Traffic scene identification method based on Internet of Things technology and related equipment

Abstract

The invention provides a traffic scene identification method and related equipment, which are used for improving the comprehensiveness of road congestion identification and the road traffic efficiency. The method is applied to a cloud platform storing historical traffic information, and edge equipment connected with the cloud platform obtains traffic information of a target road section through acquisition equipment and obtains early warning information. The method comprises the steps that early warning information of a target road section is acquired, wherein the early warning information indicates that the vehicle speed on a first lane of the target road section is smaller than a first vehicle speed threshold value or the fastest vehicle speed on the first lane is smaller than a second vehicle speed threshold value or a congestion point exists in the first lane; and acquiring traffic information indicating the real-time traffic state of the target road section. And according to the traffic information and the historical traffic information, identifying that the target road section is not completely congested, wherein the incomplete congested indicates that the second lane in the target road section has no vehicle in the current time period, or indicates that the vehicle speed on the second lane is greater than a third vehicle speed threshold, or indicates that the time of the vehicle passing through the second lane is less than the time of the vehicle passing through the first lane.

Description

[0001] This application claims the priority of a Chinese patent application with the application number 202311548836.0 and the invention title "Traffic Scene Recognition Method and Related Devices" submitted to the National Intellectual Property Administration on November 20, 2023, the entire content of which is incorporated herein by reference. Technical Field

[0002] This application relates to the field of the Internet of Things, and in particular, to a traffic scene recognition method and related devices based on Internet of Things technology. Background Art

[0003] The growing travel demand places higher requirements on the development of intelligent transportation technology. With the development of the economy, there are more and more vehicles on the road, and the construction speed of traffic facilities gradually fails to meet the surging travel demand. How to improve the traffic efficiency under the existing road conditions has become the focus of attention.

[0004] In related technical solutions, by analyzing the vehicle speeds on the road, it is determined whether the current road is congested. However, the ability to recognize complex traffic scenes is insufficient, especially for traffic road scenes that are not fully congested and still have traffic capacity, resulting in low traffic efficiency and poor road navigation or guidance effects. Summary of the Invention

[0005] This application provides a traffic scene recognition method and related devices based on Internet of Things technology, which is used to improve the comprehensiveness of road congestion recognition, thereby improving the efficiency of road navigation and guidance.

[0006] In a first aspect, this application provides a traffic scene recognition method based on Internet of Things technology. This method is applied to a cloud platform, and the method includes:

[0007] The cloud platform is connected to edge devices, and the edge devices are connected to at least one collection device. This at least one collection device is used to report the traffic information collected from the target road section to the edge device. That is to say, the edge device manages at least one collection device. The collection device collects traffic parameters on the road, processes them to obtain traffic information, and reports it to the edge device. The edge device reports the traffic information to the cloud platform, and the cloud platform stores this traffic information. For the current statistical period, the cloud platform stores historical traffic information, that is, the traffic information before the current statistical period.

[0008] The edge device can also obtain a warning message based on traffic information and report the warning message to the cloud platform. The warning message indicates that vehicles in the first lane of the target road section should slow down, that is, there is congestion in the vehicles in the first lane. Here, the first lane is part or all of the lanes of the target road section. The slowdown of the vehicles in the first lane includes that the speed of the vehicles in the first lane is less than the first speed threshold, or the speed of the fastest vehicle in the first lane is less than the second speed threshold, or there is a congestion point in the first lane. Among them, the first speed threshold can be determined according to the historical average speed of the first lane in the current period, and the second speed threshold can be determined according to the historical fastest speed or historical average speed of the first lane in the current period. The first speed threshold or the second speed threshold can also be determined according to factors affecting vehicle speed such as the speed limit standard of the first lane, and specific details are not limited here. The congestion point includes positions where vehicles are stagnant or the vehicle speed decreases, such as the accident location, temporary parking location, or vehicle queue location, etc., and specific details are not limited here.

[0009] The edge device sends a warning message to the cloud platform, enabling the cloud platform to obtain the warning message. The cloud platform obtains traffic information and historical traffic information, and based on this, determines that the target road section is not completely congested. Among them, the traffic information indicates the real-time traffic status of the target road section, and the traffic information is sent by at least one edge device of the target road section to the cloud platform. Here, the at least one edge device refers to part or all of the edge devices that manage the collection devices of the target road section. The so-called incomplete congestion means that the number of vehicles in the second lane in the same direction as the first lane in the current period is less than the number of vehicles in the first lane. Or, the incomplete congestion indicates that the vehicle speed in the second lane is greater than the third speed threshold, or indicates that the time for the vehicle to pass through the second lane is less than the time for the vehicle to pass through the first lane. Here, the second lane is the lane in the same direction as the first lane in the target road section, and the third speed threshold is greater than or equal to the first speed threshold.

[0010] In this application, in the case of obtaining a warning message for the target road section, by combining the traffic information and historical traffic information of the target road section, it is identified whether the target road section is an incomplete congestion traffic scenario. The congested traffic scenario is further divided into incomplete congestion and complete congestion. That is, the technical solution of this application can identify a new scenario (incomplete congestion), thereby improving the comprehensiveness of road congestion identification. In addition, since the vehicles in the first lane with incomplete congestion can still pass, the efficiency of road navigation and guidance is improved.

[0011] In some alternative implementations of the first aspect, the traffic information includes the real-time average vehicle speed of the first lane and the real-time driving trajectory of the target section. The historical traffic information includes the historical average vehicle speed of the first lane, the historical average vehicle speed of the second lane, and the historical driving trajectory of the target section. Herein, the second lane is part or all of the lanes in the target section that are in the same direction as the first lane. The second lane may or may not be adjacent to the first lane, and specific details are not limited herein. Additionally, the same direction as mentioned in this application means the same driving direction. For example, both the first lane and the second lane are lanes driving from north to south.

[0012] Based on the traffic information and historical traffic information, the cloud platform identifies that the target section is not completely congested, including: determining the vehicle speed difference of the first lane according to the real-time average vehicle speed of the first lane, the historical average vehicle speed of the second lane, and the historical average vehicle speed of the first lane. Determining the detour trajectory coefficient of the target section according to the real-time driving trajectory of the target section and the historical driving trajectory of the target section. Identifying that the target section is not completely congested according to the vehicle speed difference of the first lane and the detour trajectory coefficient of the target section.

[0013] In some alternative implementations of the first aspect, the traffic information includes the real-time number of driving trajectories and the real-time number of lane-changing trajectories of the target section, the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, and the real-time average vehicle speed of the target section. The historical traffic information includes the historical average number of driving trajectories and the historical average number of lane-changing trajectories of the target section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane.

[0014] Based on the traffic information and historical traffic information, the cloud platform identifies that the target section is not completely congested, including: determining the lane-changing parameter of the target section according to the real-time number of driving trajectories and the real-time number of lane-changing trajectories of the target section, and the historical average number of driving trajectories and the historical average number of lane-changing trajectories of the target section. Determining the vehicle speed difference of the target section according to the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, the real-time average vehicle speed of the target section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane. Identifying whether the target section is not completely congested according to the lane-changing parameter of the target section and the vehicle speed difference of the target section.

[0015] In this application, there are various possible implementations for identifying that the target section is not completely congested based on the traffic information and historical traffic information, which enriches the application scenarios of the technical solution of this application and improves the flexibility of the technical solution.

[0016] In some alternative implementations of the first aspect, the cloud platform stores map information of a target road section, and the map information indicates sub-road sections included in the target road section. Then, identifying that the target road section is not completely congested includes identifying that the sub-road sections of the target road section are not completely congested. The specific implementation of identifying the sub-road sections is similar to the foregoing implementation. The difference is that the parameters used to identify that the sub-road sections are not completely congested are for the sub-road sections, and their specific values may be the same as or different from the parameters of the target road section, and are not specifically limited here.

[0017] In this application, it is possible to identify whether the sub-road sections included in the target road section are not completely congested from a finer granularity, further improving the accuracy of congestion identification.

[0018] In some alternative implementations of the first aspect, when the sub-road section of the target road section includes an on-ramp sub-road section and it is identified that the on-ramp sub-road section is not completely congested, the cloud platform can determine the merge point of the on-ramp sub-road section. The cloud platform obtains the first position information and the first driving purpose information of the first vehicle. If the first position information indicates that the first vehicle is currently at a position before the merge point, and the first driving purpose information indicates that the first vehicle is about to enter the on-ramp sub-road section, then the cloud platform sends the first navigation information to the first device, and the first navigation information instructs the first vehicle to enter the on-ramp sub-road section at the merge point. Among them, the on-ramp sub-road section is used to divert the vehicles on the road section before the merge.

[0019] In this application, the cloud platform further differentiates the not-completely-congested scenarios, can identify the on-ramp not-completely-congested scenarios, provide a more efficient navigation solution for the vehicles in the on-ramp scenarios, and improve the traffic efficiency of the road. That is, the cloud platform can identify the incomplete congestion of the on-ramp sub-road section and the merge point of the on-ramp sub-road section. Thus, the first navigation information is determined for the first vehicle that is about to enter the on-ramp sub-road section, instructing the first vehicle to enter the on-ramp sub-road section at the merge point, improving the road traffic efficiency of the on-ramp sub-road section.

[0020] In some alternative implementations of the first aspect, when the target road section includes an on-ramp sub-road section, the cloud platform can also obtain the first position information and the first driving purpose information of the first vehicle. When it is identified that the on-ramp sub-road section is completely congested, if the first position information indicates that the first vehicle is currently at a position before the on-ramp sub-road section, and the first driving purpose information indicates that the first vehicle is about to enter the on-ramp sub-road section. Then the cloud platform sends the second navigation information to the first device, and the second navigation information instructs the first vehicle to enter the queuing lane, and the vehicles in the queuing lane queue up to enter the on-ramp sub-road section.

[0021] In this application, in a scenario where the merging sub-section is completely congested and the first vehicle is about to enter the merging sub-section, the second navigation information determined by the cloud platform for the first vehicle instructs the first vehicle to enter the queuing lane, so as to queue up and enter the merging sub-section, avoiding increasing the degree of road congestion.

[0022] In some alternative implementation manners of the first aspect, the cloud platform may further obtain the second position information and the second driving destination information of the second vehicle. If the second position information indicates that the second vehicle is currently at a position before the straight sub-section, and the second driving destination information indicates that the second vehicle is about to enter the straight sub-section. When the sub-sections of the target road section include a straight sub-section and the straight sub-section is not completely congested, the cloud platform sends the third navigation information to the first device, and the third navigation information instructs the second vehicle to drive in the second lane in the straight sub-section, and the second lane is the lane in the target road section that is in the same direction as the first lane.

[0023] In this application, in a scenario where the straight sub-section is not completely congested and the second vehicle is about to enter the straight sub-section, the third navigation information determined by the cloud platform for the second vehicle instructs the second vehicle to drive in the second lane, improving the road traffic efficiency.

[0024] In some alternative implementation manners of the first aspect, after the cloud platform sends the third navigation information to the first device, it may further send the fourth navigation information to the first device, and the fourth navigation information instructs the second vehicle to drive in the second lane until it reaches a position after the non-completely congested area, and then enter the first lane again.

[0025] In some alternative implementation manners of the first aspect, the first device that receives the navigation information sent by the cloud platform has multiple possibilities, and may be at least one of an on-board unit (OBU), a roadside unit (RSU), or a navigation facility. The first device is used to prompt the vehicle with the navigation information.

[0026] In this application, the first device that receives the navigation information sent by the cloud platform has multiple possibilities, which can flexibly adapt to different scenarios, further enriching the implementation manners of the technical solution of this application and improving the flexibility of the technical solution.

[0027] In a second aspect, this application provides a cloud platform, which is connected to an edge device, and the edge device is connected to at least one collection device. The at least one collection device is used to report the traffic information of the target road section collected to the edge device. The edge device is used to obtain the warning information according to the traffic information, and the cloud platform stores the historical traffic information. The cloud platform includes:

[0028] A transceiver unit for obtaining early warning information, where the early warning information is used to indicate that the vehicle speed on the first lane in the target section is less than the first vehicle speed threshold, or the vehicle speed of the fastest vehicle on the first lane is less than the second vehicle speed threshold, or there is a congestion point on the first lane. Obtain traffic information, where the traffic information is used to indicate the real-time traffic status of the target section.

[0029] A processing unit for identifying whether the target section is not completely congested according to the traffic information and historical traffic information, where not completely congested indicates that the number of vehicles on the second lane in the target section is less than the number of vehicles on the first lane, or indicates that the vehicle speed on the second lane is greater than the third vehicle speed threshold, or indicates that the time for a vehicle to pass through the second lane is less than the time for the vehicle to pass through the first lane, where the second lane and the first lane are in the same direction.

[0030] The cloud platform is used to implement the method shown in the foregoing first aspect or any possible implementation manner of the first aspect.

[0031] In a third aspect, the present application provides a computing device, which includes a processor and a memory. The processor of the computing device is used to execute instructions stored in the memory, so that the computing device implements the method shown in the foregoing first aspect or any possible implementation manner of the first aspect.

[0032] In a fourth aspect, the present application provides a computing device cluster, including at least one computing device, and each computing device includes a processor and a memory; the processor of at least one computing device is used to execute instructions stored in the memory of at least one computing device, so that the computing device cluster implements the method disclosed in the first aspect and any possible implementation manner of the first aspect.

[0033] In a fifth aspect, the present application provides a computer program product containing instructions, which, when executed on a processor, implements the method shown in the foregoing first aspect or any possible implementation manner of the first aspect; or, when the instructions are run by a computer device cluster, enables the computer device cluster to implement the method disclosed in the first aspect and any possible implementation manner of the first aspect.

[0034] In a sixth aspect, the present application provides a computer-readable storage medium, in which computer program instructions are stored, and when the computer program instructions are run on a processor, the method shown in the foregoing first aspect or any possible implementation manner of the first aspect is implemented; or, when the computer program instructions are run by a computer device cluster, enables the computer device cluster to implement the method disclosed in the first aspect and any possible implementation manner of the first aspect.

[0035] The beneficial effects shown in any one of the second to sixth aspects are similar to those in the first aspect or any possible implementation manner of the first aspect, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 FIG. is a schematic diagram of the system architecture provided by an embodiment of the present application;

[0037] Figure 2 FIG. is a schematic flowchart of a method for identifying a traffic scene based on Internet of Things technology provided by an embodiment of the present application;

[0038] Figure 3 FIG. is a schematic diagram of a traffic scene provided by an embodiment of the present application;

[0039] Figure 4 FIG. is another schematic diagram of a traffic scene provided by an embodiment of the present application;

[0040] Figure 5 FIG. is another schematic diagram of a traffic scene provided by an embodiment of the present application;

[0041] Figure 6 FIG. is another schematic diagram of a traffic scene provided by an embodiment of the present application;

[0042] Figure 7 FIG. is a schematic diagram of the structure of a cloud platform provided by an embodiment of the present application;

[0043] Figure 8 FIG. is a schematic diagram of the structure of a computing device provided by an embodiment of the present application;

[0044] Figure 9 FIG. is a schematic diagram of the structure of a computing device cluster provided by an embodiment of the present application;

[0045] Figure 10 FIG. is another schematic diagram of the structure of a computing device cluster provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] An embodiment of the present application provides a method for identifying a traffic scene based on Internet of Things technology and related devices, which are used to improve the comprehensiveness of road congestion identification, thereby improving the efficiency of road navigation and guidance.

[0047] The embodiments of the present application will be described below with reference to the accompanying drawings. Those of ordinary skill in the art will know that with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0048] In the description and claims of this application and the above-mentioned drawings, terms such as "first" and "second" are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing objects with the same attributes when describing the embodiments of this application. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device comprising a series of units does not have to be limited to those units, but may include other units not clearly listed or inherent to these processes, methods, products or devices. Additionally, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item(s) or plural item(s). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c can be single or multiple.

[0049] First, the relevant concepts and proprietary terms involved in this application are described:

[0050] Internet of Things technology (IoT), through information sensing devices, enables any object to be connected to the network. In IoT technology, objects exchange and communicate information through information dissemination media, thereby achieving functions such as intelligent identification, positioning, and management.

[0051] An early warning event indicates that vehicles on the first lane of the target road section are moving slowly, or in other words, there is congestion among the vehicles on the first lane. Here, the first lane is part or all of the lanes of the target road section. The slow movement of vehicles on the first lane includes the vehicle speed on the first lane being less than the first vehicle speed threshold, or the vehicle speed of the fastest vehicle on the first lane being less than the second vehicle speed threshold, or there being a congestion point on the first lane.

[0052] Incomplete congestion means that in the current time period, the number of vehicles on the second lane in the same direction as the first lane in the target road section is less than the number of vehicles on the first lane, or the vehicle speed on the second lane is greater than the third vehicle speed threshold, or the time for vehicles to pass through the second lane is less than the time for vehicles to pass through the first lane.

[0053] Next, please refer to Figure 1 ,Figure 1 Schematic diagram of the system architecture provided by the embodiment of the present application.

[0054] The edge computing platform acquires the data collected by the collection device for the vehicles traveling on the road, analyzes the data, obtains traffic information such as the cross-section flow of the road, the density of the traveling vehicles, the traveling speeds of various types of vehicles, and the traveling trajectories of various types of vehicles, and reports the traffic information to the cloud platform. Among them, the collection device includes devices such as radars and cameras that can collect the traveling data of vehicles.

[0055] In the embodiment of the present application, the edge computing platform also counts the speed and the change trend of the trajectory of the vehicle, determines whether there is a vehicle slowdown event, and reports the event to the cloud platform.

[0056] In the embodiment of the present application, the cloud platform stores historical traffic information. In the case where the edge computing platform reports a slowdown event, in combination with the traffic information and historical traffic information of the road, it is determined whether the road is incompletely congested. The specific process will be described later and will not be elaborated here. In the subsequent description, the so-called edge device is the edge computing platform here.

[0057] After the cloud platform identifies the congestion type of the road, it will issue navigation information to guide the vehicles on the road or about to enter the road. Optionally, the cloud platform can send navigation information to the on-vehicle unit at the vehicle end, or can also send navigation information to the roadside unit, and then the roadside unit sends the navigation information to the on-vehicle unit. Optionally, for the vehicle end without an on-vehicle unit, the cloud platform can perform navigation reminders on the vehicle end through Internet navigation and navigation software. Optionally, the cloud platform can also send navigation information to traffic facilities, and the traffic facilities include facilities such as display screens, drones, and signal lights on the road for prompting the road traffic status. Optionally, the cloud platform can also send navigation information to traffic managers for assisting traffic managers in managing road traffic.

[0058] Next, please refer to Figure 2 , Figure 2 Schematic flowchart of the recognition method for traffic scenarios based on Internet of Things technology provided by the embodiment of the present application, including:

[0059] 201. The cloud platform acquires warning information, and the warning information is used to indicate that the vehicle speed on the first lane in the target section is less than the first vehicle speed threshold, or the vehicle speed of the fastest vehicle on the first lane is less than the second vehicle speed threshold, or there is a congestion point on the first lane.

[0060] The traffic scene recognition method provided by the embodiment of the present application is applied to a cloud platform, and the cloud platform is connected to edge devices. The edge device is connected to at least one collection device and manages the at least one collection device. Specifically, the collection device collects traffic information of the target road section and reports the traffic information to the edge device. Among them, the traffic information is used for the traffic state of the target road section. Optionally, for each collection cycle, the traffic information includes parameters reflecting the traffic state of the target road section, such as the cross-sectional flow, average vehicle speed, driving trajectory, and fastest vehicle speed of the target road section within the cycle.

[0061] The edge device sends the traffic information to the cloud platform, and the cloud platform stores the traffic information for traffic scene recognition. It can be understood that for the current moment or the current statistical cycle, the traffic information stored by the cloud platform before can be called historical traffic information. That is to say, the cloud platform stores historical traffic information, and the historical traffic information is used to indicate the historical traffic state of the target road section. Among them, the historical traffic information includes parameters reflecting the traffic state of the target road section, such as the historical cross-sectional flow, historical average vehicle speed, and historical driving trajectory of the target road section. The historical traffic information plays a reference role in analyzing the congestion state of the current target road section. In addition, it should be noted that optionally, when identifying whether the current target road section is not completely congested, the historical traffic information used by the cloud platform can be the traffic information of the first lane of the target road section in a non-congested state.

[0062] The way for the cloud platform to obtain the warning information of the target road section can be to receive the warning information sent by the edge computing platform. Such as Figure 1As shown in the relevant description, the edge computing platform obtains the data collected by the acquisition device and analyzes these data to determine whether a vehicle slowdown event has occurred on the target road section. There are various possible situations for the vehicles in the first lane to slow down. It could be that there is an accident in the first lane, resulting in the average speed or the maximum speed of the vehicles after the accident location in the first lane being less than the threshold; or there could be a vehicle temporarily parked in the first lane, causing the average speed or the maximum speed of the vehicles in the first lane to be less than the threshold. In addition, it could also be other scenarios that cause the speed of the first lane to decrease, such as low-speed driving scenarios, cutting in, etc., which are not specifically limited here. In other words, the warning information indicates that the speed of the vehicles in the first lane of the target road section is less than the first speed threshold, or the speed of the vehicle with the fastest speed among the vehicles traveling in the first lane of the target road section is less than the second speed threshold, or there is a congestion point in the first lane. Among them, the first speed threshold can be determined according to the historical average speed of the target road section in the current statistical period, and the second speed threshold can be determined according to the historical maximum speed or the historical average speed of the target road section in the current statistical period. Optionally, the first speed threshold and the second speed threshold can also be determined with reference to the historical traffic information and the speed limit standard of the target road section, which are not specifically limited here. The congestion points include locations where vehicles are stagnant or the speed is reduced, such as the accident site, temporary parking areas, or vehicle queuing areas, etc., which are not specifically limited here.

[0063] Exemplarily, assume that the current time is 8 am, during the morning rush hour (such as from 7 am to 9 am). The historical average speed of the first lane of the target road section during the morning rush hour is 50 km / h, and the first threshold can be set to 50% of 50 km / h, which is 25 km / h. If the edge computing platform analyzes the data reported by the acquisition device and determines that the average speed of the target road section at the current time is 10 km / h, then the edge computing platform sends a warning message to the cloud platform.

[0064] It should be noted that the target road section can be a one-way road section or a multi-way road section, and each driving direction can be a single lane or multiple lanes, which are not specifically limited here. The warning information sent by the edge computing platform to the cloud platform indicates a slowdown event at the lane level. The first lane is part or all of the lanes of the target road section.

[0065] In this application, there are various possibilities for the vehicle slowdown in the first lane indicated by the warning information of the edge device, which can remind the cloud platform from multiple angles to judge whether the target road section is not completely congested, further improving the accuracy of congestion recognition, and also facilitating the cloud platform to timely issue navigation information to guide vehicles to pass quickly.

[0066] 202. Obtain traffic information, and the real-time traffic information indicates the real-time traffic status of the target road section.

[0067] A large number of collection devices can be deployed on or around the target road section, and these collection devices may be managed by different edge devices. In order to accurately identify the congestion status of the target road section, the cloud platform will also obtain real-time traffic information sent by at least one edge device of the target road section. The at least one edge device mentioned here can be some or all of the edge devices that manage the collection devices on the target road section.

[0068] Exemplarily, assume that the target road section is a two-way driving road section, and there are two lanes in each driving direction. Cameras and radars are deployed on the driving road sections in each direction. When the warning information reported by the edge computing platform to the cloud platform is for the first lane, the cloud platform can analyze the traffic status of the road section in the same driving direction as the first lane by obtaining the traffic information of the lanes in the same driving direction as the first lane. It is not necessary to obtain the traffic information of the lanes in the other driving direction. Therefore, in this example, the real-time traffic information obtained by the cloud platform is reported by the edge device that manages the collection devices on the road section in the same driving direction as the first lane on the target road section.

[0069] It should be noted that the warning information being for the first lane in the foregoing example means that the warning information indicates that the vehicle speed on the first lane in the target road section is less than the first vehicle speed threshold, or indicates that the vehicle speed of the vehicle with the fastest speed on the first lane is less than the second vehicle speed threshold.

[0070] 203. Based on the traffic information and historical traffic information, identify that the target road section is not completely congested. Not being completely congested indicates that there are no vehicles in the second lane of the target road section during the current period, or indicates that the vehicle speed on the second lane is greater than the third vehicle speed threshold, or indicates that the time for a vehicle to pass through the second lane is less than the time for the vehicle to pass through the first lane.

[0071] Generally speaking, the target road section not being completely congested can be understood as follows: the warning information is for the first lane in the target road section, and the number of vehicles on the second lane in the target road section during the current period is less than the number of vehicles on the first lane, or the vehicle speed on the second lane is greater than the third vehicle speed threshold, or the time for a vehicle to pass through the second lane is less than the time for the vehicle to pass through the first lane.

[0072] Among them, the third vehicle speed threshold is greater than or equal to the first vehicle speed threshold. The third vehicle speed threshold can be determined according to historical traffic information.

[0073] Exemplarily, the historical traffic information stored in the cloud platform includes the average vehicle speed threshold of the second lane in a non-congested scenario within the current statistical period. The third vehicle speed threshold can be less than or equal to this average vehicle speed threshold. For example, assume the current time is 8 am, which is included in the morning rush hour (7 am to 9 am). Then the cloud platform determines from the historical traffic information that the average vehicle speed of vehicles when there are vehicles traveling in the second lane of the target section during the morning rush hour is 40 km / h. The third vehicle speed threshold can be set to be less than or equal to 40 km / h, assume it is 35 km / h. Then, when the warning information is for the first lane and the average vehicle speed of vehicles in the second lane is greater than or equal to 35 km / h, the cloud platform determines that the target section is not completely congested.

[0074] Exemplarily, the historical traffic information stored in the cloud platform includes the slowest vehicle speed on the second lane in a non-congested scenario within the current statistical period. The third vehicle speed threshold can be greater than or equal to this slowest vehicle speed. For example, assume the current time is 8 am, which is included in the morning rush hour (7 am to 9 am). Then the cloud platform determines from the historical traffic information that the slowest vehicle speed is 20 km / h when there are vehicles traveling in the second lane of the target section during the morning rush hour. The third vehicle speed threshold can be set to be greater than or equal to 20 km / h, assume it is 25 km / h. Then, when the warning information is for the first lane and the average vehicle speed of vehicles in the second lane is greater than or equal to 25 km / h, the cloud platform determines that the target section is not completely congested.

[0075] In this application, when obtaining the warning information for the target section, by combining the traffic information and historical traffic information of the target section, it is identified whether the target section is a traffic scenario of incomplete congestion. The congested traffic scenario is further divided into incomplete congestion and complete congestion, that is, the technical solution of this application can identify a new scenario (incomplete congestion), thereby improving the comprehensiveness of road congestion identification. In addition, since vehicles in the second lane of incomplete congestion can still pass, the efficiency of road navigation and guidance is further improved.

[0076] Further, the implementation process of the cloud platform identifying whether the target section is incompletely congested based on traffic information and historical traffic information is described below.

[0077] In some alternative embodiments, the traffic information includes the real-time average vehicle speed of the first lane and the real-time driving trajectory of the target section. The historical traffic information includes the historical average vehicle speed of the first lane, the historical average vehicle speed of the second lane, and the historical driving trajectory of the target section. Herein, the second lane is part or all of the lanes in the target section that are in the same direction as the first lane. The second lane may or may not be adjacent to the first lane, and specific details are not limited herein. Additionally, the same direction as mentioned in this application means the same driving direction. For example, both the first lane and the second lane are lanes driving from north to south.

[0078] In this embodiment, the cloud platform identifies that the target section is not completely congested. Specifically, it determines the vehicle speed difference of the first lane based on the real-time average vehicle speed of the first lane, the historical average vehicle speed of the adjacent lane, and the historical average vehicle speed of the first lane. It determines the detour trajectory coefficient of the target section based on the real-time driving trajectory of the target section and the historical driving trajectory of the target section. It identifies that the target section is not completely congested based on the vehicle speed difference of the first lane and the detour trajectory coefficient of the target section.

[0079] Herein, the vehicle speed difference includes the backward vehicle speed difference and the lateral vehicle speed difference of the current first lane. The backward vehicle speed difference can reflect the slowness of the vehicle speed in the first lane, and the lateral vehicle speed difference reflects the vehicle speed difference between the first lane and the second lane in the same driving direction. The trajectory detour coefficient of the target section can reflect the number of times, frequency, and degree of detour of the vehicles on the first lane.

[0080] In some alternative embodiments, the traffic information includes the real-time number of driving trajectories and the real-time number of lane change trajectories of the target section, the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, and the real-time average vehicle speed of the target section. The historical traffic information includes the historical average number of driving trajectories and the historical average number of lane change trajectories of the target section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane.

[0081] In this embodiment, the cloud platform identifies whether the target section is not completely congested. Specifically, it determines the lane change parameter of the target section based on the real-time number of driving trajectories and the real-time number of lane change trajectories of the target section, and the historical average number of driving trajectories and the historical average number of lane change trajectories of the target section. It determines the vehicle speed difference of the target section based on the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, the real-time average vehicle speed of the target section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane. It identifies whether the target section is not completely congested based on the lane change parameter of the target section and the vehicle speed difference of the target section.

[0082] Exemplarily, the cloud platform can identify whether the target section is not completely congested based on the following formula:

[0083]

[0084] Among them, T c represents the number of real-time lane-changing trajectories of the target road section, T s represents the number of real-time driving trajectories of the target road section, T hc represents the historical average number of lane-changing trajectories of the target road section, T hs represents the historical average number of driving trajectories of the target road section, v l represents the real-time average vehicle speed of the first lane, v lc represents the real-time average vehicle speed of the second lane, v represents the real-time average vehicle speed of the target road section, v h represents the historical average vehicle speed of the target road section. The constant c represents the threshold for reaching incomplete congestion.

[0085] In addition, α represents the vehicle lane-changing coefficient, which is used to control the proportion of lane-changing behavior in the recognition process. Its value can be determined according to the needs of actual applications and is not specifically limited here. For example, in the scenario of multi-lane roads, the lane-changing behavior increases in congested scenarios, and the value of α can be set to be greater than that in the single-lane scenario.

[0086] β represents the vehicle speed difference coefficient, which is used to define the proportion of the vehicle speed difference between the second lane in the recognition process. Its value can be determined according to the needs of actual applications and is not specifically limited here.

[0087] It should be noted that to identify incomplete congestion, a certain degree of congestion needs to be reached first In a certain congestion situation, the number of lane changes is proportional to the possibility of incomplete congestion In a certain congestion situation, the average vehicle speed difference between lanes is proportional to the possibility of incomplete congestion

[0088] It should also be noted that the statistical period corresponding to the historical traffic information of the target road section is the same as, or includes, the statistical period corresponding to the traffic information of the target road section. Exemplarily, the statistical period can be divided into time periods by hour or by day, and different time periods of weekdays or holidays can also be distinguished, which is not specifically limited here. For example, 24 hours of a day can be divided into a night time period and a day time period, and the day time period can be further divided into several peak time periods and non-peak time periods. The duration of each peak time period can be the same or different. For example, it is determined that 7:00 to 9:00 in the morning on weekdays is the morning peak time period, 11:00 to 13:00 at noon is the noon peak time period, and 5:00 to 8:00 in the afternoon is the evening peak time period.

[0089] Assume that the time when the vehicle on the first lane indicated by the warning information is slow is 12:00 noon on weekdays. Then, the cloud platform can obtain the traffic information of the time period from 11:00 to 13:00 as historical traffic information from the database for identifying the congestion type of the target road section.

[0090] Based on the foregoing description, it can be seen that in the present application, there are various possible ways to identify whether a target road section is not completely congested based on traffic information and historical traffic information, which enriches the application scenarios of the technical solution of the present application and improves the flexibility of the technical solution.

[0091] In some alternative embodiments, the cloud platform may also store map information of the target road section, and the map information is used to indicate the sub-road sections included in the target road section. Then, the cloud platform can identify that the sub-road sections included in the target road section are not completely congested. Specifically, the cloud platform can identify whether each sub-road section is not completely congested according to the traffic information of each sub-road section and the historical traffic information of each sub-road section. That is to say, in the present application, the congestion state of the road can be identified from a finer-grained sub-road section, further improving the accuracy of congestion identification.

[0092] Among them, the map information of the target road section may further include lane information of the target road section, and may also include facility information of the target road section, and the facility information is used to indicate fixed facilities on the target road section, such as green belts, sidewalk areas, etc.

[0093] There are various possible bases for the cloud platform to divide sub-road sections, which can be determined according to actual application needs based on factors such as road section type, road section length, and infrastructure included in the road section that may affect the traffic state of the road. Specifically, it is not limited here.

[0094] Exemplarily, assume that the target road section is a straight road section without forks. In this scenario, the cloud platform can divide the sub-road sections based on the road section length, and divide the target road section into several sub-road sections with the same length for each sub-road section.

[0095] Exemplarily, assume that the target road section includes a bend. Then the cloud platform can divide the sub-road sections based on the road section type, into a sub-road section before the bend, a sub-road section of the bend, and a sub-road section after the bend. Further, if the length of the sub-road section before the bend or the sub-road section after the bend is long, the cloud platform can further divide the sub-road section before the bend or the sub-road section after the bend into multiple sub-road sections based on the road section length.

[0096] Exemplarily, assume that there is a tunnel on the target road section. Then the cloud platform can divide the target road section into a tunnel sub-road section and a non-tunnel sub-road section based on the infrastructure included in the road section. Further, if the length of the non-tunnel sub-road section is long, the cloud platform can further divide the non-tunnel sub-road section into multiple sub-road sections based on the road section length.

[0097] In the embodiments of the present application, the warning information sent by the edge device to the cloud platform indicates the area where vehicles on the first lane are moving slowly. The cloud platform determines the sub-sections corresponding to the area where vehicles on the first lane of the target section are moving slowly according to the map information of the target section. Then, based on the traffic information and historical traffic information of the sub-section, it identifies whether the sub-section is not completely congested.

[0098] Among them, the number of sub-sections corresponding to the area where vehicles on the first lane are moving slowly can be one or multiple, which is determined according to the actual application scenario and is not specifically limited here.

[0099] In the embodiments of the present application, there are various possibilities for the specific process of identifying whether each sub-section is not completely congested. Generally speaking, the cloud platform obtains the warning information for the first lane in the target section, and for each sub-section included in the target section, determines whether the sub-section is not completely congested according to the traffic information of the sub-section and the historical traffic information of the sub-section. Its specific implementation process is similar to that of determining whether the target section is not completely congested based on the traffic information of the target section and the historical traffic information of the target section. The difference is that the parameters used in the identification process are for the sub-section rather than the target section, as shown in the previous text and will not be elaborated here.

[0100] In the present application, the target section can be divided into sub-sections, and whether each sub-section of the target section is not completely congested can be identified from a finer granularity, further improving the accuracy of congestion identification. In addition, when identifying whether a sub-section is not completely congested, there are also various solutions, enriching the implementation methods and application scenarios of the technical solutions of the present application.

[0101] The incomplete congestion scenarios of different types of sub-sections will be described below. Please refer to Figures 3 to 6 , Figures 3 to 6 Both are schematic diagrams of traffic scenarios provided by the embodiments of the present application. In Figures 3 to 6 the shown implementation, lane ① represents the first lane. In Figures 3 to 6 the shown embodiment, the black rectangular frame represents the vehicles that have traveled on the target section, and the white rectangular frame represents the first vehicle or the second vehicle.

[0102] In some alternative implementation manners, the cloud platform stores the map information of the target section. When the map information indicates that the target section includes an on-ramp sub-section, the cloud platform identifies whether the on-ramp sub-section is not completely congested.

[0103] Among them, the on-ramp sub-section is used to divert the vehicles on the section before the on-ramp. Exemplarily, such as Figure 3As shown in the figure, vehicles on the target road section can enter the merging sub-section through Lane 1. After entering the merging sub-section, the driving direction of the vehicles changes from northbound to eastbound. If the vehicles still drive in Lane 2 on the merging section, the driving direction of this part of the vehicles remains unchanged, thus realizing vehicle diversion.

[0104] If the cloud platform identifies that the merging sub-section is not completely congested, indicating that the merging sub-section can be entered through detours and other directions, then the cloud platform can further determine the mergeable points of the merging sub-section, and the mergeable points indicate the positions where vehicles enter the merging sub-section.

[0105] The cloud platform obtains the first position information and the first driving destination information of the first vehicle. If the first position information indicates that the first vehicle is at a position before the merging sub-section, and the first driving destination information indicates that the first vehicle is about to enter the merging sub-section. Then the cloud platform sends the first navigation information to the first device, and the first navigation information is used to instruct the first vehicle to enter the merging sub-section at the mergeable point.

[0106] Among them, the first device has various possibilities and can be an on-vehicle unit, a roadside unit, a navigation facility, or other devices installed with navigation software and capable of prompting navigation information to the first vehicle. Among them, the navigation facilities include signal lights, electronic screens, drones, etc.

[0107] Exemplarily, as Figure 3 shown, the northbound section of the target road section is a two-lane road, including Lane 1 and Lane 2. At the current time period, there are 3 vehicles parked on Lane 1, and there are no vehicles driving on Lane 2 and Lane 3. The cloud platform identifies that the merging sub-section is not completely congested.

[0108] The first vehicle is at a position before the merging sub-section on Lane 1 at the current moment, and the first driving destination information indicates that the first vehicle is going to enter the merging sub-section. Then the first navigation information sent by the cloud platform can instruct the first vehicle to change lanes from Lane 1 to Lane 2 before the merging sub-section, and then enter the merging sub-section near the mergeable point A.

[0109] Optionally, if there are vehicles driving on Lane 1 in the lanes after the merging sub-section, in order to accelerate the driving of the first vehicle, the first navigation information can also instruct the first vehicle to change lanes from Lane 1 to Lane 3 when exiting the merging section.

[0110] Optionally, if there are no vehicles driving on Lane 1 in the lanes after the merging sub-section, then the first vehicle can continue to drive on Lane 1 or change lanes from Lane 1 to Lane 3, and no specific limitation is made here.

[0111] In this application, the cloud platform further differentiates the incomplete congestion scenario, can identify the merging incomplete congestion scenario, provide a more efficient navigation solution for the vehicles in the merging scenario, and improve the traffic efficiency of the road. That is, the cloud platform can identify the incomplete congestion of the merging sub-section and the mergeable points of the merging sub-section. Thereby, the first navigation information is determined for the first vehicle about to enter the merging sub-section, instructing the first vehicle to enter the merging sub-section at the mergeable point, which improves the road traffic efficiency of the merging sub-section.

[0112] In some alternative embodiments, the merging sub-section of the target section may be completely congested. At this time, the cloud platform sends the second navigation information to the first device, and the second navigation information is used to instruct the first vehicle to enter the queuing lane, and the vehicles in the queuing lane queue up to enter the merging sub-section. The so-called complete congestion of the merging sub-section means that the vehicle speed in the merging sub-section is less than the fourth vehicle speed threshold, and the merging sub-section cannot be entered through detours or the like, or taking a detour will cause an increase in the road congestion level. Among them, the fourth vehicle speed threshold is less than the first vehicle speed threshold.

[0113] Exemplarily, as Figure 4 shown, before the first vehicle, lane ① is completely occupied, that is, on the target section, the vehicles queue up to enter the merging sub-section. If the first vehicle enters lane ② and the first vehicle is about to enter the merging sub-section, it will cause cutting in line and increase the congestion level of the merging sub-section. Therefore, the second navigation information instructs the first vehicle to enter lane ① (that is, the queuing lane) and queue up to enter the merging sub-section, thereby avoiding an increase in the congestion level of the merging sub-section.

[0114] In this application, in the scenario where the merging sub-section is completely congested and the first vehicle is about to enter the merging sub-section, the second navigation information determined by the cloud platform for the first vehicle instructs the first vehicle to enter the queuing lane, and thus queue up to enter the merging sub-section, avoiding an increase in the road congestion level.

[0115] In some alternative embodiments, the cloud platform stores the map information of the target section. In the case where the map information indicates that the target section includes a straight sub-section, the cloud platform identifies whether the straight sub-section is incompletely congested. The so-called straight sub-section refers to a section without vehicle diversion. Throughout the straight sub-section, the driving direction of the vehicle can change (for example, enter a curve), or it can remain unchanged, and specific details are not limited here.

[0116] If the cloud platform identifies that the straight sub-section is not completely congested, it means that for the vehicles before the vehicle slowdown area, they can avoid it by taking a detour or other means. Among them, the vehicle slowdown area refers to the area where the vehicles in the first lane indicated by the warning information have a speed less than the first speed threshold, or the area where the fastest vehicle speed in the first lane indicated by the warning information is less than the second speed threshold, or the area including the congestion point in the first lane.

[0117] Exemplarily, in Figure 5 the illustrated embodiment, the vehicle slowdown area may be the area of three temporarily parked vehicles represented by the black rectangular frame. The congestion point may be the position of the leading vehicle among these three vehicles (such as Figure 5 point B shown). In Figure 6 the illustrated embodiment, the vehicle slowdown area may be the area of two collided vehicles represented by the black rectangular frame, and the area of two vehicles that cannot go straight due to the collision, represented by the gray rectangular frame behind these two vehicles. The congestion point may be the position of the vehicle collision (such as Figure 6 point C shown).

[0118] In addition, in Figure 5 or Figure 6 the illustrated embodiments, the target section is a two-lane road, and the warning information is for the first lane (lane ①) as an example. In this example, there are vehicles driving on the second lane (lane ②). That is to say, in this embodiment, the target section is not completely congested means that there are vehicles driving on the second lane in the same direction as the first lane in the target section, and the speed of the vehicles on the second lane is greater than the third speed threshold, or the time for the vehicles to pass through the second lane is less than the time for the vehicles to pass through the first lane.

[0119] The cloud platform obtains the second position information and the second driving purpose information of the second vehicle. The second position information indicates the position of the second vehicle, and the second driving purpose information indicates the driving purpose of the second vehicle.

[0120] If the straight sub-section is not completely congested, and the second position information indicates a position before the straight sub-section, and the second driving purpose information indicates that the second vehicle is about to drive into a position after the straight sub-section, then the cloud platform sends the third navigation information to the first device. The third navigation information indicates that the second vehicle drives through the second lane in the straight sub-section, so that the second vehicle avoids the vehicle slowdown area. The second lane is the lane in the straight sub-section that is in the same direction as the first lane, and the speed of the second lane is greater than the speed of the first lane, or the time to pass through the second lane is less than the time to pass through the first lane.

[0121] Exemplarily, in Figure 5 and Figure 6 the illustrated embodiments, the straight sub-section of the target section is a two-lane road, and the gray rectangular frame represents the vehicles that have already driven on the target lane.

[0122] As Figure 5 and Figure 6 shown, the second vehicle represented by the white rectangular box is located at the position before the straight sub-section on Lane 1 at the current moment, and the second driving destination information indicates that the second vehicle is to drive into the position after the straight sub-section. Then, the third navigation information sent by the cloud platform can instruct the second vehicle to change lanes from Lane 1 to Lane 2 before the straight sub-section to avoid congestion.

[0123] In this application, in the scenario where the straight sub-section is not completely congested and the second vehicle is to drive into the position after the straight sub-section, the third navigation information determined by the cloud platform for the second vehicle instructs the second vehicle to drive on the second lane in the straight sub-lane to avoid the slow-moving vehicle area, thereby improving the road traffic efficiency.

[0124] In some optional implementation manners, after the cloud platform sends the third navigation information to the first device, it can also send the fourth navigation information to the first device. The fourth navigation information instructs the second vehicle to drive into the first lane again after driving to the position after the slow-moving vehicle area.

[0125] Exemplarily, in Figure 5 the shown embodiment, the second vehicle changes lanes from Lane 1 to Lane 2 according to the instruction of the third navigation information. After driving to the position after point B on Lane 2, it can change lanes from Lane 2 to Lane 1 based on the instruction of the fourth navigation information.

[0126] It should be noted that in the foregoing implementation manners, the vehicle needs to drive into the target section. However, in actual applications, there are vehicles that may not need to drive into the target section. That is to say, the cloud platform can determine whether the driving path of the vehicle must pass through the target section by obtaining the position information and driving destination information of the vehicle. If it can bypass the target section and the target section is congested, then the cloud platform can preferentially send the navigation information that does not pass through the target section to the first device, or set a higher priority for the navigation information that does not pass through the target section among the multiple navigation information sent to the first device.

[0127] In some optional implementation manners, the cloud platform can identify that the target section is completely congested, that is, all lanes in the same direction as the first lane on the target section are congested. In this case, the cloud platform can send a detour message to the first device to guide the vehicle to detour before driving into the target section. The cloud platform can also send a prompt message to the traffic manager to prompt the traffic manager to manage the vehicles on the target section.

[0128] The relevant devices provided by the embodiments of the present application will be described below. Please refer to Figure 7 , Figure 7A schematic structural diagram of the cloud platform provided by an embodiment of the present application.

[0129] In an embodiment of the present application, the cloud platform is connected to edge devices, and the edge devices are connected to at least one collection device. The at least one collection device is used to report the traffic information of the target road section collected to the edge device, and the edge device is used to obtain early warning information according to the traffic information. The cloud platform 700 stores the historical traffic information of the target road section. As Figure 7 shown, the cloud platform 700 includes a transceiver unit 701 and a processing unit 702.

[0130] In some optional embodiments, the transceiver unit 701 is used to obtain early warning information, where the early warning information is used to indicate that the vehicle speed on the first lane in the target road section is less than the first vehicle speed threshold, or the vehicle speed of the vehicle with the fastest speed on the first lane is less than the second vehicle speed threshold, or there is a congestion point on the first lane. Obtain traffic information, where the traffic information is used to indicate the real-time traffic state of the target road section.

[0131] The processing unit 702 is used to identify that the target road section is not completely congested according to the traffic information and the historical traffic information. The incomplete congestion indicates that the number of vehicles on the second lane in the target road section is less than the number of vehicles on the first lane, or indicates that the vehicle speed on the second lane is greater than the third vehicle speed threshold, or indicates that the time for the vehicle to pass through the second lane is less than the time for the vehicle to pass through the first lane, where the second lane and the first lane are in the same direction.

[0132] In some optional embodiments, the traffic information includes the real-time average vehicle speed of the first lane and the real-time driving trajectory of the target road section. The historical traffic information includes the historical average vehicle speed of the first lane, the historical average vehicle speed of the second lane, and the historical driving trajectory of the target road section.

[0133] The processing unit 702 is specifically used to: determine the vehicle speed difference of the first lane according to the real-time average vehicle speed of the first lane, the historical average vehicle speed of the second lane, and the historical average vehicle speed of the first lane. Determine the detour trajectory coefficient of the target road section according to the real-time driving trajectory of the target road section and the historical driving trajectory of the target road section. Identify that the target road section is not completely congested according to the vehicle speed difference of the first lane and the detour trajectory coefficient of the target road section.

[0134] In some optional embodiments, the traffic information includes the real-time number of driving trajectories and the real-time number of lane change trajectories of the target road section, the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, and the real-time average vehicle speed of the target road section. The historical traffic information includes the historical average number of driving trajectories and the historical average number of lane change trajectories of the target road section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane.

[0135] The processing unit 702 is specifically configured to: determine the lane-changing parameter of the target road section according to the real-time number of driving trajectories and the real-time number of lane-changing trajectories of the target road section, and the historical average number of driving trajectories and the historical average number of lane-changing trajectories of the target road section. Determine the vehicle speed difference of the target road section according to the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, the real-time average vehicle speed of the target road section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane. Identify whether the target road section is not completely congested according to the lane-changing parameter of the target road section and the vehicle speed difference of the target road section.

[0136] In some alternative embodiments, the cloud platform stores the map information of the target road section, and the map information indicates the sub-road sections included in the target road section. The processing unit 702 is specifically configured to identify that the sub-road sections of the target road section are not completely congested.

[0137] In some alternative embodiments, the sub-road sections of the target road section include merging sub-road sections, and the merging sub-road sections are used to divert the vehicles on the road section before merging.

[0138] The processing unit is further configured to determine the mergeable points of the merging sub-road section if the merging sub-road section is not completely congested.

[0139] The transceiver unit 701 is further configured to: obtain the first position information and the first driving destination information of the first vehicle. If the first position information indicates that the first vehicle is at a position before the mergeable point, and the first driving destination information indicates that the first vehicle is about to drive into the merging sub-road section, then send the first navigation information to the first device, and the first navigation information is used to instruct the first vehicle to drive into the merging sub-road section at the mergeable point.

[0140] In some alternative embodiments, the sub-road sections of the target road section include merging sub-road sections.

[0141] The transceiver unit 701 is further configured to: obtain the first position information and the first driving destination information of the first vehicle. If the first position information indicates that the first vehicle is at a position before the mergeable point, and the first driving destination information indicates that the first vehicle is about to drive into the merging road section, and the merging sub-road section is completely congested, then send the second navigation information to the first device, and the second navigation information is used to instruct the first vehicle to drive into the queuing lane, and the vehicles in the queuing lane queue up to drive into the merging road section.

[0142] In some alternative embodiments, the sub-road sections stored in the cloud platform for the target road section include straight sub-road sections.

[0143] The transceiver unit 701 is further configured to: obtain the second position information and the second driving destination information of the second vehicle. If the straight sub-section is not completely congested, and the second position information indicates that the second vehicle is at a position before the straight sub-section, and the second driving destination information indicates that the second vehicle is about to enter the straight sub-section, then send third navigation information to the first device, where the third navigation information indicates that the second vehicle travels in the second lane in the straight sub-section.

[0144] Among them, both the transceiver unit 701 and the processing unit 702 can be implemented by software or by hardware. Exemplarily, next, taking the processing unit 702 as an example, the implementation manner of the processing unit 702 will be introduced. Similarly, the implementation manner of the transceiver unit 701 can refer to the implementation manner of the processing unit 702.

[0145] As an example of a software functional unit, the processing unit 702 may include code running on a computing instance. Among them, the computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the above computing instance may be one or more. For example, the processing unit 702 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers for running the code may be distributed in the same region or in different regions. Further, the multiple hosts / virtual machines / containers for running the code may be distributed in the same availability zone (AZ), or in different AZs, and each AZ includes one data center or multiple geographically proximate data centers. Among them, generally one region may include multiple AZs.

[0146] Similarly, the multiple hosts / virtual machines / containers for running the code may be distributed in the same virtual private cloud (VPC), or in multiple VPCs. Among them, generally one VPC is set within one region. For cross-region communication between two VPCs within the same region and between VPCs in different regions, a communication gateway needs to be set in each VPC, and the interconnection between VPCs is realized through the communication gateway.

[0147] As an example of a hardware functional unit, the processing unit 702 may include at least one computing device, such as a server. Alternatively, the processing unit 702 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). Among them, the above PLD may be implemented by a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0148] The multiple computing devices included in the processing unit 702 may be distributed in the same region or in different regions. The multiple computing devices included in the processing unit 702 may be distributed in the same availability zone (AZ) or in different AZs. Similarly, the multiple computing devices included in the processing unit 702 may be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Among them, the multiple computing devices may be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0149] It should be noted that different steps in the traffic scene recognition method are respectively implemented by the transceiver unit 701 and the processing unit 702 to implement all functions of the data cloud platform 700. The cloud platform 700 is used for the operations performed by the cloud platform in the foregoing Figures 1 to 7 illustrated embodiments to implement the traffic scene recognition method provided in the embodiments of the present application, which will not be elaborated here.

[0150] Please refer to Figure 8 , Figure 8 which is a schematic structural diagram of a computing device provided in an embodiment of the present application. The computing device 800 includes a processor 801, a communication interface 802, a bus 803, and a memory 804. Among them, the processor 801, the communication interface 802, and the memory 804 communicate through the bus 803. In practical applications, communication may also be achieved by other means such as wireless transmission, and specific details are not limited here.

[0151] The computing device 800 may be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computing device 800.

[0152] The processor 801 may include any one or more of processors such as a central processing unit (CPU), a graphics processing unit (GPU), a micro processor (MP), or a digital signal processor (DSP).

[0153] The communication interface 802 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 800 and other devices or communication networks.

[0154] The bus 803 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 8 only one line is used to represent it, but it does not mean that there is only one bus or one type of bus. The bus 803 may include a path for transmitting information between various components of the computing device 800 (for example, the memory 804, the processor 801, and the communication interface 802).

[0155] The memory 804 may include volatile memory, such as random access memory (RAM). The memory 804 may also include non-volatile memory, such as read-only memory (ROM), flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0156] The memory 804 stores executable program code, and the processor 801 executes the executable program code to respectively implement the functions of the aforementioned transceiver unit 701 and processing unit 702, thereby implementing the traffic scene recognition method. Instructions for executing the traffic scene recognition method are stored on the memory 804.

[0157] The embodiments of the present application also provide a computing device cluster, which includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some alternative embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.

[0158] Please refer to Figure 9 and Figure 10 , Figure 9 and Figure 10 are all schematic structural diagrams of the computing device cluster provided by the embodiments of the present application.

[0159] As Figure 10 shown, the computing device cluster includes at least one computing device 800. Instructions for executing the traffic scene recognition method provided by the embodiments of the present application can be stored in the memory 804 of one or more of the computing devices 800 in the computing device cluster.

[0160] In some possible embodiments, partial instructions for executing the traffic scene recognition method can also be stored separately in the memory 804 of one or more of the computing devices 800 in the computing device cluster. In other words, the combination of one or more computing devices 804 can jointly execute the instructions for executing the traffic scene recognition method.

[0161] It should be noted that the memories 804 of different computing devices 800 in the computing device cluster can store different instructions, which are respectively used to execute some functions of the cloud platform. That is, the instructions stored in the memories 804 of different computing devices 800 can implement the functions of one or more units in the transceiver unit 701 and the processing unit 702.

[0162] In some possible implementation manners, one or more computing devices in the computing device cluster can be connected through a network. Among them, the network can be a wide area network or a local area network, etc. Figure 10 shows a possible implementation manner. As Figure 10 shown, two computing devices 800A and 800B are connected through a network. Specifically, they are connected to the network through the communication interfaces in each computing device. In this type of possible implementation manner, instructions for executing the function of the transceiver unit 701 are stored in the memory 804 of the computing device 800A. At the same time, instructions for executing the function of the processing unit 702 are stored in the memory 804 of the computing device 800B.

[0163] Figure 10The connection mode between the computing device clusters shown can be considered that in the traffic scene recognition method provided by this application, the processing operations and the operations other than the processing operations are executed separately. That is, therefore, it is considered to hand over the function of the transceiver unit 701 to the computing device 800A, and hand over the function of the processing unit 702 to the computing device 800B.

[0164] It should be understood that Figure 10 the functions of the computing device 800A shown in can also be completed by multiple computing devices 800. Similarly, the functions of the computing device 800B can also be completed by multiple computing devices 800.

[0165] The embodiments of this application also provide another computing device cluster. The connection relationship between the computing devices in this computing device cluster can be similarly referred to Figure 9 and Figure 10 the connection mode of the computing device cluster shown, which will not be elaborated here.

[0166] The embodiments of this application also provide a computer program product containing instructions. The computer program product can be software or a program product containing instructions that can run on a computing device or be stored in any available medium. When the computer program product runs on at least one computer device, it causes at least one computer device to execute the above-mentioned traffic scene recognition method.

[0167] The embodiments of this application also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive), etc. The computer-readable storage medium includes instructions that direct the computing device to execute the above-mentioned traffic scene recognition method.

[0168] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, which will not be elaborated here.

[0169] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the protection scope of the technical solutions of the embodiments of this application.

Claims

1. A method for identifying traffic scenes based on Internet of Things technology, characterized in that: The method is applied to a cloud platform, the cloud platform is connected to an edge device, the edge device is connected to at least one acquisition device, the at least one acquisition device is used to report the collected traffic information of the target road section to the edge device, and the edge device is used to obtain warning information according to the traffic information, wherein the cloud platform stores the historical traffic information of the target road section. The method includes: Acquire the warning information, where the warning information is used to indicate that the speed of vehicles in the first lane of the target road section is less than a first speed threshold, or the speed of the fastest vehicle in the first lane is less than a second speed threshold, or there is a congestion point in the first lane; Acquiring the traffic information, where the traffic information is used to indicate the real-time traffic status of the target road section; According to the traffic information and the historical traffic information, it is identified that the target road section is not completely congested, and the incomplete congestion indicates that the number of vehicles on the second lane in the target road section is less than the number of vehicles on the first lane, or that the speed of the vehicles on the second lane is greater than a third speed threshold, or that the time it takes for vehicles to pass through the second lane is less than the time it takes for vehicles to pass through the first lane, wherein the second lane is in the same direction as the first lane.

2. The method according to claim 1, characterized in that: The traffic information includes the real-time average vehicle speed of the first lane and the real-time driving trajectory of the target road section; The historical traffic information includes the historical average vehicle speed of the first lane, the historical average vehicle speed of the second lane, and the historical driving trajectory of the target road section; The identifying, based on the traffic information and the historical traffic information, that the target road section is not completely congested includes: determining a speed difference of the first lane according to the real-time average speed of the first lane, the historical average speed of the second lane and the historical average speed of the first lane; Determining a detour trajectory coefficient of the target road section according to the real-time driving trajectory of the target road section and the historical driving trajectory of the target road section; According to the speed difference of the first lane and the detour trajectory coefficient of the target road section, it is identified that the target road section is not completely congested.

3. The method according to claim 1, characterized in that The traffic information includes the number of real-time driving trajectories and the number of real-time lane change trajectories of the target road section, the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, and the real-time average vehicle speed of the target road section; The historical traffic information includes the historical average number of driving trajectories and the historical average number of lane change trajectories of the target road section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane; The identifying, based on the traffic information and the historical traffic information, that the target road section is not completely congested includes: Determining a lane change parameter of the target road section according to the real-time driving trajectory number and the real-time lane change trajectory number of the target road section, the historical average driving trajectory number and the historical average lane change trajectory number of the target road section; Determine the speed difference of the target road section according to the real-time average speed of the first lane, the real-time average speed of the second lane, the real-time average speed of the target road section, the historical average speed of the first lane, and the historical average speed of the second lane; According to the lane change parameter of the target road section and the vehicle speed difference of the target road section, it is identified that the target road section is not completely congested.

4. The method according to any one of claims 1 to 3, characterized in that The cloud platform stores map information of the target road section, and the map information indicates sub-road sections included in the target road section; The identifying that the target road section is not completely congested includes: identifying that a sub-road section included in the target road section is not completely congested.

5. The method according to claim 4, characterized in that The sub-sections of the target section include a merging sub-section, and the merging sub-section is used to divert vehicles from the section before merging; The method further comprises: If the merging sub-segment is not completely congested, determining a possible merging point of the merging sub-segment; Acquire first position information and first travel destination information of a first vehicle; If the first position information indicates that the first vehicle is at a position before the merging point, and the first driving purpose information indicates that the first vehicle is about to enter the merging sub-section, first navigation information is sent to the first device, and the first navigation information is used to instruct the first vehicle to enter the merging sub-section at the merging point.

6. The method according to claim 4, characterized in that The sub-segments of the target segment include a merging sub-segment; The method further comprises: Acquire first position information and first travel destination information of a first vehicle; If the first position information indicates that the first vehicle is at a position before the merging sub-section, and the first driving purpose information indicates that the first vehicle is about to enter the merging sub-section, and the merging sub-section is completely congested, second navigation information is sent to the first device, and the second navigation information is used to instruct the first vehicle to enter a queuing lane, and the vehicles in the queuing lane queue up to enter the merging section.

7. The method according to claim 4, characterized in that The sub-section of the target section includes a straight sub-section; The method further comprises: Acquire second position information and second travel destination information of the second vehicle; If the straight sub-section is not completely congested, and the second position information indicates that the second vehicle is at a position before the straight sub-section, and the second driving purpose information indicates that the second vehicle is about to enter the straight sub-section, then the third navigation information is sent to the first device, and the third navigation information indicates that the second vehicle is driving in the second lane of the straight sub-section.

8. The method according to any one of claims 5 to 7, characterized in that The first device includes at least one of an on-board unit, a roadside unit, or a navigation facility.

9. A cloud platform, characterized in that: The cloud platform is connected to an edge device, the edge device is connected to at least one collection device, the at least one collection device is used to report the collected traffic information of the target road section to the edge device, and the edge device is used to obtain warning information according to the traffic information, wherein the cloud platform stores the historical traffic information of the target road section; the cloud platform includes: a transceiver unit, configured to obtain the warning information, wherein the warning information is used to indicate that the speed of a vehicle in a first lane in the target road section is less than a first speed threshold, or the speed of the fastest vehicle in the first lane is less than a second speed threshold, or there is a congestion point in the first lane; The transceiver unit is further used to obtain the traffic information, where the traffic information is used to indicate the real-time traffic status of the target road section; A processing unit is used to identify that the target road section is not completely congested based on the traffic information and the historical traffic information, wherein the incomplete congestion indicates that the number of vehicles on the second lane in the target road section is less than the number of vehicles on the first lane, or that the speed of the vehicles on the second lane is greater than a third speed threshold, or that the time it takes for vehicles to pass through the second lane is less than the time it takes for vehicles to pass through the first lane, wherein the second lane is in the same direction as the first lane.

10. The cloud platform according to claim 9, characterized in that: The traffic information includes the real-time average vehicle speed of the first lane and the real-time driving trajectory of the target road section; The historical traffic information includes the historical average vehicle speed of the first lane, the historical average vehicle speed of the second lane, and the historical driving trajectory of the target road section; The processing unit is specifically used for: determining a speed difference of the first lane according to the real-time average speed of the first lane, the historical average speed of the second lane and the historical average speed of the first lane; Determining a detour trajectory coefficient of the target road section according to the real-time driving trajectory of the target road section and the historical driving trajectory of the target road section; According to the speed difference of the first lane and the detour trajectory coefficient of the target road section, it is identified that the target road section is not completely congested.

11. The cloud platform according to claim 9, characterized in that: The traffic information includes the number of real-time driving trajectories and the number of real-time lane change trajectories of the target road section, the real-time average vehicle speed of the first lane, the real-time average vehicle speed of the second lane, and the real-time average vehicle speed of the target road section; The historical traffic information includes the historical average number of driving trajectories and the historical average number of lane change trajectories of the target road section, the historical average vehicle speed of the first lane, and the historical average vehicle speed of the second lane; The processing unit is specifically used for: Determining a lane change parameter of the target road section according to the real-time driving trajectory number and the real-time lane change trajectory number of the target road section, the historical average driving trajectory number and the historical average lane change trajectory number of the target road section; Determine the speed difference of the target road section according to the real-time average speed of the first lane, the real-time average speed of the second lane, the real-time average speed of the target road section, the historical average speed of the first lane, and the historical average speed of the second lane; According to the lane change parameter of the target road section and the vehicle speed difference of the target road section, it is identified that the target road section is not completely congested.

12. The cloud platform according to any one of claims 9 to 11, characterized in that: The cloud platform stores map information of the target road section, and the map information indicates sub-road sections included in the target road section; The processing unit is specifically configured to identify that a sub-section of the target section is not completely congested.

13. The cloud platform according to claim 12, characterized in that: The sub-sections of the target section include a merging sub-section, and the merging sub-section is used to divert vehicles from the section before merging; The processing unit is further configured to determine a possible merging point of the merging sub-segment if the merging sub-segment is not completely congested; The transceiver unit is further used to obtain first position information and first travel destination information of the first vehicle; The transceiver unit is further used to send first navigation information to the first device if the first position information indicates that the first vehicle is at a position before the merging point and the first driving purpose information indicates that the first vehicle is about to enter the merging sub-section, and the first navigation information is used to instruct the first vehicle to enter the merging sub-section at the merging point.

14. The cloud platform according to claim 12, characterized in that: The sub-segments of the target segment include a merging sub-segment; The transceiver unit is further used to obtain first position information and first travel destination information of the first vehicle; The transceiver unit is further used to send second navigation information to the first device if the first position information indicates that the first vehicle is at a position before the merging point, and the first driving purpose information indicates that the first vehicle is about to enter the merging section, and the merging sub-section is completely congested, wherein the second navigation information is used to instruct the first vehicle to enter a queuing lane, and the vehicles in the queuing lane queue up to enter the merging section.

15. The cloud platform according to claim 12, characterized in that: The sub-section of the target section includes a straight sub-section; The transceiver unit is further used to obtain second position information and second travel destination information of the second vehicle; The transceiver unit is further used to send third navigation information to the first device if the straight sub-section is not completely congested, and the second position information indicates that the second vehicle is at a position before the straight sub-section, and the second driving purpose information indicates that the second vehicle is about to enter the straight sub-section, and the third navigation information indicates that the second vehicle is traveling in the second lane of the straight sub-section.

16. A computing device cluster, characterized in that: comprising at least one computing device, each computing device comprising a processor and a memory; The processor of the at least one computing device is configured to execute instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the method according to any one of claims 1 to 8.

17. A computer program product comprising instructions, characterized in that When the instructions are executed by a computing device cluster, the computing device cluster is caused to perform the method according to any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes computer program instructions, which, when executed by a computing device cluster, cause the computing device cluster to perform the method according to any one of claims 1 to 8.

Images