Route recommendation methods and related equipment

Abstract

This application discloses a route recommendation method and related equipment, which can be applied to the fields of transportation or mapping. It can determine a target navigation route from a starting position to a destination position for a target object; identify at least one accompanying route triggering intersection from the road intersections of the target navigation route; obtain at least one candidate accompanying route based on the accompanying route triggering intersection and the destination position; determine route transfer probability information corresponding to each candidate accompanying route based on the transfer relationships between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route; and select a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the route transfer probability information corresponding to the candidate accompanying routes. The route transfer probability information in this application can provide a quantitative description of route quality, thus improving the quality of the selected target accompanying routes.

Description

Technical Field

[0001] This application relates to the field of computer technology, specifically to a route recommendation method and related equipment. Background Technology

[0002] With the rapid development of computer and communication technologies, vehicle navigation has been widely used in people's daily travel. Generally speaking, vehicle navigation mainly refers to calculating a navigation route based on the user's set origin and destination, and guiding the user to the destination according to the navigation route. During the navigation process, the vehicle navigation system may discover better routes and provide them as supplementary routes for the user's reference.

[0003] Current technologies typically calculate alternative routes at the intersection ahead when there is congestion ahead, such as obtaining recommended routes to the user based on estimated arrival time. However, because the design of these alternative route schemes is relatively simple, they cannot provide a quantitative description of route quality, thus compromising the quality of the obtained routes. Summary of the Invention

[0004] This application provides a route recommendation method and related equipment. The related equipment may include a route recommendation device, electronic equipment, computer-readable storage medium, and computer program product, which can improve the quality of the selected target accompanying route.

[0005] This application provides a route recommendation method, including:

[0006] Determine a target navigation route from the starting position to the ending position of the target object, wherein the target navigation route includes at least one road segment and a road intersection, and one road intersection connects at least two road segments;

[0007] From the road intersections of the target navigation route, identify at least one accompanying route trigger intersection;

[0008] Based on the intersection triggered by the accompanying route and the destination location, at least one candidate accompanying route is obtained;

[0009] Based on the transfer relationships between road segments in the historical driving routes corresponding to the historical objects, and the road segments in each candidate accompanying route, determine the route transfer probability information corresponding to each candidate accompanying route;

[0010] Based on the route transition probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain the sorting result;

[0011] Based on the sorting results, a target accompanying route is selected from the candidate accompanying routes for recommendation to the target object.

[0012] Accordingly, embodiments of this application provide a route recommendation device, including:

[0013] The first determining unit is used to determine the target navigation route of the target object from the starting position to the ending position. The target navigation route includes at least one road segment and a road intersection, and one road intersection connects at least two road segments.

[0014] The second determining unit is used to determine at least one accompanying route triggering intersection from the road intersections of the target navigation route;

[0015] The acquisition unit is used to acquire at least one candidate accompanying route based on the intersection triggered by the accompanying route and the destination location;

[0016] The third determining unit is used to determine the route transfer probability information corresponding to each candidate accompanying route based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route.

[0017] The sorting unit is used to sort the candidate accompanying routes based on the route transition probability information corresponding to the candidate accompanying routes, and obtain the sorting result;

[0018] The selection unit is used to select a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the sorting result.

[0019] Optionally, in some embodiments of this application, the acquisition unit may be specifically used to acquire at least one candidate accompanying route based on the accompanying route triggering intersection and the destination location if the distance between the real-time location of the target object and the accompanying route triggering intersection meets the route recommendation triggering condition.

[0020] Optionally, in some embodiments of this application, the second determining unit may be specifically used to determine the yaw probability at the road intersection based on at least one driving route including the road intersection, and to determine at least one accompanying route triggering intersection from the road intersection based on the yaw probability, wherein the yaw probability is used to indicate the probability that the target object will move to a non-target navigation route at the road intersection.

[0021] Optionally, in some embodiments of this application, the second determining unit may include a first calculation subunit and a first determining subunit, as follows:

[0022] The first calculation subunit is used to calculate the transfer probability of the target object transferring to the road segment of the target navigation route at the road intersection based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object, wherein the historical driving route includes the road intersection;

[0023] The first determining subunit is configured to determine at least one accompanying route trigger intersection from the road intersections of the target navigation route based on the transition probability.

[0024] Optionally, in some embodiments of this application, the second determining unit may include a route acquisition subunit, a comparison subunit, and a second determining subunit, as follows:

[0025] The route acquisition subunit is used to acquire at least one candidate route from the starting position to the ending position, wherein the candidate route is a non-target navigation route;

[0026] The comparison subunit is used to compare the road intersections of the candidate route and the road intersections of the target navigation route to determine the diverging road intersections of the candidate route and the target navigation route.

[0027] The second determining subunit is used to determine at least one accompanying route triggering intersection in the target navigation route based on the branching road intersection.

[0028] Optionally, in some embodiments of this application, the comparison subunit may be specifically used to select target candidate routes corresponding to each dimension from the candidate routes based on the route attribute information of the candidate routes in at least one dimension; compare the road intersections of the target candidate routes and the road intersections of the target navigation routes to determine the diverging road intersections of the target candidate routes and the target navigation routes.

[0029] Optionally, in some embodiments of this application, the second determining unit may include an analysis subunit, a third determining subunit, and a first selecting subunit, as follows:

[0030] The analysis subunit is used to perform deviation behavior analysis on the historical driving route corresponding to the historical object, and obtain the frequency information of deviation behavior at each road intersection in the historical driving route.

[0031] The third determining subunit is used to determine the target deviation road intersection from each road intersection of the historical driving route based on the frequency information.

[0032] The first selection subunit is used to select the road intersection as the accompanying route trigger intersection of the target navigation route if the road intersection in the target navigation route belongs to the target deviation road intersection.

[0033] Optionally, in some embodiments of this application, the third determining unit may include a statistical subunit, a second calculation subunit, and a fusion subunit, as follows:

[0034] The statistical subunit is used to count the transfer frequency information between every two adjacent road segments in the historical driving route corresponding to the historical object, and the end point of the historical driving route is the end point of the target navigation route.

[0035] The second calculation subunit is used to calculate the transfer probability between each pair of adjacent road segments in each candidate accompanying route based on the transfer frequency information between each pair of adjacent road segments in each candidate accompanying route.

[0036] The fusion subunit is used to fuse the transition probabilities between every two adjacent road segments in each of the candidate accompanying routes to obtain the route transition probability information corresponding to each of the candidate accompanying routes.

[0037] Optionally, in some embodiments of this application, the sorting unit may include a comparison subunit and a sorting subunit, as follows:

[0038] The comparison subunit is used to compare the route attribute information of the candidate accompanying route in at least one dimension with the route attribute information of the remaining navigation route corresponding to the target navigation route in at least one dimension to obtain a first comparison result.

[0039] The sorting subunit is used to sort the candidate accompanying routes according to the first comparison result and the route transition probability information corresponding to the candidate accompanying routes, so as to obtain the sorting result.

[0040] Optionally, in some embodiments of this application, the sorting subunit may be specifically used to select a target candidate accompanying route from the candidate accompanying routes based on the first comparison result; and to sort the target candidate accompanying routes based on the route transition probability information corresponding to the target candidate accompanying route to obtain a sorting result.

[0041] The selection unit may include a traversal sub-unit and a second selection sub-unit, as follows:

[0042] The traversal subunit is used to traverse the target candidate accompanying route based on the sorting result;

[0043] The second selection subunit is used to select the target candidate accompanying route as the target accompanying route to recommend to the target object if the route attribute information of the traversed target candidate accompanying route in the at least one dimension meets the preset quality conditions.

[0044] Optionally, in some embodiments of this application, the second selection subunit may be specifically used to compare the route attribute information of the traversed target candidate accompanying routes in at least one dimension with the route attribute information of the remaining navigation routes corresponding to the target navigation route in at least one dimension to obtain a second comparison result; if the second comparison result meets a preset quality condition, the traversed target candidate accompanying routes are selected as target accompanying routes to be recommended to the target object.

[0045] Optionally, in some embodiments of this application, the route recommendation device may further include a switching unit, as follows:

[0046] The switching unit is configured to respond to a navigation switching command for the target object to switch to the target accompanying route. If the target object reaches the accompanying route trigger intersection corresponding to the target accompanying route, the accompanying route trigger intersection corresponding to the target accompanying route is used as the new starting position, and the target accompanying route is used as the new target navigation route; and return to the step of determining at least one accompanying route trigger intersection from the road intersections of the target navigation route.

[0047] An electronic device provided in this application includes a processor and a memory. The memory stores multiple instructions, and the processor loads the instructions to execute the steps in the route recommendation method provided in this application.

[0048] This application also provides a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps in the route recommendation method provided in this application.

[0049] Furthermore, embodiments of this application also provide a computer program product, including a computer program or instructions, which, when executed by a processor, implement the steps in the route recommendation method provided in embodiments of this application.

[0050] This application provides a route recommendation method and related equipment, which can determine a target navigation route from a starting position to a destination position for a target object. The target navigation route includes at least one road segment and a road intersection, and each road intersection connects at least two road segments. From the road intersections of the target navigation route, at least one accompanying route triggering intersection is determined. Based on the accompanying route triggering intersection and the destination position, at least one candidate accompanying route is obtained. Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route, route transfer probability information corresponding to each candidate accompanying route is determined. Based on the route transfer probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain a sorting result. Based on the sorting result, a target accompanying route for recommendation to the target object is selected from the candidate accompanying routes. The route transfer probability information in this application can provide a quantitative description of route quality, thus improving the quality of the selected target accompanying routes. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1a This is a schematic diagram of a scenario for the route recommendation method provided in an embodiment of this application;

[0053] Figure 1b This is a flowchart of the route recommendation method provided in the embodiments of this application;

[0054] Figure 1c This is another flowchart of the route recommendation method provided in the embodiments of this application;

[0055] Figure 1d This is a schematic diagram of the route recommendation method provided in the embodiments of this application;

[0056] Figure 1e This is another flowchart of the route recommendation method provided in the embodiments of this application;

[0057] Figure 2 This is another flowchart of the route recommendation method provided in the embodiments of this application;

[0058] Figure 3 This is a schematic diagram of the route recommendation device provided in the embodiments of this application;

[0059] Figure 4This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0060] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0061] This application provides a route recommendation method and related equipment. The related equipment may include a route recommendation device, an electronic device, a computer-readable storage medium, and a computer program product. Specifically, the route recommendation device may be integrated into an electronic device, which may be a terminal or a server, etc.

[0062] It is understood that the route recommendation method in this embodiment can be executed on a terminal, on a server, or jointly by a terminal and a server. The above examples should not be construed as limiting this application.

[0063] like Figure 1a As shown, the route recommendation method is executed jointly by a terminal and a server as an example. The route recommendation system provided in this application includes a terminal 10 and a server 11, etc.; the terminal 10 and the server 11 are connected through a network, such as through a wired or wireless network, etc., wherein the route recommendation device can be integrated into the server.

[0064] Server 11 can be used to: determine a target navigation route for a target object from a starting position to an ending position, the target navigation route including at least one road segment and a road intersection, wherein one road intersection connects at least two road segments; determine at least one accompanying route triggering intersection from the road intersections of the target navigation route; obtain at least one candidate accompanying route based on the accompanying route triggering intersection and the ending position; determine route transfer probability information corresponding to each candidate accompanying route based on the transfer relationship between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route; and select a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the route transfer probability information corresponding to the candidate accompanying routes. Server 11 can be a single server, a server cluster composed of multiple servers, or a cloud server. In the route recommendation method or apparatus disclosed in this application, multiple servers can form a blockchain, and the server is a node on the blockchain.

[0065] Terminal 10 can be used to receive a target accompanying route sent by server 11 and display the target accompanying route on the corresponding vehicle navigation page. Terminal 10 may include a mobile phone, intelligent voice interaction device, smart home appliance, in-vehicle terminal, tablet computer, laptop computer, or personal computer (PC), etc. A client can also be set on terminal 10, which can be an application client or a browser client, etc.

[0066] The step of server 11 obtaining the target's accompanying route can also be performed by terminal 10.

[0067] The route recommendation method provided in this application can be applied to the fields of transportation or mapping, and relates to intelligent vehicle-road cooperative systems in intelligent transportation systems.

[0068] Intelligent Traffic System (ITS), also known as Intelligent Transportation System, effectively integrates advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control, and vehicle manufacturing. It strengthens the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, improves the environment, and saves energy.

[0069] Intelligent Vehicle Infrastructure Cooperative Systems (IVICS), or vehicle-road cooperative systems for short, represent a development direction for Intelligent Transportation Systems (ITS). IVICS utilizes advanced wireless communication and next-generation Internet technologies to implement comprehensive, real-time dynamic information exchange between vehicles and infrastructure. Based on the collection and fusion of dynamic traffic information across all times and spaces, it conducts active vehicle safety control and cooperative road management, fully realizing effective collaboration between people, vehicles, and roads. This ensures traffic safety, improves traffic efficiency, and ultimately forms a safe, efficient, and environmentally friendly road traffic system.

[0070] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0071] This embodiment will be described from the perspective of a route recommendation device, which can be integrated into an electronic device, such as a server or a terminal.

[0072] It is understood that in the specific implementation of this application, user information, such as the user's corresponding driving route and other related data, is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0073] The route recommendation method of this application embodiment can be applied to vehicle navigation scenarios. This embodiment can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, and assisted driving.

[0074] like Figure 1b As shown, the specific process of this route recommendation method can be summarized as follows:

[0075] 101. Determine the target navigation route from the starting position to the ending position of the target object, wherein the target navigation route includes at least one road segment and a road intersection, and one road intersection connects at least two road segments.

[0076] The target object can be a vehicle or other means of transportation, or it can be an object undergoing route navigation. The starting position can be the beginning of the target navigation route, and the ending position can be the end of the target navigation route. The starting and ending positions can be set by the target object itself.

[0077] In navigation scenarios, based on the user-defined origin and destination, at least one candidate route from the origin (i.e., the starting point of the route) to the destination (i.e., the end point of the route) can be obtained, and then one candidate route can be selected as the target navigation route.

[0078] The target navigation route can consist of at least one road segment. A road segment can be the smallest data unit describing a road, specifically represented by a link. A link can be viewed as a set of structured data, including but not limited to attributes such as the link's length, width, and road classification. Specifically, a road segment can be a segment between two road intersections.

[0079] The route recommendation method provided in this application can select the triggering time for accompanying routes during navigation, specifically selecting the road intersections that trigger the acquisition of accompanying routes (considered as accompanying route trigger points), and triggering an accompanying route calculation request when arriving at or approaching the accompanying route trigger point, ranking the recalled candidate accompanying route schemes, and thus designing an accompanying route distribution strategy. For example... Figure 1c The diagram shown is a flowchart corresponding to the accompanying route recommendation strategy in this embodiment.

[0080] There are various ways to select the timing of the accompanying route triggering, and this embodiment does not limit this. For example, the transition probability of each road intersection in the target navigation route can be queried, and the accompanying route calculation request can be triggered at the road intersection where the transition probability is lower than the threshold T; another example is to determine the road intersection that triggers the accompanying route calculation request by obtaining the divergence points between the optimal solution route in each dimension and the target navigation route scheme through the corresponding pre-trip route calculation request; yet another example is to determine the road intersection that triggers the accompanying route calculation request based on the high-frequency deviation points in the target navigation route.

[0081] The accompanying route can be a better route discovered by the system in real time during navigation, and this route is provided to the user as an accompanying route for reference. Specifically, in this embodiment, the accompanying route refers to a route that starts at the intersection triggered by the corresponding accompanying route and ends at the end of the target navigation route. By displaying the accompanying route on the navigation page, the user can quickly determine the subsequent direction of travel.

[0082] 102. From the road intersections of the target navigation route, determine at least one accompanying route trigger intersection.

[0083] In this embodiment, at least one dimension of the road intersections in the target navigation route can be used for transition analysis to obtain at least one accompanying route triggering intersection in the target navigation route. The accompanying route triggering intersection can be a road intersection that triggers an accompanying route calculation request.

[0084] Optionally, in this embodiment, the step "determining at least one accompanying route trigger intersection from the road intersections of the target navigation route" may include:

[0085] Based on at least one driving route including the road intersection, a yaw probability is determined at the road intersection, and at least one accompanying route trigger intersection is determined from the road intersection based on the yaw probability, wherein the yaw probability is used to indicate the probability that the target object will move to a non-target navigation route at the road intersection.

[0086] Optionally, in this embodiment, the step "determining the yaw probability at the road intersection based on at least one driving route including the road intersection, and determining at least one accompanying route triggering intersection from the road intersections based on the yaw probability" may include:

[0087] Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object, the transfer probability of the target object being transferred to the road segment of the target navigation route at the road intersection is calculated, wherein the historical driving route includes the road intersection;

[0088] Based on the transition probability, at least one accompanying route trigger intersection is determined from the road intersections of the target navigation route.

[0089] In some embodiments, the intersections between two adjacent road segments with a transition probability lower than a preset value can be identified as the trigger intersections for the accompanying route. This preset value can be set according to the actual situation, and this embodiment does not impose any restrictions on it. In other embodiments, the intersections between every two adjacent road segments can be sorted according to the magnitude of the transition probability, such as sorting them from smallest to largest, to obtain sorted road intersections, and then the first n road intersections in the sorted road intersections can be used as the trigger intersections for the accompanying route.

[0090] Optionally, in this embodiment, the step "calculating the transfer probability of the target object transferring to the road segment of the target navigation route at the road intersection based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object" may include:

[0091] The frequency of transfers between every two adjacent road segments in the historical driving route corresponding to the historical object is statistically analyzed, and the endpoint of the historical driving route is the endpoint of the target navigation route.

[0092] Based on the transfer frequency information between each two adjacent road segments in the target navigation route, calculate the transfer probability between each two adjacent road segments in the target navigation route.

[0093] This embodiment can mine historical driving routes of historical objects and identify target historical driving routes whose endpoints match the endpoints of the target navigation route. Based on the driving data corresponding to the target historical driving routes, it can statistically analyze how the historical object chose the next road intersection when it reached a certain intersection. Based on the transfer frequency information between each pair of adjacent road segments, it can determine the transfer probability between each pair of adjacent road segments. The more transfer frequency information, the higher the transfer probability; conversely, the fewer transfer frequency information, the lower the transfer probability.

[0094] Specifically, the transfer frequency information between each pair of adjacent road segments can be the number of times a historical object appears in the target's historical driving route data, indicating its transfer from one road segment to the next adjacent road segment. The transfer probability can be obtained through object navigation trajectory mining, which yields the probability that road segment linkL1 links to the adjacent road segment linkL2 under the condition that the destination is determined. This probability can be denoted as P(L1, L2|Dest), where Dest represents the destination location.

[0095] Specifically, the object navigation trajectory can be a navigation trajectory composed of object GPS (Global Positioning System) data, where the GPS data can include timestamps, latitude and longitude, driving speed, altitude, and direction angle at each moment.

[0096] For example, road segment A has two adjacent road segments, road segment B and road segment C. Road segment A and road segment B belong to the target navigation route. If, based on the driving data corresponding to the target's historical driving route, it is found that when a historical object travels along road segment A to the next road intersection, 100 historical objects choose to continue traveling along road segment B (the transfer frequency information in the above embodiment), and 300 historical objects choose to continue traveling along road segment C, then the transfer probability corresponding to road segment A and road segment B can be 100 / (100+300) = 0.25.

[0097] Specifically, the target navigation route can be denoted as R0, and the target navigation route R0 can be described in the form of a link string, defined as follows: The last link is defined as the endpoint link. dest It can be iterated over. Each adjacent link pair in the array can be denoted as Link. in Link out Based on the driving data corresponding to the historical driving routes, query each link pair based on the destination link. dest The transition probability, which can be denoted as P(Link). in Link out |Link dest If P < T, T ∈ [0, 1], then Link can be used. in The next road intersection serves as the starting point to trigger route calculation, and T can be set according to the actual situation. Among them, P(Link) in Link out |Link dest ) indicates that the route's endpoint is Link. dest Under the conditions, from the road segment Link in Move to adjacent road segment Link out The transition probability.

[0098] In this embodiment, the triggering timing of the accompanying route can be determined by the transition probability P(L1, L2|Dest), which can effectively improve the quality of the triggering intersection of the accompanying route and reduce invalid accompanying route triggering. In addition, compared with the method of treating each road intersection as the triggering intersection of the accompanying route, it can significantly reduce the road calculation pressure while improving the quality of the triggering timing of the accompanying route.

[0099] Optionally, in this embodiment, the step "determining the yaw probability at the road intersection based on at least one driving route including the road intersection, and determining at least one accompanying route triggering intersection from the road intersections based on the yaw probability" may include:

[0100] Obtain at least one candidate route from the starting position to the ending position, wherein the candidate route is a non-target navigation route;

[0101] The road intersections of the candidate route and the road intersections of the target navigation route are compared and processed to determine the diverging road intersections of the candidate route and the target navigation route;

[0102] Based on the diverging road intersections, at least one accompanying route trigger intersection is determined in the target navigation route.

[0103] In some embodiments, the first road intersection in the target navigation route that diverges from the candidate route can be used as the trigger intersection for the accompanying route.

[0104] Optionally, in this embodiment, the step of "comparing the road intersections of the candidate route and the road intersections of the target navigation route to determine the diverging road intersections of the candidate route and the target navigation route" may include:

[0105] Based on the route attribute information of the candidate routes in at least one dimension, target candidate routes corresponding to each dimension are selected from the candidate routes;

[0106] The road intersections of the target candidate route and the road intersections of the target navigation route are compared and processed to determine the diverging road intersections of the target candidate route and the target navigation route.

[0107] Among them, route attribute information in at least one dimension may include mileage, travel time, congestion, road width, and whether it is a popular route.

[0108] In a specific scenario, before navigation, the route calculation engine can obtain N optional routes based on the user's input start and end locations. The user selects one of these routes to initiate navigation, defining this route as the target navigation route R0. Other routes besides the target navigation route R0 can be considered as candidate routes R. This embodiment can obtain high-quality routes (i.e., target candidate routes) under various route attribute dimensions based on the pre-trip route calculation's route N-recall, and then determine the accompanying route trigger intersections based on the divergence points between the target candidate routes and the target navigation route. Here, route N-recall refers to obtaining N optional routes based on the start and end points. Pre-trip route calculation specifically refers to the first route calculation request when determining the start and end points using the navigation function.

[0109] The route attribute dimensions can be denoted as S (frequently used routes), B (main roads preferred), E (shortest distance), G (less congested), A (shortest time), SKL (number of user routes), etc.; the obtained high-quality routes (optimal solutions) under each route attribute dimension can be denoted as S0, B0, E0, G0, A0, SKL0, etc. Comparing the target navigation route R0, the intersections where each optimal solution route diverges from R0 are calculated. Specifically, the first inconsistent link between R0 and each optimal solution route is found and denoted as Link. diff Thus, at the intersections where each optimal solution route branches off from R0, Link... diff The path calculation for the accompanying route is triggered from the starting point.

[0110] This embodiment can obtain a set of high-quality routes under various dimensions of route weights (e.g., shortest time, shortest distance, most commonly taken routes, etc.), and then determine the trigger intersections for accompanying routes based on the divergence points between the routes in the high-quality route set and the target navigation route. By combining the results of pre-trip route calculation, the diversity of accompanying routes can be effectively guaranteed.

[0111] In this context, route weights refer to the weights that represent the cost of traveling on roads in a route planning optimization algorithm. Route weights can express different costs through different dimensions, such as shortest time, shortest distance, and most commonly used routes. The optimal route solution is the route with the lowest cost calculated by the route planning optimization algorithm under different weighted costs.

[0112] Optionally, in this embodiment, the step "determining the yaw probability at the road intersection based on at least one driving route including the road intersection, and determining at least one accompanying route triggering intersection from the road intersections based on the yaw probability" may include:

[0113] By performing a deviation behavior analysis on the historical driving routes corresponding to the historical objects, the frequency information of deviation behavior at each road intersection in the historical driving routes is obtained.

[0114] Based on the frequency information, the target deviation road intersection is determined from each road intersection of the historical driving route;

[0115] If the road intersection in the target navigation route is a target deviation road intersection, the road intersection will be selected as the accompanying route trigger intersection of the target navigation route.

[0116] Among them, road intersections where the frequency of deviation behavior is higher than a preset value can be identified as target deviation road intersections. This preset value can be set according to the actual situation.

[0117] Specifically, high-frequency deviation points in the road network (specifically, the target deviation road intersections in the above embodiment) can be identified by analyzing deviation behaviors in historical navigation data, denoted as D(Link). H ); Traverse the target navigation route For each link in the equation, if the link is a high-frequency yaw point, i.e., link∈D(Link H If the link is used as the starting point, a route calculation request for the accompanying route will be triggered; among them, high-frequency deviation points refer to road intersections in the road network with a high probability of deviation, obtained by mining historical navigation data.

[0118] This embodiment can trigger a route calculation request for the accompanying route at an appropriate intersection during the navigation process, ensuring that the triggering opportunity of the main accompanying route is not missed, while minimizing the calculation overhead of the route calculation.

[0119] 103. Based on the intersection triggered by the accompanying route and the destination location, obtain at least one candidate accompanying route.

[0120] Optionally, in this embodiment, the step "obtaining at least one candidate accompanying route based on the accompanying route trigger intersection and the destination location" may include:

[0121] If the distance between the real-time location of the target object and the intersection triggering the accompanying route meets the route recommendation triggering condition, at least one candidate accompanying route is obtained based on the intersection triggering the accompanying route and the destination location.

[0122] The route recommendation triggering conditions can be set according to actual conditions, and this embodiment does not impose any restrictions on them. For example, the route recommendation triggering condition can be that the distance between the real-time location of the target object and the intersection where the accompanying route is triggered is less than a preset value, which can be set according to actual conditions; another example is that the next road intersection corresponding to the real-time location of the target object is the intersection where the accompanying route is triggered, etc.

[0123] The starting point of the candidate accompanying route can be the corresponding accompanying route trigger intersection, and the ending point is the end point of the target navigation route.

[0124] 104. Based on the transfer relationships between road segments in the historical driving routes corresponding to historical objects, and the road segments in each candidate accompanying route, determine the route transfer probability information corresponding to each candidate accompanying route.

[0125] Optionally, in this embodiment, the step "determining the route transfer probability information corresponding to each candidate accompanying route based on the transfer relationships between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route" may include:

[0126] The frequency of transfers between every two adjacent road segments in the historical driving route corresponding to the historical object is statistically analyzed, and the endpoint of the historical driving route is the endpoint of the target navigation route.

[0127] Based on the transfer frequency information between each pair of adjacent road segments in each candidate accompanying route, calculate the transfer probability between each pair of adjacent road segments in each candidate accompanying route.

[0128] The transition probabilities between every two adjacent road segments in each candidate accompanying route are fused to obtain the route transition probability information corresponding to each candidate accompanying route.

[0129] Specifically, the transfer frequency information between each pair of adjacent road segments in each candidate accompanying route can be obtained by querying the transfer frequency information between each pair of adjacent road segments in the historical driving route.

[0130] Among them, route transition probability information can be regarded as route-level transition probability, which can be used for quantitative evaluation of route quality.

[0131] There are various ways to fuse the transition probabilities between every two adjacent road segments in the candidate accompanying routes, and this embodiment does not limit this. For example, the fusion method can be various mathematical operations, such as standard deviation calculation and square root calculation.

[0132] In a specific scenario, each candidate accompanying route R can be obtained. i The link string, for each candidate accompanying route R i It can be described in the form of a link string, and is defined as follows: And denote the endpoint link of the target navigation route as Link. dest This embodiment can traverse... Each adjacent link pair in the array can be denoted as Link.in Link out Based on the driving data corresponding to the historical driving routes, query each link pair based on the destination link. dest The transition probability P(Link) in Link out |Link dest The queried candidate accompanying routes R i The conditional transition probabilities P for M links are given. i Accumulating and raising the Mth root of |i∈[1,M] can be denoted as: Then calculate the standard deviation of the conditional probability std(P) for the M link pairs. i |i∈[1,M]), will and std(P i We perform weighted summation on |i∈[1,M]) to obtain candidate accompanying routes R. i The route transition probability information, i.e. the quantitative evaluation score P(R) of route quality; P(R) can be used as a feature of the route in the route ranking model to score and rank candidate accompanying routes; where M can be the number of road intersections in the candidate accompanying routes.

[0133] The pow(x, y) function can be used to calculate the value of x raised to the power of y, and the std() function can be used to calculate the standard deviation.

[0134] 105. Based on the route transition probability information corresponding to the candidate accompanying routes, sort the candidate accompanying routes to obtain the sorting result.

[0135] In some embodiments, candidate accompanying routes with route transition probability information less than a preset value can be used as target accompanying routes; in other embodiments, candidate accompanying routes can be sorted according to the magnitude of route transition probability information, such as sorting them in descending order from smallest to largest, to obtain sorted candidate accompanying routes, and the first n routes in the sorted candidate accompanying routes can be used as target accompanying routes.

[0136] Optionally, in this embodiment, the step "sorting the candidate accompanying routes based on the route transition probability information corresponding to the candidate accompanying routes to obtain a sorting result" may include:

[0137] The route attribute information of the candidate accompanying route in at least one dimension is compared with the route attribute information of the remaining navigation routes corresponding to the target navigation route in at least one dimension to obtain a first comparison result;

[0138] Based on the first comparison result and the route transition probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain the sorting result.

[0139] Specifically, this embodiment can compare candidate accompanying routes with the remaining navigation routes of the target navigation route based on some key route attribute information. By comparing these, some candidate accompanying routes containing defects are filtered out, preventing routes with route defects from being issued as accompanying routes. These route defects can include: traversing difficult road sections, bumpy roads, etc. These route attribute information can include estimated arrival time, mileage, traffic lights, tolls, etc.

[0140] 106. Based on the sorting results, select a target accompanying route from the candidate accompanying routes for recommendation to the target object.

[0141] Optionally, in this embodiment, the step "sorting the candidate accompanying routes according to the first comparison result and the route transition probability information corresponding to the candidate accompanying routes to obtain a sorting result" may include:

[0142] Based on the first comparison result, a target candidate accompanying route is selected from the candidate accompanying routes;

[0143] Based on the route transition probability information corresponding to the target candidate accompanying routes, the target candidate accompanying routes are sorted to obtain the sorting result;

[0144] The step "selecting a target accompanying route from the candidate accompanying routes to recommend to the target object based on the sorting results" may include:

[0145] Based on the sorting results, the target candidate accompanying routes are traversed;

[0146] If the route attribute information of the traversed target candidate accompanying route in at least one dimension meets the preset quality conditions, the target candidate accompanying route is selected as the target accompanying route to be recommended to the target object.

[0147] Based on the first comparison result, candidate accompanying routes with route defects can be filtered out, and candidate accompanying routes without obvious defects can be selected as target candidate accompanying routes. Then, the target candidate accompanying routes are traversed according to the route transition probability information. Specifically, the target candidate accompanying routes can be sorted in descending order according to the route transition probability information to obtain a sequence of target candidate accompanying routes, and then the target candidate accompanying routes in the sequence are traversed sequentially.

[0148] Optionally, in this embodiment, the step "if the route attribute information of the traversed target candidate accompanying route in at least one dimension meets the preset quality conditions, select the target candidate accompanying route as the target accompanying route to recommend to the target object" may include:

[0149] The route attribute information of the traversed target candidate accompanying route in at least one dimension is compared with the route attribute information of the remaining navigation route corresponding to the target navigation route in at least one dimension to obtain a second comparison result;

[0150] If the second comparison result meets the preset quality conditions, the traversed target candidate accompanying routes are selected as target accompanying routes to be recommended to the target object.

[0151] In this embodiment, the remaining navigation routes of the target navigation route can be compared with the target candidate accompanying route based on some key route attribute information. By comparing the comparison, routes with obvious advantages can be selected as target accompanying routes. Moreover, the target accompanying routes obtained in this way have advantages in a certain key route characteristics and have good interpretability.

[0152] The preset quality conditions can be set according to the actual situation. For example, the mileage of the candidate accompanying route traversed can be much smaller than the mileage of the remaining navigation route corresponding to the target navigation route.

[0153] Specifically, when the number of target accompanying routes obtained meets the preset number, the traversal of target candidate accompanying routes can be stopped.

[0154] like Figure 1d As shown, after obtaining the target accompanying route, the target accompanying route can be recommended and displayed on the navigation page for users to refer to and determine their next route. The target accompanying route has one less traffic light than the remaining route of the target navigation route.

[0155] In a specific scenario, when a certain accompanying route trigger point is reached, the routing engine is requested to return multiple candidate accompanying routes R. bs And obtain each candidate accompanying route R bs The score (i.e., the route transition probability information in the above embodiments); can traverse each candidate accompanying route R bs Remove candidate accompanying route schemes that are significantly inferior to the remaining navigation routes of the target navigation route R0 in terms of main route attribute information, such as mileage. Mileage L bs If the remaining mileage L0 of the navigation route is greater than T times the target navigation route R0, then the candidate accompanying route scheme can be removed. After removing candidate adjoint routes that have obvious disadvantages, we can proceed based on the candidate adjoint route R. bs Based on the scores, the candidate accompanying routes are sorted in descending order to obtain the sorted candidate accompanying routes List(R). bs), iterate through List(R) in sequence bs ),like The route exhibits a significant advantage over the remaining navigation routes of the target navigation route R0 in a certain key route characteristic, such as in the mileage dimension, where the candidate accompanying route scheme has a clear advantage. Mileage L bs If the remaining navigation route mileage L0 is less than T times the target navigation route R0, then... The target accompanying route is issued based on the current accompanying route triggering timing.

[0156] Optionally, in this embodiment, after the step "selecting a target accompanying route from the candidate accompanying routes according to the sorting result for recommendation to the target object", it may further include:

[0157] In response to a navigation switching command that the target object switches to the target accompanying route, if the target object reaches the accompanying route trigger intersection corresponding to the target accompanying route, the accompanying route trigger intersection corresponding to the target accompanying route is taken as the new starting position, and the target accompanying route is taken as the new target navigation route.

[0158] Return to the step of determining at least one accompanying route trigger intersection from the road intersections of the target navigation route.

[0159] Specifically, when the target object switches from the target navigation route to the target accompanying route, the target accompanying route can be used as the new target navigation route, the accompanying route trigger intersection corresponding to the target accompanying route can be used as the new starting position, and then a new round of accompanying route recommendation can be executed.

[0160] The accompanying route scheme of this application can be mainly divided into two parts: the selection of the accompanying route triggering time (i.e., the selection of the accompanying route triggering intersection) and the selection of the accompanying route under the determined accompanying route triggering time.

[0161] The design of accompanying route schemes needs to balance performance and computational overhead. Too few accompanying route requests will result in too few accompanying routes being issued, missing some high-quality accompanying routes; too many accompanying route requests will lead to frequent route calculations at unnecessary intersections, causing excessive computational load on the system.

[0162] like Figure 1eAs shown, this solution allows for the selection of the triggering timing for accompanying routes during navigation. Specifically, it involves selecting the road intersections (considered as accompanying route trigger points) to trigger the acquisition of accompanying routes. There are various ways to select the accompanying route triggering timing, and this embodiment does not impose any restrictions on this. For example, the accompanying route triggering timing can be selected by setting a transfer probability threshold, setting a route divergence point, or setting a high-frequency yaw point. When the system reaches or approaches the accompanying route trigger point, an accompanying route calculation request is triggered. The transfer probability at the route level is calculated for the recalled candidate accompanying routes, and the candidate accompanying routes are sorted according to the transfer probability at the route level to design an accompanying route distribution strategy.

[0163] Among them, the timing of triggering the accompanying route can be selected by setting a transition probability threshold. Specifically, this can be done by querying the transition probability of each road intersection in the target navigation route and identifying the road intersections with a transition probability lower than the threshold T as the road intersections that trigger the accompanying route calculation request.

[0164] Specifically, the timing of the accompanying route triggering can be selected by setting route divergence points. This can be achieved by using the divergence points Y between the optimal solution route in each dimension and the target navigation route scheme obtained from the pre-navigation route calculation request, and then determining the road intersections that trigger the accompanying route calculation request.

[0165] Among them, the timing of the accompanying route triggering can be selected by setting high-frequency yaw points. Specifically, it can be: based on the high-frequency yaw points in the target navigation route, determine the road intersections that trigger the accompanying route calculation request.

[0166] This scheme integrates the rationality of accompanying route triggering timing and the diversity of accompanying routes in its accompanying route triggering timing strategy. During the selection process, the quality of candidate accompanying routes can be effectively quantified through route-level transition probabilities, ensuring that higher-quality accompanying routes are obtained with as few triggering opportunities as possible, achieving an optimal trade-off between accompanying route effectiveness and computational cost.

[0167] As described above, this embodiment can determine the target navigation route from the starting position to the ending position of the target object. The target navigation route includes at least one road segment and a road intersection, and each road intersection connects at least two road segments. From the road intersections of the target navigation route, at least one accompanying route triggering intersection is determined. Based on the accompanying route triggering intersection and the ending position, at least one candidate accompanying route is obtained. Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route, route transfer probability information corresponding to each candidate accompanying route is determined. Based on the route transfer probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain a sorting result. Based on the sorting result, a target accompanying route recommended to the target object is selected from the candidate accompanying routes. The route transfer probability information in this application can provide a quantitative description of route quality, which can improve the quality of the selected target accompanying routes.

[0168] Based on the method described in the preceding embodiments, the following will provide a more detailed explanation by taking the specific integration of the route recommendation device into the server as an example.

[0169] This application provides a route recommendation method, such as... Figure 2 As shown, the specific process of this route recommendation method can be summarized as follows:

[0170] 201. The server determines the target navigation route from the starting position to the ending position of the target object, and the target navigation route includes at least one road segment and road intersections connecting the road segments.

[0171] The target object can be a vehicle or other means of transportation, or it can be an object undergoing route navigation. The starting position can be the beginning of the target navigation route, and the ending position can be the end of the target navigation route. The starting and ending positions can be set by the target object itself.

[0172] The target navigation route can consist of at least one road segment. A road segment can be the smallest data unit describing a road, specifically represented by a link. A link can be viewed as a set of structured data, including but not limited to attributes such as the link's length, width, and road classification. Specifically, a road segment can be a segment between two road intersections.

[0173] The accompanying route can be a better route discovered by the system in real time during navigation, and this route is provided to the user as an accompanying route for reference. Specifically, in this embodiment, the accompanying route refers to a route that starts at the intersection triggered by the corresponding accompanying route and ends at the end of the target navigation route. By displaying the accompanying route on the navigation page, the user can quickly determine the subsequent direction of travel.

[0174] 202. The server determines at least one accompanying route trigger intersection from the road intersections of the target navigation route.

[0175] In this embodiment, at least one dimension of the road intersections in the target navigation route can be used for transition analysis to obtain at least one accompanying route triggering intersection in the target navigation route. The accompanying route triggering intersection can be a road intersection that triggers an accompanying route calculation request.

[0176] Optionally, in this embodiment, the step "determining at least one accompanying route trigger intersection from the road intersections of the target navigation route" may include:

[0177] Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object, the transfer probability between every two adjacent road segments in the target navigation route is calculated.

[0178] Based on the transition probability, at least one accompanying route trigger intersection is determined from the road intersections of the target navigation route.

[0179] Optionally, in this embodiment, the step "calculating the transfer probability between every two adjacent road segments in the target navigation route based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object" may include:

[0180] The frequency of transfers between every two adjacent road segments in the historical driving route corresponding to the historical object is statistically analyzed, and the endpoint of the historical driving route is the endpoint of the target navigation route.

[0181] Based on the transfer frequency information between each two adjacent road segments in the target navigation route, calculate the transfer probability between each two adjacent road segments in the target navigation route.

[0182] Optionally, in this embodiment, the step "determining at least one accompanying route trigger intersection from the road intersections of the target navigation route" may include:

[0183] Obtain at least one candidate route from the starting position to the ending position, wherein the candidate route does not include the target navigation route;

[0184] The road intersections of the candidate route and the road intersections of the target navigation route are compared and processed to determine the diverging road intersections of the candidate route and the target navigation route;

[0185] Based on the diverging road intersections, at least one accompanying route trigger intersection is determined in the target navigation route.

[0186] In some embodiments, the first road intersection in the target navigation route that diverges from the candidate route can be used as the trigger intersection for the accompanying route.

[0187] Optionally, in this embodiment, the step of "comparing the road intersections of the candidate route and the road intersections of the target navigation route to determine the diverging road intersections of the candidate route and the target navigation route" may include:

[0188] Based on the route attribute information of the candidate routes in at least one dimension, target candidate routes corresponding to each dimension are selected from the candidate routes;

[0189] The road intersections of the target candidate route and the road intersections of the target navigation route are compared and processed to determine the diverging road intersections of the target candidate route and the target navigation route.

[0190] Among them, route attribute information in at least one dimension may include mileage, travel time, congestion, road width, and whether it is a popular route.

[0191] Optionally, in this embodiment, the step "determining at least one accompanying route trigger intersection from the road intersections of the target navigation route" may include:

[0192] By performing a deviation behavior analysis on the historical driving routes corresponding to the historical objects, the frequency information of deviation behavior at each road intersection in the historical driving routes is obtained.

[0193] Based on the frequency information, the target deviation road intersection is determined from each road intersection of the historical driving route;

[0194] If the road intersection in the target navigation route is a target deviation road intersection, the road intersection will be selected as the accompanying route trigger intersection of the target navigation route.

[0195] Among them, road intersections where the frequency of deviation behavior is higher than a preset value can be identified as target deviation road intersections. This preset value can be set according to the actual situation.

[0196] 203. If the distance between the real-time location of the target object and the intersection of the accompanying route triggering point meets the route recommendation triggering condition, the server obtains at least one candidate accompanying route based on the intersection of the accompanying route triggering point and the destination location.

[0197] The route recommendation triggering conditions can be set according to actual conditions, and this embodiment does not impose any restrictions on them. For example, the route recommendation triggering condition can be that the distance between the real-time location of the target object and the intersection where the accompanying route is triggered is less than a preset value, which can be set according to actual conditions; another example is that the next road intersection corresponding to the real-time location of the target object is the intersection where the accompanying route is triggered, etc.

[0198] The starting point of the candidate accompanying route can be the corresponding accompanying route trigger intersection, and the ending point is the end point of the target navigation route.

[0199] 204. The server counts the transfer frequency information between every two adjacent road segments in the historical driving route corresponding to the historical object, and the end point of the historical driving route is the end point of the target navigation route.

[0200] 205. The server calculates the transfer probability between each pair of adjacent road segments in each candidate accompanying route based on the transfer frequency information between each pair of adjacent road segments in each candidate accompanying route.

[0201] Specifically, the transfer frequency information between each pair of adjacent road segments in each candidate accompanying route can be obtained by querying the transfer frequency information between each pair of adjacent road segments in the historical driving route.

[0202] 206. The server fuses the transition probabilities between every two adjacent road segments in each of the candidate accompanying routes to obtain the route transition probability information corresponding to each candidate accompanying route.

[0203] Among them, route transition probability information can be regarded as route-level transition probability, which can be used for quantitative evaluation of route quality.

[0204] There are various ways to fuse the transition probabilities between every two adjacent road segments in the candidate accompanying routes, and this embodiment does not limit this. For example, the fusion method can be various mathematical operations, such as standard deviation calculation and square root calculation.

[0205] 207. Based on the route transition probability information corresponding to the candidate accompanying routes, the server selects a target accompanying route from the candidate accompanying routes for recommendation to the target object.

[0206] In some embodiments, candidate accompanying routes with route transition probability information less than a preset value can be used as target accompanying routes; in other embodiments, candidate accompanying routes can be sorted according to the magnitude of route transition probability information, such as sorting them in descending order from smallest to largest, to obtain sorted candidate accompanying routes, and the first n routes in the sorted candidate accompanying routes can be used as target accompanying routes.

[0207] Optionally, in this embodiment, the step "selecting a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the route transition probability information corresponding to the candidate accompanying routes" may include:

[0208] The route attribute information of the candidate accompanying route in at least one dimension is compared with the route attribute information of the remaining navigation routes corresponding to the target navigation route in at least one dimension to obtain a first comparison result;

[0209] Based on the first comparison result and the route transition probability information corresponding to the candidate accompanying routes, a target accompanying route is selected from the candidate accompanying routes for recommendation to the target object.

[0210] Optionally, in this embodiment, the step "selecting a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the first comparison result and the route transition probability information corresponding to the candidate accompanying routes" may include:

[0211] Based on the first comparison result, a target candidate accompanying route is selected from the candidate accompanying routes;

[0212] Based on the route transition probability information corresponding to the target candidate accompanying route, the target candidate accompanying route is traversed.

[0213] If the route attribute information of the traversed target candidate accompanying route in at least one dimension meets the preset quality conditions, the target candidate accompanying route is selected as the target accompanying route to be recommended to the target object.

[0214] Based on the first comparison result, candidate accompanying routes with route defects can be filtered out, and candidate accompanying routes without obvious defects can be selected as target candidate accompanying routes. Then, the target candidate accompanying routes are traversed according to the route transition probability information. Specifically, the target candidate accompanying routes can be sorted in descending order according to the route transition probability information to obtain a sequence of target candidate accompanying routes, and then the target candidate accompanying routes in the sequence are traversed sequentially.

[0215] Optionally, in this embodiment, the step "if the route attribute information of the traversed target candidate accompanying route in at least one dimension meets the preset quality conditions, select the target candidate accompanying route as the target accompanying route to recommend to the target object" may include:

[0216] The route attribute information of the traversed target candidate accompanying route in at least one dimension is compared with the route attribute information of the remaining navigation route corresponding to the target navigation route in at least one dimension to obtain a second comparison result;

[0217] If the second comparison result meets the preset quality conditions, the traversed target candidate accompanying routes are selected as target accompanying routes to be recommended to the target object.

[0218] In this embodiment, the remaining navigation routes of the target navigation route can be compared with the target candidate accompanying route based on some key route attribute information. By comparing the comparison, routes with obvious advantages can be selected as target accompanying routes. Moreover, the target accompanying routes obtained in this way have advantages in a certain key route characteristics and have good interpretability.

[0219] As can be seen from the above, this embodiment can determine the target navigation route from the starting position to the ending position of the target object through the server. The target navigation route includes at least one road segment and road intersections connecting the road segments. From the road intersections of the target navigation route, at least one accompanying route triggering intersection is determined. If the distance between the real-time position of the target object and the accompanying route triggering intersection meets the route recommendation triggering condition, at least one candidate accompanying route is obtained based on the accompanying route triggering intersection and the ending position. The transfer frequency information between every two adjacent road segments in the historical driving route corresponding to the historical object is statistically analyzed, and the ending position of the historical driving route is the ending position of the target navigation route. Based on the transfer frequency information between every two adjacent road segments in each candidate accompanying route, the transfer probability between every two adjacent road segments in each candidate accompanying route is calculated. The transfer probabilities between every two adjacent road segments in each candidate accompanying route are fused to obtain the route transfer probability information corresponding to each candidate accompanying route. Based on the route transfer probability information corresponding to the candidate accompanying routes, a target accompanying route for recommendation to the target object is selected from the candidate accompanying routes. The route transition probability information in this application can provide a quantitative description of route quality, which can improve the quality of the selected target-accompanying routes.

[0220] To better implement the above methods, embodiments of this application also provide a route recommendation device, such as... Figure 3As shown, the route recommendation device may include a first determining unit 301, a second determining unit 302, an acquiring unit 303, a third determining unit 304, a sorting unit 305, and a selection unit 306, as follows:

[0221] (1) First determining unit 301;

[0222] The first determining unit is used to determine the target navigation route of the target object from the starting position to the ending position. The target navigation route includes at least one road segment and a road intersection, and one road intersection connects at least two road segments.

[0223] (2) Second determining unit 302;

[0224] The second determining unit is used to determine at least one accompanying route trigger intersection from the road intersections of the target navigation route.

[0225] Optionally, in some embodiments of this application, the second determining unit may be specifically used to determine the yaw probability at the road intersection based on at least one driving route including the road intersection, and to determine at least one accompanying route triggering intersection from the road intersection based on the yaw probability, wherein the yaw probability is used to indicate the probability that the target object will move to a non-target navigation route at the road intersection.

[0226] Optionally, in some embodiments of this application, the second determining unit may include a first calculation subunit and a first determining subunit, as follows:

[0227] The first calculation subunit is used to calculate the transfer probability of the target object transferring to the road segment of the target navigation route at the road intersection based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object, wherein the historical driving route includes the road intersection;

[0228] The first determining subunit is configured to determine at least one accompanying route trigger intersection from the road intersections of the target navigation route based on the transition probability.

[0229] Optionally, in some embodiments of this application, the second determining unit may include a route acquisition subunit, a comparison subunit, and a second determining subunit, as follows:

[0230] The route acquisition subunit is used to acquire at least one candidate route from the starting position to the ending position, wherein the candidate route is a non-target navigation route;

[0231] The comparison subunit is used to compare the road intersections of the candidate route and the road intersections of the target navigation route to determine the diverging road intersections of the candidate route and the target navigation route.

[0232] The second determining subunit is used to determine at least one accompanying route triggering intersection in the target navigation route based on the branching road intersection.

[0233] Optionally, in some embodiments of this application, the comparison subunit may be specifically used to select target candidate routes corresponding to each dimension from the candidate routes based on the route attribute information of the candidate routes in at least one dimension; compare the road intersections of the target candidate routes and the road intersections of the target navigation routes to determine the diverging road intersections of the target candidate routes and the target navigation routes.

[0234] Optionally, in some embodiments of this application, the second determining unit may include an analysis subunit, a third determining subunit, and a first selecting subunit, as follows:

[0235] The analysis subunit is used to perform deviation behavior analysis on the historical driving route corresponding to the historical object, and obtain the frequency information of deviation behavior at each road intersection in the historical driving route.

[0236] The third determining subunit is used to determine the target deviation road intersection from each road intersection of the historical driving route based on the frequency information.

[0237] The first selection subunit is used to select the road intersection as the accompanying route trigger intersection of the target navigation route if the road intersection in the target navigation route belongs to the target deviation road intersection.

[0238] (3) Obtain unit 303;

[0239] The acquisition unit is used to acquire at least one candidate accompanying route based on the accompanying route trigger intersection and the destination location.

[0240] Optionally, in some embodiments of this application, the acquisition unit may be specifically used to acquire at least one candidate accompanying route based on the accompanying route triggering intersection and the destination location if the distance between the real-time location of the target object and the accompanying route triggering intersection meets the route recommendation triggering condition.

[0241] (4) Third determining unit 304;

[0242] The third determining unit is used to determine the route transfer probability information corresponding to each candidate accompanying route based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route.

[0243] Optionally, in some embodiments of this application, the third determining unit may include a statistical subunit, a second calculation subunit, and a fusion subunit, as follows:

[0244] The statistical subunit is used to count the transfer frequency information between every two adjacent road segments in the historical driving route corresponding to the historical object, and the end point of the historical driving route is the end point of the target navigation route.

[0245] The second calculation subunit is used to calculate the transfer probability between each pair of adjacent road segments in each candidate accompanying route based on the transfer frequency information between each pair of adjacent road segments in each candidate accompanying route.

[0246] The fusion subunit is used to fuse the transition probabilities between every two adjacent road segments in each of the candidate accompanying routes to obtain the route transition probability information corresponding to each of the candidate accompanying routes.

[0247] (5) Sorting unit 305;

[0248] The sorting unit is used to sort the candidate accompanying routes based on the route transition probability information corresponding to the candidate accompanying routes, and obtain the sorting result.

[0249] (6) Select unit 306;

[0250] The selection unit is used to select a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the sorting result.

[0251] Optionally, in some embodiments of this application, the sorting unit may include a comparison subunit and a sorting subunit, as follows:

[0252] The comparison subunit is used to compare the route attribute information of the candidate accompanying route in at least one dimension with the route attribute information of the remaining navigation route corresponding to the target navigation route in at least one dimension to obtain a first comparison result.

[0253] The sorting subunit is used to sort the candidate accompanying routes according to the first comparison result and the route transition probability information corresponding to the candidate accompanying routes, so as to obtain the sorting result.

[0254] Optionally, in some embodiments of this application, the sorting subunit may be specifically used to select a target candidate accompanying route from the candidate accompanying routes based on the first comparison result; and to sort the target candidate accompanying routes based on the route transition probability information corresponding to the target candidate accompanying route to obtain a sorting result.

[0255] The selection unit may include a traversal sub-unit and a second selection sub-unit, as follows:

[0256] The traversal subunit is used to traverse the target candidate accompanying route based on the sorting result;

[0257] The second selection subunit is used to select the target candidate accompanying route as the target accompanying route to recommend to the target object if the route attribute information of the traversed target candidate accompanying route in the at least one dimension meets the preset quality conditions.

[0258] Optionally, in some embodiments of this application, the second selection subunit may be specifically used to compare the route attribute information of the traversed target candidate accompanying routes in at least one dimension with the route attribute information of the remaining navigation routes corresponding to the target navigation route in at least one dimension to obtain a second comparison result; if the second comparison result meets a preset quality condition, the traversed target candidate accompanying routes are selected as target accompanying routes to be recommended to the target object.

[0259] Optionally, in some embodiments of this application, the route recommendation device may further include a switching unit, as follows:

[0260] The switching unit is configured to respond to a navigation switching command for the target object to switch to the target accompanying route. If the target object reaches the accompanying route trigger intersection corresponding to the target accompanying route, the accompanying route trigger intersection corresponding to the target accompanying route is used as the new starting position, and the target accompanying route is used as the new target navigation route; and return to the step of determining at least one accompanying route trigger intersection from the road intersections of the target navigation route.

[0261] As can be seen from the above, in this embodiment, the first determining unit 301 determines the target navigation route from the starting position to the ending position of the target object. The target navigation route includes at least one road segment and a road intersection, and one road intersection connects at least two road segments. The second determining unit 302 determines at least one accompanying route triggering intersection from the road intersections of the target navigation route. The obtaining unit 303 obtains at least one candidate accompanying route based on the accompanying route triggering intersection and the ending position. The third determining unit 304 determines the route transfer probability information corresponding to each candidate accompanying route based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route. The sorting unit 305 sorts the candidate accompanying routes based on the route transfer probability information corresponding to the candidate accompanying routes to obtain a sorting result. The selection unit 306 selects the target accompanying route recommended to the target object from the candidate accompanying routes according to the sorting result. The route transfer probability information in this application can provide a quantitative description of route quality, which can improve the quality of the selected target accompanying routes.

[0262] This application also provides an electronic device, such as... Figure 4 The diagram shows a structural schematic of an electronic device involved in an embodiment of this application. This electronic device can be a terminal or a server, specifically:

[0263] The electronic device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0264] The processor 401 is the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes various functions and processes data by running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0265] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0266] The electronic device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0267] The electronic device may also include an input unit 404, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0268] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, as follows:

[0269] The system determines a target navigation route from the starting position to the ending position of the target object. The target navigation route includes at least one road segment and a road intersection, with each road intersection connecting at least two road segments. From the road intersections of the target navigation route, at least one accompanying route triggering intersection is determined. Based on the accompanying route triggering intersection and the ending position, at least one candidate accompanying route is obtained. Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route, route transfer probability information corresponding to each candidate accompanying route is determined. Based on the route transfer probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain a sorting result. Based on the sorting result, a target accompanying route recommended to the target object is selected from the candidate accompanying routes.

[0270] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0271] As described above, this embodiment can determine the target navigation route from the starting position to the ending position of the target object. The target navigation route includes at least one road segment and a road intersection, and each road intersection connects at least two road segments. From the road intersections of the target navigation route, at least one accompanying route triggering intersection is determined. Based on the accompanying route triggering intersection and the ending position, at least one candidate accompanying route is obtained. Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route, route transfer probability information corresponding to each candidate accompanying route is determined. Based on the route transfer probability information corresponding to the candidate accompanying routes, a target accompanying route recommended to the target object is selected from the candidate accompanying routes. The route transfer probability information in this application can provide a quantitative description of route quality, which can improve the quality of the selected target accompanying routes.

[0272] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0273] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the route recommendation methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0274] The system determines a target navigation route from the starting position to the ending position of the target object. The target navigation route includes at least one road segment and a road intersection, with each road intersection connecting at least two road segments. From the road intersections of the target navigation route, at least one accompanying route triggering intersection is determined. Based on the accompanying route triggering intersection and the ending position, at least one candidate accompanying route is obtained. Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route, route transfer probability information corresponding to each candidate accompanying route is determined. Based on the route transfer probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain a sorting result. Based on the sorting result, a target accompanying route recommended to the target object is selected from the candidate accompanying routes.

[0275] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0276] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0277] Since the instructions stored in the computer-readable storage medium can execute the steps in any of the route recommendation methods provided in the embodiments of this application, the beneficial effects that any of the route recommendation methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0278] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in various alternative implementations of the above-described route recommendation aspect.

[0279] The above provides a detailed description of a route recommendation method and related equipment provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A route recommendation method, characterized in that, include: Determine a target navigation route from the starting position to the ending position of the target object, wherein the target navigation route includes at least one road segment and a road intersection, and one road intersection connects at least two road segments; Based on at least one driving route including the road intersection, a yaw probability is determined at the road intersection, and at least one accompanying route trigger intersection is determined from the road intersection based on the yaw probability, wherein the yaw probability is used to indicate the probability that the target object will move to a non-target navigation route at the road intersection. Based on the intersection triggered by the accompanying route and the destination location, at least one candidate accompanying route is obtained; Based on the transfer relationships between road segments in the historical driving routes corresponding to the historical objects, and the road segments in each candidate accompanying route, determine the route transfer probability information corresponding to each candidate accompanying route; Based on the route transition probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain the sorting result; Based on the sorting results, a target accompanying route is selected from the candidate accompanying routes for recommendation to the target object.

2. The method according to claim 1, characterized in that, The step of obtaining at least one candidate accompanying route based on the accompanying route trigger intersection and the destination location includes: If the distance between the real-time location of the target object and the intersection triggering the accompanying route meets the route recommendation triggering condition, at least one candidate accompanying route is obtained based on the intersection triggering the accompanying route and the destination location.

3. The method according to claim 1, characterized in that, The step of determining a yaw probability at a road intersection based on at least one travel route including the road intersection, and determining at least one accompanying route trigger intersection from the road intersections based on the yaw probability, includes: Based on the transfer relationships between road segments in the historical driving route corresponding to the historical object, the transfer probability of the target object being transferred to the road segment of the target navigation route at the road intersection is calculated, wherein the historical driving route includes the road intersection; Based on the transition probability, at least one accompanying route trigger intersection is determined from the road intersections of the target navigation route.

4. The method according to claim 1, characterized in that, The step of determining a yaw probability at a road intersection based on at least one travel route including the road intersection, and determining at least one accompanying route trigger intersection from the road intersections based on the yaw probability, includes: Obtain at least one candidate route from the starting position to the ending position, wherein the candidate route is a non-target navigation route; The road intersections of the candidate route and the road intersections of the target navigation route are compared and processed to determine the diverging road intersections of the candidate route and the target navigation route; Based on the diverging road intersections, at least one accompanying route trigger intersection is determined in the target navigation route.

5. The method according to claim 4, characterized in that, The process of comparing the road intersections of the candidate route and the road intersections of the target navigation route to determine the diverging road intersections of the candidate route and the target navigation route includes: Based on the route attribute information of the candidate routes in at least one dimension, target candidate routes corresponding to each dimension are selected from the candidate routes; The road intersections of the target candidate route and the road intersections of the target navigation route are compared and processed to determine the diverging road intersections of the target candidate route and the target navigation route.

6. The method according to claim 1, characterized in that, The step of determining a yaw probability at a road intersection based on at least one travel route including the road intersection, and determining at least one accompanying route trigger intersection from the road intersections based on the yaw probability, includes: By performing a deviation behavior analysis on the historical driving routes corresponding to the historical objects, the frequency information of deviation behavior at each road intersection in the historical driving routes is obtained. Based on the frequency information, the target deviation road intersection is determined from each road intersection of the historical driving route; If the road intersection in the target navigation route is a target deviation road intersection, the road intersection will be selected as the accompanying route trigger intersection of the target navigation route.

7. The method according to claim 1, characterized in that, The method of determining route transfer probability information for each candidate accompanying route based on the transfer relationships between road segments in the historical driving route corresponding to the historical object, and the road segments in each candidate accompanying route, includes: The frequency of transitions between every two adjacent road segments in the historical driving route corresponding to the historical object is statistically analyzed, and the endpoint of the historical driving route is the endpoint of the target navigation route. Based on the transfer frequency information between each pair of adjacent road segments in each candidate accompanying route, calculate the transfer probability between each pair of adjacent road segments in each candidate accompanying route. The transition probabilities between every two adjacent road segments in each candidate accompanying route are fused to obtain the route transition probability information corresponding to each candidate accompanying route.

8. The method according to claim 1, characterized in that, The process of ranking the candidate accompanying routes based on the route transition probability information corresponding to the candidate accompanying routes to obtain a ranking result includes: The route attribute information of the candidate accompanying route in at least one dimension is compared with the route attribute information of the remaining navigation routes corresponding to the target navigation route in at least one dimension to obtain a first comparison result; Based on the first comparison result and the route transition probability information corresponding to the candidate accompanying routes, the candidate accompanying routes are sorted to obtain the sorting result.

9. The method according to claim 8, characterized in that, The step of sorting the candidate accompanying routes based on the first comparison result and the route transition probability information corresponding to the candidate accompanying routes to obtain a sorting result includes: Based on the first comparison result, a target candidate accompanying route is selected from the candidate accompanying routes; Based on the route transition probability information corresponding to the target candidate accompanying routes, the target candidate accompanying routes are sorted to obtain the sorting result; The step of selecting a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the sorting result includes: Based on the sorting results, the target candidate accompanying routes are traversed; If the route attribute information of the traversed target candidate accompanying route in at least one dimension meets the preset quality conditions, the target candidate accompanying route is selected as the target accompanying route to be recommended to the target object.

10. The method according to claim 9, characterized in that, If the route attribute information of the traversed target candidate accompanying route in at least one dimension meets a preset quality condition, the target candidate accompanying route is selected as the target accompanying route to be recommended to the target object, including: The route attribute information of the traversed target candidate accompanying route in at least one dimension is compared with the route attribute information of the remaining navigation route corresponding to the target navigation route in at least one dimension to obtain a second comparison result; If the second comparison result meets the preset quality conditions, the traversed target candidate accompanying routes are selected as target accompanying routes to be recommended to the target object.

11. The method according to claim 1, characterized in that, After selecting a target accompanying route from the candidate accompanying routes based on the sorting result, the method further includes: In response to a navigation switching command that the target object switches to the target accompanying route, if the target object reaches the accompanying route trigger intersection corresponding to the target accompanying route, the accompanying route trigger intersection corresponding to the target accompanying route is taken as the new starting position, and the target accompanying route is taken as the new target navigation route. Return to the step of determining at least one accompanying route trigger intersection from the road intersections of the target navigation route.

12. A route recommendation device, characterized in that, include: The first determining unit is used to determine the target navigation route of the target object from the starting position to the ending position. The target navigation route includes at least one road segment and a road intersection, and one road intersection connects at least two road segments. The second determining unit is configured to determine a yaw probability at the road intersection based on at least one driving route including the road intersection, and to determine at least one accompanying route triggering intersection from the road intersection based on the yaw probability, wherein the yaw probability is used to indicate the probability that the target object will move to a non-target navigation route at the road intersection. The acquisition unit is used to acquire at least one candidate accompanying route based on the intersection triggered by the accompanying route and the destination location; The third determining unit is used to determine the route transfer probability information corresponding to each candidate accompanying route based on the transfer relationship between each road segment in the historical driving route corresponding to the historical object and the road segments in each candidate accompanying route. The sorting unit is used to sort the candidate accompanying routes based on the route transition probability information corresponding to the candidate accompanying routes, and obtain the sorting result; The selection unit is used to select a target accompanying route from the candidate accompanying routes for recommendation to the target object based on the sorting result.

13. An electronic device, characterized in that, It includes a memory and a processor; the memory stores an application program, and the processor runs the application program within the memory to perform the operations in the route recommendation method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to perform the steps of the route recommendation method according to any one of claims 1 to 11.

15. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the route recommendation method according to any one of claims 1 to 11.

Images