Driving route recommendation method and device, equipment and storage medium

Abstract

This application discloses a driving route recommendation method, apparatus, device, and storage medium, relating to the field of intelligent driving. The method includes: selecting a target driving area from a map based on the user's driving needs; determining a first layer and a second layer corresponding to the target driving area, wherein the first layer reflects the user takeover status of the vehicle when performing driving assistance functions in the target driving area, and the second layer reflects the availability of the vehicle's memory driving function in the target driving area; and generating a recommended driving route for the user in the target driving area based on the first and second layers. This application combines the user takeover status and the availability of the vehicle's memory driving function to generate a recommended driving route for the user in the target driving area, thereby providing early warnings or avoiding road sections where the vehicle may automatically exit memory driving, preventing situations where the user needs to actively take over the vehicle without warning during driving, and improving the user's driving continuity.

Description

Technical Field

[0001] This application relates to the field of intelligent driving, and in particular to a method, apparatus, device and storage medium for recommending driving routes. Background Technology

[0002] Commute Navigation on Autopilot (CNOA) is a city-level driver assistance product. It can automatically assist driving from point A to point B based on a learned specific driving route, enabling functions such as autonomous steering, lane changing, and obstacle avoidance.

[0003] However, in actual driving scenarios involving memory-based navigation, complex driving conditions and variable environments can lead to unforeseen circumstances. These include situations like multiple vehicles vying for control in high-traffic areas, sudden road impingement in normally clear sections, or sections where the memory-based navigation function is temporarily unavailable. If the conventional driving route is followed in these situations, the vehicle may abruptly disengage from automated driving assistance and require manual intervention / takeover by the user, resulting in poor driving continuity and significantly impacting the user's driving experience. Therefore, the industry urgently needs a method for recommending driving routes that can improve driving continuity during the memory-based navigation process. Summary of the Invention

[0004] The main objective of this application is to provide a driving route recommendation method, apparatus, device, and storage medium, which aims to provide a driving route recommendation method that can improve driving continuity during the memorization of driving processes.

[0005] To achieve the above objectives, this application provides a driving route recommendation method, the method comprising the following steps:

[0006] Select the target driving area from the map based on the user's driving needs;

[0007] A first layer and a second layer corresponding to the target driving area are determined. The first layer is used to reflect the user takeover status of the vehicle in the target driving area when performing driving assistance functions, and the second layer is used to reflect the availability of the vehicle's memory driving function in the target driving area.

[0008] Based on the first layer and the second layer, a recommended driving route for the user in the target driving area is generated.

[0009] In one embodiment, before the step of selecting the target driving area from the map according to the user's driving needs, the method further includes:

[0010] Collect embedded data uploaded by the target vehicle, wherein the embedded data is the vehicle status data corresponding to the target vehicle when it is taken over during the execution of the driving assistance function;

[0011] Based on the embedded data, the user takeover situation of the target vehicle when performing driver assistance functions is visualized to obtain a takeover hotspot layer;

[0012] The portion of the takeover hotspot layer corresponding to the target driving area is the first layer.

[0013] In one embodiment, the step of visualizing the user takeover situation of the target vehicle when performing driver assistance functions based on the embedded data to obtain a takeover hotspot layer includes:

[0014] The frequency of user takeover of the target vehicle in different road sections is statistically analyzed based on the data collected at the data points, and the reasons for user takeover of the target vehicle are determined based on the data type of the data collected at the data points.

[0015] Based on the user takeover frequency and the reasons for user takeover, the user takeover situation of the target vehicle is visualized to obtain a takeover hotspot layer.

[0016] In one embodiment, before the step of selecting the target driving area from the map according to the user's driving needs, the method further includes:

[0017] Download the self-learning map and route management list of the area where the target vehicle is located. The self-learning map is used to update and store the self-learning information of the target vehicle, and the route management list contains several driving routes of the target vehicle.

[0018] The self-learning confidence of each road segment in the self-learning map is visualized based on the route management list to obtain a map confidence layer. The self-learning confidence is used to indicate the availability of the target vehicle's memory driving function.

[0019] The portion of the map confidence layer corresponding to the target driving area is the second layer.

[0020] In one embodiment, the step of generating a recommended driving route for the user in the target driving area based on the first layer and the second layer includes:

[0021] The user's driving route in the target driving area is filtered according to the first layer to obtain the first route;

[0022] The second route is obtained by filtering the user's driving route in the target driving area based on the second layer;

[0023] Based on the first route and the second route, a recommended driving route for the user in the target driving area is generated.

[0024] In one embodiment, the driving route recommendation method further includes:

[0025] When activity recommendation information is received, target users matching the activity recommendation information are identified;

[0026] Based on the activity recommendation information, a recommended activity route is generated in the self-learning map, and the recommended activity route is pushed to the target user.

[0027] Furthermore, to achieve the above objectives, this application also proposes a route recommendation device, which includes:

[0028] The requirements analysis module is used to select the target driving area from the map based on the user's driving needs;

[0029] The layer acquisition module is used to determine the first layer and the second layer corresponding to the target driving area. The first layer is used to reflect the user takeover status of the vehicle in the target driving area when performing driving assistance functions, and the second layer is used to reflect the availability of the vehicle's memory driving function in the target driving area.

[0030] The route recommendation module is used to generate a recommended driving route for the user in the target driving area based on the first layer and the second layer.

[0031] In addition, to achieve the above objectives, this application also proposes a route recommendation device, the device comprising: a memory, a processor, and a route recommendation program stored in the memory and executable on the processor, the route recommendation program being configured to implement the steps of the route recommendation method as described above.

[0032] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, storing a route recommendation program, which, when executed by a processor, implements the steps of the route recommendation method as described above.

[0033] In addition, to achieve the above objectives, the present invention also provides a computer program product, the computer program product including a route recommendation program, which, when executed by a processor, implements the steps of the route recommendation method as described above.

[0034] This application selects a target driving area from a map based on the user's driving needs; determines a first layer and a second layer corresponding to the target driving area, where the first layer reflects the user's takeover status when the vehicle in the target driving area is performing driving assistance functions, and the second layer reflects the availability of the vehicle's memory driving function in the target driving area; and generates a recommended driving route for the user in the target driving area based on the first layer and the second layer. Compared to traditional driving route recommendation methods, this application's method combines the user's takeover status when the vehicle in the target driving area is performing driving assistance functions with the availability of the vehicle's memory driving function in the target driving area to generate a recommended driving route for the user in the target driving area. This enables early warning or avoidance of road sections where the vehicle may automatically exit memory driving, preventing situations where the user needs to actively take over the vehicle without warning during driving, thereby improving the user's driving continuity. Attached Figure Description

[0035] Figure 1 This is a schematic diagram of the driving route recommendation device for the hardware operating environment involved in the embodiments of this application;

[0036] Figure 2 This is a flowchart illustrating the first embodiment of the driving route recommendation method of this application;

[0037] Figure 3 This is a diagram illustrating the takeover reminder method for the recommended driving route in this application;

[0038] Figure 4 This is a flowchart illustrating the second embodiment of the driving route recommendation method of this application;

[0039] Figure 5 This is a partial layer diagram illustrating the takeover of the hotspot layer in the driving route recommendation method of this application;

[0040] Figure 6 This is a schematic diagram illustrating the updating of the self-learning map in the driving route recommendation method of this application;

[0041] Figure 7 This is a partial schematic diagram of the map confidence layer in the driving route recommendation method of this application;

[0042] Figure 8 This is a flowchart illustrating the third embodiment of the driving route recommendation method of this application;

[0043] Figure 9 This is a structural block diagram of the first embodiment of the driving route recommendation device of this application.

[0044] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0045] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0046] Reference Figure 1 , Figure 1 This is a schematic diagram of the driving route recommendation device structure for the hardware operating environment involved in the embodiments of this application.

[0047] like Figure 1 As shown, the route recommendation device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the route recommendation device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0049] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a route recommendation program.

[0050] exist Figure 1 In the driving route recommendation device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the driving route recommendation device of this application can be set in the driving route recommendation device, and the driving route recommendation device calls the driving route recommendation program stored in the memory 1005 through the processor 1001 and executes the driving route recommendation method provided in the embodiment of this application.

[0051] The driving route recommendation method provided in this application can be deployed on a computer device for execution. The computer device can be an in-vehicle device (such as an in-vehicle controller, in-vehicle processor, or other in-vehicle unit, etc.), or it can be a terminal outside the vehicle, an independent server, a cloud, a server cluster, a distributed system, an Internet of Things device, or a vehicle network device, etc. This embodiment does not limit this, and those skilled in the art can set up the computer device to implement the driving route recommendation method according to actual needs.

[0052] This application provides a method for recommending driving routes, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the driving route recommendation method of this application.

[0053] In this embodiment, the driving route recommendation method includes the following steps:

[0054] Step S10: Select the target driving area from the map according to the user's driving needs.

[0055] Understandably, the aforementioned driving requirements may include, but are not limited to, information such as origin, destination, transit points, and driving preferences (e.g., more wide roads, fewer traffic lights, shorter driving distances, shorter driving times, etc.), and the aforementioned map may be an electronic map stored in the cloud.

[0056] It should be understood that the aforementioned target driving area may refer to the area covered by all feasible driving routes that meet the user's driving needs on the map.

[0057] Step S20: Determine the first layer and the second layer corresponding to the target driving area. The first layer is used to reflect the user takeover status of the vehicle in the target driving area when performing driving assistance functions, and the second layer is used to reflect the availability of the vehicle's memory driving function in the target driving area.

[0058] It should be noted that both the first and second layers mentioned above are visual layers, meaning that users can intuitively obtain the user takeover status of each road segment in the target driving area and the availability of the driving memory function from the first and second layers.

[0059] Among them, user takeover situations can be obtained from the scenarios where temporary situations occur during the vehicle's memory driving process, such as scenarios where users frequently intervene in the accelerator and scenarios where users frequently intervene in the steering wheel: On the one hand, due to the high traffic volume and complex scenarios during commuting hours, users are in a hurry to drive, so in some road sections, scenarios such as multi-vehicle games, abnormal intersections, and sudden braking are likely to occur, where users frequently intervene in the accelerator; on the other hand, due to the changeable urban environment and the many extreme scenarios, in some road sections, scenarios such as large vehicles approaching, sharp curves, and narrow lanes are likely to occur, where users frequently intervene in the steering wheel.

[0060] The availability of the vehicle's memory driving function can be obtained from the vehicle's learning scenarios in various road sections. The learning completion time is related to factors such as the route length, road conditions, and environmental complexity of each road section. For example, it takes a long time in scenarios such as congested roads, roads with mixed pedestrian and vehicle traffic, complex large intersections, roundabouts, and continuous high-curvature curves. It may not be able to learn successfully in road sections such as tidal lanes, internal roads of parks, and roads that have been occupied for a long time.

[0061] Step S30: Generate a recommended driving route for the user in the target driving area based on the first layer and the second layer.

[0062] In its implementation, the first layer reflects the user takeover status of vehicles in the target driving area when performing driver assistance functions, while the second layer reflects the availability of the vehicle's memory driving function within the target driving area. Therefore, when a user drives within the target driving area, the onboard system can quickly determine which road sections require active user takeover based on both layers, and, while meeting the user's driving needs, try to avoid these sections in the recommended driving route. Specifically, for road sections that cannot be avoided and require active user takeover, an early warning can be provided in the recommended driving route to remind the user to prepare for takeover in advance, avoiding potential driving safety issues caused by unannounced takeover. See the specific example below. Figure 3 , Figure 3 This is a diagram illustrating the takeover warning method for the recommended driving route in this application. Figure 3 As you can see, the recommended driving route marks two warning sections. The red warning section indicates a very complex section (i.e., a high-intervention section), while the yellow warning section indicates a relatively complex section (i.e., a higher-intervention section).

[0063] This embodiment selects a target driving area from the map based on the user's driving needs; it determines a first layer and a second layer corresponding to the target driving area. The first layer reflects the user's takeover status when the vehicle in the target driving area is performing driving assistance functions, and the second layer reflects the availability of the vehicle's memory driving function in the target driving area. Based on the first layer and the second layer, a recommended driving route for the user in the target driving area is generated. Compared to traditional driving route recommendation methods, this embodiment combines the user's takeover status when the vehicle in the target driving area is performing driving assistance functions with the availability of the vehicle's memory driving function to generate a recommended driving route for the user in the target driving area. This allows for early warning or avoidance of road sections where the vehicle may automatically exit memory driving, preventing situations where the user needs to take over the vehicle without warning during driving, thereby improving the user's driving continuity.

[0064] refer to Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the driving route recommendation method of this application.

[0065] In one feasible implementation, the following may be included before step S10:

[0066] Step S1: Collect the embedded data uploaded by the target vehicle. The embedded data is the vehicle status data corresponding to the target vehicle when it is taken over during the execution of the driving assistance function.

[0067] It should be noted that the target vehicles mentioned above can include any vehicle equipped with any driver assistance function, and the vehicle status data mentioned above may include, but is not limited to, the target vehicle's current location, surrounding environment, driving parameters, etc. Since the data is collected in real time and continuously, the real-time performance and effectiveness of the hotspot layer can be guaranteed.

[0068] The aforementioned driving assistance functions may include ACC (Adaptive Cruise Control), ICC (Intelligent Cruise Control), ALCA (Alternate Lane Change Assist), ICC MAX (Enhanced Intelligent Cruise Control), NOA (Navigation Assist), CNOA (Commuter Navigation Assist), etc., and this embodiment does not limit them.

[0069] Step S2: Based on the embedded data, visualize the user takeover situation of the target vehicle when performing driving assistance functions to obtain a takeover hotspot layer.

[0070] The portion of the takeover hotspot layer corresponding to the target driving area is the first layer.

[0071] In practical implementation, the user takeover level (e.g., high takeover, relatively high takeover, moderate takeover, relatively low takeover, low takeover, etc.) corresponding to each road segment can be determined based on the aforementioned embedded data when the target vehicle performs driver assistance functions. Then, different visualization elements (e.g., different colors, different icons, etc.) can be assigned to different user takeover levels. For example, refer to... Figure 5 , Figure 5 This is a partial layer diagram illustrating the hotspot layer takeover method in the driving route recommendation method of this application. Users can... Figure 5 The diagram clearly shows that dark red sections indicate high-level control sections, light red sections indicate relatively high-level control sections, dark yellow sections indicate moderate-level control sections, light yellow sections indicate relatively low-level control sections, and green sections indicate low-level control sections.

[0072] Furthermore, for ease of understanding, the aforementioned takeover hotspot layer can be regarded as the overall takeover hotspot layer of the city, while the aforementioned first layer is a part of the overall layer corresponding to the target driving area related to user travel needs, that is, the first layer is contained in the takeover hotspot layer.

[0073] In one feasible implementation, step S2 can be achieved through the following steps S21 and S22:

[0074] Step S21: Calculate the frequency of user takeover of the target vehicle in different road sections based on the embedded data, and determine the reason for user takeover of the target vehicle based on the data type of the embedded data.

[0075] It should be noted that the data types of the aforementioned embedded data can include, but are not limited to, lateral override, longitudinal override, normal exit, takeover exit, user-initiated exit, and system abnormal exit. Lateral override indicates that the driver actively controls the direction via the steering wheel, while longitudinal override indicates that the driver actively accelerates by pressing the accelerator / electric pedal. The aforementioned takeover hotspot layer can display the takeover / intervention speed and steering wheel frequency when the user uses any assisted driving function on different road sections, calculate average and maximum takeover values, and drill down to analyze the reasons for takeover. Users can be alerted to pay close attention in relevant road sections, or the relevant routes can be temporarily unavailable.

[0076] For example, Table 1 below can be used to illustrate the user takeover reasons and required tracking points corresponding to the data types of tracking data. Here, POI (Point of Interest) represents a point of interest.

[0077] Table 1:

[0078]

[0079] Step S22: Visualize the user takeover situation of the target vehicle based on the user takeover frequency and the user takeover reason to obtain a takeover hotspot layer.

[0080] In the specific implementation, after receiving various types of embedded data, the system can summarize and process the POI information at the time of intervention / takeover, calculate the average and maximum user takeover data for different road segments, and filter out higher / higher takeover hotspots that are above the average. The filtered higher / higher takeover road segments are then displayed in real-time on the cloud map in the form of a takeover hotspot layer. Different colors can be used to mark different levels of user takeover frequency for visualization; and different reasons for user takeover can be displayed as text in different alert boxes, thus obtaining the aforementioned takeover hotspot layer.

[0081] In one feasible implementation, the following may be included before step S10:

[0082] Step S3: Download the self-learning map and route management list of the area where the target vehicle is located. The self-learning map is used to update and store the self-learning information of the target vehicle, and the route management list contains several driving routes of the target vehicle.

[0083] It should be noted that the aforementioned self-learning map contains self-learning information about the target vehicle on various road segments. This self-learning information may include operational information such as road information and driver lane selection / steering, which is not limited in this embodiment.

[0084] Step S4: Visualize the self-learning confidence of each road segment in the self-learning map according to the route management list to obtain a map confidence layer. The self-learning confidence is used to indicate the availability of the target vehicle's memory driving function.

[0085] The portion of the map confidence layer corresponding to the target driving area is the second layer.

[0086] In the specific implementation, you can refer to Figure 6 , Figure 6 This is a schematic diagram illustrating the updating of the self-learning map in the driving route recommendation method of this application. Combined with... Figure 6The process involves the following steps: After vehicle startup, the CNOA map management center within the Automated Driving Control Unit (ADCU) downloads the created self-learning map and route management list. Simultaneously, when the cloud is detected to be online, the route status is synchronized to the cloud-based mapping data management center for online processing. Upon receiving the signal, the mapping data management center checks if the map has been updated across multiple driving trips, including static and dynamic layers. If so, the update information is synchronized to the ADCU. After processing, the ADCU transmits the data to the DHU (Desktop Head Unit), interacting with it via LINK IDs (unique codes identifying specific roads or paths on the map). LINK IDs contain route topology information, lane information, and other dynamic and static layer information, as well as geometric topology layer information, converting the data into a user-readable visual language. This data is then uniformly displayed in the learning route storage management system, creating a user-visual and operable route management card. CNOASDPathState represents the route status that needs updating in the self-learning map.

[0087] To more intuitively observe the availability of the vehicle memory driving function for each road segment in the map confidence layer, please refer to [link / reference]. Figure 7 , Figure 7 This is a partial schematic diagram of the map confidence layer in the driving route recommendation method of this application. Combined with... Figure 7 As you can see, the map confidence layer can display the self-learning confidence level of each road segment in the form of a heatmap. The self-learning confidence level can be displayed as a percentage to indicate the percentage of road segment learning completion to the user. The confidence level is dynamically updated as the self-learning map is updated. The map confidence layer can also be color-coded according to the status of each road segment, for example, in... Figure 7 In the diagram, blue indicates that the target vehicle's memory driving function can be used on that road segment; gray indicates that the target vehicle's memory driving function cannot be used on that road segment. If the road segment has completed learning after the update, it can be changed from gray to blue.

[0088] Furthermore, for ease of understanding, the aforementioned map confidence layer can also be regarded as the overall map confidence layer of the city, while the aforementioned second layer is a part of the overall layer corresponding to the target driving area related to the user's travel needs, that is, the second layer is included in the map confidence layer.

[0089] It should be noted that, based on the settings of the first and second layers mentioned above, only a portion of the layers need to be loaded when generating recommended driving routes, instead of loading the entire takeover hotspot layer and map confidence layer. This improves loading efficiency and enables faster generation of recommended driving routes.

[0090] This embodiment collects embedded data uploaded by the target vehicle, which is the vehicle status data corresponding to when the target vehicle is taken over during the execution of driver assistance functions. Based on the embedded data, the frequency of user takeover of the target vehicle in different road segments is statistically analyzed, and the reason for user takeover is determined according to the data type of the embedded data. The user takeover situation of the target vehicle is visualized based on the user takeover frequency and the reason for user takeover, resulting in a takeover hotspot layer. The portion of the takeover hotspot layer corresponding to the target driving area is the first layer. A self-learning map and route management list of the target vehicle's location are downloaded. The self-learning map is used to update and store the self-learning information of the target vehicle, and the route management list contains several driving routes of the target vehicle. The self-learning confidence of each road segment in the self-learning map is visualized based on the route management list, resulting in a map confidence layer. The self-learning confidence is used to indicate the availability of the target vehicle's memory driving function. The portion of the map confidence layer corresponding to the target driving area is the second layer. Compared to traditional route recommendation methods, the method described in this embodiment visualizes the frequency and reasons for user takeovers for each road segment by introducing a takeover hotspot layer. This allows for advance warnings or avoidance of road segments requiring user intervention, providing a smoother and more seamless driving experience. Furthermore, this embodiment introduces a map confidence layer to display the self-learning confidence level for each road segment, intuitively informing users of the available and unavailable road segments for the driving memory function. Data visualization clarifies the usable boundaries and scope of the driving memory function, thereby increasing user engagement in its use.

[0091] refer to Figure 8 , Figure 8 This is a flowchart illustrating the third embodiment of the driving route recommendation method of this application.

[0092] In one feasible implementation, step S30 can be achieved through the following steps S301, S302, and S303:

[0093] Step S301: Filter the user's driving route in the target driving area according to the first layer to obtain the first route.

[0094] Step S302: Filter the user's driving route in the target driving area according to the second layer to obtain the second route.

[0095] In the specific implementation, since the first layer reflects the user takeover situation of vehicles in the target driving area when performing driver assistance functions, high-takeover sections in the target driving area can be filtered out based on the first layer and set as non-priority recommended sections. High-takeover sections can refer to sections whose total takeover count within a preset period (e.g., 1 hour) is higher than the average takeover count of all sections in the first layer.

[0096] Similarly, since the second layer reflects the availability of the vehicle memory function in the target driving area, road segments in the target driving area that do not support the memory function can be filtered out based on the second layer, and these road segments that do not support the memory function are set as non-priority recommended road segments. Road segments that do not support the memory function can refer to road segments whose self-learning confidence level is lower than a preset percentage (e.g., 100%).

[0097] After filtering out high-interchange road sections and road sections that do not support the memory driving function in the target driving area according to the first layer and the second layer respectively, the feasible driving routes can be determined based on the remaining road sections, that is, the first route and the second route mentioned above are obtained.

[0098] Step S303: Generate a recommended driving route for the user in the target driving area based on the first route and the second route.

[0099] In practical implementation, a visual operation tool can be used to edit, open, and close road segments in the first and second routes mentioned above, thereby obtaining a recommended driving route for the user in the target driving area. For example, road segments that have maintained a high-control status for a preset duration (e.g., 30 minutes) can be edited / closed, while closed high-control road segments that have maintained a low-control status for a preset duration can be reopened.

[0100] Specifically, if all feasible driving routes inevitably include the aforementioned non-priority recommended road sections (i.e., high-takeover road sections and road sections that do not support the memory driving function), then it is permissible to add non-priority recommended road sections to the recommended driving routes. At the same time, takeover reminders will be issued to users in advance at the non-priority recommended road sections on the map so that users can prepare to take over and avoid situations where users need to take over the vehicle without warning during driving.

[0101] In one feasible implementation, the route recommendation method may further include:

[0102] Step S40: When activity recommendation information is received, determine the target user that matches the activity recommendation information.

[0103] Step S50: Generate a recommended activity route in the self-learning map based on the activity recommendation information, and push the recommended activity route to the target user.

[0104] It should be understood that the aforementioned activity recommendation information can be information that the enterprise itself defines to recommend to target users, such as promotional and operational information, testing information, etc. When target users have needs such as fixed route testing, targeted recommendations for popular commuting routes, targeted recommendations for exclusive routes, and limited-time route recommendations for operational activities, operators can distribute the activity recommendation routes generated in the self-learning map based on the activity recommendation information to the display unit of the target vehicle through the autonomous driving domain controller for target users to use, thereby achieving high-quality recommendations for target users. For example, suppose a new 4S store opens in a city. In order to promote the 4S store, operators can push activity recommendation routes to the 4S store to all car owners in the city who have activated the CNOA function during the opening period. In addition, operators can also upload and distribute self-learning maps to users' vehicles based on user travel frequency, route scenario difficulty, and operational activity needs, thereby achieving the recommendation of more customized driving routes for users.

[0105] This embodiment filters the user's driving routes in the target driving area based on the first layer to obtain a first route; it then filters the user's driving routes in the target driving area based on the second layer to obtain a second route; a recommended driving route for the user in the target driving area is generated based on the first and second routes; when activity recommendation information is received, a target user matching the activity recommendation information is identified; an activity recommendation route is generated in the self-learning map based on the activity recommendation information, and the activity recommendation route is pushed to the target user. Compared to traditional driving route recommendation methods, the method described in this embodiment filters the first and second layers to set high-interception road sections and road sections that do not support memory driving functions in the target driving area as non-priority recommendation road sections, thereby making the final recommended driving route better meet the user's intelligent driving needs.

[0106] Furthermore, this application embodiment also proposes a storage medium storing a route recommendation program, which, when executed by a processor, implements the steps of the route recommendation method described above.

[0107] Reference Figure 9 , Figure 9 This is a structural block diagram of the first embodiment of the driving route recommendation device of this application.

[0108] like Figure 9 As shown, the driving route recommendation device proposed in this application includes:

[0109] The requirements analysis module 901 is used to select the target driving area from the map based on the user's driving requirements;

[0110] The layer acquisition module 902 is used to determine the first layer and the second layer corresponding to the target driving area. The first layer is used to reflect the user takeover status of the vehicle in the target driving area when performing driving assistance functions, and the second layer is used to reflect the availability of the vehicle's memory driving function in the target driving area.

[0111] The route recommendation module 903 is used to generate a recommended driving route for the user in the target driving area based on the first layer and the second layer.

[0112] This embodiment selects a target driving area from the map based on the user's driving needs; it determines a first layer and a second layer corresponding to the target driving area. The first layer reflects the user's takeover status when the vehicle in the target driving area is performing driving assistance functions, and the second layer reflects the availability of the vehicle's memory driving function in the target driving area. Based on the first layer and the second layer, a recommended driving route for the user in the target driving area is generated. Compared to traditional driving route recommendation methods, this embodiment combines the user's takeover status when the vehicle in the target driving area is performing driving assistance functions with the availability of the vehicle's memory driving function to generate a recommended driving route for the user in the target driving area. This allows for early warning or avoidance of road sections where the vehicle may automatically exit memory driving, preventing situations where the user needs to take over the vehicle without warning during driving, thereby improving the user's driving continuity.

[0113] Based on the first embodiment of the driving route recommendation device described in this application, a second embodiment of the driving route recommendation device of this application is proposed.

[0114] In this embodiment, the layer acquisition module 902 is further used to collect the embedded data uploaded by the target vehicle. The embedded data is the vehicle status data corresponding to when the target vehicle is taken over during the execution of the driving assistance function. Based on the embedded data, the user takeover situation of the target vehicle when executing the driving assistance function is visualized to obtain a takeover hotspot layer. The part of the takeover hotspot layer corresponding to the target driving area is the first layer.

[0115] Furthermore, the layer acquisition module 902 is also used to count the user takeover frequency of the target vehicle in different road sections based on the embedded data, and to determine the user takeover reason of the target vehicle based on the data type of the embedded data; and to visualize the user takeover situation of the target vehicle based on the user takeover frequency and the user takeover reason to obtain a takeover hotspot layer.

[0116] Furthermore, the layer acquisition module 902 is also used to download a self-learning map and a route management list of the area where the target vehicle is located. The self-learning map is used to update and store the self-learning information of the target vehicle, and the route management list contains several driving routes of the target vehicle. The self-learning confidence of each road segment in the self-learning map is visualized according to the route management list to obtain a map confidence layer. The self-learning confidence is used to indicate the availability of the target vehicle's memory driving function. The part of the map confidence layer corresponding to the target driving area is the second layer.

[0117] Furthermore, the route recommendation module 903 is also used to filter the user's driving routes in the target driving area according to the first layer to obtain a first route; filter the user's driving routes in the target driving area according to the second layer to obtain a second route; and generate a recommended driving route for the user in the target driving area based on the first route and the second route.

[0118] Furthermore, the route recommendation module 903 is also used to determine the target user matching the activity recommendation information when receiving activity recommendation information; generate an activity recommendation route in the self-learning map based on the activity recommendation information; and push the activity recommendation route to the target user.

[0119] Other embodiments or specific implementations of the driving route recommendation device of this application can be found in the above-described method embodiments, and will not be repeated here.

[0120] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0121] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0122] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0123] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for recommending driving routes, characterized in that, The method includes the following steps: Select the target driving area from the map based on the user's driving needs; A first layer and a second layer corresponding to the target driving area are determined. The first layer is used to reflect the user takeover status of the vehicle in the target driving area when performing driving assistance functions, and the second layer is used to reflect the availability of the vehicle's memory driving function in the target driving area. Based on the first layer and the second layer, a recommended driving route for the user in the target driving area is generated; The first layer is the part of the takeover hotspot layer that corresponds to the target driving area, and the takeover hotspot layer is a visual heat map of the takeover situation when the user uses any assisted driving function on different road sections. The second layer is the part of the map confidence layer that corresponds to the target driving area. The map confidence layer is a visualization heatmap of the availability of vehicle memory driving function in each road segment.

2. The driving route recommendation method as described in claim 1, characterized in that, Before the step of selecting the target driving area from the map based on the user's driving needs, the method further includes: Collect embedded data uploaded by the target vehicle, wherein the embedded data is the vehicle status data corresponding to the target vehicle when it is taken over during the execution of the driving assistance function; Based on the embedded data, the user takeover situation of the target vehicle when performing driver assistance functions is visualized to obtain a takeover hotspot layer; The portion of the takeover hotspot layer corresponding to the target driving area is the first layer.

3. The driving route recommendation method as described in claim 2, characterized in that, The step of visualizing the user takeover situation of the target vehicle when performing driver assistance functions based on the embedded data to obtain a takeover hotspot layer includes: The frequency of user takeover of the target vehicle in different road sections is statistically analyzed based on the data collected at the data points, and the reasons for user takeover of the target vehicle are determined based on the data type of the data collected at the data points. Based on the user takeover frequency and the reasons for user takeover, the user takeover situation of the target vehicle is visualized to obtain a takeover hotspot layer.

4. The driving route recommendation method as described in claim 3, characterized in that, Before the step of selecting the target driving area from the map based on the user's driving needs, the method further includes: Download the self-learning map and route management list of the area where the target vehicle is located. The self-learning map is used to update and store the self-learning information of the target vehicle, and the route management list contains several driving routes of the target vehicle. The self-learning confidence of each road segment in the self-learning map is visualized based on the route management list to obtain a map confidence layer. The self-learning confidence is used to indicate the availability of the target vehicle's memory driving function. The portion of the map confidence layer corresponding to the target driving area is the second layer.

5. The driving route recommendation method as described in claim 1, characterized in that, The step of generating a recommended driving route for the user in the target driving area based on the first layer and the second layer includes: The user's driving route in the target driving area is filtered according to the first layer to obtain the first route; The second route is obtained by filtering the user's driving route in the target driving area based on the second layer; Based on the first route and the second route, a recommended driving route for the user in the target driving area is generated.

6. The driving route recommendation method as described in claim 1, characterized in that, The method further includes: When activity recommendation information is received, target users matching the activity recommendation information are identified; Based on the activity recommendation information, a recommended activity route is generated in the self-learning map, and the recommended activity route is pushed to the target user.

7. A driving route recommendation device, characterized in that, The driving route recommendation device includes: The requirements analysis module is used to select the target driving area from the map based on the user's driving needs; The layer acquisition module is used to determine the first layer and the second layer corresponding to the target driving area. The first layer is used to reflect the user takeover status of the vehicle in the target driving area when performing driving assistance functions, and the second layer is used to reflect the availability of the vehicle's memory driving function in the target driving area. The route recommendation module is used to generate a recommended driving route for the user in the target driving area based on the first layer and the second layer; The first layer is the part of the takeover hotspot layer that corresponds to the target driving area, and the takeover hotspot layer is a visual heat map of the takeover situation when the user uses any assisted driving function on different road sections. The second layer is the part of the map confidence layer that corresponds to the target driving area. The map confidence layer is a visualization heatmap of the availability of vehicle memory driving function in each road segment.

8. A driving route recommendation device, characterized in that, The device includes: a memory, a processor, and a route recommendation program stored in the memory and executable on the processor, the route recommendation program being configured to implement the steps of the route recommendation method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and the storage medium stores a route recommendation program, which, when executed by a processor, implements the steps of the route recommendation method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a route recommendation program, which, when executed by a processor, implements the steps of the route recommendation method as described in any one of claims 1 to 6.

Images