A method, device, navigation server and storage medium for determining a recommended route

Abstract

The embodiment of the present application provides a method, device, navigation server and storage medium for determining a recommended route, wherein the method includes: obtaining multiple routes from a first location to a second location; performing a first sorting on the multiple routes at least according to a first driving index, and determining the route ranked first in the first sorting as a main route; selecting at least one alternative route from the multiple routes whose second driving index is better than the main route, and whose comprehensive driving index is not lower than the route that has the same ranking as the alternative route in the recommended route in the first sorting; wherein the main route and the alternative route form a recommended route, the first driving index is different from the second driving index, and the comprehensive driving index includes a combination of multiple driving indexes. The embodiment of the present application can increase the diversity of alternative routes, so that users have a variety of optional routes when selecting a navigation route, so as to facilitate users to select a navigation route.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of navigation technology, and specifically to a method and device for determining a recommended route, a navigation server, and a storage medium. Background Art

[0002] When a user requests navigation service, the navigation service can select multiple recommended routes from all routes from the starting location to the end location, and provide the multiple recommended routes to the user so that the user can select a navigation route from the multiple recommended routes; currently, all routes from the starting location to the end location are mainly sorted based on a certain set driving indicator (such as estimated driving time, driving distance, etc.), so as to select multiple routes with the highest sorting as recommended routes and provide them to the user. The selected multiple recommended routes can be considered as multiple routes with the best set driving indicators among all routes from the starting location to the end location, among which the recommended route ranked first among the selected multiple recommended routes is called the main route, and the remaining recommended routes are called alternative routes.

[0003] The above method selects a recommended route based on a certain set driving indicator, which makes the dimension in which the user can compare the alternative routes and the main route in the recommended route relatively single, resulting in that it is not convenient for the user to select a navigation route from the recommended routes; therefore, how to provide an improved recommended route determination scheme to increase the diversity of recommended routes so that users have a variety of routes to choose from when selecting a navigation route has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a recommended route determination method, device, navigation server and storage medium to increase the diversity of recommended routes, so that users have a variety of routes to choose from when selecting a navigation route, providing a basis for facilitating users to select a navigation route from the recommended routes.

[0005] To achieve the above objectives, the present application provides the following technical solutions:

[0006] A method for determining a recommended route, comprising:

[0007] Obtain multiple routes from a first location to a second location;

[0008] performing a first sorting of the plurality of routes at least according to the first driving index, and determining a route ranked first in the first sorting as a main route;

[0009] At least one alternative route having a second driving index better than that of the main route is selected from the multiple routes, and the comprehensive driving index of the alternative route is not lower than that of a route having the same ranking as that of the alternative route in the recommended route in the first ranking; wherein the main route and the alternative route form a recommended route, the first driving index is different from the second driving index, and the comprehensive driving index includes a combination of multiple driving indexes.

[0010] The present application also provides a recommended route determination device, including:

[0011] A route acquisition module, used to acquire multiple routes from a first location to a second location;

[0012] A main route determination module, configured to perform a first sorting of the plurality of routes at least according to the first driving index, and determine the route ranked first in the first sorting as the main route;

[0013] An alternative route determination module is used to select at least an alternative route whose second driving index is better than that of the main route from the multiple routes, and the comprehensive driving index of the alternative route is not lower than that of the route that has the same ranking as the alternative route in the recommended route in the first sorting; wherein the main route and the alternative route form a recommended route, the first driving index is different from the second driving index, and the comprehensive driving index includes a combination of multiple driving indicators.

[0014] An embodiment of the present application also provides a navigation server, comprising: at least one memory and at least one processor, the memory storing one or more computer executable instructions, and the processor calling the one or more computer executable instructions to execute the recommended route determination method as described above.

[0015] An embodiment of the present application also provides a storage medium, which stores one or more computer-executable instructions, and the one or more computer-executable instructions are used to execute the recommended route determination method as described above.

[0016] The recommended route determination method provided in the embodiment of the present application can obtain multiple routes from the first position to the second position, and perform a first sorting on the multiple routes at least according to the first driving index, so as to determine the route ranked first in the first sorting as the main route; since the recommended route is formed by the main route and the alternative route, in order to increase the diversity of the recommended routes, the embodiment of the present application can select at least an alternative route whose second driving index is better than the main route from the multiple routes, so that the determined alternative route can compensate for the main route at the second driving index level, wherein the first driving index is different from the second driving index; further, in order to ensure the driving experience of the alternative route, the comprehensive driving index of the alternative route determined in the embodiment of the present application is not lower than that of the route with the same ranking as the alternative route in the recommended route in the first sorting, wherein the comprehensive driving index includes a comprehensive number of driving indicators. It can be seen that, in the case where the main route is selected at least according to the first driving index, the alternative route determined by the embodiment of the present application can compensate for the main route at least at the second driving index level, thereby reflecting the difference between the alternative route and the main route, increasing the diversity of the recommended route, so that the user has a variety of routes to choose from when selecting a navigation route, and the driving experience of the alternative route determined by the embodiment of the present application is not worse than the route that has the same ranking as the alternative route in the recommended route in the first sorting, which can ensure the rationality of the alternative route determined by the embodiment of the present application. The recommended route determination method provided by the embodiment of the present application can increase the diversity of the recommended route, so that the user has a variety of routes to choose from when selecting a navigation route, and provide a basis for facilitating the user to select a navigation route from the recommended routes. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0018] Figure 1 Example diagram for determining recommended routes for existing technologies;

[0019] Figure 2 A sample image showing the recommended route on the navigation planning page;

[0020] Figure 3 A flowchart of a method for determining a recommended route provided in an embodiment of the present application;

[0021] Figure 4 Another flow chart of the method for determining a recommended route provided in an embodiment of the present application;

[0022] Figure 5 An example diagram for determining a first alternative route provided in an embodiment of the present application;

[0023] Figure 6 An example diagram for determining a second alternative route provided in an embodiment of the present application;

[0024] Figure 7 An example diagram of using a model to determine alternative routes provided in an embodiment of the present application;

[0025] Figure 8 A training flow chart of the first sorting model provided in an embodiment of the present application;

[0026] Fig. 9 An example diagram of the model training target provided in the embodiment of the present application;

[0027] Fig.10 An example diagram of the loss function provided in the embodiment of the present application;

[0028] Fig.11 Another process of the method for determining a recommended route provided in an embodiment of the present application;

[0029] Fig.12 A training flow chart of a second sorting model provided in an embodiment of the present application;

[0030] Fig.13 A flowchart for obtaining a second alternative route provided in an embodiment of the present application;

[0031] Fig.14 This is an example diagram of compensation force defined in the embodiment of the present application;

[0032] Fig.15 An example diagram of the compensation intensity of the estimated driving time provided in an embodiment of the present application;

[0033] Fig.16 This is an example of the nonlinear relationship between the number of traffic lights and the increase of route distance;

[0034] Fig.17 Another example of the nonlinear relationship between the number of traffic lights and the increase of route distance;

[0035] Fig.18 Schematic diagram of the process for determining the recommended route;

[0036] Fig.19 A block diagram of a device for determining a recommended route provided in an embodiment of the present application;

[0037] Fig. 20 Another block diagram of the recommended route determination device provided in an embodiment of the present application;

[0038] Fig.21Another block diagram of the recommended route determination device provided in an embodiment of the present application;

[0039] Fig. 22 Another block diagram of the recommended route determination device provided in an embodiment of the present application;

[0040] Fig.23 Yet another block diagram of a device for determining a recommended route provided in an embodiment of the present application;

[0041] Fig.24 A block diagram of a navigation server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] When the user deviates from the route before or during navigation, the user needs to request navigation service. At this time, the navigation service can provide multiple recommended routes to the user so that the user can select a navigation route from the multiple recommended routes. For example, taking the case where the user requests navigation service before navigation starts, the navigation service can determine all routes from the starting point to the end point based on the starting point and the end point carried in the navigation request. Assuming that there are n routes, the navigation service can use the main route sorting model to sort the n routes based on a certain set driving index to obtain the sorting of route 1 to route n, thereby selecting multiple routes with the highest sorting (i.e., multiple routes with the best set driving index) as recommended routes to provide to the user. The set driving index can be pre-set according to actual conditions, or can be set by the user, for example, the driving index is set to a certain driving index such as the estimated driving time, driving distance, congestion level, etc.

[0043] Specifically, for example, 3 recommended routes are provided to the user, and the driving indicator is set to the estimated driving time. Figure 1 As shown, after the navigation server determines the n routes from the starting point to the end point, it can use the main route sorting model to sort the n routes in the order of the estimated travel time from small to large, so as to sort the top three routes with the smallest estimated travel time (such as Figure 1 Route 1, Route 2 and Route 3) are provided to the user as recommended routes; the route ranked first among the three recommended routes is called the main route, and the other recommended routes are called alternative routes. Specifically, the route ranked second among the recommended routes is called the first alternative route, and the route ranked third is called the second alternative route. Figure 2 The following example shows how to display three recommended routes on the navigation planning page. You can refer to it.

[0044] The recommended route in the above method is selected based on a certain set driving index (such as Figure 1In the example, the recommended route is selected based on the estimated travel time), which makes the dimension of the alternative route in the recommended route and the main route available for users to compare relatively single, and the user does not have a variety of routes to choose from when selecting a navigation route, which is not convenient for the user to select a navigation route from the recommended routes. Based on this, the embodiment of the present application provides an improved recommended route determination scheme to increase the diversity of recommended routes, so that users have a variety of routes to choose from when selecting a navigation route, and provide a basis for facilitating users to select a navigation route from the recommended routes.

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] In an optional implementation, Figure 3 The optional process of the method for determining a recommended route provided in an embodiment of the present application is shown. The method process can be executed by a navigation server. Optionally, the navigation server can, in the navigation planning stage before the navigation starts, Figure 3 The process shown in the figure determines the recommended route. It can also be used to determine the recommended route when deviation occurs during navigation and re-navigation is required. Figure 3 The process shown determines the recommended route; Figure 3 As shown, the method flow may include:

[0047] Step S100: Acquire multiple routes from a first location to a second location.

[0048] Optionally, in the navigation planning stage before navigation starts, the first position may be the starting position set by the user, and the second position may be the end position set by the user; when re-navigating during the navigation process, the first position may be the current position of the vehicle, and the second position may be the end position set by the user.

[0049] After determining the first location and the second location, in an optional implementation, the navigation service may obtain multiple routes from the first location to the second location based on the connectivity of roads in the road network. If the multiple routes are all routes in the road network that can reach the second location from the first location, the embodiment of the present application needs to determine a recommended route provided to the user from the multiple routes, that is, determine a main route and alternative routes from the multiple routes.

[0050] Step S110: performing a first sorting on the plurality of routes at least according to the first driving index, and determining the route ranked first in the first sorting as the main route.

[0051] As described above, the main route is the route ranked first among the recommended routes provided to the user by the navigation service. In the embodiment of the present application, after determining multiple routes from the first location to the second location, the navigation service may perform a first sorting of the multiple routes at least according to the first driving indicator, thereby determining the route ranked first in the first sorting as the main route.

[0052] Optionally, the first driving index may be a set driving index for sorting routes in the prior art, such as an estimated driving time, driving distance, toll value, congestion level, route comfort, high speed, and other driving indexes, and the embodiment of the present application does not limit this. In an optional implementation, step S110 may sort the multiple routes at least according to the first driving index based on the main route sorting model used in the prior art, that is, the strategy for obtaining the main route from the multiple routes may use the strategy of the prior art. Of course, in addition to considering the first driving index, the embodiment of the present application may also consider other factors to sort the multiple routes for the first time, and the embodiment of the present application does not limit this.

[0053] Step S120: selecting at least one alternative route from the multiple routes whose second driving index is better than that of the main route, and whose comprehensive driving index is not lower than that of the route in the first sorting that has the same ranking as that of the alternative route in the recommended route; the main route and the alternative route form a recommended route.

[0054] After determining the main route from the multiple routes based on step S110, the embodiment of the present application can determine alternative routes from the multiple routes except the main route. In order to increase the diversity of recommended routes, on the basis of selecting the main route based on the first driving index, the embodiment of the present application can select at least one route whose second driving index is better than the main route from the multiple routes as an alternative route based on a second driving index different from the first driving index, so that the alternative route can compensate for the main route at least in terms of the second driving index; the specific form of the second driving index can be determined according to actual conditions, for example, the second driving index can be any one of the driving indicators such as the estimated driving time, driving distance, toll value, congestion level, route comfort, high speed level, etc. that are different from the first driving index;

[0055] For example, taking the estimated driving time as the first driving indicator, after the first sorting of multiple routes from the first location to the second location based on the estimated driving time, although the main route is the route with the shortest estimated driving time that is ranked first in the first sorting, the main route is not the best in terms of other driving indicators such as driving distance and congestion level. Therefore, when selecting an alternative route, the embodiment of the present application can compensate for the shortcomings of the main route from other driving indicators except the estimated driving time; in a further example, assuming that the driving distance of the main route is not the shortest, the second driving indicator can be the driving distance. The embodiment of the present application can select at least a route with a shorter driving distance than the main route from the multiple routes as an alternative route, so that the alternative route is superior to the main route in terms of driving distance.

[0056] At the same time, since there are routes ranked after the main route in the first sorting, according to the processing of the prior art, the route ranked second in the first sorting becomes the first alternative route, and the route ranked third becomes the second alternative route. When there are more than two alternative routes, the alternative routes can be obtained by analogy. In order to make the alternative routes determined in the embodiment of the present application not worse than the alternative routes determined in the prior art in terms of driving experience, it should be ensured that the comprehensive driving index of the alternative routes determined in the embodiment of the present application is not lower than the route with the same ranking as the alternative routes in the recommended routes in the first sorting. Specifically, the comprehensive driving index of the first alternative route determined in the embodiment of the present application is not lower than the comprehensive driving index of the route ranked second in the first sorting, and the comprehensive driving index of the second alternative route determined in the embodiment of the present application is not lower than the comprehensive driving index of the route ranked third in the first sorting, thereby ensuring that the alternative routes determined in the embodiment of the present application, in addition to compensating for the main route at the second driving index level, can also be no worse than the alternative routes with the same ranking determined in the prior art in terms of driving experience.

[0057] Optionally, the comprehensive driving index may include a combination of multiple driving indexes. For example, for any route, the comprehensive driving index may be determined by combining multiple driving indexes of the route to obtain the comprehensive driving index of the route.

[0058] The recommended route determination method provided in the embodiment of the present application can obtain multiple routes from the first position to the second position, and perform a first sorting on the multiple routes at least according to the first driving index, so as to determine the route ranked first in the first sorting as the main route; since the recommended route is formed by the main route and the alternative route, in order to increase the diversity of the recommended routes, the embodiment of the present application can select at least an alternative route whose second driving index is better than the main route from the multiple routes, so that the determined alternative route can compensate for the main route at the second driving index level, wherein the first driving index is different from the second driving index; further, in order to ensure the driving experience of the alternative route, the comprehensive driving index of the alternative route determined in the embodiment of the present application is not lower than that of the route with the same ranking as the alternative route in the recommended route in the first sorting, wherein the comprehensive driving index includes a comprehensive number of driving indicators. It can be seen that, in the case where the main route is selected at least according to the first driving index, the alternative route determined by the embodiment of the present application can compensate for the main route at least at the second driving index level, thereby reflecting the difference between the alternative route and the main route, increasing the diversity of the recommended route, so that the user has a variety of routes to choose from when selecting a navigation route, and the driving experience of the alternative route determined by the embodiment of the present application is not worse than the route that has the same ranking as the alternative route in the recommended route in the first sorting, which can ensure the rationality of the alternative route determined by the embodiment of the present application. The recommended route determination method provided by the embodiment of the present application can increase the diversity of the recommended route, so that the user has a variety of routes to choose from when selecting a navigation route, and provide a basis for facilitating the user to select a navigation route from the recommended routes.

[0059] In an optional implementation, the alternative route determined by the embodiment of the present application may include a first alternative route and a second alternative route. Of course, the alternative route determined by the embodiment of the present application may be one (such as the alternative route only includes the first alternative route) or more than two, and the embodiment of the present application is not limited to this; optionally, Figure 4 Another optional process of the method for determining a recommended route provided in an embodiment of the present application is shown. Figure 4 As shown, the process may include:

[0060] Step S200: Acquire multiple routes from the first location to the second location.

[0061] Step S210: performing a first sorting on the plurality of routes at least according to the first driving index, and determining the route ranked first in the first sorting as the main route.

[0062] Optionally, the introduction of step S200 to step S210 can refer to the corresponding part of the previous text and will not be repeated here.

[0063] Step S220: determine a first alternative route from the multiple routes except the main route, wherein the comprehensive driving index of the first alternative route is not lower than the route ranked second in the first sorting, and the second driving index is better than the main route.

[0064] The first alternative route is the route ranked second in the recommended routes. According to the processing of the prior art, the route ranked second in the first sorting is used as the first alternative route. In the embodiment of the present application, in order to increase the diversity of the recommended routes and ensure the driving experience of the alternative routes determined by the embodiment of the present application, the embodiment of the present application can determine the first alternative route from the multiple routes except the main route, wherein the comprehensive driving index of the determined first alternative route is not lower than that of the route ranked second in the first sorting, and the second driving index is better than the main route.

[0065] For example, Figure 5 As shown, there are n routes from the first position to the second position. After the n routes are sorted for the first time at least according to the first driving index (such as the estimated driving time), the embodiment of the present application can obtain the sorting of routes 11 to 1n, wherein route 11 is used as the main route; according to the processing of the prior art, route 12 is used as the first alternative route, but if the main route and the first alternative route are both selected according to the first driving index, the dimension in which the user can compare the first alternative route with the main route is relatively single, and the recommended route cannot increase the diversity; to solve this problem, the embodiment of the present application can determine, from among the n-1 routes from route 12 to route 1n, a route whose comprehensive driving index is not lower than the comprehensive driving index of route 12 and whose second driving index is better than route 11 as the first alternative route;

[0066] In a further example, assuming that the first sorting is performed according to the estimated driving time, the n routes from the first position to the second position are at least sorted for the first time according to the estimated driving time. After the sorting of routes 11 to 1n is obtained, route 11 ranked first in the first sorting is used as the main route; the embodiment of the present application can determine, from the n-1 routes excluding route 11, a route whose comprehensive driving index is not lower than the comprehensive driving index of route 12, and whose second driving index except the estimated driving time is better than that of the main route 11, as the first alternative route, so that the determined first alternative route is not worse than route 12 in driving experience, and can compensate for the main route 11 in terms of the second driving index except the estimated driving time.

[0067] Step S230: Determine a second alternative route from the multiple routes except the main route and the first alternative route, wherein the comprehensive driving index of the second alternative route is not lower than the route ranked third in the first sorting, and the third driving index is better than the main route and the first alternative route; wherein the third driving index is different from the first driving index and the second driving index.

[0068] The second alternative route is the route recommended third among the recommended routes. According to the processing of the prior art, the route ranked third in the first sorting is used as the second alternative route. In the embodiment of the present application, in order to increase the diversity of the recommended routes and ensure the driving experience of the second alternative route, the embodiment of the present application, when determining the main route and the first alternative route, can determine, from the routes other than the main route and the first alternative route among the multiple routes, a route whose comprehensive driving index is not lower than the comprehensive driving index of the route ranked third in the first sorting and whose third driving index is better than that of the main route and the first alternative route, and use the route as the second alternative route. In this way, while ensuring the driving experience of the second alternative route determined in the embodiment of the present application, the second alternative route can compensate for the main route and the first alternative route at the level of the third driving index, wherein the third driving index is different from the first driving index and the second driving index.

[0069] Example, combined Figure 5 and Figure 6 As shown, assuming that the main route is 11 and the first alternative route is k, the embodiment of the present application can exclude the main route 11 and the first alternative route k from the n routes, and determine from the remaining n-2 routes a route whose comprehensive driving index is not lower than the comprehensive driving index of route 13 and whose third driving index is better than the main route 11 and the first alternative route k as the second alternative route;

[0070] In a further example, assuming that the first driving indicator is the estimated driving time and the second driving indicator is the driving distance, that is, the first alternative route compensates for the main route at the driving distance level, then the embodiment of the present application can determine, from the n-2 routes other than the main route 11 and the first alternative route k, a route whose comprehensive driving indicator is not lower than the comprehensive driving indicator of route 13, and whose third driving indicator other than the estimated driving time and driving distance is better than the main route 11 and the first alternative route k, as the second alternative route, so that the determined second alternative route is not worse than route 13 in driving experience, and can compensate for the main route 11 and the first alternative route k in terms of a certain driving indicator other than the estimated driving time and driving distance.

[0071] The above example illustrates the case where there are two alternative routes. Of course, the embodiment of the present application can also support the case where there are more than two alternative routes. The implementation process is the same as Figure 4The process shown is similar. Specifically, after determining j recommended routes from multiple routes from the first position to the second position (j is an integer not less than 1), if the j recommended routes are determined using j driving indicators, such as the first recommended route (i.e., the main route) is determined using the first driving indicator, the second recommended route (i.e., the first alternative route) is determined using the second driving indicator, and so on, then when determining the j+1th recommended route, the embodiment of the present application can determine, from the multiple routes except the j recommended routes, a route whose comprehensive driving indicator is not lower than the comprehensive driving indicator of the route ranked at the j+1th position in the first sorting, and a certain driving indicator other than the j driving indicators is better than the j recommended routes, as the j+1th recommended route. The embodiment of the present application considers any one of the driving indicators such as the expected driving time, driving distance, toll value, congestion level, route comfort, high speed, etc., which are used to compensate for the previously determined recommended routes.

[0072] The recommended route determination method provided in the embodiment of the present application can determine multiple alternative routes, and make the determined alternative routes compensate for the previously determined main route and alternative routes in terms of a certain driving index, and ensure that the driving experience of the determined alternative routes is not worse than the alternative routes with the same ranking determined by the prior art.

[0073] In a further optional implementation, the main route can be determined using the main route sorting model, and an alternative route can be determined using a sorting model. Taking the determination of the first alternative route and the second alternative route as an example, the embodiment of the present application can train the first sorting model to determine the first alternative route, and train the second sorting model to determine the second alternative route; for example, Figure 7 As shown, assuming that there are n routes from the first position to the second position, the embodiment of the present application can use the main route sorting model to sort the n routes at least for the first time according to the first driving index, so that the route ranked first in the first sorting is used as the main route; for n-1 routes other than the main route among the n routes, the embodiment of the present application can use the first sorting model to determine the sorting score of each route of the n-1 routes based on the driving index of each route in the n-1 routes and the first parameter set in the first sorting model, and take the route with the highest sorting score as the first alternative route; the first alternative route determined by the first sorting model can be considered as a route among the n-1 routes, whose comprehensive driving index is not lower than the comprehensive driving index of the route ranked second in the first sorting, and whose second driving index is better than the main route;

[0074] For the n-2 routes other than the main route and the first alternative route among the n routes, the embodiment of the present application can use the second sorting model to determine the sorting score of each of the n-2 routes based on the driving index of each route in the n-2 routes and the second parameter set in the second sorting model, and take the route with the highest sorting score as the second alternative route; the second alternative route determined by the second sorting model can be considered as a route among the n-2 routes, whose comprehensive driving index is not lower than the comprehensive driving index of the route ranked third in the first sorting, and whose third driving index is better than the main route and the first alternative route.

[0075] In order to enable the first alternative route determined by the first sorting model to compensate for the main road in the second driving index, and the driving experience is not worse than the route ranked second in the first sorting, the embodiment of the present application can train the first sorting model to determine the first parameter of the first sorting model, so that when the first sorting model is used to determine the sorting scores of each route except the main route among the multiple routes, it can be ensured that the route with the highest sorting score is better than the main route in the second driving index, and the comprehensive driving index is not lower than the route ranked second in the first sorting; optionally, Figure 8 The training flow chart of the first sorting model provided in the embodiment of the present application is shown as follows: Figure 8 As shown, the process may include:

[0076] Step S300: Acquire multiple route sets, wherein one route set includes multiple routes sorted at least according to a first driving index.

[0077] Multiple route sets may be data sets used by an embodiment of the present application to train a first sorting model. In an optional implementation, an embodiment of the present application may obtain multiple routes from the starting point to the end point of each historical navigation request for multiple historical navigation requests, thereby sorting the multiple routes of each historical navigation request at least according to the first driving indicator to obtain a route set corresponding to each historical navigation request, and then the route sets corresponding to the multiple historical navigation requests form the multiple route sets.

[0078] Step S310: For each route in the plurality of route sets, a compensation item driving index and a restriction item driving index are obtained.

[0079] In an optional implementation, the compensation item driving indicator may be composed of at least multiple driving indicators including the second driving indicator, and is used to compensate the main route on a driving indicator other than the first driving indicator; the embodiment of the present application can set the compensation item driving indicator according to actual conditions, for example, setting any one of the driving indicators such as estimated driving time, driving distance, toll value, congestion level, route comfort, high speed level, etc. as the compensation item driving indicator.

[0080] Optionally, the restricted driving indicator may be composed of at least a plurality of driving indicators that form a comprehensive driving indicator, which is used for comparison with the route ranked second in the route set, so as to ensure that the driving experience of the first alternative route determined by the trained first sorting model is no worse than the route ranked second in the route set; the embodiment of the present application may set the restricted driving indicator according to actual conditions; it can be understood that, since each route set is sorted according to at least the first driving indicator, there is a route ranked second in a route set, and thus there are multiple routes ranked second in the multiple route sets.

[0081] Step S320: training a first sorting model according to the compensating driving index, the restricting driving index characteristics and the loss function of each route, wherein the parameters of the first sorting model after training are the first parameters; wherein the loss function represents the average level of the restricting driving index of each route, which is not lower than the average level of the restricting driving index of the route ranked second in the plurality of route sets, and the second driving index in the compensating driving index is maximized to be better than the main route in the plurality of route sets.

[0082] After determining the compensatory driving indicators and restricted driving indicators of each route in the plurality of route sets, the goal of training the first sorting model in the embodiment of the present application is to maximize the second driving indicator in the compensatory driving indicator, which is different from the first driving indicator, to be better than the main route in the plurality of route sets, and to ensure that the average level of the restricted driving indicators of each route is not lower than the average level of the restricted driving indicators of the route ranked second in the plurality of route sets.

[0083] Optionally, the goal of training the first sorting model defined in the embodiment of the present application can be as follows: Fig. 9 As shown in the figure, compensation count represents the compensation item driving index, such as the estimated driving time (D eta ), driving distance (D dist ), toll value (Dtoll), congestion level, route comfort, high speed, etc., and its training goal is to maximize the compensation of the main route in the plurality of route sets on a second driving index different from the first driving index;

[0084] like Fig. 9As shown, the restricted driving indicators include: estimated driving time (eta), driving distance (distance), congestion level (congestion), number of traffic lights (light count), estimated driving time ratio (etaratio) to the main route, driving distance ratio (distance ratio) to the main route, similarity between the route and the main route (similarityvs.route1), etc., and its training target is subject to the average level of the restricted driving indicators, which is not lower than the average level of the restricted driving indicators of the route ranked second in the plurality of route sets; wherein, eta oline It represents the estimated travel time of the same ranked routes in the plurality of route sets, such as the estimated travel time of the route ranked second in the plurality of route sets. The other parameters are explained similarly.

[0085] Based on the training targets of the compensation item driving index and the restriction item driving index, the embodiment of the present application can define a loss function, which represents the average level of the restriction item driving index of each route, which is not lower than the average level of the restriction item driving index of the route ranked second in the plurality of route sets, and the second driving index in the compensation item driving index that is different from the first driving index is maximized to be better than the main route in the plurality of route sets; in one example, the definition of the loss function Loss(w) can be as follows: Fig.10 As shown, w represents the first parameter in the first sorting model, which is the parameter that needs to be trained for the first sorting model, eta ratio vs.r1 represents the ratio of the estimated driving time to the main route, distance ratio vs.r1 represents the ratio of the driving distance to the main route, and spatial similarity vs.r1 represents the shape similarity to the main route.

[0086] Based on the defined loss function, the compensatory driving index and the restricted driving index of each route in the multiple route sets, the embodiment of the present application can train the first sorting model. The training process can be understood as finding the optimal solution in the analytical space (the route can compensate the previously determined main route in various compensatory driving indexes, and a second driving index different from the first driving index is maximized to be better than the main route in the multiple route sets) under the premise of satisfying the restriction conditions (the multi-dimensional restricted driving index of the route is not worse than the restricted driving index of the first alternative route determined by the prior art). It can be understood that the model can be composed of multiple parameters, and the training of the first sorting model is to determine the first parameter in the first sorting model, so that the first sorting model can determine the sorting score based on the first parameter in combination with the driving index of the route, so that the route with the highest sorting score can maximize the compensation of the previously determined main route in the compensatory driving index, and the average level of the restricted driving index is not lower than the average level of the restricted driving index of the first alternative route determined by the prior art.

[0087] It can be seen that the embodiment of the present application sets the restricted driving indicators during the training process of the first sorting model, so that these restricted driving indicators are not worse than the average level of the route ranked second in the first sorting, and at the same time, the compensation driving indicators are set to compensate for the previously determined main route; since after the training of the first sorting model is completed, the first parameter in the first sorting model has the ability to ensure that the restricted driving indicators of the route are not worse than the average level of the route ranked second in the first sorting, and can compensate for the previously determined main route, therefore, when determining the first alternative route based on the first sorting model, the embodiment of the present application can directly determine the sorting score based on the compensation driving indicators of the route and the first parameter of the first sorting model, without considering the restricted driving indicators; optionally, Fig.11 FIG. 4 shows another optional process of the method for determining a recommended route provided in an embodiment of the present application. Fig.11 As shown, the process may include:

[0088] Step S400: Acquire multiple routes from the first location to the second location.

[0089] Step S410: performing a first sorting on the plurality of routes at least according to the first driving index, and determining the route ranked first in the first sorting as the main route.

[0090] Step S420: obtaining at least the compensation item driving index of each route among the multiple routes except the main route.

[0091] In an optional implementation, the embodiment of the present application may define a variety of compensation driving indicators, such as expected driving time, driving distance, charging value, congestion level, route comfort, high speed level, etc.

[0092] Step S430: at least input the compensation item driving index of each route into the first sorting model, and the first sorting model determines the sorting score of each route based on at least the compensation item driving index of each route and the first parameter, and determines the route with the highest sorting score as the first alternative route.

[0093] Based on Figure 8 The process shown trains the first sorting model so that after the first parameter in the first sorting model is determined, the first parameter can ensure that the average level of the restricted driving index of the route with a higher sorting score determined by the first sorting model is not lower than the average level of the restricted driving index of the route ranked second in the first sorting. Therefore, after determining the main route, the embodiment of the present application can determine the sorting score of each route by the first sorting model based on the compensatory driving index of each route except the main route among the multiple routes and the first parameter of the first sorting model, and determine the route with the highest sorting score as the first alternative route, so that the first alternative route can compensate for the main route in terms of the compensatory driving index except the first driving index, and ensure that the driving experience of the first alternative route is not lower than that of the route ranked second in the first sorting.

[0094] Further, in order to enable the second alternative route determined by the second sorting model to compensate for the driving indicators of the main route and the first alternative route, and the driving experience is not worse than the route ranked third in the first sorting, the embodiment of the present application can train the second sorting model to determine the second parameter of the second sorting model, so that when the second sorting model is used to determine the sorting scores of each route among the multiple routes except the main route and the first alternative route, it can be ensured that the route with the highest sorting score is better than the main route and the first alternative route in terms of the third driving indicator, and the comprehensive driving indicator is not lower than the comprehensive driving indicator of the route ranked third in the first sorting; optionally, Fig.12 The training flow chart of the second sorting model provided in the embodiment of the present application is shown as follows: Fig.12 As shown, the process may include:

[0095] Step S500: Acquire multiple route sets, wherein one route set includes multiple routes sorted at least according to a first driving index.

[0096] Step S510: For each route in the plurality of route sets, a compensation item driving index and a restriction item driving index are obtained.

[0097] Optionally, the compensation item driving index referred to in the embodiment of the present application may be composed of at least a plurality of driving indexes including a third driving index, and is used to compensate the main route and the first alternative route on a certain driving index other than the first driving index and the second driving index;

[0098] Optionally, the restricted driving index may be composed of at least multiple driving indicators that form a comprehensive driving index, which is used for comparison with the route ranked third in the route set to ensure that the driving experience of the second alternative route determined by the trained second ranking model is no worse than that of the route ranked third in the route set.

[0099] Step S520: training a second sorting model according to the compensating driving index, the restricting driving index characteristics and the loss function of each route, wherein the parameters of the second sorting model after training are the second parameters; wherein the loss function represents the average level of the restricting driving index of each route, which is not lower than the average level of the restricting driving index of the route ranked third in the plurality of route sets, and the third driving index in the compensating driving index is maximized to be better than the main route and the first alternative route in the plurality of route sets.

[0100] Fig.12 The introduction to training the second sorting model can be referred to in the same way Figure 8 Regarding the process, it should be noted that: Fig.12 When training the second sorting model, the restricted item driving index is compared with the route ranked third in the multiple route sets, and the compensation item driving index is compensated for the previously determined main route and the first alternative route.

[0101] It can be understood that the model can be composed of multiple parameters. Training the second sorting model is to determine the second parameter in the second sorting model, so that the second sorting model can sort and score based on the second parameter in combination with the driving indicators of the route, so that the route with the highest sorting score can maximize the compensation of the main route and the first alternative route determined previously in terms of the compensatory driving indicators, and the average level of the restricted driving indicators is not lower than the average level of the restricted driving indicators of the second alternative route determined by the prior art.

[0102] Based on the trained second sorting model, after obtaining the main route and the first alternative route from the multiple routes from the first location to the second location, the embodiment of the present application can be based on Fig.13 The process shown in the figure obtains the second alternative route, refer to Fig.13 , the process may include:

[0103] Step S600: obtaining at least the compensation item driving index of each route among the multiple routes except the main route and the first alternative route.

[0104] Step S610: input the compensation item driving index of each route into the second sorting model, and the second sorting model determines the sorting score of each route based at least on the compensation item driving index of each route and the second parameter, and determines the route with the highest sorting score as the second alternative route.

[0105] Based on Fig.12 The process shown trains the second sorting model so that after the second parameter in the second sorting model is determined, the second parameter can ensure that the average level of the restricted driving index of the route with a higher sorting score determined by the second sorting model is not lower than the average level of the restricted driving index of the route ranked third in the first sorting. Therefore, after determining the main route and the first alternative route, the embodiment of the present application can determine the sorting score of each route by the second sorting model based on the compensatory driving index of each route among the multiple routes except the main route and the first alternative route and the second parameter, and determine the route with the highest sorting score as the second alternative route, so that the second alternative route can compensate for the main route and the first alternative route in terms of the compensatory driving index except the first driving index and the second driving index, and ensure that the driving experience of the second alternative route is not lower than that of the route ranked third in the first sorting.

[0106] It should be further explained that the alternative route determined by the embodiment of the present application (whether it is the first alternative route or the second alternative route) can compensate for the previously determined recommended route in terms of driving indicators. In an optional implementation, if a certain driving indicator of the previously determined recommended route is not optimal, the embodiment of the present application can select the route with the best driving indicator as the next alternative route on the basis of ensuring that the comprehensive driving indicator is not lower than the comprehensive driving indicator of the same sorted route in the first sorting; although this method can make the alternative route compensate for the previously determined recommended route in terms of driving indicators, there may be a phenomenon that the compensation strength of the alternative route in terms of driving indicators is insufficient. For example, the estimated driving time of the main route is 5 hours, and the estimated driving time of the first alternative route is the shortest but only saves 1 minute, then the compensation strength of the first alternative route in terms of the estimated driving time is obviously insufficient; based on this, the embodiment of the present application can further define the compensation strength of the driving indicators.

[0107] In one example, the embodiment of the present application can define the compensation strength of 6 driving indicators. For example, the first alternative route is used to compensate the main route, such as Fig.14As shown in the figure, Δeta bond represents the compensation strength of the estimated travel time, Δdistance bond represents the compensation strength of the travel distance, Δtoll bond represents the compensation strength of the toll value, Δlightbond represents the compensation strength of the number of traffic lights, Δturn bond represents the compensation strength of the number of navigation actions, Δcongestionbond represents the compensation strength of the congestion degree, Δuncomfortable bond represents the compensation strength of the route comfort, and Δnonfreeway bond represents the compensation strength of the high speed degree; where route1 eta represents the estimated travel time of the main route, route1 distance represents the travel distance of the main route, route1 toll represents the toll value of the main route, route1light represents the number of traffic lights of the main route, route1 turn represents the number of navigation actions of the main route, route1 congest represents the congestion degree of the main route, route1 uncomfor represents the comfort of the main route, and route1 non freeway represents the high speed degree of the main route;

[0108] Combination Fig.15 As shown in the figure, it can be seen from the compensation strength of the estimated driving time that the first alternative route needs to save at least 2 minutes (minutes) in the estimated driving time compared with the main route, and at most 20 minutes, or save 10% of the time compared with the main route, in order to show that the first alternative route has the effect of compensating the estimated driving time of the main route. The compensation strength of other driving indicators is defined in the same way.

[0109] It can be seen that the alternative route must be better than the main route in the second driving index by a set value or a set ratio, in order to be considered that the alternative route has a compensatory effect on the main route.

[0110] It needs to be further explained that if Fig.16 and Fig.17As shown in the figure, the driving index of the number of traffic lights (also involving the number of navigation actions) does not increase linearly when the route distance increases, which may cause some extreme situations. For example, the alternative route saves 5 traffic lights compared to the main route, but the driving distance doubles. After data analysis, it is found that the number of traffic lights and the number of navigation actions increase nonlinearly with the increase of navigation distance, that is, after the navigation distance exceeds a certain threshold, the number of traffic lights and the number of navigation actions enter a plateau period. This is because when the navigation distance increases to a certain extent, they are all cross-city navigation. At this time, under the intelligent recommendation strategy, most users will choose to take the highway, and there will be basically no navigation actions and traffic lights on the highway. Therefore, there will be a phenomenon of taking the highway to detour and save traffic lights. Therefore, for short-distance navigation, the reduction in the number of traffic lights is a good driving index compensation item, but when the navigation distance becomes longer, the compensation for saving the number of traffic lights may lead to the extreme situation of a long detour.

[0111] Based on this, in further optimization, the embodiment of the present application may mark the number of traffic lights and / or the number of navigation actions for the main route and the alternative route, while not introducing the number of traffic lights and the number of navigation actions in the compensation item driving indicator, that is, neither the first sorting model nor the second sorting model determines the route sorting score based on the number of traffic lights and the number of navigation actions.

[0112] In an alternative implementation, Fig.18 The process of determining a recommended route when multiple routes from a first location to a second location are recalled is shown. Fig.18 As shown, in the embodiment of the present application, for the recalled multiple routes from the first position to the second position, the main route sorting model can be used to sort the multiple routes for the first time according to at least the first driving index, so that the route ranked first in the first sorting is used as the main route; then, the routes other than the main route in the multiple routes are filtered, and the filtering may involve three stages. First, abnormal routes are removed from the multiple routes other than the main route, and then manual intervention filtering is performed. The manual intervention filtering is a quality check of the route, which may involve multiple rules, such as filtering routes that violate restrictions, filtering routes with too high a proportion of side roads, and filtering dangerous sections. routes, etc.; after manual intervention filtering, for the remaining routes, the embodiment of the present application can determine the road shape similarity between the remaining routes and the main route, and then filter the routes with a road shape (route shape) similar to the main route based on the determined road shape similarity; further, the embodiment of the present application can use the first sorting model to determine the sorting score of each route after the road shape similarity filtering, and use the route with the highest sorting score as the first alternative route; further, after determining the first alternative route, for the remaining routes, the embodiment of the present application can use the second sorting model to determine the sorting score of the remaining routes, and use the route with the highest sorting score as the second alternative route;

[0113] In the retrieval stage, the route retrieval logic is a supplement to the first sorting and filtering. For example, if all the recommended routes are toll routes, the retrieval logic will try to find a free route in the filtered routes to replace the last alternative route, thereby providing users with a free route option. Of course, retrieval can also have other similar logics. When a certain attribute of multiple recommended routes is the same, the retrieval logic is used to find a route with a different attribute from the filtered routes to replace the last alternative route, thereby providing users with more diverse choices.

[0114] The recommended route determination method provided in the embodiment of the present application can be applied to the navigation planning stage before navigation starts, and can also be applied to the stage of re-planning the route during navigation; for example, when no navigation route is selected, if it is in the navigation planning stage before navigation starts, the embodiment of the present application can sort the multiple routes from the starting point to the end point according to the first driving index for the first time, so that the route ranked first is used as the main route, and then the routes similar to the main route in terms of road shape are filtered out from the multiple routes, and for the remaining routes, the remaining routes are selected to compensate for the main route at least in the second driving index, and the comprehensive driving index is not lower than the alternative route of the same sorted route in the first sorting;

[0115] In the case where no navigation route is selected and deviation occurs during the navigation process, the embodiment of the present application can perform a first sorting of the multiple routes from the current location to the destination location according to the first driving indicator, thereby selecting the main route, and then selecting the alternative route after filtering the road shape similarity; of course, the embodiment of the present application can also determine the main route and the alternative route when the page is re-planned during the navigation process to avoid congestion or not to avoid congestion when there is an existing navigation route.

[0116] The embodiment of the present application can learn a set of reasonable first parameters and second parameters by training the first sorting model and the second sorting model, thereby taking into account multiple driving indicators, and while completing the compensation of the alternative route for the previously determined recommended route, ensuring that the alternative route has a driving experience that is no worse than the alternative route determined by the prior art, which can greatly reduce the risk of unreasonable alternative routes; because the alternative route can compensate for the previously determined recommended route in terms of driving indicators, the embodiment of the present application can improve the diversity of recommended routes provided by the navigation service, which can better facilitate users to select navigation routes from the recommended routes;

[0117] When the first sorting model is used to determine the first alternative route and the second sorting model is used to determine the second alternative route, the embodiment of the present application selects a model rather than a rule to determine the alternative route, which can reduce development costs, take into account multiple driving indicators, and complete the compensation function of the compensation driving indicator for the previously determined recommended route under the premise of constraining multiple restriction driving indicators. At the same time, the embodiment of the present application can support the addition of more restriction driving indicators and / or compensation driving indicators to improve the scalability of the solution.

[0118] The above describes multiple implementation schemes provided by the embodiments of the present application. The various optional methods introduced in each implementation scheme can be combined and cross-referenced with each other without conflict, thereby extending a variety of possible implementation schemes, which can all be considered as implementation schemes disclosed and open in the embodiments of the present application.

[0119] The following is an introduction to the recommended route determination device provided in the embodiment of the present application. The recommended route determination device described below can be considered as a functional module that the navigation server needs to set up to implement the recommended route determination method provided in the embodiment of the present application. The content of the recommended route determination device described below can be referenced to the content of the recommended route determination method described above.

[0120] In an optional implementation, Fig.19 An optional block diagram of a recommended route determination device provided in an embodiment of the present application is shown. Fig.19 As shown, the device may include:

[0121] A route acquisition module 100, for acquiring multiple routes from a first location to a second location;

[0122] A main route determination module 110, configured to perform a first sorting of the plurality of routes at least according to the first driving index, and determine the route ranked first in the first sorting as the main route;

[0123] The alternative route determination module 120 is used to select at least one alternative route whose second driving index is better than that of the main route from the multiple routes, and the comprehensive driving index of the alternative route is not lower than the route with the same ranking as the alternative route in the recommended route in the first sorting; wherein the main route and the alternative route form a recommended route, the first driving index is different from the second driving index, and the comprehensive driving index includes a combination of multiple driving indicators.

[0124] Optionally, the alternative route may include a first alternative route; the alternative route determining module 120, configured to select at least one alternative route having a second driving index better than the main route from the multiple routes, wherein the comprehensive driving index of the alternative route is not lower than a route having the same ranking as the alternative route in the recommended route in the first ranking, may include:

[0125] A first alternative route is determined from the multiple routes except the main route, wherein the comprehensive driving index of the first alternative route is not lower than the route ranked second in the first sorting, and the second driving index is better than the main route.

[0126] Optionally, further, the alternative route may further include a second alternative route; the alternative route determining module 120 is used to select at least an alternative route whose second driving index is better than the main route from the multiple routes, and the comprehensive driving index of the alternative route is not lower than the route in the first sorting that has the same ranking as the alternative route in the recommended route, and may further include:

[0127] A second alternative route is determined from the multiple routes except the main route and the first alternative route, wherein the comprehensive driving index of the second alternative route is not lower than the route ranked third in the first sorting, and the third driving index is better than the main route and the first alternative route; wherein the third driving index is different from the first driving index and the second driving index.

[0128] Optionally, the embodiment of the present application may use a first sorting model to determine a first candidate route, based on which: Fig. 20 Another optional block diagram of the recommended route determination device provided in an embodiment of the present application is shown, Fig.19 and Fig. 20 As shown, the device may also include:

[0129] The first sorting model training module 130 is used to obtain multiple route sets, one of which includes multiple routes sorted according to at least the first driving index; for each route in the multiple route sets, a compensation item driving index and a restriction item driving index are obtained, wherein the compensation item driving index is at least composed of multiple driving indicators including the second driving index, and the restriction item driving index is at least composed of multiple driving indicators that form a comprehensive driving index; according to the compensation item driving index, restriction item driving index characteristics and loss function of each route, the first sorting model is trained, and the parameters of the first sorting model after training are the first parameters; wherein the loss function represents the average level of the restriction item driving index of each route, which is not lower than the average level of the restriction item driving index of the route ranked second in the multiple route sets, and the second driving indicator in the compensation item driving index is maximized to be better than the main route in the multiple route sets.

[0130] Optionally, the alternative route determination module 120 is used to determine a first alternative route from the multiple routes except the main route, the comprehensive driving index of the first alternative route is not lower than the route ranked second in the first sorting, and the second driving index is better than the main route, including:

[0131] At least obtaining a compensation item driving index of each route among the plurality of routes except the main route;

[0132] The first sorting model determines the sorting score of each route based at least on the compensation item driving index of each route and the first parameter, and determines the route with the highest sorting score as the first candidate route.

[0133] Optionally, the embodiment of the present application may use a second sorting model to determine a second candidate route, based on which: Fig.21 Another optional block diagram of the recommended route determination device provided in the embodiment of the present application is shown, combined with Fig. 20 and Fig.21 As shown, the device may also include:

[0134] The second sorting model training module 140 is used to obtain multiple route sets, one of which includes multiple routes sorted according to at least the first driving indicator; for each route in the multiple route sets, a compensation item driving indicator and a restriction item driving indicator are obtained, wherein the compensation item driving indicator is at least composed of multiple driving indicators including a third driving indicator, and the restriction item driving indicator is at least composed of multiple driving indicators that form a comprehensive driving indicator; according to the compensation item driving indicator, the restriction item driving indicator characteristics and the loss function of each route, the second sorting model is trained, and the parameters of the second sorting model after training are the second parameters; wherein the loss function represents the average level of the restriction item driving indicator of each route, which is not lower than the average level of the restriction item driving indicator of the route ranked third in the multiple route sets, and the third driving indicator in the compensation item driving indicator is maximized to be better than the main route and the first alternative route in the multiple route sets.

[0135] Optionally, the alternative route determination module 120 is used to determine a second alternative route from the multiple routes except the main route and the first alternative route, wherein the comprehensive driving index of the second alternative route is not lower than the route ranked third in the first sorting, and the third driving index is better than the main route and the first alternative route, and may include:

[0136] At least obtaining a compensation item driving index of each route among the plurality of routes except the main route and the first alternative route;

[0137] The second sorting model determines the sorting score of each route based at least on the compensation item driving index of each route and the second parameter, and determines the route with the highest sorting score as the second candidate route.

[0138] Optionally, the compensation item driving index may include at least one of the following: expected driving time, driving distance, charging value, congestion level, route comfort, and highway level.

[0139] Optionally, the alternative route is superior to the main route in terms of a set value or a set ratio in terms of the second driving index.

[0140] In a further optional implementation, Fig. 22 Another optional block diagram of the recommended route determination device provided in an embodiment of the present application is shown, combined with Fig.19 and Fig. 22 As shown, the device may also include:

[0141] The marking module 150 is used to mark the number of traffic lights and / or the number of navigation actions for the main route and the alternative route, wherein the compensation item driving index does not include the number of traffic lights and the number of navigation actions.

[0142] Optional, Fig.23 Another optional block diagram of the recommended route determination device provided in an embodiment of the present application is shown, Fig.19 and Fig.23 As shown, the device may also include:

[0143] The similarity filtering module 160 is used to filter the routes among the multiple routes that are similar to the main route in terms of road shape.

[0144] Optionally, the route acquisition module 100 for acquiring multiple routes from the first location to the second location may include:

[0145] Get navigation request;

[0146] According to the first location and the second location carried in the navigation request, a plurality of routes from the first location to the second location are determined.

[0147] The present application also provides a navigation server, which can be loaded with the above-mentioned recommended route determination device to implement the recommended route determination method provided by the present application. Fig.24 An optional block diagram of a navigation server provided in an embodiment of the present application is shown, such as Fig.24 As shown, the navigation server may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0148] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0149] Optionally, the communication interface 2 may be an interface of a communication module for performing network communication;

[0150] Optionally, processor 1 may be a CPU (central processing unit), a GPU (Graphics Processing Unit), an NPU (embedded neural network processor), an FPGA (Field Programmable Gate Array), a TPU (tensor processing unit), an AI chip, an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement an embodiment of the present application.

[0151] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0152] The memory 3 stores one or more computer executable instructions, and the processor 1 calls the one or more computer executable instructions to execute the recommended route determination method provided in the embodiment of the present application.

[0153] An embodiment of the present application also provides a storage medium, which can store one or more computer-executable instructions, and the one or more computer-executable instructions can be used to execute the recommended route determination method provided by the embodiment of the present application.

[0154] Although the embodiments of the present application are disclosed above, the present application is not limited thereto. Any person skilled in the art may make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be subject to the scope defined by the claims.

Claims

1. A method for determining a recommended route, wherein: include: Obtain multiple routes from a first location to a second location; performing a first sorting of the plurality of routes according to the first driving index, and determining a route ranked first in the first sorting as a main route; At least one alternative route having a second driving index better than that of the main route is selected from the multiple routes, and the comprehensive driving index of the alternative route is not lower than that of a route having the same ranking as that of the alternative route in the recommended route in the first sorting; wherein the main route and the alternative route form a recommended route, the first driving index is a driving index used for route sorting and is different from the second driving index, and the comprehensive driving index includes a combination of multiple driving indexes.

2. The method for determining a recommended route according to claim 1, wherein: The selecting at least one alternative route having a second driving index better than the main route from the plurality of routes, wherein the comprehensive driving index of the alternative route is not lower than that of the main route, the routes having the same ranking as the alternative route in the recommended route in the first ranking include: A first alternative route is determined from the multiple routes except the main route, wherein the comprehensive driving index of the first alternative route is not lower than the route ranked second in the first sorting, and the second driving index is better than the main route.

3. The method for determining a recommended route according to claim 2, wherein: The step of selecting at least one alternative route having a second driving index better than the main route from the plurality of routes, wherein the comprehensive driving index of the alternative route is not lower than that of the route having the same ranking as the alternative route in the recommended route in the first ranking also includes: A second alternative route is determined from the multiple routes except the main route and the first alternative route, wherein the comprehensive driving index of the second alternative route is not lower than the route ranked third in the first sorting, and the third driving index is better than the main route and the first alternative route; wherein the third driving index is different from the first driving index and the second driving index.

4. The method for determining a recommended route according to claim 2, wherein: Also includes: Acquire multiple route sets, wherein one route set includes multiple routes sorted according to a first travel indicator; For each route in the plurality of route sets, a compensation item driving index and a restriction item driving index are obtained; wherein the compensation item driving index is at least composed of a plurality of driving indexes including the second driving index, and the restriction item driving index is at least composed of a plurality of driving indexes forming a comprehensive driving index; A first sorting model is trained according to the compensating driving indicators, the restricted driving indicators characteristics and the loss function of each route, and the parameters of the first sorting model after training are the first parameters; wherein the loss function represents the average level of the restricted driving indicators of each route, which is not lower than the average level of the restricted driving indicators of the route ranked second in the multiple route sets, and the second driving indicator in the compensating driving indicators is maximized to be better than the main route in the multiple route sets.

5. The method for determining a recommended route according to claim 4, wherein: The step of determining a first alternative route from the plurality of routes except the main route, wherein the comprehensive driving index of the first alternative route is not lower than the route ranked second in the first sorting, and the second driving index is better than the main route, comprises: At least obtaining a compensation item driving index of each route among the plurality of routes except the main route; The first sorting model determines the sorting score of each route based at least on the compensation item driving index of each route and the first parameter, and determines the route with the highest sorting score as the first candidate route.

6. The method for determining a recommended route according to claim 3, wherein: Also includes: Acquire multiple route sets, wherein one route set includes multiple routes sorted according to a first travel indicator; For each route in the plurality of route sets, obtaining a compensation item driving index and a restriction item driving index; wherein the compensation item driving index is at least composed of a plurality of driving indexes including a third driving index, and the restriction item driving index is at least composed of a plurality of driving indexes forming a comprehensive driving index; A second sorting model is trained according to the compensating driving indicators, the restricting driving indicators characteristics and the loss function of each route, and the parameters of the second sorting model after training are the second parameters; wherein the loss function represents the average level of the restricting driving indicators of each route, which is not lower than the average level of the restricting driving indicators of the route ranked third in the multiple route sets, and the third driving indicator in the compensating driving indicators is maximized to be better than the main route and the first alternative route in the multiple route sets.

7. The method for determining a recommended route according to claim 6, wherein: The step of determining a second alternative route from the plurality of routes except the main route and the first alternative route, wherein the comprehensive driving index of the second alternative route is not lower than the route ranked third in the first sorting, and the third driving index is better than the main route and the first alternative route, comprises: At least obtaining a compensation item driving index of each route among the plurality of routes except the main route and the first alternative route; The second sorting model determines the sorting score of each route based at least on the compensation item driving index of each route and the second parameter, and determines the route with the highest sorting score as the second candidate route.

8. The method for determining a recommended route according to any one of claims 4 to 7, wherein: The compensation item driving index includes at least one of the following: expected driving time, driving distance, charging value, congestion level, route comfort, and highway level.

9. The method for determining a recommended route according to claim 1, wherein: The alternative route is superior to the main route in terms of a second driving index by a set value or a set ratio.

10. The method for determining a recommended route according to any one of claims 4 to 7, wherein: Also includes: The number of traffic lights and / or the number of navigation actions are marked for the main route and the alternative route, wherein the compensation item driving index does not include the number of traffic lights and the number of navigation actions.

11. The method for determining a recommended route according to claim 1, wherein: Before selecting at least one alternative route having a second driving index better than the main route from the plurality of routes, the method further includes: Among the multiple routes, routes having a road shape similar to the main route are filtered.

12. The method for determining a recommended route according to claim 1, wherein: The acquiring of multiple routes from the first location to the second location includes: Get navigation request; According to the first location and the second location carried in the navigation request, a plurality of routes from the first location to the second location are determined.

13. A device for determining a recommended route, wherein: include: A route acquisition module, used to acquire multiple routes from a first location to a second location; A main route determination module, configured to perform a first sorting of the plurality of routes according to the first driving index, and determine the route ranked first in the first sorting as the main route; An alternative route determination module is used to select at least an alternative route whose second driving index is better than that of the main route from the multiple routes, and the comprehensive driving index of the alternative route is not lower than that of the route with the same ranking as the alternative route in the recommended route in the first sorting; wherein the main route and the alternative route form a recommended route, the first driving index is a driving index used for route sorting and is different from the second driving index, and the comprehensive driving index includes a combination of multiple driving indicators.

14. A navigation server, wherein: include: At least one memory and at least one processor, the memory storing the one or more computer executable instructions, the processor calling the one or more computer executable instructions to execute the recommended route determination method according to any one of claims 1-12.

15. A storage medium, wherein: The storage medium stores one or more computer executable instructions, and the one or more computer executable instructions are used to execute the recommended route determination method according to any one of claims 1-12.

Images