Method for determining traffic condition information, electronic device and computer readable storage medium

Abstract

The present application provides a method for determining traffic condition information, an electronic device and a computer readable storage medium. A plurality of vehicle trajectories and a road network topology of a target intersection are used for determining traffic condition information of lanes in each travel direction of an intersection approach road, so that the solution in the present application is simple and easy to implement. In addition, the vehicle trajectories of the present application can be standard precision trajectory data or high-precision trajectory data, and the road network topology can be a road network topology in a standard precision map or a road network topology in a high-precision map, so that the application range is wide, thereby reducing the cost of the solution.

Description

Road condition information determination method, electronic device, and computer-readable storage medium

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on March 29, 2024, with application number 202410396033.6 and application name “Road Condition Information Determination Method, Electronic Device and Computer-Readable Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communications, and in particular to a method for determining road condition information, an electronic device, and a computer-readable storage medium. Background Art

[0003] Map service applications (APPs) provide users with a variety of location-related services. For example, they can offer navigation, cruise control, and other services. Consequently, people are increasingly using these apps while traveling. Using these apps, users can use the traffic information they provide to avoid congested roads and reach their destinations faster. Therefore, the accuracy of traffic information has become one of the most competitive indicators for map navigation apps.

[0004] The road section before the intersection, as the portion of road before reaching the intersection, serves as a transitional area connecting the current intersection to other sub-sections. It typically includes multiple lanes with different traffic directions, such as through lanes, left-turn lanes, and right-turn lanes. At the same moment, the traffic conditions for lanes in different directions on the road section before the intersection often differ. Existing lane-level traffic condition determination methods can be used to determine lane-level traffic condition information for the road section before the intersection, but these solutions are complex and costly. Summary of the Invention

[0005] The present application provides a method for determining road condition information, an electronic device, and a computer-readable storage medium, which utilizes multiple vehicle trajectories and the road network topology of a target intersection to determine the road condition information of the lanes in each direction of travel on the road ahead of the intersection. The solution in the present application is simple and easy to implement. In addition, since the vehicle trajectories of the present application can adopt either standard precision trajectory data or high-precision trajectory data, and the road network topology can adopt the road network topology in a standard precision map or the road network topology in a high-precision map, the application range is wide, thereby reducing the cost of the solution.

[0006] In a first aspect, a method for determining road condition information is provided, the method comprising: obtaining a set of vehicle trajectories at a target intersection, the set of vehicle trajectories comprising vehicle trajectories that passed through the target intersection before a target time; determining a travel direction of the first vehicle trajectory based on the first vehicle trajectory and a road network topology of the target intersection, the travel direction of the first vehicle trajectory being used to indicate the travel direction of a lane located on a road preceding the target intersection, the road preceding the intersection comprising at least two lanes with different travel directions, the first vehicle trajectory being any one of the vehicle trajectories in the set of vehicle trajectories; and determining road condition information of each lane in each travel direction of the road preceding the intersection at the target time based on the set of vehicle trajectories, the road network topology of the target intersection, and the travel direction of each vehicle trajectory in the set of vehicle trajectories.

[0007] For example, the traffic condition information may include one or more of travel time and congestion conditions.

[0008] The first aspect provides a method for determining road condition information, which first obtains a set of vehicle trajectories that pass through a target intersection before a target time (i.e., a vehicle trajectory set), determines the travel direction of each vehicle trajectory based on each vehicle trajectory in the vehicle trajectory set and the road network topology, and then determines the road condition information of lanes in each travel direction of the road ahead of the intersection at the target time based on the vehicle trajectory set, the road network topology of the target intersection, and the travel direction of each vehicle trajectory in the vehicle trajectory set. This method can obtain road condition information of lanes in different travel directions of the road ahead of the intersection based on the vehicle trajectory set and the road network topology, and the solution is simple and easy to implement. Moreover, the vehicle trajectories in this method can adopt standard precision trajectory data or high-precision trajectory data, and the road network topology can adopt the road network topology in a high-precision map or the road network topology in a standard precision map, so the method has a wide range of applicability. In addition, since this method can be implemented using standard precision vehicle trajectories and standard precision maps, it can significantly reduce costs.

[0009] In one possible implementation of the first aspect, the direction of travel of the first vehicle trajectory is determined based on the first vehicle trajectory and the road network topology of the target intersection, including: matching the first vehicle trajectory with the road network topology of the target intersection to obtain a topological driving route corresponding to the first vehicle trajectory, the topological driving route being used to indicate a route representing the first vehicle trajectory using the road network topology; and determining the direction of travel of the first vehicle trajectory based on the topological driving route corresponding to the first vehicle trajectory. In this implementation, the topological driving route is a route representing the first vehicle trajectory using the road network topology. Since the road network topology carries turning information of the intersection, the topological driving route representing the first vehicle trajectory using the road network topology also carries the turning information of the intersection. It is easy to obtain the direction of travel of the first vehicle trajectory based on the topological driving route with turning information, and the method is simple and easy to implement.

[0010] In some embodiments, the travel direction of the first vehicle trajectory can also be obtained by inputting the road network topology of the first vehicle trajectory and the target intersection into a preset travel direction model, where the preset travel direction model can be a pre-trained machine learning model or a neural network model. This application does not enumerate or limit the specific types of machine learning or neural network models.

[0011] In one possible implementation of the first aspect, a road network topology includes multiple directed line segments for representing road lengths and road travel directions. A first vehicle trajectory is matched with the road network topology of a target intersection to obtain a topological driving route corresponding to the first vehicle trajectory. This method includes: projecting multiple trajectory points of the first vehicle trajectory onto the directed line segments of the road network topology to obtain multiple projection points, with each trajectory point corresponding to a projection point; and determining, among the multiple directed line segments of the road network topology, the multiple directed line segments on which the projection points are located as target directed line segments. The topological driving route corresponding to the first vehicle trajectory includes the target directed line segments. In this implementation, the target directed line segments included in the topological driving route of the first vehicle trajectory are determined by projecting the multiple trajectory points of the first vehicle trajectory onto the road network topology, thereby achieving representation of the first vehicle trajectory using the road network topology. This method is simple and easy to implement.

[0012] In some other embodiments, the process of obtaining a topological driving route may include: connecting multiple trajectory points of the first vehicle trajectory in chronological order to form a first trajectory line; determining the directed line segment combination with the highest correlation with the first trajectory line among multiple directed line segment combinations as the topological driving route corresponding to the first vehicle trajectory; each directed line segment combination includes two directed line segments in the road network topology of the target intersection, and the two directed line segments include: a directed line segment corresponding to the front section of the target intersection, and a directed line segment corresponding to the rear section of the intersection, and different directed line segments exist between different directed line segment combinations.

[0013] Exemplarily, the correlation between the first trajectory line and the directed line segment combination mainly represents the similarity of their trends, which can be obtained through slope analysis, derivative analysis or any other feasible method, which is not elaborated in this application.

[0014] In one possible implementation of the first aspect, the direction of travel of the first vehicle trajectory is determined based on the topological driving route corresponding to the first vehicle trajectory, including: determining the vector angle between two reference directed line segments, the reference directed line segment including a directed line segment in the target directed line segment whose node is located at the target intersection; and determining the direction of travel of the first vehicle trajectory based on the vector angle. In this implementation, the two reference directed line segments whose nodes are located at the target intersection represent the road preceding the intersection of the target intersection and the connecting road connected to the road preceding the intersection. Since each reference directed line segment is a directional vector, the method for determining the direction of travel of the first vehicle trajectory using the vector angle between the two reference directed line segments is simple and has low computational cost.

[0015] In a possible implementation of the first aspect, based on a vehicle trajectory set, a road network topology of a target intersection, and the travel directions of the vehicle trajectories in the vehicle trajectory set, determining the road condition information of the lanes in each travel direction of the road ahead of the intersection at a target time includes: determining the speed information of each vehicle trajectory in the vehicle trajectory set based on the vehicle trajectory set and the road network topology of the target intersection, the speed information of each vehicle trajectory including the speed information of the vehicle trajectory passing through the road ahead of the intersection; based on the travel directions of the vehicle trajectories in the vehicle trajectory set, determining the vehicle trajectories corresponding to each travel direction of the road ahead of the intersection from the vehicle trajectory set; and determining the road condition information of the lanes in each travel direction of the road ahead of the intersection at the target time based on the speed information of the vehicle trajectories corresponding to each travel direction of the road ahead of the intersection. In this implementation, the vehicle trajectories corresponding to each travel direction of the road ahead of the intersection are determined from the vehicle trajectory set, which is equivalent to grouping the vehicle trajectories in the vehicle trajectory set according to the travel direction. This is equivalent to improving the accuracy of the vehicle trajectories from the road level to the travel direction level. The speed information of the vehicle trajectories corresponding to each travel direction of the road ahead of the intersection is then used to determine the road condition information of the lanes in each travel direction of the road ahead of the intersection at the target time. This method is simple and has low computational cost.

[0016] In a possible implementation of the first aspect, the road condition information includes a travel time, and the speed information of each vehicle trajectory includes a first average speed, the first average speed being used to indicate the average speed of the corresponding vehicle trajectory on the road preceding the intersection. Determining the road condition information for each lane in each direction of the road preceding the intersection at a target time based on the speed information of the vehicle trajectory corresponding to each direction of the road preceding the intersection includes: determining the average speed corresponding to each direction of the road preceding the intersection based on the first average speed of the vehicle trajectory corresponding to each direction of the road preceding the intersection; and determining the travel time for each lane in each direction of the road preceding the intersection at the target time based on the directed line segments corresponding to the road preceding the intersection in the road network topology and the average speed corresponding to each direction of the road preceding the intersection. In this implementation, the travel time refers to the time required to pass through the target road preceding the intersection. When determining the average speed corresponding to each direction of the road preceding the intersection, the first average speed of all vehicle trajectories corresponding to that direction is fully considered, so that the average speed corresponding to each direction of the road preceding the intersection has high accuracy, thereby making the obtained travel time more accurate.

[0017] In a possible implementation of the first aspect, the road condition information also includes congestion information, and the speed information of each vehicle trajectory includes a first average speed, the first average speed being used to indicate the average speed of the corresponding vehicle trajectory on the road preceding the intersection; determining the road condition information of the lanes in each direction of travel on the road preceding the intersection at a target time based on the speed information of the vehicle trajectory corresponding to each direction of travel on the road preceding the intersection, including: determining the average speed corresponding to each direction of travel on the road preceding the intersection based on the first average speed of the vehicle trajectory corresponding to each direction of travel on the road preceding the intersection; and determining the congestion information of the lanes in each direction of travel on the road preceding the intersection at the target time based on the average speed corresponding to each direction of travel on the road preceding the intersection. In this implementation, when determining the average speed corresponding to each direction of travel, the first average speeds of all vehicle trajectories corresponding to that direction are fully considered, so that the average speed corresponding to each direction of travel has a high degree of accuracy, thereby making the obtained congestion information more accurate.

[0018] For example, the average speed corresponding to each direction of traffic on the road ahead of the intersection can be compared with a preset speed range to determine the congestion level of lanes in each direction of traffic on the road ahead of the intersection at the target time. In this implementation, the congestion level of lanes in each direction of traffic on the road ahead of the intersection at the target time is determined by comparing the average speed corresponding to each direction of traffic with a preset speed range. This method is simple and has low computational cost.

[0019] Illustratively, the congestion situation may include any one of unimpeded traffic, light congestion, congestion, or severe congestion.

[0020] For example, if the average speed corresponding to the first traffic direction is greater than 30km / h, the congestion situation of the lane in the first traffic direction of the road ahead of the intersection at the target time is determined to be unobstructed; if the average speed corresponding to the first traffic direction is greater than 20km / h and less than or equal to 30km / h, the congestion situation of the lane in the first traffic direction of the road ahead of the intersection at the target time is determined to be slightly congested; if the average speed corresponding to the first traffic direction is greater than 10km / h and less than or equal to 20km / h, the lane in the first traffic direction of the road ahead of the intersection at the target time is determined to be congested; if the average speed corresponding to the first traffic direction is less than or equal to 10km / h, the lane in the first traffic direction of the road ahead of the intersection at the target time is determined to be severely congested.

[0021] In a possible implementation of the first aspect, the road ahead of the intersection includes multiple different sub-sections, the road condition information includes the congestion situation of each sub-section, and the speed information of each vehicle trajectory includes multiple second average speeds, each second average speed is used to indicate the average speed of the corresponding vehicle trajectory on a sub-section of the road ahead of the intersection; based on the speed information of the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection, the road condition information of the lane in each traveling direction of the road ahead of the intersection at the target time is determined, including: based on the second average speed of each sub-section of the road ahead of the intersection corresponding to each traveling direction of the road ahead of the intersection, the average speed of each sub-section of the road ahead of the intersection in each traveling direction is determined; based on the average speed of each sub-section of the road ahead of the intersection in each traveling direction, the congestion situation of the lane in each traveling direction of each sub-section of the road ahead of the intersection at the target time is determined. In this implementation, when determining the average speed of each sub-section of the road before the intersection in each direction of travel, the second average speed of all vehicle trajectories corresponding to the direction of travel in each sub-section is fully considered, so that the average speed of each sub-section of the road before the intersection in each direction of travel has high accuracy, and thus the congestion situation of each sub-section obtained is more accurate; by determining the congestion situation of each sub-section of the multiple sub-sections of the road before the intersection, the obtained road condition information is more refined.

[0022] In a possible implementation of the first aspect, the traffic condition information of the target intersection at the target time also includes traffic condition information of the road behind the target intersection, the traffic condition information includes travel time and congestion, and the road network topology includes multiple directed line segments for representing the road length and the travel direction of the road; according to the vehicle trajectory set, the road network topology of the target intersection and the travel direction of the vehicle trajectory in the vehicle trajectory set, the traffic condition information of the target intersection at the target time is determined, including: according to the vehicle trajectory set and the road network topology of the target intersection, the speed information of each vehicle trajectory in the vehicle trajectory set is determined, and the speed information of each vehicle trajectory includes: the speed of the vehicle trajectory passing through the road in front of the intersection of the target intersection The method comprises the following steps: first, obtaining the vehicle trajectory information and the speed information of the road behind the target intersection as the vehicle trajectory passes through the target intersection; then, matching each vehicle trajectory with the road network topology of the target intersection to obtain the topological driving route corresponding to each vehicle trajectory, wherein the topological driving route corresponding to each vehicle trajectory is used to indicate the route represented by the vehicle trajectory as a directed line segment in the road network topology; and then, inputting the vehicle trajectories in the vehicle trajectory set, the topological driving routes of the vehicle trajectories in the vehicle trajectory set, the speed information of the vehicle trajectories in the vehicle trajectory set, and the travel directions of the vehicle trajectories in the vehicle trajectory set into a preset road condition information determination model to obtain the road condition information of the target intersection at the target time, wherein the preset road condition information determination model is a neural network model. In this implementation, the road condition information of the target intersection at the target time is obtained using the preset road condition information determination model, and the method is simple and highly accurate.

[0023] In a possible implementation of the first aspect, the preset neural network model includes: any one of a GraphSAGE model, a WDR model, a STGNN model, a Graph Transformer model, and a GCN model.

[0024] In a possible implementation of the first aspect, a road network topology includes multiple directed line segments for representing road lengths and road travel directions. Based on a vehicle trajectory set and the road network topology of a target intersection, speed information for each vehicle trajectory in the vehicle trajectory set is determined, including: projecting multiple trajectory points of each vehicle trajectory in the vehicle trajectory set onto the directed line segments of the road network topology to obtain multiple projection points, one for each trajectory point; and determining the speed information of each vehicle trajectory based on the projection points of each vehicle trajectory point on a first directed line segment and time information of each vehicle trajectory point, wherein the first directed line segment includes: a directed line segment in the road network topology corresponding to a road preceding the target intersection and / or a directed line segment in the road network topology corresponding to a road following the target intersection. In this implementation, the speed information of each vehicle trajectory is determined by projecting each vehicle trajectory point onto the directed line segments of the road network topology, and based on the projection points of each vehicle trajectory point on the first directed line segment and time information of each vehicle trajectory point. This method is simple and computationally inefficient.

[0025] In a possible implementation of the first aspect, the road condition information includes congestion conditions; obtaining a set of vehicle trajectories at a target intersection includes: obtaining a set of vehicle trajectories at the target intersection when it is determined that the distance between the location of the terminal device and the target intersection is less than a preset threshold; the method further includes: sending the congestion conditions of lanes in each direction of travel on the road preceding the intersection at a target time to the terminal device. In this implementation, the road condition information includes the congestion conditions of the road preceding the intersection; when it is determined that the distance between the location of the terminal device and the target intersection is less than a preset threshold, it indicates that the vehicle at the terminal device is relatively close to the intersection. At this time, the congestion conditions of lanes in each direction of travel on the road preceding the intersection at the target time are determined, and the congestion conditions are sent to the terminal device. The terminal device can display or voice broadcast the congestion conditions, so that the user can promptly obtain the congestion conditions of lanes in different directions on the road preceding the intersection, so that the user can select the appropriate lane as needed.

[0026] In a possible implementation of the first aspect, the road condition information also includes travel time, and the method further includes: obtaining a first travel direction, the first travel direction representing the travel direction of the lane of the navigation route in the front section of the road at the target intersection; using the travel time of the lane of the first travel direction of the front section of the road at the target time, updating the estimated arrival time of the navigation route, and obtaining the estimated arrival time of the navigation route at the target time; and sending the estimated arrival time of the navigation route at the target time to the terminal device. In this implementation, the road condition information includes travel time, and after obtaining the travel time of the lane of each travel direction of the front section of the road at the target time, the estimated arrival time of the navigation route in the terminal device is updated, obtaining the estimated arrival time of the navigation route at the target time, and sending the estimated arrival time of the navigation route at the target time to the terminal device. Because the travel time for each lane in each direction of travel at the target time is accurate to the lane's direction, the obtained travel time is highly accurate. Consequently, the estimated arrival time (ETA) updated based on the travel time is also accurate to the lane's direction of travel, making the navigation route's ETA at the target time highly accurate. The terminal device can display or voice broadcast the ETA for the navigation route at the target time, allowing users to obtain the navigation route's accurate ETA in a timely manner.

[0027] In a second aspect, a road condition information determination device is provided, which includes a unit for each step of the method in the above first aspect or any possible implementation of the first aspect.

[0028] In a third aspect, a communication device is provided, which includes units for performing each step of the method in the above first aspect or any possible implementation of any first aspect.

[0029] In a fourth aspect, a communication device is provided, which includes at least one processor and a memory, the processor and the memory are coupled, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the method in the above first aspect or any possible implementation of any first aspect is executed.

[0030] In a fifth aspect, a communication device is provided, which includes at least one processor and an interface circuit, and the at least one processor is used to execute: the method in the above first aspect or any possible implementation of any first aspect.

[0031] In a sixth aspect, an electronic device is provided, comprising a processor and a memory, wherein the memory is used to store instructions, and the processor is used to read the instructions to execute the method in the above first aspect or any possible implementation of any first aspect.

[0032] In the seventh aspect, a road condition information determination system is provided, which includes a terminal device and the electronic device described in the sixth aspect or any possible implementation method of the sixth aspect, and the terminal device is communicatively connected to the electronic device.

[0033] In an eighth aspect, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, it is used to execute the method in the above first aspect or any possible implementation of the first aspect.

[0034] In the ninth aspect, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed, it is used to execute the method in the above first aspect or any possible implementation of any first aspect.

[0035] In the tenth aspect, a chip is provided, which includes: a processor for calling and running a computer program from a memory, so that a terminal device equipped with the chip executes the method in the above first aspect or any possible implementation of any first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] FIG1 is a schematic diagram of two different intersections in a standard map.

[0037] FIG2 is a schematic diagram of an application scenario of a road condition recognition method and a schematic diagram of a lane-level road condition calculation method.

[0038] FIG3 is a schematic diagram of a system architecture provided in an embodiment of the present application, and a schematic diagram of an application scenario provided in an embodiment of the present application.

[0039] FIG4 is an interactive diagram of a method for determining road condition information provided in an embodiment of the present application.

[0040] FIG5 is a schematic diagram of matching vehicle trajectories to Links in a road network topology in one embodiment of the present application.

[0041] FIG6 is a schematic diagram of determining the travel direction of the lane where the vehicle is located based on the topological travel route in one embodiment of the present application.

[0042] FIG7 is a schematic diagram of determining the travel direction of the lane where the vehicle is located based on the topological driving route in another embodiment of the present application.

[0043] FIG8 is a schematic diagram of speed calculation in a method for determining road condition information in an embodiment of the present application.

[0044] Figure 9 is a schematic diagram of the navigation interface of the terminal device in one embodiment of the present application, and a schematic diagram of the cruise interface of the terminal device in one embodiment of the present application.

[0045] FIG10 is a schematic diagram of a navigation interface displayed when a vehicle passes through an intersection in different directions starting from the same starting point in an embodiment of the present application.

[0046] FIG11 is a schematic diagram of the lane-level road conditions and ETA calculation process for each direction of travel on the road ahead of the intersection in the road condition information determination method provided in one embodiment of the present application.

[0047] FIG12 is a technical effect diagram of a method for determining road condition information provided in an embodiment of the present application.

[0048] FIG13 is a schematic diagram of a lane-level ETA determined in a method for determining road condition information provided in an embodiment of the present application.

[0049] FIG14 is a flow chart of a method for determining road condition information provided in an embodiment of the present application.

[0050] FIG15 is a flow chart of determining the travel direction of the first vehicle trajectory in the road condition information determination method provided in an embodiment of the present application.

[0051] FIG16 is a hardware structure block diagram of an example of a terminal device provided in this application.

[0052] FIG17 is a schematic diagram of a chip system provided in this application. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0054] The terms used in the following embodiments are only for the purpose of describing specific embodiments and are not intended to be limiting of the present application. As used in the specification and appended claims of this application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include expressions such as "one or more", unless there is a clear contrary indication in the context. It should also be understood that in the embodiments of the present application, "one or more" refers to one or more (including two); "and / or" describes the association relationship of associated objects, indicating that three relationships may exist; for example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship.

[0055] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically stated. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically stated.

[0056] The "multiple" involved in the embodiments of the present application means greater than or equal to two. It should be noted that in the description of the embodiments of the present application, the words "first" and "second" are only used for the purpose of distinguishing the description and cannot be understood as indicating or implying relative importance or order.

[0057] In addition, various aspects or features of the present application can be implemented as methods, devices or products using standard programming and / or engineering techniques. The term "product" used in the embodiments of the present application covers computer programs that can be accessed from any computer-readable device, carrier or medium. For example, computer-readable media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks or tapes, etc.), optical disks (e.g., compact discs (CDs), digital versatile discs (DVDs), etc.), smart cards and flash memory devices (e.g., erasable programmable read-only memories (EPROMs), cards, sticks or key drives, etc.). In addition, the various storage media described herein may represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing and / or carrying instructions and / or data.

[0058] To facilitate understanding, the key terms involved in this application are first explained below.

[0059] Standard Definition (SD) maps have relatively low accuracy and detail and are typically used to meet general navigation and location-based service needs. With an accuracy of approximately 5 to 10 meters, SD maps are generally used in scenarios where precision is not a priority or where fast loading and processing is required. For example, they can be used for mobile app navigation and in-car navigation. The road information included in SD maps is Standard Definition Road (SdRoad), which typically includes basic information such as the road's direction, length, and width.

[0060] High-definition (HD) maps are extremely precise and detailed map data. HD maps achieve both absolute and relative accuracy down to the centimeter level. They contain a rich set of navigational elements, supporting lane-level navigation and intelligent driving. HD maps include high-definition lanes (HdLane) and high-definition roads (HdRoad). This means that HD maps accurately represent road direction, shape, lane divisions, traffic signals, and other information.

[0061] High-precision positioning information: refers to positioning information with positioning accuracy reaching the decimeter, centimeter, or even millimeter level. The realization of high-precision positioning mainly relies on the integrated use of multiple positioning technologies, including satellite positioning (such as GPS, Galileo satellite navigation system, China's Beidou satellite navigation system, etc.), inertial measurement unit (IMU) positioning, geomagnetic and map matching positioning, and visual inertial positioning.

[0062] Standard-precision positioning information: This refers to positioning information with relatively low accuracy, typically reaching meter-level accuracy or better. This type of positioning information is sufficient for daily life and many applications, such as mobile navigation and location-based services. Standard-precision positioning primarily relies on traditional GPS or mobile network positioning technology.

[0063] Road condition information: The road condition in the embodiment of the present application mainly refers to real-time road condition information, which mainly describes the current road conditions, for example, may include: estimated arrival time, congestion conditions, etc.

[0064] Estimated Time of Arrival (ETA): This is used to indicate the estimated time required to travel from a starting point to a destination. In navigation, it can indicate the estimated time required to travel from the starting point or the vehicle's location to the destination according to the planned route. It can also indicate the time it takes for a vehicle to travel over any section of road.

[0065] Road network topology, also known as road topology, is a crucial component of map data used to describe the connections between road elements in a road network. It represents relationships such as connectivity, intersections, and junctions between roads. In road network topology, a link, also known as a directed line segment or link, is the fundamental element that describes the connections between sub-segments in a road network. A link represents a direct connection between two nodes, and the endpoints of a link are called nodes. Nodes typically represent intersections or road endpoints.

[0066] The road before the intersection: This refers to the section of road before the intersection, serving as the transitional area between the current intersection and other sub-segments. This road before the intersection can be the road before a T-junction, Y-junction, crossroads, or X-junction. In the Link connection relationship of the road network topology in the map data, the link corresponding to the road before the intersection has multiple subsequent links.

[0067] Intersection back section: This refers to the section of road after the intersection, forming the transition area between the current intersection and other sub-segments. The back section of the intersection road connects with the front section of the intersection to form the intersection. At an intersection, each front section of the intersection road is connected to multiple back sections of the intersection road. In the Link connection relationship of the road network topology in the map data, the link corresponding to the back section of the intersection road is the successor link of the link corresponding to the front section of the intersection.

[0068] The concept of the road ahead of an intersection is exemplarily described below with reference to the accompanying drawings. FIG1 is a schematic diagram of two different intersections in a precise map.

[0069] As shown in Figure 1a, the first intersection in the precision map includes: an SD intersection area, an SD road topology, lane boundaries, ground arrow information, and lane numbers. The SD road topology includes multiple interconnected links. Figure 1 illustrates three links: a first link 111, a second link 112, and a third link 113. Second link 112 and third link 113 are successors to first link 111. The link corresponding to the front section of the intersection is first link 111, while second link 112 and third link 113 correspond to the two rear sections of the intersection. As shown in Figure 1, based on the ground arrow information, the front section of the intersection includes three lanes with different traffic directions: a left-turn lane, a through lane, and a right-turn and through lane.

[0070] As shown in Figure 1(b), the second intersection in the precision map includes: an SD intersection area, an SD road topology, lane boundaries, ground arrow information, and lane numbers. The SD road topology includes multiple interconnected links. Figure 1(b) also illustrates three links, namely, the fourth link 121, the fifth link 122, and the sixth link 123. The fifth link 122 and the sixth link 123 are the subsequent links of the fourth link 121. The link corresponding to the front section of the intersection is the fourth link 121, and the fifth link 122 and the sixth link 123 are the links corresponding to the two rear sections of the intersection. As shown in Figure 1b, according to the ground arrow information, under the actual lane division, the road section before the intersection includes three through lanes. However, according to the road network topology, there is a small road on the left side that can be turned. Therefore, the leftmost through lane in the road section before the intersection is actually a through lane and a left-turn lane. Therefore, the road section before the intersection still has two lanes with different traffic directions.

[0071] As shown in Figure 1, the road section before the intersection is the part of the road before reaching the intersection. It is a transition area connecting the current intersection and other sub-sections. The road section before the intersection usually includes multiple lanes with different traffic directions, such as through lanes, left-turn lanes, and right-turn lanes. At the same time, the traffic condition information of lanes with different traffic directions in the road section before the intersection often varies.

[0072] In addition, the rear section of the road after the intersection is the part of the road after the intersection. Generally, the rear section of the road after the intersection only includes through lanes. As shown in Figure a of Figure 1, the rear section of the road after the intersection corresponding to the third link 113 only includes two through lanes.

[0073] The navigation function of currently commonly used map apps can usually only provide road-level traffic information; road-level traffic information can usually be determined based on the GPS positioning information uploaded by the user's terminal device. The positioning accuracy of GPS positioning information is at the level of several meters to more than ten meters. Therefore, the traffic information determined based on GPS positioning information is difficult to be accurate to the lane level, and therefore it is difficult to determine the traffic information of lanes with different traffic directions on the road ahead of the intersection.

[0074] Currently, there are also some solutions that can determine lane-level road conditions, which are exemplified below.

[0075] Figure 2(a) shows an example application scenario for a road condition recognition method that can determine lane-level road conditions. The road condition recognition method in this example is used to identify lane-level road condition information in front of a target object. This road condition recognition method collects the driving trajectory of vehicles in front of the target object and analyzes the driving trajectory to determine the road condition information of the lane in which the target object is located. In the scenario shown in Figure 2(a), the target object is a toll booth, and the different lanes are ETC toll lanes and manual toll lanes. The identified lane-level road condition information includes lane-level road condition information for manual toll lanes and lane-level road condition information for ETC toll lanes. In this scenario, the server collects the driving trajectories of vehicles in front of the highway toll booth and, based on the driving trajectory statistics, obtains the queue distance distribution information and queue duration distribution information of vehicles in front of the toll booth. Based on this queue distance distribution information and queue duration distribution information, the lane-level road condition in front of the toll booth is determined. When it is determined that a lane-level road condition has occurred in front of a toll station based on the queue distance distribution information and the queue time distribution information, the vehicles are divided into fast vehicles and slow vehicles based on their driving speed in front of the toll station, with ETC vehicles being fast vehicles and non-ETC vehicles being slow vehicles; the road condition information of the ETC toll channel is determined based on the average driving speed and average queue time of fast vehicles, and the road condition information of the manual toll channel is determined based on the average driving speed and average queue time of slow vehicles.

[0076] The road condition recognition method shown in Figure a in Figure 2 relies on the target object to calculate the lane-level road condition in front of the target object. It cannot calculate the lane-level road condition in the intersection scenario without the target object. That is, for the intersection without the target object, the road condition recognition method shown in Figure a in Figure 2 cannot determine the road condition information of the lanes in different directions of the road in front of the intersection; if the road condition calculation of the lanes in different directions of the road in front of each intersection is to be realized, it is necessary to set the target object for the lane in each direction of each intersection, which will cost a huge amount of money.

[0077] Figure 2b shows a schematic diagram of a lane-level road condition calculation method. The method illustrated in Figure 2b includes: obtaining positioning data collected by a high-precision positioning sensor on a vehicle, sorting the trajectory points according to the sampling time and plane coordinates corresponding to each trajectory point in the positioning data, and generating a vehicle trajectory sequence; segmenting the trajectory sequence based on the positional relationship between the centerlines of each lane in the preset high-precision map data and each trajectory point in the trajectory sequence, and determining trajectory subsequences matching each lane; and calculating the average vehicle speed within each lane based on the trajectory subsequence matching the lane, and determining the lane's road condition by comparing the average vehicle speed with the preset speed for the lane. Figure 2b illustrates eight trajectory points ① through ⑧. Taking trajectory point ① as an example, trajectory point ① can be perpendicularly projected onto the centerlines L1, L2, and L3 of the first, second, and third lanes in the high-precision map data, respectively. The perpendicular projection distances D1, D2, and D3 from the plane coordinate corresponding to trajectory point ① to the centerlines of each lane are calculated, respectively. Assuming that D1 has the smallest value among D1, D2, and D3, it can be seen that the vertical projection distance from trajectory point ① to centerline L1 is the shortest. Therefore, the first lane to which centerline L1 belongs can be determined as the lane where trajectory point ① is located. Traverse all trajectory points in the trajectory sequence in Figure 2b, determine the centerline with the smallest vertical projection distance from each trajectory point, and then determine the lane that matches each trajectory point. This method requires matching the high-precision positioned trajectory points to the centerline of the lane on the high-precision map. Therefore, it is highly dependent on high-precision positioning sensors and high-precision map data. If the positioning information accuracy or map data accuracy is not high, it is impossible to calculate the lane-level road conditions of the road ahead of the intersection. In addition, since this method is based on high-precision data, the data maintenance cost and computational cost are relatively high.

[0078] In summary, based on the current lane-level road condition determination method, in order to determine the road condition information of lanes in different traffic directions on the road ahead of the intersection, it is necessary to set specific targets for each intersection, or rely on high-precision positioning information and high-precision map data. Therefore, the implementation plan is relatively complex and the cost will be relatively high.

[0079] In view of this, the present application provides a method for determining road condition information, in which a vehicle trajectory set is first obtained, the vehicle trajectory set including multiple vehicle trajectories that pass through the intersection before the target time; then, based on each vehicle trajectory and the road network topology of the intersection, the travel direction of each vehicle trajectory is determined, and the travel direction of each vehicle trajectory is used to indicate the travel direction of the lane where each vehicle trajectory is located on the road ahead of the intersection; finally, based on the vehicle trajectory set, the road network topology of the intersection and the travel direction of each vehicle trajectory in the vehicle trajectory set, the road condition information of each lane in each travel direction of the road ahead of the intersection at the target time is determined. This method determines the lane direction that the vehicle trajectory has traveled in the road ahead of the intersection based on each vehicle trajectory and the road network topology of the intersection, thereby realizing lane-level road condition calculation for the road ahead of the intersection. The above method can realize the determination of road condition information on lanes of different travel directions on the road ahead of the intersection, and the method is simple and easy to implement. Moreover, the vehicle trajectory used in the above method can be standard precision trajectory data or high precision trajectory data, and the map data used can be standard precision map data or high precision map data. Therefore, lane-level road condition information calculation can be achieved without relying on high precision trajectory data and high precision maps, which has a wide range of applications and low calculation costs.

[0080] The following is an illustrative description of the road condition information determination method provided by the present application. Those skilled in the art will appreciate that the following content is merely an example and is not intended to limit the scope of protection of the present application.

[0081] It should be noted that in the embodiments of the present application, "terminal device," "electronic device," and "terminal" all have the same meaning and can be used interchangeably. "Travel time" and "travel duration" have the same meaning and can be used interchangeably.

[0082] To facilitate understanding, the system architecture in the embodiments of the present application is first described below.

[0083] Referring to FIG3 , FIG3 a is a schematic diagram of a system architecture in an embodiment of the present application, and FIG3 b is a schematic diagram of an application scenario in an embodiment of the present application.

[0084] As shown in Figure a in Figure 3, the system architecture includes a server 310 and a terminal device 320, wherein the server 310 and multiple terminal devices 320 are communicatively connected, and the communication connection can be a wired communication connection or a wireless communication connection, which is not limited in this application.

[0085] In the embodiment of the present application, the wireless communication may be one or more of mobile communication, satellite communication, wireless local area network (WLAN), wireless local area network (Wi-Fi), Bluetooth, Bluetooth Low Energy (BLE), radio frequency identification (RFID), infrared, and ultra-wideband (UWB).

[0086] Among them, the server 310 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal device 320 can be a vehicle-mounted terminal, or a mobile terminal device located on a vehicle. The mobile terminal device is an electronic device installed with an electronic map, and can include, for example: handheld devices (such as smartphones), various portable notebooks, various tablet computers, laptops, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), vehicle-mounted devices (such as vehicle-mounted head-up display devices), wearable devices, etc. For example, the terminal device in the embodiment of the present application can be: a smartphone, a mobile tablet, a vehicle-mounted tablet, a smart watch, and other terminal devices. The embodiment of the present application is not limited here.

[0087] Exemplarily, the server 310 may be a cloud server that carries cloud-based map services and provides map services, such as real-time navigation, route planning, and cruise services, to the terminal device 320 through a network request service interface; the terminal device 320 serves as a human-computer interaction interface for users to use map applications, and users interact with the terminal device through clicks, touches, buttons, voice, gestures, etc. to use the navigation function, route planning function, cruise function, etc. of the map application.

[0088] It is understandable that since the server 310 interacts with multiple terminal devices for navigation, the server 310 can obtain the positioning information of multiple different terminal devices, and then determine the driving trajectory of the vehicle where each terminal device is located based on the positioning information sent by different terminal devices.

[0089] As shown in Figure b in Figure 3, the application scenario of the road condition information determination method in the embodiment of the present application mainly relies on the terminal device. For example, the terminal device can be a mobile phone, a car-mounted tablet, and other terminal devices with map functions and other hardware; in terms of software, it is mainly used in map-related APPs, map-related applets, and other APPs with map functions; in terms of usage scenarios, it is mainly used in path planning and cruising in navigation.

[0090] The following is an illustrative description of the usage scenario of the road condition information determination method in the embodiment of the present application in combination with the system architecture in Figure a in Figure 3. The road condition information determination method in the embodiment of the present application is applied to the server 310 in the system architecture as shown in Figure a in Figure 3.

[0091] First, the usage scenario of navigation is explained. Take the scenario where the user uses the map application software in the terminal device 320 for navigation while driving vehicle A as an example. In this scenario, while the server 310 interacts with one terminal device 320, the server 310 can also interact with other terminal devices in the same way.

[0092] In this application scenario, while driving vehicle A, the user uses the map application software on terminal device 320 for navigation, and the route being navigated is displayed on the interface of terminal device 320. Terminal device 320 sends real-time positioning information to server 310. Server 310 updates the traffic information of the route being navigated based on the received positioning information and sends the updated result to terminal device 320, which then displays the updated navigation route.

[0093] When the server 310 determines that the distance between vehicle A and intersection B is less than a preset threshold based on the current positioning information sent by the terminal device 320, the server 310 obtains multiple vehicle trajectories that passed through intersection B before the current moment; the server 310 determines the travel direction of the lane of the road ahead of the intersection B for each vehicle trajectory based on each vehicle trajectory and the road network topology of intersection B; the server 310 determines the traffic condition information of each lane in each travel direction of the road ahead of the intersection at the current moment based on the multiple vehicle trajectories, the road network topology of intersection B and the travel direction corresponding to each vehicle trajectory; the server 310 obtains the first travel direction of the lane of the road ahead of the intersection for the route being navigated displayed in the interface of the terminal device 320; the server 310 uses the traffic condition information of the lane in the first travel direction of the road ahead of the intersection at the current moment to update the traffic condition information of the navigated route, and sends the updated route to the terminal device 320, and the terminal device 320 displays the updated route.

[0094] For example, the road condition information may include congestion conditions and travel time. Therefore, the server 310 uses the road condition information of the first travel direction lane in the road ahead of the intersection at the current moment to update the navigation route, which may include: updating the congestion conditions of the navigation route in the road ahead of intersection B, and updating the estimated arrival time of the navigation route.

[0095] For example, the server 310 updating the congestion situation of the road ahead of the intersection of the navigation route at intersection B may include: sending the congestion situation of each direction of the road ahead of the intersection to the terminal device 320. After receiving the congestion situation of each direction of the road ahead of the intersection sent by the server 310, the terminal device 320 may render the lane-level congestion situation of the road ahead of the intersection in the enlarged view of the intersection. The terminal device 320 may also render the congestion situation of the first direction of travel to the portion of the navigation route corresponding to the road ahead of the intersection.

[0096] For another example, the server 310 updating the estimated time of arrival of the navigation route may include: calculating the estimated time of arrival of the navigation route using the travel time in the first direction of travel of the road ahead of the intersection, and sending the calculated estimated time of arrival of the navigation route to the terminal device 320. The terminal device 320 may display the received estimated time of arrival on the navigation interface. The specific display method of the estimated time of arrival can be set as needed and is not described in detail here.

[0097] After explaining the usage scenarios of navigation, the following explains the usage scenarios of cruising. Take the scenario where the user opens the map application software in the terminal device 320 while driving vehicle A, but does not use the map application software for navigation as an example. In this scenario, the terminal device 320 can send positioning information to the server 310, and the server 310 provides services related to the current location to the terminal device 320.

[0098] When server 310 determines, based on the current positioning information sent by terminal device 320, that the distance between vehicle A and intersection B is less than a preset threshold, server 310 obtains multiple vehicle trajectories that passed through intersection B before the current moment. Server 310 determines the direction of travel of each vehicle trajectory in the lane of the road preceding intersection B based on each vehicle trajectory and the road network topology of intersection B. Server 310 determines the current traffic condition information for each lane in each direction of travel on the road preceding intersection based on the multiple vehicle trajectories, the road network topology of intersection B, and the direction of travel corresponding to each vehicle trajectory. In this scenario, the traffic condition information may include congestion. Server 310 transmits the current congestion status of each lane in each direction of travel on the road preceding intersection to terminal device 320, which can then prompt the user with the traffic condition information for intersection B. For example: the terminal device 320 can pop up an enlarged image of intersection B in the interface, and the enlarged image of intersection B will show the congestion situation of the lanes in each direction of the road ahead of the intersection B where vehicle A is about to arrive; of course, the terminal device 320 can also prompt the user through voice broadcast the congestion situation of the lanes in each direction of the road ahead of the intersection B where vehicle A is about to arrive, and this application does not impose any restrictions on this.

[0099] The following is an exemplary description of the process of the road condition information determination method in the embodiment of the present application based on the scenario where the server 310 provides navigation services to the terminal device 320 when the vehicle A where the terminal device 320 is located has arrived at or is about to arrive at the front section of the intersection B.

[0100] FIG4 is an interactive diagram of a method for determining road condition information provided in an embodiment of the present application. As shown in FIG4 , the method for determining road condition information in this embodiment includes steps S410 to S470, wherein:

[0101] S410: The server obtains multiple vehicle trajectories.

[0102] Exemplarily, the server 310 determines that the current location of the terminal device 320 (i.e., vehicle A) is located on the road in front of the intersection B based on the positioning information sent by the terminal device 320. The server 310 obtains multiple vehicle trajectories, which are trajectories formed in the process of vehicles before vehicle A passing through the intersection B, and the moment when the vehicle corresponding to each vehicle trajectory passes through the intersection B is less than the current moment. The difference is less than a first threshold.

[0103] For example, the first threshold may be 2 minutes, that is, each vehicle trajectory is a trajectory of a vehicle that passed through intersection B within 2 minutes before the current moment.

[0104] It should be understood that the size of the first threshold is related to the refresh speed of the road condition information, so the first threshold can also be other values, which will not be described or enumerated here.

[0105] S420: The server matches each vehicle trajectory to a Link in the road network topology and determines the topological driving route corresponding to each vehicle trajectory.

[0106] FIG5 is a schematic diagram of matching a vehicle trajectory to a Link in a road network topology in one embodiment of the present application.

[0107] As shown in Figure 5 , this embodiment uses the intersection shown in Figure 1 as an example. The SD road topology includes three links: a first link 111, a second link 112, and a third link 113. Each vehicle trajectory includes multiple trajectory points 501. Each trajectory point 501 is projected onto a link in the road network topology to obtain a projection point 502 of each trajectory point 501 on the link. Each trajectory point 501 corresponds to a projection point 502. After the projection is completed, a topological driving route corresponding to the vehicle trajectory can also be obtained. A topological driving route is a driving route expressed in links of the road network topology. As shown in Figure 5 , the topological driving route obtained in this embodiment includes the driving routes of the first link 111 and the third link 113.

[0108] It should be understood that projecting trajectory points onto Links in the road network topology is a mature existing technology and will not be described in detail here.

[0109] S430: The server determines the travel direction of the lane where each vehicle trajectory is located in the front section of the road at the intersection according to the topological travel route corresponding to each vehicle trajectory.

[0110] In an embodiment, after determining the topological driving route corresponding to the vehicle trajectory, the travel direction of the lane where the vehicle trajectory is located in the front section of the road at the intersection can be determined based on the topological driving route.

[0111] Figure 6 is a schematic diagram illustrating how the direction of travel of a vehicle's lane is determined based on a topological route in one embodiment of the present application. As shown in Figure 6 , the refined map of this embodiment also includes an intersection lane connectivity relationship 601 before and after the intersection. Intersection lane connectivity relationship 601 represents the lane connectivity relationship between two links before and after the intersection in the road network topology, as well as the lane number and direction attribute of the lane corresponding to each of the two links in the intersection lane connectivity relationship. The direction attribute may also be referred to as the travel direction.

[0112] It should be understood that Figure 6 only illustrates a portion of the lane connectivity relationship corresponding to the intersection, specifically the lane connectivity relationship corresponding to a left turn on the road ahead of the intersection. The complete lane connectivity relationship should also include the lane connectivity relationship for vehicles traveling in other directions on the road ahead of the intersection, as well as the lane connectivity relationship for oncoming vehicles, which are not shown in Figure 6 for simplicity.

[0113] In the embodiment shown in FIG6 , the topological driving route is a driving route including a first Link 611 and a second Link 612 , and the direction of the topological driving route is from the second Link 612 to the first Link 611 , and the second Link 612 is a link corresponding to the road ahead of the intersection.

[0114] When determining the travel direction of the vehicle trajectory in the lane located on the road ahead of the intersection, first, based on the first link 611 and the second link 612 in the topological travel route, the intersection lane connectivity relationship corresponding to the topological travel route is determined from the intersection lane connectivity relationship 601 (this partial intersection lane connectivity relationship is the intersection lane connectivity relationship shown in Figure 6). Then, based on this partial intersection lane connectivity relationship, the travel direction of the lane corresponding to the second link 612 is determined. This travel direction is the travel direction of the vehicle trajectory in the lane located on the road ahead of the intersection.

[0115] For example, based on the topological driving route, it can be determined that the road section before the intersection corresponds to the second link 612, and the road section after the intersection corresponds to the first link 611. From the intersection lane connectivity relationship in the road network topology, the local intersection lane connectivity relationship corresponding to the topological driving route from the second link 612 to the first link 611 can be queried. As shown in Figure 6, the three lanes corresponding to the second link 612 are numbered ①, ②, and ③, respectively, and the two lanes corresponding to the first link 611 are numbered ④ and ⑤, respectively. Based on the local intersection lane connectivity relationship corresponding to the topological driving route, the lane connection relationship from the second link 612 to the first link 611 can be determined as: lane ① of the second link 612 to lanes ④ and ⑤ of the first link 611. Therefore, it can be determined that the lane the vehicle track traveled in on the second link 612 was lane ①. Since lane ① is a left-turn lane, the direction of travel of the vehicle track in the lane of the road section before the intersection is determined to be a left turn.

[0116] It is understandable that in the front section of the road at some large intersections, there may be multiple lanes with the same traffic direction, such as 2 left-turn lanes, 3 straight lanes, etc. The method in the embodiment of the present application can determine the traffic direction of the lane where the vehicle trajectory is located. For the front section of the road at the intersection where there are multiple lanes with the same traffic direction, the road condition information of different lanes in the same direction is usually basically the same. Therefore, it is only necessary to determine the traffic direction of the lane where the vehicle trajectory is located, and there is no need to specifically determine the specific lane to which the vehicle trajectory belongs.

[0117] In other embodiments, when determining the travel direction of the lane where the vehicle is located based on the topological driving route, the travel direction of the lane where the vehicle trajectory is located in the front section of the road at the intersection can also be determined based on the vector angle between two links involved in the topological driving route.

[0118] For example, Figure 7 is a schematic diagram of determining the travel direction of the lane where the vehicle is located based on the topological driving route in another embodiment of the present application. In the embodiment shown in Figure 7, the topological driving route includes the driving route of the first Link 711 and the second Link 712. The topological driving route is determined according to the size of the vector angle from the first Link 711 to the second Link 712 to determine the travel direction of the lane where the vehicle trajectory is located in the front section of the road at the intersection.

[0119] Exemplarily, as shown in FIG7 , the first link 711 is extended along its direction to obtain an extension line 701 ; the angle from the extension line 701 to the first link 711 is rotated counterclockwise as β, and the direction of travel of the vehicle trajectory in the lane where the road in front of the intersection is located is determined according to the size of β.

[0120] For example, when 0°≤β≤20° or 340°≤β≤360°, the direction of the vehicle trajectory in the lane where the road ahead of the intersection is located is determined to be straight ahead; when 20°<β<180°, the direction of the vehicle trajectory in the lane where the road ahead of the intersection is located is determined to be a left turn or a U-turn; when 180°<β<340°, the direction of the vehicle trajectory in the lane where the road ahead of the intersection is located is determined to be a right turn.

[0121] It should be understood that when the vehicle trajectory turns left or makes a U-turn on the road ahead of the intersection, the vehicle will travel in the left-turn lane. Therefore, when 20°<β<180°, the lane where the vehicle is located is the left-turn lane.

[0122] It is understandable that in some other embodiments, the angle α rotated counterclockwise from the extension line 701 to the first link 711 can be determined, and the direction of travel of the vehicle trajectory in the lane where the road in front of the intersection is located can be determined based on the size of α. The principle is similar to the method of determining the direction of travel by angle β, and this application will not elaborate on this.

[0123] S440 , the server determines speed information of each vehicle trajectory according to each vehicle trajectory and the topological driving route corresponding to each vehicle trajectory.

[0124] Exemplarily, the speed information of each vehicle trajectory may include the speed information of the vehicle trajectory on the road ahead of the intersection. The speed information of each vehicle trajectory on the road ahead of the intersection can be determined based on the projection point on the link corresponding to the road ahead of the intersection in the topological driving route of each vehicle trajectory and the corresponding trajectory point.

[0125] For example, the speed information of each vehicle trajectory may include: the average speed of the Link corresponding to the preceding section of the intersection in the topological driving route of each vehicle trajectory, and the average speed of each sub-segment in the Link corresponding to the preceding section of the intersection.

[0126] In some other embodiments, the speed information of each vehicle trajectory may also include: the speed information of the vehicle trajectory on the road behind the intersection. The speed information of each vehicle trajectory on the road behind the intersection can be determined based on the projection point on the link corresponding to the road behind the intersection in the topological driving route of each vehicle trajectory and the corresponding trajectory point.

[0127] For example, the speed information of each vehicle trajectory may include: the average speed of the link corresponding to the rear section of the intersection in the topological driving route of each vehicle trajectory, and the average speed of each sub-segment in the link corresponding to the rear section of the intersection.

[0128] It is understood that, among the multiple track points of each vehicle track, the marking time of each track point is fixed, so the time interval between any two track points can be determined based on the marking time of the two track points. The distance between any two projection points in the topological driving route corresponding to the vehicle track can be determined based on the coordinates of the two projection points.

[0129] Assuming that the time interval between the marking times of two trajectory points in the vehicle trajectory is t, and the distance s between the two projection points corresponding to the two trajectory points in the topological driving route corresponding to the vehicle trajectory is s, then the average speed v between the two projection points can be obtained according to formula (1):

[0130] In formula (1), v represents the average speed of the vehicle between two projection points, s represents the distance between the two projection points, and t represents the time interval between the two trajectory points.

[0131] For example, based on the same principle as formula (1), the average speed corresponding to each link in the topological driving route corresponding to each vehicle trajectory can be determined, or each link can be divided into multiple sub-segments and the average speed corresponding to each sub-segment in each link can be determined.

[0132] For example, the average speed corresponding to a Link can be determined based on the distance between the two farthest projection points on a Link and the time interval between the trajectory points corresponding to the two projection points; similarly, the average speed corresponding to the Link can be determined based on the distance between the two farthest projection points on a subsegment of the Link and the time interval between the trajectory points corresponding to the two projection points.

[0133] In some embodiments, the time interval between the marking of two adjacent track points in the vehicle trajectory is fixed. Figure 8 is a schematic diagram of speed calculation in the road condition information determination method in one embodiment of the present application. As shown in Figure 8, track point G1 and track point G2 are two adjacent track points in the vehicle trajectory, projection point Y1 is the projection point corresponding to track point G1, and projection point Y2 is the projection point corresponding to track point G2; the time interval between the marking of track point G1 and track point G2 is 1 second, and the distance between projection point Y1 and projection point Y2 is 5 meters, then the average speed of the vehicle trajectory between the two track points is 18 km / h.

[0134] S450, the server determines the traffic condition information of the lanes in each direction of travel on the road ahead of the intersection based on the travel direction of the lane where each vehicle trajectory is located on the road ahead of the intersection and the speed information of each vehicle trajectory.

[0135] In an embodiment, the traffic condition information may include one or more of congestion conditions and estimated arrival time, wherein the estimated arrival time indicates the travel time in each direction of travel on the road ahead of the intersection.

[0136] In some embodiments, the traffic condition information of the lanes in each direction of travel of the road ahead of the intersection can be determined by setting a speed threshold by summarizing and calculating the data of vehicle trajectories in different directions of travel.

[0137] It should be understood that, assuming that vehicle trajectory S1 and vehicle trajectory S2 correspond to the same travel direction, then the Link in the topological driving route corresponding to vehicle trajectory S1 is the same as the Link in the topological driving route corresponding to vehicle trajectory S2, that is, the topological driving routes corresponding to vehicle trajectories corresponding to the same travel direction have the same Link.

[0138] Assume that the road ahead of the intersection has three different traffic directions: left turn, right turn, and straight ahead. There are N1 vehicle trajectories with a left turn direction, N2 vehicle trajectories with a right turn direction, and N3 vehicle trajectories with a straight ahead direction. Below, we use the N1 vehicle trajectories with a left turn direction as an example to illustrate the process of determining traffic condition information for the left-turn lane on the road ahead of the intersection.

[0139] Assume that the topological driving route corresponding to N1 vehicle trajectories in the left-turn direction is shown in Figure 7. That is, the topological driving route includes a first link 711 and a second link 712. The first link 711 corresponds to the road ahead of the intersection, and the length of the first link 711 is L1. The first link 711 corresponds to N1 first average speeds, and the average of the N1 first average speeds is determined as the average speed V1 corresponding to the first link 711. The travel time t of the left-turn lane on the road ahead of the intersection is LAccording to formula (2), we can obtain:

[0140] It is understandable that, in addition to determining the average speed V1 corresponding to the first Link 711 by averaging the N1 first average speeds, other methods can also be used to determine it. For example, it can be determined by taking a weighted average of the N1 first average speeds, or the median of the N1 first average speeds can be used as the average speed V1 corresponding to the first Link 711. This application does not elaborate on this.

[0141] For example, the congestion condition of the left-turn lane of the road ahead of the intersection may be determined according to the speed range in which the average speed V1 corresponding to the first Link 711 lies.

[0142] For example, the average vehicle speed corresponding to the first Link 711 is V1: if V1>30km / h, the congestion condition of the left-turn lane of the road ahead of the intersection is determined to be unobstructed; if 20km / h<V1≤30km / h, the congestion condition of the left-turn lane of the road ahead of the intersection is determined to be slightly congested; if 10km / h<V1≤20km / h, the congestion condition of the left-turn lane of the road ahead of the intersection is determined to be congested; if V1≤10km / h, the congestion condition of the left-turn lane of the road ahead of the intersection is determined to be severely congested.

[0143] It should be understood that the congestion conditions in the above example are divided into four types: unobstructed, light congestion, congestion and severe congestion. The types of congestion conditions can be increased or decreased as needed; in addition, the speed ranges corresponding to different types of congestion conditions can be adjusted as needed, and this application does not impose any restrictions on this.

[0144] It is understandable that the travel time t for the left turn is L , which can also be called the estimated arrival time on the left-turn lane of the road ahead of the intersection.

[0145] Alternatively, the first link 711 can be divided into multiple sub-segments, and the average speed corresponding to each sub-segment can be determined. Based on the speed range within which the average speed of each sub-segment falls, the congestion situation of the corresponding sub-segment can be determined. This segmented processing of the link allows for a more refined and accurate assessment of the congestion situation on the road ahead of the intersection.

[0146] It should be understood that the above example only takes the N1 vehicle trajectories in the left-turn direction as an example to illustrate the process of determining the road condition information of the left-turn lane of the road in front of the intersection. The road condition information of lanes in other directions of travel can be determined by referring to the above example, and this application will not go into details.

[0147] It is understood that the road behind the intersection generally includes a through lane. For the same road behind the intersection, the road condition information for different through lanes is almost identical. Therefore, the road condition information for the road behind the intersection can be determined based on the speed information of each vehicle trajectory. The specific process is similar to step S450 and is not further described here.

[0148] In some other embodiments, a preset road condition information determination model may be used to determine the road condition information of lanes in each direction of travel on the road ahead of the intersection.

[0149] Exemplarily, the preset road condition information determination model can be a neural network model. Exemplarily, the road condition information determination model can be a GraphSage model, a WDR (Wide-deep-recurrent) model, an STGNN model, a Graph Transformer model, a GCN model, etc. This application does not impose any restrictions on this.

[0150] Among them, the GraphSage (Graph Sample and Aggregate) model is an inductive learning method based on graphs. The WDR (Wide-deep-recurrent) model is a neural network model used to predict estimated time of arrival (ETA). The STGNN () model refers to a graph neural network model that combines spatial and temporal information. The Graph Transformer model is a framework that combines the Transformer model and the Graph Neural Network (GNN). The GCN (Graph Convolutional Network) model is a deep learning model for processing graph data.

[0151] Illustratively, each neural network model described in the examples of this application includes a basic model and a model that is optimized and improved based on the core idea of ​​the basic model for specific problems or scenarios.

[0152] For example, the GraphSage model includes the basic GraphSage model and the improved model based on the GraphSage model.

[0153] It should be understood that the preset road condition information determination model can be obtained by training the neural network model using a training data set. The specific training method of the model can adopt any feasible training method in the existing technology, which is not elaborated in this application.

[0154] To facilitate understanding, the neural network model built based on GraphSage is used as an example to illustrate the input and output information of the model.

[0155] Exemplarily, the input information of the neural network model built based on GraphSage includes relevant information of multiple vehicle trajectories. For example, the input information may include: the coordinates of the trajectory points of each vehicle trajectory, the links included in the topological driving route corresponding to each vehicle trajectory, the travel direction of each vehicle trajectory, the speed information corresponding to each vehicle trajectory, etc. The output information of the neural network model built based on GraphSage may include: the congestion situation and travel time of the road in front of the intersection in each travel direction, as well as the congestion situation and travel time of the road in the back of the intersection. For example, the congestion situation can be any one of unimpeded, light congestion, congestion and severe congestion; the output information may also include the travel time of the road in front of the intersection in each travel direction.

[0156] It is understandable that for different neural network models, the type of input information may be different, and those skilled in the art may select and adjust it as needed, which is not elaborated in this application.

[0157] S460, the server sends the traffic condition information of the lanes in each direction of travel of the road ahead of the intersection to the terminal device.

[0158] S470, the terminal device displays the traffic condition information of the lanes in each direction of travel on the road ahead of the intersection.

[0159] It should be understood that after receiving the traffic information sent by the server, the terminal device displays the traffic information in the navigation interface.

[0160] For example, when the vehicle in which the terminal device is located is about to arrive at an intersection, the traffic condition information of the lanes in each direction of travel of the road ahead of the intersection will be displayed in the navigation interface.

[0161] Figure 9 is a schematic diagram of the navigation interface of the terminal device in one embodiment of the present application, and a schematic diagram of the cruise interface of the terminal device in one embodiment of the present application.

[0162] As shown in Figure 9 a, the interface schematic diagram displays a map interface 910 of the vehicle's current location, and a navigation route 920 is displayed on the map interface 910. The navigation route 920 is used to highlight the route. As shown in Figure 9 a, in this embodiment, the color of the navigation route 920 is different from the colors of other roads in the map interface, so that the user can easily identify the navigation route 920.

[0163] As shown in Figure a in Figure 9, a first prompt box 930 is also displayed in the interface schematic diagram. A first prompt message is displayed in the first prompt box 930. The first prompt message is used to prompt the driving direction of the vehicle at the upcoming intersection, and the distance between the current position and the upcoming intersection. As shown in Figure a in Figure 9, in this embodiment, the first prompt message prompts the user: the distance between the current position and the intersection is 1.4 kilometers, and the vehicle needs to turn right at the intersection.

[0164] As shown in Figure a of Figure 9 , a second prompt box 940 is also displayed in the interface schematic diagram. A second prompt message is displayed in the second prompt box 940. The second prompt message is used to indicate the direction of traffic of the lanes included in the upcoming intersection, as well as the congestion situation of the intersection in each direction of traffic. As shown in Figure 9 , in this embodiment, the second prompt message includes four arrow icons: a first arrow icon 941, a second arrow icon 942, a third arrow icon 943, and a fourth arrow icon 944. The direction indicated by the arrow in the four arrow icons is the direction of traffic represented by the arrow icon. The first arrow icon 941 represents the left-turn lane, the second arrow icon 942 and the third arrow icon 943 represent the two through lanes, and the fourth arrow icon 944 represents the right-turn lane.

[0165] It should be understood that the color of the arrow icon can be used to indicate the congestion of the lane in the direction of travel corresponding to the arrow icon. For example, green can be used to indicate unobstructed traffic, yellow to indicate mild congestion, red to indicate congestion, and dark red to indicate severe congestion.

[0166] Exemplarily, each arrow icon may include a first part close to the arrow and a second part away from the arrow, wherein the first part is used to indicate whether the vehicle should travel in the lane corresponding to the arrow icon under the current navigation route, and the second part is used to indicate the congestion situation of the lane corresponding to the arrow icon.

[0167] For example, if the first part of the arrow icon is black, it means that the vehicle can travel in the lane corresponding to the arrow icon under the current navigation route; if the first part of the arrow icon is gray, it means that the vehicle should not travel in the lane corresponding to the arrow icon under the current navigation route.

[0168] For example, if the second part of the arrow icon is green, it means that the lane corresponding to the arrow icon is unobstructed; if the second part of the arrow icon is yellow, it means that the lane corresponding to the arrow icon is slightly congested; if the second part of the arrow icon is red, it means that the lane corresponding to the arrow icon is congested; if the second part of the arrow icon is dark red, it means that the lane corresponding to the arrow icon is severely congested.

[0169] In some embodiments, the first arrow icon 941 includes a first part 9411 and a second part 9412, wherein the first part 9411 is displayed in gray, indicating that the vehicle should not travel in the left-turn lane corresponding to the first arrow icon 941 under the current navigation route, and the second part 9412 is displayed in a color corresponding to unobstructed traffic (for example, green), indicating that the left-turn lane corresponding to the first arrow icon 941 is unobstructed.

[0170] As shown in Figure a in Figure 9, the first part of the second arrow icon 942 and the first part of the third arrow icon 943 are both displayed in black, indicating that the vehicle should travel in the lane corresponding to the second arrow icon 942 under the current navigation route, or travel in the lane corresponding to the third arrow icon 943, that is, the vehicle should travel in the straight lane under the current navigation route.

[0171] As shown in Figure a of FIG9 , the second part of the fourth arrow icon 944 is displayed in a color corresponding to congestion (eg, red), indicating that the right-turn lane corresponding to the fourth arrow icon 944 is congested.

[0172] Figure a in Figure 9 shows the display of road condition information of lanes in various directions of traffic on the road ahead of the intersection by the terminal device in the navigation scenario. In the cruising scenario, the method in the embodiment of the present application is also applicable.

[0173] The following is an illustrative description of the application of the present invention in a cruising scenario. It should be understood that a cruising scenario refers to a scenario in which a user opens a map app through a terminal but does not use the map app for navigation. In this case, the terminal device can send positioning information to a server, and the server provides the terminal device with relevant information about the current location. When the user is about to reach an intersection, the terminal device can prompt the user with intersection information.

[0174] For example, when a vehicle on which a terminal device is located approaches an intersection, an enlarged view of the intersection may pop up on the interface of the terminal device, and the road condition information of the lanes in each direction of travel in front of the intersection where the current vehicle is about to arrive may be displayed in the enlarged view of the intersection.

[0175] For example, the server sends traffic information for lanes in each direction of travel on the road ahead of the intersection as additional information to the terminal device. Based on the intersection lane information, the terminal device matches the traffic information for different directions to the intersection according to the lane direction and displays it on the lanes in the magnified intersection image, thus rendering lane-level traffic conditions. In this way, traffic information for lanes in different directions can be displayed to cruising users, making it easier for them to change lanes in advance according to different road conditions.

[0176] Figure b in Figure 9 is a schematic diagram of the cruise interface of the terminal device in one embodiment of the present application.

[0177] As shown in Figure b in Figure 9, a map interface 950 of the vehicle's current location is displayed in the interface schematic diagram, and a third prompt box 960 is displayed on the map interface 950. A third prompt message is displayed in the third prompt box 960. The third prompt message is used to prompt the congestion situation of the upcoming intersection and the distance between the upcoming intersection and the current location. As shown in Figure b in Figure 9, in this embodiment, the third prompt message prompts the user: the distance between the current location and the intersection is 1.4 kilometers, and the right turn lane of the intersection is congested.

[0178] As shown in Figure 9(b), a fourth prompt box 970 is also displayed in the interface schematic diagram. The fourth prompt box 970 displays a fourth prompt message. The fourth prompt message is used to indicate the traffic direction of the lanes included in the upcoming intersection, as well as the congestion situation of the intersection in each traffic direction. As shown in Figure 9(b), in this embodiment, the fourth prompt message includes four arrow icons: a fifth arrow icon 971, a sixth arrow icon 972, a seventh arrow icon 973, and an eighth arrow icon 974. The direction indicated by the arrow in the four arrow icons is the traffic direction represented by the arrow icon. The fifth arrow icon 971 represents the left turn lane, the sixth arrow icon 972 and the seventh arrow icon 973 represent the two through lanes, and the eighth arrow icon 974 represents the right turn lane.

[0179] It should be understood that the color of the arrow icon can be used to indicate the congestion of the lane in the direction of travel corresponding to the arrow icon. For example, green can be used to indicate unobstructed traffic, yellow to indicate mild congestion, red to indicate congestion, and dark red to indicate severe congestion.

[0180] In some embodiments, the fifth arrow icon 971, the sixth arrow icon 972 and the seventh arrow icon 973 are displayed in green, indicating that the left-turn lane and the straight lane are both unobstructed; the eighth arrow icon 974 is displayed in red, indicating that the right-turn lane is congested.

[0181] In some other embodiments, after the server determines the traffic condition information of the lanes in each direction of travel on the road ahead of the intersection in step S450, the server updates the navigation information of the navigation route according to the traffic condition information of the lanes in each direction of travel on the road ahead of the intersection; and sends the updated navigation route to the terminal device; and the terminal device displays the updated navigation route.

[0182] Exemplarily, the traffic condition information for each direction of travel on the road ahead of the intersection includes: the travel time for each direction of travel on the road ahead of the intersection. The server updates the estimated arrival time of the navigation route based on the travel time corresponding to the travel direction of the navigation route on the road ahead of the intersection. The estimated arrival time corresponding to the navigation route is the time it takes for the vehicle to reach the end point of the navigation route from the current position.

[0183] FIG10 is a schematic diagram of a navigation interface displayed when a vehicle passes through an intersection in different directions starting from the same starting point in an embodiment of the present application.

[0184] As shown in Figure 10 a, the interface schematic diagram displays a navigation starting point 1011, a navigation route 1012, a navigation end point 1013 and a traffic condition information prompt box 1014, wherein the navigation end point 1013 is located in the straight direction of the intersection. As shown in Figure 10 a, the traffic condition information prompt box 1014 displays that the travel time when going straight through the intersection is 1 minute.

[0185] As shown in Figure 10 b, the interface schematic diagram displays a navigation starting point 1021, a navigation route 1022, a navigation end point 1023 and a traffic information prompt box 1024, wherein the navigation end point 1023 is located in the right turn direction of the intersection. As shown in Figure 10 b, the travel time when turning right through the intersection is 10 minutes.

[0186] As shown in Figure 10, when the terminal device renders and displays the road conditions of the navigation route, it can differentiate and render according to the road condition information in different traffic directions on the road before the intersection on the navigation route; as shown in Figure a in Figure 10, since the road condition information in the straight direction of the road before the intersection is unobstructed, the navigation route on the road before the intersection can be displayed in the first color corresponding to "unobstructed", for example, the first color can be green; as shown in Figure b in Figure 10, since the road condition information in the right turn direction of the road before the intersection is congested, the navigation route on the road before the intersection can be displayed in the second color corresponding to "congested", for example, the second color can be red.

[0187] To facilitate understanding, the following exemplary description of the lane-level traffic conditions (lane-level traffic conditions may also be referred to as lane-level congestion conditions) and the ETA calculation process in each direction of the road ahead of the intersection in the embodiment of the present application is provided in conjunction with the accompanying drawings.

[0188] Figure 11 is a schematic diagram of the lane-level road conditions and ETA calculation process for each direction of travel on the road ahead of the intersection in the road condition information determination method provided by an embodiment of the present application. As shown in Figure 11, the lanes of the road ahead of the intersection generally have three types of directional attributes: left turn, straight ahead, and right turn. Through the topological driving trajectories of different vehicle trajectories in the same intersection, the vehicle trajectories are classified as left turn, straight ahead, and right turn, and the ETA and road conditions in each direction of travel are calculated separately. The current road-level ETA and road condition calculation technology is relatively mature. The road-level ETA calculation usually does not consider the directional attributes of the lanes that the vehicle trajectory passes through when passing through the road ahead of the intersection. The embodiment of the present application takes the directional attributes of the lanes of the vehicle trajectory passing through the road ahead of the intersection as an independent dimension, and uses the road-level ETA and road condition calculation method to calculate the ETA and road conditions of the lanes of the road ahead of the intersection Link in different directions of travel.

[0189] The following is an exemplary description of the effects that can be achieved by the embodiments of the present application.

[0190] FIG12 is a technical rendering of a method for determining road condition information provided by an embodiment of the present application. As shown in FIG12 , a server (e.g., a cloud server) restores the GPS track points obtained from the terminal device into a vehicle track 1203. Based on the turning relationship of the vehicle track 1203 on the road network topology 1201 of the intersection area 1202, the lane direction attribute (i.e., the direction of travel, such as left turn, straight ahead, or right turn) of the vehicle track 1203 on the road ahead of the intersection area 1202 is obtained. Combined with the dot information of the GPS track points, the lane direction and travel speed of the vehicle track 1203 when passing through the road ahead of the intersection area 1202 are obtained. Based on this information, the road condition and ETA of the lane in a specific direction of the road ahead of the intersection area 1202 are calculated. The road condition information of the lanes in different directions of the road ahead of the intersection area 1202 is aggregated to obtain the lane-level road condition and lane-level ETA of all lanes in different directions on the road ahead of the intersection.

[0191] As shown in FIG12 , the filling pattern of the road condition indication block 1204 can be used to indicate the specific road condition of the lane. In this implementation, the road conditions (i.e., congestion conditions) of different lanes are different, so the filling patterns of the road condition indication blocks 1204 of different lanes are different.

[0192] Of course, the color of the road condition indication block 1204 may also be used to indicate the specific road condition of the lane, which will not be described in detail.

[0193] It should be further explained that the effects of the embodiments of the present application are not limited to the scenario shown in Figure 12. That is, the scenarios implemented by the embodiments of the present application are not limited to intersections. As long as the topological relationship on the map satisfies a one-to-many or many-to-many relationship, that is, when there are multiple connections after a road, the technology can be used to calculate the road conditions and ETAs when traveling to different connections.

[0194] Figure 13 is a schematic diagram of the lane-level ETA determined in the road condition information determination method provided in one embodiment of the present application. Figure 13 illustrates the effect of a route planning navigation scenario. In a route planning navigation scenario, the ETA of the entire navigation route is calculated by summing the ETAs of all links on the navigation route. This solution calculates the ETA of the entire navigation route using the lane-level ETAs corresponding to the travel directions between links on the navigation route.

[0195] When a navigation route passes through intersection area 1302, the route's direction of travel on road network topology 1301 is determined. The lane-level ETA and road conditions of the road preceding the intersection in the corresponding direction are used based on the direction of travel. As shown in Figure 13, the fill pattern of the road condition indicator block 1304 in the lane indicates the lane's road condition. Because the road conditions (i.e., congestion) vary among lanes in this implementation, the fill patterns of the road condition indicator blocks 1304 differ for each lane. For example, lane 1 of intersection area 1302, in the road preceding the intersection, is extremely congested for left turns, with a corresponding travel time of 10 minutes; lane 2, going straight ahead, is unobstructed, with a travel time of 2 minutes; and lane 3, in the road preceding the intersection, is congested, with a travel time of 5 minutes. Therefore, for different navigation routes passing through this intersection in different directions, the total ETA for left turns, straight turns, and right turns at the intersection will accumulate 10 minutes, 2 minutes, and 5 minutes, respectively.

[0196] It can be understood that the road conditions in the above Figures 11 to 13 and the corresponding descriptions refer to congestion conditions.

[0197] It should be understood that the above-mentioned examples, various interfaces of terminal devices, and various user operations in this application are merely illustrative and do not constitute specific limitations on the embodiments of this application. For example, in other embodiments of this application, the icons on the interfaces displayed by the various terminals provided above may include more or fewer icons than those displayed on any of the interfaces shown in the above figures, or may combine certain icons, separate certain icons, or use different icons. This is not a limitation of the embodiments of this application.

[0198] It should also be understood that any one of the above examples or the solution shown in any one of the figures can be an independent solution, or a solution composed of any multiple examples or a solution composed of any multiple figures can also be an independent solution, and this application does not limit this.

[0199] Based on the above application scenario, the system architecture shown in Figure 3a, and the above examples, the following describes the steps of the method for determining road condition information provided by this application. Figure 14 is a schematic flow chart of the method for determining road condition information provided by an embodiment of this application. As shown in Figure 14, the method includes steps S1410 to S1430, wherein:

[0200] S1410 , obtaining a vehicle trajectory set of a target intersection, where the vehicle trajectory set includes vehicle trajectories that pass through the target intersection before a target time.

[0201] It is understandable that the vehicle trajectory set includes multiple vehicle trajectories, which refers to the trajectory of a vehicle that has passed the target intersection at the target time. The multiple vehicle trajectories can be the trajectories formed by multiple different vehicles after passing the target intersection.

[0202] It should be understood that each vehicle trajectory can be determined based on positioning information of the vehicle at multiple different locations of the target intersection when passing through the target intersection.

[0203] Exemplarily, each vehicle trajectory may include a plurality of trajectory points that are continuous in time, and each trajectory point includes position information and time information. The position information may include coordinates in the positioning information, and the time information may include the acquisition time of the positioning information.

[0204] For example, location information may include GPS (Global Positioning System) positioning information uploaded by the user's terminal device, and time information may include the time when the GPS positioning information was collected. Because the positioning accuracy of GPS positioning information is generally a few meters to tens of meters, trajectory points based on GPS positioning information can only be matched to roads, not lanes.

[0205] S1420: Determine a travel direction of the first vehicle trajectory based on the first vehicle trajectory and the road network topology of the target intersection. The travel direction of the first vehicle trajectory is used to indicate the travel direction of a lane located on a road section ahead of the target intersection. The road section ahead of the intersection includes at least two lanes with different travel directions.

[0206] Exemplarily, the road section before the intersection has at least two lanes with different traffic directions. For example, the road section before the intersection may include at least two lanes of a straight lane, a left-turn lane, and a right-turn lane.

[0207] It should be understood that since the road network topology has a direction attribute, the road network topology can be used to assign a direction attribute to the first vehicle trajectory, that is, to determine the travel direction of the lane in which the first vehicle trajectory travels on the road before the target intersection.

[0208] In some embodiments, the travel direction of the first vehicle trajectory can also be obtained by inputting the road network topology of the first vehicle trajectory and the target intersection into a preset travel direction model, where the preset travel direction model can be a pre-trained machine learning model or a neural network model. This application does not enumerate or limit the specific types of machine learning or neural network models.

[0209] S1430, based on the vehicle trajectory set, the road network topology of the target intersection, and the travel direction of each vehicle trajectory in the vehicle trajectory set, determine the traffic condition information of the target intersection at the target time, wherein the traffic condition information of the target intersection at the target time includes: the traffic condition information of the lanes in each travel direction of the road ahead of the intersection at the target time.

[0210] It is understandable that the traffic condition information of the target intersection at the target time may also include: traffic condition information of the rear section of the intersection at the target time.

[0211] In some embodiments, step S1430 includes: determining the speed information of each vehicle trajectory in the vehicle trajectory set based on the vehicle trajectory set and the road network topology of the target intersection, the speed information of each vehicle trajectory including the speed information of the vehicle trajectory passing through the road ahead of the intersection; determining the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection from the vehicle trajectory set based on the traveling directions of the vehicle trajectories in the vehicle trajectory set; determining the road condition information of the lanes in each traveling direction of the road ahead of the intersection at the target time based on the speed information of the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection.

[0212] For example, the traffic condition information may include one or both of travel time and congestion conditions.

[0213] In some embodiments, the road condition information includes the travel time, and the speed information of each vehicle trajectory includes a first average speed, and the first average speed is used to indicate the average speed of the corresponding vehicle trajectory in the road ahead of the intersection; based on the speed information of the vehicle trajectory corresponding to each travel direction of the road ahead of the intersection, the road condition information of the lane in each travel direction of the road ahead of the intersection at the target time is determined, including: based on the first average speed of the vehicle trajectory corresponding to each travel direction of the road ahead of the intersection, the average speed corresponding to each travel direction of the road ahead of the intersection is determined; based on the directed line segments corresponding to the road ahead of the intersection in the road network topology and the average speed corresponding to each travel direction of the road ahead of the intersection, the travel time of the lane in each travel direction of the road ahead of the intersection at the target time.

[0214] In some other embodiments, the road condition information also includes congestion conditions, and the speed information of each vehicle trajectory includes a first average speed, which is used to indicate the average speed of the corresponding vehicle trajectory in the road ahead of the intersection; based on the speed information of the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection, the road condition information of the lanes in each traveling direction of the road ahead of the intersection at the target time is determined, including: based on the first average speed of the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection, the average speed corresponding to each traveling direction of the road ahead of the intersection is determined; based on the average speed corresponding to each traveling direction of the road ahead of the intersection, the congestion conditions of the lanes in each traveling direction of the road ahead of the intersection at the target time are determined.

[0215] In some embodiments, the road ahead of the intersection includes multiple different sub-sections, the road condition information includes the congestion situation of each sub-section, the speed information of each vehicle trajectory includes multiple second average speeds, and each second average speed is used to indicate the average speed of the corresponding vehicle trajectory on a sub-section of the road ahead of the intersection; based on the speed information of the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection, the road condition information of the lane in each traveling direction of the road ahead of the intersection at the target time is determined, including: based on the second average speed of each sub-section of the road ahead of the intersection corresponding to each traveling direction of the road ahead of the intersection, the average speed of each sub-section of the road ahead of the intersection in each traveling direction is determined; based on the average speed of each sub-section of the road ahead of the intersection in each traveling direction, the congestion situation of the lane in each traveling direction of each sub-section of the road ahead of the intersection at the target time is determined.

[0216] In some embodiments, the traffic condition information of the target intersection at the target time also includes traffic condition information of the road behind the target intersection, the traffic condition information includes travel time and congestion, and the road network topology includes multiple directed line segments for representing the road length and the travel direction of the road; step S1430 includes: determining the speed information of each vehicle trajectory in the vehicle trajectory set according to the vehicle trajectory set and the road network topology of the target intersection, the speed information of each vehicle trajectory includes: the speed information of the road before the intersection when the vehicle trajectory passes through the target intersection and the speed information of the road after the intersection when the vehicle trajectory passes through the target intersection; The vehicle trajectories are matched with the road network topology of the target intersection to obtain the topological driving route corresponding to each vehicle trajectory, and the topological driving route corresponding to each vehicle trajectory is used to indicate the route of the vehicle trajectory represented by the directed line segment in the road network topology; the vehicle trajectories in the vehicle trajectory set, the topological driving routes of the vehicle trajectories in the vehicle trajectory set, the speed information of the vehicle trajectories in the vehicle trajectory set, and the travel directions of the vehicle trajectories in the vehicle trajectory set are input into a preset road condition information determination model to obtain the road condition information of the target intersection at the target time, and the preset road condition information determination model is a neural network model.

[0217] Exemplarily, the preset neural network models include: any one of: GraphSAGE neural network model, WDR neural network model, extended STGNN model, Graph Transformer model and GCN model.

[0218] In some embodiments, the road network topology includes multiple directed line segments for representing the road length and the road's travel direction. Based on the vehicle trajectory set and the road network topology of the target intersection, the speed information of each vehicle trajectory in the vehicle trajectory set is determined, including: projecting multiple trajectory points of each vehicle trajectory in the vehicle trajectory set onto the directed line segments of the road network topology to obtain multiple projection points, each trajectory point corresponding to one projection point; determining the speed information of each vehicle trajectory based on the projection point of the trajectory point in each vehicle trajectory on the first directed line segment and the time information of the trajectory point in each vehicle trajectory, the first directed line segment including: a directed line segment in the road network topology corresponding to the road in front of the target intersection and / or a directed line segment in the road network topology corresponding to the road in the rear of the target intersection.

[0219] In some embodiments, the road condition information includes congestion conditions; obtaining the vehicle trajectory set of the target intersection includes: when it is determined that the distance between the location of the terminal device and the target intersection is less than a preset threshold, obtaining the vehicle trajectory set of the target intersection; the method also includes: sending the congestion conditions of the lanes in each direction of travel of the road in front of the intersection at the target time to the terminal device.

[0220] In some embodiments, the road condition information also includes travel time, and the method also includes: obtaining a first travel direction, the first travel direction indicating the travel direction of the lane of the navigation route in the terminal device at the front section of the road at the target intersection; using the travel time of the lane of the first travel direction of the road at the front section of the intersection at the target time, updating the estimated arrival time of the navigation route, and obtaining the estimated arrival time of the navigation route at the target time; sending the estimated arrival time of the navigation route at the target time to the terminal device.

[0221] FIG15 is a flow chart of determining the direction of travel of the first vehicle track in the method for determining road condition information according to an embodiment of the present application. As shown in FIG15 , the process of determining the direction of travel of the first vehicle track may include steps S1421 to S1422, wherein:

[0222] S1421, matching the first vehicle trajectory with the road network topology of the target intersection to obtain a topological driving route corresponding to the first vehicle trajectory, where the topological driving route is used to indicate a route representing the first vehicle trajectory using the road network topology.

[0223] It should be understood that the topological driving route is a route that represents the first vehicle trajectory using the road network topology. Since the road network topology carries the direction information of each road section in the intersection, the topological driving route that represents the first vehicle trajectory using the road network topology will also carry the direction information of each road section at the intersection. Based on the topological driving route with the direction information of each road section at the intersection, it is easy to obtain the travel direction of the first vehicle trajectory. The method is simple and easy to implement.

[0224] For example, the road network topology includes multiple directed line segments for representing the road length and the road's travel direction. The topological driving route may include directed line segments in the road network topology corresponding to the vehicle trajectory. The directed line segments may also be called links.

[0225] In some embodiments, the process of obtaining a topological driving route may include: projecting multiple trajectory points of the first vehicle trajectory onto directed line segments of the road network topology to obtain multiple projection points, with each trajectory point corresponding to a projection point; determining, among the multiple directed line segments of the road network topology, the multiple directed line segments on which the projection points are located as target directed line segments, and the topological driving route corresponding to the first vehicle trajectory including the target directed line segments. By projecting the multiple trajectory points of the first vehicle trajectory onto the road network topology to determine the target directed line segments included in the topological driving route of the first vehicle trajectory, the first vehicle trajectory is represented by the road network topology, and the method is simple and easy to implement.

[0226] In some other embodiments, the process of obtaining a topological driving route may include: connecting multiple trajectory points of the first vehicle trajectory in chronological order to form a first trajectory line; determining the directed line segment combination with the highest correlation with the first trajectory line among multiple directed line segment combinations as the topological driving route corresponding to the first vehicle trajectory; each directed line segment combination includes two directed line segments in the road network topology of the target intersection, and the two directed line segments include: a directed line segment corresponding to the front section of the target intersection, and a directed line segment corresponding to the rear section of the intersection, and different directed line segments exist between different directed line segment combinations.

[0227] Exemplarily, the correlation between the first trajectory line and the directed line segment combination mainly represents the similarity of their trends, which can be obtained through slope analysis, derivative analysis or any other feasible method, which is not elaborated in this application.

[0228] S1422: Determine a travel direction of the first vehicle trajectory according to the topological travel route corresponding to the first vehicle trajectory.

[0229] In some embodiments, determining the direction of travel of the first vehicle trajectory includes determining a vector angle between two reference directed line segments, the reference directed line segment including a directed line segment of the target directed line segment whose node is located at the target intersection; and determining the direction of travel of the first vehicle trajectory based on the vector angle. The specific calculation process is shown in FIG. 7 and the related description and is not further described here.

[0230] In other embodiments, the topological driving route and the lane connectivity relationship of the intersection can also be used to determine the direction of travel of the vehicle trajectory in the lane where the road ahead of the intersection is located. Specific details are shown in FIG6 and the description related to FIG6, which will not be repeated here.

[0231] It should be understood that the above is only to help those skilled in the art better understand the embodiments of the present application, rather than to limit the scope of the embodiments of the present application. Based on the above examples given, those skilled in the art can obviously make various equivalent modifications or changes. For example, some steps in the above process (method embodiment) may not be necessary, or some new steps may be added. Or a combination of any two or any multiple embodiments described above. Such modifications, changes or combined solutions also fall within the scope of the embodiments of the present application.

[0232] It should also be understood that the division of the modes, situations, categories and embodiments in the embodiments of the present application is only for the convenience of description and should not constitute a special limitation. The features of various modes, categories, situations and embodiments can be combined without contradiction.

[0233] It should also be understood that the various numerical numbers involved in the embodiments of this application are only for the convenience of description and are not intended to limit the scope of the embodiments of this application. The order of the sequence numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0234] It should also be understood that the above description of the embodiments of the present application focuses on emphasizing the differences between the various embodiments. The same or similar points that are not mentioned can be referenced with each other. For the sake of brevity, they will not be repeated here.

[0235] In this embodiment, each device (including each terminal device or server) can be divided into functional modules according to the above method embodiment. For example, each function can be divided into functional modules, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. In actual implementation, other division methods can be used.

[0236] It should be noted that the relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module and will not be repeated here.

[0237] The terminal device or server provided in the embodiments of the present application is used to execute the process provided in any of the above embodiments, thereby achieving the same effect as the above implementation method. In the case of an integrated unit, the terminal device may include a processing module, a storage module, and a communication module. Among them, the processing module can be used to control and manage the actions of the terminal device. For example, it can be used to support the terminal device to execute the steps performed by the processing unit. The storage module can be used to support the storage of program code and data, etc. The communication module can be used to support communication between the terminal device and other devices.

[0238] The processing module may be a processor or a controller. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, and so on. The storage module may be a memory. The communication module may specifically be a device that interacts with other terminal devices, such as a radio frequency circuit, a Bluetooth chip, or a Wi-Fi chip.

[0239] The above describes the road condition information determination method, system architecture, and application scenarios of the road condition information determination method provided by the embodiment of the present application in conjunction with Figures 1 to 15. The terminal device provided by the embodiment of the present application is described below.

[0240] An embodiment of the present application provides a terminal device, which is used to execute the steps performed by the terminal device in the road condition information determination method provided in the present application. For example, the terminal device in the embodiment of the present application can be any terminal device in the above-mentioned embodiments. The terminal device in the embodiment of the present application can be a handheld device (such as a mobile phone terminal), various portable notebooks, various tablet computers, vehicle-mounted terminals, wearable devices, etc., and the embodiment of the present application is not limited to this.

[0241] For example, FIG16 shows a schematic diagram of the structure of the terminal device 320. The terminal device 320 may include a processor 1610, an external memory interface 1620, an internal memory 1621, a universal serial bus (USB) interface 1630, a charging management module 1640, a power management module 1641, a battery 1642, an antenna 1, an antenna 2, a mobile communication module 1650, a wireless communication module 1660, an audio module 1670, a speaker 1670A, a receiver 1670B, a microphone 1670C, an earphone interface 1670D, a sensor module 1680, a button 1690, a motor 1691, an indicator 1692, a camera 1693, a display 1694, and a subscriber identification module (SIM) card interface 1695. The sensor module 1680 may include a pressure sensor 1680A, a gyroscope sensor 1680B, an air pressure sensor 1680C, a magnetic sensor 1680D, an acceleration sensor 1680E, a distance sensor 1680F, a proximity light sensor 1680G, a fingerprint sensor 1680H, a temperature sensor 1680J, a touch sensor 1680K, an ambient light sensor 1680L, a bone conduction sensor 1680M, and the like.

[0242] It should be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the terminal device 320. In other embodiments of the present application, the terminal device 320 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0243] The processor 1610 may include one or more processing units. For example, the processor 1610 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0244] The controller may be the nerve center and command center of the terminal device 320. The controller may generate an operation control signal based on the instruction operation code and the timing signal to complete the control of instruction fetching and execution.

[0245] Processor 1610 may also include a memory for storing instructions and data. In some embodiments, the memory in processor 1610 is a cache memory. This memory can store instructions or data that have just been used or are being recycled by processor 1610. If processor 1610 needs to use the instruction or data again, it can directly access the memory. This avoids duplicate accesses, reduces processor 1610 latency, and thus improves system efficiency.

[0246] In some embodiments, the processor 1610 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface.

[0247] USB interface 1630 is an interface that complies with USB standards and specifications, and may be a Mini USB interface, a Micro USB interface, a USB Type-C interface, or the like. USB interface 1630 can be used to connect a charger to charge terminal device 320, or to transfer data between terminal device 320 and peripheral devices. It can also be used to connect headphones to play audio. This interface can also be used to connect to other terminal devices, such as AR devices.

[0248] It is understood that the interface connection relationship between the modules illustrated in the embodiment of the present application is merely an illustrative illustration and does not constitute a structural limitation on the terminal device 320. In other embodiments of the present application, the terminal device 320 may also adopt a different interface connection method from the above embodiment, or a combination of multiple interface connection methods.

[0249] The charging management module 1640 is configured to receive charging input from a charger. The charger can be either a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 1640 can receive charging input from the wired charger via the USB interface 1630. In some wireless charging embodiments, the charging management module 1640 can receive wireless charging input via the wireless charging coil of the terminal device 320. While charging the battery 1642, the charging management module 1640 can also provide power to the terminal device via the power management module 1641.

[0250] The power management module 1641 is used to connect the battery 1642, the charging management module 1640, and the processor 1610. The power management module 1641 receives input from the battery 1642 and / or the charging management module 1640 and provides power to the processor 1610, the internal memory 1621, the external memory, the display 1694, the camera 1693, and the wireless communication module 1660. The power management module 1641 can also be used to monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage, impedance). In other embodiments, the power management module 1641 can also be provided in the processor 1610 or in the same device.

[0251] The wireless communication function of the terminal device 320 can be implemented through antenna 1, antenna 2, mobile communication module 1650, wireless communication module 1660, modem processor and baseband processor.

[0252] Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in terminal device 320 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In other embodiments, the antennas can be used in conjunction with a tuning switch.

[0253] The mobile communication module 1650 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the terminal device 320. The mobile communication module 1650 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 1650 can receive electromagnetic waves from the antenna 1, filter, amplify, and process the received electromagnetic waves, and transmit them to the modem processor for demodulation. The mobile communication module 1650 can also amplify the signal modulated by the modem processor and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 1650 can be set in the processor 1610. In some embodiments, at least some of the functional modules of the mobile communication module 1650 can be set in the same device as at least some of the modules of the processor 1610.

[0254] The modem processor may include a modulator and a demodulator. The modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to the speaker 1670A, the receiver 1670B, etc.) or displays an image or video through the display screen 1694. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 1610 and be provided in the same device as the mobile communication module 1650 or other functional modules.

[0255] The wireless communication module 1660 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the terminal device 320. The wireless communication module 1660 can be one or more devices that integrate at least one communication processing module. The wireless communication module 1660 receives electromagnetic waves via antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 1610. The wireless communication module 1660 can also receive the signal to be sent from the processor 1610, frequency modulate it, amplify it, and convert it into electromagnetic waves for radiation through antenna 2.

[0256] In some embodiments, antenna 1 of terminal device 320 is coupled to mobile communication module 1650, and antenna 2 is coupled to wireless communication module 1660, so that terminal device 320 can communicate with a network and other devices via wireless communication technologies. The wireless communication technologies may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TDSCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (QZSS) and / or a satellite based augmentation system (SBAS).

[0257] For example, the terminal device 320 may send GPS positioning information to a server, and the server may determine the vehicle trajectory based on the GPS positioning information.

[0258] The terminal device 320 implements display functions through a GPU, display screen 1694, and an application processor. The GPU is a microprocessor for image processing that connects the display screen 1694 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 1610 may include one or more GPUs that execute program instructions to generate or modify display information.

[0259] Display screen 1694 is used to display images, videos, and the like. Display screen 1694 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a Micro-oLed, or a quantum dot light-emitting diode (QLED). In some embodiments, terminal device 320 may include one or N display screens 1694, where N is a positive integer greater than one.

[0260] For example, the display screen can be used to display a navigation interface or a cruise interface.

[0261] The terminal device 320 can realize the shooting function through the ISP, camera 1693, video codec, GPU, display screen 1694 and application processor.

[0262] The ISP is used to process data fed back by the camera 1693. For example, when taking a photo, the shutter is opened, and light is transmitted through the lens to the camera's photosensitive element (i.e., image sensor). The light signal is converted into an electrical signal, and the camera's photosensitive element (i.e., image sensor) transmits the electrical signal to the ISP for processing and converting it into an image visible to the naked eye. The ISP can also perform algorithmic optimization on image noise, brightness, and skin color. The ISP can also optimize parameters such as exposure and color temperature of the shooting scene. In some embodiments, the ISP can be set in the camera 1693.

[0263] The camera 1693 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element (i.e., image sensor). The photosensitive element (i.e., image sensor) can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element (i.e., image sensor) converts the optical signal into an electrical signal, and then passes the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV, or other format. In some embodiments, the terminal device 320 may include 1 or N cameras 1693, where N is a positive integer greater than 1.

[0264] The digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the terminal device 320 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0265] Video codecs are used to compress or decompress digital video. Terminal device 320 may support one or more video codecs. This allows terminal device 320 to play or record videos in various encoding formats, such as Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, and MPEG4.

[0266] The NPU is a neural network (NN) computing processor. Drawing on the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it rapidly processes input information and can continuously self-learn. The NPU enables intelligent cognitive applications in the terminal device 320, such as image recognition, face recognition, speech recognition, and text comprehension.

[0267] The external memory interface 1620 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the terminal device 320. The external memory card communicates with the processor 1610 via the external memory interface 1620 to implement data storage functions. For example, files such as music and videos can be stored on the external memory card.

[0268] The internal memory 1621 can be used to store computer executable program codes, which include instructions. The processor 1610 executes various functional applications and data processing of the terminal device 320 by running the instructions stored in the internal memory 1621. The internal memory 1621 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area can store data created during the use of the terminal device 320 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 1621 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0269] The terminal device 320 can implement audio functions such as music playback and recording through the audio module 1670, the speaker 1670A, the receiver 1670B, the microphone 1670C, the headphone jack 1670D, and the application processor.

[0270] The audio module 1670 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 1670 can also be used to encode and decode audio signals. In some embodiments, the audio module 1670 can be provided in the processor 1610, or some functional modules of the audio module 1670 can be provided in the processor 1610.

[0271] The speaker 1670A, also called a "speaker," is used to convert audio electrical signals into sound signals. The terminal device 320 can listen to music or make hands-free calls through the speaker 1670A.

[0272] The receiver 1670B, also called a "handset", is used to convert audio electrical signals into sound signals. When the terminal device 320 receives a call or voice message, the user can hear the voice by placing the receiver 1670B close to the ear.

[0273] Microphone 1670C, also known as "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting their mouth close to the microphone 1670C to input the sound signal into the microphone 1670C. The terminal device 320 can be provided with at least one microphone 1670C. In other embodiments, the terminal device 320 can be provided with two microphones 1670C, which can not only collect sound signals but also realize noise reduction function. In other embodiments, the terminal device 320 can also be provided with three, four or more microphones 1670C to collect sound signals, reduce noise, identify the source of sound, realize directional recording function, etc.

[0274] Exemplarily, the detection of sound by microphone 1670C can be used as an indicator of a car accident. For example, when microphone 1670C in the terminal device detects sounds exceeding a certain sound level around the terminal device, in this case, the vehicle in which the terminal device is located may have suffered a serious collision, resulting in the sound, and therefore it may be determined that a car accident has occurred.

[0275] The headphone jack 1670D is used to connect a wired headphone. The headphone jack 1670D can be a USB interface 1630 or a 3.5mm open mobile terminal platform (OMTP) standard interface or a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0276] Keys 1690 include a power button, a volume button, and the like. Keys 1690 may be mechanical keys or touch-sensitive keys. Terminal device 320 may receive key inputs and generate key signal inputs related to user settings and function control of terminal device 320.

[0277] Motor 1691 can generate vibration prompts. Motor 1691 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. For touch operations acting on different areas of the display screen 1694, motor 1691 can also correspond to different vibration feedback effects. Different application scenarios (for example: time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0278] Indicator 1692 can be an indicator light, which can be used to indicate charging status, power changes, messages, missed calls, notifications, etc.

[0279] The SIM card interface 1695 is used to connect a SIM card. A SIM card can be connected to and disconnected from the terminal device 320 by inserting or removing it from the SIM card interface 1695. The terminal device 320 can support one or N SIM card interfaces, where N is a positive integer greater than one. The SIM card interface 1695 can support Nano SIM cards, Micro SIM cards, SIM cards, and the like. Multiple cards can be inserted into the same SIM card interface 1695 simultaneously. The multiple cards can be of the same or different types. The SIM card interface 1695 is also compatible with different types of SIM cards. The SIM card interface 1695 is also compatible with external memory cards. The terminal device 320 interacts with the network through the SIM card to implement functions such as calls and data communications. In some embodiments, the terminal device 320 uses an eSIM, or embedded SIM card. The eSIM card can be embedded in the terminal device 320 and cannot be separated from the terminal device 320.

[0280] An embodiment of the present application provides an electronic device for executing the steps of the method for determining road condition information provided in the present application.

[0281] The embodiment of the present application also provides a chip system, as shown in Figure 17, which includes at least one processor 1701 and at least one interface circuit 1702. The processor 1701 and the interface circuit 1702 can be interconnected via a line. For example, the interface circuit 1702 can be used to receive signals from other devices (such as the memory of any of the above-mentioned terminal devices). For another example, the interface circuit 1702 can be used to send signals to other devices (such as the processor 1701). Exemplarily, the interface circuit 1702 can read instructions stored in the memory and send the instructions to the processor 1701. When the instructions are executed by the processor 1701, the terminal device can execute the various steps executed by any terminal device in the above-mentioned embodiments (for example, the terminal device can be a handheld device (such as a mobile phone terminal), various portable notebooks, various tablet computers, smart cameras, wearable devices, etc.), or when the instructions are executed by the processor 1701, the server can execute the various steps executed by any server in the above-mentioned embodiments. Of course, the chip system can also include other discrete components, and the embodiment of the present application does not specifically limit this.

[0282] The present application also provides an apparatus, included in a terminal device, that implements the functionality of any of the terminal devices described in any of the above embodiments. This functionality can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes at least one module or unit corresponding to the functionality described above.

[0283] The present application also provides an apparatus, included in an electronic device, that implements the functionality of any of the electronic devices described in any of the above embodiments. The functionality can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes at least one module or unit corresponding to the functionality described above.

[0284] It should also be understood that the division of units in the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, the units in the device can all be implemented in the form of software called through processing elements; or all be implemented in the form of hardware; or some units can be implemented in the form of software called through processing elements, and some units can be implemented in the form of hardware. For example, each unit can be a separately established processing element, or it can be integrated into a certain chip of the device. In addition, it can also be stored in a memory in the form of a program, and called by a certain processing element of the device to execute the function of the unit. Here, the processing element can also be called a processor, which can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each unit above can be implemented by the integrated logic circuit of the hardware in the processor element or in the form of software called through the processing element. In one example, the unit in any of the above devices may be one or more integrated circuits configured to implement the above method, such as one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms. For another example, when the unit in the device can be implemented in the form of a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0285] The present application also provides a computer-readable storage medium for storing computer program code, wherein the computer program includes steps for executing the steps of executing or displaying an interface on a terminal device in any of the embodiments provided above. The readable medium may be a read-only memory (ROM) or a random access memory (RAM), which is not limited in the present application.

[0286] The present application also provides a computer-readable storage medium for storing computer program code, wherein the computer program includes code for executing the steps performed by the server in any of the above embodiments of the present application. The readable medium may be a read-only memory (ROM) or a random access memory (RAM), which is not limited in the present application.

[0287] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device executes the steps of executing or displaying the interface of the terminal device in any of the above embodiments.

[0288] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device executes the steps executed by the server in any of the above embodiments.

[0289] An embodiment of the present application also provides a graphical user interface on a terminal device, wherein the terminal device has a display screen, a camera, a memory, and one or more processors, wherein the one or more processors are used to execute one or more computer programs stored in the memory, and the graphical user interface includes a graphical user interface displayed when the terminal device executes the steps performed by the terminal device in any of the above embodiments.

[0290] Among them, the terminal equipment, electronic equipment, device, computer-readable storage medium, computer program product or chip system provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0291] It is understandable that, in order to realize the above functions, the above-mentioned terminal devices etc. include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present application.

[0292] The embodiment of the present application can divide the functional modules of the above-mentioned terminal device etc. according to the above-mentioned method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0293] Through the description of the above embodiments, those skilled in the art will clearly understand that for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0294] The functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0295] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as flash memory, mobile hard disk, read-only memory, random access memory, magnetic disk or optical disk.

[0296] The above is only a specific embodiment of the present application, but the scope of protection of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for determining road condition information, characterized in that: The method comprises: Obtaining a vehicle trajectory set of a target intersection, the vehicle trajectory set including vehicle trajectories that pass through the target intersection before a target time; Determining a travel direction of the first vehicle trajectory based on the first vehicle trajectory and a road network topology of the target intersection, where the travel direction of the first vehicle trajectory indicates a travel direction of a lane on a road preceding the target intersection where the first vehicle trajectory is located, the road preceding the intersection including at least two lanes with different travel directions, and the first vehicle trajectory being any one of the vehicle trajectory sets; Determine the traffic condition information of the target intersection at the target time based on the vehicle trajectory set, the road network topology of the target intersection, and the travel direction of each vehicle trajectory in the vehicle trajectory set. The traffic condition information of the target intersection at the target time includes: traffic condition information of lanes in each travel direction of the road ahead of the intersection at the target time.

2. The method according to claim 1, characterized in that The determining the travel direction of the first vehicle trajectory according to the first vehicle trajectory and the road network topology of the target intersection includes: Matching the first vehicle trajectory with the road network topology of the target intersection to obtain a topological driving route corresponding to the first vehicle trajectory, wherein the topological driving route is used to indicate a route representing the first vehicle trajectory using the road network topology; A travel direction of the first vehicle trajectory is determined according to a topological travel route corresponding to the first vehicle trajectory.

3. The method according to claim 2, characterized in that The road network topology includes a plurality of directed line segments for representing road lengths and road travel directions. Matching the first vehicle trajectory with the road network topology of the target intersection to obtain a topological driving route corresponding to the first vehicle trajectory includes: Projecting the plurality of trajectory points of the first vehicle trajectory onto the directed line segments of the road network topology to obtain a plurality of projection points, where each trajectory point corresponds to a projection point; Among the multiple directed line segments of the road network topology, the multiple directed line segments where the projection points are located are determined as target directed line segments, and the topological driving route corresponding to the first vehicle trajectory includes the target directed line segments.

4. The method according to claim 3, characterized in that The determining the travel direction of the first vehicle trajectory according to the topological travel route corresponding to the first vehicle trajectory includes: Determining a vector angle between two reference directed line segments, wherein the reference directed line segment includes a directed line segment of the target directed line segment whose node is located at the target intersection; The travel direction of the first vehicle trajectory is determined according to the vector angle.

5. The method according to any one of claims 1 to 4, characterized in that Determining the traffic condition information of the lanes of each traffic direction of the road ahead of the intersection at the target time according to the vehicle trajectory set, the road network topology of the target intersection, and the traffic directions of the vehicle trajectories in the vehicle trajectory set, including: Determining speed information of each vehicle trajectory in the vehicle trajectory set according to the vehicle trajectory set and the road network topology of the target intersection, wherein the speed information of each vehicle trajectory includes speed information of the vehicle trajectory passing through the road preceding the intersection; Determining, from the vehicle trajectory set, a vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection; The road condition information of the lanes of each traveling direction of the road ahead of the intersection at the target time is determined according to the speed information of the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection.

6. The method according to claim 5, characterized in that The road condition information includes travel time, and the speed information of each vehicle track includes a first average speed, where the first average speed is used to indicate the average speed of the corresponding vehicle track on the road ahead of the intersection; The determining, based on the speed information of the vehicle trajectory corresponding to each direction of travel of the road ahead of the intersection, the road condition information of the lane in each direction of travel of the road ahead of the intersection at the target time includes: Determining an average speed corresponding to each direction of travel on the road ahead of the intersection based on a first average speed of vehicle trajectories corresponding to each direction of travel on the road ahead of the intersection; The travel time of the lanes in each travel direction of the road ahead of the intersection at the target time is determined based on the directed line segments corresponding to the road ahead of the intersection in the road network topology and the average speed corresponding to each travel direction of the road ahead of the intersection.

7. The method according to claim 5 or 6, characterized in that The road condition information also includes congestion conditions, and the speed information of each vehicle trajectory includes a first average speed, where the first average speed is used to indicate the average speed of the corresponding vehicle trajectory on the road ahead of the intersection; The determining, based on the speed information of the vehicle trajectory corresponding to each direction of travel of the road ahead of the intersection, the road condition information of the lane in each direction of travel of the road ahead of the intersection at the target time includes: Determining an average speed corresponding to each direction of travel on the road ahead of the intersection based on a first average speed of vehicle trajectories corresponding to each direction of travel on the road ahead of the intersection; The congestion condition of the lanes in each direction of travel of the road ahead of the intersection at the target time is determined according to the average speed corresponding to each direction of travel of the road ahead of the intersection.

8. The method according to claim 5 or 6, characterized in that The road section before the intersection includes a plurality of different sub-sections, the road condition information includes a congestion condition of each sub-section, and the speed information of each vehicle trajectory includes a plurality of second average speeds, each second average speed being used to indicate an average speed of the corresponding vehicle trajectory on a sub-section of the road section before the intersection; The determining, based on the road network topology of the target intersection and the speed information of the vehicle trajectory corresponding to each direction of travel of the road ahead of the intersection, the road condition information of the lane in each direction of travel of the road ahead of the intersection at the target time comprises: Determining an average speed of each sub-section of the road ahead of the intersection in each traveling direction based on the vehicle trajectory corresponding to each traveling direction of the road ahead of the intersection and the second average speed of each sub-section of the road ahead of the intersection; The congestion condition of the lanes in each traveling direction of each sub-section of the road ahead of the intersection at the target time is determined according to the average speed of each sub-section of the road ahead of the intersection in each traveling direction.

9. The method according to any one of claims 1 to 4, characterized in that The traffic condition information of the target intersection at the target time further includes traffic condition information of a road behind the target intersection, the traffic condition information includes travel time and congestion situation, and the road network topology includes a plurality of directed line segments for representing road length and road travel direction; The determining, based on the vehicle trajectory set, the road network topology of the target intersection, and the travel directions of the vehicle trajectories in the vehicle trajectory set, the road condition information of the target intersection at the target time includes: Determining speed information of each vehicle trajectory in the vehicle trajectory set according to the vehicle trajectory set and the road network topology of the target intersection, wherein the speed information of each vehicle trajectory includes: speed information of a road preceding the target intersection when the vehicle trajectory passes through the target intersection, and speed information of a road following the target intersection when the vehicle trajectory passes through the target intersection; Matching each vehicle trajectory with the road network topology of the target intersection to obtain a topological driving route corresponding to each vehicle trajectory, wherein the topological driving route corresponding to each vehicle trajectory is used to indicate a route representing the vehicle trajectory using directed line segments in the road network topology; The vehicle trajectories in the vehicle trajectory set, the topological travel routes of the vehicle trajectories in the vehicle trajectory set, the speed information of the vehicle trajectories in the vehicle trajectory set, and the travel directions of the vehicle trajectories in the vehicle trajectory set are input into a preset road condition information determination model to obtain the road condition information of the target intersection at the target time. The preset road condition information determination model is a neural network model.

10. The method according to claim 9, characterized in that The preset road condition information determination model includes: any one of a GraphSAGE model, a WDR model, a STGNN model, a Graph Transformer model and a GCN model.

11. The method according to any one of claims 5 to 10, characterized in that The road network topology includes a plurality of directed line segments for representing road lengths and travel directions of the roads, and determining speed information of each vehicle trajectory in the vehicle trajectory set based on the vehicle trajectory set and the road network topology of the target intersection includes: Projecting multiple trajectory points of each vehicle trajectory in the vehicle trajectory set onto directed line segments of the road network topology to obtain multiple projection points, where each trajectory point corresponds to a projection point; Speed ​​information of each vehicle trajectory is determined based on a projection point of a trajectory point in each vehicle trajectory on the first directed line segment and time information of the trajectory point in each vehicle trajectory, wherein the first directed line segment includes: a directed line segment in the road network topology corresponding to a road section before the target intersection and / or a directed line segment in the road network topology corresponding to a road section after the target intersection.

12. The method according to any one of claims 1 to 11, characterized in that The traffic condition information includes congestion conditions; The acquiring of the vehicle trajectory set of the target intersection includes: acquiring the vehicle trajectory set of the target intersection when it is determined that the distance between the location of the terminal device and the target intersection is less than a preset threshold; The method further includes: sending the congestion situation of the lanes of each traffic direction of the road in the front section of the intersection at the target time to the terminal device.

13. The method according to claim 12, characterized in that The traffic condition information also includes travel time, and the method further includes: Obtaining a first traveling direction, where the first traveling direction represents the traveling direction of a lane of a road preceding the target intersection of the navigation route in the terminal device; Using the passing time of the lane in the first direction of the road in front of the intersection at the target time, the estimated arrival time of the navigation route is updated to obtain the estimated arrival time of the navigation route at the target time; The estimated arrival time of the navigation route at the target time is sent to the terminal device.

14. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory is used to store instructions, and the processor is used to read the instructions to execute the method according to any one of claims 1 to 13.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 13.

Images