Vehicle safety early warning method and system for highway network

Abstract

The invention provides a vehicle safety early warning method and system for a highway network, relates to the field of traffic safety management and control, and solves the technical problem of inaccurate early warning in the prior art. The method comprises the following steps: acquiring environment data of a highway; dividing the expressway into a plurality of areas, and calculating an initial risk value of each area according to the environment data; calculating a risk propagation value of each region based on a dynamic risk propagation equation according to the initial risk value, and determining a risk level of each region according to the risk propagation value; and triggering early warning measures of each area according to the risk level. The method is used in the real-time safety management and control process of the highway network in severe weather, accurate prediction and graded early warning of risks can be realized through multi-dimensional data fusion and dynamic risk propagation modeling, and the safety and traffic efficiency of the highway network under complex meteorological conditions are improved.

Description

Technical Field

[0001] The present invention belongs to the field of traffic control, and specifically relates to a vehicle safety early warning method and system for a highway network. Background Art

[0002] In the field of highway operations and management, severe weather poses a severe challenge to driving safety and smooth road operations. Currently, domestic safety warning methods for inclement weather conditions suffer from significant flaws: they primarily rely on manual automatic identification of road conditions and data collection from meteorological monitoring equipment, followed by manual operation to issue warnings. This process is severely constrained by various objective conditions. Firstly, the complex manual processing steps and lengthy information transmission links make it difficult for warning information to reach drivers and passengers in a timely manner, resulting in significant lags and preventing drivers and passengers from grasping rapidly changing road conditions in real time. Secondly, inclement weather causes a sharp decrease in road adhesion and severely obstructs vision. Even if drivers maintain standard driving procedures, vehicles are prone to lane deviation or even loss of control, greatly increasing the risk of accidents.

[0003] Existing vehicle safety warning systems for severe weather conditions typically use a static threshold warning method, which often predicts the current warning level by modeling and processing multi-source data. However, in highway networks, the risk situation in the previous area will spread through traffic flow and have a superimposed impact on subsequent areas. For example, if the friction coefficient of the road surface in an upstream section drops sharply due to heavy rain, the braking distance will be extended when the traffic passes through this area, and the risk will be transmitted downstream with the traffic flow, forming a chain reaction. Therefore, existing technologies have the problem of inaccurate warnings and the disconnection between warning results and actual risk situations. Summary of the Invention

[0004] The present application provides a vehicle safety warning method and system for a highway network, which solves the technical problem of inaccurate warning in the prior art.

[0005] To achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a vehicle safety warning method for a highway network is provided, comprising:

[0007] Collect environmental data of highways, including meteorological data, traffic condition data and road surface status data;

[0008] Divide the highway into several areas, and calculate the initial risk value of each area according to the environmental data;

[0009] Calculate the risk propagation value of each region based on the dynamic risk propagation equation according to the initial risk value;

[0010] determining a risk level for each area based on the risk propagation value;

[0011] Early warning measures are triggered for each area based on the risk level; the early warning measures include light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage, and visual early warning information on information boards.

[0012] Based on the above technical solution, in a vehicle safety warning method for highway networks provided in this application, by collecting multi-dimensional environmental data such as meteorological, traffic conditions, and road conditions, the initial risk value of each area of ​​the highway is calculated, and the road network risk is analyzed in a refined and targeted manner; and the risk propagation value is derived with the help of the dynamic risk propagation equation, fully considering the characteristics of the dynamic diffusion and transmission of risks in the road network with factors such as traffic flow, so that the risk assessment is more in line with the actual traffic flow operation rules. According to the risk propagation value, the risk level is determined and the corresponding warning measures are triggered. From light strip prompts, broadcast notifications to speed limit adjustments, a multi-level, multi-means warning system is constructed, which can intervene in a timely and precise manner according to different risk levels, effectively improve the driving safety of the highway network, reduce the probability of accidents, ensure efficient and orderly traffic operation, and provide technical support for vehicle escort.

[0013] In combination with the first aspect above, in a possible implementation, the meteorological data includes: temperature, humidity, visibility, precipitation, wind speed, and wind direction;

[0014] The traffic condition data includes: average vehicle speed, traffic density, and cross-sectional flow.

[0015] The road surface condition data includes: road surface friction coefficient.

[0016] In combination with the first aspect above, in a possible implementation, the calculation formula of the initial risk value is: Among them, the V i represents the average vehicle speed in area i, V max represents the highway design speed limit, μ i represents the road friction coefficient of area i, μ0 represents the friction coefficient safety threshold, ρ i represents the traffic density in area i, ρ th represents the traffic density threshold, W i represents the comprehensive meteorological index of region i, W th Indicates the meteorological risk threshold.

[0017] In combination with the first aspect above, in a possible implementation, the calculation formula of the comprehensive meteorological index is: Among them, W i represents the comprehensive meteorological index of region i, w k Represents the weight coefficients of each item, and the sum is 1, f k Represents the normalized function of each element in the meteorological data, X k Represents the various elements in the meteorological data, Xkref Indicates the safety thresholds of various elements in the meteorological data, including:

[0018] Temperature factor: f1(T,T ref )=1-|TT ref | / ΔT max ; T represents temperature, T ref Indicates the temperature safety threshold, ΔT max Indicates the maximum temperature change;

[0019] Humidity factor: f2(H,H ref )=H / H ref ; H represents temperature, H ref Indicates the temperature safety threshold;

[0020] Visibility factor: f3(V,V ref )=1-V s / V ref ; V s Indicates visibility, V ref Indicates the visibility safety threshold;

[0021] Precipitation factor: f4(R,R ref )=R / R ref ; R represents precipitation, R ref Indicates the precipitation safety threshold;

[0022] Wind speed factor: f5(v,v vef )=v / v vef ; v represents wind speed, v ref Indicates the wind speed safety threshold;

[0023] Wind direction factor: f6(θ)=cos(θ / 2); θ represents wind direction.

[0024] In combination with the first aspect above, in a possible implementation, the dynamic risk propagation equation is:

[0025]

[0026] Among them, R i (t) represents the initial risk value of region i at time t, R j (t) represents the initial risk value of region j at time t, Ω i represents the upstream node set of region i, Q ji represents the cross-sectional flow from area j to area i, Q max Indicates the maximum cross-sectional flow rate, d ji represents the distance between region j and region i, λ represents the risk diffusion coefficient, and Δt represents the time interval.

[0027] In combination with the first aspect above, in one possible implementation, the cross-sectional flow rate represents the number of vehicles entering the sub-area per unit time, and the cross-sectional flow rate is obtained by:

[0028] If the sub-area includes an electronic toll collection system (ETC), the number of vehicles entering the sub-area per unit time is counted using the license plate recognition technology of the ETC gantry system.

[0029] If the sub-area contains a surveillance camera, the number of vehicles entering the sub-area per unit time is counted using video image recognition technology;

[0030] If the sub-area includes a microwave radar or a laser detector, the microwave radar or the laser detector is used to count the number of vehicles entering the sub-area per unit time.

[0031] In combination with the first aspect above, in one possible implementation, the upstream node set represents a set consisting of all areas directly connected to area i and located upstream of area i, guided by the direction of traffic flow. The traffic path is determined by the Dijkstra algorithm to obtain the node affiliation; the traffic path represents the optimal route for a vehicle from a downstream node to an upstream node.

[0032] In conjunction with the first aspect above, in one possible implementation, determining the risk level of each area according to the risk propagation value includes:

[0033] If the risk propagation value is greater than or equal to the first threshold and less than the second threshold, it is marked as a level one risk;

[0034] If the risk propagation value is greater than or equal to the second threshold and less than the third threshold, it is marked as a level 2 risk;

[0035] If the risk propagation threshold is greater than or equal to the third threshold, it is marked as a level 3 risk;

[0036] Here, 0<first threshold<second threshold<third threshold<1.

[0037] In conjunction with the first aspect above, in one possible implementation, triggering early warning measures for each area based on the risk level includes:

[0038] The warning measures for level 1 risk are: triggering a yellow light, starting a broadcast notification of level 1 risk, and adjusting the speed limit to the first speed;

[0039] The warning measures for level 2 risk are: triggering orange lights, initiating a broadcast notification of level 2 risk, adjusting the speed limit to the second speed, and triggering a fog light linkage response;

[0040] The warning measures for level 3 risk are: triggering red lights, starting broadcast notification of level 3 risk, and adjusting the speed limit to the third speed;

[0041] Among them, the first speed>the second speed>the third speed.

[0042] In a second aspect, the present application provides a vehicle safety warning system for a highway network, comprising: a data acquisition module, a risk assessment module, and a warning execution module; wherein,

[0043] The data acquisition module is used to collect highway meteorological data, traffic condition data and road surface status data to obtain environmental data;

[0044] The risk assessment module is used to divide the highway into several areas and calculate the initial risk value of each area based on the environmental data;

[0045] And calculate the risk propagation value of each area based on the dynamic risk propagation equation according to the initial risk value;

[0046] The early warning execution module is used to determine the risk level of each area according to the risk propagation value;

[0047] Early warning measures are triggered for each area based on the risk level; the early warning measures include light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage, and visual early warning information on information boards.

[0048] In a third aspect, a vehicle safety warning device for a highway network is provided, comprising: a communication unit and a processing unit;

[0049] The communication unit is used to receive environmental data, including highway weather data, traffic condition data, and road surface status data, and to send warning instructions to the light strip, broadcast system, and information board;

[0050] The processing unit is used to divide the highway into several areas, calculate the initial risk value of each area according to environmental data, calculate the risk propagation value based on the dynamic risk propagation equation, determine the risk level and trigger corresponding early warning measures.

[0051] In a fourth aspect, the present application provides a vehicle safety warning device for a highway network, comprising: a processor and a storage medium; the storage medium comprising instructions, the processor configured to execute the instructions to implement the method described in the first aspect and any possible implementation of the first aspect. The vehicle safety warning device for a highway network may be an electronic device or a chip within an electronic device.

[0052] In the fifth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are run on a vehicle safety warning device of a highway network, the vehicle safety warning device of the highway network executes the method described in the first aspect and any possible implementation of the first aspect.

[0053] In the sixth aspect, the present application provides a computer program product comprising instructions, which, when run on a vehicle safety warning device of a highway network, enables the vehicle safety warning device of the highway network to execute the method described in the first aspect and any possible implementation of the first aspect.

[0054] The present application provides a vehicle safety warning method and system for a highway network, which can realize comprehensive monitoring of the weather, traffic conditions and road conditions of the highway through multi-dimensional environmental data collection; using the dynamic risk propagation equation and nonlinear initial risk calculation model, fully integrating parameters such as traffic density, road friction coefficient, and comprehensive meteorological index, accurately depicting the dynamic diffusion law of risks in the road network, breaking through the limitations of traditional static warning. By dividing the upstream node set through the Dijkstra algorithm, the risk propagation path is more in line with the actual traffic direction, and the spatiotemporal dynamics of risk assessment is improved. Based on the three-level risk level division and the corresponding multi-level warning measures such as light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage, and information board visualization, precise intervention of different risk levels is achieved, effectively reducing the probability of accidents caused by bad weather and traffic anomalies, and ensuring driving safety and traffic efficiency of the highway network.

[0055] It should be understood that the description of technical features, technical solutions, beneficial effects or similar language in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution or beneficial effect is included in at least one embodiment. Therefore, the description of a technical feature, technical solution or beneficial effect in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in the present embodiment can also be combined in any appropriate manner. Those skilled in the art will understand that the embodiment can be implemented without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 A system architecture diagram of a vehicle safety warning system for a highway network provided in an embodiment of the present application;

[0058] Figure 2 A flowchart of a vehicle safety warning method for a highway network provided in an embodiment of the present application;

[0059] Figure 3 A flowchart of another vehicle safety warning method for a highway network provided in an embodiment of the present application;

[0060] Figure 4 A flowchart of another vehicle safety warning method for a highway network provided in an embodiment of the present application;

[0061] Figure 5 A schematic diagram of the structure of a vehicle safety warning device for a highway network provided in an embodiment of the present application;

[0062] Figure 6 A schematic diagram of the hardware structure of a vehicle safety warning device for a highway network provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In the description of this application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "a plurality" means two or more. Words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not limit them to be necessarily different.

[0064] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0065] The vehicle safety warning method for a highway network provided in the embodiment of the present application can be applied to Figure 1 In a vehicle safety warning system for a highway network, as shown in FIG. Figure 1 As shown, the communication system includes: a data acquisition module, a risk assessment module, and an early warning execution module; wherein, Data acquisition module, used to collect highway meteorological data, traffic condition data and road surface status data to obtain environmental data; The risk assessment module is used to divide the highway into several areas and calculate the initial risk value of each area based on environmental data; And calculate the risk propagation value of each area based on the dynamic risk propagation equation according to the initial risk value; The early warning execution module is used to determine the risk level of each area based on the risk propagation value; Early warning measures are triggered in each area based on the risk level; these measures include light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage, and visual warning information on information boards.

[0066] Data acquisition module, used to collect highway meteorological data, traffic condition data and road surface status data to obtain environmental data;

[0067] The risk assessment module is used to divide the highway into several areas and calculate the initial risk value of each area based on environmental data;

[0068] And calculate the risk propagation value of each area based on the dynamic risk propagation equation according to the initial risk value;

[0069] The early warning execution module is used to determine the risk level of each area based on the risk propagation value;

[0070] Early warning measures are triggered in each area based on the risk level; these measures include light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage, and visual warning information on information boards.

[0071] To address the technical problems of inaccurate risk warnings and lack of risk diffusion mechanisms in the prior art, an embodiment of the present application provides a vehicle safety warning method for a highway network, the method comprising: collecting environmental data of the highway, including meteorological data, traffic condition data, and road surface condition data;

[0072] Divide the highway into several areas and calculate the initial risk value of each area based on environmental data;

[0073] Calculate the risk propagation value of each region based on the dynamic risk propagation equation according to the initial risk value;

[0074] Determine the risk level of each area based on the risk propagation value;

[0075] Early warning measures are triggered in each area based on the risk level; these measures include light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage, and visual warning information on information boards.

[0076] Based on this, through multi-dimensional data fusion and dynamic risk propagation modeling, we have achieved spatiotemporal dynamic assessment and accurate early warning of highway network risks.

[0077] like Figure 2 As shown, an embodiment of the present application provides a vehicle safety warning method for a highway network, comprising:

[0078] S1. Collect environmental data of highways, including meteorological data, traffic condition data and road surface status data.

[0079] Meteorological data include but are not limited to: temperature, humidity, visibility, precipitation, wind speed, and wind direction;

[0080] Traffic condition data include but are not limited to: average vehicle speed, traffic density, and cross-sectional flow;

[0081] Road surface condition data includes but is not limited to: road surface friction coefficient and road surface temperature.

[0082] In some implementations, meteorological data can be collected by deploying traffic weather stations and millimeter-wave radars, traffic condition data can be collected through ETC gantry systems and microwave radars, and road surface condition data can be collected through embedded sensors and infrared temperature measurement equipment.

[0083] S2. Divide the highway into several areas and calculate the initial risk value of each area based on environmental data.

[0084] Among them, the initial risk value is a basic risk indicator calculated based on the region’s own real-time environmental data. It reflects the independent risk level of the region without considering the impact of adjacent areas, and is used to directly reflect the current accident hazards in the region.

[0085] In some implementations, a nonlinear coupling mathematical model can be constructed to integrate traffic flow parameters and meteorological factors to obtain a calculation formula for the initial risk value. Alternatively, a neural network algorithm can be used to train a model using historical accident data and real-time monitored environmental data to predict the initial risk values ​​at different locations.

[0086] It should be pointed out that the division of expressways can be carried out according to fixed mileage or dynamic traffic flow characteristics through the Geographic Information System (GIS); for example, every 5 kilometers can be used as a basic unit, or the regional boundaries can be adaptively adjusted according to the sudden change points of traffic density.

[0087] S3. Calculate the risk propagation value of each region based on the dynamic risk propagation equation according to the initial risk value.

[0088] The risk propagation value is calculated based on the dynamic risk propagation equation to determine the impact of risk diffusion in adjacent regions. It reflects the superimposed effect of upstream regional risk on the current region through traffic flow. Its core logic includes:

[0089] The risk of upstream nodes spreads to the mid- and downstream areas through traffic flow;

[0090] The longer the distance and the smaller the cross-sectional flow, the weaker the impact of risk transmission;

[0091] Updated at time intervals to reflect the real-time spread of risks.

[0092] In some implementations, the dynamic risk equation can be constructed by abstracting the highway network into a directed graph model and combining the traffic direction and distance attenuation characteristics.

[0093] For example, when congestion occurs in the upstream area, the risk will spread downstream with the traffic flow. Even if the current downstream condition is good, the overall risk level will be increased due to the impact of the upstream.

[0094] S4. Trigger early warning measures for each area based on the risk propagation value.

[0095] Among them, the risk propagation threshold can be mapped to the risk level through threshold division, and then the warning measures corresponding to each risk level can be set to send warning information.

[0096] In some implementations, the risk level threshold can be dynamically adjusted in combination with historical accident data and expert experience to adapt to the risk characteristics of different road sections.

[0097] It's important to note that the triggering logic for early warning measures supports multiple linkage conditions, such as considering both the risk level and the risk change rate. For example, if the risk level in an area is Level 2 (corresponding to an orange alert), but the risk change rate exceeds a preset threshold (e.g., a risk value increase of ≥0.1 per minute), the system will automatically raise the alert level to Level 3, triggering a red light warning, adjusting the speed limit to 60 km / h, and simultaneously activating the fog light linkage and the "Emergency Speed ​​Reduction" visual prompt on the information board to respond to the rapidly deteriorating risk situation.

[0098] Based on the above technical solution, the highway network vehicle safety warning method provided in this application has achieved a leap from local risk monitoring to global risk prevention and control of the road network, providing an intelligent solution for driving safety in severe weather and complex traffic flow scenarios.

[0099] In a possible implementation of the embodiment of the present application, the above S1 can be specifically implemented by the following S101, S102 and S103, which are specifically described below:

[0100] S101. Divide the expressway into sections.

[0101] The division of expressway sections can be achieved by combining fixed distances with a GIS platform: the expressway is divided into a basic sub-area every 5 kilometers (preset distance, which can also be preset to other values ​​based on actual conditions) through the GIS platform. In special sections such as bridges and tunnels, the distance is shortened to 2 kilometers / area according to the actual terrain to ensure the homogeneity of environmental data within each sub-area.

[0102] S102. Build a multi-source data acquisition network.

[0103] The equipment deployment method of the multi-source data acquisition network is as follows:

[0104] Meteorological data collection equipment: A small weather station is deployed in each sub-area, integrating temperature, humidity, visibility, precipitation, wind speed and direction sensors, with a sampling frequency of 1 time per minute;

[0105] Traffic condition collection equipment: Utilize the existing video surveillance system within the sub-area to collect traffic condition data. Deploy a small edge computing device within each video surveillance camera to collect real-time statistics on cross-sectional traffic flow, calculate average speed, traffic density, and other information. In sub-areas without video surveillance, install lidar on both sides of the road to monitor real-time traffic conditions.

[0106] Road surface condition acquisition equipment: A set of distributed friction coefficient sensors is embedded in the emergency lane of each sub-area, and infrared temperature sensors are simultaneously deployed on the road shoulders.

[0107] In some implementations, a "fixed + mobile" hybrid deployment can also be used: when equipment in a sub-area fails, patrol cars equipped with weather stations and lidars are dispatched for temporary re-collection to ensure data continuity.

[0108] S103. Collect multi-source data.

[0109] The specific types and collection methods of multi-source data are as follows:

[0110] Meteorological data: including temperature, humidity, visibility, precipitation, wind speed, wind direction, etc., collected in real time through weather station sensors;

[0111] Traffic condition data: including average vehicle speed, traffic density, and cross-sectional flow, all obtained through traffic condition collection equipment. Traffic density represents the number of vehicles distributed on a unit length of highway, and cross-sectional flow represents the number of vehicles entering a sub-area per unit time. Unit time and unit length can be set according to actual conditions, for example, 10 minutes as a unit time and 1 km as a unit length.

[0112] Take cross-sectional flow as an example:

[0113] If the sub-area includes an electronic toll collection system (ETC), the license plate recognition technology of the ETC gantry system can be used to count the number of vehicles entering the sub-area within a unit time;

[0114] If the sub-area contains a surveillance camera, the number of vehicles entering the sub-area per unit time is counted using video image recognition technology;

[0115] If the sub-area includes a microwave radar or a laser detector, the microwave radar or the laser detector is used to count the number of vehicles entering the sub-area per unit time.

[0116] Road surface condition data: The road surface friction coefficient is measured by an embedded sensor in each sub-area (sampling frequency 10 Hz), and the road surface temperature can be obtained by an infrared sensor.

[0117] It should be pointed out that when a certain type of data is missing, a data interpolation mechanism can be used: for example, when the visibility detector fails, resulting in missing visibility data, an alternative value can be predicted based on the humidity and temperature data through a machine learning model (such as LSTM).

[0118] Based on the above technical solution, the refined collection of highway network environmental data is achieved, providing standardized data input for subsequent initial risk value calculation and dynamic risk propagation analysis, ensuring that the risk assessment results are highly consistent with the actual traffic operation status.

[0119] In a possible implementation of the embodiment of the present application, combined with Figure 2 ,like Figure 3 As shown, the above S2 can be specifically implemented through the following S201 and S202, which are specifically described below:

[0120] S201 : Calculate multi-dimensional parameters of sub-region i based on collected environmental data.

[0121] Traffic parameters: The average vehicle speed V is obtained by collecting equipment based on traffic conditions i and traffic density ρ i ;

[0122] Road surface parameters: Obtain road surface friction coefficient μ through embedded sensors i ;

[0123] Meteorological parameters: using the formula of the comprehensive meteorological index Calculate, where W i represents the comprehensive meteorological index of region i, w k Represents the weight coefficients of each item, and the sum is 1, f k Represents the normalized function of each element in the meteorological data, X k Represents the various elements in the meteorological data, X kref Indicates the safety thresholds of various elements in the meteorological data, including:

[0124] Temperature factor: f1(T,T ref )=1-|TT ref | / ΔT max ; T represents temperature, T ref Indicates the temperature safety threshold, ΔT max Indicates the maximum temperature change;

[0125] Humidity factor: f2(H,H ref )=H / Href ; H represents temperature, H ref Indicates the temperature safety threshold;

[0126] Visibility factor: f3(V,V ref )=1-V s / V ref ; V s Indicates visibility, V ref Indicates the visibility safety threshold;

[0127] Precipitation factor: f4(R,R ref )=R / R ref ; R represents precipitation, R ref Indicates the precipitation safety threshold;

[0128] Wind speed factor: f5(v,v vef )=v / v vef ; v represents wind speed, v ref Indicates the wind speed safety threshold;

[0129] Wind direction factor: f6(θ)=cos(θ / 2); θ represents wind direction.

[0130] It should be noted that in the calculation formula of the comprehensive meteorological index, the weight coefficients w k and safety threshold X kref The specific determination method can be as follows:

[0131] The weight coefficient can be determined by the expert scoring method, specifically: construct a judgment matrix of meteorological factors through expert scoring, and calculate the relative importance of each factor to the accident risk. For example, compare the factors such as temperature and visibility according to their influence, form a matrix, solve the eigenvector, and normalize it to obtain the weight w k ,make sure

[0132] The weight can also be calculated based on the information entropy of historical meteorological data:

[0133] For the kth meteorological element X k , calculate its information entropy based on historical data Among them, p ki is the number X in the i-th sample k The proportion of standardized values;

[0134] Then calculate the weight coefficient according to the normalization formula: Give higher weights to factors with greater data variability.

[0135] The safety threshold can be determined by constructing different weather scenarios through traffic simulators and collecting vehicle handling stability data. For example, in a slippery road scenario, the critical value R of the vehicle braking distance as it changes with R is tested. ref ; Threshold value v for wind speed v ref This can be determined by simulating experiments on the effect of crosswinds on the stability of large vehicles.

[0136] It can also be obtained by analyzing the correlation between historical meteorological data and accident records to determine the critical value that triggers a sudden change in risk. For example, by fitting a curve between accident rate and visibility, determining the inflection point of the fitted curve and determining the value at which the accident rate significantly increases when visibility falls below a certain value, the visibility safety threshold is obtained;

[0137] The temperature safety threshold can be determined by combining the road surface icing temperature and the road surface temperature at the time of high-temperature tire blowout with the fitting curve of the accident rate.

[0138] S202. Calculate the initial risk value based on the nonlinear model and multi-dimensional parameters.

[0139] Among them, the initial risk value calculation formula Quantifying risks in environmental data:

[0140] When the traffic density ρ i Exceeding the threshold ρ th When the index term Amplify risk contribution;

[0141] When the comprehensive meteorological index W i More than W th When , through the Sigmoid function Reflects the sudden change effect of meteorological risks.

[0142] Similarly, the threshold value in the initial risk value calculation formula can also be obtained through simulation experiment calibration method, specifically:

[0143] (1) Experimental preparation

[0144] A joint simulation platform based on PreScan (a multi-physics field simulation platform) and Simulink (a visual simulation tool in MATLAB launched by Mathworks, an American company) was used to build a three-dimensional digital twin model of the target expressway section, including road geometry parameters (such as curvature and slope), traffic facilities (such as ETC gantries and surveillance cameras) and meteorological simulation modules (adjustable parameters such as temperature, humidity, and visibility).

[0145] Vehicle braking stability coefficient (where R is the curve radius and g is the acceleration due to gravity) and the accident rate P are used as core indicators for risk assessment. When P suddenly increases, it is determined to be a critical risk state.

[0146] (2) Traffic density threshold ρ th Calibration.

[0147] Set different traffic density ρ in the simulation section i (Range: 10-80 vehicles / km), maintain weather conditions of normal temperature (25°C), dry (humidity 60%), good visibility (1000 meters), test vehicle at the design speed limit V max Driving.

[0148] Record different ρ i The following distance, braking distance and K value of the vehicle under the given conditions are used to draw the K-\rhoi curve.

[0149] When the curve has an inflection point (such as K increases with ρ i When the growth rate increases exponentially, the corresponding ρ i This is the traffic density threshold ρ in the initial risk value calculation formula th For example, experiments show that when ρ i = 35 vehicles / km, the average following distance of vehicles is less than the safe braking distance, and the accident rate P increases by 2 times. Therefore, ρ is determined th =35 vehicles / km.

[0150] (3) Meteorological risk threshold W th Calibration.

[0151] By adjusting 6 types of meteorological parameters such as temperature, humidity, and visibility, the corresponding comprehensive meteorological index is calculated.

[0152] Set up the following typical weather scenario:

[0153] Fog: Visibility V s =50-200 meters, temperature T = 5-10 ° C, humidity H = 90-100%;

[0154] Heavy rain: precipitation R = 30-100 mm / hour, wind speed v = 10-20 m / s.

[0155] Record different W i The K value and accident rate P under the sigmoid function Fitting curve, when P exceeds the acceptable risk level (such as P = 0.05), the corresponding W i That is W th .

[0156] (4) Calibration of the friction coefficient safety threshold μ0.

[0157] Set different road friction coefficients μ in the simulation system i(Range: 0.2-0.8), corresponding to dry, wet, icy and other road conditions, the vehicle at different speeds v i Drive and perform emergency braking.

[0158] Record braking distance When S exceeds the designed safe braking distance S0 (e.g. 100 km / h corresponds to S0 = 50 m), the corresponding μ i That is μ0.

[0159] For example, experiments show that μ0 = 0.7 for dry roads, μ0 = 0.4 for wet roads, and μ0 = 0.2 for icy roads. The minimum value μ0 = 0.2 is taken as the unified safety threshold.

[0160] In some implementations, a region importance weight α is introduced i (such as tunnel area α i =1.2), and the model is modified to: Improve risk sensitivity of key road sections.

[0161] Based on the above technical solution, through the parameter fusion and nonlinear modeling of multi-dimensional environmental data, the basic risk status of the highway network is accurately portrayed, and a refined assessment of the initial risk of the highway network is achieved.

[0162] In a possible implementation of the embodiment of the present application, combined with Figure 2 ,like Figure 3 As shown, the above S3 can be specifically implemented through the following S301, S302 and S303, which are specifically described below:

[0163] S301. Construct a dynamic risk propagation equation.

[0164] The dynamic risk propagation equation is:

[0165] The following parameters need to be determined in advance:

[0166] Upstream node set Ω i : Guided by the traffic direction, the Dijkstra algorithm is used to determine the optimal upstream path of area i and extract the set of directly connected upstream areas.

[0167] Cross-sectional flow rate Q ji : The number of vehicles entering sub-area j from sub-area i per unit time through ETC gantry license plate recognition, surveillance camera video analysis, or microwave radar detection. For example, the cross-sectional flow rate of a certain area obtained through ETC statistics is 800 vehicles / hour.

[0168] Risk diffusion coefficient λ: It is set according to the type of road section (e.g., 0.5 for mountain curves and 0.3 for plain sections based on experience), reflecting the rate at which risk decays with distance.

[0169] In some implementations, λ can be optimized by inverting historical accident data, for example, by using the maximum likelihood estimation method to fit the relationship between the accident rate and the risk propagation value, and dynamically adjusting λ to minimize the model error.

[0170] It should be pointed out that the upstream node set needs to be updated in real time. When the traffic path changes due to congestion or construction, the Dijkstra algorithm needs to be rerun to correct the subordination relationship.

[0171] In some implementations, the specific steps of determining the traffic path using the Dijkstra algorithm to obtain the node affiliation are as follows:

[0172] First, build a graph model of the highway network:

[0173] Each area of ​​the highway is divided into nodes V of a directed graph, and the road segments between adjacent areas are defined as directed edges E, where the direction of the edge represents the direction of traffic flow. For example, the directed edge e from area i to area j is ij Indicates that traffic can flow from i to j.

[0174] The weight of the edge w(e ij ) can be based on the road segment distance d ij , travel time or real-time traffic conditions (such as traffic density, average speed). For example, the cross-sectional flow Q ji It can indirectly reflect the degree of congestion on the road section. The greater the flow, the higher the weight, which reflects the resistance to risk diffusion. Therefore, the edge weight can be calculated using the weight calculation formula related to the end panel flow. For example, the calculation function of the edge weight can be: Among them, α and β are empirical parameters, and the default values ​​are α=0.6, β=0.4, Q max Design capacity for road segments.

[0175] Then perform Dijkstra's algorithm:

[0176] Select target area i as the end point, set the initial distance of all nodes to infinity, and the distance of end point i to 0;

[0177] Establish a priority queue to sort the nodes to be processed by distance.

[0178] Perform iterative optimization: take the node u with the smallest distance from the queue and traverse all its outgoing edges e uv (Outflow direction of traffic); if the distance from u to the adjacent node v is dist[u]+w(e uv ) is less than the current distance of v, update dist[v] and record u as the predecessor node of v.

[0179] After the algorithm terminates, it traces back to the predecessor node from each node to obtain the optimal path set from the starting point to the target area i, that is, the shortest path of the traffic flow from the upstream node to i.

[0180] Then determine the subordinate relationship between each node:

[0181] Taking the target area i as the end point, all nodes on the optimal path and directly connected to i constitute the upstream node set Ω i For example, if the optimal path is j->k->i, then k is the direct upstream node of i, and j is the upstream node of k. The directly connected upstream areas need to be screened based on the traffic direction.

[0182] It's important to note that when traffic conditions change (such as congestion or construction), the algorithm is rerun to update the upstream node set by updating edge weights in real time (for example, adjusting travel time on a road section based on real-time traffic density). For example, if a road section is congested due to an accident, causing the edge weight to increase, the algorithm will replan the optimal path and adjust the dependencies.

[0183] S302. Calculate the risk propagation value based on the dynamic risk propagation equation.

[0184] The iterative calculation is performed at a time interval Δt (e.g., 5 minutes). The specific steps are:

[0185] 1. Initial risk input: The initial risk value R of region i and upstream nodes i (t), R j Substitute (t) into the equation;

[0186] 2. Weight calculation: according to the cross-sectional flow Q ji and maximum cross-sectional flow Q max The ratio of and distance attenuation factor Calculate the propagation weight of upstream risks;

[0187] 3. Risk superposition: The difference between the upstream regional risk and the current regional risk is weighted and superimposed on the current risk to obtain R p (i,t).

[0188] It should be pointed out that when the upstream area risk R j (t) is less than the current regional risk R i (t), the risk propagation term R j (t)-R i (t) is a negative value, which means that the current regional risk is attenuated upstream, reflecting the bidirectional nature of risk transmission.

[0189] For example, the initial risk value R of region i is i (t) = 0.4, R of upstream region j j (t) = 0.6, Qji / Q max =0.8, Δt=0.1h, then the risk transmission value R p (i,t)=0.4+0.8×0.449×(0.6×0.4)×0.1=0.407.

[0190] It should be pointed out that the risk diffusion coefficient λ needs to be calibrated regularly, for example, the parameters should be updated every quarter according to seasonal changes (such as snowy weather in winter increasing λ).

[0191] Based on the above technical solution, a spatiotemporal dynamic simulation of highway network risk propagation is realized, allowing risk assessment to fully consider the risk diffusion characteristics driven by traffic flow. Compared with the traditional static assessment model, it can improve the accuracy of accident prediction and provide a scientific basis for the precise triggering of multi-level early warning measures.

[0192] In a possible implementation of the embodiment of the present application, combined with Figure 2 ,like Figure 3 As shown, the above S4 "triggering early warning measures for each area according to the risk propagation value" can be specifically implemented through the following S401, S402 and S403, which are specifically explained below:

[0193] S401. Classify risk levels based on risk propagation values.

[0194] Risk levels are divided into three levels:

[0195] If the risk transmission value R p Satisfy the first threshold ≤ R p < the second threshold, marked as level one risk;

[0196] If the second threshold ≤ R p < the third threshold, marked as level 2 risk;

[0197] If R is satisfied p ≥ the third threshold, marked as level three risk, and 0<first threshold<second threshold<third threshold<1.

[0198] It should be noted that the specific values ​​of the three thresholds can be divided according to empirical values, for example, the first threshold = 0.4, the second threshold = 0.6, and the third threshold = 0.85.

[0199] S402. Establish a mapping relationship between risk levels and early warning measures.

[0200] Different risk levels correspond to differentiated early warning measures:

[0201] Level 1 risk: The light strip turns on yellow, a broadcast notification of level 1 risk is given, and the speed limit is adjusted to the first speed.

[0202] Level 2 risk: The light strip turns on orange, a broadcast notification of the level 2 risk is given, the speed limit is adjusted to the second speed, and the fog lights are activated;

[0203] Level 3 risk: The light strip is triggered to turn on red, a Level 3 risk notification is broadcast, and the speed limit is adjusted to the third speed, with the first speed > the second speed > the third speed.

[0204] It should be noted that the preset speed can be determined through experimental simulation or experience. For example, the effect of different speed limits on the accident rate can be tested in a simulated cockpit. For example, if the risk propagation value of the current environmental data is at the critical value between level 2 and level 3 risk, and reducing the speed limit from 120 km / h to 80 km / h can reduce the accident rate by 40%, then the speed limit for level 2 risk will be determined to be 80 km / h.

[0205] It should be pointed out that early warning measures can be combined with information board prompts. For example, when it is determined to be the first risk, the information board will display "The current road section is smooth, please pay attention to keep a safe distance"; in the second risk case, it will prompt "There are potential risks in the road section ahead, it is recommended to slow down and drive carefully"; in the third risk case, it will warn "The risk ahead is high, the intervention strategy has been activated, please strictly follow the guidance and do not brake suddenly to change lanes." Through differentiated text reminders, drivers can be assisted to respond to different road conditions in a targeted manner and improve driving safety on the highway network.

[0206] For example, the speed limit for level one risk is 100km / h, the speed limit for level two risk is 80km / h, and the speed limit for level three risk is 60km / h. When a level two risk is triggered in a certain area, the orange lights, broadcasts, and fog lights are activated at the same time.

[0207] S403. Execute early warning measures in real time.

[0208] Among them, early warning measures are implemented through the following steps:

[0209] 1. Instruction generation: Generate control instructions (including light strip color coding, speed limit value, and information board content) based on risk level;

[0210] 2. Multi-device collaboration: Send instructions to light strips, broadcasting systems, and information boards through the communication unit.

[0211] Based on the above technical solution, the entire process from risk assessment to early warning intervention has been automated. Compared with traditional fixed threshold early warning, it can improve the accuracy of accident rate prediction and provide a quantifiable and iterative technical solution for active safety management and control of highway networks.

[0212] In addition, in the embodiments of the present application, digital twin technology can be combined to achieve real-time warning of vehicle safety in highway networks. Specifically, by constructing a digital twin of the highway network, the environmental data and traffic flow characteristics of the physical road network are deeply integrated with the virtual simulation model to form a closed-loop system of "data-driven virtual mapping real-time warning". The specific construction methods may include:

[0213] (1) Build a digital twin model of the highway network.

[0214] 1. 3D road network modeling

[0215] Using a GIS platform and BIM technology, high-precision 3D modeling of highways is performed, including road geometry parameters (such as curvature and slope), infrastructure (bridges, tunnels, toll booths), and environmental elements (vegetation and terrain), achieving a 1:1 virtual mapping of the physical road network. For example, sub-areas defined in the document (such as every 5-kilometer road section) are mapped as independent units in the virtual model, facilitating subsequent risk area delineation.

[0216] 2. Vehicle dynamic entity modeling

[0217] A digital twin is created for each passing vehicle, integrating on-board OBU (On Board Unit) data, including speed, location, driving trajectory, and traffic condition data (average speed, traffic density), and synchronizing the status of the virtual vehicle and the physical vehicle through a real-time communication protocol.

[0218] (2) Multi-source data of real-time twin models.

[0219] 1. Data Fusion Architecture

[0220] Build edge computing nodes and access environmental data in real time:

[0221] Collect meteorological data through traffic weather stations and synchronize it to the meteorological module of the virtual model to drive weather simulation in the virtual environment;

[0222] Data such as the road surface friction coefficient and traffic density are collected through embedded sensors and microwave radars, and mapped into the anti-skid performance parameters and traffic flow status of the virtual road surface.

[0223] 2. Dynamic Risk Propagation Simulation

[0224] Dynamic risk propagation equation in digital twin, based on upstream node set Ω i and cross-sectional flow Q ji , real-time simulation of the risk diffusion process in the virtual road network. For example, when a sudden fog occurs in a certain area, the digital twin model automatically calculates the risk propagation path and impact range upstream and downstream.

[0225] (3) Risk assessment and early warning linkage based on twin models.

[0226] 1. Virtual risk simulation

[0227] By using digital twins to simulate risk evolution under different meteorological conditions (such as heavy rain, ice and snow) and traffic scenarios (congestion, accidents), we can optimize the setting of risk level thresholds. For example, when using historical accident data to train the twin model, if the risk propagation value is greater than 0.7 when the actual accident probability is greater than 5%, the third-level risk threshold is determined to be 0.7.

[0228] 2. Visual linkage of early warning measures

[0229] Map early warning measures to the digital twin interface, including:

[0230] Level 1 risk triggers the yellow light in the virtual road network to flash, synchronously controlling the LED light strips on the physical road network;

[0231] At the second level of risk, the virtual model displays an orange warning area and automatically generates a speed limit of 80km / h and pushes it to the traffic signal system;

[0232] When the risk reaches level three, the virtual model highlights the red warning area, links the physical road network's broadcast system and information board, and displays an "emergency speed reduction" message.

[0233] Finally, a three-layer architecture of "perception-simulation-control" is built based on digital twin technology to achieve accurate mapping and dynamic interaction of all elements and processes of the physical system. This includes:

[0234] Perception layer: Deploy the ETC gantries, surveillance cameras, and other equipment specified in the document to collect environmental data in real time.

[0235] Simulation layer: runs the digital twin engine, integrates the risk assessment model with the dynamic propagation equation, and outputs risk prediction results;

[0236] Control layer: Based on the warning instructions of the twin model, physical equipment such as light strip control and speed limit adjustment are linked and executed.

[0237] By integrating digital twin technology with the method of this application, the twin model can be used to accurately preview the operation status of the road network and detect potential risk factors in advance; during the evolution of risks, intervention strategies can be intelligently triggered based on real-time mapping data to dynamically regulate traffic flow; afterwards, based on the twin data, a retrospective review can be conducted to deeply explore the risk occurrence mechanism, analyze the handling experience, and build a closed-loop management system from risk prevention to handling optimization, thereby facilitating the intelligent and refined upgrade of highway network operation and management.

[0238] The above mainly introduces the scheme of the embodiment of the present application from the perspective of device implementation. It is understandable that each device, for example, a vehicle safety warning device for a highway network, includes at least one of the hardware structures and software modules corresponding to the execution of each function in order to realize the above functions. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0239] The embodiment of the present application can divide the functional units of the vehicle safety warning device of the highway network according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0240] In the case of an integrated unit, Figure 5 A possible structural diagram of the vehicle safety warning device for the expressway network involved in the above embodiment (referred to as the vehicle safety warning device 50 for the expressway network) is shown. The vehicle safety warning device 50 for the expressway network includes a processing unit 501 and a communication unit 502, and may also include a storage unit 503. Figure 5 The structural diagram shown can be used to illustrate the structure of the vehicle safety warning device for the expressway network involved in the above embodiments.

[0241] when Figure 5 The structural schematic diagram shown is used to illustrate the structure of the vehicle safety warning device for the highway network involved in the above-mentioned embodiment. The processing unit 501 is used to control and manage the operation of the vehicle safety warning device for the highway network, the communication unit 502 is used for the vehicle safety warning device for the highway network to communicate with other devices, and the storage unit 503 is used to store the program code and data of the vehicle safety warning device for the highway network.

[0242] For example, the communication unit 502 is used to establish a real-time communication link with the roadside unit (RSU), the on-board terminal (OBU) and the cloud platform to receive road condition data, weather information, vehicle location and status data; the processing unit 501 is used to identify potential risk scenarios (such as foggy sections, icy roads, abnormal vehicle deceleration, etc.) based on multi-source data fusion analysis and generate early warning instructions.

[0243] In a possible implementation, the processing unit 501 is further configured to dynamically adjust the warning strategy according to the risk level, such as triggering an audio-visual coordinated warning for a high-risk scenario and pushing a text prompt for a low-risk scenario.

[0244] In one possible implementation, the communication unit 502 is further used to synchronize the warning information to surrounding vehicles and the traffic management center, and the processing unit 501 is further used to receive feedback data, evaluate the warning effect and optimize the warning model parameters.

[0245] Among them, the processing unit 501 can be a processor or a controller, and the communication unit 502 can be a communication interface, a transceiver, a transceiver, a transceiver circuit, a transceiver device, etc. Among them, the communication interface is a general term and can include one or more interfaces. The storage unit 503 can be a memory. When the vehicle safety warning device 50 of the highway network is a chip, the processing unit 501 can be a processor or a controller, and the communication unit 502 can be an input interface and / or output interface, a pin or a circuit, etc. The storage unit 503 can be a storage unit within the chip (for example, a register, a cache, etc.), or it can be a storage unit located outside the chip (for example, a read-only memory (ROM), a random access memory (RAM), etc.).

[0246] Among them, the communication unit can also be called a transceiver unit. The antenna and control circuit with transceiver functions in the vehicle safety warning device 50 for the highway network can be regarded as the communication unit 502 of the vehicle safety warning device 50 for the highway network, and the processor with processing function can be regarded as the processing unit 501 of the vehicle safety warning device 50 for the highway network. Optionally, the device used to implement the receiving function in the communication unit 502 can be regarded as a communication unit, and the communication unit is used to perform the receiving steps in the embodiment of the present application. The communication unit can be a receiver, a receiver, a receiving circuit, etc. The device used to implement the sending function in the communication unit 502 can be regarded as a sending unit, and the sending unit is used to perform the sending steps in the embodiment of the present application. The sending unit can be a transmitter, a transmitter, a sending circuit, etc.

[0247] Figure 5If the integrated units are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The storage medium for storing computer software products includes various media that can store program codes, such as USB flash drives, mobile hard drives, read-only memories, random access memories, magnetic disks or optical disks.

[0248] Figure 5 A unit in a can also be called a module, for example, a processing unit can be called a processing module.

[0249] The embodiment of the present application also provides a hardware structure diagram of a vehicle safety warning device for a highway network (denoted as a vehicle safety warning device for a highway network 60), see Figure 6 The vehicle safety warning device 60 for the highway network includes a processor 601 and, optionally, a memory 602 connected to the processor 601 .

[0250] In the first possible implementation, see Figure 6 The vehicle safety warning device 60 for a highway network also includes a transceiver 603. The processor 601, the memory 602, and the transceiver 603 are connected via a bus. The transceiver 603 is used to communicate with other devices or a communication network. Optionally, the transceiver 603 may include a transmitter and a receiver. The device used to implement the receiving function in the transceiver 603 can be considered a receiver, and the receiver is used to perform the receiving step in the embodiment of the present application. The device used to implement the sending function in the transceiver 603 can be considered a transmitter, and the transmitter is used to perform the sending step in the embodiment of the present application.

[0251] Based on the first possible implementation, Figure 6 The structural diagram shown can be used to illustrate the structure of the vehicle safety warning device for the expressway network involved in the above embodiments.

[0252] in, Figure 6 It can also represent a system chip in a vehicle safety warning device for a highway network. In this case, the actions performed by the vehicle safety warning device for the highway network can be implemented by the system chip. The specific actions performed can be found above and will not be repeated here.

[0253] During implementation, each step of the method provided in this embodiment can be completed by hardware integrated logic circuits in a processor or by software instructions. The steps of the method disclosed in the embodiments of this application can be directly implemented as execution by a hardware processor, or as a combination of hardware and software modules in a processor.

[0254] The processor in this application may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, and other types of computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform operations or processing. The processor may be a separate semiconductor chip, or it may be integrated into a semiconductor chip together with other circuits. For example, it may form an SoC (system on a chip) with other circuits (such as a codec circuit, a hardware acceleration circuit, or various bus and interface circuits), or it may be integrated into the ASIC as a built-in processor of the ASIC. The ASIC with the integrated processor may be packaged separately or together with other circuits. In addition to the core for executing software instructions to perform operations or processing, the processor may further include necessary hardware accelerators, such as a field programmable gate array (FPGA), a PLD (programmable logic device), or a logic circuit that implements dedicated logic operations.

[0255] The memory in the embodiments of the present application may include at least one of the following types: read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or electrically erasable programmable read-only memory (EEPROM). In some scenarios, the memory may also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0256] An embodiment of the present application also provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enables the computer to execute any of the above methods.

[0257] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above methods.

[0258] An embodiment of the present application also provides a chip, which includes a processor and an interface circuit, the interface circuit is coupled to the processor, the processor is used to run a computer program or instruction to implement the above method, and the interface circuit is used to communicate with other modules outside the chip.

[0259] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0260] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0261] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, the present application is intended to encompass such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

Claims

1. A vehicle safety early warning method for a highway network, characterized in that: include: Collect environmental data of highways, including meteorological data, traffic condition data and road surface status data; Divide the highway into several areas, and calculate the initial risk value of each area according to the environmental data; Calculate the risk propagation value of each region based on the dynamic risk propagation equation according to the initial risk value; determining a risk level for each area based on the risk propagation value; Trigger early warning measures for each area according to the risk level; The warning measures include light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage and visual warning information on information boards.

2. A vehicle safety early warning method for a highway network according to claim 1, characterized in that: The initial risk value R i The calculation formula is: ; Among them, V i represents the average vehicle speed in area i, V max represents the highway design speed limit, μ i represents the road friction coefficient of area i, μ0 represents the friction coefficient safety threshold, ρ i represents the traffic density in area i, ρ th represents the traffic density threshold, W i represents the comprehensive meteorological index of region i, W th Indicates the meteorological risk threshold.

3. The vehicle safety early warning method for a highway network according to claim 2, characterized in that: The calculation formula of the comprehensive meteorological index is: Among them, W i represents the comprehensive meteorological index of region i, w k Represents the weight coefficients of each item, and the sum is 1, f k Represents the normalized function of each element in the meteorological data, X k Represents the various elements in the meteorological data, X kref Indicates the safety threshold of each element in the meteorological data.

4. A vehicle safety warning method for a highway network according to claim 3, characterized in that: The dynamic risk propagation equation R p (i,t) is: ; Among them, R i (t) represents the initial risk value of region i at time t, R j (t) represents the initial risk value of region j at time t, represents the upstream node set of region i, Q ji represents the cross-sectional flow from area j to area i, Q max Indicates the maximum cross-sectional flow rate, d ji represents the distance between region j and region i, λ represents the risk diffusion coefficient, t represents the time interval and i represents the region index.

5. The vehicle safety early warning method for a highway network according to claim 4, characterized in that: The cross-sectional flow rate represents the number of vehicles entering the sub-area per unit time, and the cross-sectional flow rate is obtained in the following ways: If the sub-area includes an electronic toll collection system (ETC), the number of vehicles entering the sub-area per unit time is counted using the license plate recognition technology of the ETC gantry system. If the sub-area contains a surveillance camera, the number of vehicles entering the sub-area per unit time is counted using video image recognition technology; If the sub-area includes a microwave radar or a laser detector, the microwave radar or the laser detector is used to count the number of vehicles entering the sub-area per unit time.

6. The vehicle safety early warning method for a highway network according to claim 4, characterized in that: The upstream node set represents a set consisting of all areas that are directly connected to area i and located upstream of area i, guided by the traffic direction.

7. The vehicle safety early warning method for a highway network according to claim 1, characterized in that: Determining the risk level of each area according to the risk propagation value includes: If the risk propagation value is greater than or equal to the first threshold and less than the second threshold, it is marked as a level one risk; If the risk propagation value is greater than or equal to the second threshold and less than the third threshold, it is marked as a level 2 risk; If the risk propagation threshold is greater than or equal to the third threshold, it is marked as a level 3 risk; Here, 0<first threshold<second threshold<third threshold<1.

8. The vehicle safety early warning method for a highway network according to claim 1, characterized in that: The early warning measures for each area triggered according to the risk level include: The warning measures for level 1 risk are: triggering a yellow light, starting a broadcast notification of level 1 risk, and adjusting the speed limit to the first speed; The warning measures for level 2 risk are: triggering orange lights, initiating a broadcast notification of level 2 risk, adjusting the speed limit to the second speed, and triggering a fog light linkage response; The warning measures for level 3 risk are: triggering red lights, starting broadcast notification of level 3 risk, and adjusting the speed limit to the third speed; Among them, the first speed>the second speed>the third speed.

9. The vehicle safety early warning method for a highway network according to claim 1, characterized in that: The meteorological data includes: temperature, humidity, visibility, precipitation, wind speed, and wind direction; The traffic condition data includes: average vehicle speed, traffic density, and cross-sectional flow.

10. The road surface condition data includes: Road friction coefficient.

11. A vehicle safety warning system for a highway network, characterized in that: include: Data collection module, risk assessment module, and early warning execution module; among them, The data acquisition module is used to collect highway meteorological data, traffic condition data and road surface status data to obtain environmental data; The risk assessment module is used to divide the highway into several areas and calculate the initial risk value of each area based on the environmental data; And calculate the risk propagation value of each area based on the dynamic risk propagation equation according to the initial risk value; The early warning execution module is used to determine the risk level of each area according to the risk propagation value; Early warning measures are triggered for each area based on the risk level; the early warning measures include light strip prompts, broadcast notifications, speed limit adjustments, fog light linkage, and visual early warning information on information boards.

Images