured to,

Optionally, when obtaining the similarity parameter between the first road and the second road according to the first type feature of the first road and the first type feature of the second road, the first matching module 1302 is configured to,

Optionally, when the local matching length of each pair of adjacent shape points and the weight of each pair of adjacent shape points are obtained according to the spherical distance between each pair of adjacent shape points, the first matching module 1302 is configured to,

Optionally, before determining that the first road matches the second road, the first matching module 1302 is further configured to,

Optionally, the second matching module 1303 is configured to,

Optionally, the first network data obtaining module 1301 is configured to,

Optionally, the first matching module 1302 is configured to perform road matching on a specified type of road in the ith pyramid of the first road network according to the road network data corresponding to the ith pyramid of the first road network and the road network data corresponding to the ith pyramid of the second road network, so as to obtain a matching result corresponding to the ith pyramid in the first matching result; i is more than or equal to 1 and less than or equal to n, and i is an integer.

Optionally, the second matching module 1303 is configured to perform road matching on other roads in the ith pyramid of the first road network according to the road network data corresponding to the ith pyramid of the first road network and the road network data corresponding to the ith pyramid of the second road network, so as to obtain a matching result corresponding to the ith pyramid in the second matching result; i is more than or equal to 1 and less than or equal to n, and i is an integer.

Optionally, when the road network data of the target road network is acquired according to the n-layer road network pyramid, the first road network data acquisition module 1301 is configured to,

Optionally, the apparatus further comprises:

an original data acquisition module, configured to acquire original road network data of a first road network and original road network data of a second road network before the first road network data acquisition module 1301 acquires the road network data of the first road network and the road network data of the second road network;

the first road network data obtaining module 1301 is configured to obtain road network data of the first road network and road network data of the second road network according to the original road network data of the first road network after format unification and the original road network data of the second road network after format unification.

or,

Optionally, the mapping module 1304 is configured to,

Optionally, the apparatus further comprises:

FIG. 14 is a schematic diagram illustrating a configuration of a computer device, according to an example embodiment. The computer device 1400 includes a Central Processing Unit (CPU)1401, a system memory 1404, and a system bus 1405. The computer device 1400 also includes a basic input/output system (I/O system) 1406, which facilitates transfer of information between various components within the computer, and a mass storage device 1407.

The basic input/output system 1406 includes a display 1408 for displaying information and an input device 1409, such as a mouse, keyboard, etc., for user input of information. Wherein the display 1408 and input device 1409 are both connected to the central processing unit 1401 via an input-output controller 1410 connected to the system bus 1405. Similarly, input-output controller 1410 also provides output to a display screen, a printer, or other type of output device.

The mass storage device 1407 is connected to the central processing unit 1401 through a mass storage controller (not shown) connected to the system bus 1405. The mass storage device 1407 and its associated computer-readable media provide non-volatile storage for the computer device 1400. That is, the mass storage device 1407 may include a computer readable medium (not shown) such as a hard disk or CD-ROM drive.

Without loss of generality, the computer-readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media is not limited to the foregoing. The system memory 1404 and mass storage device 1407 described above may collectively be referred to as memory.

The computer device 1400 may connect to the internet or other network devices through the network interface unit 1411 connected to the system bus 1405.

The memory further includes one or more programs, which are stored in the memory, and the central processing unit 1401 implements all or part of the steps of the method shown in fig. 2 or fig. 4 by executing the one or more programs.

In an exemplary embodiment, a non-transitory computer readable storage medium comprising instructions, such as a memory comprising computer programs (instructions), executable by a processor of a computer device to perform all or part of the steps of the methods shown in the various embodiments of the present application, is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A road network matching method, characterized in that said method comprises:

2. The method according to claim 1, wherein said performing road matching on the specified type of road in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a first matching result comprises:

3. The method of claim 2, wherein the obtaining the similarity parameter between the first road and the second road according to the first type feature of the first road and the first type feature of the second road comprises:

4. The method of claim 2, wherein prior to determining that the first road matches the second road, further comprising:

5. The method according to claim 1, wherein said performing road matching on other roads in the first road network according to the road network data of the first road network and the road network data of the second road network to obtain a second matching result comprises:

6. The method according to any one of claims 1 to 5,

the acquiring of the road network data of the first road network and the road network data of the second road network includes:

7. The method according to claim 6, wherein said obtaining road network data of said target road network according to said n-level road network pyramid comprises:

8. The method of claim 6, wherein said obtaining road network data for a first road network and road network data for a second road network further comprises:

acquiring original road network data of the first road network and original road network data of the second road network;

unifying the format of the original road network data of the first road network and the original road network data of the second road network;

and acquiring the road network data of the first road network and the road network data of the second road network according to the original road network data of the first road network after the formats are unified and the original road network data of the second road network after the formats are unified.

9. The method of claim 8, wherein said unifying the formats of said first road network raw road network data and said second road network raw road network data comprises:

or,

10. The method according to any one of claims 1 to 5, wherein the obtaining a first route matching result according to the first matching result and the second matching result comprises:

11. The method of claim 10, further comprising:

according to the first road network matching result, road network data of a third road network and road network data of a fourth road network are obtained, wherein the third road network comprises roads which are not sufficiently matched in the first road network, and the fourth road network comprises roads which are not sufficiently matched in the second road network; the road which is not fully matched is a road of which the ratio of the matching length to the length of the road is less than a proportional threshold;

acquiring a second road network matching result according to the road network data of the third road network and the road network data of the fourth road network, wherein the second road network matching result comprises a mapping relation between each road in the third road network and each road in the fourth road network;

and updating the first road network matching result according to the second road network matching result to obtain an updated road network matching result.

12. The method of claim 10, further comprising:

displaying a road network matching interface according to the updated road network matching result;

13. A road network matching apparatus, said apparatus comprising:

14. A computer device comprising a processor and a memory, said memory having stored therein at least one instruction, at least one program, set of codes or set of instructions, said at least one instruction, said at least one program, set of codes or set of instructions being loaded and executed by said processor to implement a road network matching method according to any one of claims 1 to 12.

15. A computer-readable storage medium, wherein at least one instruction, at least one program, a set of codes, or a set of instructions is stored, loaded and executed by a processor to implement the road network matching method according to any one of claims 1 to 12.