Road state early warning method, system and device and storage medium

Abstract

The invention relates to the technical field of data processing, and particularly provides a road state early warning method, system and device and a storage medium, and the method comprises the steps: collecting road state information which comprises environment information, flow information, accident information and congestion information; generating an abnormal event and an abnormal event position based on the state information, and generating a road section limiting speed and early warning prompt information for the abnormal event; and calling a target road display screen based on the position of the abnormal event, and outputting the road section limiting speed and early warning prompt information of the abnormal event to the target road display screen. According to the invention, the road state is collected through the sensor, abnormity screening is carried out on the road state, the abnormal events are generated based on the screening result, after the abnormal events are integrated, the display screen is controlled to carry out display early warning, and the road management quality is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a road status early warning method, system, equipment and storage medium. Background Art

[0002] Bad weather such as rain, snow and fog occurs frequently, seriously affecting the normal traffic on the road. Night driving and fatigue driving have a greater impact on driving safety. Vehicles are intertwined in the interchange area, and speed and lane changes are frequent. The cross-sectional speed difference and the speed difference between adjacent lanes are large. The main line merging and diverging areas are under great pressure, prone to congestion and accidents. Accidents are frequent in merging and diverging sections, and safety issues are prominent in the areas adjacent to the interchange. It is very necessary to set up intelligent road variable information boards and take corresponding measures in a timely manner to ensure that the road sections are fast, safe and unobstructed. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the present invention provides a road status early warning method, system, device and storage medium to solve the above-mentioned technical problems.

[0004] In a first aspect, the present invention provides a road state early warning method, comprising: Collecting road status information, including environmental information, traffic information, accident information and congestion information; Generate an abnormal event and an abnormal event location based on the state information, and generate a road section speed limit and warning prompt information for the abnormal event; The target road display screen is retrieved based on the abnormal event location, and the road section speed limit and warning prompt information of the abnormal event are output to the target road display screen.

[0005] In an optional implementation, collecting road status information, the status information including environment information, flow information, accident information and congestion information, includes: Establishing a communication connection with a sensor combination deployed at a key node of the road through wireless communication, wherein the sensor combination includes an environmental monitoring sensor, a flow monitoring sensor, and a camera; Assigning a unique signal code to the sensor and binding the signal code to the key node location code where the sensor is located; Receive a sensor signal, convert the sensor signal into state data of a specified format, and save the state data into a file named after the key node position code based on the signal code carried by the sensor signal; Using a Kalman filter to remove noise from the state data, and converting the state data into an environmental data sequence, a vehicle flow value sequence, accident description data, and congestion description data; Input the state data into the pre-trained neural network model; According to the output of the neural network, the data of each sensor is weighted and fused to predict the accident probability, congestion level and congestion duration.

[0006] In an optional implementation, generating an abnormal event and an abnormal event location based on the state information, and generating a road section speed limit and warning prompt information for the abnormal event, includes: If the congestion level reaches the set level threshold, an abnormal event is generated for the corresponding key node, and the congestion level and congestion time are written into the abnormal event; If there is accident information or the accident probability reaches the set threshold, an abnormal event is generated for the corresponding key node, and the accident information or high accident probability is written into the abnormal event; If there are abnormal events at adjacent key nodes, the abnormal events at adjacent key nodes are merged into one abnormal event; If there are multiple abnormal events at the same key node, the multiple abnormal events at the same key node are merged into one abnormal event; A correspondence between congestion levels and speed limits is preset, and based on the correspondence and the congestion level of the abnormal event, a road section speed limit is generated for the abnormal event, and corresponding warning prompt information is generated based on the content of the abnormal event.

[0007] In an optional embodiment, the target road display screen is retrieved based on the abnormal event location, and the road section speed limit and warning prompt information of the abnormal event are output to the target road display screen, including: Retrieving multiple upstream nodes of the key node where the abnormal event is located, where the upstream nodes are nodes that the vehicle passes before reaching the key node where the abnormal event is located; Calculate the distance from the upstream node to the location of the abnormal event; Sorting the abnormal events from near to far based on the distance, and displaying the speed limit and warning information of the road section of the abnormal event on the display screen of the upstream node according to the sorting; An importance score is generated for the abnormal event according to the congestion level and congestion time of the abnormal event, and a corresponding display font size and display font color are matched for the abnormal event based on the importance score.

[0008] In a second aspect, the present invention provides a road status warning system, comprising: A status collection module, used to collect road status information, including environmental information, traffic information, accident information and congestion information; An event generation module, used to generate abnormal events and abnormal event locations based on the state information, and generate road section speed limit and warning prompt information for the abnormal events; The event display module is used to retrieve the target road display screen based on the abnormal event location, and output the road section speed limit and warning prompt information of the abnormal event to the target road display screen.

[0009] In an optional implementation, the status collection module includes: A communication establishing unit, used to establish a communication connection with a sensor combination deployed at a key node of the road through wireless communication, wherein the sensor combination includes an environmental monitoring sensor, a flow monitoring sensor, and a camera; A position binding unit, used to assign a unique signal code to the sensor and bind the signal code to a key node position code where the sensor is located; A data conversion unit, used for receiving a sensor signal, converting the sensor signal into state data of a specified format, and saving the state data into a file named after the key node position code based on the signal code carried by the sensor signal; A denoising processing unit, used to remove noise from the state data by using a Kalman filter, and convert the state data into an environmental data sequence, a vehicle flow value sequence, accident description data, and congestion description data; A feature extraction unit, used to input state data into a pre-trained neural network model; The congestion prediction unit is used to perform weighted fusion of the data from various sensors based on the output of the neural network to predict the accident probability, congestion level and congestion duration.

[0010] In an optional implementation, the event generation module includes: A first generating unit, configured to generate an abnormal event for a corresponding key node if the congestion level reaches a set level threshold, and write the congestion level and congestion time into the abnormal event; A second generating unit is used to generate an abnormal event for the corresponding key node if there is accident information or the accident probability reaches a set threshold, and write the accident information or high accident incidence into the abnormal event; A first merging unit, configured to merge the abnormal events of adjacent key nodes into one abnormal event if both adjacent key nodes have abnormal events; A second merging unit is used to merge the multiple abnormal events of the same key node into one abnormal event if there are multiple abnormal events at the same key node; The parameter generation unit is used to pre-set the correspondence between the congestion level and the speed limit, generate a road section speed limit for the abnormal event based on the correspondence and the congestion level of the abnormal event, and generate corresponding warning prompt information based on the content of the abnormal event.

[0011] In an optional implementation, the event display module includes: A target retrieval unit, used to retrieve multiple upstream nodes of the key node where the abnormal event is located, wherein the upstream nodes are nodes that the vehicle passes before reaching the key node where the abnormal event is located; A distance calculation unit, used to calculate the distance from the upstream node to the location of the abnormal event; An event sorting unit, used to sort the abnormal events from near to far based on the distance, and display the speed limit and warning prompt information of the road section of the abnormal event on the display screen of the upstream node according to the sorting; The display setting unit is used to generate an importance score for the abnormal event according to the congestion level and congestion time of the abnormal event, and match a corresponding display font size and display font color for the abnormal event based on the importance score.

[0012] In a third aspect, a device is provided, including: A memory, used for storing a road status warning program; A processor is used to implement the steps of the road state warning method provided in the first aspect when executing the road state warning program.

[0013] In a fourth aspect, a computer-readable storage medium is provided, on which a road status warning program is stored. When the road status warning program is executed by a processor, the steps of the road status warning method provided in the first aspect are implemented.

[0014] The beneficial effect of the present invention lies in that the road status warning method, system, equipment and storage medium provided by the present invention collect road status through sensors, perform abnormal screening on road status, generate abnormal events based on the screening results, and after integrating the abnormal events, control the display screen to display warnings, thereby improving the quality of road management.

[0015] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0018] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.

[0019] Figure 3 A schematic diagram of the structure of a device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0022] The key terms appearing in the present invention are explained below.

[0023] Kalman filter is a highly efficient recursive filter (autoregressive filter) that can estimate the state of a dynamic system from a series of incomplete and noisy measurements. This filter was proposed by Rudolf E. Kálmán in 1960 and is now widely used in aerospace, automotive navigation systems, robot navigation, economics, signal processing and control theory.

[0024] The Kalman filter is based on the state space representation of linear dynamic systems. It assumes that the system state is linear and that both process noise and observation noise are Gaussian distributed. This property of Gaussian distribution makes calculations involving these noises relatively simple, especially when it comes to prediction and filtering. The basic Kalman filter can be divided into two main steps: prediction and update.

[0025] Prediction step: predict the current state based on the previous state of the system and the control inputs, along with the estimated uncertainty (covariance) of the current state.

[0026] Update step: Use the new measurement data to update the prediction, calculate a gain (Kalman gain) which determines which part of the prediction or measurement is more reliable, and then update the estimated state and estimated uncertainty.

[0027] The road state warning method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the road state warning system runs in the computer device.

[0028] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be a road status warning system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0029] like Figure 1 As shown, the method includes: S1. Collect road status information, which includes environmental information, traffic information, accident information and congestion information.

[0030] Systematically collect various types of information related to road conditions to ensure a comprehensive understanding of road conditions. Specific status information collected includes but is not limited to: Environmental information: covers weather conditions (such as sunny, rainy, snowy, etc.), visibility, road temperature and humidity, etc. This information is crucial to road driving safety.

[0031] Traffic information: Obtain road traffic volume, speed distribution and traffic density in real time through traffic monitoring equipment or vehicle GPS data to assess road capacity and potential congestion risks.

[0032] Accident information: Timely collection of detailed information on traffic accidents, including the time, location, type (such as rear-end collision, rollover, etc.), number of vehicles involved and casualties, etc. This information is crucial for rapid response and handling of accidents.

[0033] Congestion information: Identify and track road congestion through traffic flow data and user feedback, including the start time, duration, impact range and severity of the congestion.

[0034] S2. Generate an abnormal event and an abnormal event location based on the state information, and generate a road section speed limit and warning prompt information for the abnormal event.

[0035] Based on the collected road status information, we use advanced data analysis technology and algorithms to intelligently identify and generate abnormal events and the specific locations of these events. Abnormal events may include but are not limited to traffic accidents, severe congestion, road construction, bad weather, etc. For each abnormal event, we further generate the following key information: Road speed limit: Dynamically adjust the speed limit of the affected road section based on the nature, severity and road conditions of the abnormal event to ensure driving safety.

[0036] Warning prompt information: Design and generate clear and intuitive warning information to convey to the driver the type, location, impact range and recommended actions of abnormal events, such as detour, slow down, etc., through text, icons or animations.

[0037] S3. Retrieve a target road display screen based on the abnormal event location, and output the road section speed limit and warning prompt information of the abnormal event to the target road display screen.

[0038] After determining the location of the abnormal event, we quickly retrieve road display screen resources located at or near the scene of the abnormal event. These display screens are usually located at highway entrances, important intersections or congested sections, and are important channels for conveying information to passing drivers. We use advanced communication technology to push the generated speed limit and warning prompt information of the abnormal event section to the target road display screen in real time and accurately. The key to this step is to ensure the timeliness and accuracy of the information so that drivers can respond quickly and adjust their driving plans, thereby effectively avoiding or reducing the impact of abnormal events on traffic flow and improving road traffic efficiency and safety.

[0039] In an embodiment of the present invention, based on step S1, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0040] S101. Establish a communication connection with a sensor combination deployed at key road nodes through wireless communication, wherein the sensor combination includes an environmental monitoring sensor, a flow monitoring sensor, and a camera.

[0041] Use advanced wireless communication protocols (such as LoRa, Zigbee, NB-IoT or 5G, etc.) to establish stable and reliable communication connections with sensor combinations deployed at key road nodes (such as intersections, bridges, tunnel entrances, highway service areas, etc.). Sensor combinations include but are not limited to: Environmental monitoring sensors: used to monitor environmental parameters such as air quality (such as PM2.5 and PM10 concentrations), temperature, humidity, wind speed, wind direction, and road conditions (such as water accumulation, ice, cracks, etc.).

[0042] Traffic monitoring sensor: uses geomagnetic induction, radar or video analysis technology to monitor vehicle flow, speed, vehicle model distribution and other data in real time to provide basic information for traffic management.

[0043] Camera: used to capture real-time images of the road. It not only supports traffic monitoring, but also detects traffic violations, traffic accidents and congestion through image recognition technology.

[0044] S102. Allocate a unique signal code to the sensor, and bind the signal code to the key node position code where the sensor is located.

[0045] To ensure the uniqueness and traceability of each sensor in the system, we assign a unique signal code to each sensor. At the same time, the signal code is bound to the key node location code where the sensor is located. The location code is usually based on a geographic coordinate system (such as GPS coordinates) or a custom road node numbering system. This step provides the basis for subsequent data processing and event positioning.

[0046] S103. Receive a sensor signal, convert the sensor signal into state data in a specified format, and save the state data into a file named after the key node position code based on the signal code carried by the sensor signal.

[0047] Continuously receive signals from each sensor, and use a dedicated signal decoder and data processing module to convert the sensor signal into status data in a specified format. These status data include but are not limited to environmental monitoring data, flow monitoring data, and video image data. According to the signal coding, the system saves the status data to a file named after the key node location coding to facilitate subsequent data management and query.

[0048] S104. Use a Kalman filter to remove noise from the state data, and convert the state data into an environmental data sequence, a vehicle flow value sequence, accident description data, and congestion description data.

[0049] In order to improve data quality and accuracy, we use Kalman filter to remove noise and smooth the state data. Kalman filter can dynamically adjust the state estimate based on the state estimate of the previous moment and the observed value of the current moment, thereby effectively reducing the impact of noise. The processed state data is converted into a series of time series data, including environmental data series (such as air quality change trend), traffic flow value series (such as traffic flow changes over time), accident description data (such as accident type, location, time, etc.) and congestion description data (such as congestion start time, duration, impact range, etc.).

[0050] In a specific example, suppose there is an environmental monitoring sensor that measures and reports the PM2.5 concentration in the air in real time. Since the sensor may be interfered by various external factors (such as temperature fluctuations, electromagnetic interference, etc.), the data it reports may contain noise.

[0051] Kalman filter applications: Initialization: Set the initial state of the Kalman filter (such as the initial estimate of PM2.5 concentration) and the initial covariance (indicating the uncertainty of the estimate).

[0052] Prediction step: Based on the estimated PM2.5 concentration at the previous moment and the dynamic model of the system (which may be a simple linear model assuming that the PM2.5 concentration changes slowly over time), predict the PM2.5 concentration at the current moment.

[0053] Observation steps: Get the PM2.5 concentration observation value at the current moment from the sensor.

[0054] Update step: Use the Kalman gain (a value between 0 and 1 that indicates the relative credibility between the observed and predicted values) to update the estimated value of PM2.5 concentration. The higher the Kalman gain, the more reliable the observed value; conversely, the more reliable the predicted value.

[0055] Iteration: Repeat the above steps. Over time, the Kalman filter will gradually converge to the true PM2.5 concentration value while reducing the impact of noise.

[0056] Conversion results: The data processed by the Kalman filter can be converted into time series data, such as a PM2.5 concentration change trend chart per hour or per minute.

[0057] S105. Input the state data into a pre-trained neural network model.

[0058] The preprocessed state data is input into a pre-trained neural network model. The neural network model may include a convolutional neural network (CNN) for image recognition (such as accident detection), a recurrent neural network (RNN) or a long short-term memory network (LSTM) for time series prediction (such as traffic flow prediction, congestion duration prediction), etc. The neural network model can realize intelligent analysis and prediction of current data by learning the patterns and rules in historical data.

[0059] CNN for image recognition: Suppose we have a camera that captures real-time images of the road. We can use CNN to identify traffic accidents (such as vehicle collisions, rear-end collisions, etc.) in the images.

[0060] Implementation: The image captured by the camera is input into the pre-trained CNN model, which will output a probability value indicating whether there is a traffic accident in the image. If the probability value exceeds a certain threshold, the system considers that a traffic accident has occurred.

[0061] LSTM is used for time series prediction: Suppose we have a series of historical traffic flow data, and we want to predict the traffic flow in the future.

[0062] Implementation: Input historical traffic flow data into a pre-trained LSTM model, which will output traffic flow forecasts for a period of time in the future. These forecasts can be used for traffic management and planning.

[0063] S106. Based on the output of the neural network, the data of each sensor is weighted and fused to predict the accident probability, congestion level and congestion duration.

[0064] According to the output of the neural network, a weighted fusion method is used to comprehensively consider information from different sensors and different types of data to improve the accuracy and reliability of the prediction results. Weighted fusion can be dynamically adjusted based on factors such as sensor reliability and data relevance. Ultimately, the system can predict the probability of an accident (such as the possibility of a traffic accident occurring on a certain road section within a certain period of time), the level of congestion (such as mild, moderate, and severe congestion), and the duration of congestion (such as how long the congestion is expected to last), providing decision support for traffic management departments, optimizing traffic resource allocation, and improving road traffic efficiency and safety.

[0065] In a specific example, suppose we have multiple sensors (such as environmental monitoring sensors, traffic monitoring sensors, and cameras) that provide multiple types of data about the road status.

[0066] Weighted Fusion: Determine weights: Assign a weight to each sensor’s data based on factors such as the reliability of the sensor, the relevance of the data, etc. For example, if the historical data of a sensor is highly consistent with the actual observations, we can assign it a higher weight.

[0067] Fusion data: The data from different sensors are weighted and fused according to their weights to obtain a comprehensive road state estimate.

[0068] Prediction: Based on the fused data, a neural network model is used to make predictions (such as accident probability, congestion level, and congestion duration).

[0069] Result output: The system finally outputs a comprehensive road status report, including information such as accident probability, congestion level and congestion duration, to provide decision support for traffic management departments.

[0070] In an embodiment of the present invention, based on step S2, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0071] S201. If the congestion level reaches a set level threshold, an abnormal event is generated for the corresponding key node, and the congestion level and congestion time are written into the abnormal event.

[0072] When the system detects that the congestion level of a key node or the predicted congestion level reaches or exceeds the preset level threshold (such as the set severe congestion level), it will automatically generate an abnormal event for the key node. In the generated abnormal event, the system will record in detail the level of congestion (such as severe congestion) and the specific time when the congestion started (accurate to minutes or seconds). This step is to capture road congestion in a timely manner and provide accurate information for subsequent processing.

[0073] S202. If there is accident information or the accident probability reaches a set threshold, an abnormal event is generated for the corresponding key node, and the accident information or high accident incidence is written into the abnormal event.

[0074] If the system detects that a key node has clear accident information (such as a traffic accident image captured by a camera), or the accident probability predicted by the neural network model reaches or exceeds the preset threshold (such as an accident probability higher than 80%), the system will also generate an abnormal event for the key node. In the abnormal event, the system will write specific accident information (such as accident type, location, time, etc.), or mark it as a "high-incidence" area. This step helps to quickly respond to traffic accidents and ensure road safety.

[0075] S203. If there are abnormal events at adjacent key nodes, the abnormal events at the adjacent key nodes are merged into one abnormal event.

[0076] In order to improve the efficiency and accuracy of abnormal event processing, the system will check the abnormal event status of adjacent key nodes. If there are abnormal events (whether congestion, accidents or other types) at adjacent key nodes, the system will automatically merge these abnormal events into a larger abnormal event. The merged abnormal event will contain information from all relevant key nodes, which will help traffic management departments to have a more comprehensive understanding of road conditions and make corresponding decisions.

[0077] Detect adjacent key nodes: The system first defines the adjacency relationships of key nodes, which are usually based on the road network topology.

[0078] The adjacency relationship can be physical (such as between two intersections) or logical (such as nodes with a large mutual influence determined based on the traffic flow model).

[0079] Abnormal event detection and matching: The system will continuously monitor abnormal events at each key node.

[0080] When abnormal events are detected at adjacent key nodes, the system will perform event matching to confirm whether these events can be merged.

[0081] Event merging rules: If the abnormal events of adjacent key nodes are of the same type (such as congestion), they are directly merged into a larger congestion event, and the congestion level and scope are updated.

[0082] If the abnormal events are of different types (e.g. one is congestion and the other is an accident), the system will make a comprehensive judgment based on factors such as the severity of the event and the scope of impact to decide whether to merge them into one comprehensive event.

[0083] The merged abnormal events will contain information of all relevant key nodes, such as location, time, type, level, etc.

[0084] S204. If there are multiple abnormal events at the same key node, the multiple abnormal events at the same key node are merged into one abnormal event.

[0085] For the same key node, if the system detects multiple abnormal events of different types (such as congestion and accidents at the same time), or the same type of abnormal events occur multiple times in a short period of time, the system will automatically merge these abnormal events into one. The merged abnormal events will comprehensively reflect the overall status of the key node, avoiding information redundancy and repeated processing.

[0086] Detect abnormal events at the same key node: The system will continuously monitor abnormal events at each key node, including the type, time, and level of the event.

[0087] Event classification and screening: The system will classify abnormal events according to their types, such as congestion, accidents, equipment failures, etc.

[0088] For abnormal events of the same type, the system will further screen to determine whether they are different manifestations or repeated detections of the same event.

[0089] Event merging rules: If multiple abnormal events of the same type occur at the same key node within a short period of time (such as multiple consecutive detections of congestion), the system will merge these events into a continuous event and update the start time, duration, and level of the congestion.

[0090] If multiple abnormal events of different types (such as congestion and accidents) occur at the same key node at the same time, the system will consider the severity of the events and their mutual impact and decide whether to merge these events into a comprehensive event.

[0091] The merged abnormal events will comprehensively reflect the overall status of the key node, including information on all related events.

[0092] Information update and release: The merged abnormal event information will be updated to the traffic management system in a timely manner.

[0093] The system will release the merged abnormal event information through the corresponding channels so that relevant departments and personnel can take timely measures to respond.

[0094] In order to improve the rationality of abnormal event merging, the following means are also used for adjustment: Time window: When merging abnormal events, the system will set a time window. If the time interval between two events exceeds this time window, they will not be considered as adjacent or simultaneous events for merging.

[0095] Event priority: When merging different types of abnormal events, the system will consider the priority of the event. For example, accidents usually have a higher priority, so accident information will be given priority when merging.

[0096] Event level: The system will assign different levels to abnormal events according to their severity and impact. When merging events, the system will comprehensively consider the levels of all related events to determine the level of the merged event.

[0097] Manual intervention: Although the system can automatically merge abnormal events, in some cases (such as complex accidents, large-scale congestion, etc.), manual intervention and adjustment may be required to ensure the accuracy and rationality of the merged results.

[0098] S205. Preset a correspondence between congestion levels and speed limits, generate a road speed limit for the abnormal event based on the correspondence and the congestion level of the abnormal event, and generate corresponding warning information based on the content of the abnormal event.

[0099] In order to effectively deal with abnormal road conditions, the system will generate a corresponding speed limit for the road section where the abnormal event occurs based on the preset correspondence between the congestion level and the speed limit. For example, when the congestion level reaches severe, the system may reduce the speed limit of the road section to 40 km / h or lower. At the same time, the system will also generate corresponding early warning information based on the specific content of the abnormal event (such as congestion level, accident information, etc.).

[0100] In an embodiment of the present invention, based on step S3, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0101] S301. Retrieve multiple upstream nodes of the key node where the abnormal event is located, where the upstream nodes are nodes that the vehicle passes before reaching the key node where the abnormal event is located.

[0102] After determining the location of the abnormal event, the system further retrieves multiple upstream nodes of the key node where the abnormal event is located. The upstream nodes are nodes that the vehicle passes before reaching the key node where the abnormal event is located. These upstream nodes are the front end of the traffic flow and are of great significance for early warning and traffic diversion.

[0103] Suppose that in a city's traffic network, there is a key node A, which connects multiple main roads and is an important hub for urban traffic. One day, the system detects that a serious traffic accident occurred at node A, causing serious traffic congestion at the node.

[0104] After determining the location of the abnormal event, the system further retrieves multiple upstream nodes of node A, which are nodes that the vehicle passes before reaching the key node where the abnormal event is located. These upstream nodes include node B and node C directly connected to node A, and nodes on road D indirectly connected to A through other nodes.

[0105] S302. Calculate the distance from the upstream node to the abnormal event location.

[0106] Using the road network topology and traffic flow model, the actual distance from each upstream node to the location of the abnormal event is calculated. This distance information will be used for subsequent sorting and display of abnormal events.

[0107] S303. Sort by distance and display information on the upstream node display The system sorts abnormal events from near to far according to the distance from the upstream node to the location of the abnormal event. The sorted abnormal events will display the speed limit and warning information of the road section on the display screen of the upstream node in order. In this way, the driver can obtain relevant information in advance when approaching the abnormal event and be prepared for it.

[0108] S304. Generate importance score of abnormal events and match display attributes The system generates an importance score for the abnormal event based on the congestion level and congestion time. The higher the congestion level and the longer the congestion time, the higher the importance score of the abnormal event.

[0109] Based on the importance score, the system matches the corresponding display font size and display font color for each abnormal event. Abnormal events with high importance scores will be displayed with larger fonts and eye-catching colors to attract the driver's attention.

[0110] Through the above steps, the intelligent traffic management system can not only generate early warning information in time when abnormal events occur and display it on the target road display screen, but also sort and prioritize abnormal events according to the actual situation of the abnormal events and the location information of the upstream nodes, and display the corresponding information on the display screen of the upstream nodes. Such a design not only improves the efficiency and safety of traffic management, but also provides drivers with more accurate, timely and useful road condition information, helping them make more informed driving decisions.

[0111] The following is a specific application example: Collect events that may occur on the road, such as road maintenance, weather events, road accidents, vehicle accidents, etc., and save them in the database.

[0112] Collect information about road cameras, radars, bayonet recognition units, weather stations, visibility monitors, variable information boards, computer rooms, and other equipment, including data such as pile number, location, equipment code, status, and type, save it in the database, set thresholds for various types of equipment, trigger events when parameters are greater than or less than a certain value, obtain information boards related to event settings, and display them on the information boards.

[0113] Information board preset, editing, publishing and other functions, displaying information board content on the web page, simulating motion effects and switching effects.

[0114] The preset editing module of the information board can add preset categories, edit commonly used information, upload commonly used pictures, and emergency presets as a general setting for handling similar events.

[0115] The editor of the information board associates events, equipment types, event levels, and road section types.

[0116] Displays and related devices can be divided into gantry type and cantilever type. The gantry type is set up on the road and can be set up as a whole or in lanes. The cantilever type is set up beside the road. Event level settings: no level, Level VI - ordinary, Level V - minor, Level IV - general, Level III - large, Level I - extra large, Level II - major.

[0117] Road section settings: reminder area (2KM-3KM), control area (300-500m), organization area (500-700m), event area (0-300m), congestion area (700-2KM), all (whole road section).

[0118] The information editing interface of the information board obtains the list of information board equipment. According to different types, different styles of information board simulation components are generated in the page. You can edit the text in the component and modify the properties to support font, color, font size, horizontal spacing, line spacing, retention time, effective time, alignment and other field information. You can also drag and drop the pre-compiled text and pictures in the information board preset, set the screen entry mode and effective time. In the cantilever lane mode, the information board simulation component is evenly divided into components, and the lane prompt information can be set separately in each module.

[0119] Click on the information board to publish. After publishing, when an event occurs, when the event detection module sends a message in, the set information board content is sent to the corresponding information board to alert road participants.

[0120] Information board release record list: Click on the variable information board, and the map will show the location of each information board. Click on a specific point to display the information displayed on the information board and whether there are any abnormalities.

[0121] In some embodiments, the road status warning system may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the road status warning system may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Function of road status warning.

[0122] In this embodiment, the road status warning system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules of the system 200 may include: a state collection module 210, an event generation module 220 and an event display module 230. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0123] A status collection module, used to collect road status information, including environmental information, traffic information, accident information and congestion information; An event generation module, used to generate abnormal events and abnormal event locations based on the state information, and generate road section speed limit and warning prompt information for the abnormal events; The event display module is used to retrieve the target road display screen based on the abnormal event location, and output the road section speed limit and warning prompt information of the abnormal event to the target road display screen.

[0124] Optionally, as an embodiment of the present invention, the status collection module includes: A communication establishing unit, used to establish a communication connection with a sensor combination deployed at a key node of the road through wireless communication, wherein the sensor combination includes an environmental monitoring sensor, a flow monitoring sensor, and a camera; A position binding unit, used to assign a unique signal code to the sensor and bind the signal code to a key node position code where the sensor is located; A data conversion unit, used for receiving a sensor signal, converting the sensor signal into state data of a specified format, and saving the state data into a file named after the key node position code based on the signal code carried by the sensor signal; A denoising processing unit, used to remove noise from the state data by using a Kalman filter, and convert the state data into an environmental data sequence, a vehicle flow value sequence, accident description data, and congestion description data; A feature extraction unit, used to input state data into a pre-trained neural network model; The congestion prediction unit is used to perform weighted fusion of the data from various sensors based on the output of the neural network to predict the accident probability, congestion level and congestion duration.

[0125] Optionally, as an embodiment of the present invention, the event generation module includes: A first generating unit, configured to generate an abnormal event for a corresponding key node if the congestion level reaches a set level threshold, and write the congestion level and congestion time into the abnormal event; A second generating unit is used to generate an abnormal event for the corresponding key node if there is accident information or the accident probability reaches a set threshold, and write the accident information or high accident incidence into the abnormal event; A first merging unit, configured to merge the abnormal events of adjacent key nodes into one abnormal event if both adjacent key nodes have abnormal events; A second merging unit is used to merge the multiple abnormal events of the same key node into one abnormal event if there are multiple abnormal events at the same key node; The parameter generation unit is used to pre-set the correspondence between the congestion level and the speed limit, generate a road section speed limit for the abnormal event based on the correspondence and the congestion level of the abnormal event, and generate corresponding warning prompt information based on the content of the abnormal event.

[0126] Optionally, as an embodiment of the present invention, the event display module includes: A target retrieval unit, used to retrieve multiple upstream nodes of the key node where the abnormal event is located, wherein the upstream nodes are nodes that the vehicle passes before reaching the key node where the abnormal event is located; A distance calculation unit, used to calculate the distance from the upstream node to the location of the abnormal event; An event sorting unit, used to sort the abnormal events from near to far based on the distance, and display the speed limit and warning prompt information of the road section of the abnormal event on the display screen of the upstream node according to the sorting; The display setting unit is used to generate an importance score for the abnormal event according to the congestion level and congestion time of the abnormal event, and match a corresponding display font size and display font color for the abnormal event based on the importance score.

[0127] Figure 3 The road state early warning method provided for the embodiment of the present application can be applied to equipment. Those skilled in the art will appreciate that the equipment structure involved in the embodiment of the present invention does not constitute a limitation on the equipment, and the equipment may include more or less components than shown, or combine certain components, or arrange different components. In an embodiment of the present invention, the equipment includes but is not limited to a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The equipment may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0128] The device 300 may include: a processor 310, a memory 320 and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0129] The memory 320 may be used to store the execution instructions of the processor 310, and the memory 320 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the device 300 is enabled to perform some or all of the steps in the following method embodiments.

[0130] The processor 310 is the control center of the storage device, and uses various interfaces and lines to connect various parts of the entire electronic device. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of a plurality of packaged ICs with the same or different functions. For example, the processor 310 can include only a central processing unit (CPU). In an embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0131] The communication unit 330 is used to establish a communication channel so that the storage device can communicate with other devices, receive user data sent by other devices or send user data to other devices.

[0132] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0133] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer device (which can be a personal computer, a server, or a second device, a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0134] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0135] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0136] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0138] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A road status early warning method, characterized in that: include: Collecting road status information, including environmental information, traffic information, accident information and congestion information; Generate an abnormal event and an abnormal event location based on the state information, and generate a road section speed limit and warning prompt information for the abnormal event; The target road display screen is retrieved based on the abnormal event location, and the road section speed limit and warning prompt information of the abnormal event are output to the target road display screen.

2. The method according to claim 1, characterized in that Collect road status information, including environmental information, traffic information, accident information and congestion information, including: Establishing a communication connection with a sensor combination deployed at a key node of the road through wireless communication, wherein the sensor combination includes an environmental monitoring sensor, a flow monitoring sensor, and a camera; Assigning a unique signal code to the sensor and binding the signal code to the key node location code where the sensor is located; Receive a sensor signal, convert the sensor signal into state data of a specified format, and save the state data into a file named after the key node position code based on the signal code carried by the sensor signal; Using a Kalman filter to remove noise from the state data, and converting the state data into an environmental data sequence, a vehicle flow value sequence, accident description data, and congestion description data; Input the state data into the pre-trained neural network model; According to the output of the neural network, the data of each sensor is weighted and fused to predict the accident probability, congestion level and congestion duration.

3. The method according to claim 2, characterized in that Generate an abnormal event and an abnormal event location based on the state information, and generate a road section speed limit and warning prompt information for the abnormal event, including: If the congestion level reaches the set level threshold, an abnormal event is generated for the corresponding key node, and the congestion level and congestion time are written into the abnormal event; If there is accident information or the accident probability reaches the set threshold, an abnormal event is generated for the corresponding key node, and the accident information or high accident probability is written into the abnormal event; If there are abnormal events at adjacent key nodes, the abnormal events at adjacent key nodes are merged into one abnormal event; If there are multiple abnormal events at the same key node, the multiple abnormal events at the same key node are merged into one abnormal event; A correspondence between congestion levels and speed limits is preset, and based on the correspondence and the congestion level of the abnormal event, a road section speed limit is generated for the abnormal event, and corresponding warning prompt information is generated based on the content of the abnormal event.

4. The method according to claim 1, characterized in that: Retrieving a target road display screen based on the abnormal event location, and outputting the road section speed limit and warning prompt information of the abnormal event to the target road display screen, including: Retrieving multiple upstream nodes of the key node where the abnormal event is located, where the upstream nodes are nodes that the vehicle passes before reaching the key node where the abnormal event is located; Calculate the distance from the upstream node to the location of the abnormal event; Sorting the abnormal events from near to far based on the distance, and displaying the speed limit and warning information of the road section of the abnormal event on the display screen of the upstream node according to the sorting; An importance score is generated for the abnormal event according to the congestion level and congestion time of the abnormal event, and a corresponding display font size and display font color are matched for the abnormal event based on the importance score.

5. A road status warning system, characterized in that: include: A status collection module, used to collect road status information, including environmental information, traffic information, accident information and congestion information; An event generation module, used to generate abnormal events and abnormal event locations based on the state information, and generate road section speed limit and warning prompt information for the abnormal events; The event display module is used to retrieve the target road display screen based on the abnormal event location, and output the road section speed limit and warning prompt information of the abnormal event to the target road display screen.

6. The system according to claim 5, characterized in that The status collection module includes: A communication establishing unit, used to establish a communication connection with a sensor combination deployed at a key node of the road through wireless communication, wherein the sensor combination includes an environmental monitoring sensor, a flow monitoring sensor, and a camera; A position binding unit, used to assign a unique signal code to the sensor and bind the signal code to a key node position code where the sensor is located; A data conversion unit, used for receiving a sensor signal, converting the sensor signal into state data of a specified format, and saving the state data into a file named after the key node position code based on the signal code carried by the sensor signal; A denoising processing unit, used to remove noise from the state data by using a Kalman filter, and convert the state data into an environmental data sequence, a vehicle flow value sequence, accident description data, and congestion description data; A feature extraction unit, used to input state data into a pre-trained neural network model; The congestion prediction unit is used to perform weighted fusion of the data from various sensors based on the output of the neural network to predict the accident probability, congestion level and congestion duration.

7. The system according to claim 6, characterized in that The event generation module comprises: A first generating unit, configured to generate an abnormal event for a corresponding key node if the congestion level reaches a set level threshold, and write the congestion level and congestion time into the abnormal event; A second generating unit is used to generate an abnormal event for the corresponding key node if there is accident information or the accident probability reaches a set threshold, and write the accident information or high accident incidence into the abnormal event; A first merging unit, configured to merge the abnormal events of adjacent key nodes into one abnormal event if both adjacent key nodes have abnormal events; A second merging unit is used to merge the multiple abnormal events of the same key node into one abnormal event if there are multiple abnormal events at the same key node; The parameter generation unit is used to pre-set the correspondence between the congestion level and the speed limit, generate a road section speed limit for the abnormal event based on the correspondence and the congestion level of the abnormal event, and generate corresponding warning prompt information based on the content of the abnormal event.

8. The system according to claim 5, characterized in that The event display module comprises: A target retrieval unit, used to retrieve multiple upstream nodes of the key node where the abnormal event is located, wherein the upstream nodes are nodes that the vehicle passes before reaching the key node where the abnormal event is located; A distance calculation unit, used to calculate the distance from the upstream node to the location of the abnormal event; An event sorting unit, used to sort the abnormal events from near to far based on the distance, and display the speed limit and warning prompt information of the road section of the abnormal event on the display screen of the upstream node according to the sorting; The display setting unit is used to generate an importance score for the abnormal event according to the congestion level and congestion time of the abnormal event, and match a corresponding display font size and display font color for the abnormal event based on the importance score.

9. A device, characterized in that: include: A memory, used for storing a road status warning program; A processor is used to implement the steps of the road status warning method as described in any one of claims 1-4 when executing the road status warning program.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a road status warning program, and when the road status warning program is executed by the processor, the steps of the road status warning method according to any one of claims 1 to 4 are implemented.

Images