CN120636166B - A traffic emergency big data analysis system and data fusion method - Google Patents
A traffic emergency big data analysis system and data fusion methodInfo
- Publication number
- CN120636166B CN120636166B CN202511105695.4A CN202511105695A CN120636166B CN 120636166 B CN120636166 B CN 120636166B CN 202511105695 A CN202511105695 A CN 202511105695A CN 120636166 B CN120636166 B CN 120636166B
- Authority
- CN
- China
- Prior art keywords
- city
- lane
- target
- motor
- electric vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种交通应急大数据研判系统及数据融合方法，涉及数据融合技术领域，本发明包括整合目标电动车实时数据、气象监测数据和传统交通检测数据，实现了交通应急管理能力的全方位提升，首先突破了传统固定检测设备的空间局限，利用电动车的高频移动特性实现了城市路网无盲区覆盖，特别是针对传统监测手段难以覆盖的非机动车道和支路小巷，显著提升了交通态势感知的精细度，在数据处理层面，有效解决了异构数据融合的难题，使交通事件检测的实时性和准确性得到质的飞跃，基于改进的行为分析模型和拥堵评估算法，能够精准识别降雨等恶劣天气条件下的交通异常。
The present invention discloses a traffic emergency big data analysis and judgment system and a data fusion method, which relate to the field of data fusion technology. The present invention includes integrating real-time data of target electric vehicles, meteorological monitoring data and traditional traffic detection data, realizing an all-round improvement in traffic emergency management capabilities. Firstly, it breaks through the spatial limitations of traditional fixed detection equipment and utilizes the high-frequency mobility characteristics of electric vehicles to achieve blind-spot coverage of urban road networks, especially for non-motorized vehicle lanes and branch roads and alleys that are difficult to cover with traditional monitoring methods, significantly improving the precision of traffic situation perception. At the data processing level, it effectively solves the problem of heterogeneous data fusion, making a qualitative leap in the real-time and accuracy of traffic event detection. Based on the improved behavior analysis model and congestion assessment algorithm, it can accurately identify traffic anomalies under severe weather conditions such as rainfall.
Description
Technical Field
The invention relates to the technical field of data fusion, in particular to a traffic emergency big data studying and judging system and a data fusion method.
Background
With the acceleration of the urban process and the continuous increase of traffic demands, urban traffic jam problems are increasingly serious, and especially under severe weather conditions, traffic jam and accident risks are remarkably increased, and the traditional traffic emergency management method mainly depends on fixed traffic detection equipment and is relatively less in monitoring of non-motor lanes, so that emergency data analysis is necessary for the non-motor lanes.
An intelligent traffic condition analysis method for uncertain mode deletion is disclosed in the patent application of CN120032512A, and comprises the steps of analyzing traffic data by using accurate mode fusion traffic data, so as to improve the accuracy of analysis results of traffic conditions. And further, carrying out traffic emergency treatment analysis according to the traffic condition analysis result, determining traffic emergency treatment advice, and sending the traffic emergency treatment advice to the traffic management terminal.
The invention discloses an emergency event identification method and system based on multi-source data fusion, wherein the method comprises the steps of obtaining a multi-source data training sample set of a target emergency event, obtaining characteristic information, obtaining target fusion data, and inputting the fusion data into a constructed emergency event identification model to obtain an emergency event identification result. The method can effectively improve the identification accuracy and timeliness of the emergency event.
As can be seen from the above solution, the traffic emergency data fusion method of the target includes:
(1) The deployment of the main fixed detection equipment is concentrated on main roads and key intersections, the coverage of areas such as urban branches, non-motor lanes and the like is limited, a monitoring blind area is formed, and particularly in the non-motor lanes, an effective real-time data acquisition means is lacking, so that the traffic management department is difficult to master the running state of the whole road network in time.
(2) Conventional methods rely on manual research and periodic data reporting by stationary detection devices, which typically take several minutes or even longer from the event to the response.
(3) Existing systems are based primarily on structured data (e.g., vehicle flow, speed), and lack fusion analysis of unstructured data (e.g., electric vehicle behavior, trajectory dynamics).
(4) Professions who transport goods and need a platform to plan transport routes in real time frequently adjust paths to avoid congested or dangerous areas in rainfall weather, but these dynamic path data are not effectively integrated into traffic management.
Disclosure of Invention
The invention aims to provide a traffic emergency big data studying and judging system and a data fusion method, which solve the problems in the background technology.
In order to solve the technical problems, the invention adopts the following technical scheme:
A traffic emergency data fusion method comprising:
step 1, during rainfall, obtaining characteristic values of each lane plan and each traffic data of each target electric vehicle to which the city belongs in a target time period, and obtaining rainfall of each non-motor vehicle lane to which the city belongs in the target time period at each monitoring time point;
step 2, analyzing behaviors of all target electric vehicles, and analyzing feedback congestion degree of electric vehicle data of all non-motor lanes to which the city belongs;
Step 3, based on the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs, evaluating the actual congestion level of each non-motor vehicle lane to which the city belongs according to the rainfall of each non-motor vehicle lane to which the city belongs at each monitoring time point, and analyzing each estimated congestion area of each non-motor vehicle lane to which the city belongs;
and step 4, transmitting the actual congestion level and each estimated congestion area of each non-motor vehicle lane to which the city belongs to the traffic terminal, and carrying out visual display.
Based on the same inventive concept, a traffic emergency big data studying and judging system for executing the traffic emergency data fusion method is also provided, which comprises the following steps:
The road information acquisition module is used for acquiring characteristic values of each lane plan and each traffic data of each target electric vehicle of the city in the target time period when rainfall occurs, and acquiring rainfall of each non-motor vehicle lane of the city in the target time period at each monitoring time point.
And the electric vehicle behavior analysis module is used for performing behavior analysis on each target electric vehicle and analyzing feedback congestion degree of electric vehicle data of each non-motor vehicle lane of the city.
The data fusion evaluation module is used for evaluating the actual congestion level of each non-motor lane to which the city belongs based on the feedback congestion degree of the electric vehicle data of each non-motor lane to which the city belongs and according to the rainfall of each non-motor lane to which the city belongs at each monitoring time point, and analyzing each estimated congestion area of each non-motor lane to which the city belongs.
The visual processing module is used for sending the actual congestion level and each estimated congestion area of each non-motor vehicle lane to which the city belongs to the traffic terminal and carrying out visual display.
The invention has the beneficial effects that:
According to the invention, the real-time data, the weather monitoring data and the traditional traffic detection data of the target electric vehicle are integrated, the comprehensive improvement of the traffic emergency management capability is realized, the space limitation of the traditional fixed detection equipment is broken through, the urban road network non-blind area coverage is realized by utilizing the high-frequency mobile characteristic of the electric vehicle, the traffic situation perception fineness is obviously improved particularly aiming at non-motorized lanes and branch lanes which are difficult to be covered by the traditional monitoring means, the problem of heterogeneous data fusion is effectively solved in the data processing aspect, the real-time performance and the accuracy of traffic event detection are improved, the traffic abnormality under severe weather conditions such as rainfall can be accurately identified based on an improved behavior analysis model and a congestion evaluation algorithm, and the expandability and the cross-platform compatibility of the system are ensured through a standardized data interface and a modularized design.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a schematic diagram of a system module according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a traffic emergency data fusion method, which comprises the following steps:
and step 1, during rainfall, obtaining characteristic values of each lane plan and each traffic data of each target electric vehicle of the city in a target time period, and obtaining rainfall of each non-motor vehicle lane of the city in each monitoring time point in the target time period.
In a specific embodiment of the invention, the characteristic values of the lane plans and the traffic data of the target electric vehicles of the cities in the target time period are obtained, and the rainfall of the non-motor lanes of the cities in the target time period is obtained at the monitoring time points.
It should be noted that, the target electric vehicle of the present invention is an electric vehicle used by professions that transport goods and require a platform to plan a transport route in real time, including but not limited to, professions such as express delivery, catering service delivery, etc.
It should be noted that, each lane planning of each target electric vehicle is planned by the data monitoring platform, each target electric vehicle has an initial lane planning, if the lane planning deviates from the route of the initial lane planning, the second lane planning is updated, if the lane planning deviates from the route of the second lane planning, the third lane planning is updated, and so on, so as to obtain each lane planning of each target electric vehicle to which the city belongs in the target time period.
Determining the stable position of each target electric vehicle, installing each sensor at the stable position of each target electric vehicle, and acquiring the characteristic value of each traffic data of each target electric vehicle belonging to the city in the target time period through each sensor, wherein each traffic data comprises a speed value and a GPS position at each monitoring time point.
In a specific embodiment, the method for determining the stable position of each target electric vehicle comprises the following steps that the existing stable position analysis technology of the electric vehicle is relatively mature, and the stable position of each target electric vehicle can be determined through the existing stable position analysis technology of the electric vehicle.
By uniformly installing the sensors, the acquired data information is ensured to have higher credibility, and larger errors of the acquired data information caused by the differentiation of the target electric vehicle are prevented.
And obtaining the rainfall of each non-motor lane of the city at each monitoring time point from the meteorological platform.
And 2, performing behavior analysis on each target electric vehicle, and analyzing feedback congestion degree of electric vehicle data of each non-motor vehicle lane of the city.
In a specific embodiment of the present invention, the behavior analysis is performed on each target electric vehicle, and the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs is analyzed, and the specific analysis method includes: according to the position of each target electric vehicle of the city on each non-motor vehicle lane in each monitoring time point in the target time period, the speed-reducing congestion evaluation coefficient of each target electric vehicle of the city on each non-motor vehicle lane in the target time period is analyzed, and the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane of the city is calculated.
In one embodiment, the method for calculating the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs comprises the steps of mapping the deceleration congestion evaluation coefficients of each target electric vehicle of each non-motor vehicle lane to which the city belongs in a target time period according to the deceleration congestion evaluation coefficients of each target electric vehicle of each non-motor vehicle lane to which the city belongs in the target time periodWherein x is the number of each target electric vehicle,Y is a positive integer greater than 2, n is the number of each non-motor vehicle lane,M is a positive integer greater than 2, and the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs is calculated。
According to the specific embodiment of the invention, the deceleration congestion evaluation coefficient of each target electric vehicle of the city in each non-motor lane in the target time period is analyzed, and the specific analysis method comprises the steps of mapping to obtain each monitoring time point of each target electric vehicle of the city in each non-motor lane in the target time period according to the position of each target electric vehicle of the city in each monitoring time point in each non-motor lane in the target time period, and extracting to obtain the speed value of each target electric vehicle of the city in each monitoring time point of each non-motor lane in the target time period according to the speed value of each target electric vehicle of the city in each monitoring time point in the target time period.
And acquiring the rainfall intervals, the speed values of the target electric vehicles of the cities at each historical monitoring time point and the rainfall from a local database, and calculating the proper speed values of the target electric vehicles of the cities at each monitoring time point according to the speed values.
The local database is used for storing each rainfall interval, the speed value and the rainfall of each target electric vehicle of the city at each historical monitoring time point, the type and the road width of each non-motor vehicle lane of the city, the actual congestion grade corresponding to each comprehensive congestion evaluation coefficient interval, the proper floating traffic of each non-motor vehicle lane type under each rainfall interval under each road width interval, each segmented area of each non-motor vehicle lane of the city, the estimated congestion coefficient threshold value and the display color corresponding to each actual congestion grade.
According to the corresponding relation between the position and each monitoring time point, and according to the speed value of each target electric vehicle of the city in each monitoring time point of each non-motor lane in the target time period, mapping to obtain the speed value of each target electric vehicle of each position of each non-motor lane of the city in the target time period, and according to the proper speed value of each target electric vehicle of the city in each monitoring time point, calculating the speed-down congestion evaluation coefficient of each target electric vehicle of the city in each non-motor lane in the target time period.
It should be noted that, the correspondence between the position and each monitoring time point is that a certain position on the non-motor vehicle lane corresponds to a different monitoring time point.
In one embodiment, the method for calculating the deceleration congestion evaluation coefficient of each target electric vehicle of the city in each non-motor lane in the target time period comprises the following steps of according to the velocity value of each target electric vehicle of each non-motor lane of the city in each positionWhere i is the number of each location,J is a positive integer greater than 2, and calculating the rate fluctuation hazard coefficient of each target electric vehicle on each position of each non-motor vehicle lane of the cityWhere j is expressed as the number of locations.
According to the proper speed value of each target electric vehicle of the city at each monitoring time point and the corresponding relation between the position and each monitoring time point, mapping to obtain the proper speed value of each target electric vehicle of each non-motor vehicle lane of the city at each positionCalculating the speed reduction comparison coefficient of each target electric vehicle on each position of each non-motor vehicle lane of the cityCalculating the deceleration congestion evaluation coefficients of all target electric vehicles belonging to the city in all non-motor lanes in the target time period。
In a specific embodiment of the invention, the calculation method is that if the rainfall of a certain non-motor lane to which the city belongs at a certain monitoring time point is included in a certain rainfall interval, the rainfall interval is used as the target rainfall interval of the non-motor lane to which the city belongs at the monitoring time point, so as to obtain the target rainfall interval of the non-motor lane to which the city belongs at the monitoring time point.
If the rainfall of a certain target electric vehicle belonging to the city at a certain historical monitoring time point is contained in a target rainfall interval of a certain non-motor lane at a certain monitoring time point, the historical monitoring time point is taken as a target historical monitoring time point of the target electric vehicle belonging to the city at the monitoring time point, so that each target historical monitoring time point of each target electric vehicle belonging to the city at each monitoring time point is obtained through screening, and according to the speed value of each target electric vehicle belonging to the city at each historical monitoring time point, the speed value of each target historical monitoring time point of each target electric vehicle belonging to the city at each monitoring time point is obtained through mapping, so that the proper speed value of each target electric vehicle belonging to the city at each monitoring time point is calculated.
In a specific embodiment, the calculating method specifically includes that the calculating method includes the steps of calculating the suitable speed value of each target electric vehicle of the city at each monitoring time point according to the speed value of each target historical monitoring time point of each target electric vehicle of the city at each monitoring time point, accumulating the speed values, and then calculating an average value to obtain the suitable speed value of each target electric vehicle of the city at each monitoring time point.
And 3, based on the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs, evaluating the actual congestion level of each non-motor vehicle lane to which the city belongs according to the rainfall of each non-motor vehicle lane to which the city belongs at each monitoring time point, and analyzing each estimated congestion area of each non-motor vehicle lane to which the city belongs.
The actual congestion level is divided into a first congestion level, a second congestion level, a third congestion level and a fourth congestion level, wherein the first congestion level is greater than the second congestion level, the second congestion level is greater than the third congestion level, and the third congestion level is greater than the fourth congestion level.
In the specific embodiment of the invention, the actual congestion level of each non-motor vehicle lane to which the city belongs is estimated, and the specific estimation method comprises the steps of acquiring the type and the road width of the non-motor vehicle lane to which the city belongs from a local database, and analyzing the vehicle quantity congestion coefficient of each non-motor vehicle lane to which the city belongs according to the type and the road width.
It should be noted that, the non-motor vehicle lane types have three different forms, namely, one is a dedicated non-motor vehicle lane, at this time, the non-motor vehicle lane type is dedicated, the other is a non-motor vehicle lane without the dedicated, and the motor vehicle lane in the driving direction is not a single lane, then the rightmost motor vehicle lane is taken as the non-motor vehicle lane, at this time, the non-motor vehicle lane type is occupied by the motor vehicle lane, the other is a non-motor vehicle lane without the dedicated, and the motor vehicle lane in the driving direction is a single lane, at this time, the non-motor vehicle lane type is mixed with the motor vehicle.
It should be noted that, the road width is the road width of the exclusive non-motor vehicle lane if the non-motor vehicle lane type is exclusive, the road width of the rightmost motor vehicle lane is the road width if the non-motor vehicle lane type is occupied by the motor vehicle lane, and the road width of the motor vehicle lane of the single lane is the road width if the non-motor vehicle lane type is mixed use of the motor vehicle and the electric vehicle.
According to the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs, and by combining the vehicle quantity congestion coefficients of each non-motor vehicle lane to which the city belongs, calculating the comprehensive congestion evaluation coefficients of each non-motor vehicle lane to which the city belongs.
In one embodiment, the method for calculating the comprehensive congestion evaluation coefficient of each non-motor lane of the city comprises the following steps of feeding back the congestion degree according to the electric vehicle data of each non-motor lane of the cityAnd combining the congestion coefficients of the number of vehicles of each non-motor vehicle lane to which the city belongsCalculating comprehensive congestion evaluation coefficients of all non-motor lanes to which the city belongs。
And obtaining actual congestion levels corresponding to the comprehensive congestion evaluation coefficient intervals from a local database, and mapping to obtain the actual congestion levels of the non-motor vehicle lanes to which the city belongs according to the comprehensive congestion evaluation coefficients of the non-motor vehicle lanes to which the city belongs.
According to the specific embodiment of the invention, the vehicle quantity congestion coefficients of all the non-motor lanes of the city are analyzed, and the specific analysis method comprises the steps of respectively obtaining the floating vehicle flow of the corresponding non-motor lanes of the city in a target time period according to the non-motor lane types of all the non-motor lanes of the city and different non-motor lane types, and calculating the vehicle quantity congestion coefficients of all the non-motor lanes of the city according to the road width of all the non-motor lanes of the city and the rainfall at all the monitoring time points.
In a specific embodiment, the method for acquiring the floating traffic of the non-motor vehicle lane corresponding to the city in the target time period according to different non-motor vehicle lane types includes that if the non-motor vehicle lane type of the city in the target time period is exclusive, the floating traffic of the non-motor vehicle lane corresponding to the city in the target time period is acquired through a camera at an entrance of the exclusive non-motor vehicle lane, if the non-motor vehicle lane type of the city in the non-motor vehicle lane is occupied by the motor vehicle lane, the floating traffic of the non-motor vehicle lane corresponding to the city in the target time period is acquired through a camera at an entrance direction of a rightmost lane of the intersection, and if the non-motor vehicle lane type of the city in the non-motor vehicle lane is mixed with the motor vehicle, the floating traffic of the non-motor vehicle lane corresponding to the city in the target time period is acquired through a camera at an entrance direction of a single lane of the intersection.
In one embodiment, the calculating method comprises obtaining the appropriate floating traffic flow of each non-motor lane type under each road width interval and each rainfall interval from a local database, mapping to obtain the appropriate floating traffic flow of each non-motor lane of the city in a target time period according to the non-motor lane type of each non-motor lane of the city and according to the road width of each non-motor lane of the city and the rainfall at each monitoring time pointAccording to the floating traffic flow of each non-motor vehicle lane of the cityCalculating the number congestion coefficient of vehicles of each non-motor lane to which the city belongsWhere e is denoted as a natural constant.
The appropriate floating traffic flow of each non-motor vehicle lane type under each rainfall interval under each road width interval is set by scientific researchers according to actual conditions, and the relationship needs to be satisfied that the larger the road width is, the larger the corresponding appropriate floating traffic flow is, the larger the rainfall is, and the smaller the corresponding appropriate floating traffic flow is.
According to the specific embodiment of the invention, the estimated blocking areas of the non-motor lanes to which the cities belong are analyzed, and the specific analysis method comprises the steps of obtaining the positions of the target electric vehicles to which the cities belong on the non-motor lanes when the target electric vehicles to which the cities belong are monitored at the monitoring time points in the target time period according to the GPS positions of the target electric vehicles to which the cities belong at the monitoring time points in the target time period, and analyzing to obtain the actual travelling routes of the target electric vehicles to which the cities belong in the target time period.
According to the lane planning and the actual travelling route of each target electric vehicle of the city in the target time period, analyzing the rerouting nodes of each target electric vehicle of the city in each non-motor lane in the target time period, and mapping to obtain the rerouting nodes of each target electric vehicle of each non-motor lane of the city in the target time period.
And obtaining each segmented area of each non-motor vehicle lane to which the city belongs from a local database, adding 1 to the estimated jam coefficient of the segmented area if the rerouting node of a certain target electric vehicle of a certain non-motor vehicle lane to which the city belongs is contained in the segmented area, and the like to obtain the estimated jam coefficient of each segmented area of each non-motor vehicle lane to which the city belongs.
And acquiring a predicted blocking coefficient threshold value from a local database, and if the predicted blocking coefficient of a certain segmented area of a certain non-motor vehicle lane to which the city belongs is larger than the predicted blocking coefficient threshold value, marking the segmented area as a predicted blocking area so as to screen each predicted blocking area of each non-motor vehicle lane to which the city belongs.
In a specific embodiment of the present invention, the analyzing a rerouting node of each target electric vehicle of a city in each non-motor lane in a target time period includes: comparing the actual travelling route of a certain target electric vehicle belonging to the city with a corresponding first lane plan in a target time period, extracting the position of a non-motorized lane where the actual travelling route of the certain target electric vehicle belonging to the city is inconsistent with the first lane plan, comparing the subsequent travelling route of the certain target electric vehicle with a second lane plan, extracting the position of the non-motorized lane where the subsequent travelling route of the certain target electric vehicle belonging to the city is inconsistent with the second lane plan, and the like, and taking the position of the non-motorized lane where the inconsistent selection occurs in the derivation process as a rerouting node of each corresponding non-motorized lane of the certain target electric vehicle belonging to the city, thereby summarizing the rerouting nodes of each non-motorized lane of the certain target electric vehicle belonging to the city in the target time period.
The following route is a route which is left after subtracting the route consistent with the first lane planning from the actual route.
And step 4, transmitting the actual congestion level and each estimated congestion area of each non-motor vehicle lane to which the city belongs to the traffic terminal, and carrying out visual display.
In a specific embodiment, the visual display is performed by acquiring display colors corresponding to actual congestion levels from a local database, mapping to obtain the display colors of the non-motor lanes to which the city belongs according to the actual congestion levels of the non-motor lanes to which the city belongs, displaying the display colors on a screen, and performing early warning identification on the estimated blocking areas of the non-motor lanes to which the city belongs.
According to the invention, the real-time data, the weather monitoring data and the traditional traffic detection data of the target electric vehicle are integrated, the comprehensive improvement of the traffic emergency management capability is realized, the space limitation of the traditional fixed detection equipment is broken through, the non-blind area coverage of the urban road network is realized by utilizing the high-frequency mobile characteristic of the target electric vehicle, the fineness of traffic situation perception is obviously improved particularly for non-motorized lanes and branch lanes which are difficult to be covered by the traditional monitoring means, the difficulty of heterogeneous data fusion is effectively solved in the data processing aspect, the real-time performance and accuracy of traffic event detection are improved, the traffic abnormality under severe weather conditions such as rainfall can be accurately identified based on an improved behavior analysis model and a congestion evaluation algorithm, and the expandability and cross-platform compatibility of the system are ensured through a standardized data interface and a modularized design.
Based on the same inventive concept, a traffic emergency big data studying and judging system for executing the traffic emergency data fusion method is also provided, which comprises the following steps:
The system comprises a road information acquisition module, an electric vehicle behavior analysis module, a data fusion evaluation module, a visual processing module and a local database.
The road information acquisition module is connected with the electric vehicle behavior analysis module, the electric vehicle behavior analysis module is connected with the data fusion evaluation module, the data fusion evaluation module is connected with the visual processing module, and the local database is connected with the electric vehicle behavior analysis module, the data fusion evaluation module and the visual processing module.
The road information acquisition module is used for acquiring characteristic values of each lane plan and each traffic data of each target electric vehicle of the city in the target time period and acquiring rainfall of each non-motor lane of the city in the target time period at each monitoring time point during rainfall.
The electric vehicle behavior analysis module is used for analyzing behaviors of all target electric vehicles and analyzing feedback congestion degree of electric vehicle data of all non-motor lanes of the city.
The data fusion evaluation module is used for evaluating the actual congestion level of each non-motor lane to which the city belongs based on the feedback congestion degree of the electric vehicle data of each non-motor lane to which the city belongs and according to the rainfall of each non-motor lane to which the city belongs at each monitoring time point, and analyzing each estimated congestion area of each non-motor lane to which the city belongs.
The visual processing module is used for sending the actual congestion level and each estimated congestion area of each non-motor vehicle lane to which the city belongs to the traffic terminal and performing visual display.
The foregoing is merely illustrative and explanatory of the principles of this invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of this invention or beyond the scope of this invention as defined in the claims.
Claims (8)
1. A traffic emergency data fusion method, comprising:
step 1, during rainfall, obtaining characteristic values of each lane plan and each traffic data of each target electric vehicle of the city in a target time period, and obtaining rainfall of each non-motor vehicle lane of the city in a monitoring time point in the target time period, wherein the specific obtaining method comprises the following steps:
Acquiring each lane plan of each target electric vehicle to which the city belongs in a target time period from a data monitoring platform;
Determining the stable position of each target electric vehicle, installing each sensor at the stable position of each target electric vehicle, and acquiring the characteristic value of each traffic data of each target electric vehicle belonging to the city in a target time period through each sensor, wherein each traffic data comprises a speed value and a GPS position at each monitoring time point;
obtaining rainfall of each non-motor lane of a city at each monitoring time point from a meteorological platform;
step 2, analyzing behaviors of all target electric vehicles, and analyzing feedback congestion degree of electric vehicle data of all non-motor lanes to which the city belongs;
Step 3, based on the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs, and according to the rainfall of each non-motor vehicle lane to which the city belongs at each monitoring time point, evaluating the actual congestion level of each non-motor vehicle lane to which the city belongs, and analyzing each estimated congestion area of each non-motor vehicle lane to which the city belongs, the specific analysis method comprises the following steps:
According to the GPS positions of all the target electric vehicles of the city in the target time period at all the monitoring time points, the positions of all the target electric vehicles of the city in the target time period on the non-motor vehicle lanes at all the monitoring time points are obtained, and the actual travelling routes of all the target electric vehicles of the city in the target time period are obtained through analysis;
According to the lane planning and actual travelling routes of all target electric vehicles of the cities in the target time period, analyzing the rerouting nodes of all target electric vehicles of the cities in all non-motor lanes in the target time period, and mapping to obtain the rerouting nodes of all target electric vehicles of all non-motor lanes of the cities in the target time period;
Obtaining each segmented area of each non-motor vehicle lane to which the city belongs from a local database, adding 1 to the estimated jam coefficient of the segmented area if the rerouting node of a certain target electric vehicle of a certain non-motor vehicle lane to which the city belongs is contained in the segmented area, and the like to obtain the estimated jam coefficient of each segmented area of each non-motor vehicle lane to which the city belongs;
Obtaining a predicted blocking coefficient threshold value from a local database, and if the predicted blocking coefficient of a certain segmented area of a certain non-motor vehicle lane to which the city belongs is larger than the predicted blocking coefficient threshold value, marking the segmented area as a predicted blocking area so as to screen each predicted blocking area of each non-motor vehicle lane to which the city belongs;
and step 4, transmitting the actual congestion level and each estimated congestion area of each non-motor vehicle lane to which the city belongs to the traffic terminal, and carrying out visual display.
2. The traffic emergency data fusion method according to claim 1, wherein the behavior analysis is performed on each target electric vehicle, and the feedback congestion degree of the electric vehicle data of each non-motor lane to which the city belongs is analyzed, and the specific analysis method is as follows:
According to the position of each target electric vehicle of the city on each non-motor vehicle lane in each monitoring time point in the target time period, the speed-reducing congestion evaluation coefficient of each target electric vehicle of the city on each non-motor vehicle lane in the target time period is analyzed, and the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane of the city is calculated.
3. The traffic emergency data fusion method according to claim 2, wherein the analyzing the deceleration congestion evaluation coefficients of each target electric vehicle of the city in each non-motor lane in the target time period comprises the following specific analyzing method:
Mapping according to the positions of all the target electric vehicles of the city in each monitoring time point on the non-motor vehicle lane in the target time period to obtain all the monitoring time points of all the target electric vehicles of the city in each non-motor vehicle lane in the target time period, and extracting according to the speed values of all the target electric vehicles of the city in each monitoring time point in the target time period to obtain the speed values of all the monitoring time points of all the target electric vehicles of the city in each non-motor vehicle lane in the target time period;
Obtaining the rainfall intervals, the speed values of the target electric vehicles of the city at each historical monitoring time point and the rainfall from a local database, and calculating the proper speed values of the target electric vehicles of the city at each monitoring time point according to the speed values;
According to the corresponding relation between the position and each monitoring time point, and according to the speed value of each target electric vehicle of the city in each monitoring time point of each non-motor lane in the target time period, mapping to obtain the speed value of each target electric vehicle of each position of each non-motor lane of the city in the target time period, and according to the proper speed value of each target electric vehicle of the city in each monitoring time point, calculating the speed-down congestion evaluation coefficient of each target electric vehicle of the city in each non-motor lane in the target time period.
4. A traffic emergency data fusion method according to claim 3, wherein, the calculation method for calculating the proper speed value of each target electric vehicle of the city at each monitoring time point comprises the following steps:
If the rainfall of a certain non-motor vehicle lane to which the city belongs at a certain monitoring time point is contained in a certain rainfall interval, taking the rainfall interval as a target rainfall interval of the non-motor vehicle lane to which the city belongs at the monitoring time point, so as to obtain target rainfall intervals of all the non-motor vehicle lanes to which the city belongs at all the monitoring time points;
If the rainfall of a certain target electric vehicle belonging to the city at a certain historical monitoring time point is contained in a target rainfall interval of a certain non-motor lane at a certain monitoring time point, the historical monitoring time point is taken as a target historical monitoring time point of the target electric vehicle belonging to the city at the monitoring time point, so that each target historical monitoring time point of each target electric vehicle belonging to the city at each monitoring time point is obtained through screening, and according to the speed value of each target electric vehicle belonging to the city at each historical monitoring time point, the speed value of each target historical monitoring time point of each target electric vehicle belonging to the city at each monitoring time point is obtained through mapping, so that the proper speed value of each target electric vehicle belonging to the city at each monitoring time point is calculated.
5. The traffic emergency data fusion method according to claim 1, wherein the actual congestion level of each non-motor vehicle lane to which the evaluation city belongs is specifically evaluated by:
obtaining the type of the non-motor vehicle lane and the road width of each non-motor vehicle lane of the city from a local database, and analyzing the number congestion coefficient of the vehicles of each non-motor vehicle lane of the city according to the type and the road width;
according to the feedback congestion degree of the electric vehicle data of each non-motor vehicle lane to which the city belongs, and by combining the vehicle quantity congestion coefficients of each non-motor vehicle lane to which the city belongs, calculating the comprehensive congestion evaluation coefficients of each non-motor vehicle lane to which the city belongs;
And obtaining actual congestion levels corresponding to the comprehensive congestion evaluation coefficient intervals from a local database, and mapping to obtain the actual congestion levels of the non-motor vehicle lanes to which the city belongs according to the comprehensive congestion evaluation coefficients of the non-motor vehicle lanes to which the city belongs.
6. The traffic emergency data fusion method according to claim 5, wherein the analyzing the vehicle number congestion coefficients of each non-motor vehicle lane to which the city belongs comprises the following specific steps:
According to the types of the non-motor lanes of the city, respectively obtaining the floating traffic flow of the non-motor lanes corresponding to the city in the target time period according to the different non-motor lane types, and calculating the vehicle quantity congestion coefficient of the non-motor lanes of the city according to the road width of the non-motor lanes of the city and the rainfall at each monitoring time point.
7. The traffic emergency data fusion method according to claim 1, wherein the analyzing the rerouting nodes of each target electric vehicle in each non-motor lane to which the city belongs in the target time period comprises the following specific steps:
Comparing the actual travelling route of a certain target electric vehicle belonging to the city with a corresponding first lane plan in a target time period, extracting the position of a non-motorized lane where the actual travelling route of the certain target electric vehicle belonging to the city is inconsistent with the first lane plan, comparing the subsequent travelling route of the certain target electric vehicle with a second lane plan, extracting the position of the non-motorized lane where the subsequent travelling route of the certain target electric vehicle belonging to the city is inconsistent with the second lane plan, and the like, and taking the position of the non-motorized lane where the inconsistent selection occurs in the derivation process as a rerouting node of each corresponding non-motorized lane of the certain target electric vehicle belonging to the city, thereby summarizing the rerouting nodes of each non-motorized lane of the certain target electric vehicle belonging to the city in the target time period.
8. A traffic emergency big data studying and judging system for executing a traffic emergency data fusion method according to any one of claims 1 to 7, comprising:
The road information acquisition module is used for acquiring characteristic values of each lane plan and each traffic data of each target electric vehicle of the city in a target time period and acquiring rainfall of each non-motor lane of the city in each monitoring time point in the target time period when rainfall occurs;
the electric vehicle behavior analysis module is used for performing behavior analysis on each target electric vehicle and analyzing feedback congestion degree of electric vehicle data of each non-motor vehicle lane of the city;
The data fusion evaluation module is used for evaluating the actual congestion level of each non-motor lane to which the city belongs according to the feedback congestion degree of the electric vehicle data of each non-motor lane to which the city belongs and the rainfall of each monitoring time point of each non-motor lane to which the city belongs, and analyzing each estimated congestion area of each non-motor lane to which the city belongs;
The visual processing module is used for sending the actual congestion level and each estimated congestion area of each non-motor vehicle lane to which the city belongs to the traffic terminal and carrying out visual display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511105695.4A CN120636166B (en) | 2025-08-08 | 2025-08-08 | A traffic emergency big data analysis system and data fusion method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511105695.4A CN120636166B (en) | 2025-08-08 | 2025-08-08 | A traffic emergency big data analysis system and data fusion method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120636166A CN120636166A (en) | 2025-09-12 |
| CN120636166B true CN120636166B (en) | 2025-10-28 |
Family
ID=96955367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511105695.4A Active CN120636166B (en) | 2025-08-08 | 2025-08-08 | A traffic emergency big data analysis system and data fusion method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120636166B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115691115A (en) * | 2022-09-26 | 2023-02-03 | 甘肃省交通规划勘察设计院股份有限公司 | Traffic big data analysis early warning platform |
| CN119068682A (en) * | 2024-11-05 | 2024-12-03 | 南京补天科技实业有限公司 | An intelligent traffic security monitoring and early warning system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311961B (en) * | 2020-02-28 | 2021-03-12 | 山东交通学院 | Intelligent prompting system and method based on driving behavior of non-motor vehicle and non-motor vehicle |
| CN118262509B (en) * | 2024-02-26 | 2024-11-26 | 广东智视云控科技有限公司 | Traffic route prediction method, system and medium for non-main road in urban area |
| CN118485895A (en) * | 2024-04-28 | 2024-08-13 | 合肥工业大学 | A safety rating method for urban non-motorized vehicle lanes |
| CN120356338B (en) * | 2025-06-23 | 2025-08-19 | 四川交通职业技术学院 | A carbon emission management system for the transportation industry based on the Internet of Things |
-
2025
- 2025-08-08 CN CN202511105695.4A patent/CN120636166B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115691115A (en) * | 2022-09-26 | 2023-02-03 | 甘肃省交通规划勘察设计院股份有限公司 | Traffic big data analysis early warning platform |
| CN119068682A (en) * | 2024-11-05 | 2024-12-03 | 南京补天科技实业有限公司 | An intelligent traffic security monitoring and early warning system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120636166A (en) | 2025-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109686088B (en) | Traffic video alarm method, equipment and system | |
| CN109919347B (en) | Road condition generation method, related device and equipment | |
| US20200211374A1 (en) | System, method, and apparatus for analyzing a traffic road condition | |
| CN114363316B (en) | A cross-regional road infrastructure intelligent networking monitoring and supervision system | |
| CN103985250A (en) | Light-weight holographic road traffic state visual inspection device | |
| CN114454878B (en) | Method and device for determining vehicle speed control model training sample | |
| CN112734242A (en) | Method and device for analyzing availability of vehicle running track data, storage medium and terminal | |
| CN113724497A (en) | Method and device for predicting real-time traffic flow of target road | |
| CN117238145A (en) | Intelligent traffic management method and system based on big data | |
| CN119694138A (en) | A dynamic construction method for highway digital twin | |
| CN118781559B (en) | Low-visibility weather disaster treatment method, system and equipment based on image processing | |
| CN120071272A (en) | Abnormal condition detection system and method for highway traffic | |
| CN104217591B (en) | Dynamic road condition detection method and system | |
| CN109785627A (en) | A kind of crossroad access flux monitoring system | |
| CN115188194A (en) | Highway traffic lane level accurate induction system and method | |
| CN119694132A (en) | A highway high-risk section early warning method and system | |
| CN120220396A (en) | Traffic network monitoring method and equipment based on artificial intelligence | |
| CN116434523B (en) | Vehicle active safety control method and device based on constraint degree in information perception scene | |
| CN117494018A (en) | Abnormal behavior monitoring and early warning method based on group data analysis | |
| CN120636166B (en) | A traffic emergency big data analysis system and data fusion method | |
| CN119024381B (en) | Real-time travel path track big data analysis processing method based on Beidou positioning | |
| CN114519500A (en) | Method, device and equipment for determining road safety risk level and storage medium | |
| CN109754606A (en) | A method of based on taxi location prediction congestion in road situation | |
| CN120708401A (en) | A GPS-based vehicle trajectory intelligent GIS electronic fence visualization system | |
| Yin et al. | Detecting illegal pickups of intercity buses from their gps traces |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |