A road intelligent induction and early warning method and system based on intelligent studs

Abstract

The application discloses a road intelligent induction and early warning method and system based on intelligent studs, and relates to the technical field of intelligent transportation. A plurality of intelligent studs are deployed in a target road area; each of the intelligent studs is taken as an independent blockchain node, is connected to a pre-constructed initial blockchain network, and a decentralized intelligent stud blockchain networking system is constructed; the blockchain networking system collects sensing data uploaded by each intelligent stud, and constructs a dynamic traffic scenario model; based on the dynamic traffic scenario model, a traffic operation trend parameter is predicted through a preset algorithm, driving dynamic decision and traffic adaptive control are executed on a target vehicle in combination with the traffic operation trend parameter, and early warning information of a corresponding level is generated and pushed according to a preset safety level division standard. The application is helpful for resolving traffic conflicts in advance, reducing the accident rate, optimizing vehicle passing efficiency through adaptive control, and thus comprehensively improving the safety and intelligent management level of road operation.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and more specifically to a road intelligent guidance and early warning method and system based on intelligent road studs. Background Technology

[0002] With the accelerating pace of urbanization and the continuous increase in motor vehicle ownership, road traffic volume has surged. Severe weather conditions such as heavy rain, dense fog, and snow, as well as unforeseen road conditions like road damage, vehicle breakdowns, and traffic congestion, are increasingly impacting road safety and efficiency. In particular, low visibility conditions reduce drivers' visibility distance, making rear-end collisions and side impacts more likely. Therefore, building an efficient, real-time, and intelligent road guidance and early warning system has become an urgent need to improve road traffic management and ensure public safety.

[0003] Currently, road guidance and early warning mainly rely on traditional traffic facilities. Traditional road studs, as basic guidance components, can only passively reflect the road outline through reflection. Their guidance effect is greatly reduced in low visibility conditions such as rain, fog, and night, and they cannot achieve active perception and information interaction. Some existing smart road studs can collect basic road condition data and integrate LED lighting functions, but their perception dimensions are limited. They cannot comprehensively collect multi-dimensional information such as weather conditions, road surface conditions, and traffic flow parameters. Furthermore, they lack an efficient and reliable networking mechanism, and the data from each road stud is scattered and independent, making it difficult to support the needs of precise road guidance and early warning.

[0004] Existing road guidance and early warning systems mostly employ centralized server architectures, resulting in significant data silos and security vulnerabilities. Furthermore, centralized architectures suffer from insufficient data storage and transmission security, making them susceptible to data tampering and leakage. Additionally, system response is often slow, guidance strategies are fixed and cannot be dynamically adjusted based on real-time traffic conditions, leading to poor adaptability. Blockchain technology, with its core advantages of decentralization, immutability, and multi-node collaboration, can effectively address these pain points. However, it has not yet achieved deep integration with smart road beacons, failing to fully leverage the technological value of both technologies.

[0005] Furthermore, existing smart road beacon networks largely rely on traditional communication methods, resulting in limited coverage, poor signal stability, and high communication latency in complex scenarios such as tunnels and remote road sections, further impacting the real-time performance and reliability of guidance and warning. Simultaneously, the large-scale deployment of smart road beacons faces the dual challenges of cost control and operational efficiency; existing technologies struggle to organically combine low-cost deployment, efficient operation and maintenance, and efficient data utilization. In summary, existing road guidance and warning technologies suffer from numerous shortcomings. Developing a blockchain-based smart road beacon guidance and warning method capable of multi-dimensional perception has significant practical implications and application value. Summary of the Invention

[0006] In view of this, the present invention provides a road intelligent guidance and early warning method and system based on smart road studs to solve the problems existing in the background art.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: A road intelligent guidance and early warning method based on smart road studs includes the following steps: Several smart road studs are deployed in the target road area. The smart road studs have multi-dimensional perception capabilities, and each smart road stud is assigned a unique identification code, which is bound to the geographical location information of the smart road stud. Each smart road stud is treated as an independent blockchain node and connected to a pre-built initial blockchain network. By using blockchain technology, all smart road studs are networked together, thus constructing a decentralized smart road stud blockchain network system. The blockchain networking system aggregates the sensing data uploaded by each smart road beacon, constructs a dynamic traffic scene model, and realizes real-time dynamic replication of the road traffic environment. Based on the dynamic traffic scenario model, traffic operation trend parameters are predicted by a preset algorithm. Combined with the traffic operation trend parameters, dynamic driving decisions and adaptive traffic control are performed on the target vehicle. According to the preset safety level classification standard, corresponding warning information is generated and pushed.

[0008] Optionally, the networking system has node authentication, encrypted data transmission and malicious behavior prevention functions, and reduces network concurrency pressure through node hierarchical and cluster management strategies, so as to achieve stable networking and collaborative interaction of ultra-large-scale intelligent road beacon clusters.

[0009] Optionally, the node authentication is achieved through a blockchain asymmetric encryption algorithm. Each smart beacon node generates a unique public key and private key. When data is exchanged between nodes, the public key is used to verify the legitimacy of the other party's identity, and the private key is used for its own data signature to prevent data from being tampered with or forged. The malicious behavior prevention includes node anomaly monitoring and data anomaly verification, and isolation of malicious nodes to ensure the stability of the network system and data security.

[0010] Optionally, the node hierarchical and grouped management strategy is as follows: based on the geographical location, sensing range and computing power of the smart road stud, the smart road stud nodes are divided into different levels and groups. Nodes within the same group realize local data interaction and preprocessing, while nodes across groups realize data aggregation and interaction through hierarchical gateways, thereby reducing the global network concurrency pressure and adapting to the networking needs of ultra-large-scale smart road stud clusters.

[0011] Optionally, the preset algorithm is built on hierarchical contrastive learning and the QTRAN framework to achieve accurate prediction of traffic operation trend parameters, specifically including the following steps: The latent representations corresponding to the multi-source sensing data collected by each smart road stud are extracted. The latent representations are obtained by adding and fusing the features of road surface state data, traffic flow data and time dimension data by three independent encoders respectively. The K-means clustering algorithm is used to perform unsupervised clustering on the potential representation of all smart road studs, generating cluster labels and using them as pseudo-labels for regions. Based on the pseudo-labels, the smart road studs are divided into different functional regions. A subgraph is constructed for each functional region. The subgraph uses smart road studs as nodes, road network topology connection relationships or spatial proximity as edges, and Euclidean distance between intersections and road capacity as edge weights. A two-layer graph convolutional network is applied to each subgraph to propagate and aggregate features within the region, capture the spatial dependency of smart road studs within the region, obtain region-aware features, and perform max pooling operation on the region-aware features to generate cluster-level state vectors for each functional region. A contrastive learning loss function is constructed using regional pseudo-labels as supervision signals, and a cluster-level state vector is used as an abstract representation of the traffic state of functional areas. Based on the QTRAN framework, a QTRAN total loss function is constructed that includes temporal difference loss, optimal action constraint loss, and non-optimal action constraint loss. The contrastive learning loss function and the QTRAN total loss function are then fused to obtain a joint loss function. The Adam optimizer is used to jointly update the parameters of the policy network and the value network to minimize the joint loss function. The trained policy network is then used to analyze the dynamic traffic scenario model and predict traffic operation trend parameters.

[0012] Optional traffic operation trend parameters include the probability of traffic congestion, vehicle speed, road surface condition change trends, and potential safety risks within a preset time period in the future.

[0013] Optionally, it also includes data fusion processing of the sensing data uploaded by smart road studs. The data fusion processing adopts a multi-source data fusion algorithm, which combines the geographical location correlation of smart road studs to perform complementary verification on the same source data collected by different smart road studs, and performs correlation analysis on the heterogeneous data to remove abnormal data and improve data accuracy. The dynamic traffic scene model can be updated in real time, and the update frequency is synchronized with the data collection frequency of smart road studs.

[0014] A road intelligent guidance and early warning system based on smart road studs includes: Smart road stud deployment module: used to deploy several smart road studs in the target road area. The smart road studs have multi-dimensional perception capabilities, and each smart road stud is assigned a unique identification code, which is bound to the geographical location information of the smart road stud. Smart road stud blockchain networking module: Each smart road stud is treated as an independent blockchain node and connected to a pre-built initial blockchain network. Through blockchain technology, all smart road studs are networked to build a decentralized smart road stud blockchain networking system. Dynamic traffic scene construction module: used by the blockchain networking system to collect the perception data uploaded by each smart road beacon, construct a dynamic traffic scene model, and realize the real-time dynamic replication of the road traffic environment; Traffic guidance and early warning module: Based on the dynamic traffic scenario model, it predicts traffic operation trend parameters through a preset algorithm, combines the traffic operation trend parameters, performs dynamic driving decisions and traffic adaptive control for the target vehicle, and generates and pushes corresponding level early warning information according to the preset safety level classification standard.

[0015] As can be seen from the above technical solution, compared with the prior art, the present invention provides a road intelligent guidance and early warning method and system based on smart road studs, which has the following beneficial effects: 1. By assigning a unique identifier code to each smart road stud with multi-dimensional perception capabilities and binding it with geographical location information, the accurate positioning and identity authentication of road perception nodes are realized, laying a reliable foundation for subsequent data association and spatial analysis; 2. By using smart road studs as independent blockchain nodes to build a decentralized networking system, the immutability and distributed consensus mechanism of blockchain technology are utilized to ensure the authenticity, integrity and security of sensing data during transmission, storage and sharing, effectively avoiding the single point of failure and data tampering risks under the traditional centralized architecture. 3. Based on the multi-source perception data collected by the blockchain networking system, a dynamic traffic scenario model is constructed, which can dynamically replicate the road traffic environment in real time, significantly improving the comprehensiveness, timeliness and accuracy of traffic situation perception. 4. By predicting traffic operation trend parameters through preset algorithms and combining them with safety level classification standards, the system performs dynamic driving decisions, traffic adaptive control, and graded early warning pushes for target vehicles. This realizes the transformation from passive response to proactive prevention, which helps to resolve traffic conflicts in advance and reduce the accident rate. At the same time, the system optimizes vehicle traffic efficiency through adaptive control, thereby comprehensively improving the safety and intelligent management level of road operation. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the method flow provided by the present invention; Figure 2 This is a schematic diagram of the system structure provided by the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] This invention discloses a road intelligent guidance and early warning method based on smart road studs, such as... Figure 1 As shown, it includes the following steps: Step 1: Deploy several smart road studs in the target road area. The smart road studs have multi-dimensional perception capabilities to collect road-related perception data. Each smart road stud is assigned a unique identification code, which is bound to the smart road stud's geographical location information to achieve accurate positioning and identification of the smart road studs. Step 2: Each smart road stud is treated as an independent blockchain node and connected to the pre-built initial blockchain network. The network of all smart road studs is achieved through blockchain technology, and a decentralized smart road stud blockchain networking system is constructed. The networking system has node authentication, encrypted data transmission and malicious behavior prevention functions. Through node hierarchical and cluster management strategies, the network concurrency pressure is reduced, and stable networking and collaborative interaction of ultra-large-scale smart road stud clusters are achieved. Step 3: The blockchain networking system aggregates the sensing data uploaded by each smart beacon, cleans and fuses the multi-source sensing data, and constructs a dynamic traffic scene model to realize real-time dynamic replication of the road traffic environment. Step 4: Based on the dynamic traffic scenario model, traffic operation trend parameters are predicted through a preset algorithm. Combined with the traffic operation trend parameters, dynamic driving decisions and adaptive traffic control are performed on the target vehicle. According to the preset safety level classification standard, corresponding level of early warning information is generated and pushed to complete intelligent road guidance and early warning.

[0020] Furthermore, the multi-dimensional perception data mentioned in step 1 includes weather condition data, road surface condition data, and traffic flow data. The weather condition data includes precipitation, visibility, temperature, and humidity parameters. The road surface condition data includes information on road surface water accumulation, icing, damage, and traffic accidents. The traffic flow data includes the number of vehicles, vehicle speed, vehicle spacing, and vehicle type information.

[0021] Furthermore, the smart road stud described in step 1 has multiple types of built-in sensors, including temperature and humidity sensors, microwave sensors, geomagnetic sensors, and vibration sensors, to achieve real-time acquisition of multi-dimensional perception data. The smart road stud also has a data preprocessing function, which performs noise reduction and deduplication on the collected raw data before uploading it to the blockchain networking system.

[0022] Furthermore, the node authentication described in step 2 is achieved through a blockchain asymmetric encryption algorithm. Each smart beacon node generates a unique public key and private key. When data is exchanged between nodes, the public key is used to verify the legitimacy of the other party's identity, and the private key is used for its own data signature to prevent data from being tampered with or forged. The malicious behavior prevention includes node anomaly monitoring and data anomaly verification, and the isolation of malicious nodes to ensure the stability of the network system and data security.

[0023] The node hierarchical and grouped management strategy described in step 2 is as follows: based on the geographical location, sensing range and computing power of the smart road studs, the smart road stud nodes are divided into different levels and groups. Nodes within the same group realize local data interaction and preprocessing, while nodes across groups realize data aggregation and interaction through hierarchical gateways, reducing the global network concurrency pressure and adapting to the networking needs of ultra-large-scale smart road stud clusters.

[0024] Furthermore, the specific method of the smart road stud blockchain networking described in step 2 is based on the Internet of Things blockchain networking technology. By combining the geographical location characteristics of the smart road studs with network topology optimization, it can achieve efficient access, stable networking and dynamic optimization of smart road stud nodes, improve the communication efficiency and robustness of the networking system, and reduce communication overhead.

[0025] Furthermore, the data fusion processing in step 3 employs a multi-source data fusion algorithm. By combining the geographical location correlation of smart road studs, complementary verification is performed on the same-source data collected from different smart road studs, correlation analysis is performed on the heterogeneous data, abnormal data is eliminated, and data accuracy is improved. The dynamic traffic scene model can be updated in real time, and the update frequency is synchronized with the smart road stud data collection frequency.

[0026] Furthermore, the preset algorithm in step 4 includes a machine learning algorithm and a traffic flow prediction algorithm. The traffic operation trend parameters include the probability of traffic congestion, vehicle speed, road surface condition change trend and potential safety risks within a preset time period in the future. The driving dynamic decision includes vehicle route adjustment and speed suggestion. The traffic adaptive control includes lane guidance and traffic flow diversion control.

[0027] Furthermore, the preset safety level classification standard mentioned in step 4 is determined based on traffic operation trend parameters and road safety thresholds, and is divided into multiple levels. Different safety levels correspond to different warning methods and warning content. Warning information is pushed through one or more of the following methods: the LED light of the smart road stud itself, the vehicle terminal, and the road warning equipment, to ensure that the warning information is accurately delivered.

[0028] Furthermore, the preset algorithm described in step 4 is based on hierarchical contrastive learning and the QTRAN framework, and is used to achieve accurate prediction of traffic operation trend parameters. Specifically, it includes the following steps: S41: Extract the latent representations corresponding to the multi-source sensing data collected by each smart road stud. The latent representations are obtained by adding and fusing the features of the road surface state data, traffic flow data, and time dimension data by three independent encoders respectively. The three independent encoders are the road surface state encoder, the traffic flow encoder, and the time delay encoder. The road surface state encoder adopts a two-layer fully connected network, the traffic flow encoder adopts a ResNet-18 deep residual network combined with a linear layer, and the time delay encoder adopts a multilayer perceptron. S42: Use the K-means clustering algorithm to perform unsupervised clustering on the potential representations of all smart road studs, generate cluster labels and use them as pseudo-labels for regions, divide the smart road studs into different functional regions according to the pseudo-labels for regions, and construct a subgraph for each functional region. The subgraph uses smart road studs as nodes, road network topology connection relationships or spatial proximity as edges, and Euclidean distance between intersections and road capacity as edge weights. S43: Apply a two-layer graph convolutional network to each subgraph to propagate and aggregate features within the region, capture the spatial dependency of smart road studs within the region, obtain region-aware features, perform max pooling on the region-aware features, and generate cluster-level state vectors for each functional region. S44: Construct a contrastive learning loss function using regional pseudo-labels as supervision signals, use cluster-level state vectors as abstract representations of functional area traffic states, construct a QTRAN total loss function based on the QTRAN framework that includes time difference loss, optimal action constraint loss, and non-optimal action constraint loss, and fuse the contrastive learning loss function and the QTRAN total loss function to obtain a joint loss function; S45: The Adam optimizer is used to jointly update the parameters of the policy network and the value network to minimize the joint loss function. The trained policy network is used to analyze the dynamic traffic scenario model and predict traffic operation trend parameters. The traffic operation trend parameters include the probability of traffic congestion, vehicle speed, road surface condition change trend and potential safety risks in the future preset time period.

[0029] Furthermore, step 5 includes storing all data in the blockchain network system in an immutable manner, including smart road beacon sensing data, node interaction data, dynamic traffic scene model data, and early warning record data, to achieve data traceability and facilitate subsequent traffic incident tracing and liability determination.

[0030] and Figure 1 Corresponding to the method shown, this invention also discloses a road intelligent guidance and early warning system based on smart road studs, used for... Figure 1 The implementation of the method, specifically the structure is as follows: Figure 2 As shown, it includes: Smart road stud deployment module: used to deploy several smart road studs in the target road area. The smart road studs have multi-dimensional perception capabilities, and each smart road stud is assigned a unique identification code, which is bound to the geographical location information of the smart road stud. Smart road stud blockchain networking module: Each smart road stud is treated as an independent blockchain node and connected to a pre-built initial blockchain network. Through blockchain technology, all smart road studs are networked to build a decentralized smart road stud blockchain networking system. Dynamic traffic scene construction module: used by the blockchain networking system to collect the perception data uploaded by each smart road beacon, construct a dynamic traffic scene model, and realize the real-time dynamic replication of the road traffic environment; Traffic guidance and early warning module: Based on the dynamic traffic scenario model, it predicts traffic operation trend parameters through a preset algorithm, combines the traffic operation trend parameters, performs dynamic driving decisions and traffic adaptive control for the target vehicle, and generates and pushes corresponding level early warning information according to the preset safety level classification standard.

[0031] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0032] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A road intelligent guidance and early warning method based on smart road studs, characterized in that, Includes the following steps: Several smart road studs are deployed in the target road area. The smart road studs have multi-dimensional perception capabilities, and each smart road stud is assigned a unique identification code, which is bound to the geographical location information of the smart road stud. Each smart road stud is treated as an independent blockchain node and connected to a pre-built initial blockchain network. By using blockchain technology, all smart road studs are networked together, thus constructing a decentralized smart road stud blockchain network system. The blockchain networking system aggregates the sensing data uploaded by each smart road beacon, constructs a dynamic traffic scene model, and realizes real-time dynamic replication of the road traffic environment. Based on the dynamic traffic scenario model, traffic operation trend parameters are predicted by a preset algorithm. Combined with the traffic operation trend parameters, dynamic driving decisions and adaptive traffic control are performed on the target vehicle. According to the preset safety level classification standard, corresponding warning information is generated and pushed.

2. The intelligent road guidance and early warning method based on smart road studs according to claim 1, characterized in that, The networking system has node authentication, encrypted data transmission and malicious behavior prevention functions. Through node hierarchical and cluster management strategies, it reduces network concurrency pressure and achieves stable networking and collaborative interaction of ultra-large-scale intelligent road beacon clusters.

3. The intelligent road guidance and early warning method based on smart road studs according to claim 2, characterized in that, The node authentication is achieved through a blockchain asymmetric encryption algorithm. Each smart beacon node generates a unique public key and private key. When data is exchanged between nodes, the public key is used to verify the legitimacy of the other party's identity, and the private key is used for its own data signature to prevent data from being tampered with or forged. The malicious behavior prevention includes node anomaly monitoring and data anomaly verification, and isolation of malicious nodes to ensure the stability of the network system and data security.

4. The intelligent road guidance and early warning method based on smart road studs according to claim 2, characterized in that, The node hierarchical and grouped management strategy is as follows: based on the geographical location, sensing range and computing power of the smart road studs, the smart road stud nodes are divided into different levels and groups. Nodes within the same group realize local data interaction and preprocessing, while nodes across groups realize data aggregation and interaction through hierarchical gateways, reducing the global network concurrency pressure and adapting to the networking needs of ultra-large-scale smart road stud clusters.

5. A road intelligent guidance and early warning method based on smart road studs according to claim 1, characterized in that, The preset algorithm is based on hierarchical contrastive learning and the QTRAN framework, and is used to accurately predict traffic operation trend parameters. Specifically, it includes the following steps: The latent representations corresponding to the multi-source sensing data collected by each smart road stud are extracted. The latent representations are obtained by adding and fusing the features of road surface state data, traffic flow data and time dimension data by three independent encoders respectively. The K-means clustering algorithm is used to perform unsupervised clustering on the potential representation of all smart road studs, generating cluster labels and using them as pseudo-labels for regions. Based on the pseudo-labels, the smart road studs are divided into different functional regions. A subgraph is constructed for each functional region. The subgraph uses smart road studs as nodes, road network topology connection relationships or spatial proximity as edges, and Euclidean distance between intersections and road capacity as edge weights. A two-layer graph convolutional network is applied to each subgraph to propagate and aggregate features within the region, capture the spatial dependency of smart road studs within the region, obtain region-aware features, and perform max pooling operation on the region-aware features to generate cluster-level state vectors for each functional region. A contrastive learning loss function is constructed using regional pseudo-labels as supervision signals, and a cluster-level state vector is used as an abstract representation of the traffic state of functional areas. Based on the QTRAN framework, a QTRAN total loss function is constructed that includes temporal difference loss, optimal action constraint loss, and non-optimal action constraint loss. The contrastive learning loss function and the QTRAN total loss function are then fused to obtain a joint loss function. The Adam optimizer is used to jointly update the parameters of the policy network and the value network to minimize the joint loss function. The trained policy network is then used to analyze the dynamic traffic scenario model and predict traffic operation trend parameters.

6. The intelligent road guidance and early warning method based on smart road studs according to claim 1, characterized in that, Traffic operation trend parameters include the probability of traffic congestion, vehicle speed, road surface condition change trends, and potential safety risks within a preset time period in the future.

7. A road intelligent guidance and early warning method based on smart road studs according to claim 1, characterized in that, It also includes data fusion processing of the sensing data uploaded by smart road studs. The data fusion processing adopts a multi-source data fusion algorithm, which combines the geographical location correlation of smart road studs to perform complementary verification on the same source data collected by different smart road studs, and performs correlation analysis on the heterogeneous source data to remove abnormal data and improve data accuracy. The dynamic traffic scene model can be updated in real time, and the update frequency is synchronized with the data collection frequency of smart road studs.

8. A road intelligent guidance and early warning system based on smart road studs, characterized in that, include: Smart road stud deployment module: used to deploy several smart road studs in the target road area. The smart road studs have multi-dimensional perception capabilities, and each smart road stud is assigned a unique identification code, which is bound to the geographical location information of the smart road stud. Smart road stud blockchain networking module: Each smart road stud is treated as an independent blockchain node and connected to a pre-built initial blockchain network. Through blockchain technology, all smart road studs are networked to build a decentralized smart road stud blockchain networking system. Dynamic traffic scene construction module: used by the blockchain networking system to collect the perception data uploaded by each smart road beacon, construct a dynamic traffic scene model, and realize the real-time dynamic replication of the road traffic environment; Traffic guidance and early warning module: Based on the dynamic traffic scenario model, it predicts traffic operation trend parameters through a preset algorithm, combines the traffic operation trend parameters, performs dynamic driving decisions and traffic adaptive control for the target vehicle, and generates and pushes corresponding level early warning information according to the preset safety level classification standard.

Images