Environment early warning collaborative response method, device and equipment based on traffic agent

Abstract

The embodiment of the invention discloses an environment early warning collaborative response method, device and equipment based on a traffic agent. A specific embodiment of the method comprises the following steps: acquiring a persistent multi-source environment data set from multi-source environment monitoring equipment; preprocessing the persistent multi-source environment data set to obtain a standard multi-source environment data set; performing single-point feature extraction and spatial association on the standard multi-source environment data set to obtain a multi-source environment data feature set; determining an environment event knowledge object based on a preset judgment rule base, the standard multi-source environment data set and the multi-source environment data feature set, and executing cascade early warning measures based on the environment event knowledge object; and based on the multi-source environment data feature set, determining a derivative high-risk scene, and based on the derivative high-risk scene, executing a traffic cooperative response measure. According to the embodiment, the effects of avoiding excessive reduction of passing efficiency or resource waste, reducing secondary accident risks and reducing casualties are achieved.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and more specifically to a method, apparatus, and device for environmental early warning and collaborative response based on traffic intelligent agents. Background Technology

[0002] With the acceleration of urbanization and the increasing complexity of transportation networks, severe weather events (such as fog, road icing, and short-duration heavy rainfall) pose a growing threat to road traffic safety and operational efficiency. Currently, the common approach to issuing warnings based on severe weather is to use fixed sensors and a pre-defined rule engine. This involves deploying weather stations, cameras, and other equipment on a few road sections to achieve basic monitoring of environmental conditions. When abnormal weather is detected, the pre-defined rule engine typically determines the event and issues a single control command, such as a speed limit for the entire section or road closure.

[0003] However, when using the above methods to issue warnings based on severe weather, the following technical problems often arise: Excessive decrease in traffic efficiency or waste of resources. Commonly used measures such as zoned speed limits and road closures fail to allow for precise adjustments based on individual road conditions and vehicle types, easily leading to excessive decreases in traffic efficiency or waste of resources.

[0004] Lack of foresight and coordination. It is difficult to accurately predict traffic flow under the influence of weather. Vehicles and infrastructure are "information silos," making it impossible to achieve coordinated risk avoidance, which can easily lead to secondary accidents and casualties.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure propose environmental early warning and collaborative response methods, devices, electronic devices, and computer-readable media based on traffic intelligent agents to solve one or more of the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide an environmental early warning and collaborative response method based on traffic intelligent agents. The method includes: acquiring a persistent multi-source environmental dataset from multi-source environmental monitoring equipment; preprocessing the persistent multi-source environmental dataset to obtain a standard multi-source environmental dataset; performing single-point feature extraction and spatial correlation on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set; determining environmental event knowledge objects based on a preset judgment rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, and executing tiered early warning measures based on the environmental event knowledge objects; and performing event correlation analysis and situational deduction on the environmental event knowledge objects based on the multi-source environmental data feature set to determine derived high-risk scenarios, and executing traffic collaborative response measures based on the derived high-risk scenarios.

[0009] Secondly, some embodiments of this disclosure provide an environmental early warning and collaborative response device based on traffic intelligent agents. The device includes: an acquisition unit configured to acquire a persistent multi-source environmental dataset from multi-source environmental monitoring equipment; a preprocessing unit configured to preprocess the persistent multi-source environmental dataset to obtain a standard multi-source environmental dataset; an extraction unit configured to perform single-point feature extraction and spatial correlation on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set; a determination unit configured to determine environmental event knowledge objects based on a preset judgment rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, and to execute tiered early warning measures based on the environmental event knowledge objects; and an analysis unit configured to perform event correlation analysis and situational deduction on the environmental event knowledge objects based on the multi-source environmental data feature set to determine derived high-risk scenarios, and to execute traffic collaborative response measures based on the derived high-risk scenarios.

[0010] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0012] The above embodiments of this disclosure have the following beneficial effects: The environmental early warning and collaborative response method based on traffic intelligent agents in some embodiments of this disclosure avoids excessive decline in traffic efficiency or waste of resources, reduces the risk of secondary accidents, and reduces casualties. Specifically, the reasons for excessive decline in traffic efficiency or waste of resources, as well as the lack of foresight and coordination, are as follows: Excessive decline in traffic efficiency or waste of resources: Commonly adopted extensive measures such as regional speed limits and road closures cannot be finely adjusted according to micro-road conditions and vehicle types, easily leading to excessive decline in traffic efficiency or waste of resources. Lack of foresight and coordination: It is difficult to accurately predict traffic flow under the influence of weather; vehicles and infrastructure are "information silos," unable to achieve collaborative risk avoidance, easily causing secondary accidents and resulting in casualties. Based on this, the environmental early warning and collaborative response method based on traffic intelligent agents in some embodiments of this disclosure first acquires a persistent multi-source environmental dataset from multi-source environmental monitoring equipment. This avoids system overload or data loss, ensuring the continuity and reliability of subsequent processing. Secondly, the aforementioned persistent multi-source environmental dataset is preprocessed to obtain a standard multi-source environmental dataset. This transforms the chaotic raw data into high-quality, well-organized, standardized data. Then, single-point feature extraction and spatial correlation are performed on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set. This elevates discrete point-like data into deep features that reflect spatiotemporal patterns and overall trends. Next, based on a pre-defined rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, environmental event knowledge objects are identified, and tiered early warning measures are implemented based on these environmental event knowledge objects. This generates a digital knowledge entity containing all elements such as event type, level, precise boundaries, and evolution trends, enabling targeted, tiered early warning measures. Finally, based on the multi-source environmental data feature set, event correlation analysis and situational projection are performed on the environmental event knowledge objects to identify derivative high-risk scenarios, and traffic collaborative response measures are implemented based on these derivative high-risk scenarios. Therefore, through refined guidance of "remote early warning - near-end command - strong control of the core area" and coordinated measures of vehicle-road-cloud collaboration, traffic efficiency can be maximized while ensuring safety, fundamentally reducing the risk of secondary accidents. This implementation method avoids excessive decline in traffic efficiency or waste of resources, reduces the risk of secondary accidents, and reduces casualties. Attached Figure Description

[0013] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0014] Figure 1 This is a flowchart of some embodiments of the environmental early warning and collaborative response method based on traffic intelligent agents disclosed herein; Figure 2 This is a schematic diagram of the structure of some embodiments of the environmental early warning and collaborative response device based on traffic intelligent agents according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0015] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0016] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0017] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0018] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0019] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0020] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0021] Figure 1 A flowchart 100 is shown, illustrating some embodiments of the traffic agent-based environmental early warning and collaborative response method according to this disclosure. This traffic agent-based environmental early warning and collaborative response method includes the following steps: Step 101: Obtain the persistent multi-source environmental dataset from the multi-source environmental monitoring equipment.

[0022] In some embodiments, the implementing entity (e.g., a server) of the traffic intelligent agent-based environmental early warning collaborative response method can acquire persistent multi-source environmental datasets from multi-source environmental monitoring devices.

[0023] In some optional implementations of certain embodiments, the aforementioned execution entity may obtain a persistent multi-source environmental dataset from the multi-source environmental monitoring device through the following steps: The first step is to acquire the multi-source environmental dataset collected by the multi-source environmental monitoring equipment via wired or wireless communication networks. This multi-source environmental data may include: temperature, humidity, wind speed, wind direction, air pressure, rainfall, visibility, and road surface condition. The multi-source environmental monitoring equipment can be various monitoring devices deployed along the roadside, including: six-element monitoring equipment, visibility monitors, and road surface condition detectors. The wired communication network can be fiber optic. The wireless communication network can be 4G / 5G or LoRa.

[0024] The second step involves using a message queue to cache the aforementioned multi-source environment dataset, creating a multi-source environment dataset cache to handle peak data inflows and ensure system stability and reliability. For example, the message queue could be Apache Kafka, RabbitMQ, or RocketMQ.

[0025] The third step involves caching and storing the aforementioned multi-source environment dataset based on the time-series database, resulting in a persistent multi-source environment dataset. This facilitates aggregation queries and trend analysis within a time window. For example, the time-series database could be InfluxDB or TDengine.

[0026] Step 102: Preprocess the persistent multi-source environment dataset to obtain a standard multi-source environment dataset.

[0027] In some embodiments, the execution entity may preprocess the persistent multi-source environmental dataset to obtain a standard multi-source environmental dataset. The standard multi-source environmental data in the standard multi-source environmental dataset may include: temperature, humidity, wind speed, wind direction, air pressure, rainfall, visibility, and road surface conditions.

[0028] In some optional implementations of certain embodiments, the aforementioned execution entity may preprocess the aforementioned persistent multi-source environment dataset to obtain a standard multi-source environment dataset through the following steps: The first step is to perform outlier processing on the aforementioned persistent multi-source environment dataset to obtain an anomaly-corrected multi-source environment dataset. In practice, the execution entity can use the interquartile range (IQR) method to perform outlier processing on the persistent multi-source environment dataset to obtain the anomaly-corrected multi-source environment dataset. As an example, the execution entity can use the IQR method to remove persistent multi-source environment data that exceed the upper limit (Q1 - 1.5IQR, where IQR is the IQR) and lower limit (Q3 + 1.5IQR) as outliers.

[0029] The second step is to perform data completion on the aforementioned anomaly correction multi-source environmental dataset to obtain a completed multi-source environmental dataset. In practice, the implementing entity can use time series interpolation to complete the anomaly correction multi-source environmental dataset for missing data from a single environmental monitoring device. For data missing data in a large monitoring area, the missing values ​​for the large monitoring area are determined using the observation values ​​of other geographically adjacent environmental monitoring devices at the same time, through the inverse distance weighting method, to complete the anomaly correction multi-source environmental dataset. As an example, the aforementioned time series interpolation method can be linear interpolation or spline interpolation.

[0030] The third step is to perform data standardization on the aforementioned data to complete the multi-source environment dataset, resulting in a standard multi-source environment dataset. In practice, the implementing entity can utilize the Z-Score standardization method to perform data standardization on the aforementioned data to complete the multi-source environment dataset, thereby obtaining a standard multi-source environment dataset.

[0031] Step 103: Perform single-point feature extraction and spatial correlation on the standard multi-source environmental dataset to obtain the multi-source environmental data feature set.

[0032] In some embodiments, the aforementioned execution entity may perform single-point feature extraction and spatial correlation on the aforementioned standard multi-source environmental dataset to obtain a multi-source environmental data feature set.

[0033] In some optional implementations of certain embodiments, the aforementioned execution entity may perform single-point feature extraction and spatial correlation on the aforementioned standard multi-source environmental dataset through the following steps to obtain a multi-source environmental data feature set: The first step is to perform time-series analysis on the aforementioned standard multi-source environmental dataset to obtain a time-series smoothing feature set. In practice, the executing entity can use the moving average method to perform time-series analysis on the aforementioned standard multi-source environmental dataset to obtain a time-series smoothing feature set. As an example, the executing entity can define a fixed-duration time window for each environmental data point (such as temperature, humidity, wind speed, wind direction, air pressure, rainfall, visibility, and road surface condition) in the aforementioned standard multi-source environmental dataset at a certain moment. Then, the arithmetic mean within the aforementioned time window is determined as the time-series smoothing feature at that moment. Finally, the time-series smoothing features of each parameter at each moment on the time axis are determined as the time-series smoothing feature set. As an example, the aforementioned time window can be 10 minutes.

[0034] The second step is to quantify the change trends of the aforementioned standard multi-source environmental dataset to obtain an environmental evolution trend feature set. In practice, the implementing entity can perform linear regression analysis on each environmental data point in the aforementioned standard multi-source environmental dataset within the aforementioned time window to obtain the slope of the data change within the aforementioned time window, which is taken as the rate of change. Furthermore, the rate of change of each environmental data point at each time point is determined as the environmental evolution trend feature set. As an example, the aforementioned rate of change may include, but is not limited to, "temperature decrease rate: 2°C / hour" and "air pressure change rate: -1.5 hPa / hour".

[0035] The third step involves quantifying the derived parameters of the aforementioned standard multi-source environmental dataset to obtain a comprehensive environmental index feature set. In practice, the implementing entity can use the temperature and humidity data from the standard multi-source environmental dataset to determine the dew point temperature (Td) using the Margras formula. Then, based on the temperature and wind speed data from the standard multi-source environmental dataset, the implementing entity can use the formula: Wind chill index = 13.12 + 0.6215 Temperature -11.37 Wind speed^0.16 + 0.3965 temperature Wind speed ≥ 0.16 is used to determine the wind chill index, which is used to quantify the combined impact of strong winds and low temperatures on people (such as outdoor workers) and vehicles (such as engine efficiency and wind resistance). Finally, the aforementioned implementing entities can define the aforementioned dew point temperature and wind chill index as a comprehensive environmental indicator feature set.

[0036] The fourth step is to obtain the geographic information set of the aforementioned multi-source environmental monitoring devices. In practice, the executing entity can read the unique and precise geographic coordinate information (such as latitude and longitude, highway markers) of each multi-source environmental monitoring device from the system configuration library or device metadata, as the geographic information set. The system configuration library can be a structured database or a collection of configuration files used to uniformly store and manage all hardware devices, software parameters, and business rules connected to the system. The device metadata can be "data on data" describing the device's own characteristics and data meaning, typically embedded in the device firmware or data stream, used to dynamically identify data sources and parse data content.

[0037] The fifth step involves spatially associating the aforementioned geographic information set with the aforementioned standard multi-source environmental dataset and the aforementioned comprehensive environmental indicator feature set to obtain a multi-source environmental element field set. In practice, the executing entity can associate and bind each environmental data in the aforementioned standard multi-source environmental dataset and each comprehensive environmental indicator feature in the aforementioned comprehensive environmental indicator feature set with the corresponding coordinates in the aforementioned geographic information set via device ID, to form a complete data record containing "time, parameter value, and spatial location," which serves as a multi-source environmental element field, thus obtaining a multi-source environmental element field set.

[0038] Step 6: The aforementioned time-series smoothing feature set, the aforementioned environmental evolution trend feature set, and the aforementioned multi-source environmental element field set are determined as the multi-source environmental data feature set. Among them, the time-series smoothing feature set and the environmental evolution trend feature set in the aforementioned multi-source environmental data feature set can be used to provide temporal support for the predictive warnings in the tiered early warning measures implemented in step 104. The multi-source environmental element field set in the aforementioned multi-source environmental data feature set can be used to provide spatial location support for the tiered early warning measures implemented in step 104 based on the event impact boundaries.

[0039] The first to sixth steps and related content described above constitute an inventive point of this disclosure, and in conjunction with steps 104 and 105, solve the technical problem of "low traffic efficiency and high risk of secondary accidents caused by traditional severe weather warning methods on highways." Factors leading to low traffic efficiency and high risk of secondary accidents often include: the lack of quantitative physical indicators to reflect the nature of events (such as icing risk); and the lack of a continuous spatial distribution field, resulting in monitoring loopholes. Solving these factors can improve traffic efficiency and reduce the risk of secondary accidents. To achieve this, firstly, a time-series analysis is performed on the aforementioned standard multi-source environmental dataset to obtain a time-series smoothing feature set. This eliminates random fluctuations and noise in the data, extracts stable and reliable environmental change trends, and provides a quantitative basis for the accurate determination of event levels (such as rainfall intensity classification). Secondly, the change trend is quantified on the aforementioned standard multi-source environmental dataset to obtain an environmental evolution trend feature set. This quantifies the rate and direction of change of key parameters (such as air pressure and temperature), supports dynamic prediction of severe weather events (such as fog movement), and achieves predictive early warning. Third, the derived parameters of the aforementioned standard multi-source environmental dataset are quantified to obtain a comprehensive environmental indicator feature set. This allows for the calculation of key physical indicators such as dew point temperature and wind chill index, enhancing the ability to identify the nature of events (such as icing risk). Fourth, the geographic information set of the aforementioned multi-source environmental monitoring equipment is obtained. This allows for the assignment of precise spatial coordinates (such as latitude and longitude, highway station number) to the data at each monitoring point. Fifth, the aforementioned geographic information set is spatially correlated with the aforementioned standard multi-source environmental dataset and the aforementioned comprehensive environmental indicator feature set to obtain a multi-source environmental element field set. This allows for the fusion of discrete point data into a continuous spatial distribution field (such as a visibility field and a temperature field), achieving precise visualization of the entire road network environmental situation. Sixth, the aforementioned time-series smoothing feature set, the aforementioned environmental evolution trend feature set, and the aforementioned multi-source environmental element field set are determined as a multi-source environmental data feature set. This allows for the formation of a complete environmental feature knowledge base integrating time, trend, and spatial dimensions. Finally, by combining steps 104 and 105, implementing tiered early warning measures and traffic coordination response measures, we can achieve predictive warnings and adaptive traffic flow control, ultimately improving traffic efficiency and reducing the risk of secondary accidents.

[0040] Step 104: Based on the preset judgment rule base, standard multi-source environmental dataset and multi-source environmental data feature set, determine the environmental event knowledge object, and execute tiered early warning measures based on the environmental event knowledge object.

[0041] In some embodiments, the aforementioned executing entity can determine environmental event knowledge objects based on a preset judgment rule base, the aforementioned standard multi-source environmental dataset, and the aforementioned multi-source environmental data feature set, and execute tiered early warning measures based on the aforementioned environmental event knowledge objects. The preset judgment rule base is a rule base that predefines triggering conditions for various severe weather conditions. As an example, the preset judgment rule base may include the following rule: IF (visibility < 500 meters) AND (humidity > 90%) THEN event type = dense fog.

[0042] In addressing the technical challenges of severe weather-based early warning systems, and considering the application scenario—long-distance, high-speed highways—localized severe weather conditions such as fog, icy roads, and strong crosswinds pose significant safety hazards. This often presents additional technical challenges: traditional methods rely on single-parameter thresholds, lacking the ability to identify correlations between complex weather events, and lacking quantitative predictions of event duration, evolution trends, and movement speed. This makes it difficult to accurately delineate the continuous spatial contours of severe weather, potentially leading to over- or under-control of the affected area, resulting in excessively reduced traffic efficiency or wasted resources. To meet the specific requirements of this application scenario—adaptability to complex weather events, quantification of weather event impacts, and tiered control—we have decided to adopt the following solution: In some optional implementations of certain embodiments, the aforementioned execution entity may determine environmental event knowledge objects based on a preset judgment rule base, the aforementioned standard multi-source environmental dataset, and the aforementioned multi-source environmental data feature set, and then execute tiered early warning measures based on the aforementioned environmental event knowledge objects: The first step involves performing rule matching on the aforementioned multi-source environmental data feature set based on a pre-defined rule base to obtain the basic event types. In practice, the executing entity can perform rapid, parallel matching of each environmental data feature in the aforementioned multi-source environmental data feature set with the aforementioned pre-defined rule base to confirm the basic event types through environmental data features (such as temperature, humidity, wind speed, wind direction, air pressure, rainfall, visibility, road surface condition, dew point temperature, and wind chill index). These basic event types may include, but are not limited to, heavy fog, heavy rain, or road icing.

[0043] The second step involves verifying and classifying the basic event types based on the aforementioned time-series smoothing feature set to obtain preliminary event types. In practice, the executing entity can use the time-series smoothing feature set to verify the basic event types, determining whether instantaneous low visibility is a continuous or non-continuous phenomenon, thus ensuring the reliability of event determination. Then, based on the magnitude of the time-series smoothing features in the aforementioned time-series smoothing feature set, the basic event types are classified into multiple levels to obtain preliminary event types. As an example, the executing entity can achieve precise classification of rainfall events by classifying the time-series smoothing feature of average rainfall (mm / h) within a time window in the aforementioned time-series smoothing feature set into multiple levels: light rain: average rainfall ≤ 2.5 mm / h, moderate rain: 2.5 mm / h < average rainfall ≤ 8 mm / h, heavy rain: 8 mm / h < average rainfall ≤ 16 mm / h, torrential rain: average rainfall > 16 mm / h. The aforementioned implementing entity can achieve precise classification of visibility events by performing multi-level classification of the average visibility (m) within the time window of the aforementioned time-series smoothing feature set: light fog: 500m ≤ average visibility < 1000m, heavy fog: 200m ≤ average visibility < 500m, dense fog: 50m ≤ average visibility < 200m, and very dense fog: average visibility < 50m.

[0044] The third step involves performing spatial field analysis on the aforementioned multi-source environmental element set to obtain the event impact boundary. In practice, the executing entity can employ image edge detection algorithms to perform spatial field analysis on the multi-source environmental element set, identifying the spatial contours corresponding to the set and thus obtaining the event impact boundary. As an example, in the visibility element field grid of the aforementioned multi-source environmental element set, tracing the contour lines where visibility equals 200 meters, the spatial area enclosed by these contour lines represents the event impact boundary of the "fog event." This event impact boundary is represented by a series of geographic coordinate points, precisely describing the geometry of the affected area.

[0045] The fourth step is to overlay the event impact boundary with the digital road network layer to obtain the event-road overlay model.

[0046] The fifth step involves determining the safety buffer based on the aforementioned event-road overlay model to obtain the event scope. In practice, the executing entity can extend the scope of the event-road overlay model using the safety model and buffer analysis method to obtain the event scope. The safety model can be the AASHTO parking sight distance model.

[0047] The sixth step involves conducting a spatiotemporal correlation analysis on the multi-source environmental element field set based on the aforementioned event scope and environmental evolution trend feature set, thereby obtaining the event's spatiotemporal information. In practice, the implementing entity can utilize the cross-correlation method to conduct a spatiotemporal correlation analysis on the multi-source environmental element field set based on the aforementioned event scope and environmental evolution trend feature set, in order to determine the overall movement vector (direction and velocity) of the event and obtain its spatiotemporal information. This movement vector can include both the direction and velocity of movement. For example, "The fog is moving northeast at a speed of 15 kilometers per hour."

[0048] Step 7: Based on the aforementioned preliminary event types and spatiotemporal information, construct an event knowledge graph to obtain environmental event knowledge objects. In practice, the implementing entity can use "severe weather event" as the main entity, with the aforementioned preliminary event types (type, level) as core attributes, and the aforementioned spatiotemporal information (direction, speed), the aforementioned event impact boundary (geometric outline), and the aforementioned event scope (control area) as related attributes to construct a structured environmental event knowledge object. This environmental event knowledge object can be a digital entity containing complete attributes such as "type, level, location, boundary, direction, speed, and impact area," used to provide comprehensive and accurate decision-making basis for tiered control.

[0049] Step 8: Based on the aforementioned knowledge of environmental events, implement tiered early warning measures.

[0050] In some optional implementations of certain embodiments, the aforementioned execution entity may perform tiered early warning measures based on the aforementioned environmental event knowledge object through the following steps: Step 1: Based on the aforementioned environmental event knowledge objects, issue the following differentiated early warning information at different spatial distances along the traffic flow direction: A forward-looking warning is issued at a first preset distance (e.g., 5 kilometers) from the aforementioned environmental event knowledge object. In practice, the implementing entity can input the event scope into a generative model to obtain the forward-looking warning. Then, through traffic radio (FM / RDS) or navigation map app data interfaces, the forward-looking warning is issued to vehicles at the first preset distance (e.g., 5 kilometers) from the aforementioned derived high-risk scenario, along the traffic flow direction. The generative model can be a large language model (LLM) (such as the GPT series, BERT, T5, etc.). The forward-looking warning can be a reminder to drivers of severe weather risks. For example, "Dense fog area 5 kilometers ahead, visibility minimum 150 meters, moving eastward. Please prepare in advance and drive cautiously."

[0051] At a second preset distance (e.g., 2 kilometers) from the aforementioned environmental event knowledge object, specific instruction information is issued. This specific instruction information can be a reminder to the driver of necessary operational instructions in response to the environmental event. For example, the specific instruction information could be: "Approaching a dense fog area, current visibility 150 meters. Please immediately reduce speed to below 60 km / h, turn on fog lights and low beam headlights, and strictly prohibit sudden braking."

[0052] Within the aforementioned environmental event knowledge object, strong constraint information is published. This strong constraint information can be information reminding drivers of the necessary operational instructions for environmental events. For example, the strong constraint information could be: "Dense fog area, low visibility. Speed ​​limit 40km / h, maintain a safe distance of at least 150 meters. Beware of high risk ahead at K31+500."

[0053] Step two involves controlling the roadside lighting guidance facilities within the aforementioned environmental event knowledge object. In practice, the executing entity can input the environmental event knowledge object into the generative model to obtain control commands, and then send these commands to the roadside lighting guidance facilities via a dedicated communication network to execute on / off operations. The lighting guidance facilities can be active light-emitting devices deployed on both sides of the road to provide drivers with visual guidance regarding road alignment and direction in low-visibility environments (such as heavy fog, nighttime, or heavy rain). Examples include fog lights and delineators. As an example, the dedicated communication network may include, but is not limited to, industrial Ethernet and IoT private networks.

[0054] The first to eighth steps and related content described above, as an inventive point of this disclosure, solve the technical problem that "traditional methods often provide a general first-level response to events such as 'dense fog,' excessively suppressing road capacity and leading to widespread and prolonged traffic congestion." Factors leading to widespread and prolonged traffic congestion often include: on long-distance, high-speed highways, localized severe weather such as dense fog, icy roads, and strong crosswinds pose significant safety hazards. Traditional methods typically rely on single parameter thresholds, lacking the ability to identify the correlation between complex weather events, and lacking quantitative prediction of event duration, evolution trends, and movement speed. This makes it difficult to accurately delineate the continuous spatial contours of severe weather, potentially leading to over-expansion or under-expansion of the control scope, resulting in excessive reduction in traffic efficiency or waste of resources. Solving these factors can avoid the excessive reduction in traffic efficiency or waste of resources caused by generalized scope control. To achieve this effect, firstly, based on a preset judgment rule base, rule matching is performed on the aforementioned multi-source environmental data feature set to obtain basic event types. This allows for accurate identification of the essential types of severe weather (such as dense fog, icy roads, heavy rainfall, etc.). Second, based on the aforementioned time-series smoothing feature set, feature verification and multi-level classification are performed on the basic event types to obtain preliminary event types. This allows for verification of event authenticity and quantification of severity levels (e.g., subdividing fog into "light fog" and "dense fog"), avoiding mismatches in control intensity due to misjudgment of severity levels. Third, spatial field analysis is performed on the aforementioned multi-source environmental element field set to obtain event impact boundaries. This allows for precise delineation of the geometric boundaries of severe weather (e.g., the outline of patchy fog). Fourth, the aforementioned event impact boundaries are overlaid with a digital road network layer to obtain an event-road overlay model. This allows for mapping meteorological impacts to specific road locations (e.g., G6 expressway K30+200 to K33+500), clarifying the target of control. Fifth, based on the aforementioned event-road overlay model, safety buffers are determined to obtain the event's scope. This allows for the scientific calculation of safety buffer distances (based on vehicle speed and reaction time models), balancing safety and efficiency requirements. Sixth, based on the aforementioned event scope and the aforementioned environmental evolution trend feature set, spatiotemporal correlation analysis is performed on the aforementioned multi-source environmental element field set to obtain event spatiotemporal information. Therefore, the direction, speed, and evolution trend of events can be predicted (e.g., fog moving eastward at 15 km / h), enabling proactive regulation. Seventh, based on the aforementioned preliminary event types and spatiotemporal information, an event knowledge graph is constructed to obtain environmental event knowledge objects. This allows for the generation of structured decision-making criteria (including attributes such as type, level, boundary, and direction). Eighth, based on the aforementioned environmental event knowledge objects, tiered early warning measures are implemented. This achieves automated and tiered management. Ultimately, this avoids excessive decline in traffic efficiency or resource waste caused by generalized area control.

[0055] Step 105: Based on the feature set of multi-source environmental data, conduct event correlation analysis and situational simulation on the knowledge objects of environmental events to identify derivative high-risk scenarios, and implement traffic collaborative response measures based on the derivative high-risk scenarios.

[0056] In some embodiments, the aforementioned implementing entity may perform event correlation analysis and situational simulation on the aforementioned environmental event knowledge object based on the aforementioned multi-source environmental data feature set, in order to identify derivative high-risk scenarios, and implement traffic collaborative response measures based on the aforementioned derivative high-risk scenarios.

[0057] In addressing the technical challenges of issuing early warnings based on severe weather, the following technical solutions were adopted for the application scenario: airports and train stations have complex road networks, requiring simultaneous efforts to ensure unobstructed emergency vehicle access and orderly evacuation of other vehicles during severe weather. This often leads to conflicting and complex measures, accompanied by the following technical problems: traditional control methods frequently involve one-way command issuance (e.g., speed limits) and singular measures (e.g., district-wide speed limits), making it difficult to accurately predict traffic flow under weather conditions. The lack of multi-measure coordination and fine-grained spatial differentiation increases the risk of secondary accidents. Considering the following requirements for this application scenario—adaptability to complex weather events and real-time traffic conditions—we decided to adopt the following solution: In some optional implementations of certain embodiments, the aforementioned executing entity may, based on the aforementioned multi-source environmental data feature set, perform event correlation analysis and situational simulation on the aforementioned environmental event knowledge object to identify derived high-risk scenarios, and based on the aforementioned derived high-risk scenarios, execute traffic collaborative response measures: The first step involves performing a coupling correlation analysis on the aforementioned environmental event knowledge objects and the aforementioned multi-source environmental data feature sets to obtain event correlation analysis results. In practice, the aforementioned implementing entity can analyze the causal relationship or synergistic effect between the aforementioned environmental event knowledge objects and the aforementioned multi-source environmental data feature sets based on preset correlation rules to obtain preliminary event correlation analysis results. Then, statistical methods are used to quantify the correlation between event parameters in the aforementioned preliminary event correlation analysis results to obtain the event correlation analysis results. The aforementioned preset correlation rules can be pre-set rules that map specific numbers in the aforementioned environmental event knowledge objects and the aforementioned multi-source environmental data feature sets to events. As an example, the aforementioned statistical methods can be Pearson correlation coefficient and Granger causality test. The aforementioned preset correlation rules can include, but are not limited to, the following: IF (Atmospheric temperature continuously >30°C) AND (Relative humidity >80%) AND (Air pressure drops >2hPa within 1 hour) THEN Severe convective weather (short-term heavy rainfall / thunderstorm winds). IF (Road surface temperature ≤0°C) AND (Road surface condition sensor detects "wet" or "precipitation") THEN Road icing. If (Event Type == Heavy Rainfall) then visibility is low. If (Event Type == Strong Winds) AND (Dust Source in Monitoring Area) then visibility is low.

[0058] The second step involves constructing a dynamic link topology map of the environment-traffic impact based on the road network topology, traffic flow characteristic data, and the event correlation analysis results mentioned above. In practice, the implementing entity can utilize graph theory models and spatial overlay analysis to fuse the road network topology (such as road hierarchy, connection relationships, and ramp locations) with the event correlation analysis results to obtain the environment-traffic link topology map. Then, the implementing entity can combine traffic flow characteristic data (such as traffic volume, average speed, and density) with the environment-traffic link topology map to determine the attenuation coefficient of the event on the capacity of key nodes (such as hubs and bottleneck sections), thus obtaining the dynamic link topology map of the environment-traffic impact. The graph theory model can include a node set and an edge set. Each node in the node set can represent a key point in the road network (such as road intersections, ramp entrances / exits, traffic hubs, and monitoring equipment installation points). Each node in the node set has a unique ID and geographical coordinates. Each edge in the edge set represents a road segment connecting two nodes. Each edge in the aforementioned edge set has directionality (directed edges) to represent the actual direction of traffic flow (e.g., from ramp A to hub B). The attenuation coefficient can be a value between 0 and 1, representing the proportion by which an event reduces the capacity of a road segment. For example, if a road segment has a baseline capacity of 2000 vehicles / hour under normal weather conditions, and dense fog (visibility 150 meters) causes a 40% reduction in capacity, then the attenuation coefficient for that road segment is 0.4, and the effective capacity of that road segment under the current conditions is 2000 vehicles / hour. (1-0.4)=1200 vehicles / hour.

[0059] The third step involves generating a spatiotemporal propagation vector field using a spatiotemporal prediction model, based on the aforementioned environmental evolution trend feature set and the multi-source environmental element field set. In practice, the executing entity can input the aforementioned environmental evolution trend feature set and the multi-source environmental element field set into the spatiotemporal prediction model to obtain the spatiotemporal propagation vector field. This spatiotemporal prediction model can be used to determine the displacement and intensity changes of each grid cell (e.g., 100m × 100m) over continuous time steps, thereby deducing the direction of movement, velocity, and diffusion trend of an event (e.g., a fog patch). For example, the spatiotemporal prediction model can be a cellular automata model.

[0060] The fourth step involves performing a multi-dimensional coupled simulation of the aforementioned dynamic link topology diagram of the environment-traffic impact and the aforementioned spatiotemporal propagation vector field to obtain the traffic flow situation. In practice, the aforementioned implementing entity can input the aforementioned dynamic link topology diagram of the environment-traffic impact and the aforementioned spatiotemporal propagation vector field into traffic simulation software to simulate how vehicles adjust their behavior according to intelligent driving logic (such as following models and lane-changing decisions) under dynamically changing environmental influences (such as changes in visibility caused by moving fog), thereby obtaining the traffic flow situation. The aforementioned traffic flow situation can represent the predicted distribution of road network traffic flow parameters within a specific future time period, including but not limited to speed fields, density fields, spatiotemporal maps of congestion indices, and predictions of queue lengths at key bottleneck locations. The aforementioned traffic simulation software can be SUMO or PTV Vissim.

[0061] The fifth step involves predicting derivative risks based on the aforementioned traffic flow patterns to obtain derivative high-risk scenarios. In practice, the implementing entities can utilize these traffic flow patterns to determine risk indicators. Then, spatial clustering algorithms (such as DBSCAN) are used to identify areas where these risk indicators exceed risk thresholds, thus obtaining derivative high-risk scenarios. These risk indicators may include: Time to Collision (TTC), Post-Encroachment Time (PET), traffic conflict point density, and travel time reliability index. Post-Encroachment Time can be used to assess rear-end collision risk. Traffic conflict point density can be the frequency or density of traffic conflicts occurring in a specific area or time period, used to identify accident hotspots. Traffic conflict point density = (number of conflict events) / (area or time window). The travel time reliability index can be the travel time standard deviation, the buffer time index (BTI), or the planned delay index, which can be used to assess road network stability. The aforementioned high-risk scenarios may include, but are not limited to, risk types (such as rear-end collision risk, bottleneck congestion, and secondary accident risk), geographical coordinates of the risk area (such as the G6 expressway from K50+300 to K52+100), and risk severity (the degree to which indicators such as TTC and PET exceed thresholds). As an example, the aforementioned risk thresholds could be TTC < 3 seconds or PET < 1.5 seconds.

[0062] Step 6: Based on the aforementioned traffic flow situation and the aforementioned derivative high-risk scenarios, match the traffic collaborative response plan database to obtain traffic collaborative response measures. In practice, the implementing entities can match the aforementioned traffic flow situation, as well as the risk type, geographical coordinate range of the risk area, and risk severity of the aforementioned derivative high-risk scenarios, with the traffic collaborative response plan database to obtain traffic collaborative response measures. These traffic collaborative response measures may include, but are not limited to: in areas where TTC < 3 seconds, controlling variable speed limit signs to display speed limits via the aforementioned dedicated communication network to reduce the speed limit from 80 km / h to 40 km / h; within the aforementioned risk area's geographical coordinate range, controlling variable information signs to display (e.g., "Maintain a 100-meter distance") via the aforementioned dedicated communication network; and at upstream entrance toll stations within the aforementioned risk area's geographical coordinate range, implementing flow restriction or closure measures via the aforementioned dedicated communication network and sending notifications of these measures to vehicles via traffic radio (FM / RDS) or navigation map app data interfaces. The aforementioned traffic collaborative response plan library can be a pre-set, structured, and digital collection of expert knowledge used to store and manage standardized response strategies for various anticipated high-risk traffic scenarios. This library can include: triggering conditions, based on quantitative risk indicators (e.g., TTC < 3 seconds, PET < 1.5 seconds) or event types (e.g., fog, icing); execution actions, specific equipment control commands, such as controlling variable speed limit signs to display specific speed values, publishing customized warning text on variable message signs, and operating toll plaza systems to implement flow control or closures; and a defined geographical coordinate range or road network area to ensure precise deployment of measures.

[0063] Step 7: Conduct a cost-benefit simulation of the aforementioned traffic coordination response measures to obtain safety benefits and efficiency costs. In practice, the implementing entities can input the aforementioned traffic coordination response measures into the traffic simulation software to obtain safety benefits and efficiency costs. The aforementioned safety benefits may include: the number of conflict points (such as rear-end collisions and side collisions), and the TTC / PET value (the fewer times the TTC / PET value is below the danger threshold, the higher the safety benefit). The aforementioned efficiency costs may include: travel time (the average travel time of the entire road network or a specific route and its variations), delays (time lost by vehicles due to congestion or traffic control), queue length (the maximum or average queue length at key nodes), and traffic capacity (the number of vehicles passing through a road segment per hour).

[0064] Step 8: Based on the aforementioned safety benefits and efficiency costs, implement the optimal traffic coordination response measures. In practice, the implementing entity can use the Pareto optimization method to determine the Pareto optimal solution for the aforementioned safety benefits and efficiency costs, which will then serve as the optimal traffic coordination response measures.

[0065] Step nine involves acquiring real-time traffic flow parameters and safety indicators from the aforementioned multi-source environmental monitoring equipment, and analyzing the actual effectiveness of the optimal traffic coordination response measures based on these parameters and indicators. In practice, the implementing entity can acquire the real-time traffic flow parameters and safety indicators collected by the multi-source environmental monitoring equipment via wired or wireless communication networks. Then, the implementing entity can input these parameters and indicators into the traffic simulation software and compare them with the simulated traffic flow situation after implementing the optimal traffic coordination response measures to obtain the actual effectiveness of these measures. The safety indicators may include Time to Collision (TTC), Post-Encroachment Time (PET), traffic conflict point density, and travel time reliability index. For example, the actual effectiveness of the optimal traffic coordination response measures could be: the average speed in the real-time traffic flow parameters is 10% higher than the speed in the simulated traffic flow situation, or the mainline queue length in the real-time traffic flow parameters is 500 meters shorter than the length in the simulated traffic flow situation.

[0066] The aforementioned steps one through nine and related content, as an inventive point of this disclosure, solve the technical problem that "the road networks around airports and train stations are complex, and in severe weather, it is necessary to simultaneously ensure the smooth flow of emergency vehicle lanes and the orderly evacuation of social vehicles, resulting in conflicting and complex measures. Traditional control measures often involve unidirectional command issuance (such as speed limits) and single measures (such as speed limits across the entire area), making it difficult to accurately predict traffic flow under weather conditions, lacking multi-measure coordination and fine spatial differentiation, leading to an increased risk of secondary accidents." Factors leading to an increased risk of secondary accidents often include: the complex road networks around airports and train stations, the need to simultaneously ensure the smooth flow of emergency vehicle lanes and the orderly evacuation of social vehicles in severe weather, and the conflicting and complex measures; traditional control measures often involve unidirectional command issuance (such as speed limits) and single measures (such as speed limits across the entire area), making it difficult to accurately predict traffic flow under weather conditions, lacking multi-measure coordination and fine spatial differentiation, leading to an increased risk of secondary accidents. Solving these factors can reduce the risk of secondary accidents and reduce casualties. To achieve this effect, firstly, a coupling correlation analysis is performed on the aforementioned environmental event knowledge object and the aforementioned multi-source environmental data feature set to obtain event correlation analysis results. Therefore, concurrent risk coupling relationships can be accurately identified. Second, based on the road network topology, traffic flow characteristic data, and the above event correlation analysis results, a dynamic link topology map of environment-traffic impact is constructed. This allows for visualization of risk transmission paths. Third, based on the above environmental evolution trend feature set and the above multi-source environmental element field set, a spatiotemporal propagation vector field is generated using a spatiotemporal prediction model. This enables advanced prediction of risk situations. Fourth, the above dynamic link topology map of environment-traffic impact and the above spatiotemporal propagation vector field are subjected to multi-dimensional coupled simulation to obtain the traffic flow situation. This allows for prediction of traffic flow deterioration trends. Fifth, based on the above traffic flow situation, derivative risk prediction is performed to obtain derivative high-risk scenarios. This allows for the location of high-risk conflict areas. Sixth, based on the above traffic flow situation and the above derivative high-risk scenarios, the traffic collaborative response plan library is matched to obtain traffic collaborative response measures. This allows for precise alignment of risk scenarios with control strategies. Seventh, cost-benefit simulation of the above traffic collaborative response measures is performed to obtain safety benefits and efficiency costs. This allows for the establishment of a scientific decision-making model with quantitative trade-offs. Eighth, based on the aforementioned safety benefits and efficiency costs, implement optimal traffic coordination response measures. This enables safe traffic flow management in high-risk scenarios. Ninth, acquire real-time traffic flow parameters and safety indicators from the aforementioned multi-source environmental monitoring equipment, and analyze the actual effectiveness of the optimal traffic coordination response measures based on these parameters. This allows for the formation of a self-improving evolutionary mechanism. Ultimately, this reduces the risk of secondary accidents and minimizes casualties.

[0067] The above embodiments of this disclosure have the following beneficial effects: The environmental early warning and collaborative response method based on traffic intelligent agents in some embodiments of this disclosure avoids excessive decline in traffic efficiency or waste of resources, reduces the risk of secondary accidents, and reduces casualties. Specifically, the reasons for excessive decline in traffic efficiency or waste of resources, as well as the lack of foresight and coordination, are as follows: Excessive decline in traffic efficiency or waste of resources: Commonly adopted extensive measures such as regional speed limits and road closures cannot be finely adjusted according to micro-road conditions and vehicle types, easily leading to excessive decline in traffic efficiency or waste of resources. Lack of foresight and coordination: It is difficult to accurately predict traffic flow under the influence of weather; vehicles and infrastructure are "information silos," unable to achieve collaborative risk avoidance, easily causing secondary accidents and resulting in casualties. Based on this, the environmental early warning and collaborative response method based on traffic intelligent agents in some embodiments of this disclosure first acquires a persistent multi-source environmental dataset from multi-source environmental monitoring equipment. This avoids system overload or data loss, ensuring the continuity and reliability of subsequent processing. Secondly, the aforementioned persistent multi-source environmental dataset is preprocessed to obtain a standard multi-source environmental dataset. This transforms the chaotic raw data into high-quality, well-organized, standardized data. Then, single-point feature extraction and spatial correlation are performed on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set. This elevates discrete point-like data into deep features that reflect spatiotemporal patterns and overall trends. Next, based on a pre-defined rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, environmental event knowledge objects are identified, and tiered early warning measures are implemented based on these environmental event knowledge objects. This generates a digital knowledge entity containing all elements such as event type, level, precise boundaries, and evolution trends, enabling targeted, tiered early warning measures. Finally, based on the multi-source environmental data feature set, event correlation analysis and situational projection are performed on the environmental event knowledge objects to identify derivative high-risk scenarios, and traffic collaborative response measures are implemented based on these derivative high-risk scenarios. Therefore, through refined guidance of "remote early warning - near-end command - strong control of the core area" and coordinated measures of vehicle-road-cloud collaboration, traffic efficiency can be maximized while ensuring safety, fundamentally reducing the risk of secondary accidents. This implementation method avoids excessive decline in traffic efficiency or waste of resources, reduces the risk of secondary accidents, and reduces casualties.

[0068] Continue to refer to Figure 2 As a response to the above Figure 1 The implementation of the method shown in this disclosure provides some embodiments of an environmental early warning and collaborative response device based on traffic intelligent agents. These device embodiments are similar to... Figure 1Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0069] like Figure 2 As shown, some embodiments of the traffic intelligent agent-based environmental early warning and collaborative response device 200 include: an acquisition unit 201, a preprocessing unit 202, an extraction unit 203, a determination unit 204, and an analysis unit 205. The acquisition unit 201 is configured to acquire a persistent multi-source environmental dataset from multi-source environmental monitoring equipment; the preprocessing unit 202 is configured to preprocess the persistent multi-source environmental dataset to obtain a standard multi-source environmental dataset; the extraction unit 203 is configured to perform single-point feature extraction and spatial correlation on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set; the determination unit 204 is configured to determine environmental event knowledge objects based on a preset judgment rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, and to execute tiered early warning measures based on the environmental event knowledge objects; the analysis unit 205 is configured to perform event correlation analysis and situational deduction on the environmental event knowledge objects based on the multi-source environmental data feature set to determine derived high-risk scenarios, and to execute traffic collaborative response measures based on the derived high-risk scenarios.

[0070] It is understandable that the units described in the device 200 are related to the reference. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units contained therein, and will not be repeated here.

[0071] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0072] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0073] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0074] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0075] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0076] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0077] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire a persistent multi-source environmental dataset from a multi-source environmental monitoring device; preprocess the persistent multi-source environmental dataset to obtain a standard multi-source environmental dataset; perform single-point feature extraction and spatial correlation on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set; determine environmental event knowledge objects based on a preset judgment rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, and execute tiered early warning measures based on the environmental event knowledge objects; and perform event correlation analysis and situational simulation on the environmental event knowledge objects based on the multi-source environmental data feature set to determine derivative high-risk scenarios, and execute traffic collaborative response measures based on the derivative high-risk scenarios.

[0078] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0080] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a preprocessing unit, an extraction unit, a determination unit, and an analysis unit. The names of these units do not necessarily limit the specific unit; for example, an acquisition unit may also be described as "a unit that acquires persistent multi-source environmental datasets from multi-source environmental monitoring devices."

[0081] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0082] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A collaborative response method for environmental early warning based on traffic intelligent agents, comprising: Acquire persistent multi-source environmental datasets from multi-source environmental monitoring devices; The persistent multi-source environment dataset is preprocessed to obtain a standard multi-source environment dataset; Single-point feature extraction and spatial correlation are performed on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set; Based on the preset judgment rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, environmental event knowledge objects are determined, and tiered early warning measures are executed based on the environmental event knowledge objects. Based on the multi-source environmental data feature set, event correlation analysis and situational simulation are performed on the environmental event knowledge object to identify derivative high-risk scenarios, and traffic collaborative response measures are implemented based on the derivative high-risk scenarios.

2. The method according to claim 1, wherein, The multi-source environmental monitoring equipment refers to various monitoring devices deployed along the road, including: six-element monitoring equipment, visibility monitors, and road surface condition detectors.

3. The method according to claim 1, wherein, The acquisition of persistent multi-source environmental datasets from multi-source environmental monitoring devices includes: The multi-source environmental dataset collected by the environmental monitoring equipment is acquired through a wired or wireless communication network. The multi-source environmental dataset includes: temperature, humidity, wind speed, wind direction, air pressure, rainfall, visibility, and road surface condition. The multi-source environment dataset is cached using a message queue to obtain a multi-source environment dataset cache. Based on the time-series database, the multi-source environment dataset is cached and stored to obtain a persistent multi-source environment dataset.

4. The method according to claim 1, wherein, The preprocessing of the persistent multi-source environment dataset to obtain a standard multi-source environment dataset includes: Anomaly processing is performed on the persistent multi-source environment dataset to obtain an anomaly-corrected multi-source environment dataset; The anomaly correction multi-source environment dataset is augmented to obtain a augmented multi-source environment dataset. The data is then standardized to complete the multi-source environment dataset, resulting in a standard multi-source environment dataset.

5. The method according to claim 1, wherein, The implementation of tiered early warning measures based on the environmental event knowledge object includes: Based on the aforementioned environmental event knowledge object, differentiated early warning information is issued at different spatial distances along the traffic flow direction as follows: A forward-looking warning is issued at a first preset distance from the knowledge object of the environmental event; At a second preset distance from the environmental event knowledge object, specific instruction information is issued; Within the aforementioned environmental event knowledge object, publish strongly constrained information; Within the knowledge object of the environmental event, control the lighting guidance facilities deployed on the roadside.

6. The method according to claim 1, wherein, The step of performing single-point feature extraction and spatial correlation on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set includes: Temporal analysis was performed on the standard multi-source environmental dataset to obtain a temporal smoothing feature set; The change trend of the standard multi-source environmental dataset is quantified to obtain an environmental evolution trend feature set. The standard multi-source environmental dataset is subjected to derivative parameter quantification to obtain a comprehensive environmental index feature set; Obtain the geographic information set of the multi-source environmental monitoring equipment; Spatially correlate the geographic information set with the standard multi-source environmental dataset and the environmental comprehensive index feature set to obtain a multi-source environmental element field set. The time-series smoothing feature set, the environmental evolution trend feature set, and the multi-source environmental element field set are determined as the multi-source environmental data feature set.

7. An environmental early warning and collaborative response device based on traffic intelligent agents, comprising: The acquisition unit is configured to acquire persistent multi-source environmental datasets from multi-source environmental monitoring devices; The preprocessing unit is configured to preprocess the persistent multi-source environment dataset to obtain a standard multi-source environment dataset. The extraction unit is configured to perform single-point feature extraction and spatial correlation on the standard multi-source environmental dataset to obtain a multi-source environmental data feature set. The determining unit is configured to determine environmental event knowledge objects based on a preset judgment rule base, the standard multi-source environmental dataset, and the multi-source environmental data feature set, and to execute tiered early warning measures based on the environmental event knowledge objects; The analysis unit is configured to perform event correlation analysis and situational simulation on the environmental event knowledge object based on the multi-source environmental data feature set, in order to identify derivative high-risk scenarios, and to execute traffic collaborative response measures based on the derivative high-risk scenarios.

8. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 6.

Images