YTS-based vehicle-road collaboration method and device for connected vehicles

Abstract

The present application provides a vehicle-road collaboration method and device for connected vehicles based on YTS. The roadside equipment sends the vehicle status within the risk period to the cloud; the cloud clusters the vehicle status collected by each roadside equipment to determine one or more vehicle status sets; simulation is performed based on the vehicle status set and the cloud-side YTS and secondary risk prediction is performed to determine the predicted risk events corresponding to each vehicle status set; the cloud sends the predicted risk events to the relevant roadside equipment based on the correlation between each roadside equipment and the vehicle status set; the roadside equipment broadcasts the received predicted risk events; after receiving the predicted risk events broadcast by the roadside equipment, the connected vehicle simulates the predicted risk events based on the vehicle-side YTS and displays the simulation results on the vehicle-side display device. In this way, the risk detection capability is improved and resource utilization is improved.

Description

Technical Field

[0001] The present application relates to the field of connected vehicle technology, and more specifically, to a vehicle-road collaboration method and device for a connected vehicle based on YTS. Background Art

[0002] With the development of intelligent connected vehicles (ICVs) and vehicle-to-everything (V2X) systems, traditional traffic management methods are no longer able to meet the real-time safety requirements of complex road environments. Existing V2X solutions typically rely on roadside units (RSUs) or onboard vehicles (OBUs) for local risk detection. However, due to limited computing power, they struggle to accurately predict global traffic conditions. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a vehicle-road collaboration method and device for a connected car based on YTS, so as to enhance the risk detection capability and improve resource utilization.

[0004] In a first aspect, the present invention provides a vehicle-road collaboration method for a connected vehicle based on YTS, wherein a roadside device is communicatively connected to the connected vehicle, and the method comprises:

[0005] The roadside equipment receives the vehicle status sent by each connected vehicle. Based on the status of each vehicle, the roadside equipment periodically performs a first-level risk prediction to determine the period when risk exists. The roadside equipment then sends the vehicle status during the risk period to the cloud.

[0006] The cloud clusters the vehicle states collected by each roadside device to determine one or more vehicle state sets; simulates and performs secondary risk prediction based on the vehicle state sets and the cloud YTS to determine the predicted risk events corresponding to each vehicle state set;

[0007] The cloud sends the predicted risk event to the relevant roadside devices based on the correlation between each roadside device and the vehicle status set;

[0008] The roadside equipment broadcasts the received predicted risk events;

[0009] After receiving the predicted risk event broadcast by the roadside equipment, the connected vehicle simulates the predicted risk event based on the vehicle-side YTS and displays the simulation results on the vehicle-side display device.

[0010] In an optional embodiment, the roadside equipment sending the vehicle status in the risk period to the cloud includes:

[0011] After determining that a risk exists in a current cycle, the roadside equipment determines whether risks exist in multiple consecutive cycles;

[0012] When risks exist in multiple consecutive cycles, the vehicle status in these multiple consecutive cycles is sent to the cloud.

[0013] In an optional embodiment, the cloud performs clustering based on the vehicle states collected by each roadside device to determine one or more vehicle state sets, including:

[0014] The cloud performs clustering based on the location of the roadside equipment, the location of the vehicle, and the time of the vehicle status corresponding to the vehicle status collected by each roadside equipment to determine one or more vehicle status sets.

[0015] In an optional embodiment, the first-level risk prediction includes one or more of traffic jam prediction, accident prediction, dangerous driving prediction, flow prediction and vehicle speed prediction; the second-level risk prediction includes one or more of first-level risk prediction, root cause location and risk avoidance plan recommendation.

[0016] In an optional embodiment, the root cause location includes: performing a backtracking simulation on a set of vehicle states based on the cloud-based YTS to determine the initial vehicle state and / or road conditions that led to the risk event;

[0017] A root cause analysis report is generated based on the initial vehicle state and / or road condition.

[0018] In an optional embodiment, the method further comprises:

[0019] The cloud builds a risk knowledge graph based on the historical vehicle status set and corresponding risk events;

[0020] When performing secondary risk prediction, the current vehicle status set is matched with the risk knowledge graph to assist in predicting risk events.

[0021] In an optional embodiment, the connected vehicle simulating a predicted risk event based on the vehicle-side YTS includes:

[0022] Generate multiple risk avoidance plans based on the current vehicle status and predicted risk events;

[0023] Simulate each hedging plan and calculate the safety factor and efficiency coefficient of each plan;

[0024] The optimal solution is selected and displayed based on the safety factor and efficiency factor.

[0025] In an optional embodiment, the vehicle status includes but is not limited to: one or more of vehicle position, vehicle speed, acceleration, steering angle, braking status, vehicle type, and load status.

[0026] In an optional embodiment, the method further comprises:

[0027] The cloud regularly evaluates the accuracy of the first-level risk prediction of each roadside device;

[0028] Dynamically adjust the first-level risk prediction algorithm parameters of each roadside equipment based on the evaluation results.

[0029] In a second aspect, the present invention provides a vehicle-road cooperative device for a connected vehicle based on YTS, wherein a roadside device is communicatively connected to the connected vehicle, and the device comprises:

[0030] Roadside equipment is used to receive vehicle status information from connected vehicles, periodically perform level 1 risk prediction based on each vehicle status, determine risky periods, and send the vehicle status during risky periods to the cloud.

[0031] The cloud is used to cluster the vehicle states collected by each roadside device to determine one or more vehicle state sets; simulate and perform secondary risk prediction based on the vehicle state sets and the cloud-based YTS to determine predicted risk events corresponding to each vehicle state set; and send the predicted risk events to the relevant roadside device based on the correlation between each roadside device and the vehicle state set;

[0032] The roadside equipment is also used to broadcast the received predicted risk events;

[0033] The connected car is used to simulate the predicted risk event based on the vehicle-side YTS after receiving the predicted risk event broadcast by the roadside equipment, and display the simulation results on the vehicle-side display device.

[0034] In an optional implementation manner, the roadside equipment is specifically configured to:

[0035] After determining that the current cycle has risks, determine whether risks exist in multiple consecutive cycles;

[0036] When risks exist in multiple consecutive cycles, the vehicle status in these multiple consecutive cycles is sent to the cloud.

[0037] In an optional embodiment, the cloud is specifically used to:

[0038] The cloud performs clustering based on the location of the roadside equipment, the location of the vehicle, and the time of the vehicle status corresponding to the vehicle status collected by each roadside equipment to determine one or more vehicle status sets.

[0039] In an optional embodiment, the first-level risk prediction includes one or more of traffic jam prediction, accident prediction, dangerous driving prediction, flow prediction and vehicle speed prediction; the second-level risk prediction includes one or more of first-level risk prediction, root cause location and risk avoidance plan recommendation.

[0040] In an optional embodiment, the root cause location includes: performing a backtracking simulation on the vehicle state set based on the cloud-based YTS to determine the initial vehicle state and / or road conditions that caused the risk event; and generating a root cause analysis report based on the initial vehicle state and / or road conditions.

[0041] In an optional embodiment, the cloud is also used to construct a risk knowledge graph based on historical vehicle state sets and corresponding risk events; when performing secondary risk prediction, the current vehicle state set is matched with the risk knowledge graph to assist in predicting risk events.

[0042] In an optional embodiment, the connected vehicle is specifically used to: generate multiple risk avoidance plans based on the current vehicle status and predicted risk events; simulate each risk avoidance plan and calculate the safety factor and efficiency coefficient of each plan; and select the optimal plan based on the safety factor and efficiency coefficient for display.

[0043] In an optional embodiment, the vehicle status includes but is not limited to: one or more of vehicle position, vehicle speed, acceleration, steering angle, braking status, vehicle type, and load status.

[0044] In an optional embodiment, the cloud is specifically used to regularly evaluate the accuracy of the first-level risk prediction of each roadside device; and dynamically adjust the first-level risk prediction algorithm parameters of each roadside device based on the evaluation results.

[0045] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0046] In a fourth aspect, the present application further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method described in the first aspect above.

[0047] Provided are a vehicle-road collaboration method and device for connected vehicles based on YTS, wherein a roadside device receives the vehicle status sent by each connected vehicle, and the roadside device periodically performs a first-level risk prediction based on the status of each vehicle to determine a period in which there is a risk; the roadside device sends the vehicle status within the period in which there is a risk to the cloud; the cloud clusters the vehicle status collected by each roadside device to determine one or more vehicle status sets; simulation is performed based on the vehicle status sets and the cloud-side YTS and a second-level risk prediction is performed to determine a predicted risk event corresponding to each of the vehicle status sets; the cloud sends the predicted risk event to the relevant roadside device based on the correlation between each roadside device and the vehicle status set; the roadside device broadcasts the received predicted risk event; after receiving the predicted risk event broadcast by the roadside device, the connected vehicle simulates the predicted risk event based on the vehicle-side YTS and displays the simulation result on the vehicle-side display device. Roadside equipment conducts a first-level risk assessment based on the received vehicle status information, and then sends the data within the risk period to the cloud for more in-depth analysis. This local rapid response combined with in-depth cloud analysis ensures immediacy and improves accuracy. In addition, the cloud performs cluster analysis on the received data to identify sets of vehicle states with similar characteristics. This method helps to discover patterns and trends hidden in large amounts of data, thereby more accurately locating possible risk points. Furthermore, using YTS to perform second-level risk prediction based on vehicle state sets not only takes into account the status of individual vehicles, but also integrates the surrounding environment and the behavior of other vehicles, making risk predictions more comprehensive and accurate, thereby improving risk detection capabilities and improving resource utilization.

[0048] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A schematic flow chart of a vehicle-road collaboration method for a connected vehicle based on YTS provided in an embodiment of the present application;

[0051] Figure 2 A flowchart of another vehicle-road collaboration method for a connected vehicle based on YTS provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of the structure of a vehicle-road cooperative device for a connected car based on YTS provided in an embodiment of the present application;

[0053] Figure 4 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0054] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0055] The terms "including," "having," and any variations thereof, as used in the embodiments of this application, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.

[0056] Currently, due to limited computing power, it is difficult to accurately predict the global traffic situation. Based on this, the embodiments of the present application provide a vehicle-road collaboration method and device based on YTS for connected vehicles, which can improve risk detection capabilities and increase resource utilization.

[0057] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0058] Figure 1 A schematic flow chart of a vehicle-road collaboration method for a connected vehicle based on YTS provided in an embodiment of the present application. The roadside equipment is connected to the connected vehicle in communication, such as Figure 1 As shown, the method includes:

[0059] S110, the roadside equipment receives the vehicle status sent by each connected car, and the roadside equipment periodically performs a first-level risk prediction based on the status of each vehicle, determines the period when the risk exists, and sends the vehicle status within the period when the risk exists to the cloud.

[0060] Among them, after determining that there is a risk in the current cycle, the roadside equipment can determine whether there is a risk in multiple consecutive cycles; when there is a risk in multiple consecutive cycles, the vehicle status in the multiple consecutive cycles is sent to the cloud.

[0061] By analyzing data from multiple continuous cycles, rather than relying solely on information from a single point in time, the system can more accurately identify and predict traffic risk trends. This helps identify potential problem areas or periods in advance, allowing preventive measures to be taken. Furthermore, based on in-depth analysis of vehicle status over continuous cycles, the traffic management system can implement more refined traffic flow control strategies, such as dynamically adjusting traffic light durations and recommending alternative routes, to alleviate congestion and reduce the likelihood of accidents.

[0062] Vehicle status refers to various parameters of a vehicle during driving, such as position, speed, and acceleration. These data are crucial for assessing driving safety. Vehicle status includes, but is not limited to, one or more of vehicle position, speed, acceleration, steering angle, braking status, vehicle type, and load status. This approach makes vehicle status more comprehensive and flexible.

[0063] Roadside equipment receives vehicle status information from connected vehicles. By analyzing this information, the equipment predicts time periods with driving risks and transmits the vehicle status information during these periods to the cloud server for further processing. If the equipment detects multiple consecutive periods of risk, it transmits all vehicle status information for these periods to the cloud. Vehicle status information includes key data such as vehicle location, speed, acceleration, steering angle, braking status, vehicle type, and load status.

[0064] Connected cars refer to smart cars that can connect to external networks through in-vehicle communication technology, and they can share and receive vehicle status information.

[0065] Roadside equipment refers to electronic equipment installed on the side of the road that can collect vehicle information and exchange data with the cloud.

[0066] Risk prediction refers to the use of vehicle status information by roadside equipment to predict possible driving safety risks within a specific period of time.

[0067] The cloud usually refers to remote servers used to store and process large amounts of data. Here, it refers to the remote data center to which roadside equipment sends vehicle status information.

[0068] S120, the cloud clusters the vehicle status collected by each roadside device, determines one or more vehicle status sets, simulates and performs secondary risk prediction based on the vehicle status sets and the cloud YTS, and determines the predicted risk events corresponding to each vehicle status set.

[0069] The cloud clusters the vehicle status data collected by each roadside device, based on the location of the roadside device, the location of the vehicle, and the time of the vehicle status, to determine one or more vehicle status sets. Cluster analysis of vehicle status data can more accurately identify different traffic patterns and trends, such as traffic flow characteristics during peak hours and accident-prone areas, facilitating the development of targeted traffic management strategies. Furthermore, in the event of a traffic accident or emergency, the real-time updated vehicle status set can quickly determine the affected area and extent, allowing for the swift mobilization of appropriate rescue forces and resources to mitigate the losses caused by the accident.

[0070] It should be noted that YTS (Unity TV Service) in the embodiments of this application represents the Unity Visualization Service Engine. Unity is a real-time 3D interactive content creation and operation platform. All creators, including game developers, art, architecture, automotive design, and film and television, use Unity to turn their creativity into reality. The platform provides a complete set of software solutions that can be used to create, operate, and monetize any real-time interactive 2D and 3D content. Supported platforms include mobile phones, tablets, PCs, game consoles, augmented reality, and virtual reality devices. The YTS engine is an intelligent engine system that deeply integrates AI algorithms, physical simulation, and 3D digital rendering technology. It is designed for the next generation of smart cars. Its core goal is to promote comprehensive upgrades in areas such as autonomous driving, vehicle-road collaboration, and intelligent interaction through high-precision simulation, real-time decision optimization, and cross-domain collaboration capabilities.

[0071] Furthermore, first-level risk prediction includes one or more of the following: traffic jam prediction, accident prediction, dangerous driving prediction, traffic volume prediction, and vehicle speed prediction; second-level risk prediction includes one or more of the following: first-level risk prediction, root cause location, and risk avoidance plan recommendation. First-level risk predictions (such as traffic jam prediction, accident prediction, and dangerous driving prediction) enable the traffic management system to proactively identify potential risks and issues, allowing preventive measures to be taken. This foresight is fundamental to reducing accidents and alleviating traffic congestion. The root cause location function in second-level risk prediction allows the system to not only identify the existence of problems but also conduct in-depth analysis of their underlying causes. This helps address the root causes of problems, rather than simply treating the symptoms.

[0072] Root cause identification involves back-testing and simulating a set of vehicle states using cloud-based YTS to determine the initial vehicle state and / or road conditions that led to the risk event; and generating a root cause analysis report based on these initial vehicle state and / or road conditions. This process recreates the scenario preceding the accident, including changes in key parameters such as vehicle speed, position, and acceleration. This capability enables analysts to accurately understand how the accident occurred. By simulating and analyzing the initial vehicle state and road conditions (such as road surface conditions, weather conditions, and traffic signal settings), this mechanism can identify the key factors that led to the risk event.

[0073] In some embodiments, the cloud can construct a risk knowledge graph based on the historical vehicle state set and the corresponding risk events; when performing secondary risk prediction, the current vehicle state set is matched with the risk knowledge graph to assist in predicting risk events.

[0074] By analyzing a large amount of historical vehicle status data and its corresponding risk events, the cloud-based system is able to build a detailed risk knowledge graph. This graph not only records various possible dangerous situations but also includes the vehicle status characteristics in these situations, providing a solid data foundation for subsequent risk prediction. When performing secondary risk prediction, the system matches and compares the current vehicle status set with the constructed risk knowledge graph. This approach allows the system to identify potential risk factors in the current driving environment and accurately predict possible risk events based on similar historical cases.

[0075] Roadside equipment collects vehicle status information and then performs cluster analysis to identify clusters of different vehicle states. These clusters form the basis for the system's risk predictions. The system's predictions are divided into two levels: primary risk prediction and secondary risk prediction.

[0076] Level 1 risk prediction focuses on common traffic issues, such as traffic congestion, accidents, dangerous driving behavior, traffic volume, and speed. Level 2 risk prediction is more in-depth, encompassing not only the content of the level 1 risk prediction but also identifying the causes of the risk and proposing strategies to avoid or reduce the risk.

[0077] Root cause identification is part of secondary risk prediction. It uses backtracking simulation to determine the initial vehicle state and / or road conditions that led to the risk event and generates an analysis report based on this information. Furthermore, the system can leverage historical data to construct a risk knowledge graph. By matching the current set of vehicle states with the knowledge graph, the system can assist in more accurate risk prediction.

[0078] Cluster analysis is a statistical method used to divide samples in a dataset into multiple categories or sets based on certain characteristics. In this system, cluster analysis is used to classify the collected vehicle status information into vehicle status sets.

[0079] Cloud-based YTS refers to a cloud-based traffic simulation system that is used to simulate a set of vehicle states to help predict and analyze traffic risks.

[0080] Risk prediction is the process of assessing the potential for adverse events in the future and their impact. In this system, risk prediction is divided into primary and secondary levels. The primary level focuses on basic traffic risks, while the secondary level is more detailed, including cause analysis and response strategies.

[0081] Root cause identification is the process of determining the root cause of a problem or risk event. The system analyzes the vehicle state and road conditions to identify the root cause of a risk event.

[0082] Risk avoidance recommendations refer to strategies and suggestions for reducing or avoiding risks based on risk prediction results. The system analyzes risk events and proposes corresponding risk avoidance measures.

[0083] A risk knowledge graph is a graphical structure used to store and express risk-related knowledge. It can help the system better understand the relationship between risk events and be used for predictive analysis.

[0084] S130, the cloud sends the predicted risk event to the relevant roadside devices based on the correlation between each roadside device and the vehicle status set.

[0085] As an optional implementation, the cloud receives data from multiple roadside devices and performs cluster analysis on this data to identify sets of vehicle states with similar characteristics or patterns. For simulation and secondary risk prediction, the cloud uses its traffic simulation system to analyze each vehicle state set to further assess potential risk events. Based on the simulation results, a secondary risk prediction is performed to determine the potential risk events. The cloud then analyzes the correlation between each roadside device and the previously identified vehicle state set. This step involves understanding which roadside devices provide data that constitutes a specific vehicle state set and which roadside devices are located in areas that may be affected by the predicted risk event. Based on this analysis, the cloud sends specific predicted risk event information to the relevant roadside devices. The roadside devices that receive this information can take appropriate measures based on the predicted risk event, such as issuing warnings to nearby vehicles or adjusting traffic light control strategies, to mitigate or avoid the risk event. This process embodies the workings of modern intelligent traffic management systems that integrate real-time traffic data, advanced data analytics, and simulation tools to improve road traffic safety.

[0086] S140: The roadside equipment broadcasts the received predicted risk event.

[0087] For example, a roadside device (RSE) first receives data from the cloud indicating a predicted risk event. This data typically includes detailed information about the risk event, such as the event type, location, and expected time of occurrence. The device parses the received data to determine which vehicles or entities should be communicated with. The RSE then assesses the scope of the risk event based on its content. This may involve determining which areas or road sections are affected by the risk event, as well as which vehicles may be directly or indirectly affected. Based on this assessment, the RSE formulates a corresponding broadcast strategy. For example, it may decide whether to broadcast on all communication channels or only on specific channels (such as emergency information channels); or whether to broadcast to all nearby vehicles or send targeted warnings only to those potentially affected. The RSE then executes the broadcast operation, sending the predicted risk event information via an appropriate communication technology (such as DSRC, LTE-V2X, or other V2I communication technologies). This information is typically sent in a standardized message format so that vehicle-side systems can correctly interpret and take appropriate action. Following the broadcast, the RSE may continuously monitor the affected area and be prepared to update or add new warning information at any time. For impending risk events, roadside equipment may also need to coordinate with other traffic management systems, such as adjusting traffic light timings and issuing additional road signs, to minimize the impact of the risk event. Through these steps, roadside equipment effectively transmits information about predicted risk events to relevant vehicles and pedestrians, improving road traffic safety and efficiency.

[0088] S150: After receiving the predicted risk event broadcast by the roadside equipment, the connected vehicle simulates the predicted risk event based on the vehicle-side YTS and displays the simulation results on the vehicle-side display device.

[0089] Connected vehicles can generate multiple avoidance plans based on the current vehicle state and predicted risk events. Each avoidance plan is simulated to calculate its safety and efficiency factors. Based on these factors, the optimal plan is selected and displayed. The system can quickly generate multiple feasible avoidance plans based on the current vehicle state and predicted risk events. This provides the driver or the autonomous driving system with multiple options when encountering potential hazards, increasing flexibility in responding to emergencies. Each avoidance plan undergoes detailed simulations to evaluate its safety and efficiency factors. The safety factor measures the plan's effectiveness in avoiding collisions and other hazards, while the efficiency factor focuses on the impact of implementing the plan on travel time, fuel consumption, and other aspects. This evaluation method ensures that both safety and driving efficiency are considered.

[0090] In an embodiment of the present application, a first-level risk assessment is performed based on the received vehicle status information by the roadside equipment, and then the data within the risk period is sent to the cloud for more in-depth analysis. This local rapid response combined with deep cloud analysis ensures immediacy and improves accuracy. Moreover, the received data is clustered and analyzed by the cloud to find a set of vehicle states with similar characteristics. This method helps to discover patterns and trends hidden in large amounts of data, thereby more accurately locating possible risk points. Furthermore, YTS is used to perform a second-level risk prediction based on the vehicle state set, which not only takes into account the status of a single vehicle, but also integrates the surrounding environment and the behavior of other vehicles, making the risk prediction more comprehensive and accurate, thereby improving the risk detection capability and improving resource utilization.

[0091] In some embodiments, as Figure 2 As shown, the method also includes: step S210, the cloud regularly evaluates the first-level risk prediction accuracy of each roadside device; step S220, dynamically adjusts the first-level risk prediction algorithm parameters of each roadside device based on the evaluation results. The first-level risk prediction accuracy of each roadside device is regularly evaluated through the cloud to ensure that the current performance status of each device can be timely grasped. Based on the evaluation results, the system can dynamically adjust the first-level risk prediction algorithm parameters of each roadside device. The system can automatically optimize the algorithm based on real-time data and environmental changes to improve prediction accuracy and maintain efficient operation of the system. Through continuous evaluation and adjustment, this method significantly improves the prediction accuracy and reliability of roadside equipment for first-level risk events (such as traffic accidents, severe weather conditions, etc.). More accurate risk predictions can help traffic management departments take measures in advance, reduce the possibility of accidents, and ensure road safety.

[0092] Figure 3 A schematic diagram of the structure of a vehicle-road cooperative device for a connected car based on YTS provided in an embodiment of the present application. The roadside equipment is connected to the connected car in communication, such as Figure 3 As shown, the vehicle-road cooperative device 300 of a connected vehicle based on YTS includes:

[0093] Roadside equipment 301 is used to receive vehicle status information sent by each connected vehicle, periodically perform level 1 risk prediction based on each vehicle status, determine risky periods, and send the vehicle status within the risky periods to the cloud.

[0094] Cloud 302 is used to cluster the vehicle states collected by each roadside device to determine one or more vehicle state sets; simulate and perform secondary risk prediction based on the vehicle state sets and the cloud YTS to determine predicted risk events corresponding to each vehicle state set; and send the predicted risk events to the relevant roadside devices based on the correlation between each roadside device and the vehicle state set;

[0095] The roadside device 301 is further configured to broadcast the received predicted risk events;

[0096] The connected car 303 is used to simulate the predicted risk event based on the vehicle-side YTS after receiving the predicted risk event broadcast by the roadside equipment, and display the simulation results on the vehicle-side display device.

[0097] In some embodiments, the roadside equipment 301 is specifically used to:

[0098] After determining that the current cycle has risks, determine whether risks exist in multiple consecutive cycles;

[0099] When risks exist in multiple consecutive cycles, the vehicle status in these multiple consecutive cycles is sent to the cloud.

[0100] In some embodiments, the cloud 302 is specifically configured to:

[0101] Clustering is performed based on the position of the roadside device, the position of the vehicle, and the time of the vehicle state corresponding to the vehicle state collected by each roadside device to determine one or more vehicle state sets.

[0102] In some embodiments, the first-level risk prediction includes one or more of traffic jam prediction, accident prediction, dangerous driving prediction, traffic flow prediction, and vehicle speed prediction; the second-level risk prediction includes one or more of the first-level risk prediction, root cause location, and risk avoidance plan recommendation.

[0103] In some embodiments, root cause location includes: performing back-tracking simulation on a vehicle state set based on cloud-based YTS to determine the initial vehicle state and / or road conditions that caused the risk event to occur; and generating a root cause analysis report based on the initial vehicle state and / or road conditions.

[0104] In some embodiments, the cloud 302 is also used to construct a risk knowledge graph based on historical vehicle state sets and corresponding risk events; when performing secondary risk prediction, the current vehicle state set is matched with the risk knowledge graph to assist in predicting risk events.

[0105] In some embodiments, the connected car 303 is specifically used to: generate multiple risk avoidance plans based on the current vehicle status and predicted risk events; simulate each risk avoidance plan and calculate the safety factor and efficiency coefficient of each plan; and select the optimal plan based on the safety factor and efficiency coefficient for display.

[0106] In some embodiments, the vehicle status includes, but is not limited to, one or more of: vehicle position, vehicle speed, acceleration, steering angle, braking status, vehicle type, and load status.

[0107] In some embodiments, the cloud 302 is specifically used to regularly evaluate the accuracy of the first-level risk prediction of each roadside device; and dynamically adjust the first-level risk prediction algorithm parameters of each roadside device based on the evaluation results. In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. On the other hand, the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] An electronic device provided in an embodiment of the present application is Figure 4 As shown, the electronic device 400 includes a processor 402 and a memory 401 , wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method provided in the above embodiment when executing the computer program.

[0109] See also Figure 4 The electronic device further includes: a bus 403 and a communication interface 404, a processor 402, a communication interface 404 and a memory 401 connected via the bus 403; the processor 402 is used to execute executable modules stored in the memory 401, such as computer programs.

[0110] Memory 401 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk drive. Communication between the system network element and at least one other network element is achieved via at least one communication interface 404 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0111] The bus 403 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0112] Among them, the memory 401 is used to store programs, and the processor 402 executes the program after receiving the execution instruction. The method executed by the device defined by the process disclosed in any embodiment of the present application can be applied to the processor 402 or implemented by the processor 402.

[0113] The processor 402 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 402 or by instructions in the form of software. The above-mentioned processor 402 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 401, and processor 402 reads the information in memory 401 and, in conjunction with its hardware, completes the steps of the above method.

[0114] Corresponding to the above-mentioned vehicle-road collaboration method for connected vehicles based on YTS, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned vehicle-road collaboration method for connected vehicles based on YTS.

[0115] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0117] It should be noted that if the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0118] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0119] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A vehicle-road collaboration method for connected vehicles based on YTS, characterized in that: The roadside equipment is communicatively connected to the connected vehicle, and the method includes: The roadside equipment receives the vehicle status sent by each connected vehicle. Based on the status of each vehicle, the roadside equipment periodically performs a first-level risk prediction to determine the period when risk exists. The roadside equipment then sends the vehicle status during the risk period to the cloud. The cloud performs clustering based on the vehicle states collected by various roadside devices to determine one or more vehicle state sets; performs simulation and secondary risk prediction based on the vehicle state sets and the cloud-based YTS to determine the predicted risk events corresponding to each of the vehicle state sets; the cloud constructs a risk knowledge graph based on historical vehicle state sets and corresponding risk events. The risk knowledge graph includes a variety of dangerous situations and the state characteristics of the vehicle in each of the dangerous situations. The multiple dangerous situations and the state characteristics are used to provide a data basis for risk prediction; when performing secondary risk prediction, the current vehicle state set is matched and compared with the constructed risk knowledge graph to identify potential risk factors in the current driving environment, and the possible risk events are predicted based on similar historical cases to assist in predicting risk events; The cloud sends the predicted risk event to the relevant roadside devices based on the correlation between each roadside device and the vehicle status set; The roadside equipment broadcasts the received predicted risk events; After receiving the predicted risk event broadcast by the roadside equipment, the connected vehicle simulates the predicted risk event based on the vehicle-side YTS and displays the simulation results on the vehicle-side display device.

2. The vehicle-road cooperative method according to claim 1, characterized in that: The roadside equipment sends the vehicle status during the risk period to the cloud, including: After determining that a risk exists in a current cycle, the roadside equipment determines whether risks exist in multiple consecutive cycles; When risks exist in multiple consecutive cycles, the vehicle status in these multiple consecutive cycles is sent to the cloud.

3. The vehicle-road cooperative method according to claim 1, characterized in that: The cloud performs clustering based on the vehicle status collected by each roadside device to determine one or more vehicle status sets, including: The cloud performs clustering based on the location of the roadside equipment, the location of the vehicle, and the time of the vehicle status corresponding to the vehicle status collected by each roadside equipment to determine one or more vehicle status sets.

4. The vehicle-road cooperative method according to claim 1, characterized in that: The first-level risk prediction includes one or more of traffic jam prediction, accident prediction, dangerous driving prediction, traffic flow prediction and vehicle speed prediction; the second-level risk prediction includes one or more of first-level risk prediction, root cause location and risk avoidance plan recommendation.

5. The vehicle-road cooperative method according to claim 4, characterized in that: The root cause location includes: performing a backtracking simulation of a vehicle state set based on the cloud YTS to determine the initial vehicle state and / or road conditions that led to the risk event; A root cause analysis report is generated based on the initial vehicle state and / or road condition.

6. The vehicle-road cooperative method according to claim 1, characterized in that: The connected car simulates the predicted risk event based on the vehicle-side YTS, including: Generate multiple risk avoidance plans based on the current vehicle status and predicted risk events; Simulate each hedging plan and calculate the safety factor and efficiency factor of each plan; The optimal solution is selected and displayed based on the safety factor and efficiency factor.

7. The vehicle-road cooperative method according to claim 1, characterized in that: The vehicle status includes but is not limited to: one or more of vehicle position, vehicle speed, acceleration, steering angle, braking status, vehicle type, and load status.

8. The vehicle-road cooperative method according to claim 1, characterized in that: The method further comprises: The cloud regularly evaluates the accuracy of the first-level risk prediction of each roadside device; Dynamically adjust the first-level risk prediction algorithm parameters of each roadside equipment based on the evaluation results.

9. A vehicle-road cooperative device for a connected car based on YTS, characterized in that: The roadside equipment is communicatively connected to the connected vehicle, and the device includes: Roadside equipment is used to receive vehicle status information from connected vehicles, periodically perform level 1 risk prediction based on each vehicle status, determine risky periods, and send the vehicle status during risky periods to the cloud. The cloud side is used to cluster the vehicle states collected by each roadside device to determine one or more vehicle state sets; simulate and perform secondary risk prediction based on the vehicle state sets and the cloud side YTS to determine the predicted risk events corresponding to each of the vehicle state sets; send the predicted risk events to the relevant roadside devices based on the correlation between each roadside device and the vehicle state set; the cloud side is also used to construct a risk knowledge graph based on the historical vehicle state sets and the corresponding risk events, the risk knowledge graph contains a variety of dangerous situations, and the state characteristics of the vehicle in each of the dangerous situations, the multiple dangerous situations and the state characteristics are used to provide a data basis for risk prediction; when performing secondary risk prediction, the current vehicle state set is matched and compared with the constructed risk knowledge graph to identify potential risk factors in the current driving environment, and the possible risk events are predicted based on similar historical cases to assist in predicting risk events; The roadside equipment is also used to broadcast the received predicted risk events; The connected car is used to simulate the predicted risk event based on the vehicle-side YTS after receiving the predicted risk event broadcast by the roadside equipment, and display the simulation results on the vehicle-side display device.

Images