CN110019591B

CN110019591B - Link topological relation generation method and device, background server and storage medium

Info

Publication number: CN110019591B
Application number: CN201710828720.0A
Authority: CN
Inventors: 王在振; 孙立光; 赵红超
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2017-09-14
Filing date: 2017-09-14
Publication date: 2022-04-08
Anticipated expiration: 2037-09-14
Also published as: CN110019591A

Abstract

The embodiment of the invention provides a link topological relation generation method, a link topological relation generation device, a background server and a storage medium, wherein the method comprises the following steps: determining a target link; performing link search in the first direction of the target link, and determining the link searched in the next step for the searched current link according to the traffic flow information of the current link; the traffic flow information of the current link at least includes: the relative traffic flow of the current link and each link adjacent to the first direction; and when a search cutoff condition is reached, generating a link topological relation of the target link at least according to the link searched in the first direction of the target link. The embodiment of the invention can improve the rationality and accuracy of the generated link topological relation.

Description

Link topological relation generation method and device, background server and storage medium

Technical Field

The invention relates to the technical field of data processing, in particular to a link topological relation generating method and device, a background server and a storage medium.

Background

The link topological relation is a road network topological structure formed by a series of links connected in tandem, wherein one link refers to one road section in the road network; the link topological relation is frequently used in scenes such as road condition calculation, the link topological relation is reasonably and accurately generated, and the link topological relation is very important for application in scenes such as road condition calculation.

Currently, link topological relation generation is mainly realized on the basis of link levels, for example, when a link topological relation of a link is generated, an upstream link and a downstream link with high link levels are respectively selected from an upstream link and a downstream link of the link, and the link topological relation generation of the link is realized. The link topological relation generation mode has the problems that the generation of the link topological relation is realized only according to the link level of the link, and the rationality and the accuracy of the link topological relation generation basis are not high, so that the rationality and the accuracy of the generated link topological relation are low.

Disclosure of Invention

In view of this, embodiments of the present invention provide a link topological relation generating method, apparatus, background server and storage medium, so as to improve the rationality and accuracy of the generated link topological relation.

In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:

a link topological relation generating method comprises the following steps:

determining a target link;

performing link search in the first direction of the target link, and determining the link searched in the next step for the searched current link according to the traffic flow information of the current link; the traffic flow information of the current link at least includes: the relative traffic flow of the current link and each link adjacent to the first direction;

and when a search cutoff condition is reached, generating a link topological relation of the target link at least according to the link searched in the first direction of the target link.

An embodiment of the present invention further provides a link topological relation generating device, including:

a target link determination module for determining a target link;

the first searching module is used for searching links in the first direction of the target link and determining the link searched in the next step for the searched current link according to the traffic flow information of the current link; the traffic flow information of the current link at least includes: the relative traffic flow of the current link and each link adjacent to the first direction;

and the topological relation generating module is used for generating the link topological relation of the target link at least according to the link searched in the first direction of the target link when the search cutoff condition is reached.

An embodiment of the present invention further provides a background server, including: a memory storing an executable program for:

determining a target link;

An embodiment of the present invention further provides a storage medium, where the storage medium stores a program suitable for being executed by a processor, and the program is configured to:

determining a target link;

Based on the technical scheme, the link topological relation generation method provided by the embodiment of the invention comprises the following steps: determining a target link; performing link search in the first direction of the target link, and determining a link searched next according to the traffic information of the current link for the searched current link, wherein the traffic information of the current link at least comprises: the relative traffic flow of the current link and each link adjacent to the first direction; and generating a link topological relation of the target link according to the link searched in the first direction of the target link at least when the search cutoff condition is reached.

According to the embodiment of the invention, each link searched in the first direction of the target link is determined based on the traffic information of the link searched last, so that the link searched in the first direction of the target link can reflect the traffic condition of the target link in the first direction; therefore, the link topological relation in the first direction is generated for the target link at least according to the link searched in the first direction of the target link, the generated link topological relation of the target link has higher rationality and accuracy at least in the first direction, and the rationality and accuracy of the generated link topological relation of the target link are improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a schematic connection diagram of a link;

FIG. 2 is a flowchart of a link topology relationship generation method according to an embodiment of the present invention;

FIG. 3 is another schematic connection diagram of the link;

FIG. 4 is a schematic diagram of a search cutoff;

FIG. 5 is another flowchart of a link topology relationship generation method according to an embodiment of the present invention;

FIG. 6 is a further flowchart of a link topology generating method according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a system architecture for mining traffic information for each link;

FIG. 8 is a flowchart of a method for mining traffic information for each link according to an embodiment of the present invention;

FIG. 9 is a flowchart of a method of determining traffic flow information for each link;

FIG. 10 is a schematic flow chart of mining traffic information of links by the Hadoop server;

fig. 11 is a block diagram of a link topology relationship generation apparatus according to an embodiment of the present invention;

fig. 12 is another structural block diagram of the link topological relation generating apparatus according to the embodiment of the present invention;

fig. 13 is still another structural block diagram of the link topological relation generating apparatus according to the embodiment of the present invention;

fig. 14 is a block diagram of a hardware structure of a background server according to an embodiment of the present invention.

Detailed Description

The inventor of the invention finds that one reason that the link topological relation generated by simply utilizing the link grade of the link is not reasonable and accurate is that: for a link, the traffic flow of each upstream link and each downstream link of the link may be greatly different from the link level of each upstream link and each downstream link of the link, for example, there may be a large traffic flow of the upstream link and/or the downstream link with the link level lower than that of the link.

As an example, as shown in fig. 1, when generating a link topological relation for linkX, since the link level of link1 in the upstream link of linkX is higher than that of link2, according to the prior art, a case may occur in which link1 is added to the link topological relation of linkX, and link2 is excluded; actually, the link flow of linkX mainly comes from link2, so that the link topological relation generated for the linkX cannot reflect the main flow direction of the link flow.

Therefore, the link topological relation of a certain link is generated simply according to the link level of the link, and the link topological relation with the link is possibly ignored, so that the generated link topological relation can only reflect the link level relation of the link, the main flow direction of the link cannot be reflected, and the generated link topological relation has the possibility of low reasonability and accuracy.

Based on this, in the embodiment of the present invention, link topological relation generation is realized by considering the combination of link traffic information, and the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Fig. 2 is a flowchart of a link topological relation generating method according to an embodiment of the present invention, where the link topological relation generating method according to the embodiment of the present invention is applicable to a background server, where the background server may be a service device disposed on a network side, and the background server may be implemented by a single server or a server group including multiple servers;

referring to fig. 2, a link topological relation generating method provided in an embodiment of the present invention may include:

and step S100, determining a target link.

Optionally, in the embodiment of the present invention, a link topological relation may be generated for each link, and the target link may be any link sequentially or randomly selected in the road network.

And step S110, searching links in the first direction of the target link, and determining the links searched next for the searched current link according to the traffic flow information of the current link.

Optionally, the first direction may be an upstream direction or a downstream direction, and when generating a link topological relation for a target link, the embodiment of the present invention may search for an upstream link (link in the upstream direction of the target link) or a downstream link (link in the downstream direction of the target link) of the target link.

It should be noted that the upstream direction of a link is the direction in which the traffic flows to the link, and correspondingly, the upstream link of a link is the link in the direction in which the traffic flows to the link; the downstream direction of a link is the direction in which the traffic flows out of the link, and correspondingly, the downstream link of a link is the link in which the traffic flows out of the link;

for example, as shown in fig. 3, for linkX, a link in the direction in which the vehicle flows toward linkX is an upstream link of linkX, and the upstream link of linkX in fig. 3 includes: link1, link2, and link 3; while the link in the direction of the outflow of the traffic from linkX is the downstream link of linkX, the downstream link of linkX in FIG. 3 includes: link4, link5 and link 6.

Alternatively, the upstream link or the downstream link of the target link may be determined based on link physical connection data in the road network, the link physical connection data recording links connected in sequence in the road network, and the target link may be located in the road network through the link physical connection data, and the link in the upstream direction of the target link or the link in the downstream direction of the target link may be determined.

Optionally, the embodiment of the present invention may perform link search in the first direction of the target link based on an extent search traversal mode, where the extent search traversal is a mode of radially traversing a wider area around the node from the node.

Optionally, the traffic flow information of the current link at least includes: the current link is associated with the traffic flow for each first direction adjacent link.

Optionally, if the first direction is an upstream direction, the first-direction adjacent link of a link may be an upstream adjacent link of the link; if the first direction is a downstream direction, the first direction adjoining link of a link may be, the downstream adjoining link of the link;

for example, as shown in fig. 3, an upstream link adjacent to a link may be regarded as an upstream link adjacent to the link and does not relate to other upstream links which are not adjacent to the link in the direction in which the traffic flows toward the link, and in fig. 3, link3 in the upstream link of linkX is an upstream adjacent link of linkX; a link adjacent downstream may be considered as a downstream link adjacent to the link and does not relate to other downstream links which are not adjacent to the link in the outflow direction of the vehicle flow from the link, as shown in fig. 3, and the links 4 and 5 in the link x downstream link are the downstream adjacent links of the link x;

alternatively, the upstream adjacent link and the downstream adjacent link of the link may be recorded by link adjacency data.

It will be appreciated that if the first direction is an upstream direction, since upstream is an inflow direction, the traffic associated with a link and each upstream adjacent link may be the traffic flowing into the link by each upstream adjacent link of the link; as shown in FIG. 3, the relative traffic flow between linkX and upstream adjacent link3 may be the traffic flow of link3 into linkX;

if the first direction is a downstream direction, then the traffic associated with a link with each downstream adjacent link may be the traffic flowing out of the link to each downstream adjacent link, since downstream is the outflow direction; as in FIG. 3 the relative traffic flows of linkX to the downstream adjacent links 4 and 5 may be the traffic flows of linkX out to link4 and link5, respectively;

accordingly, if the first direction is an upstream direction, the traffic information of the current link may at least include: the traffic flow of each upstream adjacent link of the current link flowing into the current link; if the first direction is a downstream direction, the traffic information of the current link may at least include: the traffic volume of the current link flowing out to each of the downstream adjacent links.

And step S120, when a search cutoff condition is reached, generating a link topological relation of the target link at least according to the link searched in the first direction of the target link.

Optionally, the search cutoff condition of the link in the first direction of the search target link may be that the search range in the first direction reaches the range of the set search distance, for example, the search range in the first direction may be centered on the target link, and the range of the set search distance in the first direction is the search cutoff range in the first direction;

as shown in fig. 4, taking the first direction as the downstream direction and setting the range of the search distance as a circle (in actual cases, setting the range of the search distance as a circle is only optional, and does not exclude the range of the search distance in cases such as a rectangle), the range of the search distance as a radius (the range of the area shown by the solid line in fig. 4) in the first direction may be set as the range of the search cutoff in the first direction with the target link as the center;

optionally, the search cutoff condition in the first direction of the target link may be that the number of searched links in the first direction reaches a set first number; that is, by setting the number of links searched in the first direction as the first number, when the number of links searched in the first direction of the target link reaches the first number, the search is terminated.

When the search cutoff condition is met, the embodiment of the invention can form a road network topological structure consisting of links which are searched in the first direction of the target link and are connected in front and back according to the links searched in the first direction of the target link in the searching process of the links in the first direction of the target link, so as to obtain the link topological relation of the target link.

The link topological relation generation method provided by the embodiment of the invention comprises the following steps: determining a target link; performing link search in the first direction of the target link, and determining a link searched next according to the traffic information of the current link for the searched current link, wherein the traffic information of the current link at least comprises: the relative traffic flow of the current link and each link adjacent to the first direction; and generating a link topological relation of the target link according to the link searched in the first direction of the target link at least when the search cutoff condition is reached.

Optionally, according to the traffic flow information of the current link, determining the link searched next may be: determining a branch of the adjacent link in the first direction for stopping searching from the adjacent links in each first direction of the current link according to the traffic flow information of the current link;

specifically, in the embodiment of the present invention, the occupation ratio of the relevant traffic flows of the first-direction adjacent links of the current link is determined according to the traffic flow information of the current link, the first-direction adjacent links whose occupation ratio of the relevant traffic flows is lower than the predetermined occupation ratio threshold value are determined from the first-direction adjacent links of the current link, and when the determined first-direction adjacent links are not all the first-direction adjacent links of the current link, the search on the branch of the determined first-direction adjacent link is stopped, so that the branch of the first-direction adjacent link whose occupation ratio of the relevant traffic flows is lower than the predetermined occupation ratio threshold value is pruned in the search process; the purpose of the link searched next can be determined in the links adjacent to the link in the first direction, wherein the proportion of the related traffic flow is higher than a preset proportion threshold value;

optionally, the ratio of the relative traffic flow of a first-direction adjacent link may be a ratio of the relative traffic flow of the current link and the first-direction adjacent link to a total relative traffic flow of the current link and all first-direction adjacent links;

for example, the downstream adjoining links of link x are link4 and link5, where the traffic flow rate associated with link4 and link x is 30 (i.e., the traffic flow rate of link x flowing out to link4 is 30), the traffic flow rate associated with link5 and link x is 70 (i.e., the traffic flow rate of link x flowing out to link5 is 70), the total traffic flow rate associated with link x and all downstream adjoining links is 100 (i.e., the total traffic flow rate of link x flowing out to downstream adjoining links is 100), accordingly, the share ratio of the relevant traffic flow rates of link4 is 30/100 ═ 30%, and the share ratio of the relevant traffic flow rates of link5 is 70/100 ═ 70%.

Optionally, the proportion of the relevant traffic flow of each first-direction adjacent link of the current link may be determined according to the relevant traffic flow of the current link and each first-direction adjacent link recorded in the traffic flow information of the current link, for example, the total relevant traffic flow may be determined according to the relevant traffic flow of the current link and each first-direction adjacent link, and further, for each first-direction adjacent link of the current link, the proportion of the relevant traffic flow of the first-direction adjacent link to the total relevant traffic flow is taken as the proportion of the relevant traffic flow of the first-direction adjacent link.

Optionally, in another implementation, the traffic information of the current link may further include a ratio of the relevant traffic of each link adjacent to the current link in the first direction; that is, the traffic information of the current link may include: the ratio of the relative traffic flow of the current link and each link adjacent to the first direction to the relative traffic flow of each link adjacent to the first direction; further, the determination of the ratio of the traffic volumes related to the links adjacent in each first direction of the current link can be realized directly based on the traffic volume information of the current link.

Optionally, fig. 5 shows another flowchart of a link topology relationship generation method provided in an embodiment of the present invention, and referring to fig. 5, the method may include:

and step S200, determining a target link.

Step S210, performing a link search in the first direction of the target link, determining, for the searched current link, an occupancy ratio of the relevant traffic flow of each first-direction adjacent link according to the traffic flow information of the current link, determining whether there is a first-direction adjacent link in each first-direction adjacent link of the current link, where the occupancy ratio of the relevant traffic flow is lower than a predetermined occupancy ratio threshold, if so, performing step S220, and if not, performing step S240.

Step S220, determining whether the first-direction adjacent links with the occupation ratio of the relevant traffic flow lower than the preset occupation ratio threshold are all the first-direction adjacent links of the current link, if not, executing step S230, and if so, executing step S240.

Step S230 stops the search on the branch of the first-direction adjacent link whose ratio of the relevant traffic flow is lower than the predetermined ratio threshold, and determines the link searched next from the first-direction adjacent link whose ratio of the relevant traffic flow is not lower than the predetermined ratio threshold.

It can be seen that if the proportion of the related traffic flow of part of the links adjacent to the first direction in the searched links adjacent to the current link in the first direction is lower than the predetermined proportion threshold, the search may be stopped on the branch of the part of links adjacent to the first direction during the subsequent search, and the link searched next may be determined in the links adjacent to the first direction whose proportion of the related traffic flow is not lower than the predetermined proportion threshold; the link searched in the first direction of the target link is the link through which the traffic mainly passes in the first direction of the target link, and the link searched in the first direction of the target link can strongly reflect the traffic situation in the first direction of the target link.

Optionally, the link determined to be searched next from the first direction adjacent links whose ratio of the relevant traffic flow is not lower than the predetermined ratio threshold may be:

selecting a first direction adjacent link with the highest ratio of the related traffic as a link searched next step from first direction adjacent links with the ratio of the related traffic not lower than a preset ratio threshold (the set number can be one or more, and is set according to actual conditions);

or, if the difference of the occupation ratios of the relevant traffic flows of the first-direction adjacent links is within the set difference range (the set difference range can be determined according to actual conditions, such as 5%) in the first-direction adjacent links of which the occupation ratio of the relevant traffic flows is not lower than the preset occupation ratio threshold, determining the link searched next step according to the link grade of the first-direction adjacent link of which the occupation ratio of the relevant traffic flows is not lower than the preset occupation ratio threshold; generally, a link which has the highest link level and is adjacent to the link in the first direction in the straight line direction of the current link can be selected as a link searched in the next step;

alternatively, all the links adjacent in the first direction having the traffic flow ratio not lower than the predetermined ratio threshold may be directly used as the links searched next.

Step S240, selecting a preset number of first direction adjacent links with the highest ratio of the related traffic flow from all first direction adjacent links of the current link as links searched next; or if the difference of the occupation ratios of the relative traffic flows of the links adjacent to the current link in each first direction is within the set difference range, determining the link searched next step from the links adjacent to the current link in each first direction according to the link level of the links adjacent to the current link in each first direction.

It can be seen that, if the ratio of the relevant traffic flow of all the links adjacent to the first direction is not lower than the predetermined ratio threshold, or the ratio of the relevant traffic flow of all the links adjacent to the first direction is lower than the predetermined ratio threshold, step S240 may be executed to determine the link searched next. Alternatively, step S240 may refer to the description of the corresponding part of step S230.

And S250, when a search cutoff condition is reached, generating a link topological relation of the target link at least according to the link searched in the first direction of the target link.

For convenience of understanding, the determination example of the link found in the next step by the link5 and the link6 is described by taking the first direction as the downstream direction and the link4 as the downstream adjacent link to the link x after the link x is found in the above manner.

In the first case, the predetermined occupancy threshold is set to 20% (for different road grades and different actual demands, the value of the predetermined occupancy threshold may be different, and is only exemplified here), if the occupancy of the relevant traffic flow of link4 is 10%, the occupancy of the relevant traffic flow of link5 is 44%, and the occupancy of the relevant traffic flow of link6 is 46%, it may be determined that there is a downstream adjacent link4 with the occupancy of the relevant traffic flow lower than 20% in each downstream adjacent link of link x, and the link4 is not all the downstream adjacent links of link x, and then the search in the branch direction of the downstream adjacent link4 may be stopped, that is, the search is not performed for the downstream links belonging to link 4; so that the link searched next can be determined in the link5 and the link 6;

further, if the first direction adjacent links with the highest ratio of the relative traffic flow and the first set number of the first direction adjacent links with the highest ratio of the relative traffic flow are selected as the links searched next, the link6 with the highest ratio of the relative traffic flow can be selected from the links 5 and the links 6 as the links searched next; if a plurality of links searched next are allowed, the links 5 and the links 6 can be respectively used as the links searched next;

if the link searched next is determined according to the link level, the link with the highest link level can be selected from the links 5 and 6 as the link searched next when the difference between the ratios of the relative traffic volumes of the link5 and the link6 is determined to be within the set difference range.

In the second case, the predetermined occupancy threshold value is set to 20%, and if the occupancy of the relevant traffic flow of link4 is 30%, the occupancy of the relevant traffic flow of link5 is 37%, and the occupancy of the relevant traffic flow of link6 is 33%, it is determined that there is no downstream adjacent link of which the occupancy of the relevant traffic flow is lower than 20% among the downstream adjacent links of linkX; the link searched next step may be determined from the link4, the link5 and the link6 according to the link grades of the link4, the link5 and the link6, or the links with the highest ratio of the relative traffic volumes may be selected from the link4, the link5 and the link6 as the links searched next step.

In the third case, if the number of the downstream adjacent links of linkX is large and the traffic flow is uniform so that the occupation ratios of the relevant traffic flows of the downstream adjacent links of linkX are all lower than the predetermined occupation ratio threshold, such a case can be handled with reference to the second case.

It should be noted that the mode of determining the link searched next according to the traffic flow information of the current link shown in fig. 5 is only optional; according to the embodiment of the invention, the links with the highest traffic flow and the preset number are selected from the links adjacent to the current link in the first direction (for example, the two links adjacent to the first direction with the highest traffic flow are selected) and used as the links searched in the next step, and the comparison between the occupation ratio of the relative traffic flows of the links adjacent to the first direction and the preset occupation ratio threshold value is not necessarily required; as can be seen, the proportion of the traffic flow related to the links adjacent in the first direction of the current link does not necessarily need to be included in the traffic flow information of the current link.

Optionally, in the process of searching for a link in the first direction of the target link, as an optional implementation, the embodiment of the present invention may start with the target link, use the target link as a first current link, and determine a link to be searched next (at least one link to be searched next) from links adjacent to the target link in the first direction according to the traffic information of the target link; determining links searched for the next step as current links respectively, determining the links searched for the next step again according to the traffic flow information of the current links, and repeating the steps until the search cutoff condition is reached;

optionally, fig. 6 shows a further flowchart of a link topology relationship generation method provided in an embodiment of the present invention, and referring to fig. 6, the method may include:

and step S300, determining a target link.

And step S310, taking the target link as the current link.

Alternatively, the target link may be the first current link in the embodiment of the present invention.

And S320, determining the link searched next according to the traffic flow information of the current link.

Optionally, a mode of determining a link to be searched next according to the traffic flow information of the current link may be as shown in fig. 5;

optionally, the links with the highest traffic flow in the previous set number may be selected from the links adjacent to the current link in the first direction directly according to the traffic flow information of the current link, and the links with the highest traffic flow may be used as the links searched in the next step.

Step S330, determining whether a search cutoff condition is reached, if not, performing step S340, and if so, performing step S350.

And step S340, taking the link searched in the next step as the current link, and returning to the step S320.

And S350, generating a link topological relation of the target link at least according to the link searched in the first direction of the target link.

The method and the device can start from the target link, take the target link as the current link, and determine the next searched link from the links adjacent to the current link in the first direction based on the traffic flow information of the current link; and then taking the link searched in the first step as the current link, and circulating the link so as to selectively search the link in the first direction of the target link, ensure the subsequent link topological relation generated based on the link searched in the first direction of the target link, reflect the traffic flow condition in the first direction of the target link, and improve the rationality and accuracy of the generated link topological relation.

Optionally, in another implementation, the embodiment of the present invention may also use, starting from each first-direction adjacent link of the target link, each first-direction adjacent link of the target link as a first current link, and determine a link searched next according to the traffic information of the current link, so as to loop until the search cutoff condition is reached.

Optionally, the traffic information of the current link may further include: the current link and the traffic flow of the links adjacent to each second direction, wherein the second direction is related to the first direction; that is, the traffic information of the current link may include: the related traffic flow of the current link and each link adjacent in the first direction, and the related traffic flow of the current link and each link adjacent in the second direction;

if the first direction is an upstream direction, the second direction is a downstream direction, and correspondingly, the traffic information of the current link at least comprises the traffic flowing into each upstream adjacent link of the current link and also comprises the traffic flowing out from the current link to each downstream adjacent link; conversely, if the first direction is the downstream direction, the second direction is the upstream direction, and the content indicated by the traffic information of the current link is the same as this.

Further, the traffic information of the current link may further include: the ratio of the current link to the traffic flow rate associated with each link adjacent in the second direction; that is, the traffic information of the current link may include: the traffic flow rates of the current link and the links adjacent in each first direction, the ratio of the traffic flow rates of the current link and the links adjacent in each second direction, and the ratio of the traffic flow rates of the links adjacent in each second direction.

Optionally, based on the principle of the flow shown in fig. 2, the embodiment of the present invention may further perform link search in the second direction of the target link, and determine links searched in the next step in the second direction according to the traffic information of the links currently searched in the second direction, so as to determine the links searched in the second direction of the target link when the search cutoff condition is reached (refer to the description of the search cutoff condition in the flow part of fig. 2); the traffic information of the link currently searched in the second direction may at least include: the traffic volume associated with the link adjacent to each second direction;

and then generating a link topological relation of the target link according to the link searched in the first direction of the target link and the link searched in the second direction of the target link.

Optionally, the process of searching for the link in the second direction of the target link and determining the link searched in the second direction of the target link may be the same as the above-mentioned process of searching for the link in the first direction of the target link and determining the link searched in the first direction of the target link.

Optionally, in the embodiment of the present invention, the topological branch of the target link may be determined according to the link searched in the first direction of the target link and the link searched in the second direction of the target link, the topological branch of the target link is subjected to level marking according to the distance interval, the level where each topological branch of the target link is located is marked (i.e., the level index of each topological branch is obtained), and the link topological relation of the target link is output;

the step of marking the topological branches of the target link according to the hierarchy of the distance interval can be considered as that the link of each topological branch of the target link is judged according to the fixed hierarchical length; for example, the length of the distance interval is set to 100 meters, and if a Link in the topological branch of the target Link is 620 meters away from the target Link, the Link belongs to the 6 th interval, i.e., the 6 th layer.

It should be noted that, based on the principle of the flow shown in fig. 2, the link searched in the first direction of the target link and the link searched in the second direction of the target link are determined, so that generating the link topological relation of the target link is only an optional implementation;

according to the method and the device for generating the link topological relation of the target link, the link searched in the first direction of the target link is not excluded, and the link topological relation of the target link is generated, for example, the link searched in the first direction of the target link and the link determined by the link level of the link in the second direction are used for generating the link topological relation of the target link, so that the generated link topological relation of the target link has higher rationality and accuracy in the first direction of the target link, and compared with the existing method for generating the link topological relation, the rationality and accuracy of the generated link topological relation can be improved.

Optionally, the traffic flow information of the current link may be called from the traffic flow information of each link, and in order to implement the link topological relation generation method provided in the embodiment of the present invention, the embodiment of the present invention may first implement mining of the traffic flow information of each link; taking the example that the link traffic information includes the link traffic related to the links adjacent to each first direction and the link traffic related to the links adjacent to each second direction as an example, the mining of the link traffic information is described below;

if the traffic information of the link includes the traffic of the link adjacent to each first direction or the traffic of the link adjacent to each second direction, the mining scheme implementation of the traffic information of one direction of the link described below may be selected.

As an alternative implementation, the mining of the traffic information of each link may be implemented based on the system architecture shown in fig. 7, and as shown in fig. 7, the system architecture for implementing the mining of the traffic information of each link may include: a mining server 10, a plurality of terminals 20, a map navigation server 30;

the mining server 10 may be a service device arranged on a network side and used for mining traffic information of each link, and the mining server 10 may be implemented by a single server or a server group consisting of a plurality of servers; as an optional form of the mining server, the mining server can be implemented by a Hadoop (a distributed system infrastructure) cluster;

the terminal 20 may be an electronic device used by a user, such as a mobile phone, a tablet computer, a traveling computer, a vehicle data recorder, and a vehicle-mounted positioning device; the terminal can be arranged in a motor vehicle (the terminal can be built in the motor vehicle, or the terminal can be placed in the motor vehicle by a user), the terminal can position the position of the motor vehicle by positioning means such as a GPS (global positioning system) and the like in the process of driving the motor vehicle by the user, the driving track of the motor vehicle is determined by combining a map, and the driving track records links passed by the motor vehicle in the driving process;

the map navigation server 30 may be a service device that is provided on the network side and provides a map navigation service, and when a user requests the map navigation service in the process of driving a motor vehicle, the map navigation server may provide the map navigation service for the user, determine a driving track of the motor vehicle by locating the position of the motor vehicle at each time in the driving process of the motor vehicle and combining with a map, and record link that the motor vehicle passes through in the driving process by the driving track.

In the embodiment of the invention, each terminal and the map navigation server can upload the determined driving tracks of the motor vehicle to the mining server, so that the mining server can obtain massive driving tracks, and the traffic flow of each link is mined according to the massive driving tracks.

Optionally, based on the system architecture shown in fig. 7, fig. 8 shows a flow of a method for mining traffic flow information of each link according to an embodiment of the present invention, where the method for mining traffic flow information of each link is applicable to a mining server;

optionally, the mining server may be the same as the background server that implements the link topological relation generation in the embodiment of the present invention (i.e., the mining of the traffic flow information of each link and the link topological relation generation may be implemented on the background server); optionally, the mining server may also be different from the backend server that implements the link topological relation generation according to the embodiment of the present invention (that is, the backend server may implement the link topological relation generation according to the traffic flow information of each link determined by the mining server);

referring to fig. 8, a method for mining traffic flow of each link according to an embodiment of the present invention may include:

and S400, acquiring a plurality of driving tracks.

Optionally, one driving track may record links passed by the motor vehicle in one driving process, and the plurality of driving tracks may be obtained by obtaining the driving tracks uploaded by the plurality of terminals and the navigation server shown in fig. 8 within a certain time (e.g., within a certain number of days).

Obviously, it is only an alternative way to obtain a plurality of driving tracks through the driving tracks uploaded by the plurality of terminals and the navigation server shown in fig. 8; the embodiment of the invention can also only collect the driving tracks uploaded by a plurality of terminals or the driving tracks uploaded by the navigation server, thereby realizing the acquisition of a plurality of driving tracks.

S410, respectively extracting link pairs corresponding to each driving track to obtain the link pairs corresponding to the driving tracks; one driving track corresponds to at least one link pair, and one link pair comprises two adjacent links in one driving track.

Optionally, for a certain trajectory, in the embodiment of the present invention, two links adjacent to each other in the trajectory may be respectively formed into a link pair, and the link pair corresponding to the trajectory is extracted, where the number of the link pairs corresponding to the trajectory is at least one, and may be determined according to the number of the links through which the trajectory passes;

for example, links through which a certain driving track passes in sequence are Link1, Link2, Link3 and Link 4; then it can be determined that the two links adjacent to each other in the trajectory are: link1 and Link2, Link2 and Link3, Link3 and Link 4; therefore, two adjacent links in the driving track are respectively formed into a link pair, and the link pair corresponding to the driving track is determined as follows: three pairs of < Link1, Link2> < Link2, Link3> < Link3, and Link4 >.

After the link pairs corresponding to each of the plurality of trajectories are extracted, the link pairs corresponding to each of the trajectories can be collected to obtain the link pairs corresponding to the plurality of trajectories, that is, the link pairs corresponding to the plurality of trajectories can be formed by collecting the link pairs corresponding to each of the trajectories.

And step S420, merging and counting the same link pairs in the link pairs corresponding to the plurality of driving tracks, and determining the count value of each link pair to obtain the traffic flow passing through each link pair.

Merging and counting the same link pairs comprises the process of merging the same link pairs and accumulating and counting the same link pairs; the embodiment of the invention can merge the same link pairs in the link pairs corresponding to the plurality of driving tracks, and the number of each link pair in the plurality of driving tracks is used as the count value of each merged link pair, so that the merging and counting of the same link pairs are realized, and the count value of each link pair is determined;

optionally, merging the same link pair may be considered as that only one link pair in the same link pair is reserved to obtain a merged link pair, and the merged link pair does not have the same link pair; the accumulated counting of the same link pairs can be considered as that the number of the same link pairs in the plurality of driving tracks is used as the count value of each merged link pair; since the link pair is extracted from the trajectories, it is understood that the count value of one link pair may indicate the number of trajectories including the link pair in the plurality of trajectories.

Optionally, as an optional implementation, after the link pairs corresponding to the plurality of driving trajectories are obtained, if one link pair has the same link pair, the link pair and the same link pair may be merged into one (that is, the link pair and one link pair in the same link pair are reserved), and the number of the link pairs in the plurality of driving trajectories is determined at the same time, so as to obtain a count value of the link pair; for example, after the Link pairs corresponding to the plurality of driving trajectories are obtained, if there are 5 same Link pairs of < Link1, Link2>, the 5 Link pairs of < Link1, Link2> may be merged into one Link pair of < Link1, Link2>, and the Link pair of < Link1, Link2> is given a count value of 5;

if a link pair does not have the same link pair, the count value of the link pair may be determined to be 1 (i.e., only one of the trajectories may include the link pair).

After the count value of each link is determined, the count value can be used as the traffic flow of each link pair in the road network, and the traffic flow of each link pair can be recorded and obtained.

For example, the count value of the Link pair < Link1, Link2> is 100, that is, 100 of the obtained plurality of trajectories pass through the Link pair < Link1, Link2>, it is determined that the traffic volume of the Link pair < Link1, Link2> in the road network is 100, and the traffic volume of the Link pair < Link1, Link2> is recorded as 100.

Step S430, determining traffic flow information of each link according to the traffic flow passing through each link pair; the traffic information of one link includes at least: the traffic volume flowing into each upstream adjacent link of the link, and the traffic volume flowing out from the link to each adjacent downstream link.

In an embodiment of the present invention, the traffic information of a link may at least include: the traffic flow into each upstream adjacent link of the link (the expression of the traffic flow related to one link and each first direction adjacent link when the first direction is the upstream direction), and the traffic flow out from the link to each adjacent downstream link (the expression of the traffic flow related to one link and each first direction adjacent link when the first direction is the downstream direction).

According to the method for mining the traffic flow information of each link, provided by the embodiment of the invention, the link pairs corresponding to a plurality of driving tracks can be obtained by obtaining the plurality of driving tracks and extracting the link pairs corresponding to each driving track; therefore, the link pairs corresponding to the plurality of driving tracks are merged and counted, the count value of each link pair is determined, and the traffic flow passing through each link pair is determined; further, the traffic volume information of each link can be determined by determining, for each link, the traffic volume flowing into each upstream adjacent link of the link and the traffic volume flowing out from the link to each adjacent downstream link, based on the traffic volumes passing through each link pair. The embodiment of the invention is based on massive driving tracks, firstly excavates the traffic flow of a link pair formed by adjacent links, and then determines the traffic flow information of each link according to the traffic flow of the link pair, thereby realizing the excavation of the traffic flow information of each link, and realizing the accurate excavation of the traffic flow information of each link in a simpler and more convenient way.

Optionally, in the embodiment of the present invention, the traffic flow of each link may be determined based on the traffic flow of each link pair and the adjacency relation data of the links; fig. 9 shows a flow of a method for determining traffic flow information of each link according to a traffic flow passing through each link pair, where the method is applicable to a mining server, and referring to fig. 9, the method may include:

step S500 determines each upstream adjacent link and each downstream adjacent link of each link based on the adjacent relation data of the links.

Optionally, the adjacency data of the links may record the adjacency links of each link, and the adjacency links of a link may include: an upstream link and a downstream link to which the link is adjacent; the adjacency data of links may be determined based on the physical connection relationships of links in the road network.

Optionally, taking an example that an upstream Link adjacent to a Link has 1 a, and a downstream Link has 2B and C, the adjacent relationship of the Link may be considered as follows: upstream Link A, downstream Link B and C; namely, the Link has one upstream adjacent Link, namely Link A, and two downstream adjacent links, namely Link B and C; the adjacency relation of each link may be stored in a certain format and recorded in the adjacency relation data of the link.

In step S510, for any link, the traffic flow rate of the link into which each upstream adjacent link of the link flows and the traffic flow rate of the link out of which each downstream adjacent link flows are determined based on the traffic flow rate passing through each link pair, and the traffic flow rate information of the link is obtained.

Optionally, in an optional implementation, for each link, after determining each upstream adjacent link and each downstream adjacent link of the link, for a first upstream adjacent link of the link (the first upstream adjacent link may be considered as any upstream adjacent link of the link), a traffic flow from the first upstream adjacent link to a link pair corresponding to the link may be determined according to a traffic flow passing through each link pair, so as to obtain a traffic flow flowing into the first upstream adjacent link of the link;

determining the traffic flow rate of the link pair corresponding to the link to a first downstream adjacent link of the link (the first downstream adjacent link may be considered as any one of the downstream adjacent links of the link), and obtaining the traffic flow rate of the first downstream adjacent link flowing out from the link;

the traffic flow rate of the link is determined by combining the traffic flow rate flowing into the first upstream adjacent link of the link and the traffic flow rate flowing out from the link to the first downstream adjacent link. Optionally, if the traffic information of the link includes: the traffic flow associated with a link adjacent to each first direction may be determined based on the form of the first direction from the traffic flow flowing into the first upstream adjacent link of the link or the traffic flow flowing out from the link to the first downstream adjacent link.

As an alternative example, for determining the traffic flow information for linkX, the traffic flow of the Link pair < Link3, linkX > from Link3 to linkX can be determined for the upstream adjacent Link3 of linkX (it can be seen that Link3 is the first upstream adjacent Link of linkX), based on the traffic flow passing through each Link pair, and the traffic flow of Link3 flowing into linkX can be obtained, and each upstream adjacent Link of linkX can be processed to obtain the traffic flow of each upstream adjacent Link flowing into linkX;

for the Link4 adjacent to the downstream of Link X (it can be seen that Link4 is the first downstream adjacent Link of Link X), the traffic flow of the Link pair < Link X, Link4> from Link X to Link4 can be determined according to the traffic flow passing through each Link pair, and the traffic flow of the Link X flowing out to Link4 can be obtained, so that each downstream adjacent Link of Link X can be processed to obtain the traffic flow of the Link X flowing out to each downstream adjacent Link;

further, the traffic flow rate of linkX is obtained by combining the traffic flow rate of the link flowing into the link adjacent to the upstream of the linkX and the traffic flow rate of the link flowing out of the link adjacent to the downstream of the linkX.

Further, the traffic information of a link may further include: the proportion of the traffic flow rate associated with each upstream adjacent link (i.e., the proportion of the traffic flow rate flowing into each upstream adjacent link of the link to the total traffic flow rate flowing into the link), and the proportion of the traffic flow rate associated with each downstream adjacent link (i.e., the proportion of the traffic flow rate flowing out from the link to each downstream adjacent link to the total traffic flow rate flowing out from the link);

in the embodiment of the present invention, for a link, the ratio of the traffic flow rate of each upstream adjacent link flowing into the link to the traffic flow rate related to each upstream adjacent link may be regarded as the traffic flow rate confluence information of the link;

the ratio of the traffic volume flowing out from the link to each adjacent downstream link to the traffic volume related to each adjacent downstream link may be regarded as the traffic volume split information of the link;

optionally, the link traffic flow information formed by combining the link traffic flow merging information and the link traffic flow splitting information is a preferred form of the link traffic flow information.

Obviously, the traffic information of one link does not necessarily include the proportion of the relevant traffic of each upstream adjacent link and the proportion of the relevant traffic of each downstream adjacent link; the traffic information of a link may include only the traffic flowing into each upstream adjacent link of the link and the traffic flowing out from the link to each adjacent downstream link.

Optionally, the traffic flow information of a link may be recorded in a predetermined format to form a traffic flow record of the link, and the traffic flow record of a link may include: an incoming traffic flow record for the link, and an outgoing traffic flow record;

optionally, one record in the inflow vehicle flow records of a link may correspond to the vehicle flow of an upstream adjacent link flowing into the link, and the first bit data of one record corresponds to the serial number of an upstream adjacent link of the link, and the second bit data corresponds to the vehicle flow of the upstream adjacent link flowing into the link;

for example, when determining the traffic flow record for linkX, taking the link adjacent to linkX as link3 as an example, the link pair from link3 to linkX in the link pair is < link3, linkX >, and if the traffic flow of < link3, linkX > is 100, it may be determined that the traffic flow flowing into the link adjacent to upstream 3 of linkX is 100, that is, the inflow traffic flow of linkX is 100; accordingly, the inflow traffic record that can form linkX is 3, 100;

optionally, one of the outgoing traffic volume records of a link may correspond to the traffic volume of the link outgoing to a downstream adjacent link, and the first bit data of one record corresponds to the serial number of a downstream adjacent link of the link, and the second bit data corresponds to the traffic volume of the link outgoing to the downstream adjacent link;

taking the case where the downstream adjoining link of linkX is link4 and link5, the traffic flow of linkX out to the downstream adjoining link4 and the traffic flow of linkX out to the downstream adjoining link5 are determined, respectively, the traffic flow of linkX out to the downstream adjoining link4 is determined by determining the traffic flow of the link pair < linkX, link4> from linkX to link4 in the link pair as 30, and the traffic flow of the link pair < linkX, link5> from linkX to link5 in the link pair as 70, the traffic flow of the link X out to the downstream adjoining link5 is determined as 70, respectively, the outgoing traffic flow of linkX is recorded as 4, 30; 5,70.

Optionally, each record of the inflow traffic volume records of one link may further set third-bit data to record the proportion of the relevant traffic volume of the corresponding upstream adjacent link; in combination with the above, the third-bit data of one of the incoming traffic records of one link may correspondingly record the proportion of the relevant traffic of an upstream adjacent link; if the total inbound traffic flow for linkX is 100, then the inbound traffic flow for the upstream adjacent link3 is recorded as 3, 100, 100%;

optionally, each record of the outgoing traffic volume record of one link may further set third-bit data to record the proportion of the relevant traffic volume of the corresponding downstream adjacent link; in combination with the above, the third-bit data of one of the outgoing traffic records of one link can correspondingly record the occupation ratio of the related traffic of a downstream adjacent link; if the total outflowing vehicle flow rate of linkX is 100, then the inflowing vehicle flow rate of the downstream adjacent link4 is recorded as 4, 30, 30%; the incoming linkX traffic flow for the downstream adjacent link5 was recorded as 5, 70, 70%.

Obviously, the above-described manner of recording the traffic information of the link in the predetermined format is only optional, and the embodiment of the present invention may also record the traffic information of the link by setting the table, and does not necessarily have to record the traffic information according to the above-described format.

The traffic information of a link described above includes the traffic flowing into each upstream adjacent link of the link and the traffic flowing out from the link to each adjacent downstream link; while this is only an alternative form of the traffic information of one link, the embodiment of the present invention may also set that the traffic information of one link includes the traffic of the link related to each first-direction adjacent link;

the first direction may be an upstream direction or a downstream direction, and taking the first direction as the upstream direction as an example, the traffic information of one link may include the traffic flowing into each upstream adjacent link of the link; taking the first direction as a downstream direction as an example, the traffic information of one link can flow out of the link to the traffic of each adjacent downstream link;

optionally, in a case that the traffic information of one link is set to include the traffic flows related to the link and links adjacent to each first direction, in the method content for mining the traffic information of each link, only the branch flow related to the first direction may be selected and executed; if the first direction is taken as an upstream direction as an example, in the content of the method for mining traffic information of one link, a branch flow for mining traffic flowing into each upstream adjacent link of the link may be performed, and specific content may be described with reference to the corresponding parts above;

for example, if the first direction is the downstream direction, in the content of the method for mining traffic information of one link, a branch flow for mining traffic flowing from the link to each adjacent downstream link may be selected, and specific content may be described with reference to the corresponding parts above;

further, in the embodiment of the present invention, in addition to setting that the traffic information of one link includes the traffic related to the link and the links adjacent in each first direction, the occupation ratio of the traffic related to the links adjacent in each first direction may also be set; if the first direction is an upstream direction, the traffic information of a link may include: the ratio of the traffic flow rate of each upstream adjacent link flowing into the link to the traffic flow rate associated with each upstream adjacent link; if the first direction is a downstream direction, the traffic information for a link may include: the ratio of the traffic flow rate flowing out from the link to each adjacent downstream link to the traffic flow rate associated with each adjacent downstream link.

Alternatively, further, in a case where the traffic information of one link is set to include the traffic associated with the link and each of the first-direction adjoining links, the traffic information of one link may be recorded in a predetermined format.

Optionally, further, if the traffic information of a link is set to further include the traffic of the link relative to each link adjacent in the second direction, the traffic information of a link may be regarded as including the traffic of each link adjacent upstream of the link and the traffic of each link adjacent downstream of the link; the first direction is opposite to the second direction.

As an optional implementation, the above-described scheme for mining the traffic flow of each link may be implemented using a Hadoop server of a distributed cluster, as shown in fig. 10, the implementation of the traffic flow mining of each link by the Hadoop server may be divided into a map stage and a reduce stage, where the map stage mainly processes data input to the Hadoop server through a map function to obtain an intermediate result, and distributes the intermediate result to different reduces through a Hadoop framework; the reduce stage is mainly to process the intermediate result through a reduce function to obtain a final result;

as shown in fig. 10, the embodiment of the present invention may take the collected data of link adjacency relation between a plurality of driving tracks and a road network as input; in the map stage, a link pair through which each driving track passes can be output based on a plurality of driving tracks, and adjacent links are output based on link adjacent relation data; in the reduce phase, the same link pairs are merged and counted to obtain the count value of each link pair, and the traffic information of each link (for example, the incoming traffic of each upstream adjacent link and the outgoing traffic of each downstream adjacent link) is output.

According to the link topological relation generation method provided by the embodiment of the invention, the link is searched in the first direction of the target link by excavating the vehicle flow information of each link, and when the link topological relation is generated on the target link, the searched link in the next step can be determined according to the vehicle flow information of the current link excavated in advance, so that when the search cutoff condition is reached, the link topological relation of the target link is generated at least according to the link searched in the first direction of the target link; the link topological relation of the target link generated by the embodiment of the invention has higher rationality and accuracy at least in the first direction, and the rationality and accuracy of the generated link topological relation of the target link are improved.

Further, link searching can be carried out in the second direction of the target link, and the link searched in the next step is determined according to the searched traffic flow information of the current link, so that when the search cutoff condition is met, the link searched in the second direction of the target link is determined; and then the link topological relation of the target link can be generated by combining the link searched in the first direction of the target link and the link searched in the second direction of the target link, so that the rationality and the accuracy of the generated link topological relation of the target link are further improved.

The link topological relation generating device provided by the embodiment of the invention is introduced below, and the link topological relation generating device described below can be regarded as a program module which is required to be set by a background server to realize the link topological relation generating method provided by the embodiment of the invention; the contents of the link topology generation apparatus described below may be referred to in correspondence with the contents of the link topology generation method described above.

Fig. 11 is a block diagram of a link topological relation generating apparatus according to an embodiment of the present invention, where the link topological relation generating apparatus is applicable to a backend server, and referring to fig. 11, the link topological relation generating apparatus may include:

a target link determination module 100 for determining a target link;

the first searching module 200 is configured to perform link searching in the first direction of the target link, and determine, for a searched current link, a link searched next according to traffic flow information of the current link; the traffic flow information of the current link at least includes: the relative traffic flow of the current link and each link adjacent to the first direction;

and the topological relation generating module 300 is configured to generate a link topological relation of the target link at least according to the link searched in the first direction of the target link when the search cutoff condition is reached.

Optionally, the first searching module 200 is configured to determine a link to be searched next according to the traffic flow information of the current link, and specifically includes:

determining the occupation ratio of the related traffic flow of the adjacent links in each first direction according to the traffic flow information of the current link;

and if the proportion of the relative traffic of part of the links adjacent to the first direction is lower than the preset proportion threshold value, stopping searching on branches of the part of the links adjacent to the first direction, and determining the links searched next in the links adjacent to the first direction, wherein the proportion of the relative traffic is not lower than the preset proportion threshold value.

Optionally, the first searching module 200 is configured to determine a link searched next in a link adjacent in the first direction where the proportion of the relevant traffic flow is not lower than the predetermined proportion threshold, and specifically includes:

selecting a first direction adjacent links with the highest ratio of the related traffic as links searched next from the first direction adjacent links with the ratio of the related traffic not lower than the preset ratio threshold;

or if the proportion of the related traffic flow is not lower than the preset proportion threshold value, the difference value of the proportion of the related traffic flow of the first-direction adjacent links is in the set difference range, and the link searched in the next step is determined according to the link grade of the first-direction adjacent link, the proportion of the related traffic flow of which is not lower than the preset proportion threshold value;

or, the links adjacent in the first direction with the ratio of the relevant traffic flow not lower than the predetermined ratio threshold value can be directly used as the links searched next.

Optionally, if the ratio of the relevant traffic flows of all links adjacent to the first direction is not lower than the predetermined ratio threshold, or the ratio of the relevant traffic flows of all links adjacent to the first direction is lower than the predetermined ratio threshold, the first search module 200 is configured to determine a link searched in the next step according to the traffic flow information of the current link, and may further include:

selecting a preset number of first direction adjacent links with the highest ratio of the relative traffic flow from all first direction adjacent links of the current link as links searched next;

or if the difference of the occupation ratios of the relative traffic flows of the links adjacent to the current link in each first direction is within the set difference range, determining the link searched next step from the links adjacent to the current link in each first direction according to the link level of the links adjacent to the current link in each first direction.

Optionally, the traffic flow information of the current link may further include: the proportion of the relative traffic flow of the links adjacent to the current link in each first direction;

correspondingly, the first searching module 200 is configured to determine, according to the traffic flow information of the current link, a proportion of the relevant traffic flow of the links adjacent in each first direction, and may specifically include:

and determining the proportion of the relative traffic flow of the adjacent links in each first direction of the current link, which is recorded by the traffic flow information of the current link.

Optionally, fig. 12 is a block diagram showing another structure of the link topology relationship generation apparatus according to the embodiment of the present invention, and with reference to fig. 11 and 12, the apparatus may further include:

the second searching module 400 is configured to perform link search in a second direction of the target link, and determine links searched in the next step in the second direction according to traffic flow information of links currently searched in the second direction; the first direction is opposite to the second direction, and the traffic flow information of the link currently searched in the second direction at least comprises: the traffic volume associated with the link adjacent to each second direction;

correspondingly, the topological relation generating module 300 is configured to, when a search cutoff condition is reached, generate a link topological relation of a target link at least according to a link searched in the first direction of the target link, and may specifically include:

and when the search cutoff condition is reached, generating a link topological relation of the target link according to the link searched in the first direction of the target link and the link searched in the second direction of the target link.

Optionally, the topological relation generating module 300 is configured to generate a link topological relation of the target link according to the link searched in the first direction of the target link and the link searched in the second direction of the target link, and specifically includes:

determining a topological branch of the target link according to the link searched in the first direction of the target link and the link searched in the second direction of the target link;

and carrying out hierarchy marking on the topological branches of the target link according to the distance interval, marking the hierarchy of each topological branch of the target link, and outputting the link topological relation of the target link.

Optionally, the traffic flow information of the current link may further include: the current link and the traffic flow of the links adjacent to each second direction, wherein the second direction is related to the first direction;

wherein, if the first direction is a downstream direction, the related traffic flow of the current link and each link adjacent to the first direction includes: the traffic flow of the current link flowing out to each downstream adjacent link;

if the first direction is an upstream direction, the traffic flow rates related to the current link and each link adjacent to the first direction include: the traffic volume of each upstream adjacent link of the current link flows into the current link.

Optionally, fig. 13 shows a further structural block diagram of the link topological relation generating apparatus provided in the embodiment of the present invention, and as shown in fig. 12 and 13, the apparatus may further include:

the mining module 500 is used for acquiring a plurality of driving tracks; respectively extracting link pairs corresponding to each driving track to obtain the link pairs corresponding to the plurality of driving tracks; one driving track corresponds to at least one link pair, and one link pair comprises two adjacent links in one driving track; merging and counting the link pairs corresponding to the plurality of driving tracks, and determining the count value of each link pair to obtain the traffic flow passing through each link pair; determining traffic flow information of each link according to the traffic flow passing through each link pair; the traffic information of one link includes at least: the traffic volume flowing into each upstream adjacent link of the link, and the traffic volume flowing out from the link to each adjacent downstream link.

Optionally, the mining module 500 is configured to merge and count the link pairs corresponding to the multiple driving trajectories, where the same link pairs are counted, and determine a count value of each link pair, and specifically includes:

merging the same link pair in the link pairs corresponding to the plurality of driving tracks to reserve one link pair in the same link pair to obtain the merged link pair; and taking the number of each link pair in the plurality of driving tracks as the count value of each link pair after merging.

Optionally, the mining module 500 is configured to determine traffic flow information of each link according to the traffic flow passing through each link pair, and specifically includes:

determining each upstream adjacent link and each downstream adjacent link of each link according to the adjacent relation data of the links;

for any link, the traffic volume information of the link is obtained by determining the traffic volume flowing into the link by each upstream adjacent link of the link and the traffic volume flowing out of the link to each downstream adjacent link, based on the traffic volume passing through each link pair.

Optionally, the mining module 500 is configured to, for any link, determine, according to the traffic volume passing through each link pair, a traffic volume flowing into the link by each upstream adjacent link of the link, and specifically includes:

for any link, determining the traffic flow from the first upstream adjacent link to the link pair corresponding to the link according to the traffic flow passing through each link pair, and obtaining the traffic flow flowing into the first upstream adjacent link of the link; the first upstream contiguous link is any upstream contiguous link of the link;

optionally, the mining module 500 is configured to, for any link, determine, according to the traffic flow passing through each link pair, a traffic flow that the link flows out to each downstream adjacent link, and specifically includes:

for any link, determining the traffic flow of a link pair corresponding to the link to a first downstream adjacent link of the link, and obtaining the traffic flow of the first downstream adjacent link flowing out of the link; the first downstream adjacent link is any downstream adjacent link of the link.

Optionally, the traffic flow information of a link may further include: the proportion of the traffic flow rate associated with each upstream adjacent link to that link, and the proportion of the traffic flow rate associated with each downstream adjacent link to that link;

optionally, the excavation module 500 may be further configured to: recording the traffic flow information of each link through a preset format to form a traffic flow record of each link, wherein the traffic flow record of one link comprises the following steps: an incoming traffic flow record for the link, and an outgoing traffic flow record;

the first bit data of one record of the inflow vehicle flow record of one link correspondingly records the serial number of an upstream adjacent link of the link, the second bit data correspondingly records the vehicle flow of the upstream adjacent link flowing into the link, and the third bit data correspondingly records the occupation ratio of the related vehicle flow of the upstream adjacent link;

the first bit data of one record of the outgoing traffic volume record of one link correspondingly records the serial number of a downstream adjacent link of the link, the second bit data correspondingly records the traffic volume of the link outgoing to the downstream adjacent link, and the third bit data correspondingly records the occupation ratio of the related traffic volumes of the downstream adjacent link.

The link topological relation generating device provided by the embodiment of the invention can improve the reasonability and accuracy of the generated link topological relation.

The embodiment of the invention also provides a background server, wherein the background server can load a program for realizing the function of the program module to realize the link topological relation generation method provided by the embodiment of the invention; alternatively, fig. 14 shows a hardware structure block diagram of the backend server, and referring to fig. 14, the backend server may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

in the embodiment of the present invention, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 complete mutual communication through the communication bus 4;

the processor 1 may be a central processing unit CPU or an application Specific Integrated circuit asic or one or more Integrated circuits configured to implement embodiments of the present invention.

The memory 3 may comprise a high-speed RAM memory and may also comprise a non-volatile memory, such as at least one disk memory.

The memory 3 may store an executable program that is invoked for execution by the processor, the program being operable to:

determining a target link;

Alternatively, the detailed function and the extended function of the program may be as described above.

An embodiment of the present invention further provides a storage medium, where the storage medium stores a program suitable for being executed by a processor, and the storage medium may be in the form of a memory, a magnetic disk, a hard disk, and the like, where the program may be configured to:

determining a target link;

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A link topological relation generating method is characterized by comprising the following steps:

determining a target link;

searching links in the first direction of the target link, and determining the occupation ratio of the relative traffic flow of the links adjacent to each first direction according to the traffic flow information of the current link for the searched current link; the traffic flow information of the current link at least includes: the relative traffic flow of the current link and each link adjacent to the first direction;

if the occupation ratios of the relevant traffic flows of all the links adjacent to the first direction are not lower than the preset occupation ratio threshold value, or the occupation ratios of the relevant traffic flows of all the links adjacent to the first direction are lower than the preset occupation ratio threshold value, determining the links searched next step comprises the following steps:

or if the difference of the ratios of the relative vehicle flows of the links adjacent to the current link in each first direction is within the set difference range, determining the link searched in the next step from the links adjacent to the current link in each first direction according to the link level of the link adjacent to the current link in each first direction;

2. The link topology relationship generation method according to claim 1, wherein if the proportion of the relevant traffic volume of some links adjacent to the first direction is lower than a predetermined proportion threshold, the search is stopped on the branch of the some links adjacent to the first direction, and the link searched next is determined in the links adjacent to the first direction whose proportion of the relevant traffic volume is not lower than the predetermined proportion threshold.

3. The link topology relationship generation method according to claim 2, wherein the traffic flow information of the current link further includes: the proportion of the relative traffic flow of the links adjacent to the current link in each first direction;

the determining the proportion of the relative traffic flow of the adjacent links in each first direction according to the traffic flow information of the current link comprises the following steps:

4. The link topology relationship generation method according to claim 1, further comprising:

performing link search in a second direction of the target link, and determining links searched in the next step in the second direction according to the traffic flow information of the currently searched link in the second direction; the first direction is opposite to the second direction, and the traffic flow information of the link currently searched in the second direction at least comprises: the traffic volume associated with the link adjacent to each second direction;

when the search cutoff condition is reached, generating a link topological relation of the target link at least according to the link searched in the first direction of the target link comprises:

5. The link topological relation generating method according to claim 4, wherein the generating of the link topological relation of the target link according to the link searched in the first direction of the target link and the link searched in the second direction of the target link comprises:

6. The link topology relationship generation method according to any one of claims 1 to 5, wherein the traffic flow information of the current link further includes: the current link and the traffic flow of the links adjacent to each second direction, wherein the second direction is related to the first direction;

7. The link topological relation generating method according to claim 6, wherein the traffic information of the current link is extracted from traffic information of each link mined in advance; the method further comprises the following steps:

acquiring a plurality of driving tracks;

respectively extracting link pairs corresponding to each driving track to obtain the link pairs corresponding to the plurality of driving tracks; one driving track corresponds to at least one link pair, and one link pair comprises two adjacent links in one driving track;

merging and counting the link pairs corresponding to the plurality of driving tracks, and determining the count value of each link pair to obtain the traffic flow passing through each link pair;

determining traffic flow information of each link according to the traffic flow passing through each link pair; the traffic information of one link includes at least: the traffic volume flowing into each upstream adjacent link of the link, and the traffic volume flowing out from the link to each adjacent downstream link.

8. The method for generating link topological relation according to claim 7, wherein the merging and counting the same link pairs in the link pairs corresponding to the plurality of driving trajectories and determining the count value of each link pair comprises:

9. The link topological relation generation method according to claim 7, wherein the determining traffic flow information of each link according to the traffic flow passing through each link pair includes:

10. The link topology relationship generation method according to claim 9, wherein for any link, determining the traffic flow of each upstream adjacent link of the link into the link according to the traffic flow passing through each link pair comprises:

for any link, determining the traffic flow rate of the link flowing out to each downstream adjacent link according to the traffic flow rate passing through each link pair comprises the following steps:

11. The link topology relationship generation method according to any one of claims 7 to 10, wherein the traffic flow information of one link further includes: the proportion of the traffic flow rate associated with each upstream adjacent link to that link, and the proportion of the traffic flow rate associated with each downstream adjacent link to that link;

the method further comprises the following steps:

recording the traffic flow information of each link through a preset format to form a traffic flow record of each link, wherein the traffic flow record of one link comprises the following steps: an incoming traffic flow record for the link, and an outgoing traffic flow record;

12. A link topological relation generating apparatus, comprising:

a target link determination module for determining a target link;

the first searching module is used for searching links in the first direction of the target link, and for the searched current link, determining the proportion of the relative traffic flow of the links adjacent to each first direction according to the traffic flow information of the current link; the traffic flow information of the current link at least includes: the relative traffic flow of the current link and each link adjacent to the first direction;

13. A backend server, comprising: a memory storing an executable program for:

determining a target link;

14. A storage medium, characterized in that the storage medium stores a program adapted to be executed by a processor, the program being configured to:

determining a target link;