Navigation Route Recommendation Method, Location-Based Service Provision Method, and Program Product

Abstract

Embodiments of the present disclosure disclose a navigation route recommendation method, a location-based service providing method, and a program product. The method includes: obtaining historical statistical features of a target road that a user has passed through and the historical number of passes of the target road; obtaining multiple candidate routes from the user's departure location to the destination location; for the candidate routes, obtaining relevant features of the target roads in the candidate routes based on the historical number of passes of the target roads; using a route recommendation model to obtain an acceptance degree value of the user for the candidate routes based on the historical statistical features and the relevant features of the target roads in the candidate routes; and determining a navigation recommendation route from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes. This technical solution can recommend a navigation recommendation route that better meets the user's needs, improve the consistency between the recommended route and the route required by the user, and thus increase the likelihood of the recommended route being selected.

Description

Technical Field

[0001] The present disclosure relates to the field of navigation technologies, and in particular, to a navigation route recommendation method, a location-based service providing method, and a program product. Background Art

[0002] When a navigation device navigates a user, it can first plan multiple routes based on the departure location and the destination location. Then, it determines a recommended route to be provided to the user from the planned multiple routes. After the user selects a recommended route as the navigation route, the navigation device can enter the navigation state and guide the user to drive from the departure location along the navigation route to the destination location. The road traffic capacity is an important reference in route recommendation during navigation. Currently, when making route recommendations, it will try to avoid recommending routes that include roads with weak traffic capacity (also known as small roads) to prevent harm to the user. Although this can avoid harm to the user caused by small roads, it will also ignore the advantages of small roads such as taking a shortcut and short time. Sometimes the user hopes to take a small road to make the time or distance the shortest. That is, the existing technology has the problem that the navigation route planned and recommended for the user is not the route the user needs. Therefore, how to improve the consistency between the recommended route and the route the user needs, thereby increasing the possibility of the recommended route being selected, has become a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0003] Embodiments of the present disclosure provide a navigation route recommendation method, a location-based service providing method, and a program product.

[0004] In a first aspect, an embodiment of the present disclosure provides a navigation route recommendation method, which includes:

[0005] Obtain the historical statistical features of the target roads passed by the user and the historical number of times the target roads have been passed, where the target roads include pre-defined roads with difficult passage;

[0006] Obtain multiple candidate routes from the user's departure location to the destination location;

[0007] For the candidate routes, based on the historical number of times the target roads have been passed, obtain the relevant features of the target roads in the candidate routes;

[0008] Use a route recommendation model to obtain the acceptance degree value of the user for the candidate routes based on the historical statistical features and the relevant features of the target roads in the candidate routes;

[0009] Based on the acceptance degree values of the multiple candidate routes, determine a navigation recommended route from the multiple candidate routes.

[0010] Further, the historical statistical features include at least one of the following: the length statistical feature of the target road passed by the user, the total number of historical passages of the target road passed by the user, and the total number of roads of the target road passed by the user;

[0011] The relevant features of the target road in the candidate route include at least one of the following: the total number of historical passages of the target road in the candidate route, the first ratio between the total length of the first target road with the historical passage times exceeding the first preset number and the total length of the candidate route in the candidate route, the second ratio between the total length of the second target road with the historical passage times not exceeding the first preset number and the total length of the candidate route in the candidate route, and the third ratio between the total length of the first target road and the total length of the second target road.

[0012] Further, determining the navigation recommended route from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes includes:

[0013] Determining the candidate routes with acceptance degree values meeting the first preset condition from the multiple candidate routes as the navigation recommended route, where the first preset condition includes at least one of the following conditions: the highest M acceptance degree values, the acceptance degree values exceeding the first preset threshold, and M is an integer greater than or equal to 1.

[0014] Further, determining the navigation recommended route from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes includes:

[0015] Screening out the candidate routes that meet the screening rules from the multiple candidate routes to obtain the pre-recommended routes, where the screening rules include that the passing parameters of the third target road with the historical passage times not exceeding the second preset number in the candidate route exceed the preset normal range;

[0016] Determining the pre-recommended routes with acceptance degree values meeting the second preset condition from the pre-recommended routes as the navigation recommended route, where the second preset condition includes at least one of the following conditions: the highest N acceptance degree values, the acceptance degree values exceeding the second preset threshold, and N is an integer greater than or equal to 1.

[0017] Further, the screening rules include any one of the following rules:

[0018] The total passing length of the third target road exceeds the preset length;

[0019] The fourth ratio between the total passing length of the third target road and the total length of the candidate route exceeds the preset ratio;

[0020] The estimated total travel time of the third target road exceeds the first preset time;

[0021] There is a target road in the third target road whose estimated travel time exceeds the second preset time.

[0022] Further, screening out the candidate routes that meet the screening rules from the multiple candidate routes to obtain a pre-recommended route includes:

[0023] Obtain the current navigation scenario;

[0024] Based on the correspondence between the scenario security level and the screening rules, obtain the screening rules corresponding to the scenario security level where the current navigation scenario is located;

[0025] Screen out the candidate routes that meet the screening rules corresponding to the current navigation scenario from the multiple candidate routes to obtain a pre-recommended route.

[0026] Further, the method further includes:

[0027] Obtain sample data, where the sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the sample routes, and the sample scores of the sample routes;

[0028] Train the route recommendation model based on the sample data.

[0029] Further, the method further includes:

[0030] Obtain the real route of the user from the starting position to the destination position;

[0031] Determine that the sample score when the real route is used as a new sample route is a preset score;

[0032] Based on the similarity between the candidate route and the real route, determine the sample score when the candidate route is used as a new sample route;

[0033] Obtain the new sample data, where the new sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the new sample routes, and the sample scores of the new sample routes;

[0034] Update the route recommendation model based on the new sample data.

[0035] In a second aspect, an embodiment of the present disclosure provides a location-based service providing method. The method provides location-based services for the service object by using the navigation recommended route obtained by the method in the first aspect. The location-based services include one or more of navigation, map rendering, and route planning.

[0036] In a third aspect, embodiments of the present disclosure provide a navigation route recommendation device, which includes:

[0037] A first acquisition module, configured to acquire historical statistical features of a target road passed by a user and the historical number of passes of the target road, where the target road includes a pre-defined road with difficult passage;

[0038] A second acquisition module, configured to acquire multiple candidate routes from the starting position of the user to the destination position;

[0039] A third acquisition module, configured to, for the candidate routes, acquire relevant features of the target roads in the candidate routes based on the historical number of passes of the target road;

[0040] A first determination module, configured to use a route recommendation model to determine an acceptance degree value of the user for the candidate routes based on the historical statistical features and the relevant features of the target roads in the candidate routes;

[0041] A second determination module, configured to determine a navigation recommended route from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes.

[0042] Further, the historical statistical features include at least one of the following: length statistical features of the target road passed by the user, total historical number of passes of the target road passed by the user, total number of roads of the target road passed by the user;

[0043] The relevant features of the target roads in the candidate routes include at least one of the following: total historical number of passes of the target roads in the candidate routes, a first ratio between the total length of the first target roads in the candidate routes whose historical number of passes exceeds a first preset number and the total length of the candidate routes, a second ratio between the total length of the second target roads in the candidate routes whose historical number of passes does not exceed the first preset number and the total length of the candidate routes, a third ratio between the total length of the first target roads and the total length of the second target roads.

[0044] Further, the second determination module is configured to:

[0045] Determine the candidate routes whose acceptance degree values meet a first preset condition from the multiple candidate routes as the navigation recommended route, where the first preset condition includes at least one of the following conditions: the highest M acceptance degree values, acceptance degree values exceeding a first preset threshold, and M is an integer greater than or equal to 1.

[0046] Further, the second determination module is configured to:

[0047] Screen out candidate routes that meet the screening rules from the multiple candidate routes to obtain pre-recommended routes, where the screening rules include that the traffic parameters of the third target roads in the candidate routes whose historical traffic times do not exceed the second preset number exceed the preset normal range;

[0048] Determine, from the pre-recommended routes, the pre-recommended routes whose acceptance degree values meet the second preset condition as the navigation recommended routes, where the second preset condition includes at least one of the following conditions: the highest N acceptance degree values, the acceptance degree values exceeding the second preset threshold, and N is an integer greater than or equal to 1.

[0049] Furthermore, the screening rules include any one of the following rules:

[0050] The total traffic length of the third target road exceeds the preset length;

[0051] The fourth ratio between the total traffic length of the third target road and the total length of the candidate route exceeds the preset ratio;

[0052] The estimated total traffic duration of the third target road exceeds the first preset duration;

[0053] There is a target road in the third target road whose estimated traffic duration exceeds the second preset duration.

[0054] Furthermore, the part in the second determination module that screens out candidate routes that meet the screening rules from the multiple candidate routes to obtain pre-recommended routes includes:

[0055] Obtain the current navigation scenario;

[0056] Based on the correspondence between the scenario security level and the screening rules, obtain the screening rules corresponding to the scenario security level where the current navigation scenario is located;

[0057] Screen out candidate routes that meet the screening rules corresponding to the current navigation scenario from the multiple candidate routes to obtain pre-recommended routes.

[0058] Furthermore, the device further includes:

[0059] A fourth acquisition module, configured to acquire sample data, where the sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the sample routes, and the sample scores of the sample routes;

[0060] A training module, configured to train the route recommendation model based on the sample data.

[0061] Furthermore, the device further includes:

[0062] A fifth acquisition module, configured to acquire the real route of the user from the starting position to the destination position;

[0063] A third determination module, configured to determine that the sample score when the real route is used as a new sample route is a preset score;

[0064] A fourth determination module, configured to determine the sample score when the candidate route is used as a new sample route based on the similarity between the candidate route and the real route;

[0065] A sixth acquisition module, configured to acquire the new sample data, where the new sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the new sample route, and the sample score of the new sample route;

[0066] An update module, configured to update the route recommendation model based on the new sample data.

[0067] In a possible design, the structure of the above device includes a memory and a processor. The memory is used to store one or more computer instructions that support the above device to execute the corresponding method, and the processor is configured to execute the computer instructions stored in the memory. The above device may further include a communication interface for the above device to communicate with other devices or communication networks.

[0068] In a fourth aspect, an embodiment of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory. Wherein, the processor executes the computer program to implement the method described in the first aspect above.

[0069] In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium for storing computer instructions used by any of the above devices. When the computer instructions are executed by a processor, they are used to implement the method described in the first aspect above.

[0070] In a sixth aspect, an embodiment of the present disclosure provides a computer program product, which includes computer instructions. When the computer instructions are executed by a processor, they are used to implement the method described in the first aspect above.

[0071] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:

[0072] The technical solution provided by the embodiment of the present disclosure can use a route recommendation model, based on the historical statistical characteristics reflecting the user's preference for the target road and the relevant characteristics of the target road in the candidate route, to obtain the user's acceptance value for the candidate route, and determine the candidate route with a higher acceptance value from the multiple candidate routes as the navigation recommended route. In this way, when the target road in the candidate route is acceptable to the user with a high probability, the navigation recommended route containing the target road can be recommended to the user. Compared with the one-size-fits-all avoidance of the target road in the prior art, the navigation recommended route that better meets the user's needs can be recommended to the user, and the consistency between the recommended route and the route required by the user can be improved, thereby increasing the possibility of the recommended route being selected. Moreover, the navigation recommended route recommended by this embodiment can include the target road familiar to the user as much as possible, and try not to include the target road unfamiliar to the user. In this way, under the premise of ensuring that the user is not harmed, the user can be personalized and enjoy the convenience of short time or short distance brought by the target road as much as possible.

[0073] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0075] Figure 1 A flowchart of a navigation route recommendation method according to an embodiment of the present disclosure is shown.

[0076] Figure 2 The figure shows an overall flow chart of a navigation route recommendation method according to an embodiment of the present disclosure.

[0077] Figure 3 A structural block diagram of a navigation route recommendation device according to an embodiment of the present disclosure is shown.

[0078] Figure 4 A schematic diagram of an application in a navigation application scenario according to an embodiment of the present disclosure is shown.

[0079] Figure 5 It is a structural diagram of an electronic device suitable for implementing the navigation route recommendation method and / or location-based service providing method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0080] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0081] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the specification, and do not exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.

[0082] In the present disclosure, the acquisition of user information or user data is an operation authorized and confirmed by the user, or actively selected by the user.

[0083] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0084] The details of the embodiments of the present disclosure are described in detail below through specific examples.

[0085] The technical solution provided by the embodiment of the present disclosure can use a route recommendation model, based on the historical statistical characteristics reflecting the user's preference for the target road and the relevant characteristics of the target road in the candidate route, to obtain the user's acceptance value for the candidate route, and determine the candidate route with a higher acceptance value from the multiple candidate routes as the navigation recommended route. In this way, when the target road in the candidate route is acceptable to the user with a high probability, the navigation recommended route containing the target road can be recommended to the user. Compared with the one-size-fits-all avoidance of the target road in the prior art, the navigation recommended route that better meets the user's needs can be recommended to the user, and the consistency between the recommended route and the route required by the user can be improved, thereby increasing the possibility of the recommended route being selected. Moreover, the navigation recommended route recommended by this embodiment can include the target road familiar to the user as much as possible, and try not to include the target road unfamiliar to the user. In this way, under the premise of ensuring that the user is not harmed, the user can enjoy the convenience of short time or short distance brought by the target road in a personalized and as much as possible manner.

[0086] Figure 1 FIG. 1 is a flowchart of a navigation route recommendation method according to an embodiment of the present disclosure. Figure 1 As shown, the navigation route recommendation method includes the following steps:

[0087] In step S101, historical statistical characteristics of target roads traveled by a user and the historical travel times of the target roads are obtained, wherein the target roads include predefined difficult-to-travel roads;

[0088] In step S102, a plurality of candidate routes from the user's starting location to the destination location are obtained;

[0089] In step S103, for the candidate route, based on the historical travel times of the target road, relevant features of the target road in the candidate route are obtained;

[0090] In step S104, using the route recommendation model, based on the historical statistical features and the relevant features of the target road in the candidate route, the acceptance value of the candidate route is determined;

[0091] In step S105, a navigation recommended route is determined from the plurality of candidate routes based on the acceptance level values ​​of the plurality of candidate routes.

[0092] As mentioned above, when navigating for the user, the navigation device can first plan multiple routes according to the starting location and the destination location, and then determine the recommended route provided to the user from the planned multiple routes. When the user selects a recommended route as the navigation route, the navigation device can enter the navigation state and guide the user to drive from the starting location along the navigation route to the destination location. Road capacity is an important reference for route recommendation in navigation. At present, when recommending routes, it will try to avoid recommending routes that include roads with difficult passage (also called small roads) to prevent harm to users. Although this can prevent small roads from causing harm to users, it will also ignore the advantages of taking shortcuts and short time that small roads may bring. Sometimes users want to take small roads to minimize time or distance. That is, the existing technology has the problem that the navigation route planned and recommended for users is not the one that the user needs. Therefore, how to improve the consistency between the recommended route and the route required by the user, thereby increasing the possibility of the recommended route being selected, has become a problem that needs to be solved by those skilled in the art.

[0093] In view of the above defects, a navigation route recommendation method is proposed in this embodiment. The method can use a route recommendation model, based on the historical statistical characteristics reflecting the user's preference for the target road and the relevant characteristics of the target road in the candidate route, to obtain the user's acceptance value of the candidate route, and determine the candidate route with a higher acceptance value from the multiple candidate routes as the navigation recommended route. In this way, when the target road in the candidate route is acceptable to the user with a high probability, the navigation recommended route containing the target road can be recommended to the user. Compared with the one-size-fits-all avoidance of the target road in the prior art, the navigation recommended route that better meets the user's needs can be recommended to the user, and the consistency between the recommended route and the route required by the user can be improved, thereby increasing the possibility of the recommended route being selected. Moreover, the navigation recommended route recommended by this embodiment can include the target road familiar to the user as much as possible, and try not to include the target road unfamiliar to the user. In this way, under the premise of ensuring that the user is not harmed, the user can enjoy the convenience of short time or short distance brought by the target road in a personalized and as much as possible manner.

[0094] In this embodiment, the navigation route recommendation method can be applied to computers, computing devices, electronic devices, servers, server clusters, etc. for recommending navigation routes.

[0095] In this embodiment, the target road refers to a road with difficult passage, which can also be called a small road. The traffic capacity can have different definitions under different navigation systems and different expert evaluations. Generally speaking, the target road, i.e., the small road, has characteristics such as narrowness, poor road conditions, slow speed, and the risk of being closed. The road conditions of the target road can be predefined, and any road that meets these road conditions can be called a target road. For example, the road conditions can be at least one of the following: the width is less than a preset width value, the average traffic speed is less than a preset speed value, the total number of passing vehicles per day is less than a preset value, etc.

[0096] In this embodiment, the historical statistical feature refers to the statistical feature of the target roads passed by the user. This historical statistical feature can reflect the user's preference for each target road and is a user feature in the dimension of small roads. The historical statistical feature can include at least one of the following: the length statistical feature of the target roads passed by the user, the total historical passing times of the target roads passed by the user, and the total number of target roads passed by the user. Among them, the length statistical feature of the target roads passed by the user can be at least one of the following features: the total length of the target roads passed by the user, the average length, variance value, standard deviation, mean square deviation, etc. of the target roads passed by the user; the total historical passing times of the target roads passed by the user refers to the sum of the passing times of each target road passed by the user.

[0097] In this embodiment, the historical travel trajectory of the user can be obtained, and statistical calculations are performed on the historical travel trajectory to obtain the historical statistical feature and the historical passing times of each target road. The time span of the historical travel trajectory can be 1 month, 3 months, 1 year, etc.

[0098] In this embodiment, the user can initiate a path planning request from the departure location to the destination location. The navigation route recommendation device can respond to the path planning request and use a route calculation engine to calculate and obtain several candidate routes. Each candidate route starts from the departure location as the route starting point and ends at the destination location as the route ending point.

[0099] In this embodiment, the candidate route may or may not have a target road. When there is a target road in the candidate route, some of the target roads in the candidate route have been traveled by the user, and some have not. Various relevant features of the target roads in the candidate route can be obtained as the portrait of the candidate route in the dimension of the target road. The relevant features of the target roads in the candidate route include at least one of the following: the total historical passing times of the target roads in the candidate route, the first ratio between the total length of the first target roads in the candidate route whose historical passing times exceed the first preset number and the total length of the candidate route, the second ratio between the total length of the second target roads in the candidate route whose historical passing times do not exceed the first preset number and the total length of the candidate route, and the third ratio between the total length of the first target roads and the total length of the second target roads. Of course, the relevant features of the target roads in the candidate route may also include: the average total historical passing duration of the first target roads, the average total historical passing duration of the second target roads, and various other features related to the target roads.

[0100] In this embodiment, the total historical passing times of the target roads in the candidate route refers to the sum of the historical passing times of each target road in the candidate route; the first target road refers to the target road in the candidate route whose historical passing times exceed the first preset number, that is, the target road familiar to the user; the second target road refers to the target road in the candidate route whose historical passing times do not exceed the first preset number, that is, the target road unfamiliar to the user. The average total historical passing duration of the first target roads refers to the sum of the averages of the historical passing durations of each first target road; the average total historical passing duration of the second target roads refers to the sum of the averages of the historical passing durations of each second target road.

[0101] In this embodiment, the historical statistical features of the target roads traveled by the user and the relevant features of the target roads in the candidate route can be input into the route recommendation model. By executing the route recommendation model, the acceptance degree value of the user for the candidate route output by the route recommendation model can be obtained. The route recommendation model is a machine learning model trained in advance. Based on the historical statistical features reflecting the user's preference for the target road and the relevant features of the target roads in the candidate route, the acceptance degree value of the user for the candidate route can be calculated. If the acceptance degree value is high, it indicates that the user is likely to accept the target roads in the candidate route and choose the candidate route. If the acceptance degree value is low, it indicates that the user is likely to not accept the target roads in the candidate route and will not choose the candidate route. At this time, the candidate route with a higher acceptance degree value can be determined from the multiple candidate routes as the navigation recommended route.

[0102] In this embodiment, after the recommended navigation route is determined, the recommended navigation route can be displayed to the user through the user's navigation terminal (such as the user's mobile phone, car navigation terminal, etc.). The user can select a route that the user is satisfied with from these recommended navigation routes and enter navigation instructions. The navigation terminal can then navigate for the user based on the route selected by the user.

[0103] In this embodiment, the historical statistical features of the target road that the user has traveled can be first obtained as the user features of the side road dimension. After obtaining multiple candidate routes from the user's starting position to the destination position, the relevant features of the target road in each candidate route can be obtained as the candidate route features of the side road dimension based on the historical number of travels on each target road. Then, the route recommendation model can be used to obtain the user's acceptance value of the candidate route based on the historical statistical features that reflect the user's preference for the target road and the candidate route features of the side road dimension-the relevant features of the target road in the candidate route. In this way, the candidate route with a higher acceptance value can be determined from the multiple candidate routes as the navigation recommended route. In this way, when the target road in the candidate route is likely to be accepted by the user, the navigation recommended route containing the target road can be recommended to the user. Compared with the prior art that avoids the target road in a one-size-fits-all manner, a navigation recommended route that better meets the user's needs can be recommended to the user, and the consistency between the recommended route and the route required by the user can be improved, thereby increasing the possibility of the recommended route being selected. Moreover, the navigation recommended route recommended by this embodiment can include target roads that the user is familiar with as much as possible, and try not to include target roads that the user is unfamiliar with. In this way, under the premise of ensuring that the user is not harmed, the user can enjoy the convenience of short time or short distance brought by the target road in a personalized and maximum manner.

[0104] In an optional implementation of this embodiment, step S105 in the above navigation route recommendation method, i.e., the step of determining a navigation recommended route from the multiple candidate routes based on the acceptance degree values ​​of the multiple candidate routes, further includes the following steps:

[0105] Determine from the multiple candidate routes a candidate route whose acceptance value satisfies a preset condition as the navigation recommended route, wherein the preset condition includes at least one of the following conditions: M routes with the highest acceptance values, an acceptance value exceeding a preset threshold, and M is an integer greater than or equal to 1.

[0106] In this implementation, the M candidate routes with the highest acceptance values ​​can be determined from the multiple candidate routes as the navigation recommended routes, or the candidate routes with acceptance values ​​exceeding a preset threshold can be determined from the multiple candidate routes as the navigation recommended routes.

[0107] In this implementation, usually three navigation recommended routes are recommended for the user, that is, M can be 3. When determining the candidate routes with acceptance degree values exceeding the preset threshold from the multiple candidate routes as the navigation recommended routes, there may be more candidate routes with acceptance degree values exceeding the preset threshold than M. At this time, the M candidate routes with the highest acceptance degree values can be determined from the multiple candidate routes as the navigation recommended routes.

[0108] In this implementation, when presenting the navigation recommended routes to the user through the user's navigation terminal, the navigation recommended routes can be presented according to the acceptance degree values of each navigation recommended route. For example, the navigation recommended routes can be sorted according to the acceptance degree values of each navigation recommended route to obtain the serial numbers of each navigation recommended route, and the serial numbers of the navigation recommended routes are displayed when presenting the navigation recommended routes. The user can refer to the serial numbers of each navigation recommended route to select the navigation route. Of course, there can also be other presentation methods such as annotating text explanations and so on.

[0109] In an alternative implementation of this embodiment, step S105 in the above navigation route recommendation method, that is, the step of determining the navigation recommended routes from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes, further includes the following steps:

[0110] Screen out the candidate routes that meet the screening rules from the multiple candidate routes to obtain pre-recommended routes, where the screening rules include that the traffic parameters of the third target road with the number of historical passages not exceeding the second preset number in the candidate routes exceed the preset normal range;

[0111] Determine the pre-recommended routes with acceptance degree values meeting the second preset conditions from the pre-recommended routes as the navigation recommended routes, where the second preset conditions include at least one of the following conditions: the N with the highest acceptance degree values, the acceptance degree values exceeding the second preset threshold, and N is an integer greater than or equal to 1.

[0112] In this implementation, usually, the acceptance degree values output by the route recommendation model can ensure the overall route recommendation effect, but there must be some scenarios that are not suitable for recommending routes containing the target road, such as late at night. Therefore, it is necessary to screen out the candidate routes where the target roads are located that are not convenient to recommend in the current scenario through the screening rules. The screening rules include that the traffic parameters of the third target road with the number of historical passages not exceeding the second preset number in the candidate routes exceed the preset normal range. If the traffic parameters of the third target road exceed the preset normal range, it indicates that the user may be in danger when passing through this third target road in the current scenario. In order to avoid danger to the user, these candidate routes that meet the screening rules can be screened out to obtain pre-recommended routes that will not pose a danger.

[0113] In this implementation, the N pre-recommended routes with the highest acceptance degree values can be determined from the pre-recommended routes as the navigation recommended routes, or the pre-recommended routes with acceptance degree values exceeding a second preset threshold can also be determined from the pre-recommended routes as the navigation recommended routes.

[0114] In this implementation, usually 3 navigation recommended routes are recommended for the user, that is, the value of N can be 3. When determining the candidate routes with acceptance degree values exceeding a preset threshold from the multiple candidate routes as the navigation recommended routes, there may be more candidate routes with acceptance degree values exceeding the preset threshold than N. At this time, the N candidate routes with the highest acceptance degree values can be determined from the multiple candidate routes as the navigation recommended routes.

[0115] This implementation can use screening rules to pre-screen candidate routes that may be dangerous for the user, and can, while ensuring the user's travel safety, enable the user to enjoy the convenience brought by small roads as much as possible.

[0116] In an alternative implementation of this embodiment, the screening rules include any of the following rules:

[0117] The total passing length of the third target road exceeds a preset length;

[0118] The fourth ratio between the total passing length of the third target road and the total length of the candidate route exceeds a preset ratio;

[0119] The estimated total passing duration of the third target road exceeds a first preset duration;

[0120] There is a target road in the third target road with an estimated passing duration exceeding a second preset duration.

[0121] In this implementation, the third target road refers to a target road in the candidate route with the number of historical passes not exceeding a second preset number, that is, a target road with fewer user passes and unfamiliar to the user. If the total passing length of the third target road exceeds a preset length, it indicates that the target road unfamiliar to the user in the candidate route will be longer, and in this case, the possibility of the user getting into danger is greater. Therefore, the candidate routes with the total passing length of the third target road exceeding the preset length can be screened out. Similarly, if the fourth ratio between the total passing length of the third target road and the total length of the candidate route exceeds a preset ratio, it indicates that there are more target roads unfamiliar to the user in the candidate route, and in this case, the possibility of the user getting into danger is greater. Therefore, the candidate routes with the fourth ratio exceeding the preset ratio can be screened out.

[0122] In this implementation manner, the estimated total travel time of the third target road refers to the total travel time estimated to pass through all the third target roads. If this estimated total travel time exceeds the first preset time, it indicates that the user needs a long time to pass through the third target road. The longer the time, the greater the possibility of danger for the user. Therefore, candidate routes with an estimated total travel time of the third target road exceeding the first preset time can be screened out.

[0123] In this implementation manner, if there is a target road in the third target road with an estimated travel time exceeding the second preset time, it indicates that the user has a relatively long continuous time period to travel on the target road. The longer this continuous time period, the greater the possibility of danger for the user. Therefore, candidate routes with a target road in the third target road having an estimated travel time exceeding the second preset time can be screened out.

[0124] It should be noted here that in addition to the above four rules, there can be other rules for this screening rule, as long as it can screen out candidate routes that will cause events threatening the user's safety.

[0125] In an alternative implementation manner of this embodiment, the step of screening out candidate routes that meet the screening rules from the multiple candidate routes in the above navigation route recommendation method to obtain a pre-recommended route may further include the following steps:

[0126] Obtain the current navigation scenario;

[0127] Based on the correspondence between the scenario security level and the screening rule, obtain the screening rule corresponding to the scenario security level where the current navigation scenario is located;

[0128] Screen out candidate routes that meet the screening rule corresponding to the current navigation scenario from the multiple candidate routes to obtain a pre-recommended route.

[0129] In this embodiment, different navigation scenarios have different security levels. Generally, a user's navigation during the day is safer than at night, and navigation in normal weather conditions is safer than in adverse weather conditions such as rain, haze, and storms. Therefore, a scenario security level can be set for the navigation scenario. The higher the scenario security level of a navigation scenario, the safer it is, and the smaller the screening range corresponding to the screening rule. The corresponding relationship between the scenario security level and the screening rule can be set accordingly. By way of example, the corresponding relationship between the scenario security level and the screening rule can be as follows: The screening rule corresponding to the highest scenario security level can be that the fourth ratio between the total passing length of the third target roads in the candidate route with a historical passing times not exceeding 1 time and the total length of the candidate route exceeds 70%. The screening rule corresponding to the next lower scenario security level can be that the fourth ratio between the total passing length of the third target roads in the candidate route with a historical passing times not exceeding 5 times and the total length of the candidate route exceeds 50%. The screening rule corresponding to the next lower scenario security level can be that the fourth ratio between the total passing length of the third target roads in the candidate route with a historical passing times not exceeding 10 times and the total length of the candidate route exceeds 30%, and so on.

[0130] In this embodiment, the current navigation scenario may include the current time, the current weather condition, the current navigation type (such as walking navigation or self-driving navigation), etc. After obtaining the current navigation scenario, the scenario security level where the current navigation scenario is located can be obtained, and then the screening rule corresponding to the scenario security level where the current navigation scenario is located can be obtained. In this way, the candidate route can be screened according to this screening rule to obtain the pre-recommended route.

[0131] In this implementation, different screening rules are set for navigation scenarios with different security levels, which can more accurately screen out routes that may pose risks for users. Thus, while ensuring the safety of users' travel, users can enjoy the convenience brought by small roads as much as possible.

[0132] In an alternative implementation of this embodiment, the above navigation route recommendation method may further include the following steps:

[0133] Obtain sample data, where the sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the sample route, and the sample score of the sample route;

[0134] Train the route recommendation model based on the sample data.

[0135] In this implementation manner, the sample route refers to the historical actual route and other unpassed historical recommended routes in multiple historical navigations of the user within a historical period. The sample score of the historical actual route can be a first preset value. For example, the sample score of the historical actual route can be 1, and the sample score of the unpassed historical recommended route can be a second preset value such as 0, or it can be a calculated value. For example, the similarity between the historical recommended route and the historical actual route can be used as the sample score of the historical recommended route.

[0136] In this implementation manner, the feature parameters and acquisition methods included in the relevant features of the target roads in the historical statistical features and the sample route can refer to the descriptions in the above embodiments and will not be elaborated here.

[0137] In this implementation manner, these sample data can be used to train the initial route recommendation model, continuously adjust the model parameters in the route recommendation model until the accuracy of the acceptance degree value output by the route recommendation model reaches a preset threshold, and the route recommendation model is obtained.

[0138] In an alternative implementation manner of this embodiment, the above navigation route recommendation method may further include the following steps:

[0139] Obtain the actual route of the user from the starting position to the destination position;

[0140] Determine that the sample score when the actual route is used as a new sample route is a preset score;

[0141] Based on the similarity between the candidate route and the actual route, determine the sample score when the candidate route is used as a new sample route;

[0142] Obtain the new sample data, where the new sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the new sample route, and the sample score of the new sample route;

[0143] Update the route recommendation model based on the new sample data.

[0144] In this implementation, after the navigation recommendation device determines the navigation recommendation routes, the user can select one route from these navigation recommendation routes for navigation. After the user completes this navigation and reaches the destination, the navigation recommendation device can obtain the actual route of the user from the departure position to the destination position, determine that the sample score when the actual route is used as a new sample route is a preset score, such as 1, and determine that the sample score when the candidate route is used as a new sample route is the similarity between the candidate route and the actual route. In this way, new sample data can be obtained, and the new sample data can be used to continue training the route recommendation model, so that the route recommendation model can be continuously updated according to the new actual situation. Here, new sample data can be obtained regularly to update the route recommendation model.

[0145] Figure 2 FIG. shows an overall flowchart of a navigation route recommendation method according to an embodiment of the present disclosure, as Figure 2 shown, the method can be applied to a server and may include the following steps:

[0146] In step S201, sample data is obtained, and the sample data includes historical statistical features of target roads passed by the user, relevant features of target roads in the sample route, and sample scores of the sample route;

[0147] Among them, the historical statistical features include at least one of the following: length statistical features of target roads passed by the user, total historical passing times of target roads passed by the user, total number of roads of target roads passed by the user; relevant features of target roads in the sample route include at least one of the following: total historical passing times of target roads in the sample route, a first ratio between the total length of the first target road whose historical passing times exceed a first preset number and the total length of the sample route in the sample route, a second ratio between the total length of the second target road whose historical passing times do not exceed the first preset number and the total length of the sample route in the sample route, a third ratio between the total length of the first target road and the total length of the second target road;

[0148] In step S202, a route recommendation model is trained based on the sample data.

[0149] In step S203, historical statistical features of target roads passed by the user and historical passing times of the target roads are obtained, and the target roads include pre-defined roads with difficult passage;

[0150] In step S204, multiple candidate routes from the user's departure position to the destination position are obtained;

[0151] Among them, the server can obtain the starting location and destination location input by the user from the user's navigation terminal (such as a mobile phone, in-vehicle navigation, etc.), and then obtain multiple candidate routes from the starting location of the user to the destination location through a route calculation engine;

[0152] In step S205, for the candidate routes, based on the historical passing times of the target roads, obtain the relevant features of the target roads in the candidate routes;

[0153] In step S206, use a route recommendation model to determine the acceptance degree value of the user for the candidate routes based on the historical statistical features and the relevant features of the target roads in the candidate routes;

[0154] In step S207, obtain the current navigation scenario, and based on the corresponding relationship between the scenario security level and the screening rules, obtain the screening rules corresponding to the scenario security level where the current navigation scenario is located;

[0155] In step S208, screen out the candidate routes that meet the screening rules corresponding to the current navigation scenario from the multiple candidate routes to obtain pre-recommended routes;

[0156] Among them, the screening rules include any one of the following rules: the total passing length of the third target road exceeds a preset length; the fourth ratio between the total passing length of the third target road and the total length of the candidate route exceeds a preset ratio; the estimated total passing time of the third target road exceeds a first preset time; there is a target road in the third target road whose estimated passing time exceeds a second preset time;

[0157] In step S209, determine the pre-recommended routes whose acceptance degree values meet the second preset condition from the pre-recommended routes as the navigation recommended routes;

[0158] Among them, the second preset condition includes at least one of the following conditions: the highest N acceptance degree values, the acceptance degree value exceeds a second preset threshold, and N is an integer greater than or equal to 1.

[0159] In step S210, update the route recommendation model.

[0160] Among them, the steps of updating the route recommendation model include: obtaining the real route of the user from the departure location to the destination location; determining that the sample score when the real route is used as a new sample route is a preset score; determining the sample score when the candidate route is used as a new sample route based on the similarity between the candidate route and the real route; obtaining the new sample data, where the new sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the new sample route, and the sample score of the new sample route; and updating the route recommendation model based on the new sample data.

[0161] The following is an embodiment of the apparatus of the present disclosure, which can be used to execute the method embodiment of the present disclosure.

[0162] According to a navigation route recommendation apparatus of an embodiment of the present disclosure, the apparatus can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 3 The structural block diagram of a navigation route recommendation apparatus according to an embodiment of the present disclosure is shown as Figure 3 shown. The navigation route recommendation apparatus includes:

[0163] A first acquisition module 301, configured to acquire the historical statistical features of the target roads passed by the user and the historical number of times the target roads have been passed, where the target roads include roads with predefined traffic difficulties;

[0164] A second acquisition module 302, configured to acquire multiple candidate routes from the departure location of the user to the destination location;

[0165] A third acquisition module 303, configured to, for the candidate routes, acquire the relevant features of the target roads in the candidate routes based on the historical number of times the target roads have been passed;

[0166] A first determination module 304, configured to use a route recommendation model to determine the acceptance degree value of the user for the candidate routes based on the historical statistical features and the relevant features of the target roads in the candidate routes;

[0167] A second determination module 305, configured to determine a navigation recommended route from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes.

[0168] In an alternative implementation manner of this embodiment, the historical statistical features include at least one of the following: the length statistical features of the target roads passed by the user, the total historical number of times the target roads have been passed by the user, and the total number of roads of the target roads passed by the user;

[0169] The relevant features of the target road in the candidate route include at least one of the following: the total historical passing times of the target road in the candidate route, the first ratio between the total length of the first target road in the candidate route whose historical passing times exceed the first preset number and the total length of the candidate route, the second ratio between the total length of the second target road in the candidate route whose historical passing times do not exceed the first preset number and the total length of the candidate route, and the third ratio between the total length of the first target road and the total length of the second target road.

[0170] In an alternative implementation manner of this embodiment, the second determination module 305 is configured to:

[0171] Determine the candidate route whose acceptance degree value meets the first preset condition from the multiple candidate routes as the navigation recommended route, where the first preset condition includes at least one of the following conditions: the highest M acceptance degree values, the acceptance degree value exceeds the first preset threshold, and M is an integer greater than or equal to 1.

[0172] In an alternative implementation manner of this embodiment, the second determination module 305 is configured to:

[0173] Screen out the candidate routes that meet the screening rules from the multiple candidate routes to obtain a pre-recommended route, where the screening rules include that the passing parameters of the third target road in the candidate route whose historical passing times do not exceed the second preset number exceed the preset normal range;

[0174] Determine the pre-recommended route whose acceptance degree value meets the second preset condition from the pre-recommended routes as the navigation recommended route, where the second preset condition includes at least one of the following conditions: the highest N acceptance degree values, the acceptance degree value exceeds the second preset threshold, and N is an integer greater than or equal to 1.

[0175] In an alternative implementation manner of this embodiment, the screening rules include any one of the following rules:

[0176] The total passing length of the third target road exceeds the preset length;

[0177] The fourth ratio between the total passing length of the third target road and the total length of the candidate route exceeds the preset ratio;

[0178] The expected total passing duration of the third target road exceeds the first preset duration;

[0179] There is a target road in the third target road whose expected passing duration exceeds the second preset duration.

[0180] In an alternative implementation of this embodiment, the part in the second determination module 305 that screens out candidate routes that meet the screening rules from the multiple candidate routes to obtain a pre-recommended route includes:

[0181] Obtain the current navigation scenario;

[0182] Based on the correspondence between the scenario security level and the screening rules, obtain the screening rules corresponding to the scenario security level where the current navigation scenario is located;

[0183] Screen out candidate routes that meet the screening rules corresponding to the current navigation scenario from the multiple candidate routes to obtain a pre-recommended route.

[0184] In an alternative implementation of this embodiment, the device further includes:

[0185] A fourth acquisition module, configured to acquire sample data, where the sample data includes historical statistical features of target roads passed by the user, relevant features of target roads in the sample route, and sample scores of the sample route;

[0186] A training module, configured to train the route recommendation model based on the sample data.

[0187] In an alternative implementation of this embodiment, the device further includes:

[0188] A fifth acquisition module, configured to acquire the real route of the user from the starting position to the destination position;

[0189] A third determination module, configured to determine that the sample score when the real route is used as a new sample route is a preset score;

[0190] A fourth determination module, configured to determine the sample score when the candidate route is used as a new sample route based on the similarity between the candidate route and the real route;

[0191] A sixth acquisition module, configured to acquire the new sample data, where the new sample data includes historical statistical features of target roads passed by the user, relevant features of target roads in the new sample route, and sample scores of the new sample route;

[0192] An update module, configured to update the route recommendation model based on the new sample data.

[0193] In this embodiment, the navigation route recommendation device corresponds to the above navigation route recommendation method. For specific details, reference can be made to the description of the above navigation route recommendation method, which will not be elaborated here.

[0194] A method for providing location-based services according to an embodiment of the present disclosure. The method for providing location-based services uses the above navigation route recommendation method to provide location-based services for the service recipient. The location-based services include one or more of navigation, map rendering, and route planning.

[0195] In this embodiment, the method for providing location-based services can be executed on a terminal, and the terminal is a mobile phone, iPad, computer, smart watch, vehicle, etc. In the embodiments of the present disclosure, a navigation recommended route can be provided for the service recipient according to the departure location and destination location sent by the service recipient. Furthermore, during the location-based service process, the navigation recommended route can be used to provide a more accurate location service for the service recipient, such as a navigation service, a path planning service, and / or a map rendering service, etc.

[0196] The service recipient can be a mobile phone, iPad, computer, smart watch, vehicle, robot, etc. When navigating for the service recipient, planning a path, or rendering roads on a map, a navigation recommended route can be obtained based on the above method. Furthermore, when navigating or planning a path, the correct navigation actions can be output for the service recipient based on the navigation recommended route, and when rendering a map, the navigation recommended route can be rendered on the electronic map. For specific details, reference can be made to the above description of the navigation route recommendation method, which will not be elaborated here.

[0197] Figure 4 Shows an application schematic diagram in a navigation application scenario according to an embodiment of the present disclosure. As Figure 4 shown, the server can obtain the sample data of the user from the user database and train a route recommendation model based on the sample data. When the vehicle client receives a navigation request from the departure location to the destination location input by the user, it will send the navigation request to the server. The server can obtain the historical statistical features of the target roads passed by the user and the historical passing times of the target roads from the user database, as well as calculate multiple candidate routes from the departure location to the destination location; then for the candidate routes, based on the historical passing times of the target roads, obtain the relevant features of the target roads in the candidate routes; use the route recommendation model, based on the historical statistical features and the relevant features of the target roads in the candidate routes, determine the acceptance degree value of the user for the candidate routes; based on the acceptance degree values of the multiple candidate routes, determine a navigation recommended route from the multiple candidate routes and send it to the vehicle client. The vehicle client can then render the navigation recommended route on the electronic map. The user can select one of the navigation recommended routes and input a navigation instruction, and the vehicle client can respond to the navigation instruction input by the user and perform navigation actions according to the navigation recommended route selected by the user, so that the user can safely and quickly reach the destination location from the departure location based on the navigation actions.

[0198] Figure 5 It is a schematic structural diagram of an electronic device suitable for implementing a navigation route recommendation method and / or a location-based service providing method according to an embodiment of the present disclosure.

[0199] As Figure 5 shown, the computer system 500 includes a processing unit 501, which can perform various processes in the above embodiments according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The processing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0200] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read from it can be installed into the storage section 508 as needed. Among them, the processing unit 501 can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.

[0201] Specifically, according to an embodiment of the present disclosure, the method described above can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a computer-readable medium, and the computer program includes program codes for executing the navigation route recommendation method. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 509, and / or installed from the removable medium 511.

[0202] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0203] The units or modules described in the embodiments of the present disclosure can be implemented in software or in hardware. The described units or modules can also be provided in a processor, and the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves.

[0204] On the other hand, the embodiments of the present disclosure also provide a computer-readable storage medium, which can be the computer-readable storage medium included in the device described in the above embodiments; or it can exist separately and be a computer-readable storage medium not assembled into the device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the methods described in the embodiments of the present disclosure.

[0205] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, technical solutions formed by mutually replacing the above features with technical features having similar functions (but not limited to) disclosed in the embodiments of the present disclosure.

Claims

1. A navigation route recommendation method, wherein, Including: Obtaining the historical statistical features of the target roads passed by the user and the historical passing times of each target road, where the target roads are predefined roads with difficult passage, and the historical statistical features are the features of the user in the dimension of the target roads, reflecting the user's preference for the target roads; Obtaining multiple candidate routes from the starting position to the destination position of the user; For the candidate routes, based on the historical passing times of each target road, obtaining the relevant features of the target roads in the candidate routes as the portraits of the candidate routes in the dimension of the target roads; Using a route recommendation model, based on the historical statistical features and the relevant features of the target roads in the candidate routes, determining the acceptance degree value of the user for the candidate routes; Based on the acceptance degree values of the multiple candidate routes, determining a navigation recommended route from the multiple candidate routes.

2. The method according to claim 1, wherein, The historical statistical features include at least one of the following: the length statistical feature of the target roads passed by the user, the total historical passing times of the target roads passed by the user, the total number of target roads passed by the user; The relevant features of the target roads in the candidate routes include at least one of the following: the total historical passing times of the target roads in the candidate routes, the first ratio between the total length of the first target roads with historical passing times exceeding the first preset number and the total length of the candidate routes in the candidate routes, the second ratio between the total length of the second target roads with historical passing times not exceeding the first preset number and the total length of the candidate routes in the candidate routes, the third ratio between the total length of the first target roads and the total length of the second target roads.

3. The method according to claim 1, wherein The determining the navigation recommended route from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes includes: Determining the candidate routes whose acceptance degree values meet the first preset condition as the navigation recommended route from the multiple candidate routes, where the first preset condition includes at least one of the following conditions: the highest M acceptance degree values, the acceptance degree values exceeding the first preset threshold, and M is an integer greater than or equal to 1.

4. The method according to claim 1, wherein The determining the navigation recommended route from the multiple candidate routes based on the acceptance degree values of the multiple candidate routes includes: Screening out the candidate routes that meet the screening rules from the multiple candidate routes to obtain pre-recommended routes, where the screening rules include that the passing parameters of the third target roads with historical passing times not exceeding the second preset number in the candidate routes exceed the preset normal range; Determining the pre-recommended routes whose acceptance degree values meet the second preset condition as the navigation recommended route from the pre-recommended routes, where the second preset condition includes at least one of the following conditions: the highest N acceptance degree values, the acceptance degree values exceeding the second preset threshold, and N is an integer greater than or equal to 1.

5. The method according to claim 4, wherein The screening rules include any one of the following rules: The total passing length of the third target roads exceeds the preset length; The fourth ratio between the total passing length of the third target roads and the total length of the candidate routes exceeds the preset ratio; The estimated total travel time of the third target road exceeds the first preset time; There is a target road in the third target road whose estimated travel time exceeds the second preset time.

6. The method according to claim 4, wherein Screening out candidate routes that meet the screening rules from the multiple candidate routes to obtain a pre-recommended route includes: Obtaining the current navigation scenario; Based on the correspondence between the scenario security level and the screening rules, obtaining the screening rules corresponding to the scenario security level where the current navigation scenario is located; Screening out candidate routes that meet the screening rules corresponding to the current navigation scenario from the multiple candidate routes to obtain a pre-recommended route.

7. The method according to claim 1, wherein The method further includes: Obtaining sample data, where the sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the sample routes, and the sample scores of the sample routes; Training the route recommendation model based on the sample data.

8. The method according to claim 7, wherein The method further includes: Obtaining the real route of the user from the departure location to the destination location; Determining that the sample score when the real route is used as a new sample route is a preset score; Based on the similarity between the candidate route and the real route, determining the sample score when the candidate route is used as a new sample route; Obtaining new sample data, where the new sample data includes the historical statistical features of the target roads passed by the user, the relevant features of the target roads in the new sample routes, and the sample scores of the new sample routes; Updating the route recommendation model based on the new sample data.

9. A method for providing location-based services, the method using the navigation recommended route obtained by the method according to any one of claims 1-8 to provide location-based services for the service recipient, the location-based services including: One or more of navigation, map rendering, and route planning.

10. A computer program product comprising computer programs / instructions, wherein, When the computer program / instructions are executed by a processor, the method steps described in any one of claims 1-9 are implemented.

Images