Lane guidance method and apparatus, device, and storage medium

Abstract

The present application provides a lane guidance method and apparatus, a device, and a storage medium, applicable to fields such as maps or autonomous driving, and configured to solve the problem of low guidance accuracy during lane guidance. The method at least comprises: receiving a lane guidance instruction for a target road section, and determining a plurality of candidate lane segments between a starting lane segment and a destination lane segment of the target road section; on the basis of at least one pre-stored conditional entry probability associated with each candidate lane segment, determining a target entry probability for a target vehicle to enter the candidate lane segment, wherein each conditional entry probability represents, in view of historical driving data associated with the target road section, a conditional probability for past vehicles to enter the candidate lane segment from an adjacent lane segment neighboring the candidate lane segment under the condition that the vehicles entered the destination lane segment; and generating a lane guidance result, the lane guidance result comprising a guidance lane segment among the plurality of candidate lane segments that has a target entry probability satisfying a guidance condition.

Description

Lane guidance method, device, equipment and storage medium

[0001] Related documents

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on January 10, 2024, with application number 202410033893.3 and invention name “A lane guidance method, device, equipment and storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to a lane guidance method, device, equipment, and storage medium.

[0004] Background of the Invention

[0005] With the continuous development of science and technology, more and more devices can provide lane-level guidance services to achieve more refined lane-level navigation functions. For example, when a vehicle needs to turn right at a certain intersection, the vehicle is guided to enter the right-turn lane N meters in advance. The lane information can be obtained by collecting road network data, while the various parameters used by the guidance function are manually set based on experience. The parameters required for these guidance functions include, for example, guiding the vehicle to enter the turning lane when the distance to the turning location is a preset first length when the vehicle needs to turn; guiding the vehicle to travel at least a second length in the changed lane when the vehicle changes lanes, and so on. Summary of the Invention

[0006] Embodiments of the present application provide a lane guidance method, apparatus, device, and storage medium for solving the problem of low guidance accuracy during lane guidance.

[0007] Each embodiment provides a lane guidance method, including:

[0008] receiving a lane guidance instruction for a target road section, and determining a plurality of candidate lane segments between a starting lane segment and a destination lane segment of the target road section;

[0009] For each candidate lane segment among the plurality of candidate lane segments, the following operations are performed: based on at least one pre-stored conditional entry probability associated with the candidate lane segment, a target entry probability of the target vehicle entering the candidate lane segment is determined; wherein each conditional entry probability represents: in historical driving data associated with the target road section, a conditional probability that a past vehicle, conditionally entering the target lane segment, enters the candidate lane segment from an adjacent lane segment adjacent to the candidate lane segment;

[0010] A lane guidance result is generated, wherein the lane guidance result includes: a guiding lane segment whose target entry probability meets the guidance condition among the multiple candidate lane segments.

[0011] Each embodiment further provides a lane guidance device, including:

[0012] An acquisition module is configured to receive a lane guidance instruction for a target road section and determine a plurality of candidate lane sections between a starting lane section and a destination lane section of the target road section;

[0013] a processing module configured to perform the following operations for each of the plurality of candidate lane segments: determining a target entry probability of a target vehicle entering the candidate lane segment based on at least one pre-stored conditional entry probability associated with the candidate lane segment; wherein each conditional entry probability represents: a conditional probability, in historical driving data associated with the target road section, that a past vehicle enters the candidate lane segment from an adjacent lane segment adjacent to the candidate lane segment, conditional on entering the target lane segment;

[0014] The processing module is further configured to generate a lane guidance result, wherein the lane guidance result includes a guiding lane segment, among a plurality of candidate lane segments, in which a target entry probability satisfies a guidance condition.

[0015] Each embodiment further provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0016] Each embodiment further provides a computer device, including:

[0017] a memory for storing program instructions;

[0018] The processor is used to call the program instructions stored in the memory and execute the methods of each embodiment according to the obtained program instructions.

[0019] Each embodiment further provides a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the method of each embodiment.

[0020] In this embodiment of the present application, at least one conditional entry probability associated with each candidate lane segment is pre-determined. The conditional entry probability represents the conditional probability of each reference vehicle entering the candidate lane segment from an adjacent lane segment within the historical time period, conditional on entering the target lane segment. Therefore, based on the at least one conditional entry probability associated with each candidate lane segment, a target entry probability for the target vehicle entering each candidate lane segment is determined. Based on the obtained target entry probabilities, a guiding lane segment is selected to obtain a lane guidance result.

[0021] Data mining was performed on the historical driving data of each reference vehicle within the historical time period, and the driving patterns of each reference vehicle under different road conditions were analyzed. This was used as a reference for lane guidance of the currently traveling target vehicle. As a result, targeted lane guidance can be performed for different road conditions, achieving richer lane guidance effects. There is no need to manually set multiple guidance parameters. Lane guidance is performed based on these set guidance parameters in any case, avoiding guidance errors caused by the set guidance parameters not matching the actual road conditions, and improving the guidance accuracy during lane guidance.

[0022] Furthermore, the calculation process of lane guidance based on lane segments requires less data calculation and is more efficient than the calculation process based on vehicle positioning points, thereby improving the lane guidance efficiency to a certain extent.

[0023] BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The following drawings are only some examples of the technical solutions of the present invention, and the present invention is not limited to the features shown in the drawings. In the following drawings, similar reference numerals represent similar elements:

[0025] FIG1A is a schematic diagram of a first scenario of a lane guidance method in the related art;

[0026] FIG1B is a second schematic diagram of a lane guidance method in the related art;

[0027] FIG1C is an application scenario of the lane guidance method provided in an embodiment of the present application;

[0028] FIG2 is a first flow chart of a lane guidance method according to an embodiment of the present application;

[0029] FIG3A is a schematic diagram showing a first principle of a lane guidance method provided by an embodiment of the present application;

[0030] FIG3B is a second schematic diagram of a lane guidance method according to an embodiment of the present application;

[0031] FIG4A is a third schematic diagram of a lane guidance method according to an embodiment of the present application;

[0032] FIG4B is a fourth schematic diagram of a lane guidance method according to an embodiment of the present application;

[0033] FIG5A is a fifth schematic diagram of a lane guidance method according to an embodiment of the present application;

[0034] FIG5B is a sixth schematic diagram of a lane guidance method according to an embodiment of the present application;

[0035] FIG6A is a seventh schematic diagram of a lane guidance method according to an embodiment of the present application;

[0036] FIG6B is a schematic diagram showing a lane guidance method according to an embodiment of the present application; ...

[0037] FIG7A is a ninth schematic diagram of a lane guidance method according to an embodiment of the present application;

[0038] FIG7B is a second flow chart of a lane guidance method provided in an embodiment of the present application;

[0039] FIG7C is a schematic diagram showing a principle of a lane guidance method according to an embodiment of the present application;

[0040] FIG7D is a third flow chart of a lane guidance method provided in an embodiment of the present application;

[0041] FIG7E is a schematic diagram showing a principle of a lane guidance method according to an embodiment of the present application;

[0042] FIG7F is a schematic diagram 12 of a principle of a lane guidance method provided in an embodiment of the present application;

[0043] FIG8 is a first structural diagram of a lane guidance device provided in an embodiment of the present application;

[0044] FIG9 is a second structural diagram of the lane guidance device provided in an embodiment of the present application.

[0045] Modes for Carrying Out the Invention

[0046] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0047] Some of the terms used in the embodiments of the present application are explained below to facilitate understanding by those skilled in the art.

[0048] (1) Global Positioning System (GPS):

[0049] The Global Positioning System (GPS) provides accurate geographic location, vehicle speed, and precise time information anywhere in the world and in near-Earth space. GPS offers high precision, all-weather coverage, global coverage, and flexibility.

[0050] (2) High-precision map data:

[0051] Road lane-level map data generated when actual road conditions are mapped using high-precision mapping technology.

[0052] (3) Lane-level guidance service:

[0053] In navigation scenarios with high-precision map data, the navigation system provides lane-level navigation guidance and suggestion services. These lane-level guidance services include, but are not limited to: navigation guidance surfaces for high-precision road sections, consisting of a set of recommended lane segments; navigation guidance lines for high-precision road sections, consisting of a continuous string of recommended lane segments; navigation voice prompts and announcements for high-precision road sections; and signage functions for high-precision road sections, such as lane change suggestions and road marking prompts.

[0054] Intelligent Traffic System (ITS), also known as Intelligent Transportation System, effectively integrates advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control and vehicle manufacturing, strengthens the connection between vehicles, roads and users, and thus forms a comprehensive transportation system that ensures safety, improves efficiency, improves the environment and saves energy.

[0055] Intelligent Vehicle Infrastructure Cooperative Systems (IVICS), also known as VICS, are a development direction of Intelligent Transportation Systems (ITS). IVICS utilizes advanced wireless communications and next-generation internet technologies to implement dynamic, real-time information exchange between vehicles and roads. Based on the collection and integration of dynamic traffic information across time and space, IVICS conducts active vehicle safety control and collaborative road management. This fully realizes effective coordination between people, vehicles, and roads, ensuring traffic safety and improving traffic efficiency, thereby creating a safe, efficient, and environmentally friendly road transportation system.

[0056] It should be noted that the embodiments of the present application involve operations involving obtaining historical driving data and other data of each reference vehicle. When the above embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0057] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0058] The following is a brief introduction to the application areas of the lane guidance method provided in the embodiments of the present application.

[0059] With the continuous development of technology, more and more devices can provide lane-level guidance services to achieve more refined lane-level navigation functions. For example, when a vehicle needs to turn right at an intersection, it can be guided to enter the right-turn lane N meters in advance.

[0060] However, in related technologies, lane guidance methods usually set multiple guidance parameters in advance based on empirical values, including guiding the vehicle into a dedicated turning lane N1 meter before reaching the turning intersection for routes that require turning; guiding the vehicle to travel at least N2 meters in the lane after changing lanes for routes that require lane changing; and excluding lanes that need to be exited within N3 meters after entering the lane during lane guidance.

[0061] After pre-setting multiple guidance parameters, the lane in which the vehicle is currently located and the lane set of lanes that the vehicle can enter are determined through the pre-collected lane-level road network data; lane-level guidance services are provided to the vehicle according to the pre-set multiple guidance parameters.

[0062] For example, referring to Figure 1A, a vehicle is currently traveling in the middle lane. According to the navigation route, the vehicle needs to turn right at the current intersection. Therefore, a lane guidance result is generated for the vehicle 200 meters before the current intersection. The lane guidance result indicates that the vehicle is currently entering the dedicated right-turn lane.

[0063] However, due to the rich and diverse road conditions, multiple guidance parameters set based on empirical values ​​cannot meet the complex road conditions, and are prone to guidance errors such as untimely or premature lane guidance.

[0064] For example, referring to Figure 1B, a vehicle is currently traveling in the rightmost lane. According to the navigation route, the vehicle needs to turn right at the current intersection. Therefore, a lane guidance result is generated for the vehicle 200 meters before the current intersection. The lane guidance result indicates that the vehicle is currently entering the dedicated right-turn lane. However, based on current road conditions, there is no dedicated right-turn lane 200 meters from the intersection. Instead, there is a dedicated right-turn lane 50 meters before the intersection. If the driver blindly follows the lane guidance without using their own judgment, unnecessary traffic accidents may occur.

[0065] It can be seen that the lane-level guidance service provided by the lane guidance method in the related art has low accuracy.

[0066] In order to solve the problem of low guidance accuracy during lane guidance, the present application proposes a lane guidance method. In this method, after receiving the lane guidance instruction for the target road section, the following operations are performed for each candidate lane segment in a plurality of candidate lane segments: based on at least one conditional entry probability associated with the pre-stored candidate lane segment, the target entry probability of the target vehicle entering the candidate lane segment is determined. The target road section includes: a plurality of candidate lane segments located between the starting lane segment and the destination lane segment. Each conditional entry probability represents: the conditional probability of each past vehicle (also called a reference vehicle) in the historical driving data associated with the target road section, entering the candidate lane segment from an adjacent lane segment adjacent to the candidate lane segment, with entering the destination lane segment as the condition.

[0067] After obtaining the target entry probabilities corresponding to each of the multiple candidate lane segments, the system determines, based on the obtained target entry probabilities, the guiding lane segments among the multiple candidate lane segments whose corresponding target entry probabilities meet the guidance conditions, and obtains a lane guidance result. This generates a lane guidance result that includes the guiding lane segments among the multiple candidate lane segments whose target entry probabilities meet the preset guidance conditions.

[0068] The method may be performed by an electronic device. The electronic device may be, for example, an in-vehicle device, such as a navigation device in a vehicle's driving system, or an independent navigation device mounted on the vehicle, or a smart terminal running a navigation application, or a server that communicates with the navigation device to provide navigation services.

[0069] Lane guidance instructions are instructions for instructing the navigation device to provide lane-level navigation information. They can be automatically generated by the navigation device or generated by the navigation device in response to a received operation instruction. In some embodiments, during a journey guided by the navigation device, lane guidance instructions are automatically generated when preset conditions are met. For example, the preset conditions can be when the vehicle is about to enter the next road segment based on the pre-segmented navigation route. In other embodiments, lane guidance instructions are generated when the navigation device receives an operation instruction. For example, the operation instruction can be a start navigation instruction for the destination received through the user interface.

[0070] The target road section refers to the section of road between the starting location and the destination point corresponding to the current lane guidance instruction. In some embodiments, each lane in the road network is pre-divided into multiple lane segments along the road extension direction according to preset rules. In this case, the starting location and the destination point can be represented by the starting lane segment and the destination lane segment, respectively. The technical solutions of each embodiment determine at least two lane segments from the candidate lane segments between the starting lane segment and the destination lane segment. The first lane segments of the selected lane segments are connected to form a lane-level navigation route from the starting lane segment to the destination lane segment (also known as a lane guidance result).

[0071] In this embodiment of the present application, at least one conditional entry probability associated with each candidate lane segment is pre-determined based on historical driving data associated with the target road section. The conditional entry probability represents the conditional probability of each reference vehicle, within the historical time period covered by the historical driving data, entering the candidate lane segment from an adjacent lane segment, conditional on entering the target lane segment. Therefore, based on the at least one conditional entry probability associated with each candidate lane segment, a target entry probability for the target vehicle entering each candidate lane segment is determined. Based on the obtained target entry probabilities, a guiding lane segment is selected to obtain a lane guidance result.

[0072] Data mining was performed on the historical driving data of each reference vehicle within the historical time period, and the driving patterns of each reference vehicle under different road conditions were analyzed. This was used as a reference for lane guidance of the currently traveling target vehicle. As a result, targeted lane guidance can be performed for different road conditions, achieving richer lane guidance effects. There is no need to manually set multiple guidance parameters. Lane guidance is performed based on these set guidance parameters in any case, avoiding guidance errors caused by the set guidance parameters not matching the actual road conditions, and improving the guidance accuracy during lane guidance.

[0073] Furthermore, the calculation process of lane guidance based on lane segments requires less data calculation and is more efficient than the calculation process based on vehicle positioning points, thereby improving the lane guidance efficiency to a certain extent.

[0074] The following describes the application scenarios of the lane guidance method provided in this application.

[0075] Please refer to Figure 1C, which is a schematic diagram of an application scenario of the lane guidance method provided in this application. This application scenario includes a client 101 and a server 102. Taking the navigation client in the target vehicle as an example, client 101 and server 102 can communicate with each other. The communication method can be wired communication technology, such as communicating via a network cable or serial port cable; or wireless communication technology, such as communicating via Bluetooth or wireless fidelity (WIFI) technology, without specific limitation.

[0076] Client 101 generally refers to a device that can present lane guidance results, such as a terminal device, a third-party application accessible by the terminal device, or a webpage accessible by the terminal device. Terminal devices include, but are not limited to, mobile phones, computers, smart medical devices, smart home appliances, in-vehicle terminals, or aircraft. Server 102 generally refers to a device that can generate lane guidance results, such as a terminal device or a server. Servers include, but are not limited to, cloud servers, local servers, or associated third-party servers. Both client 101 and server 102 can utilize cloud computing to reduce the use of local computing resources; similarly, they can utilize cloud storage to reduce the use of local storage resources.

[0077] In various embodiments, the client 101 and the server 102 may be the same device or different devices, without specific limitation.

[0078] The lane guidance method provided by the embodiment of the present application is described in detail below based on Figure 1C. Please refer to Figure 2, which is a flow chart of the lane guidance method provided by the embodiment of the present application.

[0079] S201: Receive a lane guidance instruction for a target road section, and determine a plurality of candidate lane segments between a starting lane segment and a destination lane segment of the target road section.

[0080] Based on the full road network data of the actual road conditions and the high-precision map data of the navigation map, various reference lane segments can be pre-stored. The reference lane segments can be obtained by dividing the roads in the navigation map according to the actual road conditions. For example, please refer to Figure 3A (1). According to the actual road conditions, a traffic light at a first intersection, a traffic sign, a fork in the road leading out of the main road, and a traffic light at a second intersection are sequentially arranged on a road. Then, please refer to Figure 3A (2). Based on the respective positions of the traffic light at the first intersection, the traffic sign, the fork in the road leading out of the main road, and the traffic light at the second intersection on the road, the corresponding road in the navigation map can be divided into four segments. Since the road has three lanes in one direction, twelve reference lane segments can be obtained.

[0081] The target road section includes: a plurality of candidate lane segments located between the associated starting lane segment and the associated destination lane segment in each reference lane segment.

[0082] The starting lane segment associated with a target road segment can be a destination lane segment associated with another road segment. For example, the destination lane segment associated with another road segment that is connected to the target road segment and located in the opposite direction of travel of the target road segment is the starting lane segment associated with the target road segment. The starting lane segment associated with a target road segment can also be any lane segment that the target vehicle can enter upon departure. For example, in response to a navigation operation triggered for a destination, a road navigation route is generated from the starting location of the target vehicle to the destination. In this case, the reference lane segment on the road navigation route connected to the starting location is the starting lane segment.

[0083] The destination lane segment associated with a target road section can be the starting lane segment associated with another road section. For example, the starting lane segment associated with another road section connected to the target road section and located in the direction of travel of the target road section is the destination lane segment associated with the target road section. The destination lane segment associated with a target road section can also be a lane segment that the target vehicle exits upon approaching. For example, in response to a navigation operation triggered for a destination, a road navigation route is generated from the starting point of the target vehicle to the destination. In this case, the reference lane segment on the road navigation route connected to the destination is the destination lane segment.

[0084] Based on the full road network data of the actual road conditions and the high-precision map data of the navigation map, various marked lane segments, that is, pre-marked lane segments, can also be pre-stored. In the embodiment of the present application, the marked lane segment is taken as an example of the lane segment that the vehicle can enter when entering the fork in the road. The specific setting can be based on the actual scenario and is not limited here. The marked lane segment can be obtained by marking the reference lane segment in the navigation map according to the actual road conditions. For example, please refer to Figure 3B. The main road on the left shows twelve reference lane segments, and the auxiliary road on the right shows two reference lane segments. Since these two reference lane segments are the reference lane segments that the vehicle can enter when entering the auxiliary road, the two reference lane segments are marked, and the two reference lane segments are updated to two marked lane segments.

[0085] The marked lane segment can be used as the starting lane segment or destination lane segment associated with the target road segment or other road segments.

[0086] In various embodiments, lane guidance instructions for a target road section may be generated when the target vehicle is about to enter the target road section. For example, in response to a navigation operation triggered for a destination, a road navigation route from the target vehicle's starting location to the destination is generated. Multiple reference road sections are determined to comprise the road navigation route based on pre-stored marked lane segments and reference lane segments. When it is determined that the target vehicle is about to enter a reference road section, the reference road section is used as the target road section, and lane guidance instructions for the target road section are generated.

[0087] The lane guidance instructions for the target road section can also be generated in response to the navigation operation triggered for the destination, when generating a road navigation route from the starting point where the target vehicle is located to the destination, and each reference road section included in the road navigation route is used as the target road section in sequence, and the lane guidance instructions are generated for each target road section, etc. There is no specific restriction on the timing of generating the lane guidance instructions.

[0088] In the embodiment of the present application, the lane guidance process of a target road section in the road navigation route is specifically introduced. The lane guidance processes of other target road sections are similar and will not be repeated here.

[0089] S202 : For each of the multiple candidate lane segments, perform the following operations: determine a target entry probability of the target vehicle entering the candidate lane segment based on at least one pre-stored conditional entry probability associated with the candidate lane segment.

[0090] The multiple candidate lane segments are reference lane segments that the target vehicle can choose to enter when traveling on the target road section. In this embodiment of the present application, when the target vehicle enters the target road section, a guide lane segment from the multiple candidate lane segments can be determined for it. This is used to provide lane-level guidance services for the target vehicle entering the marked lane segment at the fork in the road, allowing the target vehicle to change lanes at a more accurate time.

[0091] The following describes the process of determining the target entry probability of the target vehicle entering a candidate lane segment. The process of determining the target entry probability of the target vehicle entering other candidate lane segments is similar and will not be repeated here.

[0092] At least one conditional entry probability associated with a candidate lane segment is obtained. Based on the obtained at least one conditional entry probability, a target entry probability for the target vehicle entering the candidate lane segment is determined. Each conditional entry probability represents the conditional probability of each passing vehicle in the historical driving data associated with the target road section entering the candidate lane segment from an adjacent lane segment, conditional on entering the target lane segment.

[0093] Referring to Figure 4A , the lane segment shown with a diagonal background is a candidate lane segment, and the lane segment shown with a horizontal background is its three adjacent lane segments, including a first adjacent lane segment 41, a second adjacent lane segment 42, and a third adjacent lane segment 43. This candidate lane segment is then associated with three conditional entry probabilities: for example, 90%, 10%, and 0%. This means that the probability of entering the candidate lane segment from the first adjacent lane segment 41 is 90%, the probability of entering the candidate lane segment from the second adjacent lane segment 42 is 10%, and the probability of entering the candidate lane segment from the third adjacent lane segment 43 is 0%.

[0094] In various embodiments, a method for determining a target entry probability of a target vehicle entering a candidate lane segment based on at least one pre-stored conditional entry probability associated with a candidate lane segment may include obtaining at least one reference entry probability associated with each reference lane segment included in each reference road section. From the obtained reference entry probabilities for each reference lane segment, at least one reference entry probability associated with each of the multiple candidate lane segments is extracted as the at least one conditional entry probability. For each of the multiple candidate lane segments, the following operations are performed: Based on the at least one conditional entry probability associated with the candidate lane segment, a target entry probability of the target vehicle entering the candidate lane segment is determined.

[0095] A reference road section is obtained by dividing a road into at least two associated preset marked lane segments. The at least two associated marked lane segments include a starting lane segment associated with the reference road section and a destination lane segment associated with the reference road section. Since there can be one or more starting lane segments associated with the reference road section and one or more destination lane segments associated with the reference road section, there can be at least two marked lane segments associated with the reference road section.

[0096] Each reference entry probability represents the conditional probability of each reference vehicle, within a historical time period, entering the reference lane segment from an adjacent lane segment, conditional on entering at least one marked lane segment associated with the corresponding reference lane segment in its travel direction. Since the at least two marked lane segments associated with a reference road segment include the starting lane segment associated with the reference road segment and the destination lane segment associated with the reference road segment, the at least one marked lane segment associated with the corresponding reference lane segment in its travel direction serves as the destination lane segment associated with the reference road segment.

[0097] In various embodiments, the conditional entry probability may further represent: the conditional probability of each reference vehicle within the historical time period entering the candidate lane segment from an adjacent lane segment, under the combined conditions of entering the destination lane segment and having a traffic congestion level below a preset level. Therefore, the entry probability may also represent: the conditional probability of each reference vehicle within the historical time period entering the reference lane segment from an adjacent lane segment, under the combined conditions of entering at least one marked lane segment associated with the corresponding reference lane segment in its travel direction and having a traffic congestion level below a preset level.

[0098] The traffic congestion level can be expressed by the time it takes for a reference vehicle to enter a candidate lane segment from an adjacent lane segment. A shorter time indicates a lower traffic congestion level; a longer time indicates a higher traffic congestion level.

[0099] The traffic congestion level can also be expressed by the traffic volume corresponding to the time and location when a reference vehicle enters a candidate lane segment from an adjacent lane segment. The lower the traffic volume, the lower the traffic congestion level; the higher the traffic volume, the higher the traffic congestion level.

[0100] The lower the congestion level, the smoother the traffic flow; the higher the congestion level, the more congested the traffic. By using complex conditions, we can mine richer information from historical driving data, enabling more accurate lane-level guidance for target vehicles. For example, we can provide earlier lane change guidance for congested road sections to avoid missing intersections. Alternatively, we can provide different lane guidance solutions for the same road section at different times to avoid traffic congestion.

[0101] The compound conditions can also be expanded from other dimensions. In the embodiment of the present application, entering the destination lane segment is used as an example to introduce a condition. The case of compound conditions is similar and will not be repeated here.

[0102] In various embodiments, each reference entry probability is obtained by data mining the historical driving data of each reference vehicle within a historical time period, and represents the driving patterns of each reference vehicle within the corresponding reference lane segment. Therefore, before obtaining at least one reference entry probability associated with each reference lane segment contained in each pre-stored reference road section, the historical driving data of each reference vehicle within the historical time period can be obtained. Based on the obtained historical driving data, as well as the pre-stored reference lane segments and marked lane segments, a lane segment driving sequence is determined for each reference vehicle. The lane segment driving sequence represents the historical driving data of the corresponding reference vehicle by connecting multiple reference lane segments and multiple marked lane segments in series. The lane segment driving sequence of each reference vehicle within the historical time period can also be pre-determined by other devices. When lane guidance is required, the server can directly obtain the pre-stored lane segment driving sequence of each reference vehicle within the historical time period from other devices, etc., without limitation.

[0103] After obtaining the lane segment driving sequence of each reference vehicle in the historical time period, at least one reference entry probability associated with each reference lane segment included in each reference road section can be determined based on the obtained lane segment driving sequence.

[0104] For example, referring to FIG4B(1), the historical driving data of a reference vehicle can be represented by multiple Global Positioning System (GPS) positioning points, which are shown as dotted lines in FIG4B(1), and each point represents GPS1, GPS2, GPS3, ..., GPS n Lane x Indicates the reference lane segment. Please refer to Figure 4B (2), where the line segments with the two end points as circles are shown. Each line segment represents the reference lane segment or the marked lane segment in the lane segment driving sequence of the reference vehicle, namely Lane1, Lane2, Lane 标记 ,……,Lane n , where Lane 标记 The first lane is the marked lane segment, and the others are reference lane segments.

[0105] In various embodiments, after obtaining each lane segment travel sequence, each reference vehicle's lane segment travel sequence can be divided into at least one travel subsequence based on each reference road segment, thereby obtaining multiple travel subsequences. The first and last lane segments of each travel subsequence are the two marked lane segments associated with the corresponding reference road segment. Thus, based on the obtained multiple travel subsequences, at least one reference entry probability associated with each reference lane segment within each reference road segment can be determined.

[0106] For example, the lane segment driving sequence of a reference vehicle is represented as Lane1, Lane2, Lane 标记 ,

[0107] Lane 4, Lane 5, Lane 6, Lane 标记 , Lane8, Lane9, Lane 标记 , Lane 11 , Lane 标记 , then the divided multiple driving sub-sequences include the first driving sub-sequence Lane1, Lane2, Lane 标记 The second driving subsequence Lane4, Lane5, Lane6, Lane 标记 , the third driving subsequence Lane8, Lane9, Lane 标记 , and the fourth traveling subsequence, Lane 11 , Lane 标记 .

[0108] In various embodiments, when determining at least one reference entry probability associated with each reference lane segment contained in each reference road interval based on the obtained lane segment driving sequence of each reference vehicle, or based on the obtained multiple driving subsequences, the reference entry probability can be calculated by counting the number of reference vehicles.

[0109] The following describes a process of determining a reference entry probability associated with a reference lane segment contained in a reference road section. Other determination processes are similar and will not be repeated here.

[0110] Based on the obtained lane segment driving sequences of each reference vehicle, the number of reference vehicles (also called first passing vehicles) that enter the reference lane segment from an adjacent lane segment adjacent to the reference lane segment is counted, with the associated marked lane segment in the driving direction of entering the corresponding reference road section as a condition, and the number of other vehicles (also called second passing vehicles) that enter other lane segments other than the reference lane segment and adjacent to an adjacent lane segment from an adjacent lane segment are counted.

[0111] Please refer to FIG5A, which shows the reference lane segments included in a reference road section, denoted as Lane 1, Lane 2-1 , Lane 2-2 , Lane 3-1 , Lane 3-2 , Lane 3-3 , Lane4, Lane 标记 Then for the reference lane segment Lane 3-3 , statistics are based on entering the associated marked lane segment Lane 标记 As a condition, from the adjacent lane segment Lane 2-2 Enter the reference lane 3-3 The number of reference vehicles of the reference vehicle is denoted as And, statistics on the lane segments that are associated with the lanes 标记 As a condition, from the adjacent lane segment Lane 2-2 Enter another lane 3-1 The number of other vehicles is recorded as And, statistics on the lane segments that are associated with the lanes 标记 As a condition, from the adjacent lane segment Lane 2-2 Enter another lane 3-2 The number of other vehicles is recorded as

[0112] Based on the obtained number of reference vehicles and other vehicle numbers, the conditional probability of each reference vehicle entering the reference lane segment from an adjacent lane segment adjacent to the reference lane segment, with the associated marked lane segment in the driving direction of the corresponding reference road section as a condition, is determined to obtain a reference entry probability of the reference lane segment.

[0113] The ratio of the number of reference vehicles to the sum of the number of reference vehicles and the number of other vehicles can be used as a reference entry probability of the reference lane segment. 标记 As a condition, from an adjacent lane segment Lane 2-2 , enter the reference lane segment Lane 3-3 The reference entry probability can be expressed as formula (1).

[0114] In various embodiments, after obtaining at least one reference entry probability associated with each reference lane segment contained in each pre-stored reference road interval, the traffic signs in the navigation map can be reconfirmed based on the results of this data mining to ensure the accuracy of the traffic signs in the navigation map, avoid the process of repeatedly confirming the traffic signs in actual road conditions, and improve the efficiency of confirming traffic signs.

[0115] Traffic signs requiring reconfirmation are marked on the navigation map. Therefore, you can retrieve at least one pending lane segment marked with a pending confirmation indicator within each reference lane segment within each reference road section. A pending confirmation indicator represents a traffic sign within the corresponding pending lane segment, or between multiple pending lane segments.

[0116] For example, a traffic sign indicating no U-turn is set on a lane that is only for left turns, but the traffic sign is partially blocked during road acquisition and may not be accurate. Therefore, the reference lane segment where the lane is located can be used as a pending lane segment, and a pending confirmation mark can be set on this pending lane segment.

[0117] For another example, the lane line between two adjacent lanes is a traffic sign indicating that the lane cannot be changed. However, the traffic sign is blocked by passing vehicles during road data collection, and the traffic sign may not be accurate. Therefore, the reference lane segments where the two lanes are located can be used as two lane segments to be confirmed, and a pending confirmation mark can be set on these two lane segments to be confirmed.

[0118] After obtaining at least one lane segment to be confirmed, at least one reference entry probability associated with each reference lane segment included in each reference road section may be selected.

[0119] Determine a traffic driving strategy corresponding to each of the at least one to-be-confirmed lane segments based on at least one reference entry probability associated with each of the at least one to-be-confirmed lane segments. Update a to-be-confirmed indicator of each of the at least one to-be-confirmed lane segments based on each of the obtained traffic driving strategies.

[0120] For example, a traffic sign prohibiting U-turns is set on a pending lane segment that is only for left turns, and at least one reference entry probability associated with the pending lane segment indicates that a large number of reference vehicles have made U-turns on the pending lane segment in a historical time period. In this case, the traffic driving strategy for the pending lane segment is that U-turns are allowed, so the pending identification of the pending lane segment can be updated.

[0121] For another example, the lane marking between two adjacent pending lane segments is a traffic sign indicating that lane changes are not allowed, and at least one reference entry probability associated with each of the two pending lane segments indicates that a large number of reference vehicles changed lanes between the two pending lane segments within a historical period. In this case, the traffic driving strategy for the two pending lane segments is that lane changes are allowed between them, so the pending identification of each of the two pending lane segments can be updated.

[0122] In each embodiment, when updating the to-be-confirmed identification of at least one to-be-confirmed lane segment based on each obtained traffic driving strategy, the process of updating the to-be-confirmed identification of a to-be-confirmed lane segment based on a traffic driving strategy is taken as an example for introduction. Other update processes are similar and will not be repeated here.

[0123] Determine the traffic driving strategy. When the traffic sign represented by the corresponding pending confirmation sign matches, unmark the corresponding pending confirmation sign. That is, if the traffic sign set in the navigation map is accurate, then the pending confirmation sign will no longer be marked on the pending confirmation lane segment, and the pending confirmation lane segment will be used as a reference lane segment again.

[0124] When the traffic driving strategy is determined and does not match the traffic sign represented by the corresponding pending confirmation sign, the corresponding pending confirmation sign is retained. This indicates that the traffic driving strategy of each reference vehicle on the pending confirmation lane segment in the historical time does not match the traffic sign. The traffic sign set in the navigation map may be inaccurate. Therefore, the pending confirmation sign can be retained so that it can be confirmed in the actual road conditions during the next road collection.

[0125] In various embodiments, when determining the target entry probability of the target vehicle entering the candidate lane segment based on at least one pre-stored conditional entry probability associated with the candidate lane segment, if the candidate lane segment is associated with one conditional entry probability, then the product of the one conditional entry probability and the associated weight coefficient is used as the target entry probability of the target vehicle entering the candidate lane segment. If the candidate lane segment is associated with multiple conditional entry probabilities, then the weighted sum of the multiple conditional entry probabilities can be used as the target entry probability of the target vehicle entering the candidate lane segment. Alternatively, the maximum value of the products of the multiple conditional entry probabilities and their associated weight coefficients can be used as the target entry probability of the target vehicle entering the candidate lane segment, and so on, without limitation.

[0126] The weight coefficient of each conditional entry probability is: the target entry probability of the adjacent lane segment determined when the corresponding adjacent lane segment is used as a candidate lane segment.

[0127] Refer to Figure 5B, which includes lane segments 1, 2, 3, 4, 5, 6, and 7. The target vehicle is located in lane segment 2. Under the condition of entering lane segment 10, the target entry probability of the target vehicle entering lane segment 3 from lane segment 2 is 90%, and the target entry probability of the target vehicle entering lane segment 5 from lane segment 2 is 10%.

[0128] The target vehicle has a conditional entry probability of 100% for entering the sixth lane from the third lane, and a conditional entry probability of 100% for entering the sixth lane from the fifth lane. Therefore, the target entry probability for the sixth lane includes:

[0129] The probability of the target vehicle entering the third lane from the second lane segment, and then the sixth lane from the third lane segment, also includes the probability of the target vehicle entering the fifth lane from the second lane segment, and then the sixth lane from the fifth lane segment. Using 90% as the weighting factor for the conditional entry probability of entering the sixth lane from the third lane segment, and 10% as the weighting factor for the conditional entry probability of entering the sixth lane from the fifth lane segment, the target entry probability for the sixth lane segment is 90% * 100% + 10% * 100% = 100%.

[0130] S203 : Generate a lane guidance result, where the lane guidance result includes: a guiding lane segment, among the multiple candidate lane segments, whose target entry probability satisfies a preset guidance condition.

[0131] This step determines, based on the obtained target entry probabilities corresponding to the multiple candidate lane segments, the guiding lane segments whose corresponding target entry probabilities meet the guidance conditions among the multiple candidate lane segments, and obtains the lane guidance result.

[0132] After obtaining the target entry probabilities corresponding to each of the multiple candidate lane segments, a guiding lane segment whose corresponding target entry probabilities meet the guidance conditions can be determined among the multiple candidate lane segments based on the obtained target entry probabilities corresponding to the multiple candidate lane segments to obtain a lane guidance result.

[0133] In various embodiments, satisfying the guidance condition may be greater than a preset probability value, or within a preset probability range, etc., without specific limitation. In the embodiments of the present application, the guidance condition is described as being greater than a preset probability value.

[0134] Among the multiple candidate lane segments, the candidate lane segment with a target entry probability greater than a preset probability value is selected as the guiding lane segment. That is, based on the obtained target entry probabilities corresponding to the multiple candidate lane segments, the guiding lane segment with a corresponding target entry probability greater than the preset probability value is selected. Based on each obtained guiding lane segment, the guided driving area and guided driving route of the target vehicle on the target road section are determined to obtain a lane guidance result.

[0135] In various embodiments, the guided driving area, or guiding surface, can represent the guided driving direction, such as guiding driving in a lane on the right side of the road or a lane on the left side of the road. The guided driving route, or guiding line, can represent the location where the vehicle is guided to change lanes. For example, when changing lanes between two adjacent lane segments, the two adjacent lane segments are connected in series to form a guiding line, thereby providing lane-level guidance services for the target vehicle.

[0136] Based on the obtained presentation areas of each guiding lane segment in the preset navigation map, the combined area formed by each guiding lane segment is used as the guiding driving area for the target vehicle on the target road section, that is, the guiding lane segments covered by the guiding surface form the guiding driving area.

[0137] Referring to Figure 6A , the area enclosed by the diagonal background's broken line frame represents the combined area of ​​the guide lane segments. The areas outside the diagonal background's broken line frame represent the candidate lane segments excluding the guide lane segments. Therefore, the area enclosed by the diagonal background's broken line frame serves as the target vehicle's guided driving area on the target road section.

[0138] A guided driving route for the target vehicle on the target road section is generated based on the multiple guide lane segments obtained by serially connecting them. If multiple serial connection methods exist for each guide lane segment, and no duplicate guide lane segments exist within each serial connection method, the serial connection method with the highest target entry probability for each serial guide lane segment is selected to generate the guided driving route.

[0139] When multiple series connection methods exist in each guide lane segment, if one of the series connection methods with the highest target entry probability for each of the series connection guide lane segments includes one or more guide lane segments whose associated traffic congestion level is higher than a preset level, then a guided driving route is obtained based on a guide lane segment with a target entry probability slightly lower than that of the one or more guide lane segments, i.e., the guide lane segment with the next highest target entry probability.

[0140] Based on the obtained guided driving area and guided driving route, a lane guidance result is generated. The lane guidance result achieves multiple guidance effects, making the target vehicle's drivable range more clear, thereby providing more accurate lane guidance services for the target vehicle.

[0141] Please refer to Figure 6B, which is a schematic diagram of a lane guidance result. The range enclosed by the broken line frame with a diagonal background represents the guided driving area, and the black arrow represents the guided driving route. Among them, for the starting lane segment where the target vehicle is currently located, when changing lanes to the right to enter the candidate lane segment adjacent to its right, the target entry probability of the candidate lane segment is the highest; when going straight forward to enter the adjacent candidate lane segment in front, the target entry probability of the candidate lane segment is the second highest. Then, if the candidate lane segment adjacent to the right is not congested, the candidate lane segment is the guiding lane segment; if the candidate lane segment is congested, then the adjacent candidate lane segment in front that is entered by going straight forward becomes the guiding lane segment. Figure 6B shows that the candidate lane segment adjacent to the right is not congested.

[0142] In various embodiments, after obtaining the lane guidance result, the lane guidance result can be presented in the client, for example, in the navigation map, the guided driving area is filled with a striking color, and the guided driving route is drawn with animated arrows.

[0143] The server may pre-store multiple multimedia presentation templates. A target presentation template that matches the lane guidance results can be selected from the pre-stored multimedia presentation templates. The multimedia presentation template is used to present content in at least one of image, video, or audio formats. The lane guidance results can then be presented based on the obtained target presentation template.

[0144] For example, please continue to refer to Figure 6B. In the navigation map, according to the target presentation template, the guided driving area is marked with a broken line frame with a diagonal background, and the guided driving route is drawn with a black arrow. At the same time, based on the current position of the target vehicle and the guided driving route, it is also possible to determine that the position of the target vehicle after entering the right lane is 200 meters away from the position where the target vehicle enters the right-turn additional lane from the right lane; and it is determined that the position of the target vehicle entering the right-turn additional lane from the right lane is 100 meters away from the position where the target vehicle enters the fork in the road. Therefore, according to the target presentation template, the content "Currently entering the right lane, and entering the right-turn additional lane after 200 meters, and after driving 100 meters on the right-turn additional lane, entering the fork in the road" can be announced by voice.

[0145] The following is an example introduction to the lane guidance method provided in the embodiment of the present application.

[0146] Please refer to Figure 7A(2), which is a schematic diagram of a road section, including three lanes in one direction, an additional right-turn lane, and a fork in the road. The lane between the left lane and the middle lane is represented by a long dashed line; the lane between the middle lane and the right lane is represented by a line consisting of a long dashed line and a long solid line; the lane between the right lane and the right additional lane is represented by a long dashed line; and the lane between the right lane and the fork in the road is represented by a long dashed line. Among them, the dotted line composed of five horizontal short segments divides each lane into multiple lane segments. Then, as shown in Figure 7A, from left to right and from bottom to top, they are the first lane segment, the second lane segment, the third lane segment, the fourth lane segment, the fifth lane segment, the sixth lane segment, the seventh lane segment, the eighth lane segment, the ninth lane segment, the tenth lane segment, the eleventh lane segment, the twelfth lane segment, the thirteenth lane segment, the fourteenth lane segment, the fifteenth lane segment, the sixteenth lane segment and the seventeenth lane segment (the names of the lane segments are not shown in the figure), as well as the marked lane segment where the fork is located, which can also be called the destination lane segment.

[0147] Then, the second lane segment can be used as a starting lane segment (shown as the lane segment where the vehicle is located in FIG7A ), and a road section is formed between the starting lane segment and the destination lane segment, and the road section can be used as a target road section.

[0148] When preparing the reference entry probabilities, please refer to FIG. 7B :

[0149] S701, obtaining historical driving data of each reference vehicle within a historical time period.

[0150] Please refer to Figure 7C(1), which is a schematic diagram of the historical driving data of a reference vehicle in the target lane section. The positioning points of the reference vehicle in the target lane section are represented by dots, and the line formed by the dots is the driving route of the reference vehicle in the target lane section.

[0151] S702: Based on the obtained historical driving data and the pre-stored reference lane segments and marked lane segments, determine the lane segment driving sequence of each reference vehicle.

[0152] S703 : Based on each reference road section, divide the lane segment driving sequence of each reference vehicle into at least one driving subsequence to obtain a plurality of driving subsequences.

[0153] Please refer to Figure 7C(2), which is a schematic diagram of a driving subsequence of the above-mentioned reference vehicle in the target road section. The line segments with two endpoints as circles represent the driving routes of the reference vehicle on each reference lane segment included in the target lane section.

[0154] S704 , based on the obtained multiple driving subsequences, for each reference lane segment and an adjacent lane segment thereof, count the number of reference vehicles and the number of other vehicles.

[0155] For the specific reference vehicle numbers and other vehicle numbers, please refer to the previous introduction and will not be repeated here.

[0156] S705 , for each reference lane segment, use the ratio of the number of reference vehicles to the sum of the number of reference vehicles and the number of other vehicles as a reference entry probability of entering the reference lane segment from an adjacent lane segment.

[0157] Taking the fifth lane segment in FIG7A as an example, for the fifth lane segment and its adjacent second lane segment, the number of reference vehicles counted can refer to formula (2).

[0158] For the second lane segment, and the first lane segment and the third lane segment adjacent to the second lane segment and excluding the fifth lane segment, the number of other vehicles counted can refer to formula (3).

[0159] Then, a reference entry probability of entering the fifth lane segment from the second lane segment can be obtained by referring to formula (4).

[0160] During the lane guidance phase, please refer to Figure 7D:

[0161] S706 : In response to the navigation operation triggered for the destination, a road navigation route is generated from the starting location where the target vehicle is located to the destination.

[0162] S707 : Determine a plurality of reference road sections included in the road navigation route based on the pre-stored marked lane segments and reference lane segments.

[0163] S708 : When it is determined that the target vehicle is about to enter a reference road section, the reference road section is used as a target road section, and a lane guidance instruction for the target road section is generated.

[0164] S709 : Selecting at least one conditional entry probability associated with each of the plurality of candidate lane segments included in the target road section from the pre-stored reference entry probabilities.

[0165] S710: For each of the candidate lane segments, perform the following operations:

[0166] When a candidate lane segment is associated with a conditional entry probability, the product of the conditional entry probability and the associated weight coefficient is used as the target entry probability of the target vehicle entering the candidate lane segment;

[0167] When a candidate lane segment is associated with multiple conditional entry probabilities, the weighted sum of the multiple conditional entry probabilities is used as the target entry probability of the target vehicle entering the candidate lane segment.

[0168] Taking the target road section as shown in FIG. 7A as an example, at least one conditional entry probability associated with each of the first lane segment, the second lane segment, ... and the seventeenth lane segment can be selected from the pre-stored reference entry probabilities.

[0169] The first lane segment is associated with a conditional entry probability. The conditional entry probability represents the conditional probability of each reference vehicle entering the first lane segment from the second lane segment, conditional on entering the destination lane segment, within a historical time period. The value of the conditional entry probability is, for example, 0%.

[0170] Since the target vehicle is currently located in the second lane segment, the conditional entry probability associated with the second lane segment is not obtained.

[0171] The third lane segment is associated with a conditional entry probability. This conditional entry probability represents the conditional probability of each reference vehicle entering the third lane segment from the second lane segment, conditional on entering the destination lane segment, within the historical time period. The value of this conditional entry probability is, for example, 90%.

[0172] The fourth lane segment is associated with two conditional entry probabilities. These two conditional entry probabilities represent: the conditional probability of each reference vehicle entering the fourth lane segment from the first lane segment, conditional on entering the destination lane segment, and the conditional probability of each reference vehicle entering the fourth lane segment from the fifth lane segment, respectively, within the historical time period. For example, the values ​​of these two conditional entry probabilities are both 0%.

[0173] The fifth lane segment is associated with three conditional entry probabilities. These represent the conditional probability of each reference vehicle entering the fifth lane segment from the second lane segment, conditional on entering the destination lane segment, the conditional probability of each reference vehicle entering the fifth lane segment from the fourth lane segment, and the conditional probability of each reference vehicle entering the fifth lane segment from the sixth lane segment, respectively, within the historical time period. For example, the values ​​of these three conditional entry probabilities are 10%, 0%, and 0%, respectively.

[0174] The sixth lane segment is associated with two conditional entry probabilities. These two conditional entry probabilities represent: the conditional probability of each reference vehicle entering the sixth lane segment from the third lane segment, conditional on entering the destination lane segment, and the conditional probability of each reference vehicle entering the sixth lane segment from the fifth lane segment, respectively, within the historical time period. For example, the values ​​of these two conditional entry probabilities are both 100%.

[0175] The seventh, tenth, and fourteenth lane segments are each associated with two conditional entry probabilities, similar to the previous description and omitted here for clarity. For example, the values ​​of these six conditional entry probabilities are all 0%. The eighth, eleventh, fifteenth, and sixteenth lane segments are each associated with three conditional entry probabilities, similar to the previous description and omitted here for clarity. For example, the values ​​of these twelve conditional entry probabilities are all 0%.

[0176] The ninth lane segment and the seventeenth lane segment are each associated with two conditional entry probabilities, which are similar to the content described above and will not be repeated here. The values ​​of these four conditional entry probabilities are, for example, all 100%.

[0177] The twelfth lane segment is associated with three conditional entry probabilities. These three conditional entry probabilities represent: the conditional probability of each reference vehicle entering the twelfth lane segment from the ninth lane segment, conditional on entering the destination lane segment, the conditional probability of each reference vehicle entering the twelfth lane segment from the eleventh lane segment, and the conditional probability of each reference vehicle entering the twelfth lane segment from the thirteenth lane segment, respectively, within the historical time period. For example, the values ​​of these three conditional entry probabilities are 30%, 100%, and 0%, respectively.

[0178] The thirteenth lane segment is associated with a conditional entry probability. This conditional entry probability represents the conditional probability of each reference vehicle in the historical time period entering the thirteenth lane segment from the twelfth lane segment, conditional on entering the destination lane segment. The value of this conditional entry probability is, for example, 90%.

[0179] Then, since the target vehicle is currently located in the second lane segment, the target entry probability of the second lane segment is regarded as 100%.

[0180] Since the target vehicle is currently located in the second lane segment adjacent to the first lane segment, the weight coefficient of the conditional entry probability associated with the first lane segment is 1, and the target entry probability of the first lane segment is 1*0%=0%.

[0181] Since the target vehicle is currently located in the second lane segment adjacent to the third lane segment, the weight coefficient of a conditional entry probability associated with the third lane segment is 1, and the target entry probability of the third lane segment is 1*90%=90%.

[0182] The conditional entry probabilities associated with the fourth lane segment, the seventh lane segment, the eighth lane segment, the tenth lane segment, the eleventh lane segment, the fourteenth lane segment, the fifteenth lane segment and the sixteenth lane segment are all 0%. Therefore, the target entry probabilities of the fourth lane segment, the seventh lane segment, the eighth lane segment, the tenth lane segment, the eleventh lane segment, the fourteenth lane segment, the fifteenth lane segment and the sixteenth lane segment are each 0%.

[0183] Since the target vehicle is currently located in the second lane segment adjacent to the fifth lane segment, the target entry probability of the fourth lane segment is 0%, and the conditional entry probability of entering the fifth lane segment from the sixth lane segment associated with the fifth lane segment is 0%. Therefore, the target entry probability of the fifth lane segment is 1*10%+0%+0%=10%.

[0184] The target entry probability of the third lane segment is 90%, the target entry probability of the fifth lane segment is 10%, and the target entry probability of the six lane segment associated with the two conditions is 100%. Therefore, the target entry probability of the sixth lane segment is 90%*100%+10%*100%=100%.

[0185] The target entry probability of the eighth lane segment is 0%, the target entry probability of the sixth lane segment is 100%, and the two conditional entry probabilities associated with the ninth lane segment are both 100%. Therefore, the target entry probability of the ninth lane segment is 0%*100%+100%*100%=100%.

[0186] The target entry probability of the ninth lane segment is 100%, the target entry probability of the eleventh lane segment is 0%, and the conditional entry probability associated with the twelfth lane segment and entering the twelfth lane segment from the thirteenth lane segment is 0%. Therefore, the target entry probability of the twelfth lane segment is 100%*30%+0%+0%=30%.

[0187] The target entry probability of the twelfth lane section is 30%, and the target entry probability of the thirteenth lane section is 30%*90%=27%.

[0188] The target entry probability of the thirteenth lane segment is 27%, the target entry probability of the sixteenth lane segment is 0%, and therefore, the target entry probability of the seventeenth lane segment is 100%*27%=27%.

[0189] Please refer to FIG7E , where the target entry probability of each lane segment is marked at the position of the corresponding lane segment.

[0190] S711 , based on the obtained target entry probabilities corresponding to the multiple candidate lane segments, select a guiding lane segment from the multiple candidate lane segments whose corresponding target entry probability is greater than a preset probability value, such as 20%.

[0191] S712: Based on the obtained guiding lane segments, the target vehicle's guided driving area and guided driving route on the target road section, namely, the guiding surface and guiding line, are determined to obtain a lane guidance result. The obtained guiding lane segments form the guiding surface. When each of the obtained guiding lane segments faces one or more enterable guiding lane segments, the target vehicle selects the guiding lane segment with the highest probability of entry to enter, forming a guiding line.

[0192] S713: Present the lane guidance result using a target presentation template that matches the lane guidance result among various pre-stored multimedia presentation templates.

[0193] Please refer to Figure 7F(1), which shows the guidance area in the lane guidance result, i.e., a presentation effect of the guidance surface. Please refer to Figure 7F(2), which shows the guidance area in the lane guidance result superimposed with the guidance route, i.e., a presentation effect of the guidance surface and guidance line.

[0194] In the embodiment of the present application, the process of obtaining the guided driving area and the guided driving route is optimized by data-driven means, thereby avoiding the problem of inaccurate guidance caused by unified guidance parameters. By mining the historical driving data of a large amount of reference vehicles, the actual lane change choices at different road sites can be adapted.

[0195] Based on the same inventive concept, the present invention provides a lane guidance device that can implement the functions corresponding to the aforementioned lane guidance method. Referring to FIG8 , the device includes an acquisition module 801 and a processing module 802 , wherein:

[0196] Acquisition module 801: for receiving lane guidance instructions for a target road section, and determining multiple candidate lane segments between the starting lane segment and the destination lane segment of the target road section

[0197] Processing module 802 is configured to perform the following operations for each of the plurality of candidate lane segments: determining a target entry probability of a target vehicle entering the candidate lane segment based on at least one pre-stored conditional entry probability associated with the candidate lane segment; wherein each conditional entry probability represents: a conditional probability, in historical driving data associated with the target road section, that a past vehicle enters the candidate lane segment from an adjacent lane segment adjacent to the candidate lane segment, conditional on entering the target lane segment;

[0198] The processing module 802 is further configured to generate a lane guidance result, wherein the lane guidance result includes a guiding lane segment whose target entry probability satisfies the guidance condition among the multiple candidate lane segments.

[0199] In various embodiments, the processing module 802 is specifically configured to:

[0200] Obtaining at least one reference entry probability associated with each reference lane segment contained in each pre-stored reference road segment; wherein the reference road segment is obtained by dividing the road into at least two associated marked lane segments; and each reference entry probability represents the conditional probability of each reference vehicle within a historical time period entering the reference lane segment from an adjacent lane segment adjacent to the reference lane segment, conditional on entering at least one associated marked lane segment in the direction of travel of the corresponding reference lane segment.

[0201] Selecting at least one conditional entry probability associated with each of the plurality of candidate lane segments from the obtained reference entry probabilities;

[0202] For each of the plurality of candidate lane segments, the following operations are performed: based on at least one conditional entry probability associated with the candidate lane segment, a target entry probability of the target vehicle entering the candidate lane segment is determined.

[0203] In various embodiments, the processing module 802 is further configured to:

[0204] Before obtaining at least one reference entry probability associated with each reference lane segment included in each pre-stored reference road section, obtaining historical driving data of each reference vehicle within a historical time period;

[0205] Determining a lane segment driving sequence for each reference vehicle based on the acquired historical driving data and the pre-stored reference lane segments and marked lane segments; wherein the lane segment driving sequence represents the historical driving data of the corresponding reference vehicle by connecting multiple reference lane segments and multiple marked lane segments in series;

[0206] Based on the obtained lane segment driving sequences of the respective reference vehicles, at least one reference entry probability associated with each reference lane segment included in each reference road section is determined.

[0207] In various embodiments, the processing module 802 is specifically configured to:

[0208] Based on each reference road section, the lane segment driving sequence of each reference vehicle is divided into at least one driving subsequence to obtain multiple driving subsequences; wherein the first lane segment and the last lane segment of each driving subsequence are: the two marked lane segments associated with the corresponding reference road section;

[0209] Based on the obtained multiple driving subsequences, at least one reference entry probability associated with each reference lane segment included in each reference road section is determined respectively.

[0210] In various embodiments, the processing module 802 is specifically configured to:

[0211] For each reference lane segment contained in each reference road section, perform the following operations:

[0212] Based on the obtained lane segment travel sequences of each reference vehicle, counting the number of reference vehicles that enter the reference lane segment from an adjacent lane segment adjacent to the reference lane segment, conditional on entering the marked lane segment associated with the travel direction of the corresponding reference road section, and the number of other vehicles that enter, from an adjacent lane segment, a lane segment other than the reference lane segment and adjacent to an adjacent lane segment;

[0213] Based on the obtained number of reference vehicles and other vehicle numbers, the conditional probability of each reference vehicle entering the reference lane segment from an adjacent lane segment adjacent to the reference lane segment, with the associated marked lane segment in the driving direction of the corresponding reference road section as a condition, is determined to obtain a reference entry probability of the reference lane segment.

[0214] In various embodiments, the processing module 802 is further configured to:

[0215] After obtaining at least one reference entry probability associated with each reference lane segment included in each pre-stored reference road section, obtaining at least one pending lane segment marked with a pending confirmation indicator in each reference lane segment included in each reference road section; wherein the pending confirmation indicator represents: a pending traffic sign included in the corresponding pending lane segment or between the corresponding multiple pending lane segments;

[0216] Selecting at least one reference entry probability associated with at least one lane segment to be confirmed from at least one reference entry probability associated with each reference lane segment included in each reference road section;

[0217] determining a traffic driving strategy corresponding to each of the at least one to-be-confirmed lane segments based on at least one reference entry probability associated with each of the at least one to-be-confirmed lane segments;

[0218] Based on the obtained traffic driving strategies, the to-be-confirmed identification of at least one to-be-confirmed lane segment is updated respectively.

[0219] In various embodiments, the processing module 802 is specifically configured to:

[0220] For each traffic driving strategy obtained, perform the following operations:

[0221] Determine a traffic driving strategy, and when a traffic sign represented by a corresponding pending identification matches, unmark the corresponding pending identification;

[0222] Determine the traffic driving strategy. When the traffic sign represented by the corresponding pending identification does not match, retain the corresponding pending identification.

[0223] In various embodiments, the acquisition module 801 is specifically configured to:

[0224] In response to a navigation operation triggered for a destination, generating a road navigation route from a starting location where the target vehicle is located to the destination;

[0225] Determining a plurality of reference road sections included in a road navigation route based on pre-stored marked lane sections and reference lane sections;

[0226] When it is determined that the target vehicle is about to enter a reference road section, the reference road section is used as the target road section, and a lane guidance instruction for the target road section is generated.

[0227] In various embodiments, each conditional entry probability is associated with a weight coefficient, where the weight coefficient is: the target entry probability of the target vehicle entering a candidate lane segment when the adjacent lane segment represented by the corresponding conditional entry probability is used as a candidate lane segment;

[0228] The processing module 802 is specifically configured to:

[0229] When a candidate lane segment is associated with a conditional entry probability, the product of the conditional entry probability and the associated weight coefficient is used as the target entry probability of the target vehicle entering the candidate lane segment;

[0230] When a candidate lane segment is associated with multiple conditional entry probabilities, the weighted sum of the multiple conditional entry probabilities, or the maximum value of the product of the multiple conditional entry probabilities and the associated weight coefficients, is used as the target entry probability for the target vehicle to enter the candidate lane segment.

[0231] In various embodiments, the processing module 802 is specifically configured to:

[0232] Based on the obtained target entry probabilities corresponding to the multiple candidate lane segments, a guiding lane segment having a corresponding target entry probability greater than a preset probability value is selected from the multiple candidate lane segments;

[0233] Based on the obtained guide lane segments, the guided driving area and guided driving route of the target vehicle on the target road section are determined to obtain a lane guidance result.

[0234] In various embodiments, the processing module 802 is specifically configured to:

[0235] Based on the obtained presentation areas of the respective guide lane segments in the preset navigation map, a combined area formed by the guide lane segments is used as a guided driving area for the target vehicle on the target road section;

[0236] generating a guided driving route for the target vehicle on the target road section based on a plurality of guide lane segments connected in series in each of the obtained guide lane segments;

[0237] A lane guidance result is generated based on the obtained guided driving area and guided driving route.

[0238] In various embodiments, the processing module 802 is further configured to:

[0239] After obtaining the lane guidance result, selecting a target presentation template that matches the lane guidance result from among various pre-stored multimedia presentation templates; wherein the multimedia presentation template is used to present content in at least one of an image format, a video format, or a voice format;

[0240] Based on the obtained target presentation template, the lane guidance result is presented.

[0241] Please refer to Figure 9, which shows a computer device 900 provided in an embodiment of the present application. The computer device 900 may be, for example, the terminal device 101 or the server 102 in Figure 1C. The current and historical versions of the data storage program and the application software corresponding to the data storage program may be installed on the computer device 900. The computer device 900 includes a processor 980 and a memory 920. In some embodiments, the computer device 900 may include a display unit 940, which includes a display panel 941 for displaying a user interactive interface. In some embodiments, the computer device 900 may also include an input unit 930, which may include an image input device 931 and other input devices 932. The computer device 900 may also include a power supply 990 for powering other modules, an audio circuit 960, a near-field communication module 970, and an RF circuit 910. The audio circuit 960 specifically includes a speaker 961 and a microphone 962. The computer device 900 may also include one or more sensors 950.

[0242] In various embodiments, the processor 980 is configured to read a computer program and then execute the method defined by the computer program. For example, the processor 980 reads a data storage program or file, thereby running the data storage program on the computer device 900 and displaying a corresponding interface on the display unit 940. The processor 980 may include one or more general-purpose processors and may also include one or more DSPs (Digital Signal Processors) to perform related operations to implement the technical solutions provided in the embodiments of the present application.

[0243] The memory 920 generally includes internal memory and external memory. The internal memory may be a random access memory (RAM), a read-only memory (ROM), and a cache (CACHE), etc. The external memory may be a hard disk, an optical disk, a USB disk, a floppy disk, or a tape drive, etc. The memory 920 is used to store computer programs and other data. The computer program includes an application corresponding to each client, etc. Other data may include data generated after the operating system or application is run, and the data includes system data (such as configuration parameters of the operating system) and user data. In the embodiment of the present application, the computer program is stored in the memory 920, and the processor 980 executes the computer program in the memory 920 to implement any of the methods discussed in the previous figure.

[0244] In various embodiments

[0245] In various embodiments, the number of processors 980 may be one or more, and the processor 980 and the memory 920 may be coupled or relatively independently configured.

[0246] In various embodiments, the processor 980 in FIG. 9 may be configured to implement the functions of the acquisition module 801 and the processing module 802 in FIG. 8 .

[0247] In various embodiments, the processor 980 in FIG. 9 may be used to implement the corresponding functions of the server or terminal device discussed above.

[0248] Those skilled in the art will appreciate that all or part of the steps of implementing the above-mentioned method embodiments may be accomplished by a computer program. The aforementioned computer program may be stored in a computer-readable storage medium. When the computer program is executed, it executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0249] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, for example, through a computer program product, which is stored in a storage medium and includes a computer program for enabling a computer device to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program code, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0250] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0251] In conclusion, the scope of the claims should not be limited to the exemplary embodiments described above, but should be given the broadest interpretation of the specification as a whole.

Claims

1. A lane guiding method, characterized in that, Executed by an electronic device, including: Receiving a lane guidance instruction for a target road section; wherein, Determining a plurality of candidate lane sections between the starting lane section and the destination lane section of the target road section; For each candidate lane section among the plurality of candidate lane sections, perform the following operations: Based on at least one conditional entry probability associated with the candidate lane section stored in advance, determining a target entry probability for the target vehicle to enter the candidate lane section; wherein, the conditional entry probability represents: in the historical driving data associated with the target road section, the conditional probability that a past vehicle enters the candidate lane section from an adjacent lane section adjacent to the candidate lane section on the condition of entering the destination lane section; Generating a lane guidance result, the lane guidance result including: among the plurality of candidate lane sections, the guidance lane sections whose target entry probabilities meet the preset guidance conditions.

2. The method according to claim 1, wherein The determining the target entry probability for the target vehicle to enter the candidate lane section based on at least one conditional entry probability associated with the candidate lane section stored in advance includes: Obtaining at least one reference entry probability associated with each reference lane section included in each stored reference road section; wherein, the reference road section is: a road divided by at least two preset marked lane sections; each reference entry probability represents: in a historical time period, for each past vehicle, the conditional probability of entering the reference lane section from an adjacent lane section adjacent to the reference lane section on the condition of entering at least one marked lane section associated with the driving direction of the reference lane section; Extracting at least one reference entry probability associated with each of the plurality of candidate lane sections from the obtained reference entry probabilities of the respective reference lane sections as the at least one conditional entry probability; For the plurality of candidate lane sections, respectively perform the following operations: Based on the at least one conditional entry probability associated with the candidate lane section, determining the target entry probability for the target vehicle to enter the candidate lane section.

3. The method according to claim 2, wherein Before obtaining at least one reference entry probability associated with each reference lane section included in each stored reference road section, it further includes: Obtaining the historical driving data of the past vehicles; Based on the obtained historical driving data and the stored reference lane sections and marked lane sections respectively, determining the lane section driving sequence of each past vehicle; wherein, the lane section driving sequence represents the historical driving data of the corresponding past vehicle with a plurality of reference lane sections and a plurality of marked lane sections in series; Based on the obtained lane section driving sequences of the respective past vehicles, respectively determining at least one reference entry probability associated with each reference lane section included in each reference road section.

4. The method according to claim 3, characterized in that, The determining at least one reference entry probability associated with each reference lane section included in each reference road section based on the obtained lane section driving sequences of the respective past vehicles includes: Based on each reference road section, the lane - segment driving sequences of the respective passing vehicles are each divided into at least one driving subsequence, obtaining a plurality of driving subsequences; wherein, the first lane segment and the last lane segment included in each of the driving subsequences are: the two marked lane segments associated with the corresponding reference road section. Based on the obtained plurality of driving subsequences, at least one reference entry probability associated with each reference lane segment included in each reference road section is respectively determined.

5. The method according to claim 3, characterized in that, The determining, based on the lane - segment driving sequences of the respective passing vehicles obtained, at least one reference entry probability associated with each reference lane segment included in each reference road section, includes: For each reference lane segment included in each of the reference road sections, the following operations are respectively performed: Based on the lane - segment driving sequences of the respective passing vehicles obtained, count the number of first passing vehicles that enter the reference lane segment from an adjacent lane segment adjacent to the reference lane segment, with the marked lane segment associated with the driving direction of entering the corresponding reference road section as a condition, and the number of second passing vehicles that enter other lane segments adjacent to the one adjacent lane segment and other than the reference lane segment from the one adjacent lane segment. Based on the number of first passing vehicles and the number of second passing vehicles obtained, determine the conditional probability that the respective passing vehicles enter the reference lane segment from an adjacent lane segment adjacent to the reference lane segment, with the marked lane segment associated with the driving direction of entering the corresponding reference road section as a condition, and obtain one reference entry probability of the reference lane segment.

6. The method according to claim 2, wherein After obtaining at least one reference entry probability associated with each reference lane segment included in each of the pre - stored reference road sections, it further includes: Obtain at least one to - be - confirmed lane segment marked with a to - be - confirmed identifier among each reference lane segment included in each of the reference road sections; wherein, the to - be - confirmed identifier represents: the traffic signs to be confirmed included in the corresponding to - be - confirmed lane segment or among the corresponding multiple to - be - confirmed lane segments. Select at least one reference entry probability associated with each of the at least one to - be - confirmed lane segment from at least one reference entry probability associated with each reference lane segment included in each of the reference road sections. Based on at least one reference entry probability associated with each of the at least one to - be - confirmed lane segment, determine the respective traffic driving strategies corresponding to the at least one to - be - confirmed lane segment. Based on the obtained respective traffic driving strategies, update the to - be - confirmed identifiers of the at least one to - be - confirmed lane segment respectively.

7. The method according to claim 6, wherein The updating the to - be - confirmed identifiers of the at least one to - be - confirmed lane segment respectively based on the obtained respective traffic driving strategies includes: For each of the obtained respective traffic driving strategies, the following operations are respectively performed: When it is determined that the traffic driving strategy matches the traffic sign represented by the corresponding to - be - confirmed identifier, cancel the marking of the corresponding to - be - confirmed identifier. When it is determined that the traffic driving strategy does not match the traffic sign represented by the corresponding to - be - confirmed identifier, retain the marking of the corresponding to - be - confirmed identifier.

8. The method according to any one of claims 1 to 7, characterized in that The receiving the lane - guiding instruction for the target road section includes: In response to a navigation operation triggered for a destination, a road navigation route from the starting point where the target vehicle is located to the destination is generated; Based on pre-stored respective marked lane segments and respective reference lane segments, a plurality of reference road intervals included in the road navigation route are determined; When it is determined that the target vehicle is about to enter a reference road interval, the reference road interval is used as a target road interval, and a lane guiding instruction for the target road interval is generated.

9. The method according to any one of claims 1 to 7, characterized in that Each conditional entry probability is associated with a weight coefficient, where the weight coefficient is: when the adjacent lane segment characterized by the conditional entry probability corresponding to the weight coefficient is used as a candidate lane segment, the determined target entry probability of the target vehicle entering the candidate lane segment; The determining the target entry probability of the target vehicle entering the candidate lane segment based on at least one conditional entry probability associated with the pre-stored candidate lane segment includes: When the candidate lane segment is associated with one conditional entry probability, the product of the one conditional entry probability and the associated weight coefficient is used as the target entry probability of the target vehicle entering the candidate lane segment; When the candidate lane segment is associated with multiple conditional entry probabilities, the weighted sum of the multiple conditional entry probabilities, or the maximum value of the products of the multiple conditional entry probabilities and their associated weight coefficients, is used as the target entry probability of the target vehicle entering the candidate lane segment.

10. The method according to any one of claims 1 to 7, characterized in that The determining the guiding lane segment among the multiple candidate lane segments whose corresponding target entry probability meets the guiding condition based on the obtained target entry probabilities of the multiple candidate lane segments respectively, and obtaining a lane guiding result includes: Selecting the candidate lane segments among the multiple candidate lane segments whose target entry probability is greater than a preset probability value as the guiding lane segments; Based on the obtained guiding lane segments, determining the guiding driving area and guiding driving route of the target vehicle on the target road interval, and obtaining a lane guiding result.

11. The method according to claim 10, wherein The determining the guiding driving area and guiding driving route of the target vehicle on the target road interval based on the obtained guiding lane segments, and obtaining a lane guiding result includes: Based on the presentation areas of the obtained guiding lane segments in a preset navigation map respectively, taking the combined area formed by the guiding lane segments as the guiding driving area of the target vehicle on the target road interval; Based on a plurality of consecutive guiding lane segments among the obtained guiding lane segments, generating the guiding driving route of the target vehicle on the target road interval; Based on the obtained guiding driving area and guiding driving route, generating a lane guiding result.

12. The method according to any one of claims 1 to 7, characterized in that, After obtaining the lane guiding result, it further includes: Selecting a target presentation template that matches the lane guiding result from pre-stored respective multimedia presentation templates; where the multimedia presentation template is used for: presenting content in at least one of an image format, a video format, or a voice format; Based on the obtained target presentation template, presenting the lane guiding result.

13. A lane guiding device, characterized in that, Includes: Obtaining module: configured to receive a lane guidance instruction for a target road section, and determine a plurality of candidate lane sections between the starting lane section and the destination lane section of the target road section; Processing module: configured to perform the following operations for each candidate lane section among the plurality of candidate lane sections: determine a target entry probability for the target vehicle to enter the candidate lane section based on at least one conditional entry probability associated with the candidate lane section stored in advance; wherein, the conditional entry probability represents: in the historical driving data associated with the target road section, the conditional probability that a past vehicle enters the candidate lane section from an adjacent lane section adjacent to the candidate lane section on the condition of entering the destination lane section; The processing module is further configured to: generate a lane guidance result, where the lane guidance result includes: a guided lane section among the plurality of candidate lane sections whose target entry probability meets a preset guidance condition.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1 to 12.

15. A computer device, characterized in that, Comprising: A memory, configured to store program instructions; A processor, configured to call the program instructions stored in the memory and execute the method according to any one of claims 1 to 12 according to the obtained program instructions.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute the method according to any one of claims 1 to 12.

Images