Traffic risk intelligent monitoring and early warning method, system, equipment and medium

Abstract

The invention provides a traffic risk intelligent monitoring and early warning method, system and device and a medium, and belongs to the technical field of intelligent traffic. The method comprises the following steps: collecting real-time traffic data, environmental meteorological data and accident report data as source data; standardizing the source data, and storing the standardized source data into a database according to different data structures in a classified manner; classifying the source data according to information recorded by the source data by utilizing a target monitoring model and an object comparison technology; the event type of the source data comprises a weather event, a vehicle event, a facility event and an environment event; based on the source data of different event types, respectively calculating the score of each event; calculating a real-time comprehensive risk index based on the score of each event; and determining a risk level based on the real-time comprehensive risk index, adding a risk identifier at an early warning position in a monitoring platform map according to the risk level, and dividing a road section management area for the early warning position.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent transportation, and more specifically, relates to a method, system, device and medium for intelligent monitoring and early warning of traffic risks. Background Art

[0002] With the accelerating urbanization process and the continuous increase in traffic demand, urban traffic systems are under unprecedented pressure. The increasing number of motor vehicles, complex and changeable traffic conditions, and various emerging traffic incidents have brought many severe challenges to urban traffic management. In this context, effective monitoring and early warning of traffic risks have become a key link in ensuring the safe and efficient operation of urban traffic systems.

[0003] Currently, traffic risk monitoring mainly relies on traditional monitoring devices and manual patrol methods. However, traditional monitoring devices often have problems such as limited monitoring range and incomplete data collection, making it difficult to achieve comprehensive and real-time monitoring of traffic systems. Manual patrols are limited by factors such as the number of patrol personnel, energy, and subjective judgment, resulting in low patrol efficiency and high rates of missed reports and false alarms. In addition, most existing traffic risk early warning methods are based on simple threshold judgments and lack the ability to accurately identify and comprehensively evaluate different types of traffic risks, making it difficult to effectively guarantee the accuracy and timeliness of early warnings.

[0004] Intelligent traffic risk identification, as an important part of intelligent traffic systems, is a key technology to meet the needs of social development and improve urban traffic management levels. It can achieve accurate identification and quantitative evaluation of traffic risks through in-depth mining and analysis of massive traffic data, providing more intelligent and efficient solutions for urban traffic management. Through intelligent traffic risk identification, the limitations of traditional monitoring and early warning methods can be broken, enabling comprehensive and real-time monitoring and management of traffic systems, improving the operation efficiency and safety of traffic systems, and providing a more convenient, efficient, and safe way for people to travel. Therefore, how to achieve intelligent monitoring and early warning of traffic risks is an urgent problem for us to solve. Summary of the Invention

[0005] Aiming at the above problems, the purpose of the present invention is to provide a method, system, device and medium for intelligent monitoring and early warning of traffic risks, which realizes comprehensive intelligent monitoring and efficient early warning response of traffic risks through multi-source data integration, accurate event classification, scientific risk assessment, intuitive risk early warning and refined road section management.

[0006] To achieve the above object, the present invention is realized through the following technical solutions: In the first aspect, an embodiment of the present application provides a method for intelligent monitoring and early warning of traffic risks, including: Collect real-time traffic data, environmental meteorological data, and accident report data as source data; After standardizing the source data, classify and store it in a database according to different data structures; Use the target monitoring model and object comparison technology to classify the source data according to the information recorded in the source data; the event types of the source data include weather events, vehicle events, facility events, and environmental events; Based on the source data of different event types, calculate the score for each event; Calculate the real-time comprehensive risk index based on the score of each event; Determine the risk level based on the real-time comprehensive risk index, add risk markers at the warning locations on the monitoring platform map according to the risk level, and divide the road section management areas for the warning locations.

[0007] In an alternative embodiment, the collecting real-time traffic data, environmental meteorological data, and accident report data as source data includes: Collect vehicle speed, traffic flow, lane occupancy, abnormal parking, and reverse driving information through radar and ETC devices, and collect the video stream of the relevant road section through cameras as real-time traffic data; Obtain the meteorological indicators of the corresponding area through the meteorological bureau API as environmental meteorological data; the meteorological indicators include wind speed, precipitation, visibility, temperature, and road icing index; Obtain the traffic accident alarm data, road disease data, and manually reported environmental events in real-time through the API interface of the traffic management department; the environmental events include greening sprinkling and chemical leakage.

[0008] In an alternative embodiment, the classifying and storing the source data in a database according to different data structures after standardizing the source data includes: For the video stream, extract key images frame by frame and remove the blurred frames; For the accident report data, remove the special symbols and perform unified timestamp processing; For the Chinese-English mixed text in the source data, extract the keyword fields using regular expressions; Convert the original geographical coordinates recorded by the radar and camera into an encrypted coordinate system; Divide the standardized source data into structured data and unstructured data, store the structured data in a time series database, store the unstructured data in an object storage system, and establish an index association relationship.

[0009] In an alternative embodiment, the classifying the source data according to the information recorded in the source data by using the target monitoring model and object comparison technology includes: Input the video frames of the key images into the target monitoring model constructed based on the event type image dataset, and output the confidence of each event type; If the confidence of the output event type is higher than the confidence threshold, calculate the intersection over union (IoU) of the corresponding video frame and the standard event template of that event type, and calculate the IoU(A,B) of the event type; The calculation formula of the intersection over union is:

[0010] Where A is the detection box area of the video frame, and B is the standard event template area; If the intersection over union is higher than the intersection over union threshold, the source data belongs to the event type corresponding to the standard event template.

[0011] In an alternative embodiment, calculate the score of each event based on the source data of different event types, including: If the source data belongs to a weather event, extract the precipitation, wind speed, and visibility from the source data, and use the formula Calculate the weather event score ; Where R is the precipitation, W is the wind speed W, V is the visibility, is the historical maximum precipitation threshold, is the historical maximum wind speed threshold, is the minimum safe visibility; If the source data belongs to a vehicle event, based on the real-time traffic data and accident report data, obtain the speeding ratio α, overloading ratio β, dangerous driving frequency N, and vehicle type coefficient γ, and use the formula S v =(0.4α + 0.3β + 0.3ln(N + 1))×γ to calculate the vehicle event score S v ; If the source data belongs to a facility event, based on the real-time traffic data and accident report data, extract the damaged area A, damaged depth D, and number of affected lanes L recorded in the corresponding video frame, and use the formula S f =(A m / A + D m / D)×L m / L×5 to calculate the facility event score S f ; Where Am is the road surface collapse area threshold, D m is the collapse depth threshold, L m is the total number of lanes; If the source data belongs to an environmental event, based on the manually reported environmental events, obtain the toxicity index T of the leaked substance and the diffusion radius B, and use the formula Calculate the environmental event score ; Where, is the reference toxicity index.

[0012] In an alternative embodiment, the real-time comprehensive risk index is calculated based on the score for each event, including: The real-time comprehensive risk index is calculated using the following formula:

[0013] where R is the comprehensive risk index.

[0014] In an alternative embodiment, the risk level is determined based on the real-time comprehensive risk index, a risk identifier is added at the warning position on the monitoring platform map according to the risk level, and a section management area is divided for the warning position, including: Determine the risk level according to the comprehensive risk index R and the preset index interval; If R≥4.5, the risk level is level one, a risk identifier is added at the warning position on the monitoring platform map, and the color of the risk identifier is set to red; If 3.5≤R<4.5, the risk level is level two, a risk identifier is added at the warning position on the monitoring platform map, and the color of the risk identifier is set to orange; If 2.5≤R<3.5, the risk level is level three, a risk identifier is added at the warning position on the monitoring platform map, and the color of the risk identifier is set to yellow; If 1.5≤R<2.5, the risk level is level four, a risk identifier is added at the warning position on the monitoring platform map, and the color of the risk identifier is set to green; If R<1.5, the risk level is level five, a risk identifier is added at the warning position on the monitoring platform map, and the color of the risk identifier is set to blue; An event area, a control area, an organization area, a congestion area, and a reminder area are divided within the preset range of the warning position and displayed on the monitoring platform map.

[0015] In a second aspect, an embodiment of the present application further provides a traffic risk intelligent monitoring and warning system, including: A data acquisition module for acquiring real-time traffic data, environmental meteorological data, and accident report data as source data; A data processing module for performing standardized processing on the source data and then classifying and storing it in a database according to different data structures; A data classification module for classifying the source data according to the information recorded in the source data by using a target monitoring model and object comparison technology; the event types of the source data include weather events, vehicle events, facility events, and environmental events; A classification calculation module for calculating the scores of each type of event separately based on the source data of different event types; A risk assessment module for calculating a real-time comprehensive risk index based on the scores of each type of event; A result display module for determining the risk level based on the real-time comprehensive risk index, adding risk marks at the warning positions on the monitoring platform map according to the risk level, and dividing the road section management areas for the warning positions.

[0016] Thirdly, an embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the traffic risk intelligent monitoring and warning method described in any one of the above are implemented.

[0017] Fourthly, an embodiment of the present application also provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the traffic risk intelligent monitoring and warning method described in any one of the above are implemented.

[0018] From the above technical solutions, the following advantages of the present invention can be seen: In the traffic risk intelligent monitoring and warning method provided by the present application, by collecting, standardizing, and classifying and storing multi-source traffic data, using the target monitoring model and object comparison technology to achieve accurate event classification, calculating scores and comprehensive risk indexes based on different event types, and then determining the risk level and intuitively displaying the risk positions on the monitoring platform map and dividing the road section management areas, the intelligent monitoring and warning of traffic risks are realized, the accuracy and response efficiency of risk assessment are improved, which helps to reduce the risk of traffic accidents and enhance the safety of the traffic system.

[0019] The present application realizes the comprehensive integration and standardization of multi-source data such as real-time traffic data, environmental meteorological data, and accident report data, improves the management and utilization efficiency of data through classified storage, and provides a solid data foundation for subsequent risk assessment.

[0020] With the help of the target monitoring model and object comparison technology, the present application can accurately classify events into weather events, vehicle events, facility events, and environmental events according to the information recorded in the source data, greatly improving the pertinence and accuracy of risk assessment.

[0021] The present application constructs a scientific event scoring mechanism for different event types. By quantitatively evaluating the risk levels of various events, it provides an objective and comprehensive basis for decision-making, which helps to formulate more accurate risk response strategies.

[0022] This application determines the risk level based on a real-time comprehensive risk index and visually displays the risk locations on the monitoring platform map. Through risk identifications of different colors, managers can quickly identify high-risk areas and take corresponding measures in a timely manner, enhancing the intuitiveness and operability of risk warnings.

[0023] This application divides the road section management area at the warning location and details functional areas such as the event area, control area, organization area, congestion area, and reminder area, which helps to achieve refined and dynamic traffic management and improve the overall operation efficiency and safety of the traffic system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] To more clearly illustrate the technical solutions of the present invention, the accompanying drawings required for description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is a schematic flowchart of the intelligent traffic risk monitoring and warning method provided by this application.

[0026] Figure 2 It is a schematic structural diagram of the intelligent traffic risk monitoring and warning system provided by this application.

[0027] Figure 3 It is a schematic structural diagram of the electronic device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] In the following, the specific steps of the intelligent traffic risk monitoring and warning method will be described in detail, and various embodiments of the present disclosure will be described more comprehensively. The present disclosure can have various embodiments and adjustments and changes can be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents, and / or alternative solutions falling within the spirit and scope of the various embodiments of the present disclosure.

[0029] In the following, the term "comprising" or "may comprise" that can be used in various embodiments of the present disclosure indicates the presence of the disclosed functions, operations, or elements, and does not limit the addition of one or more functions, operations, or elements. Further, as used in various embodiments of the present disclosure, the terms "comprising", "having", and their cognates are only intended to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be construed as first excluding the existence or addition of the possibility of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0031] See also Figure 1 The figure is a flow chart of a method for intelligent monitoring and early warning of traffic risks in a specific embodiment, the method comprising: S1: Collect real-time traffic data, environmental meteorological data and accident report data as source data.

[0032] In a specific implementation manner, dynamic information such as vehicle speed, traffic volume, lane occupancy, abnormal parking, and reverse driving is collected through radar and ETC equipment, and video streams of relevant road sections are collected through cameras as real-time traffic data.

[0033] Obtain the meteorological indicators of the corresponding area as environmental meteorological data through the weather station and weather bureau API. Meteorological indicators include wind speed, precipitation, visibility, temperature, road icing and other indicators.

[0034] Traffic accident alarm data, road damage data and manually reported environmental events are obtained in real time through the traffic control department API interface; environmental events include the time range of greening watering operations and the location description text of chemical leaks. Traffic accident alarm data includes collision coordinates and vehicle type, and road damage data includes road collapse information.

[0035] S2: After standardizing the source data, the data is classified and stored in the database according to different data structures.

[0036] In a specific implementation, this step includes: For the video stream, key images are extracted frame by frame at a frame rate of 30fps, and blurred frames are removed based on the set image clarity threshold: gradient value ≥ 50.

[0037] For accident report data, remove special symbols (such as "#" and "*") and unify the timestamp into the "YYYY-MM-DDHH:MM:SS" format.

[0038] For mixed Chinese and English texts in the source data (for example, "Accident occurred atXX Road"), regular expressions are used to extract key fields (such as road section name and event type).

[0039] Convert the original geographical coordinates WGS-84 recorded by the radar and camera into the encrypted coordinate system GCJ-02.

[0040] Divide the source data after standardization into structured data and unstructured data. Store the structured data in the time series database InfluxDB, store the unstructured data (video clips, images) in the object storage system MinIO, and establish an index association relationship.

[0041] S3: Use the target monitoring model and object comparison technology to classify the source data according to the information recorded in the source data.

[0042] Among them, the event types of the source data include weather events, vehicle events, facility events, and environmental events.

[0043] First, input the video frames of the key images into the target monitoring model constructed based on the event type image dataset, and output the confidence of each event type. Among them, the target detection model is constructed based on the YOLOv5 network, and this model is trained using the labeled dataset. The model outputs the detection box coordinates and the confidence of the event type.

[0044] If the confidence of the output event type is higher than the confidence threshold of 0.7, and it is preliminarily determined that the corresponding data belongs to this event type, then calculate the intersection over union (IoU) of the corresponding video frame and the standard event template of this event type, and calculate the intersection over union IoU(A,B) of the event type; The calculation formula for the intersection over union is:

[0045] Among them, A is the detection box area of the video frame, and B is the standard event template area; the standard event templates include standard weather event templates, standard vehicle event templates, standard facility event templates, and standard environmental event templates.

[0046] If the intersection over union is higher than the intersection over union threshold of 0.8, then the source data belongs to the event type corresponding to the standard event template.

[0047] S4: Based on the source data of different event types, calculate the score of each event respectively.

[0048] In the specific implementation, the score calculation methods for the four event types are as follows: If the source data belongs to a weather event, extract the precipitation, wind speed, and visibility in the source data, and use the formula Calculate the weather event score ; Among them, R is the precipitation, W is the wind speed W, V is the visibility, is the historical maximum precipitation threshold, is the historical maximum wind speed threshold, is the minimum safe visibility; If the source data belongs to a vehicle event, based on real-time traffic data and accident report data, obtain the speeding ratio α, the overloading ratio β, the frequency of dangerous driving N, and the vehicle type coefficient γ, and use the formula S v =(0.4α + 0.3β + 0.3ln(N + 1))×γ to calculate the vehicle event score S v ; If the source data belongs to a facility event, based on real-time traffic data and accident report data, extract the damaged area A, the damaged depth D, and the number of affected lanes L recorded in the corresponding video frame, and use the formula S f =(A m / A + D m / D)×L m / L×5 to calculate the facility event score S f ; where, Am is the threshold of the pavement collapse area, D m is the threshold of the collapse depth, L m is the total number of lanes; If the source data belongs to an environmental event, based on the manually reported environmental event, obtain the toxicity index T of the leaked substance and the diffusion radius B, and use the formula to calculate the environmental event score ; where, is the reference toxicity index.

[0049] S5: Calculate the real-time comprehensive risk index based on the scores of each event.

[0050] In the specific implementation, the weighted sum of squares is divided by the weighted sum to amplify the influence of high-score events to calculate the real-time comprehensive risk index. The specific formula is as follows:

[0051] where, R is the comprehensive risk index.

[0052] S6: Determine the risk level based on the real-time comprehensive risk index, add a risk identifier at the warning position on the monitoring platform map according to the risk level, and divide the road section management area for the warning position.

[0053] In the specific implementation, first, determine the risk level according to the comprehensive risk index R and the preset index interval: If R≥4.5, the risk level is level one, add a risk identifier at the warning position on the monitoring platform map, and set the color of the risk identifier to red; If 3.5≤R<4.5, the risk level is level two, add a risk identifier at the warning position on the monitoring platform map, and set the color of the risk identifier to orange; If 2.5 ≤ R < 3.5, the risk level is level three. Add a risk label at the warning location on the monitoring platform map, and set the color of the risk label to yellow; If 1.5 ≤ R < 2.5, the risk level is level four. Add a risk label at the warning location on the monitoring platform map, and set the color of the risk label to green; If R < 1.5, the risk level is level five. Add a risk label at the warning location on the monitoring platform map, and set the color of the risk label to blue.

[0054] It should be noted specifically that among the above five levels, level one represents that the risk degree of road traffic safety risk is extremely serious, the probability of road traffic safety incidents is very high, and the consequences are extremely serious. Once an incident occurs, it will cause extremely serious harm to the regional road traffic system, which requires special attention and special countermeasures to be taken. The risk at this level is an unacceptable risk, and the corresponding level color is red. Level two represents that the risk degree of road traffic safety risk is serious, the probability of road traffic safety incidents is high, and the consequences are serious. Once an incident occurs, it will cause serious harm to the regional road traffic system, which requires attention and corresponding measures to be taken. The risk at this level is an undesirable risk, and the corresponding level color is orange. Level three represents that the risk degree of road traffic safety risk is general, the road traffic safety incidents may occur, and the consequences are general. Once an incident occurs, it will cause general harm to the regional road traffic system, and corresponding measures need to be taken to deal with it. The risk at this level is a conditionally acceptable risk, and the corresponding level color is yellow. Level four represents that the risk degree of road traffic safety risk is relatively low, the possibility of road traffic safety incidents occurring is relatively small, and the consequences are relatively light, and the corresponding level color is green. Level five represents that the risk degree of road traffic safety risk is the lowest, the possibility of road traffic safety incidents occurring is extremely small, and the consequences are the lightest, and the corresponding level color is blue.

[0055] Then, divide the event area, control area, organization area, congestion area, and reminder area within the preset range of the warning location, and display them on the monitoring platform map. The control levels and lengths are different for different areas. For example, the event area (0 - 300m), control area (300 - 500m), organization area (500 - 700m), congestion area (700 - 2KM), reminder area (2KM - 3KM). Display the above areas on the map for the command and dispatch system to dispatch the on-site situation and evacuate and guide vehicles.

[0056] In this embodiment, the method deeply integrates multi-source traffic data and innovatively applies intelligent monitoring and evaluation technologies, achieving remarkable results in the field of traffic risk monitoring and early warning. It breaks through the limitations of traditional traffic monitoring methods and realizes all-round, real-time, and accurate monitoring of traffic risks. Whether it is weather changes, vehicle abnormalities, facility failures, or environmental emergencies, they can all be quickly captured and accurately evaluated. This ability greatly enhances the traffic system's perception of potential risks, enabling management departments to make advance judgments and respond in a timely manner, effectively avoiding traffic accidents or traffic jams caused by the accumulation of risks.

[0057] At the same time, the method also has a powerful dynamic early warning function. It can automatically adjust the early warning level and scope according to real-time traffic data and risk assessment results, providing timely and accurate early warning information for traffic participants. This not only helps drivers make preparations in advance and reduce operation errors caused by unexpected situations but also guides the reasonable distribution of traffic flow, alleviates traffic pressure, and improves the overall traffic efficiency.

[0058] In addition, the method also provides scientific and comprehensive decision-making support for urban traffic management. Through in-depth analysis of traffic risks, management departments can more accurately formulate traffic plans, optimize the layout of traffic facilities, adjust traffic signal control strategies, etc., thereby comprehensively improving the operation efficiency and service level of the urban traffic system.

[0059] In summary, the method has shown remarkable beneficial effects in enhancing traffic system safety, optimizing traffic management decisions, and promoting the sustainable development of urban traffic, providing strong technical support for building a safe, unobstructed, and efficient urban traffic network.

[0060] As Figure 2 shown, the following are embodiments of the traffic risk intelligent monitoring and early warning system provided by the present disclosure. This system and the traffic risk intelligent monitoring and early warning method of the above embodiments belong to the same inventive concept. For the details not described in detail in the embodiments of the traffic risk intelligent monitoring and early warning system, reference can be made to the embodiments of the above traffic risk intelligent monitoring and early warning method.

[0061] A traffic risk intelligent monitoring and early warning system includes: a data collection module, a data processing module, a data classification module, a classification calculation module, a risk assessment module, and a result display module.

[0062] The data collection module is used to collect real-time traffic data, environmental meteorological data, and accident report data as source data.

[0063] The data processing module is used to perform standardized processing on the source data and then store it in the database according to different data structures.

[0064] A data classification module, which is used to classify source data according to the information recorded in the source data by using a target monitoring model and object comparison technology; the event types of the source data include weather events, vehicle events, facility events, and environmental events.

[0065] A classification calculation module, which is used to calculate the score of each event respectively based on the source data of different event types.

[0066] A risk assessment module, which is used to calculate a real-time comprehensive risk index based on the score of each event.

[0067] A result display module, which is used to determine the risk level based on the real-time comprehensive risk index, add a risk label to the warning position on the monitoring platform map according to the risk level, and divide the road section management area for the warning position.

[0068] The intelligent traffic risk monitoring and early warning system provided in this embodiment breaks through the limitations of the traditional traffic risk monitoring with limited scope, insufficient warning accuracy and timeliness by integrating multi-source data and adopting intelligent monitoring and evaluation technologies, realizes the accurate identification, quantitative evaluation and dynamic early warning of traffic risks, effectively improves the operation efficiency and safety of the traffic system, provides a more intelligent and efficient solution for urban traffic management, and helps to build a convenient, efficient and safe travel environment.

[0069] Figure 3 A schematic hardware structure diagram of an electronic device for implementing various embodiments of the present invention.

[0070] The intelligent traffic risk monitoring and early warning method provided in the embodiments of the present application can be applied to an electronic device. Those skilled in the art can understand that the electronic device structure involved in the embodiments of the present invention does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. In the embodiments of the present invention, the electronic device 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 electronic device can 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 only examples and are not intended to limit the implementation of the embodiments of the present application described herein and / or required.

[0071] The electronic device may include a processor, an external memory interface, an internal memory, a Universal Serial Bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, buttons, a camera, a display screen, and a Subscriber Identity Module (SIM) card interface, etc.

[0072] The processor may include one or more processing units. For example, the processor may include a Central Processing Unit (CPU), etc., an Application Processor (AP), a modem processor, a Graphics Processing Unit (GPU), an Image Signal Processor (ISP), a controller, a memory, a video codec, a Digital Signal Processor (DSP), a baseband processor, and / or a Neural-Network Processing Unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0073] Among them, the processor may be the nerve center and command center of the electronic device. The controller may generate operation control signals according to the instruction operation code and timing signal to complete the control of fetching and executing instructions.

[0074] A memory may also be provided in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory may save the instructions or data that the processor has just used or recycled. If the processor needs to use the instruction or data again, it can directly call it from this memory. This avoids repeated accesses, reduces the waiting time of the processor, and thus improves the system efficiency.

[0075] The external memory interface may be used to connect an external memory card, such as a MicroSD card, to implement the storage capacity expansion of the electronic device. The external memory card communicates with the processor through the external memory interface to implement the data storage function. For example, files such as music and videos are saved in the external memory card.

[0076] The internal memory can be used to store computer-executable program code, and the computer-executable program code includes instructions. The processor executes various functional applications and data processing of the electronic device by running the instructions stored in the internal memory. The internal memory can include a program storage area and a data storage area. The internal memory can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0077] The wireless communication function of the electronic device can be implemented by an antenna, a wireless communication module, a modulation and demodulation processor, a baseband processor, etc.

[0078] The wireless communication module can provide wireless communication solutions applied to the electronic device, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite systems (GNSSs), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0079] The electronic device can implement audio functions, etc. through an audio module, a speaker, a receiver, a microphone, a headphone jack, an application processor, etc.

[0080] The electronic device can implement a shooting function through an ISP, a camera, a video codec, a GPU, a display screen, an application processor, etc.

[0081] The electronic device can implement a display function through a GPU, a display screen, an application processor, etc.

[0082] The GPU is a microprocessor for image processing, connecting the display screen and the application processor. The GPU is used to execute mathematical and geometric calculations for graphics rendering. The processor can include one or more GPUs, which execute program instructions to generate or change display information.

[0083] The display screen is used to display images, videos, etc. The display screen includes a display panel.

[0084] The above-mentioned electronic device implements the traffic risk intelligent monitoring and early warning method of the present application. By deeply integrating multi-source traffic data and innovatively applying intelligent monitoring and evaluation technologies, it realizes the accurate identification, real-time early warning and comprehensive judgment of traffic risks, achieving the beneficial effects of comprehensively improving the operation efficiency of the traffic system, significantly enhancing traffic safety, effectively optimizing traffic management decisions, and providing strong technical support for the sustainable development of urban traffic.

[0085] In the storage medium provided by the present application, there is a program product capable of implementing the traffic risk intelligent monitoring and early warning method.

[0086] The traffic risk intelligent monitoring and early warning method includes: Collect real-time traffic data, environmental meteorological data and accident report data as source data; After standardizing the source data, classify and store it in the database according to different data structures; Using the target monitoring model and object comparison technology, classify the source data according to the information recorded in the source data; the event types of the source data include weather events, vehicle events, facility events and environmental events; Based on the source data of different event types, calculate the score of each event respectively; Calculate the real-time comprehensive risk index based on the score of each event; Based on the real-time comprehensive risk index, determine the risk level, add risk marks at the early warning positions on the monitoring platform map according to the risk level, and divide the road section management areas for the early warning positions.

[0087] In some possible implementation manners, the traffic risk intelligent monitoring and early warning method of the present disclosure can be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to make the terminal device execute the steps according to various exemplary embodiments of the present disclosure described in the "Exemplary Method" section above of this specification.

[0088] The storage medium of the present disclosure can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0089] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent traffic risk monitoring and early warning method, characterized in that, Including: Collecting real-time traffic data, environmental meteorological data, and accident report data as source data; After standardizing the source data, classifying and storing it in a database according to different data structures; Using a target monitoring model and object comparison technology to classify the source data according to the information recorded in the source data; the event types of the source data include weather events, vehicle events, facility events, and environmental events; Based on the source data of different event types, calculating the score for each type of event; Calculating a real-time comprehensive risk index based on the score of each event; Determining the risk level based on the real-time comprehensive risk index, adding risk markers at the warning locations on the monitoring platform map according to the risk level, and dividing the road section management area for the warning locations.

2. The intelligent traffic risk monitoring and early warning method according to claim 1, wherein, The collecting real-time traffic data, environmental meteorological data, and accident report data as source data includes: Collecting vehicle speed, traffic flow, lane occupancy, abnormal parking, and reverse driving information through radar and ETC devices, and collecting video streams of relevant road sections through cameras as real-time traffic data; Obtaining meteorological indicators of the corresponding area through the meteorological bureau API as environmental meteorological data; the meteorological indicators include wind speed, precipitation, visibility, temperature, and road icing index; Obtaining traffic accident alarm data, road disease data, and manually reported environmental events in real time through the traffic management department API interface; environmental events include greening sprinkling and chemical leakage.

3. The intelligent traffic risk monitoring and early warning method according to claim 2, wherein The after standardizing the source data, classifying and storing it in a database according to different data structures includes: For the video stream, extracting key images frame by frame and removing the blurred frames; For the accident report data, removing the special symbols and performing unified timestamp processing; For the Chinese-English mixed text in the source data, extracting keyword fields using regular expressions; Converting the original geographical coordinates recorded by radar and cameras into an encrypted coordinate system; Dividing the standardized source data into structured data and unstructured data, storing the structured data in a time series database, storing the unstructured data in an object storage system, and establishing an index association relationship.

4. The intelligent traffic risk monitoring and warning method according to claim 3, characterized in that The using a target monitoring model and object comparison technology to classify the source data according to the information recorded in the source data includes: Inputting the video frames of the key images into a target monitoring model constructed based on the event type image dataset, and outputting the confidence of each event type; If the confidence of the output event type is higher than the confidence threshold, calculating the intersection over union ratio IoU(A,B) of the corresponding video frame and the standard event template of this event type; The calculation formula of the intersection over union ratio is: where A is the detection box area of the video frame and B is the standard event template area; If the intersection over union ratio is higher than the intersection over union ratio threshold, the source data belongs to the event type corresponding to the standard event template.

5. The intelligent traffic risk monitoring and warning method according to claim 4, characterized in that The based on the source data of different event types, calculating the score for each type of event includes: If the source data belongs to a weather event, extract the precipitation, wind speed, and visibility from the source data, and use the formula to calculate the weather event score ; Among them, R is the precipitation, W is the wind speed W, V is the visibility, is the threshold of the historical maximum precipitation, is the threshold of the historical maximum wind speed, is the minimum safe visibility; If the source data belongs to vehicle events, based on real-time traffic data and accident report data, the speeding ratio α, overloading ratio β, dangerous driving frequency N and vehicle type coefficient γ are obtained, and the formula S is used. v =[0.4α+0.3β+0.3ln(N+1)]×γ to calculate the vehicle event score S v ; If the source data belongs to a facility event, based on real-time traffic data and accident report data, extract the damaged area A, damaged depth D, and number of affected lanes L recorded in the corresponding video frames, and use the formula S f =(A m / A + D m / D)×L m / L×5 to calculate the facility event score S f ; where Am is the threshold of the pavement collapse area, D m is the threshold of the collapse depth, and L m is the total number of lanes; If the source data belongs to an environmental event, based on the environmentally reported events manually reported, obtain the toxicity index T of the leaked substance and the diffusion radius B, and use the formula to calculate the environmental event score ; where is the reference toxicity index.

6. The intelligent traffic risk monitoring and warning method according to claim 5, wherein The calculating a real-time comprehensive risk index based on the score of each event includes: Calculating the real-time comprehensive risk index using the following formula: where R is the comprehensive risk index.

7. The intelligent traffic risk monitoring and early warning method according to claim 6, characterized in that, The risk level is determined based on the real-time comprehensive risk index. Risk markers are added at the warning locations on the monitoring platform map according to the risk level, and road section management areas are demarcated for the warning locations, including: Determine the risk level according to the comprehensive risk index R and the preset index range; If R≥4.5, the risk level is level one. Add a risk marker at the warning location on the monitoring platform map and set the color of the risk marker to red; If 3.5≤R<4.5, the risk level is level two. Add a risk marker at the warning location on the monitoring platform map and set the color of the risk marker to orange; If 2.5≤R<3.5, the risk level is level three. Add a risk marker at the warning location on the monitoring platform map and set the color of the risk marker to yellow; If 1.5≤R<2.5, the risk level is level four. Add a risk marker at the warning location on the monitoring platform map and set the color of the risk marker to green; If R<1.5, the risk level is level five. Add a risk marker at the warning location on the monitoring platform map and set the color of the risk marker to blue; Demarcate an event area, a control area, an organization area, a congestion area, and a reminder area within the preset range of the warning location and display them on the monitoring platform map.

8. An intelligent traffic risk monitoring and early warning system, characterized in that, The system adopts the intelligent traffic risk monitoring and warning method described in any one of claims 1 to 7; The system includes: A data collection module for collecting real-time traffic data, environmental meteorological data, and accident report data as source data; A data processing module for performing standardized processing on the source data and storing it in the database according to different data structures; A data classification module for classifying the source data according to the information recorded in the source data by using the target monitoring model and the object comparison technology; the event types of the source data include weather events, vehicle events, facility events, and environmental events; A classification calculation module for calculating the score of each event respectively based on the source data of different event types; A risk assessment module for calculating the real-time comprehensive risk index based on the score of each event; A result display module for determining the risk level based on the real-time comprehensive risk index, adding risk markers at the warning locations on the monitoring platform map according to the risk level, and demarcating road section management areas for the warning locations.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein When the processor executes the program, it realizes the steps of the intelligent traffic risk monitoring and warning method described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it realizes the steps of the intelligent traffic risk monitoring and warning method described in any one of claims 1 to 7.

Images