WO2023029553A1 - Route recommendation method and apparatus, and related device - Google Patents

Abstract

A route recommendation method, comprising: acquiring a route recommendation request, the route recommendation request comprising an identifier of an origin and an identifier of a destination; determining a recommended route according to a signaling access sequence corresponding to a road network route passing through the origin and the destination, the determined recommended route comprising information of a road network section that passes from the origin to the destination; and finally outputting the recommended route. Since when recommending for a user a feasible route from the origin to the destination, the recommended route is determined according to the signaling access sequence corresponding to the road network routes of other users when passing through the origin and destination, which allows the route that is finally recommended to the user to avoid detours as much as possible, so as to meet the needs of the user.

Description

Method, device and related equipment for route recommendation

This application claims the priority of the Chinese patent application with the application number 202111007567.8 and the title of the invention "method, device and related equipment for route recommendation" submitted to the State Intellectual Property Office of China on August 30, 2021, the entire contents of which are incorporated by reference in this application.

technical field

This application relates to the technical field of artificial intelligence (AI), in particular to a method, device and related equipment for route recommendation.

Background technique

In practical application scenarios, due to the complexity of road sections in the road network, users may not know how to get from their current location to their desired destination. Wherein, the road network refers to the road network in the traffic field; and each road section in the road network may specifically be a path between two adjacent traffic intersections in the road network.

For this reason, in the application fields such as smart transportation, it is possible to intelligently recommend moving paths in the road network for users accessing the network, so that users can successfully reach the destination from the starting point under the guidance of the recommended moving path. To facilitate the travel of the user. However, if the route intelligently recommended for the user has problems such as detours and incorrect route recommendations, it will instead bring travel obstacles to the user. Therefore, how to recommend suitable road network paths for users has become an important technical problem to be solved urgently.

Contents of the invention

The present application provides a route recommendation method, device, computing device, computer-readable storage medium, and computer program product, so as to recommend a suitable road network route for a user.

In the first aspect, the present application provides a route recommendation method. When recommending a route for a user, a route recommendation request is obtained, and the route recommendation request includes the identification of the origin and the identification of the destination, such as the name of the origin and the name of the destination, etc., and then determine the recommended path according to the signaling access order corresponding to the road network path passing through the origin and destination. The signaling access order can be, for example, that other users' mobile terminals The sequence of accessing multiple access points during the process of moving from the starting point to the destination, the determined recommended route includes the road network section information passed from the starting point to the destination, and finally the determined recommended route can be output.

Since when recommending a feasible path from the origin to the destination for the user, the recommended path is determined according to the signaling access sequence corresponding to the road network paths of other users when passing through the origin and destination, which makes the final recommendation to the user The path can better meet the needs of users. For example, after the candidate path is determined according to the signaling access sequence, a deviation access point can be identified based on the access point indicated by the signaling access sequence, and the deviation access point can be identified in the road network according to the deviation access point The position of the searched candidate path is corrected so that there is no detour problem in the finally determined recommended path. In this way, the use experience of the user can be improved, and the travel of the user is facilitated.

Wherein, the access point accessed by the mobile terminal may specifically be a device whose positioning accuracy for the mobile terminal is lower than a preset accuracy threshold, for example, it may be a base station or a routing device that supports the mobile terminal to access the network, etc. The location of these devices of the mobile terminal to roughly locate the location of the mobile terminal).

In a possible implementation manner, the signaling access sequence indicates multiple access points connected in sequence, so that when the recommended path is determined according to the signaling access sequence corresponding to the road network path passing through the origin and destination , specifically, according to the positions of multiple access points in the road network, search out the candidate path through the starting point and the destination from the road network. Since the path candidate may have a detour problem, the candidate path can be The path is corrected to obtain the recommended path that is finally provided to the user. In this way, detours and the like can be avoided as far as possible in the path finally recommended to the user, so that the path recommended to the user can better meet the actual application requirements of the user and improve user experience.

In a possible implementation manner, when correcting the candidate path, it may be specifically to identify a deviating access point among the plurality of access points indicated by the access order of the signaling, and to The position in the network is corrected to obtain the corrected candidate route, that is, the determined recommended route provided to the user. In this way, path correction can be implemented according to the deviation from the access point, so as to realize the possibility that the path recommended to the user is the path actually required by the user.

In a possible implementation manner, when identifying a deviating access point, it may be specifically calculated according to the positions of the plurality of access points in the road network, and calculating the detour generated by the candidate access points among the plurality of access points. a route ratio, the detour ratio is used to indicate the degree of path deviation of the candidate path; when the detour ratio generated by the candidate access point is greater than the ratio threshold, the candidate access point is identified as deviating from the access point. In this way, the deviating access point that causes the detour of the candidate path can be determined, so that the subsequent path correction can be implemented according to the deviating access point.

In a possible implementation manner, when searching for a candidate route, specifically, the historical recommended route in the road network and the access point corresponding to the historical recommended route may be obtained first, wherein the historical recommended route may be, for example, previously used by other users The recommended path, or the actual path generated by other users when moving in the road network before; Search out the candidate routes of the origin and destination of the route. In this way, the efficiency of searching candidate paths can be improved through the historical knowledge in the historical recommended paths.

In a possible implementation manner, in a possible implementation manner, after searching for a route from the road network according to the historical recommended route, the historical recommended route and the positions of multiple access points in the road network When starting and destination candidate routes, specifically, the first bipartite graph and the second bipartite graph may be obtained first, wherein the vertices in the first bipartite graph include the road network segments in the historically recommended route and the historically recommended The access point corresponding to the path, and the vertices in the second bipartite graph include the road network segment in the historical recommended path and the last connected access point corresponding to the historical recommended path; then, according to the obtained first bipartite graph and the obtained The second bipartite graph is used to search out the candidate routes of the starting point and the destination from the road network.

In a possible implementation manner, an information input interface may be presented to the user, and the information input interface may be used to receive the identification of the starting point and the identification of the destination input by the user, so as to determine the starting point of the recommended route required by the user and destination.

In a possible implementation manner, when outputting the recommended route, specifically, a route recommendation interface may be presented, and the route recommendation interface includes the recommended route, so that the user can move in the road network based on the recommended route presented on the route recommendation interface. Alternatively, the route recommendation interface may include the recommended route and multiple access points connected sequentially indicated by the signaling access order, so that while presenting the recommended route, multiple access points that the mobile terminal can access on the recommended route may also be presented. Access Point.

In a second aspect, the present application further provides a path recommendation device, where the path recommendation device includes various modules for executing the path recommendation method in the first aspect or any possible implementation manner of the first aspect.

In a third aspect, the present application also provides a route recommendation device, including: a processor and a memory; the memory is used to store instructions, and when the route recommendation device is running, the processor executes the instructions stored in the memory, so that The path recommendation device executes the path recommendation method in the first aspect or any implementation method of the first aspect. It should be noted that, the memory may be integrated in the processor, or may be independent of the processor. A computing device may also include a bus. Wherein, the processor is connected to the memory through the bus. Wherein, the memory may include a readable memory and a random access memory.

In a fourth aspect, the present application provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium is run on a computer, the computer executes any one of the above-mentioned first aspect and the first aspect. The operational steps of the method described in the embodiment.

In a fifth aspect, the present application provides a computer program product containing instructions, which, when run on a computer, cause the computer to execute the operation steps of the first aspect and the method described in any one of the implementation manners of the first aspect.

On the basis of the implementation manners provided in the foregoing aspects, the present application may further be combined to provide more implementation manners.

Description of drawings

FIG. 1 is a schematic diagram of an application scenario provided by the present application;

FIG. 2 is a schematic diagram of a recommended path before and after correction provided by the present application;

FIG. 3 is a schematic flowchart of a method for path recommendation provided by the present application;

FIG. 4 is a schematic diagram of an information input interface provided by the present application;

FIG. 5 is a schematic diagram of a route recommendation interface provided by the present application;

FIG. 6 is a schematic flowchart of another method for path recommendation provided by the present application;

FIG. 7 is a schematic diagram of a bipartite graph constructed by a path recommendation device 300 provided in the present application;

FIG. 8 is a schematic structural diagram of a path recommendation device provided by the present application;

FIG. 9 is a schematic diagram of a hardware structure of a path recommendation device provided in the present application.

Detailed ways

The technical solutions in the present application will be described below in conjunction with the drawings in the embodiments of the present application.

Referring to FIG. 1 , it is a schematic diagram of an application scenario provided by this application. As shown in FIG. 1 , the user 100 can query the feasible road network paths between the starting point and the destination through the terminal device 200 , that is, query which road network paths the user can follow to successfully reach the destination from the starting point. During specific implementation, the user 100 may input the identifier of the origin and the identifier of the destination in the interface presented by the terminal device 200 to query which road network paths exist in the road network that can reach the destination from the origin.

The terminal device 200 generates a corresponding route recommendation request according to the origin identifier and the destination identifier input by the user 100, and sends the route recommendation request to the route recommendation device 300 in the cloud. The route recommendation device 300 can analyze the identifier of the origin and the identifier of the destination from the received route recommendation request, and determine the recommended route according to the signaling access sequence corresponding to the road network paths passing through the origin and destination , the determined recommended route includes road network segment information passed from the origin to the destination. Among them, the signaling access order can be used to indicate that before this recommended route, when other users move from the starting point to the destination, the mobile terminals (such as mobile phones, smart watches, etc.) The access point can specifically be a device whose positioning accuracy for the mobile terminal is lower than the preset accuracy threshold, for example, it can be a base station or a routing device that supports mobile terminal access to the network, etc. (according to the access point The location of these devices of the mobile terminal to roughly locate the location of the mobile terminal). Exemplarily, the route recommendation device 300 may obtain multiple access points that the mobile terminal held by the other user sequentially accesses by querying a preset database. Wherein, the preset database may be, for example, a third-party database that can be accessed by the route recommendation device 300, and the third-party database stores network access information of one or more mobile terminals, such as the access point accessed by the mobile terminal name, access point location, network access time, network access duration, etc. Then, the route recommendation device 300 may feed back the determined recommended route to the terminal device 200 , so that the terminal device 200 presents the recommended route to the user 100 .

It is worth noting that if the route recommendation device 300 directly recommends to the user 100 the road network routes that other users pass through the starting point and the destination when moving, the road network route recommended to the user 100 may not be the optimal route. , for example, there may be detours in the road network route recommended to the user 100 . Therefore, when the path recommendation device 300 determines the recommended path according to the signaling access sequence corresponding to the road network path of the origin and destination of other users when they are moving, it can use the signaling access sequence to determine the path that other users pass through. The road network path is corrected, and the corrected road network path is finally recommended to the user 100, so as to recommend a suitable road network path for the user 100 and improve user experience.

For example, assume that the real moving path of other users in the road network is the moving path 1 shown by the dotted line in FIG. 2 . However, there is _an obvious detour phenomenon in _the moving path 1 shown in FIG. There is no need to go through the road network section in the direction from the access point Z ₂ to the access point Z ₃ first, and then pass through the road network section in the direction from the access point Z ₃ to the access point Z ₄ . Therefore, in order to recommend a road network route that is more suitable for the user 100 to the user 100, when the route recommendation device 300 recommends a road network route from the starting point to the destination for the user 100, it can obtain the mobile terminal of the other user. The signaling access sequence corresponding to the road network path from the origin to the destination, that is, to obtain the Z ₁ , Z ₂ , Z ₃ , and Z ₄ information sequentially accessed by the mobile terminal in Figure 2, so as to identify the Access point Z ₃ that generates a detour. In this way, the route recommendation device 300 can correct the road network routes of other users according to the location of the access point _Z3 in the road network, so as to obtain the moving route 2 shown in FIG. 2 . In this way, the route recommendation device 300 can feed back the moving route 2 as the final recommended route to the terminal device 200 so that the terminal device 200 can present it to the user 100 .

Exemplarily, the path recommendation device 300 may be implemented by one or more servers (such as a distributed server cluster, etc., including server 301, server 302, and server 303 for illustration in FIG. 1 ), and may provide corresponding path query Serve. Specifically, one or more processors are set in the server constituting the path recommendation device 300, such as by using a central processing unit (central processing unit, CPU) or an application-specific integrated circuit (application-specific integrated circuit, ASIC), or a programmable logic Device (programmable logic device, PLD) implementation, the above-mentioned PLD can be a complex program logic device (complex programmable logical device, CPLD), FPGA, general array logic (generic array logic, GAL) or any combination thereof. In other possible implementations, in addition to the above-mentioned hardware form taking the server as an example, the route recommendation device 300 may also be implemented through an acceleration terminal (for example, an edge station), and the route recommendation device 300 may also be implemented by software, for example, the route recommendation The device 300 is a cloud service provided by a data center or a cloud operator.

It should be noted that the application scenario shown in FIG. 1 is only used as an exemplary illustration, and in actual application, the present application may also be applied to other applicable scenarios. For example, in other possible scenarios, the route recommendation device 300 can also be implemented by software and run on the terminal device 200, for example, the terminal device 200 can integrate road network information, so as to provide the user 100 with local route recommendation services, etc. .

In the following, the process of recommending a moving path in the road network for a user provided by the present application will be further introduced with reference to the accompanying drawings.

Referring to FIG. 3, FIG. 3 is a schematic flowchart of a method for route recommendation provided by an embodiment of the present application, wherein the method can be applied to the route recommendation device 300 shown in FIG. 1, or can be applied to other applicable route recommendations in the device. For the convenience of description, the following uses the route recommendation device 300 shown in FIG. 1 as an example for illustration. As shown in Figure 3, the method may specifically include:

S301: The route recommendation device 300 acquires a route recommendation request, where the route recommendation request includes an identifier of an origin and an identifier of a destination.

In a possible implementation manner, the path recommendation device 300 may present an information input interface to the user 100, so as to obtain the origin and destination of the moving path recommended to the user 100 through the information interaction interface. Specifically, the route recommendation device 300 may present the information input interface shown in FIG. 4 to the user through the terminal device 200, and prompt the user to input the identification of the origin and the identification of the destination in the information input interface. For example, it may be The name of the origin and the name of the destination, or may be information such as a building name that can indicate the location of the origin or destination. Further, the terminal device 200 can also support the user 100 to automatically locate the starting place on the information input interface, for example, the user 100 can click the positioning control in the information input interface, and the terminal device 200 can automatically input the starting place, For example, the current location of the user 100 may be automatically determined as the starting location. The terminal device 200 may generate a route recommendation request according to the origin and destination identifiers input by the user 100, and send the route recommendation request to the route recommendation device 300, so as to request the route recommendation device 300 to provide the user 100 with the route recommendation request based on the route recommendation request. Make path recommendations.

S302: The path recommendation device 300 determines the recommended path according to the signaling access sequence corresponding to the road network path from the origin to the destination, where the recommended path includes road network segment information passed from the origin to the destination .

Usually, before the route recommendation device 300 recommends a route for the user 100, there may be other users who have already completed the movement process from the origin to the destination in the road network; and other users will carry mobile terminals with them. Mobile terminals usually access different access points in the road network sequentially as other users move, so that when other users move in the road network, the access points can provide corresponding mobile terminals held by other users. Web business service. As shown in FIG. 2 , when other users move along the road network along the direction from Z ₁ to Z ₄ , the mobile terminal can access access points such as Z ₁ , Z ₂ , Z ₃ , and Z ₄ in sequence.

Therefore, in a possible implementation manner, in the process of determining the recommended route for the user 100, the route recommendation device 300 may first obtain the road network routes corresponding to the starting point and the destination when other users move in the road network. The access order of the signaling, that is, to obtain the order in which the mobile terminals of other users access each access point during the process of moving from the origin to the destination.

Then, the route recommendation device 300 can search the route starting point and destination candidate routes from the road network according to the positions in the road network of multiple access points accessed by mobile terminals of other users.

Specifically, the path recommendation device 300 may sequentially sort the multiple access points according to the time sequence in which the mobile terminal accesses the multiple access points. Then, the route recommendation device 300 can determine, for each access point, one or more candidate road network segments within the signal coverage of the access point, and calculate the moving distance from the one or more candidate road network segments. The most likely road segment that the terminal will pass through when connecting to the access point. In this way, the route recommendation device 300 can search for each access point to obtain a road segment corresponding to the access point, so that the route recommendation device 300 can splice the road network segments determined for each access point end to end, and obtain the user 100 Candidate paths that can be moved during the process from the origin to the destination.

For example, it is assumed that the mobile terminal sequentially accesses n access points Z ₁ to Z _n . Then, the route recommendation device 300 may first determine m ₁ candidate road network segments within the signal coverage range of the access point for Z ₁ . Then, the path recommendation device 300 may first determine m ₂ candidate road network segments within the signal coverage range of the access point for Z ₂ , and select a candidate road network segment from the m ₂ candidate road network segments

The optimal path connecting to _Z2 was calculated by the Viterbi method. During specific implementation, the path recommendation device 300 can first calculate all candidate road network segments corresponding to the previous access point _Z1 through the following formula (1) to switch to

The transition probability of :

in,

is the transition probability; β is the standard deviation of the distance difference distribution, which can be a constant value set by technicians based on practical application experience;

is one of the m candidate road network segments corresponding to the access point z _t , the value range of i is from 1 to m, m is the candidate road network segment corresponding to each access point, and different access The number of candidate road network segments corresponding to the point is different, that is, the value of m corresponding to different access points is different; the initial value of t is 2, and its value ranges from 2 to n; d _t is two access points z _t- The absolute value of the difference between the distance between ₁ and z _t and the shortest path length of the road network between the projection points of these two access points on the road network section, which can be calculated by the following formula (2) Calculated to get:

in,

is the candidate road network segment corresponding to the access point z _t-1 in the z _t-1

projection point on

is the candidate road network segment corresponding to the access point z _t at z _t

projection point on .

Then, the route recommendation device 300 can calculate all the candidate road network segments connected from the access point _Z1 to the candidate road network segments corresponding to the access point _z2

, and further determine the candidate road network segment that maximizes the cumulative probability from m ₂ . Exemplarily, the route recommendation device 300 can determine the candidate road network segment that maximizes the cumulative probability through the following formula (3):

in,

is the cumulative probability; c _t-1 is a set composed of m _t-1 candidate road network segments within the signal coverage of access point z _t-1 ;

is the transmission probability of the access point z _t , which can be calculated by the following formula (4):

in,

is the candidate road network segment corresponding to the access point z _t relative to z _t

The corresponding distance probability;

is the positioning point z _t in the candidate road network segment

projection on

for z _t with

The great-circle distance between the geographic coordinate points where the two access points are located, that is, z _t and

The physical distance between the two access points; the parameter σ _z is the standard deviation of the Gaussian distribution, which can be used to control the influence of the distance probability, and it can be a constant value set by the technician according to practical application experience.

In this way, the route recommendation device 300 can calculate one or more road network segments with the largest cumulative probability between the access point Z ₁ and the access point Z ₂ based on the above formulas (1) to (4). Further, the route recommendation device 300 can adopt the above-mentioned similar implementation method to calculate one or more road network sections with the largest cumulative probability between the access point _Z2 and the access point _Z3 , and between _Z3 and _Z4 . One or more road network sections with the largest cumulative probability until the one or more road network sections with the largest cumulative probability between Zn _-1 and _Zn are calculated, so that the determined two adjacent access points Connecting the road network sections between them end-to-end, one or more moving paths corresponding to the access points _Z1 to _Zn can be obtained. For the convenience of description, this embodiment is called a candidate path.

In practical applications, there may be a detour problem in the candidate paths determined based on multiple access points. For example, the determined candidate path may be, for example, the moving path 1 shown in FIG. 2 . This may be because when other users move in the road network, the mobile terminals held by other users may access a far access point, but not necessarily access the communication base station closest to the mobile terminal. For example, due to the limited number of mobile terminals that can be accessed by a single communication base station, some mobile terminals may access to distant communication base stations because the number of terminal devices connected to the nearest communication base station reaches the upper limit, which makes the There may be a detour problem in the candidate paths searched in the order in which the terminals access the communication base stations.

In this embodiment, the path recommendation device 300 can identify the deviated access point that causes the detour problem of the searched candidate route, and correct the candidate route according to the position of the deviated access point in the road network, so that the final The route recommended to the user 100 is more in line with the needs of the user 100, and detours in the recommended route are avoided as much as possible.

As an implementation example, when the path recommendation device 300 identifies a deviating access point, it may specifically calculate the candidate access points among the plurality of access points based on the positions of the plurality of access points in the road network. Detour ratio, which can be used to indicate the degree of path deviation of the candidate path. When the detour ratio is greater than a preset ratio threshold (for example, 1), the path recommendation device 300 identifies the candidate access point as a deviating access point. And if the detour ratio generated by the candidate access point is not greater than the ratio threshold, the route recommendation device 300 can determine that the position of the candidate access point in the road network does not cause the candidate route searched by the route recommendation device 300 to generate detour problem.

Exemplarily, the path recommendation device 300 can calculate the detour ratio generated by the candidate access point z _t through the following formula (5):

Among them, g _t is the detour ratio;

is the projection point of the access point z _t-1 on the candidate road network segment corresponding to z _t-1 in the candidate path;

is the projection point of the access point z _t on the candidate road network segment corresponding to z _t in the candidate path;

is the projection point of the access point z _t+1 on the candidate road network segment corresponding to z _t+1 in the candidate path; dist(a,b) _route refers to the shortest path of two points a and b in the road network, The value of a is

or

The value of b is

or

When the detour ratio g _t generated by the candidate access point z _t is greater than the preset ratio threshold 1, it is determined that the candidate access point z _t is in

as well as

The projection point e _t-1 on the shortest path between the road network, and the road network segment between the access point z _t-1 and the projection point e _t-1 is added to the corresponding candidate access point z _t Candidate road network segments.

Then, the route recommendation device 300 can recalculate the road segment connected to the candidate road network

The path with the largest cumulative probability, and the previously calculated link to the candidate road network

The path with the largest cumulative probability is covered, so as to realize the adjustment of the searched candidate path, and obtain the corrected candidate path, that is, the recommended path. At this point, connect to the candidate road network segment

The maximum cumulative probability of can be calculated by the following formula (6):

Among them, c _t-1 refers to the set formed by the candidate road network segments corresponding to the access point z _t-1 ; c _t refers to the set formed by the candidate road network segments corresponding to the access point z _t .

It should be noted that the above formula (5) and formula (6) are illustrated by taking the calculation of the detour ratio according to the candidate access point and two access points adjacent to the candidate access point as an example. In other possible embodiments, the path recommendation device 300 may also calculate the detour ratio generated by the candidate access points based on more than four (including four) consecutive access points (including candidate access points), At this time, the route recommendation device 300 may perform an exemplary adjustment to the above formula when calculating the detour ratio, which is not limited in this embodiment.

S303: The route recommendation device 300 outputs the recommended route.

After the path recommendation device 300 determines the recommended path, it may output the recommended path.

In actual application, based on the above process, the number of recommended routes determined by the route recommendation device 300 may be one or multiple. Therefore, in a possible implementation manner, when there are multiple recommended paths, the path recommendation device 300 may select the recommended path corresponding to the maximum cumulative probability as the final output recommended path according to the cumulative probability corresponding to each recommended path, and present it through the terminal device 200 . For example, the route recommendation device 300 may present a route recommendation interface as shown in FIG. 5 through the terminal device 200, and the route recommendation device 300 may present the recommended route finally determined by the route recommendation interface. Alternatively, the path recommendation device 300 may sort the multiple recommended paths in descending order of cumulative probability, and simultaneously present the multiple recommended paths in the sorted order. Among them, the presentation priority of the recommended path with a larger cumulative probability is higher. For example, the recommended path 1 with the largest cumulative probability can be displayed in the first row, and the recommended path 2 with a smaller cumulative probability can be displayed in the second row. As shown in Figure 5. Further, the path recommendation device 300 may also present multiple access points indicated by the signaling access sequence on the path recommendation interface, so that the user 100 can view multiple access points that the mobile terminal can access on the path recommendation interface. entry point.

It should be noted that, in this embodiment, the route recommendation device 300 may calculate the candidate routes corresponding to all access points (including the last access point accessed by the mobile terminal), and identify the plurality of access points Correct the candidate path by the deviation access point in . In other embodiments, the route recommendation device 300 may identify deviated access points during the search process, and use the deviated access points to correct the searched candidate routes, and based on the corrected candidate routes and the remaining The unprocessed access points continue to search for the follow-up path of the mobile terminal. In this process, the above-mentioned candidate path may be a moving path searched based on some access points that the mobile terminal sequentially accesses, for example, based on the access point Z ₁ among the n access points (Z ₁ to Z _n ). , Z ₂ to Z _h (h is less than n), then, after correcting the candidate route, the route recommendation device 300 can continue to search for the candidate road network corresponding to the next access point Z _h+1 The road network segments connected to the revised candidate route in the road segment.

In this embodiment, when the path recommendation device 300 recommends a feasible path from the origin to the destination for the user 100, it is determined according to the signaling access sequence corresponding to the road network paths of other users when passing through the origin and destination. A recommended route, which makes the route finally recommended to the user 100 more satisfy the user's needs. For example, after the candidate path is determined according to the signaling access sequence, the path recommendation device 300 may identify a deviation access point from among the multiple access points indicated by the signaling access sequence, and based on the deviation access point In the position in the road network, the candidate paths that have been searched are corrected, so that there is no detour problem in the finally determined recommended path. In this way, the use experience of the user 100 can be improved, and the travel of the user 100 is facilitated.

In the above embodiment, the route recommendation device 300 searches for all candidate road network segments under the signal coverage of each access point during the process of recommending routes for the user 100 . In an actual application scenario, the number of candidate road network segments corresponding to a single access point is relatively large, so the route recommendation device 300 may require a large amount of calculation when determining the recommended route. For this reason, in some possible implementation manners, the route recommendation device 300 may pre-filter the candidate road network segments corresponding to each access point based on data such as historical recommended routes, so as to reduce the number of candidate road network segments corresponding to each access point. quantity.

Specifically, referring to FIG. 6 , FIG. 6 shows a schematic flowchart of another method for route recommendation. As shown in Figure 6, the method may specifically include:

S601: The route recommendation device 300 acquires a route recommendation request, where the route recommendation request includes an identifier of an origin and an identifier of a destination.

In this embodiment, the specific implementation manner of step S601 is similar to the specific implementation manner of step S301 in the foregoing embodiments, and reference may be made to relevant descriptions in the foregoing embodiments, and details are not repeated here.

S602: The route recommendation device 300 acquires a historically recommended route in the road network and an access point corresponding to the historically recommended route.

Wherein, the historically recommended route refers to the moving route recommended by the route recommending device 300 for one or more other users when moving in the road network before recommending the route for the user 100 . The access point corresponding to the historical recommended route is the access point that the mobile terminal carried by one or more other users accesses sequentially while moving along the historical recommended route.

In a possible implementation manner, the path recommendation device 300 may obtain signaling paths and global positioning system (global positioning system, GPS) paths generated by mobile terminals carried by other users when other users move along the historical recommended path. Wherein, the signaling path may indicate multiple access points that mobile terminals carried by other users sequentially access while moving; and the GPS path refers to the moving path of mobile terminals carried by other users determined by using GPS technology. In practical applications, there may be differences between the GPS path of the mobile terminal carried by other users and the mobile terminal's moving path in the road network, for example, part of the moving path in the GPS path is not located in a road section in the road network. Therefore, the route recommendation device 300 can obtain the moving route of the mobile terminal in the road network based on the GPS route. For example, the route recommendation device 300 can use a hidden Markov model (hidden markov model, HMM) to convert the GPS route into the mobile terminal's moving route in the road network, that is, the historical recommended route in step S601.

Of course, in practical applications, the route recommendation device 300 may also obtain historical recommended routes of mobile terminals carried by other users in other ways. moving path, etc. This embodiment does not limit it.

In practical applications, the number of historically recommended routes may be one or multiple, and different historically recommended routes may be different, for example, different historically recommended routes may include different road network segments.

S603: The route recommendation device 300 searches out the starting point of the route from the road network according to the historical recommended route, the access point corresponding to the historical recommended route, and the signaling access sequence corresponding to the road network route passing through the starting point and the destination and candidate paths to destinations.

S604: The route recommendation device 300 corrects the candidate routes to obtain a recommended route.

As an implementation example, the route recommendation device 300 may construct a first bipartite graph and a second bipartite graph according to historical recommended routes corresponding to other users and access points corresponding to the historical recommended routes, wherein, in the first bipartite graph The two types of vertices in the bipartite graph are the road network segments in the historical recommended route and the access points corresponding to the historical recommended route, and the two types of vertices in the second bipartite graph are the road network segments in the historical recommended route and the The terminating access point (that is, the last access point accessed by the mobile terminals carried by other users along the historical recommended route). Then, the path recommendation device 300 can search out multiple paths from the road network according to the signaling access sequence corresponding to the constructed first bipartite graph, the second bipartite graph, and the road network paths passing through the origin and destination. Candidate routes corresponding to each access point, and by modifying the candidate routes, the recommended route finally provided to the user 100 is obtained.

For example, when the path recommendation device 300 constructs the bipartite graph, it can use all the road network segments in the historically recommended route and the access points corresponding to each road network segment as the two types of vertices in the first bipartite graph, and pass Traverse the road network sections included in the historical recommended route and the access points corresponding to the historical recommended route, determine the access points that the mobile terminals carried by other users access when moving on each road network section, and An edge is constructed between the access point and the road network segment in the subgraph, so that a first bipartite graph based on the access point and the road network segment can be constructed, as shown on the left side of FIG. 7 . In practical applications, there may be multiple historical recommended routes, so that there may be a pairing relationship between the same road network segment and an access point in different historical recommended routes. Therefore, the route recommendation device 300 may add a weight value to the edge when constructing an edge between the access point and the road network segment in the first bipartite graph, such as setting the initial weight value of the edge to 1, etc. Moreover, when traversing the remaining historically recommended routes and the access points corresponding to the historically recommended routes, if it is determined that mobile terminals carried by other users still access the access point when moving on the road network section, the route recommendation device 300 It is possible to increase the weight value of this edge in the first bipartite graph, such as adding 1 to the weight value of this edge every time it occurs repeatedly.

In addition, the route recommendation device 300 can also use the road network segment in the historical recommended route and the terminating access point in the historical recommended route as two types of vertices of the second bipartite graph, and traverse the last one included in the historical recommended route Road network section and the terminating access point corresponding to the historical recommended route, determine the road network section where the mobile terminal carried by other users accesses the last access point, and then in the second bipartite graph in the terminating access point An edge is constructed between the point and the road network section, so that a second bipartite graph based on the termination access point and the road network section can be constructed, as shown on the right side of FIG. 7 . In addition, the path recommendation device 300 may add a weight value to the edge when constructing an edge between the access point and the road network section in the first bipartite graph, such as setting the initial weight value of the edge to 1, etc. When the same terminating access point corresponds to the same road network segment in multiple historical recommended routes, the route recommendation device 300 can increase the weight value of this edge in the second bipartite graph. Add 1 to the weight value of the edge, etc.

After constructing the first bipartite graph and the second bipartite graph, the path recommendation device 300 can further construct the first graph embedding vector set corresponding to the first bipartite graph and the second graph embedding vector set corresponding to the second bipartite graph . Exemplarily, the path recommendation device 300 can call a graph embedding algorithm, such as a large-scale information network embedding (large-scale information network embedding, LINE) algorithm, etc., based on a predefined objective function, calculate each The graph embedding vectors corresponding to the vertices are used to obtain the first graph embedding vector set corresponding to the first bipartite graph, and the graph embedding vectors in the first graph embedding vector set make the value of the objective function lower than a preset value. At the same time, the path recommendation device 300 can call the graph embedding algorithm (which can be the same as the aforementioned graph embedding algorithm), and calculate the graph embedding corresponding to each vertex in the second bipartite graph based on the predefined objective function (which can be consistent with the aforementioned objective function). vector, so as to obtain a second set of graph embedding vectors corresponding to the second bipartite graph, and the graph embedding vectors in the second set of graph embedding vectors make the value of the objective function lower than a preset value.

Wherein, the pre-defined objective function can be, for example, the functions shown in the following formulas (7) and (8):

Among them, E _b is the set of graph embedding vectors, e _ij is the edge connecting vertex v _j and vertex v _i , w _ij is the weight of e _ij ,

is the graph embedding vector of vertex v _i ,

is the graph embedding vector of vertex v _j , and V _r is the set of vertices of the same type as v _j .

When determining the candidate road network segments corresponding to each access point accessed by the mobile terminal, taking determining the access point z _t as an example, the route recommendation device 300 may first determine N road network segments according to the signal coverage of the access point z _t Preliminary screening of candidate road network segments. Then, the route recommendation device 300 can calculate the distance probability of the access point z _t relative to each preliminary screening candidate road network segment according to the following formula (9):

At the same time, the route recommendation device 300 can calculate the historical probability of the access point z _t relative to each preliminary screening candidate road network segment according to the following formula (10):

in,

Candidate road network segments for preliminary screening

the historical probability of

and

They are the primary screening candidate road network sections

and the graph embedding vector of the access point z _t in the first bipartite graph;

and

They are the primary screening candidate road network sections

and the graph embedding vector of the terminating access point of access point z _t in the second bipartite graph.

Then, the route recommendation device 300 can calculate the transmission probability corresponding to each preliminary screening candidate road network segment according to the distance probability and historical probability corresponding to each preliminary screening candidate road network segment. Exemplarily, the transmission probability corresponding to each preliminary screening candidate road network segment can be calculated by the following formula (11):

in,

Candidate road network segments for preliminary screening

The emission probability of ; w is a weight coefficient, for example, it can be 0.5 and so on.

Next, the route recommendation device 300 can filter the preliminary screening candidate road network segments whose emission probabilities are less than the preset probability threshold according to the emission probabilities corresponding to each preliminary screening candidate road network segments, and set the remaining emission probabilities not less than the preset probability threshold The preliminary screening candidate road network section is used as the candidate road network section corresponding to the access point z _t . In this way, the route recommendation device 300 can search out the candidate route corresponding to the mobile terminal according to the candidate road network segment corresponding to the access point z _t obtained after filtering, so as to reduce the number of candidates involved in the calculation when the route recommendation device 300 determines the candidate route. The number of road network segments. Wherein, the route recommendation device 300 can search out the candidate route of the mobile terminal from the candidate road network segments corresponding to each access point after screening according to the aforementioned formulas (1), (2), (3) and formula (11). For specific implementations of searching out candidate routes from candidate road network segments and correcting candidate routes, reference may be made to relevant descriptions in the foregoing embodiments, and details are not repeated here.

S605: The route recommendation device 300 outputs the recommended route.

Wherein, for the specific implementation process of step S605, reference may be made to the description of relevant parts of step S303 in the foregoing embodiments, which will not be repeated here.

In this embodiment, when searching for candidate routes according to the candidate road network segments corresponding to each access point, the route recommendation device 300 pre-selects each access point according to historical recommended routes and other data generated by mobile terminals carried by other users. The corresponding candidate road network segments are filtered, thereby reducing the number of candidate road network segments participating in the calculation, thereby not only improving the efficiency of the route recommendation device 300 in recommending routes for the user 100, but also reducing the consumption of computing resources.

It should be noted that other reasonable step combinations conceivable by those skilled in the art based on the above description also fall within the protection scope of the present application. Secondly, those skilled in the art should also be familiar with that the embodiments described in the specification belong to preferred embodiments, and the actions involved are not necessarily required by this application.

The route recommendation method provided by the present application is described in detail above with reference to FIG. 1 to FIG. 7 , and the route recommendation device and route recommendation device provided according to the present application will be described below in conjunction with FIGS. 8 to 9 .

FIG. 8 is a schematic structural diagram of a route recommendation device provided by the present application. As shown in FIG. 8, the path recommendation device 800 may include:

An acquisition module 801, configured to acquire a route recommendation request, where the route recommendation request includes an identification of an origin and an identification of a destination;

A determination module 802, configured to determine a recommended path according to the signaling access sequence corresponding to the road network paths passing through the origin and the destination, the recommended path includes all the routes from the origin to the destination Passed road network section information;

An output module 803, configured to output the recommended path.

It should be understood that the path recommendation device 800 in this embodiment of the present invention may be implemented by a CPU or an application-specific integrated circuit (ASIC), or a programmable logic device (PLD). It can be complex programmable logic device (complex programmable logical device, CPLD), field-programmable gate array (field-programmable gate array, FPGA), general array logic (generic array logic, GAL) or any combination thereof. When the webpage search methods shown in FIGS. 1 to 8 can also be realized by software, the path recommendation device 800 and its modules can also be software modules.

In a possible implementation manner, the signaling access sequence indicates multiple access points connected in sequence, and the determining module 802 is specifically configured to:

According to the positions of the plurality of access points in the road network, searching for a candidate route passing through the starting point and the destination from the road network;

Correcting the candidate path to obtain the recommended path.

In a possible implementation manner, the determining module 802 is specifically configured to:

identifying a deviating access point in the plurality of access points;

Correcting the candidate route according to the position of the deviated access point in the road network to obtain the recommended route.

In a possible implementation manner, the determining module 802 is specifically configured to:

calculating a detour ratio generated by a candidate access point among the plurality of access points according to positions of the plurality of access points in the road network, the detour ratio being used to indicate the candidate path Existing degree of path deviation;

The candidate access point is identified as the deviating access point when the detour ratio generated by the candidate access point is greater than a ratio threshold.

In a possible implementation manner, the determining module 802 is specifically configured to:

Obtaining historical recommended routes in the road network and access points corresponding to the historical recommended routes;

According to the historical recommended route, the access point corresponding to the historical recommended route, and the positions of the plurality of access points in the road network, search for the starting point and the destination from the road network candidate paths.

In a possible implementation manner, the determining module 802 is specifically configured to:

Acquiring a first bipartite graph and a second bipartite graph, the vertices in the first bipartite graph include road network sections in the historical recommended route and access points corresponding to the historical recommended route, the second The vertices in the bipartite graph include road network segments in the historical recommended route and the last connected access point corresponding to the historical recommended route;

According to the first bipartite graph and the second bipartite graph, a candidate path passing through the origin and the destination is searched out from the road network.

In a possible implementation manner, the output module 803 is further configured to present an information input interface, and the information input interface is configured to receive the identifier of the origin and the identifier of the destination input by a user.

In a possible implementation manner, the output module 803 is specifically configured to:

A path recommendation interface is presented, where the path recommendation interface includes the recommended path, or, the path recommendation interface includes the recommended path and a plurality of sequentially connected access points indicated by the signaling access order.

The path recommendation device 800 according to the embodiment of the present application may correspond to the implementation of the method described in the embodiment of the present application, and the above-mentioned and other operations and/or functions of each module of the path recommendation device 800 are to realize the For the sake of brevity, the corresponding processes of each method are not repeated here.

In this embodiment, when recommending a feasible path from the starting point to the destination for the user, the recommended path is determined according to the signaling access sequence corresponding to the road network path when other users pass the starting point and the destination, which makes Finally, the path recommended to the user can better meet the needs of the user. In this way, the use experience of the user can be improved, and the travel of the user is facilitated.

FIG. 9 is a schematic diagram of a route recommendation device 900 provided in the present application. As shown in the figure, the route recommendation device 900 includes a processor 901 , a memory 902 , and a communication interface 903 . Wherein, the processor 901, the memory 902, and the communication interface 903 communicate through the bus 904, or communicate through other means such as wireless transmission. The memory 902 is used to store instructions, and the processor 901 is used to execute the instructions stored in the memory 902 . Further, the path recommendation device 900 may further include a memory unit 905 , and the memory unit 905 may be connected to the processor 901 , the storage medium 902 and the communication interface 903 through the bus 904 . Wherein, the memory 902 stores program codes, and the processor 901 can call the program codes stored in the memory 902 to perform the following operations:

Obtaining a route recommendation request, where the route recommendation request includes an identification of an origin and an identification of a destination;

Determine the recommended path according to the signaling access sequence corresponding to the road network path passing through the origin and the destination, and the recommended path includes road network segment information passed from the origin to the destination ;

Output the recommended path.

It should be understood that, in the embodiment of the present application, the processor 901 may be a CPU, and the processor 901 may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASICs), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete device components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like.

The memory 902 may include read-only memory and random-access memory, and provides instructions and data to the processor 901 . Memory 902 may also include non-volatile random access memory. For example, memory 902 may also store device type information.

The memory 902 can be volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the non-volatile memory can be read-only memory (read-only memory, ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically programmable Erases programmable read-only memory (electrically EPROM, EEPROM) or flash memory. Volatile memory can be random access memory (RAM), which acts as external cache memory. By way of illustration and not limitation, many forms of RAM are available such as static random access memory (static RAM, SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), Double data rate synchronous dynamic random access memory (double data date SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (synchlink DRAM, SLDRAM) and direct Memory bus random access memory (direct rambus RAM, DR RAM).

The communication interface 903 is used to communicate with other devices connected to the computing device 900 . The bus 904 may include not only a data bus, but also a power bus, a control bus, and a status signal bus. However, for clarity of illustration, the various buses are labeled as bus 904 in the figure.

It should be understood that the path recommendation device 900 according to the embodiment of the present application may correspond to the path recommendation device 900 in the embodiment of the present application, and may correspond to performing the path recommendation in the method shown in Fig. 3 and Fig. 6 according to the embodiment of the present application The above-mentioned and other operations and/or functions implemented by the device 300 and the route recommendation device 900 are respectively to realize the corresponding processes of the methods in FIG. 3 and FIG.

The above-mentioned embodiments may be implemented in whole or in part by software, hardware, firmware or other arbitrary combinations. When implemented using software, the above-described embodiments may be implemented in whole or in part in the form of computer program products. The computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server, or data center Transmission to another website site, computer, server, or data center by wired (eg, coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center that includes one or more sets of available media. The available media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, DVD), or semiconductor media. The semiconductor medium can be a solid state drive (SSD)

The above is only a specific embodiment of the application, but the scope of protection of the application is not limited thereto. Any person familiar with the technical field can easily think of various equivalents within the scope of the technology disclosed in the application. Modifications or replacements, these modifications or replacements shall be covered within the scope of protection of this application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (18)

1. A method for path recommendation, characterized in that the method comprises:

   Obtaining a route recommendation request, where the route recommendation request includes an identification of an origin and an identification of a destination;

   Determine the recommended path according to the signaling access sequence corresponding to the road network path passing through the origin and the destination, and the recommended path includes road network segment information passed from the origin to the destination ;

   Output the recommended path.
2. The method according to claim 1, wherein the signaling access order indicates a plurality of access points connected in sequence, and the access points corresponding to the road network paths passing through the origin and the destination are characterized in that, The signaling access sequence determines the path recommendation results, including:

   According to the positions of the plurality of access points in the road network, searching for a candidate route passing through the starting point and the destination from the road network;

   Correcting the candidate path to obtain the recommended path.
3. The method according to claim 2, wherein said modifying said candidate path to obtain said recommended path comprises:

   identifying a deviating access point in the plurality of access points;

   Correcting the candidate route according to the position of the deviated access point in the road network to obtain the recommended route.
4. The method according to claim 3, wherein the identifying a deviating access point among the plurality of access points comprises:

   calculating a detour ratio generated by a candidate access point among the plurality of access points according to positions of the plurality of access points in the road network, the detour ratio being used to indicate the candidate path Existing degree of path deviation;

   The candidate access point is identified as the deviating access point when the detour ratio generated by the candidate access point is greater than a ratio threshold.
5. The method according to any one of claims 2 to 4, characterized in that, according to the positions of the plurality of access points in the road network, the starting point and the starting point are searched from the road network. Candidate paths for the destination, including:

   Obtaining historical recommended routes in the road network and access points corresponding to the historical recommended routes;

   According to the historical recommended route, the access point corresponding to the historical recommended route, and the positions of the plurality of access points in the road network, search for the starting point and the destination from the road network candidate paths.
6. The method according to claim 5, characterized in that, according to the historical recommended route and the access point corresponding to the historical recommended route, the starting point and the route are searched out from the road network. Candidate paths to the destination, including:

   Acquiring a first bipartite graph and a second bipartite graph, the vertices in the first bipartite graph include road network sections in the historical recommended route and access points corresponding to the historical recommended route, the second The vertices in the bipartite graph include road network segments in the historical recommended route and the last connected access point corresponding to the historical recommended route;

   According to the first bipartite graph and the second bipartite graph, a candidate path passing through the origin and the destination is searched out from the road network.
7. The method according to any one of claims 1 to 6, wherein the method further comprises:

   An information input interface is presented, and the information input interface is used to receive the identification of the origin and the identification of the destination input by the user.
8. The method according to any one of claims 1 to 7, wherein the outputting the recommended path comprises:

   A path recommendation interface is presented, where the path recommendation interface includes the recommended path, or, the path recommendation interface includes the recommended path and a plurality of sequentially connected access points indicated by the signaling access order.
9. A path recommendation device, characterized in that the device comprises:

   An acquisition module, configured to acquire a route recommendation request, where the route recommendation request includes an identification of an origin and an identification of a destination;

   A determining module, configured to determine a recommended path according to the signaling access sequence corresponding to the road network path passing through the origin and the destination, the recommended path includes the route from the origin to the destination road network segment information;

   An output module, configured to output the recommended path.
10. The device according to claim 9, wherein the signaling access order indicates multiple access points connected in sequence, and the determining module is specifically used for:

    According to the positions of the plurality of access points in the road network, searching for a candidate route passing through the starting point and the destination from the road network;

    Correcting the candidate path to obtain the recommended path.
11. The device according to claim 10, wherein the determining module is specifically used for:

    identifying a deviating access point in the plurality of access points;

    Correcting the candidate route according to the position of the deviated access point in the road network to obtain the recommended route.
12. The device according to claim 11, wherein the determining module is specifically used for:

    calculating a detour ratio generated by a candidate access point among the plurality of access points according to positions of the plurality of access points in the road network, the detour ratio being used to indicate the candidate path Existing degree of path deviation;

    The candidate access point is identified as the deviating access point when the detour ratio generated by the candidate access point is greater than a ratio threshold.
13. The device according to any one of claims 10 to 12, wherein the determining module is specifically configured to:

    Obtaining historical recommended routes in the road network and access points corresponding to the historical recommended routes;

    According to the historical recommended route, the access point corresponding to the historical recommended route, and the positions of the plurality of access points in the road network, search for the starting point and the destination from the road network candidate paths.
14. The device according to claim 13, wherein the determining module is specifically used for:

    Acquiring a first bipartite graph and a second bipartite graph, the vertices in the first bipartite graph include road network sections in the historical recommended route and access points corresponding to the historical recommended route, the second The vertices in the bipartite graph include road network segments in the historical recommended route and the last connected access point corresponding to the historical recommended route;

    According to the first bipartite graph and the second bipartite graph, a candidate route passing through the origin and the destination is searched out from the road network.
15. The device according to any one of claims 9 to 14, wherein the output module is further configured to present an information input interface, and the information input interface is used to receive the identification and the origin of the user input. The ID of the destination in question.
16. The device according to any one of claims 9 to 15, wherein the output module is specifically used for:

    A path recommendation interface is presented, where the path recommendation interface includes the recommended path, or, the path recommendation interface includes the recommended path and a plurality of sequentially connected access points indicated by the signaling access order.
17. A route recommendation device, characterized in that it includes a processor and a memory; the memory is used to store computer instructions; the processor is used to execute the method according to any one of claims 1 to 8 according to the computer instructions. The steps of the method.
18. A computer-readable storage medium, characterized by comprising instructions, the instructions are used to implement the operation steps of the method according to any one of claims 1-8.

Images