A media-integrated intelligent generation, production and analysis system based on meteorological fusion data

Abstract

The present invention belongs to the technical field of integrated media generation and analysis, and specifically discloses an intelligent integrated media generation, production and analysis system based on meteorological fusion data. By introducing multi-source integrated data to integrate real-time traffic operation status and meteorological monitoring information, a quantitative assessment model of driving risk degree is constructed, and an integrated media content generation mechanism based on risk level differentiation is realized, so that the generated integrated media content can accurately match the traffic control needs under different risk scenarios, improve the pertinence and practicality of information release, and realize dynamic monitoring and feedback closed loop of user behavior response by constructing a post-push control efficiency evaluation mechanism after the integrated media content for actual driving scenarios is pushed. This mechanism can not only quantitatively evaluate the actual guiding effect of the pushed content on the driver's behavior, but also provide data support for the optimization of subsequent content generation strategies and push timing, thereby continuously improving the accuracy and adaptability of traffic information services.

Description

Technical Field

[0001] The present invention belongs to the technical field of integrated media generation and analysis, and specifically discloses an integrated media intelligent generation, production and analysis system based on meteorological fusion data. Background Art

[0002] Converged media combines the strengths of traditional and new media in content production, dissemination methods, and technical means to establish a communication mechanism with unified content, multi-channel distribution, and terminal adaptation. With advances in information technology, converged media has been widely applied in news dissemination, government affairs releases, education, and culture, and has gradually extended to traffic management, supporting dynamic traffic information services and driving guidance.

[0003] In the field of transportation, integrated media has been used to assist drivers in obtaining real-time traffic information, such as providing route suggestions and risk warnings to vehicle users through pictures, text, voice, video, etc. Specifically, when a vehicle enters a construction section, an accident-prone area, an area affected by severe weather, or a congested section, the traffic management system can generate corresponding integrated media content based on real-time collected traffic data, and push it through on-board terminals, mobile devices, or roadside information systems. The purpose is to enhance the driver's ability to identify emergencies and assist them in making timely and reasonable driving decisions, thereby alleviating local traffic pressure and reducing safety risks.

[0004] However, existing integrated media applications for transportation use fixed templates to generate content, failing to fully consider the differentiated management and control needs faced by vehicle users in different driving environments. This results in a poor match between pushed content and actual scenarios, impacting guidance effectiveness. Furthermore, there is a general lack of feedback mechanisms after content delivery, making it impossible to effectively collect user behavioral response data, making it difficult to quantitatively evaluate and dynamically optimize delivery strategies. This limits the accuracy and practicality of integrated media in providing transportation information services. Summary of the Invention

[0005] In view of this, the present invention aims to propose an intelligent generation, production and analysis system for integrated media based on meteorological fusion data. By improving the content generation of existing integrated media applied in the transportation field and increasing push feedback, the problems existing in the existing technology are effectively solved.

[0006] The purpose of the present invention can be achieved through the following technical solutions: a media intelligent generation, production and analysis system based on meteorological fusion data, including: a meteorological and traffic fusion module: real-time collection of meteorological data and traffic data of different road sections of highways, and generation of gridded spatiotemporal fusion data sets according to road section units.

[0007] Risk area division module: Dynamically divides risk areas based on current data and historical trend data in the fused data set, including heavy risk areas and medium risk areas.

[0008] Converged media generation module: preset converged media content templates corresponding to heavy risk and medium risk. The heavy risk template is configured with diversion converged media elements, and the medium risk template is configured with speed limit converged media elements. Then, the converged media content template is matched according to the risk area type, and the corresponding converged media elements are extracted from the fusion data set of the risk area to fill the template and generate converged media content.

[0009] Integrated media push module: pushes matching integrated media content to vehicle users within the geographic fence range of the risk area and the vehicle location.

[0010] Push feedback adjustment module: evaluates the effectiveness of diversion or speed limit control after push, and adjusts the frequency of integrated media push accordingly.

[0011] Compared with the existing technology, the beneficial effects of the present invention are as follows: 1. The present invention introduces multi-source fusion data to integrate real-time traffic operation status and meteorological monitoring information to construct a quantitative assessment model of driving risk level, and realizes a converged media content generation mechanism based on differentiated risk levels, so that the generated converged media content can accurately match the traffic control needs under different risk scenarios, improve the pertinence and practicality of information release, thereby enhancing the driver's response ability to complex road conditions and optimizing the guidance effect.

[0012] 2. After pushing integrated media content for actual driving scenarios, the present invention realizes dynamic monitoring and feedback of user behavior responses by constructing a post-push management and control efficiency evaluation mechanism. This mechanism can not only quantitatively evaluate the actual guiding effect of the pushed content on driver behavior, but also provide data support for the optimization of subsequent content generation strategies and push timing, thereby continuously improving the accuracy and adaptability of traffic information services. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 This is a schematic diagram of the system module connection in the present invention.

[0015] Figure 2 The invention sets a time window for obtaining weather data and traffic time operation diagrams of road sections.

[0016] Figure 3 This is an operation diagram for evaluating the diversion or speed limit control efficiency after push in the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] See also Figure 1 The figure shows a system for intelligently generating, producing, and analyzing converged media based on meteorological fusion data. It includes a meteorological and traffic fusion module, a risk area delineation module, a converged media generation module, a converged media push module, and a push feedback adjustment module. The modules are interconnected and data is shared across the system, forming a closed-loop information processing and optimization process. This enables intelligent management of the entire process, from environmental perception and risk assessment to content generation, precise push, and feedback.

[0019] The meteorological and traffic fusion module collects meteorological data and traffic data of different road sections of the expressway in real time, and generates a gridded spatiotemporal fusion data set by road section unit.

[0020] It should be noted that the intelligent generation method for integrated media for traffic applications involved in this invention is primarily targeted at highway traffic management scenarios. Due to the long routes, long driving distances, and high speeds of highways, their operating environment is susceptible to weather changes and traffic fluctuations, significantly increasing driving risks. By generating and pushing adaptive integrated media content based on real-time data, it can effectively improve drivers' perception and response capabilities to dynamic road conditions, enhance the timeliness and guidance of traffic control, and possess high practical value in practical applications.

[0021] The prerequisite for implementing the above modules is to divide highways into different road segments. This is because highways are long and have complex traffic environments, making it difficult to implement global traffic control through a unified strategy. Furthermore, driving risks encountered in actual operation often exhibit distinct local characteristics, concentrating on specific sections. Therefore, the refined segmentation of highways provides the foundation for subsequent segment-based risk identification, integrated media content generation, and precise push notifications.

[0022] The specific process of road segment division is as follows: the spatial location information of traffic monitoring equipment and meteorological monitoring equipment is extracted from the highway infrastructure layout map.

[0023] As an example of the above solution, the traffic monitoring equipment is a traffic camera, and the weather monitoring equipment is a weather radar.

[0024] It is important to know that traffic monitoring equipment is usually deployed on highways to monitor the number, speed and density of vehicles on the road in real time, helping management departments understand the current traffic conditions and detect congestion or accidents in a timely manner. At the same time, meteorological monitoring equipment is also deployed to monitor weather changes along the highway in real time, including key parameters such as rainfall, wind speed, visibility, etc., to provide drivers with timely weather warning information.

[0025] The road segments between adjacent traffic monitoring devices are defined as candidate road units.

[0026] The meteorological monitoring coverage status of each candidate road unit is analyzed. If the current candidate road unit is equipped with meteorological monitoring equipment, it will be determined as an independent road segment. If no meteorological monitoring equipment is installed, the unit will be extended and merged to the adjacent candidate road units, and the extended road segment will be judged to see whether it contains a meteorological monitoring equipment installation point.

[0027] When the extended road section contains meteorological monitoring equipment, the extended road section is regarded as a final road section; otherwise, the extension is continued until the conditions are met or the preset maximum extension length is reached.

[0028] Based on the above division results, the traffic monitoring equipment and meteorological monitoring equipment corresponding to each road section are determined.

[0029] The above road segment division fully considers the spatial consistency of meteorological data collection capabilities and traffic monitoring coverage. By dividing the granularity based on traffic cameras and dynamically merging them based on the deployment of meteorological radars, it ensures that each road segment has complete meteorological and traffic data collection capabilities.

[0030] It's important to note that in the aforementioned road segment division scheme, if a candidate road unit lacks a weather radar, the algorithm expands to adjacent units until a location containing a weather radar is found. This approach not only considers the actual distribution of equipment but also maximizes the use of existing resources, avoiding inaccurate risk assessments caused by a lack of weather data.

[0031] It should be noted that since meteorological monitoring equipment is typically not evenly spaced on highways, some candidate road units and their extensions may still not be covered by meteorological monitoring points. Without limiting the extension length, the road segment division may be too large, defeating the purpose of localized, refined management and control. Therefore, this invention sets a maximum extension length threshold to ensure that road segment division can both reasonably match meteorological monitoring resources spatially and maintain the controllability and management effectiveness of the road segment granularity, thus avoiding problems such as blurred environmental perception, delayed response, and reduced information adaptability caused by overly long road segments.

[0032] It is further important to explain that if a road segment, after extending to the preset maximum length, still does not include a meteorological monitoring point, meteorological data for that road segment can be extrapolated and interpolated using data from adjacent areas to fill the information gap. Specifically, using existing meteorological monitoring data from adjacent road segments, a spatial interpolation algorithm is used to generate estimated meteorological parameters for that road segment.

[0033] Among them, spatial interpolation is a mature technology in the existing technology and will not be described in detail here.

[0034] See also Figure 2 As shown, after the road segment division is completed, the specific content of the meteorological traffic fusion module is as follows: within the set time window, the traffic monitoring equipment of each road segment collects vehicle driving images at fixed time intervals to form a continuous image frame sequence.

[0035] It's important to note that the reason for setting the time window mentioned above is that data from a single point in time can only reflect traffic conditions at a specific moment. This instantaneous data lacks representation of the overall traffic state and can easily lead to misjudgments. Furthermore, road traffic is random and volatile. Data from a single point in time can be affected by accidental events, resulting in significant noise and bias, making it difficult to accurately reflect the actual operating status of a road section. To ensure the statistical stability of data analysis results, it is necessary to collect a sufficient amount of sample data within a time window. This smooths out short-term fluctuations, reveals a more stable traffic state, and provides a reliable basis for subsequent risk assessment and decision support.

[0036] In further implementations of the above solution, the time window setting can be dynamically adjusted based on the time dimension. For example, during peak traffic hours, due to high traffic volume and frequent changes in operating status, the time window can be set to 5 minutes to improve the timeliness of data collection and analysis. During off-peak hours, when traffic flow is relatively stable and the system's requirements for real-time response are lower, the time window can be extended to 10 minutes to balance data stability and system processing efficiency.

[0037] The number of vehicles is counted based on each frame of the collected vehicle driving image, and compared with the length of the corresponding road segment to obtain the instantaneous traffic flow density corresponding to each frame of the image.

[0038] The average traffic density of the instantaneous traffic density of the continuous image frame sequence is selected as the traffic density of the corresponding time window.

[0039] The geometric dimensions of each individual vehicle, including length, width, and height, are extracted from each frame of the collected vehicle driving image and compared with the set geometric dimension limits of large vehicles and ordinary vehicles. The number of large vehicles is counted and the proportion of large vehicles is calculated.

[0040] In the specific implementation of the above operations, the geometric dimension boundary values ​​between large vehicles and ordinary vehicles can refer to the vehicle classification standards.

[0041] The average of the proportion of large vehicles in the continuous image frame sequence is selected as the proportion of large vehicles in the corresponding time window.

[0042] By locating the driving position of each individual vehicle in a sequence of continuous image frames, the displacement distance of the individual vehicle between adjacent frames is obtained, and these displacements are accumulated to obtain the vehicle's driving distance.

[0043] Calculate the average distance traveled by all vehicles in unit time to obtain the vehicle speed in the corresponding time window.

[0044] Traffic density, vehicle speed and the proportion of large vehicles are used as traffic data.

[0045] It's important to explain that traffic density, vehicle speed, and the proportion of large vehicles are used as traffic data for road segments because these indicators can comprehensively and accurately reflect the operational status and safety of road traffic. Specifically, traffic density represents the number of vehicles per unit length of road and is a core parameter for assessing road congestion and capacity. Higher traffic density means more frequent interactions between vehicles, increasing the likelihood of conflicts or collisions and posing a higher accident risk.

[0046] Vehicle speed reflects the road's efficiency and the overall dynamic characteristics of traffic flow. A significant drop in average speed is usually an early signal of congestion or abnormal events, while drastic fluctuations in speed may indicate the presence of unstable driving behavior, which in turn affects driving safety.

[0047] The proportion of large vehicles reflects the degree of impact of large and medium-sized vehicles on the overall traffic flow of a road section. Due to the characteristics of large vehicles such as large size, slow acceleration and long braking distance, the higher their proportion in the traffic flow, the more likely it is that local traffic efficiency will decline and it will pose a potential threat to the safety of surrounding small vehicles.

[0048] Visibility, precipitation intensity, and wind speed are collected synchronously by meteorological monitoring equipment on each road section, and the data at multiple consecutive time points are averaged as meteorological data.

[0049] It should be explained that the reason for taking the average of the traffic and weather data continuously collected within a set time window as the traffic and weather data for the corresponding time window is that the average value can reflect the overall traffic and weather conditions within a time period, avoiding data deviations caused by abnormally high or low values ​​at individual moments, helping to filter out short-term fluctuations and making the data analysis results more stable and reliable. However, relying solely on the average value may not fully and accurately depict the true variation characteristics of the data. In another exemplary implementation, a differential fluctuation analysis mechanism can be introduced to monitor the data variation amplitude of adjacent time points and identify and select relatively stable time period data as representative values.

[0050] The meteorological data and traffic data are aligned according to the timestamps of the time window to eliminate the collection time difference.

[0051] The processed data are superimposed on the electronic map of the highway to generate a gridded spatiotemporal fusion dataset based on road section units.

[0052] It should be noted that highways have the characteristics of long routes, complex structures, and significant regional differences. By combining the time-aligned meteorological data and traffic data of each road section with electronic maps, the abstract data can be matched one-to-one with the specific spatial location, ensuring that the meteorological and traffic conditions of each road section can be accurately identified and independently analyzed, thereby realizing refined management based on road section units.

[0053] The risk area division module dynamically divides risk areas based on current data and historical trend data in the fused data set, including heavy risk areas and medium risk areas.

[0054] Preferably, the risk area division module is implemented as follows: the meteorological risk level is defined as the result obtained by normalizing the deviation between each meteorological data and the corresponding safety threshold and performing weighted averaging according to preset weights.

[0055] In a specific preferred implementation, the definition of meteorological risk is based on the following steps: calculating the deviation between each meteorological data and its corresponding safety threshold.

[0056] The deviation values ​​are normalized so that all data are in the same dimension for easy comparison and weighting.

[0057] Assign preset weights to various meteorological data based on their importance to driving safety.

[0058] The normalized deviation values ​​are weighted averaged according to the preset weights to obtain the final meteorological risk value.

[0059] The above definition of meteorological risk comprehensively considers the impact of multiple key meteorological factors, avoiding the risk assessment bias that can result from relying solely on a single indicator, thereby improving the comprehensiveness and accuracy of risk identification. Furthermore, by introducing a weighting mechanism that assigns different weights to different meteorological factors based on their actual impact on traffic safety, the risk calculation results more accurately reflect the danger level of the actual driving environment.

[0060] For example, the safety threshold in the above operation can be determined according to relevant standards and specifications issued by national or local traffic management departments.

[0061] The weighting of each meteorological data item can be determined based on historical data analysis. For example, the weighting of each meteorological data item can be determined by calculating the percentage of traffic accidents caused by meteorological factors under various weather conditions. This method can reflect the actual impact of different meteorological factors on traffic safety, making the calculation of meteorological risk more objective and practical.

[0062] Traffic risk level refers to the above definition.

[0063] The meteorological and traffic data of each road segment in the current time window are extracted from the gridded spatiotemporal fusion dataset, and compared with their respective safety thresholds to obtain the meteorological risk and traffic risk of each road segment in the time window according to the above-mentioned definition method.

[0064] The current time window is extended forward by several historical time windows to form a continuous time series as the historical observation window.

[0065] As an example, the number of historical time windows may be three.

[0066] The risk evolution curve is drawn for the meteorological risk and traffic risk of each road section in the current time window corresponding to the historical observation window, and the overall slope of the risk evolution curve is used as the meteorological risk trend and traffic risk trend.

[0067] The risk evolution curve drawn above is drawn with the time window as the horizontal axis and the meteorological risk level and traffic risk level as the vertical axis.

[0068] It should be noted that the risk evolution curve reflects the change in risk value over time, and its local slope may fluctuate significantly at different time points. To accurately depict the overall trend, a representative overall slope indicator must be extracted. To this end, the original risk evolution curve is usually linearly fitted or trend-smoothed, and the slope of the fitted line is used as the risk trend.

[0069] It should be noted that the overall slope of the risk evolution curve has a clear trend indicative significance: its sign reflects the direction of change in risk during the observation period. When the overall slope is positive, it indicates that the risk is on an upward trend; when the overall slope is close to zero, it indicates that the risk level is in a maintained state; and when the overall slope is negative, it indicates that the risk is gradually decreasing.

[0070] The meteorological risk and traffic risk of each road section in the current time window are fused and calculated to obtain the comprehensive risk.

[0071] The aforementioned meteorological risk and traffic risk are integrated and analyzed to produce a comprehensive risk index, which represents the overall driving risk level under the current road conditions. For example, this integration process can be implemented using a weighted average approach, which assigns weights to meteorological and traffic factors regarding driving risk. Considering that meteorological conditions often play a secondary role in traffic safety, while traffic flow conditions are the primary factor in determining road driving risk, in this example, the meteorological risk is weighted at 0.4, and the traffic risk is weighted at 0.6.

[0072] Risk areas are divided using multi-dimensional decision-making rules based on the comprehensive risk level and the corresponding meteorological risk trends and traffic risk trends: if the comprehensive risk level is greater than the warning value and at least one risk trend is maintaining or increasing, the road section is divided into a high-risk area.

[0073] If the comprehensive risk level is greater than the warning value, but all risk trends are decreasing, the road section will be classified as a medium-risk area.

[0074] This risk classification of road sections breaks through the traditional static risk assessment method and introduces a risk evolution trend analysis mechanism, allowing the system to not only identify the current risk level but also predict future development trends. This dual judgment logic of trend + current value can effectively improve the scientific nature of risk identification, especially in scenarios where traffic conditions change rapidly.

[0075] It should be noted that the above risk area division mechanism is only triggered when the comprehensive risk exceeds the set warning value. For situations where the comprehensive risk is lower than the warning value:

[0076] When the risk trend is downward, it indicates that the current operating environment is safe and controllable and does not need to be included in risk zone management.

[0077] When the risk trend is maintaining or rising, although the current comprehensive risk level has not yet reached the warning level, since the risk assessment is based on a dynamic calculation method of the time window, there is a trend that the risk continues to accumulate and may exceed the warning threshold in the subsequent time window.

[0078] Therefore, although it is not immediately classified as a risk area in this situation, the system will continue to monitor its evolution. Once the risk trend further intensifies in the next time window, causing the comprehensive risk level to approach or exceed the warning value, the system will promptly identify it within the time window and classify it as a medium-risk area or a severe-risk area, thereby realizing dynamic updates and early warnings of risk areas.

[0079] The integrated media generation module is used to preset integrated media content templates corresponding to heavy risks and medium risks, where the heavy risk template is configured with diversion integrated media elements, and the medium risk template is configured with speed limit integrated media elements, and then the integrated media content template is matched according to the risk area type, and the corresponding integrated media elements are extracted from the fusion data set of the risk area to fill the template and generate integrated media content.

[0080] It's important to note that within the pre-set converged media content templates for high- and medium-risk traffic, the high-risk template is configured with a diversion converged media element. This is because high-risk areas typically indicate a high level of safety hazards on the road. In such cases, the most effective response is to divert vehicles away from high-risk areas, reducing the likelihood of accidents and alleviating local traffic pressure. Therefore, configuring the high-risk template with a diversion converged media element can effectively guide drivers to take evasive measures in advance, reducing the risk of accidents.

[0081] The deployment of speed limit-related media elements in medium-risk areas is based on the assumption that, while certain driving risks exist in these areas, the overall traffic situation remains within controllable limits. In this scenario, the primary control objective is to mitigate the further development of potential risks by guiding vehicles to reduce speeds and ensure safe passage under current environmental conditions. Furthermore, implementing the same diversion measures in medium-risk areas as in high-risk areas could place additional pressure on the surrounding road network, particularly increasing the burden on alternative routes near high-risk areas, thereby impacting the overall efficiency and safety of the road network.

[0082] The diversion integrated media element includes real-time traffic data and meteorological data on the diversion point location and diversion path, and the speed limit integrated media element displays the speed limit value based on the real-time comprehensive risk level.

[0083] Preferably, the corresponding integrated media elements are extracted from the fusion data set of the risk area to fill the template and generate integrated media content as follows: the corresponding integrated media content template is loaded according to the risk area divided by each road segment in the current time window, and the placeholder position of the integrated media element to be injected is located from the integrated media template.

[0084] For road sections classified as heavy risk areas, the nearest entrance and exit in the driving direction is searched in the electronic map of the highway with the area as the center as the diversion point.

[0085] It's important to explain that, due to the one-way, fully enclosed nature of highways, vehicles cannot turn around or cross the road at will. Route changes can only be achieved through designated entrances and exits. Therefore, to ensure the practical operability and effectiveness of diversion strategies, the system only considers exits and exits downstream of the direction of travel as diversion points. This design aligns with the operational characteristics of highway traffic flow, effectively guiding vehicles away from high-risk sections in a legal and safe manner, and improving the practicality and implementation of traffic management measures.

[0086] The diversion route is planned based on the current road section and the location of the diversion point, and the traffic monitoring equipment and meteorological monitoring equipment deployed along the diversion route are activated to collect traffic data and meteorological data of the relevant road sections in real time.

[0087] In the above implementation, the diversion path planning adopts a path planning algorithm to calculate the travel path from the current road section to the diversion point. The path planning process comprehensively considers the real-time traffic status to ensure that the generated diversion path has high travel efficiency and safety.

[0088] It should be noted that the path planning algorithm is an existing mature technology in the field of intelligent transportation. Therefore, the present invention does not elaborate on the specific implementation details of the path planning.

[0089] For road sections classified as medium-risk areas, the preset mapping rules are called based on the comprehensive risk level of the road section to dynamically generate speed limit recommendations that adapt to the current risk level.

[0090] It should be added that the prerequisite for implementing the above solution is to pre-build a mapping rule between the comprehensive risk level and the speed limit value. For example, the mapping rule can be constructed in the following way:

[0091] Collect historical highway traffic data and corresponding meteorological data, clean the data and time-align it to ensure data quality and consistency.

[0092] Based on the definitions of traffic risk, meteorological risk, and comprehensive risk, the comprehensive risk of historical data is calculated to obtain comprehensive risk labels under different scenarios.

[0093] Statistics are collected on the actual driving speed distribution of vehicles under each historical comprehensive risk label, and combined with whether traffic accidents, congestion and other safety incidents occur, to identify the reasonable speed range that can still ensure driving safety under a specific risk level.

[0094] Cluster analysis is used to extract the safe speeds corresponding to different comprehensive risk intervals and to construct a mapping rule between comprehensive risk and speed limit.

[0095] Embed the refined converged media elements into the corresponding placeholder positions in the converged media template to generate complete converged media content.

[0096] It should be pointed out that after the refined converged media elements are embedded into the corresponding placeholder positions in the converged media template, content rendering and format packaging operations are also performed to generate a complete converged media content instance.

[0097] For example, the content rendering performed for the diversion integrated media element extracted from the high-risk area can be a dynamic diversion route animation, and the content rendering performed for the speed limit integrated media element extracted from the medium-risk area can be a dynamic speed limit icon.

[0098] The present invention realizes the automatic generation of integrated media content for different risk scenarios by constructing an intelligent linkage mechanism between risk areas, content templates and dynamic data. The system can not only quickly match content templates according to risk assessment results, but also extract key elements from the integrated data set for dynamic filling, thereby improving the intelligence level of traffic warning information release and user perception effect.

[0099] The integrated media push module is used to push matching integrated media content to vehicle users within the geo-fence range according to the geo-fence range of the risk area and the vehicle location.

[0100] The content of the above module is implemented as follows: the boundaries of the risk area are extracted from the electronic map of the highway as the geo-fence range.

[0101] Obtain the real-time geographic location coordinates of the vehicle through the mobile terminal.

[0102] The geographic location coordinates are compared with the geographic fence range to identify the vehicle user currently located within the geo-fence range of the risk area.

[0103] For the identified target vehicle users, integrated media content matching the risk area is pushed to their mobile terminals according to the initially set frequency.

[0104] In the above example, the initial frequency is push every 5 minutes.

[0105] What you need to know is that the on-board terminals currently equipped in vehicles and the mobile terminals held by users are all integrated with positioning modules that can collect the vehicle's geographic location information in real time. This location data can be uploaded to the traffic management system through the wireless communication network to achieve dynamic perception of the vehicle's operating status. Through this mechanism, the traffic management system can accurately grasp the spatial distribution and driving trajectory of vehicles in the road network, and combine it with geographic fencing technology to identify vehicle users in specific risk areas, and accordingly push to them integrated media content that matches the current road environment.

[0106] The push feedback adjustment module is used to evaluate the diversion or speed limit control efficiency after the push, and adjust the frequency of integrated media push accordingly.

[0107] The above modules are preferably Figure 3 As shown, the effectiveness of the diversion or speed limit control after the push is evaluated by referring to the following process: the driving trajectory of vehicle users in the high-risk area is tracked and compared with the recommended diversion route to determine whether the vehicle users follow the diversion path. Based on the statistical results, the proportion of vehicles that choose the recommended diversion path is calculated as the control effectiveness.

[0108] In specific implementation: For vehicle users in high-risk areas, the driving trajectory can be tracked by using the positioning module of the vehicle terminal or mobile device to obtain the vehicle's location information in real time to form a driving trajectory.

[0109] The driving speed of vehicle users in medium-risk areas is monitored and compared with the pushed dynamic speed limit value to determine whether the vehicle complies with the speed limit. The proportion of vehicles that comply with the speed limit is counted as the management and control effectiveness.

[0110] The above module further preferably adjusts the frequency of integrated media push as follows: within the set period after the push, the diversion or speed limit control efficiency is compared with the configured effective threshold. If the diversion or speed limit control efficiency does not reach the effective threshold, the push frequency is increased, otherwise the initial frequency is maintained.

[0111] Exemplarily, the effective threshold of control effectiveness is 0.5.

[0112] Specifically, the push frequency can be increased by adjusting the ratio of the initial frequency, exemplarily pushing once every 2.5 minutes.

[0113] It's important to emphasize that the duration of the set time period after push notifications is typically dynamically linked to the actual duration of the risk zone. Since the risk zone demarcation is based on periodic analysis of real-time traffic and weather data within a set time window, the length of the set time period should be less than or equal to the duration of the time window to ensure effective information intervention and driving behavior guidance for target users within the current risk status.

[0114] The core purpose of these operations is to continuously evaluate the effectiveness of integrated media push management and control while risk areas remain unchanged, and dynamically adjust push strategies based on the evaluation results, thereby improving the effectiveness of information guidance. If the status of a risk area changes, the system will immediately terminate the integrated media push performance evaluation and push frequency adjustment for that section of road to avoid sending redundant information to users who have left the risk environment, thereby ensuring the rationality of system resource allocation and the timeliness and relevance of information push.

[0115] The above embodiments may be implemented in whole or in part through software, hardware, firmware or any other combination. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0116] Those skilled in the art will appreciate that the modules of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0117] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0118] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A media intelligent generation, production and analysis system based on meteorological fusion data, characterized by ,include: Meteorological and traffic fusion module: collects meteorological and traffic data from different sections of highways in real time, and generates gridded spatiotemporal fusion datasets based on the road sections; Risk area division module: Dynamically divides risk areas based on current data and historical trend data in the fused data set, including high-risk areas and medium-risk areas; Converged media generation module: preset converged media content templates corresponding to heavy and medium risks. The heavy risk template is configured with diversion converged media elements, while the medium risk template is configured with speed limit converged media elements. Then, the converged media content template is matched according to the risk area type, and the corresponding converged media elements are extracted from the fusion data set of the risk area to fill the template and generate converged media content; Integrated media push module: pushes matching integrated media content to vehicle users within the geo-fence range based on the geo-fence range and vehicle location of the risk area; Push Feedback Adjustment Module: Evaluates the effectiveness of traffic diversion or speed limiting after push notifications, and adjusts the frequency of integrated media push notifications accordingly; The risk area division module is implemented as follows: The meteorological risk is defined as the result of normalizing the deviation between each meteorological data and the corresponding safety threshold and averaging it according to the preset weights. The traffic risk is defined in the same way. Extracting weather and traffic data for each road segment in the current time window from the gridded spatiotemporal fusion dataset, comparing them with their respective safety thresholds, and calculating the weather risk and traffic risk of each road segment in the time window according to the above-mentioned definition method; Extend the current time window forward by several historical time windows to form a continuous time series as the historical observation window; The risk evolution curve is drawn for the meteorological risk and traffic risk of each road segment in the current time window corresponding to the historical observation window, and the overall slope of the risk evolution curve is used as the meteorological risk trend and traffic risk trend; The meteorological risk and traffic risk of each road section in the current time window are integrated and calculated to obtain the comprehensive risk. Risk areas are divided using multi-dimensional decision-making rules based on the comprehensive risk level and the corresponding meteorological risk trends and traffic risk trends: If the comprehensive risk level is greater than the warning value and at least one risk trend is maintaining or increasing, the road section will be classified as a severe risk area; If the comprehensive risk level is greater than the warning value, but all risk trends are decreasing, the road section will be classified as a medium-risk area.

2. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 1, characterized in that: The different road sections of the expressway are divided as follows: Extract the spatial location information of traffic monitoring equipment and meteorological monitoring equipment from the highway infrastructure layout map; The road segments between adjacent traffic monitoring devices are defined as candidate road units; Analyze the meteorological monitoring coverage status of each candidate road unit. If a meteorological monitoring device is deployed within the current candidate road unit, it will be determined as an independent road segment. If no meteorological monitoring device is deployed, the unit will be extended and merged to the adjacent candidate road units, and the extended road segment will be further determined to determine whether it contains a meteorological monitoring device deployment point. When the extended road section contains meteorological monitoring equipment, the extended road section will be regarded as a final road section, otherwise it will continue to be extended until the conditions are met or the preset maximum extension length is reached; Based on the above division results, the traffic monitoring equipment and meteorological monitoring equipment corresponding to each road section are determined.

3. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 2, characterized in that: The meteorological data and traffic data are collected as follows: The traffic monitoring equipment on each road section collects vehicle driving images at fixed time intervals within a set time window to form a continuous image frame sequence; The number of vehicles is counted based on each frame of the collected vehicle driving image, and the instantaneous traffic density corresponding to each frame of the image is obtained by comparing it with the length of the corresponding road segment; The average traffic density of the instantaneous traffic density of the continuous image frame sequence is selected as the traffic density of the corresponding time window; Extract the geometric dimensions of each individual vehicle from each frame of the captured vehicle driving image, and compare them with the set geometric dimension limits of large vehicles and ordinary vehicles. Count the number of large vehicles and calculate the proportion of large vehicles. The average of the proportion of large vehicles in the continuous image frame sequence is selected as the proportion of large vehicles in the corresponding time window; By locating the driving position of each individual vehicle in a sequence of continuous image frames, the displacement distance of the individual vehicle between adjacent frames is obtained, and these displacements are accumulated to obtain the vehicle's driving distance; Calculate the average distance traveled by all vehicles in unit time to obtain the vehicle speed in the corresponding time window; The traffic density, vehicle speed and proportion of large vehicles obtained above are used as traffic data; Visibility, precipitation intensity, and wind speed are collected synchronously by meteorological monitoring equipment on each road section, and the data at multiple consecutive time points are averaged as meteorological data.

4. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 1, characterized in that: The specific steps of generating a gridded spatiotemporal fusion dataset based on road section units are as follows: Align meteorological data and traffic data according to timestamps to eliminate collection time differences; The processed data are superimposed on the electronic map of the highway to generate a gridded spatiotemporal fusion dataset based on road section units.

5. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 1, characterized in that: The diversion integrated media element includes real-time traffic data and meteorological data on the diversion point location and diversion path, and the speed limit integrated media element displays the speed limit value based on the real-time comprehensive risk level.

6. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 5, characterized in that: The method of extracting corresponding integrated media elements from the fusion data set of the risk area to fill the template and generate integrated media content is implemented as follows: Load the corresponding converged media content template based on the risk area divided by each road segment in the current time window, and locate the placeholder position of the converged media element to be injected from the converged media template; For road sections classified as high-risk areas, the nearest entrance and exit in the direction of travel is searched on the highway electronic map with the area as the center as the diversion point; Plan diversion routes based on the current road sections and diversion point locations, and activate traffic monitoring equipment and meteorological monitoring equipment deployed along the diversion routes to collect real-time traffic and meteorological data on the relevant road sections; For road sections classified as medium-risk areas, a preset mapping rule is called based on the comprehensive risk level of the road section to dynamically generate a speed limit recommendation value that adapts to the current risk level; Embed the refined converged media elements into the corresponding placeholder positions in the converged media template to generate complete converged media content.

7. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 1, characterized in that: The integrated media push module is implemented as follows: Extract the boundaries of the risk area from the electronic map of the highway as the geo-fence range; Obtain the real-time geographic location coordinates of the vehicle through the mobile terminal; Comparing the geographic location coordinates with the geo-fence range to identify vehicle users currently located within the geo-fence range of the risk area; For the identified target vehicle users, integrated media content matching the risk area is pushed to their mobile terminals according to the initially set frequency.

8. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 6, characterized in that: The effectiveness of traffic diversion or speed limit control after evaluation and push is as follows: Track the driving trajectories of vehicles in high-risk areas and compare them with recommended diversion routes to determine whether the vehicle users followed the diversion paths. Based on the statistical results, calculate the proportion of vehicles that chose the recommended diversion paths as the control effectiveness; The driving speed of vehicle users in medium-risk areas is monitored and compared with the pushed dynamic speed limit value to determine whether the vehicle complies with the speed limit. The proportion of vehicles that comply with the speed limit is counted as the management and control effectiveness.

9. The intelligent generation, production and analysis system for integrated media based on meteorological fusion data according to claim 7, characterized in that: The adjustment of the frequency of integrated media push is implemented as follows: During the set period after push notification, the traffic diversion or speed limit control efficiency is compared with the configured effective threshold. If the traffic diversion or speed limit control efficiency does not reach the effective threshold, the push frequency is increased; otherwise, the initial frequency is maintained.

Images