Real-time traffic flow prompting system based on Internet of Vehicles

Abstract

The invention, which relates to the technical field of traffic flow analysis, discloses a real-time traffic flow prompting system based on the Internet of Vehicles, comprising a data acquisition module, a road section flow evaluation module, a route comparison module, a prompting module and a response module. The data acquisition module collects data from multiple channels of vehicles, road infrastructures and traffic management departments, and provides comprehensive basic information for subsequent traffic flow evaluation and the like. According to the invention, through integration of the Internet of Vehicles technology, multi-channel data collection from vehicles, road infrastructures and traffic management departments is realized, the real-time performance and accuracy of traffic flow information are significantly improved, and the data acquisition module can monitor and analyze vehicle driving speed, road conditions and traffic events in real time. The road section flow evaluation module dynamically evaluates the traffic flow condition according to the real-time data and historical traffic parameters, so that more accurate traffic flow information and route selection suggestions are provided for drivers.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic flow analysis, and particularly to a real-time traffic flow prompting system based on the Internet of Vehicles. Background Art

[0002] With the acceleration of the urbanization process, the problem of traffic congestion has become increasingly serious, and the demand for real-time traffic flow prompting systems has also increased. Existing traffic flow prompting systems mostly rely on limited data sources, such as fixed traffic monitoring cameras and road sensors. These systems often cannot cover all sections comprehensively, resulting in untimely information updates and insufficient accuracy. In addition, traditional systems lack flexibility and real-time performance in dealing with complex traffic situations, such as traffic accidents or road construction, and cannot provide timely and effective detour suggestions and coping strategies for drivers. Therefore, existing systems have obvious deficiencies in providing real-time and accurate traffic flow information and optimizing route suggestions.

[0003] In recent years, the development of Internet of Vehicles technology has provided new solutions for traffic flow prompting systems. The Internet of Vehicles realizes the real-time collection and processing of data through vehicle-to-vehicle communication (V2V), vehicle-to-infrastructure communication (V2I), and vehicle-to-network communication (V2N). The application of this technology enables traffic flow prompting systems to obtain information from more data sources, including the real-time speed, driving route, destination, etc. of vehicles, thereby providing a more comprehensive traffic flow analysis. However, although Internet of Vehicles technology provides rich data, how to effectively integrate and utilize these data to achieve real-time and accurate traffic flow assessment and optimal route recommendation is still a technical challenge.

[0004] To solve the above deficiencies, the following technical solutions are provided. Summary of the Invention

[0005] The purpose of the present invention is to solve the problems of limited data sources, untimely information updates, insufficient accuracy, and lack of ability to handle complex traffic situations in existing traffic flow prompting systems, and to propose a real-time traffic flow prompting system based on the Internet of Vehicles.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A real-time traffic flow prompting system based on the Internet of Vehicles, comprising: A data acquisition module, which collects data from vehicles, road infrastructure, and traffic management departments to provide comprehensive basic information for subsequent traffic flow assessment, etc.; A section traffic flow assessment module, which integrates data from multiple channels and real-time assesses the traffic flow status of sections according to set criteria to provide a basis for route selection; The route comparison module integrates route information and uses a comparison algorithm to screen out the optimal driving route after comprehensively considering different traffic flow factors; The prompt module conveys traffic flow information and recommended routes to the driver through vision, hearing, and touch; The response module provides specific response strategies for the driver according to traffic congestion and special situations and dynamically adjusts according to real-time changes.

[0007] Furthermore, the process executed by the data acquisition module is as follows: Vehicle data collection: On each vehicle connected to the Internet of Vehicles, a data acquisition device is installed, including a speed sensor, an odometer sensor, and feedback information from the in-vehicle navigation system; the speed sensor measures the real-time driving speed of the vehicle; the odometer sensor records the mileage traveled by the vehicle, and by calculating the change in mileage and time, it assists in analyzing the driving state of the vehicle; the in-vehicle navigation system feeds back the driving route plan and destination information of the vehicle to the data acquisition module for understanding the travel intention of the vehicle; Road infrastructure data collection: At key nodes and sections of the road, various types of monitoring devices are set up, including induction coils installed at intersections and sections. The induction coils detect the number and time interval of passing vehicles, and the vehicle passing rate at this point can be obtained through calculation; at the same time, cameras are installed along the road to take real-time pictures of the road conditions. Through image recognition technology, the vehicle types and numbers passing through the area per unit time are counted, and whether there are special situations on the road is identified, including accident scenes, road construction, etc.; in addition, the electronic road sign facilities can also provide the data acquisition module with basic information about the section, including speed limits and lane changes; Establish a data connection channel with the traffic management department to obtain the comprehensive traffic data it holds, including real-time traffic accident information, including the accident location, severity, and the scope of impact on traffic; road construction information, including the construction section, construction time, estimated completion time, and traffic control measures during construction; and traffic control information, including temporary traffic control areas, control times, and control reasons; these data are transmitted through encryption and security authentication methods to ensure the accuracy and security of the data.

[0008] Furthermore, the specific operation steps of the section traffic flow evaluation module are as follows: First, integrate the driving data of vehicles in the section, road infrastructure monitoring data, and relevant data from the traffic management department collected from the data acquisition module; Set section traffic flow evaluation criteria according to historical traffic data and road design parameters, and set different flow thresholds for different types of roads; at the same time, when there are traffic accidents or road construction situations, increase the evaluation level of the traffic flow condition; Based on the integrated data and the set evaluation criteria, the traffic flow condition of each road section is evaluated in real time. This evaluation is not a one-time thing, but is continuously updated as new data is continuously input; Optimize the evaluation of the traffic flow of the road section by using a traffic flow prediction algorithm based on machine learning.

[0009] Furthermore, the specific operation steps for the road section flow evaluation module to optimize the evaluation of the traffic flow of the road section by using a traffic flow prediction algorithm based on machine learning are as follows: The traffic flow prediction algorithm based on machine learning adopted is a neural network algorithm. The neurons in the input layer receive vehicle speed, vehicle quantity, road type, and whether there is accident or construction information. By training historical data, the weights between the neurons in the hidden layer are adjusted to make the output layer predict the congestion degree of the traffic flow, and the degree from smooth to congested is represented by the numerical value 0 - 1; Let the traffic congestion degree be , the vehicle speed be , the vehicle quantity be , the road type be , the accident or construction situation be , then , where are the parameters to be learned, is the error term, and the values of these parameters are determined by minimizing the error term to obtain a traffic flow evaluation model, and the traffic flow is evaluated with this model.

[0010] Furthermore, the execution process of the route comparison module is as follows: Collect all the feasible route information within the preset range around the current vehicle, including the road connection situation, the grade of each road, and the speed limit information in the map data obtained from the in-vehicle navigation system; At the same time, combine the traffic flow condition information of each road section provided by the road section flow evaluation module to form a complete route information set; Adopt a multi-factor comparison algorithm to compare the advantages and disadvantages of different routes, and at the same time analyze the impact of traffic flow on the travel time; Estimate the expected passing time of each road section on each route according to the road section length, speed limit, and traffic flow condition, and comprehensively evaluate the overall travel time of the two routes; At the same time, introduce the ARIMA algorithm to calculate the optimal route; According to the result of the comparison algorithm, screen out the optimal route in the current situation from among numerous feasible routes; And, as the traffic flow changes, continuously re-evaluate and screen the optimal route to adapt to the dynamic traffic environment.

[0011] Furthermore, the specific operation steps for introducing the ARIMA algorithm in the route comparison module to calculate the optimal route are as follows: When calculating the estimated passing time, not only the current traffic flow is considered, but also historical traffic flow data is combined for prediction. A time series model is established based on historical traffic flow data to predict the traffic flow in this time period in the future; let the time series be , is the autoregressive order, is the differencing order, is the moving average order, The model is expressed as , where is the lag operator, , is a white noise sequence, and the value of is determined by analyzing historical data, and then the future traffic flow is predicted to provide a more accurate time estimate for route comparison.

[0012] Furthermore, the specific operation steps of the prompt module are as follows: Visual prompt: On the central control display screen of the vehicle, traffic flow information and recommended routes are displayed in a graphical interface; different traffic flow conditions of road sections are identified by different colors on the map interface of the display screen; At the same time, the recommended optimal route will be displayed as a prominent line on the map, and information such as the estimated driving time and distance will be marked beside it. In addition, traffic flow prompt information is displayed through the head-up display system equipped on the vehicle and projected onto the windshield, so that the driver can obtain information without shifting the line of sight; on this basis, the display of the map interface is optimized by using image processing algorithms, and the gradient effect of the colors of road sections on the map is dynamically adjusted according to the change of traffic flow, so that the driver can more intuitively feel the change trend of traffic flow; at the same time, the optimal route is optimized by the Dijkstra algorithm; Auditory prompt: The in-vehicle audio system provides auditory prompts for the driver. When the vehicle approaches a road section with heavy traffic flow, corresponding voice prompts will be issued; when approaching a severely congested road section or a road section where a sudden traffic accident occurs, the voice prompts will be more frequent; the volume and intonation of the voice prompts are adjusted according to the severity of the traffic flow to attract the driver's attention; Tactile prompt: Through the tactile feedback seat or steering wheel equipped on the vehicle, these tactile feedback devices play a role in special traffic situations. When the vehicle is about to enter a severely congested road section, the seat will vibrate to remind the driver of the change in road conditions from the side. This non-visual and non-auditory prompt method adds an additional prompt dimension without disturbing the driver's normal driving operation.

[0013] Furthermore, the specific operation steps of optimizing the optimal route by the Dijkstra algorithm in the prompt module are as follows: The Dijkstra algorithm is used to ensure that the optimal route is displayed most clearly and reasonably on the map, avoiding confusion with other road lines. The Dijkstra algorithm sets as the road network map, where is the set of nodes, is the set of edges, is the starting point, is the ending point, represents the shortest distance from the starting point to the node ; represents the predecessor node of the node ; Initialize , and for other nodes ; Then repeat the following steps: Select the node with the smallest undetermined shortest path ; For the nodes adjacent to , update , where is the weight of the edge ; Until the shortest path of the ending point is determined. After finding the optimal route through this algorithm, it is highlighted on the map with different widths, colors, and line styles.

[0014] Furthermore, the steps executed by the response module are as follows: When the prompt module prompts that there is a congestion situation on the front section of the road, the response module will provide specific response strategies for the driver according to the congestion degree and the expected duration; The judgment of the congestion degree is comprehensively determined through surrounding road conditions and weather conditions, and the determined congestion degrees are divided into mild congestion, moderate congestion, and severe congestion; For mild congestion, prompt the driver to maintain a normal speed and pay attention to the safety distance from the vehicle in front; For moderate congestion, prompt the driver to reduce the speed, prepare for slow driving, and according to the surrounding road condition information, suggest whether to change lanes to obtain a smoother driving; For severe congestion, in addition to prompting to find an alternative route, when the driver cannot change the route, provide driving skills in the congested section, including maintaining patience and avoiding frequent lane changes to reduce the occurrence of traffic accidents; When encountering special situations such as traffic accidents and road construction, provide targeted response measures; If it is a traffic accident, inform the driver of the location and severity of the accident, remind the driver to pay attention to avoiding rescue vehicles and on-site staff, and at the same time, according to the traffic control situation, guide the driver on how to bypass the accident scene; For road construction situations, prompt the driver of the scope of the construction section, the type of construction, and the traffic control measures during the construction, and assist the driver to pass through the construction area safely; The coping strategies provided by the coping module are dynamically adjusted according to the real-time changes in traffic flow and the actual operation of the driver. For example, when the driver encounters new congestion while driving along the recommended route, the system will re-evaluate and promptly provide the driver with new coping strategies to ensure that the driver can receive prompt guidance throughout the driving process.

[0015] Furthermore, the process of judging the congestion level in the coping module is as follows: It is comprehensively judged through surrounding road conditions and weather conditions. Among them, the road conditions include quantifying the number of switchable lanes, average vehicle speed, and average vehicle spacing and then performing normalization processing. The sum of the number of switchable lanes and the average vehicle speed is multiplied by the average vehicle spacing to obtain the road condition evaluation value Y. The weather condition is judged by the current weather situation, and corresponding values for different types of weather and severity are set. The weather types are divided into four types: sunny, cloudy, rainy, and snowy, corresponding to evaluation values k of 1, 2, 3, and 4 respectively. For different types of weather severity, a degree evaluation value h of 0 - 1 is set. When the current weather condition is determined, the weather evaluation value G is obtained through the formula G = k×h. Then, the calculated road condition evaluation value Y and weather evaluation value G are normalized and substituted into the following formula: To obtain the congestion judgment value DPZ, where are the preset weight coefficients of the weather evaluation value G and the road condition evaluation value Y respectively, is a correction factor, with a value set between 0.82 - 1.31, and the finally obtained congestion judgment value DPZ is used as the judgment standard for the congestion level. The obtained congestion judgment value DPZ is compared with three preset congestion judgment value intervals, which respectively correspond to mild congestion, moderate congestion, and severe congestion. When the congestion judgment value interval to which the congestion judgment value belongs is determined, the current congestion level is determined.

[0016] Compared with the prior art, the beneficial effects of the present invention are: (1) In the present invention, by integrating vehicle networking technology, data is collected from multiple channels including vehicles, road infrastructure, and traffic management departments, significantly improving the real-time performance and accuracy of traffic flow information. The data acquisition module can monitor and analyze vehicle driving speed, road conditions, and traffic events in real time. The section traffic flow evaluation module dynamically evaluates the traffic flow condition based on real-time data and historical traffic parameters, thereby providing more accurate traffic flow information and route selection suggestions for drivers. (2) In the present invention, by using the route comparison module and combining the road section traffic flow evaluation results with the multi-factor comparison algorithm, the optimal driving route can be screened out after comprehensively considering different traffic flow factors. This process not only takes into account the distance and speed limit information of the route, but also analyzes the impact of traffic flow on the driving time, thereby providing the driver with a faster and smoother route choice and optimizing the driving experience. (3) In the present invention, the prompt module and the response module convey traffic flow information and recommended routes to the driver through various means such as vision, audition, and touch, enhancing driving safety. The response module can provide specific response strategies for the driver according to real-time traffic flow changes and special situations, and dynamically adjust these strategies to help the driver promptly respond to traffic congestion and emergencies, reducing the occurrence of traffic accidents and improving the road use efficiency. Through this comprehensive prompt and response mechanism, comprehensive traffic support is provided for the driver, ensuring the safety and comfort of the driving process. Brief Description of the Drawings

[0017] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the drawings. Figure 1 It is the system general block diagram of the present invention. Detailed Embodiments

[0018] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0019] It should be understood that the terms "including" and "comprising" used in the specification and claims of this disclosure indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0020] It should also be understood that the terms used in this disclosure specification are only for the purpose of describing specific embodiments and are not intended to limit this disclosure. As used in this disclosure specification and claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms. It should also be further understood that the term "and / or" used in this disclosure specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0021] Such as Figure 1As shown in the figure, a real-time traffic flow prompting system based on the Internet of Vehicles includes a data acquisition module, a road section traffic flow evaluation module, a route comparison module, a prompting module, and a response module; The data acquisition module collects data from multiple channels including vehicles, road infrastructure, and traffic management departments, providing comprehensive basic information for subsequent traffic flow evaluation, etc.; Vehicle data collection: On each vehicle connected to the Internet of Vehicles, a dedicated data collection device is installed, including a speed sensor, an odometer sensor, and feedback information from the in-vehicle navigation system; the speed sensor can accurately measure the real-time driving speed of the vehicle, and its measurement range can be from 0 km / h (vehicle stationary state) to the maximum designed speed of the vehicle, with an accuracy of up to ±2 km / h; the odometer sensor can record the mileage traveled by the vehicle, and by calculating the change in mileage and time, it can assist in analyzing the driving state of the vehicle; the in-vehicle navigation system feeds back the vehicle's driving route plan and destination information to the data acquisition module, which is used to understand the vehicle's travel intention; Road infrastructure data collection: At key nodes and sections of the road, various types of monitoring devices are set up, including induction coils installed at intersections and some specific sections. The induction coils can detect the number and time interval of passing vehicles, and the vehicle passing rate at this point can be obtained through calculation; at the same time, high-definition cameras are installed along the road. The cameras can take real-time pictures of the road conditions. Through image recognition technology, the vehicle types and numbers passing through a specific area within a certain period of time can be counted, and it can also identify whether there are special situations on the road, including accident scenes, road construction, etc.; in addition, the electronic road sign facilities can also provide the data acquisition module with some basic information about the road section, including speed limits and lane changes; Establish a data connection channel with the traffic management department to obtain the comprehensive traffic data it holds, including real-time traffic accident information, including the accident location, severity, and the scope of impact on traffic; road construction information, such as the construction section, construction time, estimated completion time, and traffic control measures during construction; and traffic control information, such as temporary traffic control areas, control times, and control reasons; these data are transmitted through encryption and security authentication methods to ensure the accuracy and security of the data.

[0022] The road section traffic flow evaluation module integrates multi-party data and evaluates the traffic flow status of the road section in real time according to the set standards, providing a basis for route selection; First, integrate the driving data of vehicles in sections, road infrastructure monitoring data, and relevant data from traffic management departments collected by the data acquisition module; set the traffic flow evaluation criteria for sections according to historical traffic data and road design parameters. Different traffic flow thresholds are set for different types of roads (such as urban arterial roads, secondary arterial roads, highways, etc.). Taking urban arterial roads as an example, if the number of vehicles passing through a certain section within a unit time (such as every 10 minutes) exceeds 70% of the designed carrying capacity of the section, and the average vehicle speed is lower than 60% of the speed limit of the section, it is preliminarily determined that the traffic flow on this section is large. At the same time, if there are traffic accidents or road construction, etc., it will increase the evaluation level of the traffic flow situation; based on the integrated data and the set evaluation criteria, the section traffic flow evaluation module conducts real-time evaluation on the traffic flow situation of each section. This evaluation is not a one-time one, but is continuously updated as new data is continuously input; Adopt a traffic flow prediction algorithm based on machine learning, including neural network algorithms. The neurons in the input layer can receive information such as vehicle speed, number of vehicles, road type, whether there is an accident or construction, etc. By training historical data, adjust the weights between the neurons in the hidden layer so that the output layer can accurately predict the congestion degree of traffic flow, and represent the degree from smooth to congested by the numerical value 0 - 1, where 0 represents smooth and 1 represents severe congestion; Let the traffic congestion degree be , the vehicle speed be , the number of vehicles be , the road type (represented by a numerical value, such as 1 for highways, 2 for urban arterial roads, etc.) be , the accident or construction situation (1 if there is, 0 if there is none) be , then , where is parameters to be learned, the error term. Determine the values of these parameters by minimizing the error term, so as to obtain a traffic flow evaluation model, and evaluate the traffic flow with this model.

[0023] The route comparison module integrates route information and uses a comparison algorithm to screen out the optimal driving route after comprehensively considering factors such as traffic flow; Collect all available route information within a certain range around the current vehicle (e.g., within a radius of 10 kilometers centered on the vehicle). This information includes road connection conditions in the map data obtained from the in-vehicle navigation system, the grade of each road (such as highways, urban expressways, ordinary roads, etc.), speed limit information, etc. At the same time, combine the traffic flow status information of each section provided by the section flow evaluation module to form a complete set of route information; use a multi-factor comparison algorithm to compare the advantages and disadvantages of different routes. In addition to considering the distance factor of the route, more importantly, consider the impact of traffic flow on travel time. For example, for two different routes, one is shorter in distance but passes through multiple sections with heavy traffic, and the other is slightly longer in distance but has less traffic flow on most sections. By calculating the estimated passing time of each section on each route (estimated based on the section length, speed limit, and traffic flow status), comprehensively evaluate the overall travel time of the two routes.

[0024] At the same time, introduce the ARIMA algorithm to calculate the optimal route. When calculating the estimated passing time, not only consider the current traffic flow, but also combine historical traffic flow data for prediction. Establish a time series model based on historical traffic flow data to predict the traffic flow during this future time period, so as to more accurately estimate the passing time; let the time series be , be the autoregressive order, be the differencing order, be the moving average order, The model is expressed as , where is the lag operator, , is a white noise sequence, determined by analyzing historical data values, and then predict future traffic flow to provide a more accurate time estimate for route comparison; According to the results of the comparison algorithm, screen out the optimal route under the current situation from numerous available routes; this optimal route is not necessarily the shortest in distance, but must be the route with the shortest estimated travel time and the smoothest driving after comprehensively considering factors such as traffic flow. And, as the traffic flow changes, the route comparison module will continuously re-evaluate and screen the optimal route to adapt to the dynamic traffic environment.

[0025] The prompt module conveys traffic flow information and recommended routes to the driver through various ways such as vision, hearing, and touch; Visual Cue: On the central console display screen of the vehicle, traffic flow information and recommended routes are presented in an intuitive graphical interface. The map interface on the display screen will use different colors to identify sections with different traffic flow conditions. For example, green indicates smooth sections where the vehicle can travel at a normal speed; yellow indicates slightly congested sections where appropriate deceleration may be required; orange indicates moderately congested sections where the driver may need to be prepared for slow progress; and red indicates severely congested sections where it is recommended to avoid as much as possible. At the same time, the recommended optimal route will be prominently displayed on the map with a highlighted line (such as bold or color change), and information such as the estimated travel time and distance will be marked beside it. In addition, if the vehicle is equipped with a Head-Up Display (HUD), important traffic flow reminder information, such as the distance to the congested section ahead and the recommended vehicle speed, will also be projected onto the windshield, allowing the driver to obtain key information without having to shift their line of sight. On this basis, image processing algorithms are used to optimize the display of the map interface, dynamically adjusting the gradient effect of the colors of the sections on the map according to the changes in traffic flow, enabling the driver to more intuitively perceive the changing trend of traffic flow. At the same time, for the prominent display of the optimal route, the Dijkstra algorithm can be used to ensure that the optimal route is displayed most clearly and reasonably on the map, avoiding confusion with other road lines. The Dijkstra algorithm sets as the road network graph, where is the set of nodes (such as intersections), is the set of edges (road sections), is the starting point, is the ending point, represents the shortest distance from the starting point to the node , represents the predecessor node of the node . Initialize , and for other nodes . Then repeat the following steps: Select the node with the smallest undetermined shortest path ; for the nodes adjacent to , update , where is the weight of the edge (such as distance or estimated passing time); until the shortest path to the ending point is determined. After finding the optimal route through this algorithm, it is prominently displayed on the map with different widths, colors, and line styles.

[0026] Auditory Cue: Provide auditory cues for the driver through the in-vehicle audio system. When the vehicle approaches a section with heavy traffic flow, the system will issue corresponding voice prompts. For example, when it is 2 kilometers away from a moderately congested section, the voice prompt is "There is traffic congestion 2 kilometers ahead. Please drive carefully"; when approaching a severely congested section or a section with a sudden traffic accident, the voice prompts will be more urgent and frequent, such as "There is severe congestion 1 kilometer ahead. It is recommended that you find an alternative route as soon as possible". The volume and intonation of the voice prompts can be adjusted according to the severity of the traffic flow to attract the driver's sufficient attention; Tactile Cue: Through the tactile feedback seats or steering wheels equipped in the vehicle, these tactile feedback devices can play a role in special traffic situations. For example, when the vehicle is about to enter a severely congested section, the seat will produce a slight vibration to remind the driver of the change in road conditions from the side. This non-visual and non-auditory cue method can add an additional cue dimension without disturbing the driver's normal driving operation.

[0027] The response module provides specific coping strategies for the driver according to traffic congestion and special situations, and dynamically adjusts according to real-time changes; When the prompt module prompts that there is congestion on the front section, the response module will provide specific coping strategies for the driver according to the congestion degree and the expected duration; the judgment of the congestion degree is comprehensively judged through surrounding road conditions factors and weather conditions. Among them, the road conditions factors include the number of switchable lanes, the average vehicle speed, and the average vehicle spacing. After quantization and then normalization processing, the sum of the number of switchable lanes and the average vehicle speed is multiplied by the average vehicle spacing to obtain the road condition evaluation value Y; the weather condition is judged by the current weather situation, and the corresponding values for different types of weather and severity are set. The weather types are divided into four types: sunny, cloudy, rainy, and snowy, and the evaluation values k of 1, 2, 3, and 4 are set respectively. For different types of weather severity, the degree evaluation value h of 0-1 is set. When the current weather condition is determined, the weather evaluation value G is obtained through the formula G = k×h; then the calculated road condition evaluation value Y and weather evaluation value G are normalized and substituted into the following formula: To obtain the congestion judgment value DPZ, where are the preset weight coefficients of the weather evaluation value G and the road condition evaluation value Y respectively, is the correction factor, and its value is set between 0.82 and 1.31. The finally obtained congestion judgment value DPZ is used as the judgment standard for the congestion degree; the obtained congestion judgment value DPZ is compared with three preset congestion judgment value intervals. The three preset congestion judgment value intervals respectively correspond to mild congestion, moderate congestion, and severe congestion. When the congestion judgment value interval to which the congestion judgment value belongs is determined, the current congestion degree is determined; For mild congestion, prompt the driver to maintain a normal speed and pay attention to the safe distance from the vehicle ahead; for moderate congestion, prompt the driver to reduce the speed, get ready to move slowly, and based on the surrounding road conditions information, suggest whether to switch lanes for a smoother drive; for severe congestion, in addition to suggesting finding an alternative route, if the driver cannot change the route in time, provide driving skills in the congested section, including being patient and avoiding frequent lane changes to reduce the occurrence of traffic accidents; When encountering special situations such as traffic accidents and road construction, provide targeted countermeasures; if it is a traffic accident, inform the driver of the approximate location and severity of the accident, remind the driver to pay attention to avoiding rescue vehicles and on-site workers, and at the same time, according to the traffic control situation, guide the driver on how to bypass the accident scene. For road construction situations, explain in detail to the driver the scope of the construction section, the type of construction (such as road surface repair, bridge construction, etc.) and the traffic control measures during construction (such as lane narrowing, speed limit, etc.) to help the driver pass through the construction area safely; The countermeasures provided by the response module are not fixed, but will be dynamically adjusted according to the real-time changes in traffic flow and the actual operation of the driver. For example, if the driver encounters new congestion during the drive along the recommended route, the response module will re-evaluate and promptly provide the driver with new countermeasures to ensure that the driver can receive effective guidance throughout the driving process.

[0028] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor limit the present invention to only the specific implementation manners. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments to better explain the principle and practical application of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A real-time traffic flow prompting system based on the vehicle networking, characterized in that, Including: A data acquisition module, which is used to collect data from vehicles, road infrastructure and traffic management departments, providing comprehensive basic information for subsequent traffic flow assessment, etc.; A section traffic flow assessment module, which is used to integrate data from multiple channels and evaluate the traffic flow status of sections in real time according to set criteria, providing a basis for route selection; A route comparison module, which is used to integrate route information and use comparison algorithms to screen out the optimal driving route after comprehensively considering different traffic flow factors; A prompt module, which is used to convey traffic flow information and recommended routes to drivers through vision, audition and touch; A response module, which is used to provide specific response strategies for drivers according to traffic congestion and different special situations, and dynamically adjust according to real-time changes.

2. The real-time traffic flow prompting system based on the vehicle networking according to claim 1, wherein The process executed by the data acquisition module is as follows: Vehicle data collection: On each vehicle connected to the Internet of Vehicles, a data acquisition device is installed, including a speed sensor, an odometer sensor, and feedback information from the in-vehicle navigation system; the speed sensor measures the real-time driving speed of the vehicle; the odometer sensor records the mileage of the vehicle, and by calculating the change in mileage and time, it assists in analyzing the driving state of the vehicle; The in-vehicle navigation system feeds back the driving route plan and destination information of the vehicle to the data acquisition module for understanding the travel intention of the vehicle; Road infrastructure data collection: Various types of monitoring devices are set at key nodes and sections of the road, including induction coils installed at intersections and sections. The induction coils detect the number and time interval of passing vehicles, and calculate the vehicle passing rate at this point; at the same time, cameras are installed along the road to take real-time pictures of the road conditions. Through image recognition technology, the vehicle types and numbers passing through the area per unit time are counted, and whether there are special situations on the road is identified, including accident scenes and road construction; in addition, electronic road signs can also provide basic information of the section to the data acquisition module, including speed limits and lane changes; Establish a data connection channel with the traffic management department to obtain the comprehensive traffic data it holds, including real-time traffic accident information, including the accident location, severity, and the scope of impact on traffic; road construction information, including the construction section, construction time, estimated completion time, and traffic control measures during construction; and traffic control information, including temporary traffic control areas, control times, and control reasons; these data are transmitted through encryption and security authentication methods to ensure the accuracy and security of the data.

3. The real-time traffic flow prompting system based on the vehicle networking according to claim 1, wherein, The specific operation steps of the section traffic flow assessment module are as follows: First, integrate the driving data of vehicles in the section, road infrastructure monitoring data, and relevant data of the traffic management department collected from the data acquisition module; According to historical traffic data and road design parameters, set section traffic flow assessment criteria, and set different flow thresholds for different types of roads; at the same time, when there are traffic accidents or road construction situations, increase the assessment level of the traffic flow status; Based on the integrated data and the set assessment criteria, conduct real-time assessment of the traffic flow status of each section. This assessment is not a one-time assessment, but is continuously updated as new data is continuously introduced; Optimize the evaluation of road section traffic flow by using a machine learning-based traffic flow prediction algorithm.

4. The real-time traffic flow prompting system based on the vehicle networking according to claim 3, characterized in that The specific operation steps for the road section flow evaluation module to optimize the evaluation of road section traffic flow by using a machine learning-based traffic flow prediction algorithm are as follows: The machine learning-based traffic flow prediction algorithm adopted is a neural network algorithm. The neurons in the input layer receive vehicle speed, vehicle quantity, road type, and information on whether there is an accident or construction. By training historical data, the weights between the neurons in the hidden layer are adjusted so that the output layer predicts the congestion level of traffic flow, and the degree of smoothness to congestion is represented by the numerical value 0 - 1; Let the traffic congestion level be , the vehicle speed be , the vehicle quantity be , the road type be , the accident or construction situation be , then , where are the parameters to be learned, is the error term. The values of these parameters are determined by minimizing the error term to obtain a traffic flow evaluation model, and this model is used to evaluate the traffic flow.

5. The real-time traffic flow prompting system based on the vehicle networking according to claim 1, characterized in that The execution process of the route comparison module is as follows: Collect all feasible route information within a preset range around the current vehicle, including road connection conditions, the grade of each road, and speed limit information in the map data obtained from the in-vehicle navigation system; at the same time, combine the traffic flow status information of each road section provided by the road section flow evaluation module to form a complete route information set; Use a multi-factor comparison algorithm to compare the advantages and disadvantages of different routes, and at the same time analyze the impact of traffic flow on travel time; estimate the expected passing time of each road section on each route according to the road section length, speed limit, and traffic flow status, and comprehensively evaluate the overall travel time of the two routes; at the same time, introduce the ARIMA algorithm to calculate the optimal route; According to the results of the comparison algorithm, screen out the optimal route under the current situation from numerous feasible routes; and continuously re-evaluate and screen the optimal route as the traffic flow changes to adapt to the dynamic traffic environment.

6. The real-time traffic flow prompting system based on the vehicle networking according to claim 5, wherein, The specific operation steps for introducing the ARIMA algorithm in the route comparison module to calculate the optimal route are as follows: When calculating the estimated time of arrival, not only the current traffic flow is considered, but also historical traffic flow data is combined for prediction. A time series model is established based on historical traffic flow data to predict the traffic flow in the future during this time period; let the time series be , is the autoregressive order, is the differencing order, is the moving average order, The model is expressed as , where is the lag operator, , is a white noise sequence, and the value of is determined by analyzing historical data, and then the future traffic flow is predicted to provide a more accurate time estimate for route comparison.

7. The real-time traffic flow prompting system based on the vehicle networking according to claim 1, wherein, The specific operation steps of the prompt module are as follows: Visual prompt: On the central control display screen of the vehicle, display traffic flow information and recommended routes in a graphical interface; different traffic flow status road sections will be marked with different colors on the map interface of the display screen; At the same time, the recommended optimal route will be displayed as a prominent line on the map, and the estimated travel time and distance information will be marked beside it. In addition, display traffic flow prompt information through the head-up display system equipped in the vehicle and project it onto the windshield, so that the driver can obtain information without shifting the line of sight; on this basis, use an image processing algorithm to optimize the display of the map interface, and dynamically adjust the gradient effect of the road section colors on the map according to the change of traffic flow, so that the driver can more intuitively feel the change trend of traffic flow; at the same time, optimize the optimal route through the Dijkstra algorithm; Auditory prompt: Provide auditory prompts for the driver through the in-vehicle audio system. When the vehicle is below a preset distance from a road section with heavy traffic flow, corresponding voice prompts will be issued; when in a severely congested road section or encountering a sudden traffic accident road section, the frequency of the voice prompts will increase by 20 - 50%; the volume and intonation of the voice prompts will be adjusted according to the severity of the traffic flow to attract the driver's attention; Tactile prompt: Through the tactile feedback seat or steering wheel equipped in the vehicle, these tactile feedback devices play a role in special traffic situations. When the vehicle is about to enter a severely congested road section, the seat will vibrate to remind the driver of the change in road conditions from the side. This non-visual and non-auditory prompt method adds an additional prompt dimension without disturbing the driver's normal driving operation.

8. The real-time traffic flow prompting system based on the vehicle networking according to claim 7, wherein The specific operation steps for optimizing the optimal route through the Dijkstra algorithm in the prompt module are as follows: The Dijkstra algorithm is used to ensure that the optimal route is displayed most clearly and reasonably on the map, avoiding confusion with other road lines. The Dijkstra algorithm sets as the road network graph, where is the set of nodes, is the set of edges, is the starting point, is the ending point, represents the shortest distance from the starting point to the node , represents the predecessor node of the node ; Initialize , and for other nodes ; Then repeat the following steps: Select the node with the smallest undetermined shortest path ; For the nodes adjacent to , update , where is the weight of the edge ; Until the shortest path of the ending point is determined. After finding the optimal route through this algorithm, it is highlighted on the map with different widths, colors, and line styles.

9. The real-time traffic flow prompting system based on the vehicle networking according to claim 1, characterized in that The steps executed by the response module are as follows: When the prompt module indicates that there is congestion on the upcoming road section, the response module will provide specific coping strategies for the driver according to the congestion level and the expected duration; the judgment of the congestion level is comprehensively determined by factors such as the surrounding road conditions and weather conditions, and the determined congestion levels are divided into mild congestion, moderate congestion, and severe congestion; For mild congestion, prompt the driver to maintain a normal speed and pay attention to the safe distance from the vehicle ahead; for moderate congestion, prompt the driver to reduce the speed, prepare for slow driving, and according to the surrounding road condition information, suggest whether to change lanes to obtain a smoother drive; for severe congestion, in addition to prompting to find an alternative route, when the driver is unable to change the route, provide driving skills in the congested section, including maintaining patience and avoiding frequent lane changes to reduce the occurrence of traffic accidents; When encountering special situations such as traffic accidents and road construction, provide targeted coping measures; if it is a traffic accident, inform the driver of the location and severity of the accident, remind the driver to pay attention to avoiding rescue vehicles and on-site workers, and at the same time, according to the traffic control situation, guide the driver on how to bypass the accident scene; for road construction situations, prompt the driver of the scope of the construction section, the type of construction, and the traffic control measures during the construction period to assist the driver in safely passing through the construction area; The coping strategies provided by the response module are dynamically adjusted according to the real-time changes in traffic flow and the actual operation of the driver. For example, when the driver encounters new congestion during the driving process according to the recommended route, re-evaluate and promptly provide new coping strategies for the driver to ensure that the driver can receive prompt guidance throughout the driving process.

10. The real-time traffic flow prompting system based on the vehicle networking according to claim 9, characterized in that The process of judging the congestion level in the said response module is as follows: Make a comprehensive judgment through surrounding road condition factors and weather conditions. Among them, the road condition factors include quantifying the number of switchable lanes, the average vehicle speed, and the average vehicle spacing and then performing normalization processing. Respectively, sum the number of switchable lanes and the average vehicle speed and then multiply by the average vehicle spacing to obtain the road condition evaluation value Y; The weather condition is determined by judging the current weather situation, setting corresponding values for different types of weather and the degree of severity. The weather types are divided into four types: sunny, cloudy, rainy, and snowy, and the evaluation values k of 1, 2, 3, and 4 are respectively set. For different types of weather, the degree evaluation values h of 0-1 are set for the degree of severity. When the current weather condition is determined, the weather evaluation value G is obtained through the formula G = k×h; Then, the calculated road condition evaluation value Y and weather evaluation value G are normalized and substituted into the following formula: to obtain a congestion judgment value DPZ. In the formula, are respectively the preset weight coefficients of the weather evaluation value G and the road condition evaluation value Y, is a correction factor, and its value is set between 0.82 and 1.

31. The finally obtained congestion judgment value DPZ is used as the judgment criterion for the congestion degree; Compare the obtained congestion judgment value DPZ with three preset congestion judgment value intervals. The three preset congestion judgment value intervals respectively correspond to mild congestion, moderate congestion, and severe congestion. When determining the congestion judgment value interval to which the congestion judgment value belongs, the current congestion level is determined.

Images