A traffic emergency big data analysis system and data fusion method

Abstract

This invention discloses a traffic emergency big data analysis system and data fusion method, belonging to the field of data fusion technology. The invention integrates real-time data of target electric vehicles, meteorological monitoring data, and traditional traffic detection data, achieving a comprehensive improvement in traffic emergency management capabilities. Firstly, it breaks through the spatial limitations of traditional fixed detection equipment, utilizing the high-frequency mobility of electric vehicles to achieve blind-spot-free coverage of the urban road network. Particularly for non-motorized vehicle lanes and side streets that are difficult to cover using traditional monitoring methods, it significantly improves the precision of traffic situational awareness. At the data processing level, it effectively solves the problem of heterogeneous data fusion, resulting in a qualitative leap in the real-time performance and accuracy of traffic event detection. Based on an improved behavioral analysis model and congestion assessment algorithm, it can accurately identify traffic anomalies under severe weather conditions such as rainfall.

Description

Technical Field

[0001] This invention relates to the field of data fusion technology, specifically to a traffic emergency big data analysis system and data fusion method. Background Technology

[0002] With the acceleration of urbanization and the continuous growth of transportation demand, urban traffic congestion has become increasingly serious. Especially under severe weather conditions, the risk of traffic congestion and accidents increases significantly. Traditional traffic emergency management methods mainly rely on fixed traffic detection equipment, and there is relatively little monitoring of non-motorized vehicle lanes. Therefore, it is necessary to conduct emergency data analysis on non-motorized vehicle lanes.

[0003] Existing technology, such as the invention patent application with publication number CN120032512A, discloses an intelligent traffic condition analysis method for situations lacking uncertain modes. This method includes: performing traffic data analysis using accurately represented modal fusion traffic data to improve the accuracy of the traffic condition analysis results; furthermore, conducting traffic emergency response analysis based on the traffic condition analysis results, determining traffic emergency response recommendations, and sending these recommendations to the traffic management terminal.

[0004] Existing technology, such as the invention patent application with publication number CN118606775A, discloses an emergency event identification method and system based on multi-source data fusion. The method includes: acquiring a multi-source data training sample set of the target emergency event; obtaining feature information; obtaining target fused data; and inputting the fused data into a constructed emergency event identification model to obtain the emergency event identification result. This invention can effectively improve the accuracy and timeliness of emergency event identification.

[0005] As can be seen from the above scheme, the target traffic emergency data fusion methods include:

[0006] (1) The deployment of the main fixed detection equipment is concentrated on the main roads and key intersections, with limited coverage of urban branch roads, non-motorized lanes and other areas, forming monitoring blind spots. In particular, in non-motorized lanes, there is a lack of effective real-time data collection methods, making it difficult for traffic management departments to grasp the operating status of the entire road network in a timely manner.

[0007] (2) Traditional methods rely on manual judgment and periodic data reporting from fixed detection equipment, and it usually takes several minutes or even longer from the occurrence of an event to the response.

[0008] (3) Existing systems are mainly based on structured data (such as vehicle flow and speed) and lack fusion analysis of unstructured data (such as electric vehicle behavior and trajectory dynamics).

[0009] (4) Professions that transport goods and require the platform to plan delivery routes in real time frequently adjust their routes in rainy weather to avoid congestion or dangerous areas, but this dynamic route data has not been effectively integrated into traffic management. Summary of the Invention

[0010] The purpose of this invention is to provide a traffic emergency big data analysis system and data fusion method, which solves the problems existing in the background technology.

[0011] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0012] A traffic emergency data fusion method includes:

[0013] Step 1. During rainfall, obtain the feature values ​​of each lane planning and each traffic data of each target electric vehicle in the city within the target time period, and obtain the rainfall of each non-motorized vehicle lane in the city at each monitoring time point within the target time period.

[0014] Step 2. Conduct behavioral analysis on each target electric vehicle and analyze the feedback congestion level of electric vehicle data in each non-motorized vehicle lane of the city.

[0015] Step 3. Based on the feedback congestion level of electric vehicles in each non-motorized vehicle lane of the city, and based on the rainfall in each non-motorized vehicle lane of the city at each monitoring time point, assess the actual congestion level of each non-motorized vehicle lane of the city, and analyze the predicted congestion areas of each non-motorized vehicle lane of the city.

[0016] Step 4. Send the actual congestion level of each non-motorized vehicle lane in the city and the estimated congestion areas to the traffic terminal and display them visually.

[0017] Based on the same inventive concept, a traffic emergency big data analysis system that implements the aforementioned traffic emergency data fusion method is also proposed, comprising:

[0018] The road information acquisition module is used to acquire the characteristic values ​​of each lane planning and each traffic data of each target electric vehicle in the city during the target time period, and to acquire the rainfall of each non-motorized vehicle lane in the city at each monitoring time point during the target time period.

[0019] The electric vehicle behavior analysis module is used to analyze the behavior of each target electric vehicle and analyze the feedback congestion level of electric vehicle data in each non-motorized vehicle lane of the city.

[0020] The data fusion and evaluation module is used to provide feedback on congestion levels based on electric vehicle data for each non-motorized vehicle lane in the city, and to assess the actual congestion level of each non-motorized vehicle lane in the city based on the rainfall at each monitoring time point, and to analyze the predicted congestion areas of each non-motorized vehicle lane in the city.

[0021] The visualization processing module is used to send the actual congestion level of each non-motorized vehicle lane in the city and the estimated congestion areas to the traffic terminal for visualization display.

[0022] The beneficial effects of this invention are as follows:

[0023] This invention integrates real-time data from target electric vehicles, meteorological monitoring data, and traditional traffic detection data, achieving a comprehensive improvement in traffic emergency management capabilities. Firstly, it overcomes the spatial limitations of traditional fixed detection equipment, utilizing the high-frequency mobility of electric vehicles to achieve blind-spot-free coverage of urban road networks. Particularly for non-motorized vehicle lanes and side streets that are difficult to cover using traditional monitoring methods, it significantly improves the precision of traffic situational awareness. At the data processing level, it effectively solves the problem of heterogeneous data fusion, resulting in a qualitative leap in the real-time performance and accuracy of traffic incident detection. Based on improved behavioral analysis models and congestion assessment algorithms, it can accurately identify traffic anomalies under severe weather conditions such as rainfall. Furthermore, through standardized data interfaces and modular design, it ensures the system's scalability and cross-platform compatibility. Attached Figure Description

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 paying any creative work.

[0025] Figure 1 Schematic diagram of the method of the present invention.

[0026] Figure 2 This is a schematic diagram of the system modules of the present invention. Detailed Implementation

[0027] 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.

[0028] Reference Figure 1As shown, the present invention provides a traffic emergency data fusion method, including:

[0029] Step 1. During rainfall, obtain the feature values ​​of each lane planning and traffic data of each target electric vehicle in the city within the target time period, and obtain the rainfall of each non-motorized vehicle lane in the city at each monitoring time point within the target time period.

[0030] In a specific embodiment of the present invention, the method for obtaining the characteristic values ​​of each lane plan and each traffic data of each target electric vehicle in the city within the target time period, and obtaining the rainfall of each non-motorized vehicle lane in the city at each monitoring time point within the target time period, is as follows: obtain the lane plan of each target electric vehicle in the city within the target time period from the data monitoring platform.

[0031] It should be noted that the target electric vehicle described in this invention is an electric vehicle used by professions that transport goods and require the platform to plan the delivery route in real time, including but not limited to express delivery, food service delivery, and other professions.

[0032] It should also be noted that the lane planning for each target electric vehicle is planned by the data monitoring platform. Each target electric vehicle has an initial lane plan. If it deviates from the route of the initial lane plan, the second lane plan is updated. If it deviates from the route of the second lane plan, the third lane plan is updated, and so on, thereby obtaining the lane plans for each target electric vehicle in the city within the target time period.

[0033] The stable position of each target electric vehicle is determined, and each sensor is installed at the stable position of each target electric vehicle. The characteristic values ​​of each traffic data of each target electric vehicle in the city during the target time period are obtained through each sensor. The traffic data includes: the speed value at each monitoring time point and the GPS location.

[0034] In one specific embodiment, the method for determining the stable position of each target electric vehicle is as follows: the existing stable position analysis technology for electric vehicles is relatively mature, and the stable position of each target electric vehicle can be determined by using the existing stable position analysis technology for electric vehicles.

[0035] It should be noted that by installing sensors in a standardized manner, the reliability of the acquired data is ensured, preventing significant errors in the acquired data due to differences in the target electric vehicles.

[0036] Rainfall data for each non-motorized vehicle lane in the city was obtained from the meteorological platform at each monitoring time point.

[0037] Step 2. Conduct behavioral analysis on each target electric vehicle and analyze the feedback congestion level of electric vehicle data in each non-motorized vehicle lane of the city.

[0038] In a specific embodiment of the present invention, the behavior analysis of each target electric vehicle and the analysis of the feedback congestion of electric vehicle data in each non-motorized vehicle lane of the city are specifically performed as follows: based on the location of each target electric vehicle in the city on the non-motorized vehicle lane at each monitoring time point during the target time period, the speed reduction congestion assessment coefficient of each target electric vehicle in the city on each non-motorized vehicle lane during the target time period is analyzed, and the feedback congestion of electric vehicle data in each non-motorized vehicle lane of the city is calculated.

[0039] In one specific embodiment, the method for calculating the feedback congestion degree of electric vehicles in each non-motorized vehicle lane of the city is as follows: based on the speed reduction congestion assessment coefficient of each target electric vehicle in each non-motorized vehicle lane of the city during the target time period, the speed reduction congestion assessment coefficient of each target electric vehicle in each non-motorized vehicle lane of the city during the target time period is mapped to obtain the speed reduction congestion assessment coefficient of each target electric vehicle in each non-motorized vehicle lane of the city during the target time period. , where x represents the number of each target electric vehicle. y is a positive integer greater than 2, and n represents the number of each non-motorized vehicle lane. Let m be a positive integer greater than 2. Calculate the feedback congestion level of electric vehicles in each non-motorized vehicle lane within the city. .

[0040] In a specific embodiment of the present invention, the analysis of the speed reduction and congestion assessment coefficient of each target electric vehicle in the city in each non-motorized vehicle lane within the target time period is specifically performed as follows: based on the position of each target electric vehicle in the city in the non-motorized vehicle lane at each monitoring time point within the target time period, the monitoring time points of each target electric vehicle in the city in each non-motorized vehicle lane within the target time period are mapped, and based on the speed values ​​of each target electric vehicle in the city in the city at each monitoring time point within the target time period, the speed values ​​of each target electric vehicle in the city in each non-motorized vehicle lane at each monitoring time point within the target time period are extracted.

[0041] The system retrieves the rate values ​​and rainfall data for each target electric vehicle in each city at each historical monitoring time point from the local database for each rainfall interval, and calculates the appropriate rate values ​​for each target electric vehicle in the city at each monitoring time point based on this data.

[0042] It should be noted that the local database is used to store the following data: rainfall intervals, the speed values ​​and rainfall of each target electric vehicle in the city at each historical monitoring time point, the non-motorized vehicle lane types and road widths of each non-motorized vehicle lane in the city, the actual congestion levels corresponding to each comprehensive congestion assessment coefficient interval, the appropriate floating traffic flow of each non-motorized vehicle lane type in each road width interval and each rainfall interval, each segment area of ​​each non-motorized vehicle lane in the city, the estimated congestion coefficient threshold, and the display color corresponding to each actual congestion level.

[0043] Based on the correspondence between the location and each monitoring time point, and based on the speed values ​​of each target electric vehicle in each non-motorized vehicle lane in the city at each monitoring time point within the target time period, the speed values ​​of each target electric vehicle at each location in each non-motorized vehicle lane in the city within the target time period are mapped. Based on the appropriate speed values ​​of each target electric vehicle in the city at each monitoring time point, the speed reduction congestion assessment coefficient of each target electric vehicle in the city in each non-motorized vehicle lane within the target time period is calculated.

[0044] It should be noted that the correspondence between the location and each monitoring time point is that the location will correspond to a certain position on the non-motorized vehicle lane at different monitoring time points.

[0045] In one specific embodiment, the calculation of the speed reduction congestion assessment coefficient for each target electric vehicle in each non-motorized vehicle lane within the city during the target time period is specifically calculated as follows: based on the speed values ​​of each target electric vehicle at each location in each non-motorized vehicle lane within the city. , where i represents the position number. Let j be a positive integer greater than 2. Calculate the speed fluctuation hazard coefficient of each target electric vehicle at each location in each non-motorized vehicle lane within the city. , where j represents the number of positions.

[0046] Based on the appropriate speed values ​​of each target electric vehicle in the city at each monitoring time point, and according to the correspondence between their location and each monitoring time point, the appropriate speed values ​​of each target electric vehicle at each location in each non-motorized vehicle lane of the city are mapped to be obtained. Calculate the speed reduction comparison coefficient for each target electric vehicle at each location in each non-motorized vehicle lane within the city. And calculate the speed reduction and congestion assessment coefficients for each target electric vehicle in each non-motorized vehicle lane within the city during the target time period. .

[0047] In a specific embodiment of the present invention, the method for calculating the appropriate speed value of each target electric vehicle in a city at each monitoring time point is as follows: if the rainfall of a certain non-motorized vehicle lane in a city at a certain monitoring time point is included in a certain rainfall range, then the rainfall range is taken as the target rainfall range of the non-motorized vehicle lane in the city at that monitoring time point, thereby obtaining the target rainfall range of each non-motorized vehicle lane in the city at each monitoring time point.

[0048] If the rainfall of a target electric vehicle in a city at a certain historical monitoring time point is included in the target rainfall range of a non-motorized vehicle lane at a certain monitoring time point, then that historical monitoring time point is taken as the target historical monitoring time point of that target electric vehicle in the city at that monitoring time point. This allows for the selection of the target historical monitoring time points of each target electric vehicle in the city at each monitoring time point. Based on the rate values ​​of each target electric vehicle in the city at each historical monitoring time point, the rate values ​​of each target electric vehicle in the city at each historical monitoring time point are mapped to calculate the appropriate rate values ​​of each target electric vehicle in the city at each monitoring time point.

[0049] In one specific embodiment, the method for calculating the appropriate speed value of each target electric vehicle in the city at each monitoring time point is as follows: based on the speed values ​​of each target electric vehicle in the city at each monitoring time point and each historical monitoring time point, the values ​​are accumulated and then averaged to obtain the appropriate speed value of each target electric vehicle in the city at each monitoring time point.

[0050] Step 3. Based on the feedback congestion level of electric vehicles in each non-motorized vehicle lane of the city, and based on the rainfall in each non-motorized vehicle lane of the city at each monitoring time point, assess the actual congestion level of each non-motorized vehicle lane of the city, and analyze the predicted congestion areas of each non-motorized vehicle lane of the city.

[0051] It should be noted that the actual congestion levels are divided into four levels: Level 1, Level 2, Level 3, and Level 4. Level 1 is higher than Level 2, Level 2 is higher than Level 3, and Level 3 is higher than Level 4.

[0052] In a specific embodiment of the present invention, the method for assessing the actual congestion level of each non-motorized vehicle lane in a city is as follows: obtain the non-motorized vehicle lane type and road width of each non-motorized vehicle lane in a city from a local database, and analyze the vehicle quantity congestion coefficient of each non-motorized vehicle lane in a city accordingly.

[0053] It should be noted that there are three different types of non-motorized vehicle lanes: First, there is a dedicated non-motorized vehicle lane, in which case the non-motorized vehicle lane type is dedicated; second, there is no dedicated non-motorized vehicle lane, and the motorized vehicle lane in the direction of travel is not a single lane, in which case the rightmost motorized vehicle lane is used as a non-motorized vehicle lane, and the non-motorized vehicle lane type is occupied by motorized vehicle lanes; third, there is no dedicated non-motorized vehicle lane, and the motorized vehicle lane in the direction of travel is a single lane, in which case the non-motorized vehicle lane type is shared by motorized vehicles and electric vehicles.

[0054] It should also be noted that, regarding the road width, if the non-motorized vehicle lane is dedicated, the width of the dedicated non-motorized vehicle lane shall be used as the road width; if the non-motorized vehicle lane is occupied by a motorized vehicle lane, the width of the rightmost motorized vehicle lane shall be used as the road width; if the non-motorized vehicle lane is shared by motorized vehicles and electric vehicles, the width of the single-lane motorized vehicle lane shall be used as the road width.

[0055] Based on the feedback congestion level of electric vehicles in each non-motorized vehicle lane of the city, and combined with the vehicle quantity congestion coefficient of each non-motorized vehicle lane of the city, the comprehensive congestion assessment coefficient of each non-motorized vehicle lane of the city is calculated.

[0056] In one specific embodiment, the calculation method for the comprehensive congestion assessment coefficient of each non-motorized vehicle lane in the city is as follows: based on the feedback congestion level of electric vehicles in each non-motorized vehicle lane of the city. Combined with the congestion coefficient of the number of vehicles in each non-motorized vehicle lane in the city. Calculate the comprehensive congestion assessment coefficient for each non-motorized vehicle lane in the city. .

[0057] The actual congestion level corresponding to each comprehensive congestion assessment coefficient range is obtained from the local database. Based on the comprehensive congestion assessment coefficient of each non-motorized vehicle lane in the city, the actual congestion level of each non-motorized vehicle lane in the city is mapped to the actual congestion level.

[0058] In a specific embodiment of the present invention, the method for analyzing the vehicle congestion coefficient of each non-motorized vehicle lane in a city is as follows: based on the type of non-motorized vehicle lane in a city, the floating traffic flow of the corresponding non-motorized vehicle lane in the city is obtained according to different non-motorized vehicle lane types during the target time period, and the vehicle congestion coefficient of each non-motorized vehicle lane in the city is calculated based on the road width of each non-motorized vehicle lane in the city and the rainfall at each monitoring time point.

[0059] In one specific embodiment, the method for obtaining the floating traffic flow of the corresponding non-motorized vehicle lane in a city within a target time period according to different non-motorized vehicle lane types is as follows: if the non-motorized vehicle lane of a city is dedicated, the floating traffic flow of the corresponding non-motorized vehicle lane in the city within a target time period is obtained through the camera at the entrance of the dedicated non-motorized vehicle lane; if the non-motorized vehicle lane of a city is occupied by a motorized vehicle lane, the floating traffic flow of the corresponding non-motorized vehicle lane in the city within a target time period is obtained through the camera at the entrance of the rightmost lane of the intersection; if the non-motorized vehicle lane of a city is used by both motorized vehicles and electric vehicles, the floating traffic flow of the corresponding non-motorized vehicle lane in the city within a target time period is obtained through the camera at the entrance of a single lane of the intersection.

[0060] In one specific embodiment, the method for calculating the congestion coefficient of vehicle numbers for each non-motorized vehicle lane in a city is as follows: The appropriate floating traffic flow for each type of non-motorized vehicle lane under each road width range and each rainfall range is obtained from a local database. Based on the type of non-motorized vehicle lane in the city, and based on the road width of each non-motorized vehicle lane in the city and the rainfall at each monitoring time point, the appropriate floating traffic flow for each non-motorized vehicle lane in the city during the target time period is mapped. Based on the floating traffic flow of each non-motorized vehicle lane in the city Calculate the congestion coefficient of the number of vehicles in each non-motorized vehicle lane in the city. , where e represents the natural constant.

[0061] It should be noted that the appropriate floating traffic flow for each type of non-motorized vehicle lane under each road width range and each rainfall range is set by researchers based on actual conditions, and the following relationship must be met: the wider the road, the greater the appropriate floating traffic flow; the greater the rainfall, the smaller the appropriate floating traffic flow.

[0062] In a specific embodiment of the present invention, the method for analyzing the estimated congestion areas of each non-motorized vehicle lane in the city is as follows: based on the GPS location of each target electric vehicle in the city at each monitoring time point within the target time period, the location of each target electric vehicle in the city on the non-motorized vehicle lane at each monitoring time point within the target time period is obtained, and the actual travel route of each target electric vehicle in the city within the target time period is analyzed.

[0063] Based on the lane planning and actual travel routes of each target electric vehicle in the city during the target time period, the route change nodes of each target electric vehicle in each non-motorized vehicle lane in the city during the target time period are analyzed, and the route change nodes of each target electric vehicle in each non-motorized vehicle lane in the city during the target time period are mapped.

[0064] The system retrieves the segmented areas of each non-motorized vehicle lane in the city from the local database. If the route change node of a target electric vehicle in a certain non-motorized vehicle lane in the city is contained in a certain segmented area, the estimated congestion coefficient of that segmented area is increased by 1, and so on, to obtain the estimated congestion coefficient of each segmented area of ​​each non-motorized vehicle lane in the city.

[0065] The estimated congestion coefficient threshold is obtained from the local database. If the estimated congestion coefficient of a certain segment of a non-motorized vehicle lane in the city is greater than the estimated congestion coefficient threshold, the segment is marked as an estimated congestion area, thereby filtering the estimated congestion areas of each non-motorized vehicle lane in the city.

[0066] In a specific embodiment of the present invention, the analysis of the route change nodes of each target electric vehicle in each non-motorized vehicle lane within a city during a target time period is specifically performed as follows: The actual travel route of a target electric vehicle within a city during the target time period is compared with the corresponding first lane plan. The location of the non-motorized vehicle lane where the actual travel route of the target electric vehicle in the city is inconsistent with the first lane plan is extracted. Then, the subsequent travel route of the target electric vehicle is compared with the second lane plan, and the location of the non-motorized vehicle lane where the subsequent travel route of the target electric vehicle in the city is inconsistent with the second lane plan is extracted. This process is repeated, and the locations of the non-motorized vehicle lanes where inconsistent choices occur during the above derivation process are taken as the route change nodes of the target electric vehicle in each corresponding non-motorized vehicle lane within the city. This allows for the summarization of the route change nodes of each target electric vehicle in the city during the target time period.

[0067] It should be noted that the subsequent route is the remaining route after subtracting the route that is consistent with the first lane plan from the actual route.

[0068] Step 4. Send the actual congestion level of each non-motorized vehicle lane in the city and the estimated congestion areas to the traffic terminal and display them visually.

[0069] In one specific embodiment, the visualization is performed by: obtaining the display color corresponding to each actual congestion level from the local database, mapping the display color of each non-motorized vehicle lane in the city according to the actual congestion level of each non-motorized vehicle lane in the city, displaying it on the screen, and marking the estimated congestion areas of each non-motorized vehicle lane in the city with warning signs.

[0070] This invention integrates real-time data from target electric vehicles, meteorological monitoring data, and traditional traffic detection data, achieving a comprehensive improvement in traffic emergency management capabilities. Firstly, it overcomes the spatial limitations of traditional fixed detection equipment, utilizing the high-frequency mobility of target electric vehicles to achieve blind-spot-free coverage of urban road networks. Particularly for non-motorized vehicle lanes and side streets that are difficult to cover using traditional monitoring methods, it significantly improves the precision of traffic situational awareness. At the data processing level, it effectively solves the problem of heterogeneous data fusion, resulting in a qualitative leap in the real-time performance and accuracy of traffic event detection. Based on improved behavioral analysis models and congestion assessment algorithms, it can accurately identify traffic anomalies under severe weather conditions such as rainfall. Furthermore, through standardized data interfaces and modular design, it ensures the system's scalability and cross-platform compatibility.

[0071] Based on the same inventive concept, a traffic emergency big data analysis system that implements the aforementioned traffic emergency data fusion method is also proposed, comprising:

[0072] The system includes a road information acquisition module, an electric vehicle behavior analysis module, a data fusion and evaluation module, a visualization processing module, and a local database.

[0073] It should be noted that the road information acquisition module is connected to the electric vehicle behavior analysis module, the electric vehicle behavior analysis module is connected to the data fusion and evaluation module, the data fusion and evaluation module is connected to the visualization processing module, and the local database is connected to the electric vehicle behavior analysis module, the data fusion and evaluation module, and the visualization processing module.

[0074] The road information acquisition module is used to acquire the characteristic values ​​of each lane planning and each traffic data of each target electric vehicle in the city during the target time period, and to acquire the rainfall of each non-motorized vehicle lane in the city at each monitoring time point during the target time period.

[0075] The electric vehicle behavior analysis module is used to perform behavior analysis on each target electric vehicle and analyze the feedback congestion level of electric vehicle data in each non-motorized vehicle lane of the city.

[0076] The data fusion and evaluation module is used to provide feedback on congestion levels based on electric vehicle data for each non-motorized vehicle lane in the city, and to assess the actual congestion level of each non-motorized vehicle lane in the city based on rainfall at each monitoring time point, and to analyze each predicted congestion area of ​​each non-motorized vehicle lane in the city.

[0077] The visualization processing module is used to send the actual congestion level of each non-motorized vehicle lane in the city and each estimated congestion area to the traffic terminal and display them visually.

[0078] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A method for fusion of traffic emergency data, characterized in that, include: Step 1. During rainfall, obtain the feature values ​​of each lane planning and traffic data for each target electric vehicle in the city within the target time period, and obtain the rainfall of each non-motorized vehicle lane in the city at each monitoring time point within the target time period. The specific method for obtaining these features is as follows: Obtain lane plans for each target electric vehicle in the city within the target time period from the data monitoring platform; Determine the stable position of each target electric vehicle, install each sensor at the stable position of each target electric vehicle, and obtain the characteristic values ​​of each traffic data of each target electric vehicle in the city during the target time period through each sensor. The traffic data includes: the speed value and GPS position at each monitoring time point. Rainfall data for each non-motorized vehicle lane in the city at each monitoring time point were obtained from the meteorological platform. Step 2. Conduct behavioral analysis on each target electric vehicle and analyze the feedback congestion level of electric vehicle data in each non-motorized vehicle lane of the city. Step 3. Based on the feedback congestion level of electric vehicles in each non-motorized vehicle lane of the city, and according to the rainfall in each non-motorized vehicle lane at each monitoring time point, assess the actual congestion level of each non-motorized vehicle lane in the city, and analyze the predicted congestion areas of each non-motorized vehicle lane in the city. The specific analysis method is as follows: Based on the GPS location of each target electric vehicle in the city at each monitoring time point within the target time period, the location of each target electric vehicle in the city on the non-motorized vehicle lane at each monitoring time point within the target time period is obtained, and the actual travel route of each target electric vehicle in the city within the target time period is analyzed. Based on the lane planning and actual travel routes of each target electric vehicle in the city during the target time period, the route change nodes of each target electric vehicle in each non-motorized vehicle lane in the city during the target time period are analyzed, and the route change nodes of each target electric vehicle in each non-motorized vehicle lane in the city during the target time period are mapped. The local database retrieves the segmented areas of each non-motorized vehicle lane in the city. If the route change node of a target electric vehicle in a certain non-motorized vehicle lane in the city is contained in a certain segmented area, the estimated congestion coefficient of that segmented area is increased by 1, and so on, to obtain the estimated congestion coefficient of each segmented area of ​​each non-motorized vehicle lane in the city. The estimated congestion coefficient threshold is obtained from the local database. If the estimated congestion coefficient of a certain segment of a non-motorized vehicle lane in the city is greater than the estimated congestion coefficient threshold, the segment is marked as an estimated congestion area, thereby filtering the estimated congestion areas of each non-motorized vehicle lane in the city. Step 4. Send the actual congestion level of each non-motorized vehicle lane in the city and the estimated congestion areas to the traffic terminal and display them visually.

2. The traffic emergency data fusion method according to claim 1, characterized in that, The specific analysis method for conducting behavioral analysis on each target electric vehicle and analyzing the feedback congestion level of electric vehicles in each non-motorized vehicle lane of the city is as follows: Based on the location of each target electric vehicle in the city on the non-motorized vehicle lane at each monitoring time point within the target time period, the speed reduction and congestion assessment coefficient of each target electric vehicle in the city on each non-motorized vehicle lane within the target time period is analyzed, and the feedback congestion degree of electric vehicle data for each non-motorized vehicle lane in the city is calculated.

3. The traffic emergency data fusion method according to claim 2, characterized in that, The analysis assesses the speed reduction and congestion coefficients of target electric vehicles in each non-motorized vehicle lane within the city during the target time period. The specific analysis method is as follows: Based on the location of each target electric vehicle in the city on the non-motorized vehicle lane at each monitoring time point within the target time period, the monitoring time points of each target electric vehicle in the city on each non-motorized vehicle lane within the target time period are mapped. Based on the speed values ​​of each target electric vehicle in the city at each monitoring time point within the target time period, the speed values ​​of each target electric vehicle in the city on each non-motorized vehicle lane within the target time period are extracted. The system obtains the rate values ​​and rainfall of each target electric vehicle in each city at each historical monitoring time point from the local database for each rainfall interval, and calculates the appropriate rate values ​​of each target electric vehicle in the city at each monitoring time point based on this data. Based on the correspondence between the location and each monitoring time point, and based on the speed values ​​of each target electric vehicle in each non-motorized vehicle lane in the city at each monitoring time point within the target time period, the speed values ​​of each target electric vehicle at each location in each non-motorized vehicle lane in the city within the target time period are mapped. Based on the appropriate speed values ​​of each target electric vehicle in the city at each monitoring time point, the speed reduction congestion assessment coefficient of each target electric vehicle in the city in each non-motorized vehicle lane within the target time period is calculated.

4. The traffic emergency data fusion method according to claim 3, characterized in that, The specific calculation method for the appropriate speed values ​​of each target electric vehicle in the city at each monitoring time point is as follows: If the rainfall of a certain non-motorized vehicle lane in a city at a certain monitoring time point is included in a certain rainfall range, then the rainfall range is taken as the target rainfall range of that non-motorized vehicle lane in the city at that monitoring time point, thereby obtaining the target rainfall range of each non-motorized vehicle lane in the city at each monitoring time point. If the rainfall of a target electric vehicle in a city at a certain historical monitoring time point is included in the target rainfall range of a non-motorized vehicle lane at a certain monitoring time point, then that historical monitoring time point is taken as the target historical monitoring time point of that target electric vehicle in the city at that monitoring time point. This allows for the selection of the target historical monitoring time points of each target electric vehicle in the city at each monitoring time point. Based on the rate values ​​of each target electric vehicle in the city at each historical monitoring time point, the rate values ​​of each target electric vehicle in the city at each historical monitoring time point are mapped to calculate the appropriate rate values ​​of each target electric vehicle in the city at each monitoring time point.

5. The traffic emergency data fusion method according to claim 1, characterized in that, The specific assessment method for evaluating the actual congestion level of each non-motorized vehicle lane in the city is as follows: Obtain the non-motorized vehicle lane type and road width of each non-motorized vehicle lane in the city from the local database, and analyze the vehicle number and congestion coefficient of each non-motorized vehicle lane in the city accordingly. Based on the feedback congestion level of electric vehicles in each non-motorized vehicle lane of the city, and combined with the vehicle quantity congestion coefficient of each non-motorized vehicle lane of the city, the comprehensive congestion assessment coefficient of each non-motorized vehicle lane of the city is calculated. The actual congestion level corresponding to each comprehensive congestion assessment coefficient range is obtained from the local database. Based on the comprehensive congestion assessment coefficient of each non-motorized vehicle lane in the city, the actual congestion level of each non-motorized vehicle lane in the city is mapped to the actual congestion level.

6. The traffic emergency data fusion method according to claim 5, characterized in that, The specific analysis method for the congestion coefficient of vehicle quantity in each non-motorized vehicle lane of the city is as follows: Based on the type of non-motorized vehicle lanes in the city, the floating traffic flow of the corresponding non-motorized vehicle lanes in the city during the target time period is obtained according to different non-motorized vehicle lane types. Based on the road width of each non-motorized vehicle lane in the city and the rainfall at each monitoring time point, the vehicle congestion coefficient of each non-motorized vehicle lane in the city is calculated.

7. The traffic emergency data fusion method according to claim 1, characterized in that, The analysis focuses on the route change nodes of each target electric vehicle in the city's non-motorized vehicle lanes within the target time period. The specific analysis method is as follows: The actual travel route of a target electric vehicle belonging to a city within the target time period is compared with the corresponding first lane plan. The location of the non-motorized vehicle in the non-motorized lane when the actual travel route of the target electric vehicle in the city is inconsistent with the first lane plan is extracted. Then, the subsequent travel route of the target electric vehicle is compared with the second lane plan, and the location of the non-motorized vehicle in the non-motorized lane when the subsequent travel route of the target electric vehicle in the city is inconsistent with the second lane plan is extracted. This process is repeated, and the locations of the non-motorized lanes where inconsistent choices occur during the above derivation process are used as the route change nodes of the target electric vehicle in the city in each corresponding non-motorized lane. Thus, the route change nodes of each target electric vehicle in the city in each non-motorized lane within the target time period are summarized.

8. A traffic emergency big data analysis system, used to execute the traffic emergency data fusion method according to any one of claims 1-7, characterized in that, include: The road information acquisition module is used to acquire the characteristic values ​​of each lane planning and each traffic data of each target electric vehicle in the city within the target time period during rainfall, and to acquire the rainfall of each non-motorized vehicle lane in the city at each monitoring time point within the target time period. The electric vehicle behavior analysis module is used to analyze the behavior of each target electric vehicle and analyze the feedback congestion of electric vehicle data in each non-motorized vehicle lane in the city. The data fusion and evaluation module is used to provide feedback on congestion based on electric vehicle data of each non-motorized vehicle lane in the city, and to evaluate the actual congestion level of each non-motorized vehicle lane in the city based on the rainfall at each monitoring time point, and to analyze each predicted congestion area of ​​each non-motorized vehicle lane in the city. The visualization processing module is used to send the actual congestion level of each non-motorized vehicle lane in the city and the estimated congestion areas to the traffic terminal for visualization display.

Images