Road network abnormal event multi-dimensional intelligent sensing system based on intelligent Internet of Things data

Abstract

The invention discloses a road network abnormal event multi-dimensional intelligent sensing system based on intelligent Internet of Things data. The road network abnormal event multi-dimensional intelligent sensing system comprises a multi-source data acquisition module and a data fusion and preprocessing module. An abnormal event detection and identification module; an event grading and early warning module and a system management and user interaction module realize comprehensive perception of a road network operation state through a multi-source data acquisition module; the data fusion and preprocessing module carries out fusion processing on the collected multi-source data, so that the data quality is improved; data from different sources can be unified and integrated through a datamation processing mode, a high-quality data basis is provided for subsequent abnormal event detection, and the monitoring efficiency and accuracy are greatly improved; the event grading and early warning module carries out grading according to the severity and urgency of the abnormal events, so that related departments can rapidly respond and take measures in advance, delay caused by human factors is effectively avoided, and the influence of the abnormal events on road network operation and public travel is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of real-time monitoring of traffic road networks, and particularly to a multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data. Background Art

[0002] With the continuous growth of traffic flow, the management of traffic road networks such as highways faces many challenges, among which the timely perception and handling of road network abnormal events are crucial. Traditional road network monitoring systems mainly rely on manual inspections and simple sensor monitoring, suffering from problems such as low monitoring efficiency, incomplete data, and untimely responses. That is, currently, the road network linkage control system mainly uploads the abnormal event situation manually. When an abnormal event occurs, it is necessary for people to go to the scene to check. On the one hand, it wastes manpower, and on the other hand, people need to go to the scene to determine, which affects the disposal efficiency of the event, may lead to the aggravation of the severity of the situation, delay the rescue time, and cause serious consequences. Summary of the Invention

[0003] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0004] In view of the above problems existing in the current multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data, that is, the road network linkage control system mainly uploads the abnormal event situation manually. When an abnormal event occurs, it is necessary for people to go to the scene to check. On the one hand, it wastes manpower, and on the other hand, people need to go to the scene to determine, which affects the disposal efficiency of the event, may lead to the aggravation of the severity of the situation, delay the rescue time, and cause serious consequences, the present invention is proposed.

[0005] Therefore, the purpose of the present invention is to provide a multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data, including, A multi-source data acquisition module for collecting road network operation data and environmental data; A data fusion and preprocessing module for performing fusion processing on the collected multi-source data; An abnormal event detection and recognition module for performing real-time analysis on the fused data to identify abnormal events in the road network; An event grading and early warning module for grading according to the severity and urgency of the abnormal event and sending out early warning information; The system management and user interaction module is used to provide system management and user interaction functions.

[0007] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the multi-source data acquisition module includes, Internet of Things sensors, which are used to collect traffic flow, vehicle speed, and meteorological data; Video surveillance devices, which are used to collect video image data of the road network.

[0008] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the data fusion and preprocessing module includes, The data cleaning unit is used to remove noise and redundant information in the collected data; The data conversion unit is used to convert data in different formats into a unified format; The data association unit is used to associate multi-source data to form a comprehensive data set.

[0009] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the abnormal event detection and recognition module includes, The data analysis unit is used to perform real-time analysis on the fused data; The result determination unit is used to identify abnormal events in the road network, including traffic accidents, traffic jams, and bad weather.

[0010] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the event grading and early warning module includes, The event grading unit is used to grade according to the severity and urgency of abnormal events; The early warning information generation unit is used to generate early warning information; The early warning information publishing unit is used to send early warning information to relevant departments and the public through various channels.

[0011] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the system management and user interaction module includes, The device management unit is used to manage the hardware devices of the system; The user permission management unit is used to manage user permissions; The data storage management unit is used to manage the data storage of the system; The user interaction interface is used to facilitate users to view the road network status and abnormal event information in real time.

[0012] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the data cleaning unit uses the following formula for outlier detection,

[0013] wherein, X represents a data point, μ represents the mean value of the data, and σ represents the standard deviation of the data; If > 3, then this data point is considered an outlier.

[0014] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the data conversion unit uses the following formula for data normalization processing,

[0015] wherein, X represents the original data point, X min represents the minimum value of the data, X max represents the maximum value of the data, and X norm represents the data point after normalization processing.

[0016] As a preferred solution of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to the present invention, wherein: the data association unit uses the following formula for feature fusion,

[0017] wherein, α and β represent weight coefficients for adjusting the contribution degrees of different data sources, T norm represents the normalized traffic flow data, and Y norm represents the normalized vehicle speed data.

[0018] Advantages of the present invention: Through the multi-source data acquisition module, the present invention can collect various data such as traffic flow, vehicle speed, meteorological data, and video images in real time, achieving a comprehensive perception of the road network operation status. The data fusion and preprocessing module performs fusion processing on the collected multi-source data, effectively removing noise and redundant information in the data and improving the data quality; this data-based processing method enables the integration of data from different sources, providing a high-quality data basis for subsequent abnormal event detection, greatly improving the monitoring efficiency and accuracy. The abnormal event detection and recognition module can use data analysis and result determination units to analyze the fused data in real time and accurately identify abnormal events in the road network, such as traffic accidents, traffic congestion, and bad weather, significantly improving the monitoring efficiency and accuracy; the event grading and warning module grades according to the severity and urgency of abnormal events and issues warning information in a timely manner, enabling relevant departments to respond quickly and take measures in advance, effectively avoiding delays caused by human factors and reducing the impact of abnormal events on road network operation and public travel. Brief Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them: Figure 1 It is a video platform network topology diagram of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data of the present invention.

[0020] Figure 2 It is a computer device diagram of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data of the present invention. Detailed Embodiments

[0021] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification.

[0022] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0023] Secondly, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0024] Next, the present invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of the present invention, for the convenience of explanation, the cross-sectional views showing the device structure will be enlarged locally not in accordance with the general scale, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention here. In addition, the three-dimensional spatial dimensions of length, width, and depth should be included in actual production.

[0025] Embodiment, refer to Figure 1-2, as shown in the figure, the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data includes a multi-source data collection module for collecting road network operation data and environmental data; a data fusion and preprocessing module for performing fusion processing on the collected multi-source data; an abnormal event detection and identification module for performing real-time analysis on the fused data to identify abnormal events in the road network; an event grading and early warning module for grading according to the severity and urgency of abnormal events and issuing early warning information; a system management and user interaction module for providing system management and user interaction functions; real-time collection of various road network operation data including traffic flow, vehicle speed, and meteorological conditions, as well as related environmental data. These sensors and monitoring devices are carefully arranged at key nodes of the road network to ensure the comprehensiveness and real-time nature of the data, providing a solid data foundation for subsequent analysis and processing; the collected multi-source data is then transmitted to the data fusion and preprocessing module. In this module, the data is first cleaned to remove noise and redundant information therein to improve the quality and usability of the data. Then, the data conversion unit uniformly converts data in different formats into a standardized format for subsequent fusion operations. Finally, the data association unit integrates these processed data to form a comprehensive data set, preparing for the detection and identification of abnormal events. This process not only ensures the consistency of the data but also enhances the comprehensive perception ability of the road network state by fusing multi-source data; the abnormal event detection and identification module is the core part of the system, which performs real-time analysis on the fused data. The data analysis unit uses advanced algorithms and models to extract key features from the massive data, and these features can reflect the real-time operation state of the road network. The result determination unit then based on these features, uses a pre-trained machine learning model or set rules to accurately identify abnormal events such as traffic accidents, traffic jams, or bad weather. The efficient operation of this module enables the system to quickly respond at the initial stage of the occurrence of abnormal events, improving the timeliness and accuracy of event handling; the event grading and early warning module is responsible for grading the identified abnormal events. The event grading unit divides the events into different levels according to the severity and urgency of the events so that relevant departments can take corresponding measures according to the priorities of the events. The early warning information generation unit then generates detailed early warning information according to the level and specific situation of the event. These information not only include the type, location, and time of the event but may also include predictions of the event development trend and recommended countermeasures. The early warning information release unit then conveys the early warning information to relevant departments and the public in a timely manner through various channels such as text messages, App push notifications, traffic lights, or information boards, ensuring that they can quickly obtain the information and take actions, thereby effectively reducing the impact of abnormal events on road network operation and public travel; the system management and user interaction module provides support for the stable operation of the entire system and user operations.The device management unit is responsible for comprehensively monitoring and maintaining the system's hardware devices to ensure that all devices can operate normally. Once a fault is detected, it can be repaired or replaced in a timely manner. The user permission management unit strictly controls user access permissions, assigns corresponding operation permissions according to different user roles, and ensures the security and confidentiality of the system. The data storage management unit carefully manages a large amount of data. Through measures such as regular backups, it ensures the security and integrity of the data and prevents data loss or damage. The user interface provides users with an intuitive and convenient operation platform. Users can easily view the real-time status, historical data, and warning information of the road network, and can also perform system configuration and management operations, greatly improving the user experience. Through the close cooperation of the above-mentioned modules, the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data can not only effectively solve the problems existing in the prior art, such as low monitoring efficiency, incomplete data, and untimely response, but also significantly improve the monitoring and processing capabilities of road network abnormal events, enhance the safety and efficiency of road network operation, and provide a more efficient and reliable road network monitoring solution for traffic management departments and the public.

[0026] Specifically, the multi-source data acquisition module includes IoT sensors for collecting traffic volume, speed, and weather data; video surveillance equipment for collecting video image data of the road network; these sensors usually use geomagnetic induction, microwave radar, or video analysis technologies, and are precisely deployed at key sections of highways, intersections, and toll booths, etc., to monitor the number of passing vehicles in real time and provide raw data for traffic flow statistics and analysis. Speed ​​sensors use laser radar, ultrasonic speed measurement, or coil detection, and are also installed at key sections to measure vehicle speeds in real time. Through these speed data, the congestion of the road section and the driving status of the vehicle can be analyzed. Meteorological sensors include temperature sensors, humidity sensors, wind speed and direction sensors, and visibility sensors. They are installed at meteorological monitoring stations or specific monitoring points along the road network to collect real-time environmental meteorological data, such as temperature, humidity, wind speed, wind direction, and visibility. These meteorological data are crucial for assessing the impact of severe weather on the operation of the road network. Video surveillance equipment is mainly composed of high-definition cameras, which are installed at important locations such as along highways, bridges, tunnels, toll stations, and service areas. They can capture video image data of the road network in real time. These video images not only provide intuitive road condition information for traffic management departments, but also can assist in identifying abnormal events such as traffic accidents and traffic congestion through image analysis technology. Video surveillance equipment usually has night vision and autofocus functions to ensure that road condition information can be clearly captured under different lighting conditions. In addition, some video surveillance equipment is also equipped with an intelligent analysis module that can analyze video streams in real time, automatically detect abnormal behaviors such as vehicles driving in the wrong direction and pedestrians breaking in, and promptly feed back relevant information to the system; these IoT sensors and video surveillance equipment are connected to the data fusion and preprocessing module via wired or wireless networks to ensure that the collected data can be transmitted to the system in a timely and accurate manner, providing comprehensive and real-time data support for subsequent abnormal event detection and identification. Through this multi-dimensional data collection method, the system can more comprehensively perceive the operating status of the road network, laying a solid foundation for improving the monitoring efficiency and accuracy of abnormal events on the road network.

[0027] Furthermore, the data fusion and preprocessing module includes a data cleaning unit for removing noise and redundant information in the collected data; a data conversion unit for converting data in different formats into a unified format; and a data association unit for associating multi-source data to form a comprehensive data set.

[0028] Specifically, the abnormal event detection and recognition module includes a data analysis unit for real-time analysis of the fused data, and a result determination unit for identifying abnormal events in the road network, including traffic accidents, traffic congestion, and bad weather, ensuring that various types of collected data can enter the subsequent analysis and processing process in a high-quality and standardized form. Specifically, this module covers three key units that work together to optimize data quality. The data cleaning unit is the primary link in the data fusion and preprocessing process. In the road network monitoring scenario, the collected data may be interfered by various factors, such as sensor failures, environmental noise, data transmission errors, etc., resulting in noise and redundant information in the data. The data cleaning unit screens and corrects these raw data through a series of algorithms and technical means. It can identify and eliminate obviously incorrect data records, such as speed values outside the reasonable range or abnormal meteorological data readings. At the same time, for duplicate data records, this unit will perform deduplication to ensure the uniqueness and accuracy of the data. In addition, the data cleaning unit can also fill in missing data, using methods such as interpolation and mean replacement to make the data set more complete, providing a reliable data basis for subsequent data processing and analysis. The data conversion unit is responsible for solving the problem of inconsistent data formats. In the multi-source data acquisition module, the data collected by Internet of Things sensors and video monitoring devices often have different formats. For example, the traffic flow sensor may output digital signals, while the video monitoring device provides images or video streams. The data conversion unit converts these different formats of data into a unified format for subsequent fusion processing. For example, for text-format meteorological data, this unit converts it into a structured data table; for image data, it performs format normalization processing, such as uniformly adjusting images with different resolutions to a standard resolution and converting them into an image format suitable for analysis. Through this process, the data conversion unit ensures the consistency of all data in format, creating conditions for further data processing and analysis. The data association unit further integrates data from different sources to form a comprehensive data set. In road network monitoring, traffic flow, vehicle speed, meteorological data, and video image data, etc., each reflect different aspects of the road network operation. The data association unit associates these different types of data through key information such as timestamps and geographical locations. For example, it can match the traffic flow data at a certain moment with the meteorological data at the same moment according to the timestamp, and at the same time combine the road condition images captured by the video monitoring device to generate a comprehensive data record containing various information. This association not only includes data at the same time point but also can involve data at different time points to reflect the changing trend of the road network state.Through the processing of the data association unit, the system can obtain a comprehensive and integrated dataset, providing richer and more comprehensive information support for the detection and identification of abnormal events; through the collaborative work of the data cleaning unit, data conversion unit and data association unit, the data fusion and preprocessing module effectively improves the quality and usability of the data, providing a strong guarantee for the efficient operation of the multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data.

[0029] Specifically, the event grading and early warning module includes an event grading unit for grading according to the severity and urgency of abnormal events; an early warning information generation unit for generating early warning information; an early warning information release unit for sending early warning information to relevant departments and the public through various channels; the event grading unit considers the following key factors to evaluate the severity and urgency of abnormal events; According to the event type: Different types of events such as traffic accidents, traffic jams, and bad weather have different impacts on the operation of the road network.

[0030] According to the impact scope: The length of the road section affected by the event, the number of lanes involved, the number of vehicles affected, etc.

[0031] According to the duration: The estimated time from the occurrence to the resolution of the event, and the longer the duration, the greater the impact.

[0032] According to the potential hazards: The degree of secondary disasters that the event may cause or the threat to personnel safety, such as the number of casualties in traffic accidents, visibility in bad weather, etc.

[0033] Here, the event grading unit uses a comprehensive scoring algorithm to grade abnormal events. The specific steps are as follows: Set a weight value for each grading factor. The weight value is determined according to the importance of the factor. The weight of the event type is w1, the weight of the impact scope is w2, the weight of the duration is w3, and the weight of the potential hazards is w4. Then, perform a quantitative scoring for each factor. The score of the event type is S1; the score of the impact scope is S2; the score of the duration is S3; the score of the potential hazards is S4. The specific algorithm is; ; Here, the weight value of the event type w1 is 0.3, the weight value of the impact scope w2 is 0.3, the weight value of the duration w3 is 0.2, and the weight value of the potential hazards w4 is 0.2. The values here are determined by analyzing historical data and statistically calculating the actual contributions of different factors to the operation of the road network. It should be noted that if a certain type of event frequently occurs in a certain area, the weight of this type of event needs to be adjusted to more accurately reflect its impact on the operation of the road network; Events are classified into different levels according to the comprehensive score S. Among them, level 1 events are determined as: S≥80. At this time, it is a serious event and needs to be processed immediately; level 2 events are determined as: 50≤S<80. At this time, it is a relatively serious event and needs to be processed preferentially; level 3 events are determined as: S<50. At this time, it is a general event and is processed according to the normal process. The event classification unit also has a dynamic adjustment mechanism, which can adjust the classification criteria and weights according to real-time data and historical data. For example, if a certain type of event frequently occurs in a certain area, the system will automatically adjust the weight of this type of event to more accurately reflect its impact on the road network operation; The event type score can be determined according to the severity of the event and its impact on the road network operation. Generally, it is set as follows: traffic accident: 100, which is the most serious; traffic congestion: 70; bad weather: 50; other events: 30. It should be noted that if traffic congestion usually causes serious traffic interruption and safety problems within a section of the road, a higher score can be given; The impact range score can be determined according to the length of the road section affected by the event, the number of lanes involved, the number of vehicles affected, etc. Regarding the score based on the length of the affected road section: 0 - 1 km: 20; 1 - 5 km: 50; more than 5 km: 100; Regarding the number of lanes involved: 1 lane: 20; 2 lanes: 50; 3 lanes and above: 100; Regarding the number of affected vehicles: 0 - 100 vehicles: 20; 101 - 500 vehicles: 50; more than 500 vehicles: 100; The potential hazard score can be determined according to the secondary disasters that the event may cause or the degree of threat to personnel safety; no casualties: 20; minor injuries: 50; serious injuries or deaths: 100; visibility less than 50 meters: 100; visibility 50 - 100 meters: 50; visibility more than 100 meters: 20; That is, if an event causes serious injuries or deaths, or the visibility is less than 50 meters, then S4 can take 100.

[0034] Furthermore, the system management and user interaction module includes a device management unit for managing the hardware devices of the system; a user permission management unit for managing user permissions; a data storage management unit for managing the data storage of the system; and a user interaction interface for facilitating users to view the road network status and abnormal event information in real time.

[0035] Specifically, the data cleaning unit uses the following formula for outlier detection, where X represents the data point, μ represents the mean of the data, and σ represents the standard deviation of the data; If >3, then this data point is considered an outlier.

[0036] Furthermore, the data conversion unit uses the following formula for data normalization processing,

[0037] Among them, X represents the original data point, X min represents the minimum value of the data, X max represents the maximum value of the data, X norm represents the data point after normalization.

[0038] Furthermore, the data association unit performs feature fusion using the following formula,

[0039] Among them, α and β represent weight coefficients, used to adjust the contribution degrees of different data sources, T norm represents the normalized traffic flow data, Y norm represents the normalized vehicle speed data.

[0040] Furthermore, if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention essentially or the part that makes a contribution to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. And the aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0041] Operation process: First, the deployment of hardware devices will be carried out, including deploying Internet of Things sensors such as traffic flow sensors, vehicle speed sensors, and meteorological sensors at key sections and nodes, as well as installing video monitoring devices to ensure that various data such as traffic flow, vehicle speed, meteorological data, and video images can be collected in real time. At the same time, a data server and storage devices will also be configured for storing and processing the collected data. In terms of the software system, a data fusion and preprocessing module, an abnormal event detection and identification module, an event classification and early warning module, and a system management and user interaction module will be deployed, which are respectively responsible for functions such as data cleaning, conversion, association, analysis and determination of abnormal events, generation and release of early warning information, and device management, user permission management, data storage management, and user interaction of the system.

[0042] In the data collection and preprocessing stage, IoT sensors and video surveillance devices collect data in real time and transmit the collected data to the data server for storage. The data cleaning unit in the data fusion and preprocessing module processes the collected data, removes noise and redundant information, detects and removes outliers to ensure the accuracy and reliability of the data. The data conversion unit converts data in different formats into a unified format and normalizes the data to eliminate the dimensional differences between different data sources. The data association unit associates multi-source data to form a comprehensive data set, and through time alignment and spatial alignment, ensures the consistency of data from different data sources in terms of time and space.

[0043] Entering the abnormal event detection and identification link, the data analysis unit analyzes the fused data in real time, extracts key features, and deeply analyzes the data to identify potential abnormal events. The result determination unit identifies abnormal events in the road network, such as traffic accidents, traffic jams, bad weather, etc., based on the analysis results, and classifies and marks the identified abnormal events to provide a basis for subsequent early warning and handling.

[0044] In the event grading and early warning stage, the event grading unit grades the abnormal events according to their severity and urgency, divides the events into different levels so as to take corresponding countermeasures. The early warning information generation unit generates early warning information according to the level and type of the event. The early warning information includes event type, occurrence location, severity, recommended measures, etc. The early warning information release unit then sends out early warning information to relevant departments and the public through various channels. The release channels include text messages, App push notifications, traffic lights, information boards, etc., to ensure that the information can be conveyed in a timely manner.

[0045] In terms of system management and user interaction, the device management unit centrally manages the hardware devices of the system to ensure the normal operation of the devices, regularly checks the device status, and promptly discovers and handles device failures. The user permission management unit manages user permissions, assigns different permissions according to user roles to ensure the security and confidentiality of the system. The data storage management unit centrally manages the data of the system to ensure the security and integrity of the data, and regularly backs up the data to prevent data loss. The user interaction interface provides a friendly interaction experience for users, facilitating users to view the road network status and abnormal event information in real time. Users can view real-time data, historical data, early warning information, etc. through the interface, and can also perform system configuration and management operations.

[0046] During operation, the system continuously collects and processes data, monitors the road network status, and regularly generates system operation reports to analyze system performance and abnormal event handling situations. At the same time, it also regularly maintains and upgrades the system, promptly updates the software system, fixes known vulnerabilities, and optimizes system performance to ensure the stability and advancement of the system.

[0047] Importantly, it should be noted that the construction and arrangement of the present application shown in multiple different exemplary embodiments are merely illustrative. Although only a few embodiments are described in detail in this disclosure, those who refer to this disclosure should readily understand that many modifications are possible without materially departing from the novel teachings and advantages of the subject matter described in this application (e.g., changes in the dimensions, scales, structures, shapes and proportions of various elements, as well as parameter values (such as temperature, pressure, etc.), installation arrangements, use of materials, colors, orientations, etc.). For example, an element shown as integrally formed may be composed of multiple parts or elements, the position of the element may be inverted or otherwise changed, and the nature, number or position of discrete elements may be altered or changed. Accordingly, all such modifications are intended to be included within the scope of the present invention. The order or sequence of any process or method steps may be altered or reordered according to alternative embodiments. In the claims, any clause of "means-plus-function" is intended to cover the structures that perform the functions described herein, and not only structurally equivalent but also equivalent structures. Other substitutions, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments without departing from the scope of the present invention. Accordingly, the present invention is not limited to a particular embodiment, but extends to various modifications that still fall within the scope of the appended claims.

[0048] In addition, in order to provide a concise description of the exemplary embodiments, not all features of the actual embodiments may be described (i.e., those features that are not relevant to the currently contemplated best mode of carrying out the present invention, or those features that are not relevant to the implementation of the present invention).

[0049] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous specific implementation decisions may be made. Such development efforts may be complex and time-consuming, but for those of ordinary skill in the art who benefit from this disclosure, the development efforts will be a routine task of design, fabrication and production without undue experimentation.

[0050] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention may be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data, characterized in that: including a multi-source data acquisition module for acquiring road network operation data and environmental data; a data fusion and preprocessing module for performing fusion processing on the acquired multi-source data; an abnormal event detection and recognition module for performing real-time analysis on the fused data to identify abnormal events in the road network; an event grading and early warning module for grading according to the severity and urgency of abnormal events and sending out early warning information; a system management and user interaction module for providing system management and user interaction functions.

2. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to claim 1, characterized in that: The multi-source data acquisition module includes Internet of Things sensors for acquiring traffic flow, vehicle speed, and meteorological data; video monitoring devices for acquiring video image data of the road network.

3. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to claim 1, characterized in that: The data fusion and preprocessing module includes a data cleaning unit for removing noise and redundant information from the acquired data; a data conversion unit for converting data in different formats into a unified format; a data association unit for associating multi-source data to form a comprehensive data set.

4. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to claim 1, wherein: The abnormal event detection and recognition module includes a data analysis unit for performing real-time analysis on the fused data; a result determination unit for identifying abnormal events in the road network, including traffic accidents, traffic congestion, and bad weather.

5. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to claim 1, characterized in that: The event grading and early warning module includes an event grading unit for grading according to the severity and urgency of abnormal events; an early warning information generation unit for generating early warning information; an early warning information release unit for sending out early warning information to relevant departments and the public through multiple channels.

6. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data as claimed in claim 1 or 5, characterized in that: The system management and user interaction module includes a device management unit for managing the hardware devices of the system; a user permission management unit for managing user permissions; a data storage management unit for managing the data storage of the system; a user interaction interface for facilitating users to view the road network status and abnormal event information in real time.

7. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to claim 5, characterized in that: The data cleaning unit uses the following formula for outlier detection Where X represents the data point, μ represents the mean of the data, and σ represents the standard deviation of the data; If > 3, then this data point is considered an outlier.

8. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to claim 7, characterized in that: The data conversion unit uses the following formula for data normalization processing Among them, X represents the original data point, X min represents the minimum value of the data, X max represents the maximum value of the data, X norm represents the data point after normalization.

9. The multi-dimensional intelligent perception system for road network abnormal events based on intelligent Internet of Things data according to claim 8, wherein: The data association unit uses the following formula for feature fusion Among them, α and β represent weight coefficients used to adjust the contribution degrees of different data sources, and T norm represents the traffic flow data after normalization, and Y norm represents the vehicle speed data after normalization.

Images