CN115331425A - Traffic early warning method, device and system - Google Patents
Traffic early warning method, device and system Download PDFInfo
- Publication number
- CN115331425A CN115331425A CN202210770647.7A CN202210770647A CN115331425A CN 115331425 A CN115331425 A CN 115331425A CN 202210770647 A CN202210770647 A CN 202210770647A CN 115331425 A CN115331425 A CN 115331425A
- Authority
- CN
- China
- Prior art keywords
- traffic
- data
- special area
- early warning
- congestion
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000006243 chemical reaction Methods 0.000 claims description 20
- 238000010586 diagram Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 8
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 239000011159 matrix material Substances 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a traffic early warning method, a traffic early warning device and a traffic early warning system. The method comprises the following steps: marking a special area, and establishing a road network topological graph corresponding to the special area; associating the urban road network model, and collecting traffic data of a special area; constructing a path library, analyzing the path correlation in the special area by combining traffic data, and screening a key traffic detector; converting data acquired by the key traffic detector into traffic flow space density, and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density; acquiring congestion information of a special area according to a pressure threshold, confirming and marking the congestion information, and generating marking data; and training a congestion prediction model according to the marking data and the traffic data, and early warning the traffic condition of the special area through the congestion prediction model. The scheme provided by the invention can reduce the input sample amount, reduce the training pressure and reduce the technical effect of overfitting on the premise of ensuring the model precision.
Description
Technical Field
The invention relates to the field of traffic network technology application, in particular to a traffic early warning method, a traffic early warning device and a traffic early warning system.
Background
With the increase of the quantity of retained private automobiles, the contradiction between supply and demand of urban roads is increasingly aggravated, the road vehicle running environment is more complex, the traffic jam condition often occurs, the running speed of a traveler is generally reduced, the travel time is increased, and therefore the traffic jam early warning technology is needed to find the jam point in time, distribute tasks to workers efficiently, quickly process the jam, help the traveler to plan the travel route more effectively, and save the travel time.
However, the traditional road congestion early warning is mostly aimed at single nodes, the coverage area is small, when congestion is about to exist at a monitored intersection, an alarm can be given out, the congestion upstream and downstream cannot be monitored and early warned in time according to the actual road circulation condition, and when the congestion phenomenon around buildings with high traffic density such as hospitals and schools in special areas of certain time periods is serious, the traditional traffic early warning system cannot rapidly judge the type and the problem source of traffic pressure, so that the problem road sections cannot be effectively and rapidly dredged, the traffic congestion is difficult to rapidly and efficiently relieve, and the traffic smoothness is difficult to guarantee.
Aiming at the problems that the type and the problem source of traffic pressure cannot be judged quickly in the related technology, and then the problem road sections cannot be effectively and quickly treated and dredged, traffic jam cannot be relieved quickly and efficiently, and the smoothness of traffic cannot be guaranteed, an effective solution is not provided at present.
Disclosure of Invention
In order to solve the technical problems, the invention is expected to provide a traffic early warning method, a traffic early warning device and a traffic early warning system, so as to at least solve the problems that the type and the problem source of traffic pressure cannot be judged quickly in the related technology, so that the problem road sections cannot be effectively and quickly treated and dredged, the traffic jam cannot be relieved quickly and efficiently, and the smoothness of traffic cannot be ensured.
The technical scheme of the invention is realized as follows:
in a first aspect, the present invention provides a traffic early warning method, including: marking a special area, and establishing a road network topological graph corresponding to the special area; associating the urban road network model, and acquiring traffic data of a special area; constructing a path library, analyzing the path correlation in the special area by combining traffic data, and screening a key traffic detector; converting data acquired by the key traffic detector into traffic flow space density, and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density; acquiring congestion information of a special area according to a pressure threshold, confirming and marking the congestion information, and generating marking data; and training a congestion prediction model according to the marking data and the traffic data, and early warning the traffic condition of the special area through the congestion prediction model.
Optionally, marking the special area, and establishing the road network topological graph corresponding to the special area includes: marking a special area, wherein the special area is an area covered by a building or facility with a traffic demand larger than a preset threshold value in a specific time period and a road facility in a preset adjacent range around the building or facility; and screening the central nodes of the special area, setting intersections in the preset adjacent range of the central nodes as nodes, taking the nodes as centers, taking all associated road sections of the nodes as road sections close to the central nodes, and establishing a road network topological graph of the special area.
Further, optionally, the collecting traffic data of the regional road network model in the road network topological graph by associating the urban road network model includes: through associating the urban road network model, acquiring traffic data of the regional road network model in the road network topological graph according to the traffic detectors of all road sections, wherein the traffic data comprises: data of regional network models and traffic detector data.
Optionally, constructing a path library, analyzing path correlation in a special area by combining traffic data, and screening a key traffic detector includes: screening vehicles passing around a central node based on historical traffic detector data, tracking vehicle tracks, reversely deducing driving paths of the vehicles in a special area, and constructing a path library; on the basis of historical traffic data, flow data of the paths in a specified period are counted to obtain flow characteristics of each path; counting flow data flowing into the central node in a specified period based on the real-time traffic data to obtain the flow characteristics of the central node; judging the correlation between the path and the central node according to the correlation coefficient of the flow characteristics of the path and the flow characteristics of the central node, and screening a target path according to the correlation; and considering the influence of the path flow on the regional congestion according to the weight of the corresponding target path for the target path corresponding to each correlation, and selecting the traffic detector arranged on the flow direction in the road section as a key traffic detector according to the flow direction on the path.
Further, optionally, the method further includes: and for the road section lacking the bayonet device in the path, searching the shortest path by adopting a path searching algorithm and completing the path.
Optionally, converting the data collected by the key traffic detector into the spatial density of the traffic flow comprises: calculating an approximate value of the current queuing length according to the sum of the length of the standard small car and the distance between the heads by using the flow or the distance between the heads, and comparing the approximate value of the current queuing length with the length of the road section to obtain the first traffic flow space density of the road section; using the headway or the queue length, multiplying the time interval acquired by two continuous vehicles through a key traffic detector in a fixed point by the road section free flow speed to obtain a distance interval, and comparing the distance interval with the road section length to obtain a second traffic flow space density of the road section; and carrying out normalization processing on the first traffic flow space density and the second traffic flow space density, and carrying out weighted average on the data after normalization processing to obtain the target traffic flow space density of the road section.
Further, optionally, the setting of the pressure threshold of the regional traffic warning according to the spatial density of the traffic flow includes: classifying traffic pressure according to the spatial density of the traffic flow, and setting a pressure threshold value of regional traffic early warning; wherein the traffic pressure classification includes an inflow pressure and an internal pressure; the pressure threshold values are provided in a plurality of sets.
Optionally, obtaining congestion information of the special area according to the pressure threshold, and confirming and marking the congestion information, and generating marking data includes: according to the pressure alarm of the pressure threshold value, acquiring the real-time congestion condition of the area and giving an alarm, manually confirming the real-time congestion condition, marking a correct sensing result, and generating marking data; wherein, the manual confirmation is carried out in real time or off-line confirmation through monitoring and traffic index comparison.
Further, optionally, training a congestion prediction model according to the label data and the traffic data, and performing early warning on the traffic condition in the special area through the congestion prediction model includes: sequencing the key traffic detector data in the target path according to time, processing the data to obtain a traffic state index of the target path, and associating a congestion tag marking the data; inputting a neural network time sequence model for training to obtain a time sequence congestion early warning model; adjusting the time series prediction result obtained through the test set by using a state estimation algorithm, and training to obtain a congestion prediction model of the special area; and early warning is carried out on the traffic condition of the special area according to the congestion prediction model.
In a second aspect, the present invention provides a traffic warning device, including: the establishing module is used for marking the special area and establishing a road network topological graph corresponding to the special area; the acquisition module is used for associating the urban road network model and acquiring traffic data of the regional road network model in the road network topological graph; the screening module is used for constructing a path library, analyzing the path correlation in a special area by combining traffic data and screening a key traffic detector; the conversion module is used for converting the data acquired by the key traffic detector into the traffic flow space density and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density; the marking module is used for acquiring congestion information of the special area according to the pressure threshold, confirming and marking the congestion information and generating marking data; and the early warning module is used for training a congestion prediction model according to the marking data and the traffic data, and early warning the traffic condition of the special area through the congestion prediction model.
In a third aspect, the present invention provides a traffic early warning system, including: the marking module is used for marking the special area in a dividing way; the data acquisition module is used for acquiring the road network model of the key road section and traffic data; the data conversion module is used for carrying out conversion calculation on the acquired data; the key path monitoring module is used for monitoring the real-time overall traffic state of the key paths in the area and displaying the thermodynamic diagram based on the relevance weight; the real-time congestion sensing module is used for giving an alarm to a road network in a special area in real time and confirming the alarm condition manually; the congestion early warning module is used for inputting the real-time data into an offline model library to predict congestion and sending out an early warning signal;
wherein, the data conversion module includes: the length data conversion module is used for calculating an approximate value of the current queuing length for the sum of the length of the standard small car and the distance between heads of the small car, and comparing the result with the length of the road section to obtain the first traffic flow space density of the road section; and the speed data conversion module is used for comparing the time interval of two continuous vehicles passing through a fixed point with the free flow speed of the road section to obtain a distance interval, and comparing the distance interval with the length of the road section to obtain the second traffic flow space density of the road section.
The invention provides a traffic early warning method, a traffic early warning device and a traffic early warning system. Establishing a road network topological graph corresponding to the special area by marking the special area; associating the urban road network model, and collecting traffic data of a special area; constructing a path library, analyzing path correlation in a special area by combining traffic data, and screening a key traffic detector; converting data acquired by the key traffic detector into traffic flow space density, and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density; acquiring congestion information of a special area according to a pressure threshold, confirming and marking the congestion information, and generating marking data; according to the marked data and the traffic data, a congestion prediction model is trained, and the traffic condition of a special area is early warned through the congestion prediction model, so that the input sample size can be reduced, the training pressure is reduced, and the technical effect of overfitting is reduced on the premise of ensuring the model accuracy.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention and do not constitute a limitation of the invention. In the drawings:
fig. 1 is a schematic flow chart of a traffic warning method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a road network topology diagram in a traffic warning method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a traffic warning device according to a second embodiment of the present invention;
fig. 4 is a schematic diagram of a traffic early warning system according to a third embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first", "second", and the like in the description and claims of the present invention and the accompanying drawings are used for distinguishing different objects, and are not used for limiting a specific order.
It should be noted that the following embodiments of the present invention may be implemented individually, or may be implemented in combination with each other, and the embodiments of the present invention are not limited in this respect.
Example one
In a first aspect, an embodiment of the present invention provides a traffic early warning method, and fig. 1 is a schematic flow diagram of a traffic early warning method provided in an embodiment of the present invention; as shown in fig. 1, the traffic warning method provided in the embodiment of the present application includes:
step S101, marking a special area, and establishing a road network topological graph corresponding to the special area;
optionally, the step S101 of marking the special area and establishing the road network topological graph corresponding to the special area includes: marking a special area, wherein the special area is an area covered by a building or a facility with a traffic demand larger than a preset threshold value in a specific time period and a road facility in a preset adjacent range around the building or the facility; and screening the central nodes of the special area, setting intersections in the preset adjacent range of the central nodes as nodes, taking the nodes as centers, taking all associated road sections of the nodes as road sections close to the central nodes, and establishing a road network topological graph of the special area.
The specific areas in the embodiment of the present application include, but are not limited to: a mall, a school, a hospital, a scenic spot, wherein there may be multiple central nodes in the scenic spot;
it should be noted that, in the embodiment of the present application, a road network topological graph corresponding to a special area is established as shown in fig. 2, and fig. 2 is a schematic diagram of a road network topological graph in a traffic early warning method provided in an embodiment of the present invention. In order to meet the subsequent calculation requirements, the crossing screening range of the central building needs to include three layers of crossings.
Step S102, associating the urban road network model and collecting traffic data of a special area;
specifically, the step S102 of associating the urban road network model and collecting the traffic data of the special area includes: the method comprises the steps of collecting traffic data of a regional road network model in a road network topological graph according to a traffic detector of each road section by associating with an urban road network model, wherein the traffic data comprises the following steps: data of regional network models and traffic detector data.
The data of the regional road network model may include: road, road segment, intersection, lane data; the traffic detector data includes: flow, occupancy, headway, and queue length data;
in the embodiment of the application, traffic data in the regional road network model is collected through traffic detectors such as geomagnetism and checkpoints, the traffic detectors detect information and passing conditions of vehicles by taking the vehicles as detection targets, and simultaneously calculate or count various traffic parameters such as flow, occupancy, headway, queuing length and the like, and the traffic detectors are used for providing multi-dimensional traffic information for a control system so as to perform signal control.
Wherein, the flow rate is the number of vehicles passing through the detector in unit time;
the occupancy comprises a time occupancy and a space occupancy, wherein the time occupancy refers to the time occupancy on any road section of the road, and the ratio of the accumulated value of the vehicle passing time to the total observation time is called the time occupancy; is calculated by the formula
The space occupancy is that on a certain road section of a road, the ratio of the total length of a vehicle to the total length of the road section is called the space occupancy, and is usually expressed in percentage, and the calculation formula is as follows:
wherein, R is the occupancy, L is the road segment length, and T is the accumulated value of the vehicle passing time;
the headway is the time interval between two continuous vehicles passing through a fixed point in the traffic flow;
the queuing length is the length of the traffic flow waiting for the intersection to pass;
in the relationship between the flow rate and the occupancy, when the flow rate is small, the occupancy is small or large. The flow is small, the occupancy rate is small, the traffic pressure of the road section is low, and vehicles can smoothly pass through the road section; the traffic is small, the occupancy rate is large, the situation that the traffic jam exists in the road section is shown, the number of the passing vehicles is small, the situation that the vehicles stay in the detection area of the detector for a long time can also exist, and the staff on duty can be conveniently reminded to timely handle the traffic.
Step S103, constructing a path library, analyzing the path correlation in a special area by combining traffic data, and screening a key traffic detector;
optionally, constructing a path library in step S103, analyzing the path correlation in the special area in combination with the traffic data, and screening the key traffic detector includes: screening passing vehicles around the central node based on historical traffic detector data, tracking vehicle tracks, reversely deducing driving paths of the vehicles in the special area, and constructing a path library; on the basis of historical traffic data, flow data of the paths in a specified period are counted to obtain flow characteristics of each path; counting flow data flowing into the central node in a specified period based on real-time traffic data to obtain the flow characteristics of the central node; judging the correlation between the path and the central node according to the correlation coefficient of the flow characteristics of the path and the flow characteristics of the central node, and screening a target path according to the correlation; and considering the influence of the path flow on the regional congestion for the target paths corresponding to the correlations according to the weights corresponding to the target paths, and selecting the traffic detector installed on the flow direction in the road section as the key traffic detector according to the flow direction on the paths.
Further, optionally, the traffic warning method provided in the embodiment of the present application further includes: and for the road section lacking the bayonet device in the path, searching the shortest path by adopting a path searching algorithm and completing the path.
Optionally, the traffic early warning method provided in the embodiment of the present application further includes: and according to the similarity between the historical path data and the real-time data of the central building, obtaining a path flow model from the historical data, and identifying a target path.
Specifically, based on historical checkpoint detector data, vehicles passing around a central building are screened, vehicle tracks are tracked, and driving paths of the vehicles in a special area are reversely deduced. Screening vehicles passing around a central building requires that the screening vehicle pass the nearest gate of the central building and do not pass the next detector for a certain period of time. And associating the gate detector equipment with the road network, arranging the gate data of each vehicle in a reverse order, and judging whether the gates corresponding to the data adjacent in time belong to the connected road sections in space. If the road sections belong to the connected road sections, the road sections are counted into a path; otherwise, the shortest path between two checkpoints at adjacent time is searched by using Dijkstra, floyd and other algorithms (i.e., the path search algorithm in the embodiment of the present application), and path completion is performed. And integrating the paths obtained by data aggregation to generate a path library in the special area.
The historical data is aggregated according to paths with certain granularity, and the data of a certain time window before the time needing congestion identification is taken as the historical flow characteristics of different paths at the current time. Meanwhile, data before the same moment of a central building surrounding detector is acquired according to the same aggregation granularity and a time window and aggregated into a central building flow characteristic, wherein the central building surrounding detector refers to a detector on a road section where traffic pressure directly flows into the central building, and is usually a detector on a circle of road sections surrounding the building. And judging the relevance of the route and the traffic condition of the central building according to the correlation coefficient of the route flow characteristics and the central building flow, and dynamically screening the target route according to the relevance. The use of the time window to select portions of the data allows for the use of data that is close to the time of day to better characterize the traffic characteristics at that time of day.
For target paths with different correlations, the influence of different path flows on regional congestion at different degrees is considered by taking the correlation coefficient as a weight. And selecting traffic detectors arranged on the road sections in the flow direction as key traffic detectors on the path according to the flow direction, and calculating the traffic indexes of the path.
In the embodiment of the present application, the flow correlation is calculated as follows:
and aggregating the historical data of 3 months according to the paths with the granularity of 10 minutes, and sequencing according to the time sequence to obtain the historical flow characteristics of each path within one day. Selecting a time T required to be subjected to congestion identification, such as 15: taking 1 hour time window data before T time, namely 14: 10-15: the historical flow rate characteristic between 10 is denoted as X as the historical flow rate change characteristic at that point in time. Meanwhile, real-time data are aggregated according to the granularity of 10 minutes, and the same time window data are taken as the current flow characteristic of the central building and are recorded as Y. The correlation was calculated for X and Y.
In the embodiment of the application, after the abnormal outlier is removed by filtering in consideration of the nonlinearity and the continuity of the data, a Pearson correlation coefficient calculation method is adopted,
wherein cov (X, Y) is the covariance of X and Y,σ X standard deviation of X, σ Y And is the standard deviation of Y. The correlation coefficient is between-1 and 1, and in the embodiment, setting a coefficient less than 0 as 0 indicates that the path flow characteristic does not conform to the center building flow characteristic, and the possibility of transmitting traffic pressure to the center building is low.
In the embodiment of the present application, the idea and process for searching the shortest path by using Dijkstra algorithm are as follows:
if a directed graph with N nodes and weights is given, firstly, an array D is set to store the shortest distance from the starting point to each node, and then a set T is defined to store all the nodes with the shortest paths from the found starting point to the node. Under the initial condition, the distance from the departure point to the departure point is 0, the distance between the departure point and the node connected with the departure point is a corresponding weight, the distance between the nodes without direct connection is defined as infinity (infinity), then the node with the minimum distance value from the departure point is selected, the point is added into the set T, the node with the minimum distance value from the departure point is taken as the departure point, the distance values from the departure point are updated in sequence, namely if the sum of the distance value from the point and the distance values from the point to other points is less than the distance value directly reached by the departure point, the value is used for replacing the directly reached value, otherwise, the process is repeated until the T contains all the nodes in the graph, and the algorithm is ended;
in the embodiment of the present application, the idea and process for searching the shortest path by using the Floyd algorithm are as follows:
assuming that there is a directed or undirected graph with N nodes, the Floyd algorithm needs to define two N × N matrices, denoted as D and P, where the element a [ i ] [ j ] in the D matrix represents the distance from vertex i to vertex j, and the element b [ i ] [ j ] in the P matrix represents the vertex passing through the middle of vertex j from vertex i. In an initial state; the matrix D represents the distance from each vertex to each other vertex, usually weighted in a computer, and if there is no direct connection between two points, the distance value is ∞, while the P matrix is initially the j values of all b [ i ] [ j ] elements. Recording the updating times as K (N times of updating is needed), if (a [ i ] [ K-1] + a [ K-1] [ j ]) < a [ i ] [ j ], replacing the value of the latter with the former value, and simultaneously updating b [ i ] [ j ] = b [ i ] [ K-1] in the P matrix in sequence until the updating times are N, ending the algorithm, and combining the D matrix and the P matrix to obtain the shortest paths from any node to all other nodes;
in the embodiment of the application, through counting the vehicle driving paths with the travel end points as the central building, a passing path library from different nodes to the central building can be constructed, and paths with high correlation between the flow around the central building and the historical flow of the paths are screened to obtain important paths in a special area.
Based on a gate detector, a passing path between a node and a central building is established, and for a road section lacking a gate, dijkstra and a Floyd algorithm (namely, a path search algorithm in the embodiment of the application) are adopted to search a shortest path, so that a passing path library is established. And marking the traffic flow direction on the path at each node to obtain a key lane on the path. And the key detectors needing important attention are obtained by the lane-level traffic detectors arranged in relation to the key lanes.
In the embodiment of the application, the detectors needing to pay attention to screening are used for eliminating the influence of irrelevant traffic flows on congestion perception of a special area, traffic flows in different flow directions are included in a road section with high correlation, and traffic pressure which is most likely to flow into a central building can be obtained according to the detectors needing to pay attention to screening, so that accurate pressure analysis is achieved.
Step S104, converting data collected by the key traffic detector into traffic flow space density, and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density;
optionally, the step S104 of converting the data collected by the key traffic detector into the traffic flow spatial density includes: calculating an approximate value of the current queuing length according to the sum of the length of the standard small car and the distance between the heads by using the flow or the distance between the heads, and comparing the approximate value of the current queuing length with the length of the road section to obtain the first traffic flow space density of the road section; using the headway or the queue length, multiplying the time interval acquired by two continuous vehicles through a key traffic detector in a fixed point by the road section free flow speed to obtain a distance interval, and comparing the distance interval with the road section length to obtain a second traffic flow space density of the road section; and normalizing the first traffic flow space density and the second traffic flow space density, and performing weighted average on the data after normalization to obtain the target traffic flow space density of the road section.
Further, optionally, the setting of the pressure threshold of the regional traffic warning according to the spatial density of the traffic flow includes: classifying traffic pressure according to the spatial density of the traffic flow, and setting a pressure threshold value of regional traffic early warning; wherein the traffic pressure classification includes an inflow pressure and an internal pressure; the pressure threshold values are provided in a plurality of sets.
Specifically, when the traffic flow space density of a road segment transmitting the traffic flow to the area on the node reaches the quantile threshold value, the traffic condition in the area is about to be affected, the traffic flow space density is inflow pressure, and the traffic flow space density of a road segment adjacent to the building reaches the threshold value, which indicates that the traffic pressure around the building is large, and the traffic pressure is internal pressure.
In the embodiment of the application, the pressure threshold is provided with a plurality of groups of levels, different alarm levels correspond to the condition that a certain node or a plurality of nodes in a special area are congested, and the alarm levels can be divided into multiple levels such as smooth, slow running, congestion and severe congestion according to actual conditions.
In the embodiment of the application, the pressure threshold value of the pressure alarm is obtained by counting historical traffic laws on the basis of lane-level data and an intersection facility model to obtain historical traffic density data sets of different road sections, a group of quantiles is selected to distinguish congestion and unblocked conditions of the road sections, the traffic conditions of different road sections are different, the quantiles are used as the pressure threshold value to obtain early warning standards according to the historical traffic laws of the road sections in a targeted manner, meanwhile, the adjustment of the quantiles can be adjusted according to regulation manpower and actual alarm requirements, when the quantile value is set to be large, the number of problem areas is small, but the traffic problems which need to be solved urgently exist generally; when the quantile value is reduced, the number of the problem areas is increased, the global traffic condition can be observed, and the design can be flexibly adjusted according to the actual condition.
It should be noted that, in the embodiment of the present application, the alarm sensitivity may be adjusted according to the user requirement, and for a scene with a high sensitivity requirement, an alarm is performed as long as 1 threshold is reached, and for a scene with a low requirement, a situation that both the inflow pressure and the pressure corresponding to the internal pressure are satisfied needs to be reached. Specifically, the above example is only a preferred example of the traffic warning method provided in the embodiment of the present application, and is not limited specifically to the implementation of the traffic warning method provided in the embodiment of the present application. Step S105, acquiring congestion information of the special area according to the pressure threshold, confirming and marking the congestion information, and generating marking data;
optionally, in step S105, obtaining congestion information of the special area according to the pressure threshold, and confirming and marking the congestion information, and generating marking data includes: according to the pressure alarm of the pressure threshold value, acquiring the real-time congestion condition of the area and giving an alarm, manually confirming the real-time congestion condition, marking a correct sensing result, and generating marking data; wherein, the manual confirmation is carried out in real time or off-line confirmation through monitoring and traffic index comparison.
Specifically, based on the correlation coefficient weight in S103, a weight threshold between 0 and 1 is defined according to the congestion alarm service demand, and a target route meeting the weight requirement is considered to be relatively similar to the central building traffic characteristic at the current time when congestion identification needs to be performed, and the possibility that the route transmits traffic pressure to the central building is relatively high. When the space density of the road traffic flow on the path reaches the early warning threshold value, the path inputs more flow to the area, the traffic condition in the area is about to be influenced, congestion alarm can be carried out for inflow pressure, peripheral traffic flow and the traffic flow of the outflow area are dredged, personnel can be guided to locate specific problems during signal timing, measures such as increasing downstream release force can be matched, and the traffic pressure is quickly relieved. Meanwhile, the target path is considered integrally, and priority early warning is carried out on the areas with the congestion of a plurality of paths.
In the embodiment of the application, the step of manually confirming and marking the sensing result is to monitor the regional traffic parameters in real time, record the alarm condition meeting the pressure threshold value to obtain the real-time congestion alarm, confirm the data alarm by manually observing intersection monitoring and other methods, and further obtain the congestion alarm accuracy label.
And S106, training a congestion prediction model according to the marking data and the traffic data, and early warning the traffic condition of the special area through the congestion prediction model.
Optionally, the training of the congestion prediction model in step S106 according to the label data and the traffic data, and the early warning of the traffic condition in the special area by using the congestion prediction model includes: sequencing the key traffic detector data in the target path according to time, processing the data to obtain a traffic state index of the target path, and associating a congestion tag marking the data; inputting a neural network time sequence model for training to obtain a time sequence congestion early warning model; adjusting the time series prediction result obtained through the test set by using a state estimation algorithm, and training to obtain a congestion prediction model of the special area; and early warning is carried out on the traffic condition of the special area according to the congestion prediction model.
Specifically, since the number of links included in different paths is different and the number of key detectors in different links on a path is different, it is necessary to perform aggregate calculation on the detector data, calculate the flow sum, the average occupancy, the average traffic flow spatial density, and other indexes in units of links, and calculate the average traffic index value in units of paths as the index of the path. The path index data are sequentially input according to time sequence, a special area congestion model is constructed, congestion labels are marked, a neural network time sequence model such as LSTM, RNN and GRU is used for carrying out circular calculation to obtain threshold values of various data of the traffic monitor before congestion occurs, and the threshold values are recorded on the labels to obtain the congestion prediction labels of the special area. And adjusting the time sequence prediction result obtained through the test set by using a state estimation method such as a Kalman time update equation, a least square method and the like to obtain a hybrid model prediction result.
In the embodiment of the application, the key detector data on the key path is used for learning and training, the detector with small influence on the regional traffic condition is eliminated, the input sample size can be reduced, the training pressure is reduced, and overfitting is reduced on the premise of ensuring the model precision.
In the embodiment of the application, the time sequence model is a time sequence model obtained by reading the variable of traffic flow data monitored in the traffic detector at each moment according to a time sequence at a series of moments and integrating the acquired discrete data;
in the embodiment of the application, the segmentation data set belongs to the prior art in an AI training learning system, and comprises the steps of splitting the acquired data set into a test set and a training set, and testing and training samples, wherein the split test set and the split training set are mutually exclusive, namely the test samples are not present in the training set as much as possible and are not used in the training set, so as to ensure the early warning accuracy of the time sequence congestion early warning model;
in the embodiment of the application, in predicting the hybrid model according to the kalman time update equation, setting X (k) as the system state at the time k, U (k) as the control quantity of the system at the time k, a and B as the system parameters, a as the traffic flow space density change parameter, B as the traffic flow control quantity parameter, they are matrices for the hybrid model, Z (k) as the measurement value at the time k, H as the parameter of the measurement system, W (k) and V (k) respectively represent the process and the measured noise, covariance is respectively represented by Q and R, and setting Q and R not to change with the system state, introducing a set of linear random differential equations:
X(k)＝AX(k-1)+BU(k)+W(k)
system measurement Z (k) = HX (k) + V (k);
firstly, predicting the next state according to a process model of the system; setting the system state at a certain moment as k, and predicting the state at the certain moment according to the last state of the system model:
X(k|k-1)＝AX(k-1|k-1)+BU(k) (1)
x (k | k-1) is the result predicted using the previous state, X (k-1) is the optimal result for the previous state, U (k) is the controlled variable of the state at a certain moment, if there is no controlled variable, it may be 0;
until some point, the system results have been updated, however, the covariance corresponding to X (k | k-1) has not been updated, denoted by P;
P(k|k-1)＝AP(k-1|k-1)+A'+Q (2)
p (k | k-1) is covariance corresponding to X (k | k-1), A' represents a transposed matrix of A, Q is covariance of a system process, and the comprehensive calculation formulas (1) and (2) can obtain a result predicted by the hybrid model according to X (k | k-1) and compare the result with a preset threshold, if the calculation result exceeds the threshold, congestion occurs in the next period of the prediction result, and a predicted congestion alarm is sent out at the moment.
The traffic early warning method provided by the embodiment of the application can be used for monitoring the traffic flow space density data of the peripheral road sections in real time by taking the special area as a center, quickly determining the type of traffic pressure and the problem road sections when congestion occurs, realizing timely congestion sensing when the traffic flow space density is too high, quickly processing and dredging the problem road sections, and ensuring that the traffic around the special area is smooth. And the congestion perception threshold around the special area can be automatically adjusted, the observation and the control of the global traffic condition are facilitated, the traffic congestion can be timely calculated and early warned through the data of the traffic detector, the signal timing and personnel positioning processing can be guided in advance, measures such as increasing downstream release force can be matched, and the traffic pressure can be integrally and quickly relieved. Real-time data input is adopted, real-time alarming can be achieved for a road network in a special area, congestion can be predicted in advance according to data matching and calculation of real-time data and an off-line model base, a command center can conveniently master traffic conditions in the special area in real time, response and command are carried out in advance, traffic dispersion is carried out on congestion points, congestion is reduced, and smooth traffic is guaranteed. And in the time series prediction model, a certain error may exist between the prediction series and the real time series. By carrying out secondary estimation and optimization on sequences with errors and carrying out dynamic adjustment on predicted sequences again, the prediction precision can be improved.
The embodiment of the invention provides a traffic early warning method. Establishing a road network topological graph corresponding to the special area by marking the special area; associating the urban road network model, and acquiring traffic data of a special area; constructing a path library, analyzing the path correlation in the special area by combining traffic data, and screening a key traffic detector; converting data acquired by the key traffic detector into traffic flow space density, and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density; acquiring congestion information of a special area according to a pressure threshold, confirming and marking the congestion information, and generating marking data; according to the labeled data and the traffic data, a congestion prediction model is trained, and the traffic condition of a special area is early warned through the congestion prediction model, so that the input sample amount is reduced, the training pressure is reduced, and the technical effect of overfitting is reduced on the premise of ensuring the model accuracy.
Example two
In a second aspect, an embodiment of the present invention provides a traffic warning device, and fig. 3 is a schematic diagram of the traffic warning device provided in the second embodiment of the present invention; as shown in fig. 3, the traffic early warning device provided in the embodiment of the present application includes: the establishing module 31 is used for marking the special area and establishing a road network topological graph corresponding to the special area; the acquisition module 32 is used for associating the urban road network model and acquiring traffic data of a special area; the screening module 33 is used for screening the key traffic detectors by constructing a path library and analyzing the path correlation in the special area by combining the traffic data; the conversion module 34 is used for converting the data acquired by the key traffic detector into the traffic flow space density and setting a pressure threshold value of the regional traffic early warning according to the traffic flow space density; the marking module 35 is configured to obtain congestion information of the special area according to the pressure threshold, confirm and mark the congestion information, and generate marking data; and the early warning module 36 is configured to train a congestion prediction model according to the tag data and the traffic data, and perform early warning on the traffic condition of the special area through the congestion prediction model.
The embodiment of the invention provides a traffic early warning device. Establishing a road network topological graph corresponding to the special area by marking the special area; associating the urban road network model, and acquiring traffic data of a special area; constructing a path library, analyzing path correlation in a special area by combining traffic data, and screening a key traffic detector; converting data acquired by the key traffic detector into traffic flow space density, and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density; acquiring congestion information of a special area according to a pressure threshold, confirming and marking the congestion information, and generating marking data; according to the labeled data and the traffic data, a congestion prediction model is trained, and the traffic condition of a special area is early warned through the congestion prediction model, so that the input sample amount is reduced, the training pressure is reduced, and the technical effect of overfitting is reduced on the premise of ensuring the model accuracy.
EXAMPLE III
In a third aspect, an embodiment of the present invention provides a traffic early warning system, and fig. 4 is a schematic diagram of a traffic early warning system provided in a third embodiment of the present invention; as shown in fig. 4, the traffic early warning system provided in the embodiment of the present application includes: a marking module 41, configured to mark the special area by division; the data acquisition module 42 is used for acquiring a road network model of the key road section and traffic data; the data conversion module 43 is used for performing conversion calculation on the acquired data; the key path monitoring module 44 is used for monitoring the real-time overall traffic state of the key paths in the area and displaying thermodynamic diagrams based on the relevance weights; the real-time congestion sensing module 45 is used for giving an alarm to a road network in a special area in real time and confirming the alarm condition manually; and the congestion early warning module 46 is used for inputting the real-time data into the offline model library to predict congestion and sending out an early warning signal.
Optionally, the data conversion module 43 includes: the length data conversion module is used for calculating an approximate value of the current queuing length according to the sum of the length of the standard compact car and the distance between heads of the compact car, and comparing the result with the length of the road section to obtain the first traffic flow space density of the road section; and the speed data conversion module is used for comparing the time interval of two continuous vehicles passing through the fixed point with the road section free flow speed to obtain a distance interval, and comparing the distance interval with the road section length to obtain a second traffic flow space density of the road section.
Specifically, as shown in fig. 4, the marking module 41 is marked as a marking module, the data acquisition module 42 is marked as a data acquisition module, the data conversion module 43 is marked as a data conversion module, the key path monitoring module 44 is marked as a key path monitoring module, the real-time congestion sensing module 45 is marked as a real-time congestion sensing module, and the congestion early warning module 46 is marked as a congestion early warning module.
The traffic early warning system provided by the embodiment of the application confirms a special area at first, searches for a shortest path and divides an area key road section by taking the special area as a center, then further acquires data of roads, road sections, intersections, lanes, flow, occupancy, headway and queuing length, then calculates and integrates the data, obtains the integral traffic flow space density of the road section through normalization processing and weighted average, and then matches the data with traffic parameters in a traffic detector, wherein when the traffic flow space density of the road section which transmits traffic flow to the area on a node reaches an early warning threshold value, the upstream road section inputs more flow to the area, influences the traffic condition in the area are about to be caused, and early warning can be carried out for leading out peripheral traffic flow in advance for inflow pressure;
real-time data input is adopted, real-time alarm can be realized for a road network in a special area, congestion can be predicted in advance according to the real-time data and the data matching and calculation of an offline model base, a command center can conveniently make response and command in advance, traffic dispersion is carried out on congestion points in advance, the occurrence of congestion is greatly reduced, and the smoothness of traffic is guaranteed;
meanwhile, when the space density of the road traffic flow adjacent to the special area reaches a threshold value, the traffic pressure around the special area is high, the traffic problem can be warned through a detector, signal timing personnel can be guided to locate the specific problem, measures such as increasing downstream release force can be matched, and the traffic pressure can be relieved quickly.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.
Claims (10)
1. A traffic early warning method is characterized by comprising the following steps:
marking a special area, and establishing a road network topological graph corresponding to the special area;
associating the urban road network model, and acquiring traffic data of the special area;
constructing a path library, analyzing the path correlation in the special area by combining the traffic data, and screening a key traffic detector;
converting data collected by the key traffic detector into traffic flow space density, and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density;
acquiring congestion information of the special area according to the pressure threshold, confirming and marking the congestion information, and generating marking data;
and training a congestion prediction model according to the marking data and the traffic data, and early warning the traffic condition of the special area through the congestion prediction model.
2. The traffic early warning method according to claim 1, wherein the marking of the special area and the establishing of the road network topological graph corresponding to the special area comprise:
marking the special area, wherein the special area is an area covered by buildings or facilities with traffic demands larger than a preset threshold value in a specific time period and road facilities in a preset adjacent range around the buildings or facilities;
and screening the central nodes of the special area, setting intersections in a preset adjacent range of the central nodes as nodes, taking the nodes as centers, taking all associated road sections of the nodes as road sections close to the central nodes, and establishing the road network topological graph of the special area.
3. The traffic early warning method according to claim 2, wherein the constructing a route library, analyzing the relevance of the route in the special area in combination with the traffic data, and screening a key traffic detector comprises:
screening passing vehicles around the central node based on historical traffic detector data, tracking vehicle tracks, reversely deducing driving paths of the vehicles in the special area, and constructing a path library;
on the basis of historical traffic data, flow data of the paths in a specified period are counted to obtain flow characteristics of each path; counting flow data flowing into the central node in a specified period based on real-time traffic data to obtain the flow characteristics of the central node;
judging the correlation between the path and the central node according to the correlation coefficient of the flow characteristics of the path and the flow characteristics of the central node, and screening a target path according to the correlation;
and considering the influence of the path flow on the regional congestion for the target paths corresponding to the correlations according to the weights corresponding to the target paths, and selecting the traffic detector installed on the flow direction in the road section as the key traffic detector according to the flow direction on the paths.
4. The traffic warning method according to claim 3, further comprising:
and for the road section lacking the bayonet device in the path, searching the shortest path by adopting a path searching algorithm and completing the path.
5. The traffic-warning method of claim 3, wherein converting the data collected by the critical traffic detector into a spatial density of traffic flow comprises:
calculating an approximate value of the current queuing length according to the sum of the length of the standard minicar and the distance between the heads by using the flow or the distance between the heads, and comparing the approximate value of the current queuing length with the length of the road section to obtain the first traffic flow space density of the road section;
multiplying the time interval acquired by the key traffic detector in the fixed point by the road section free flow speed by using the headway distance or the queue length to obtain a distance interval, and comparing the distance interval with the road section length to obtain a second traffic flow space density of the road section;
and carrying out normalization processing on the first traffic flow space density and the second traffic flow space density, and carrying out weighted average on data after normalization processing to obtain the target traffic flow space density of the road section.
6. The traffic early warning method according to claim 5, wherein the setting of the pressure threshold of the regional traffic early warning according to the spatial density of the traffic flow comprises:
classifying traffic pressure according to the traffic flow space density, and setting a pressure threshold value of the regional traffic early warning;
wherein the traffic pressure classification includes an inflow pressure and an internal pressure; the pressure threshold values are provided in a plurality of groups.
7. The traffic early warning method according to claim 6, wherein the acquiring congestion information of the special area according to the pressure threshold, and confirming and marking the congestion information, and the generating marking data comprises:
according to the pressure alarm of the pressure threshold value, acquiring a real-time congestion situation of an area, giving an alarm, manually confirming the real-time congestion situation, marking a correct sensing result, and generating marking data;
and the manual confirmation is carried out in real time or off-line confirmation through monitoring and traffic index comparison.
8. The traffic early warning method according to claim 7, wherein the training of a congestion prediction model according to the labeled data and the traffic data and the early warning of the traffic condition in the special area through the congestion prediction model comprises:
sequencing the key traffic detector data in the target path according to time, performing data processing to obtain a traffic state index of the target path, and associating a congestion tag of the marked data;
inputting a neural network time sequence model for training to obtain a time sequence congestion early warning model;
adjusting the time series prediction result obtained through the test set by using a state estimation algorithm, and training to obtain a congestion prediction model of the special area;
and early warning the traffic condition of the special area according to the congestion prediction model.
9. A traffic early warning device, comprising:
the system comprises an establishing module, a judging module and a judging module, wherein the establishing module is used for marking a special area and establishing a road network topological graph corresponding to the special area;
the acquisition module is used for associating the urban road network model and acquiring traffic data of the regional road network model in the road network topological graph;
the screening module is used for constructing a path library, analyzing the path correlation in the special area by combining the traffic data and screening a key traffic detector;
the conversion module is used for converting the data acquired by the key traffic detector into traffic flow space density and setting a pressure threshold value of regional traffic early warning according to the traffic flow space density;
the marking module is used for acquiring the congestion information of the special area according to the pressure threshold, confirming and marking the congestion information and generating marking data;
and the early warning module is used for training a congestion prediction model according to the marking data and the traffic data, and early warning the traffic condition of the special area through the congestion prediction model.
10. A traffic warning system, comprising:
the marking module is used for marking the special area in a dividing way;
the data acquisition module is used for acquiring the road network model of the key road section and traffic data;
the data conversion module is used for carrying out conversion calculation on the acquired data;
the key path monitoring module is used for monitoring the real-time overall traffic state of the key paths in the area and displaying the thermodynamic diagram based on the relevance weight;
the real-time congestion sensing module is used for giving an alarm to a road network in a special area in real time and confirming the alarm condition manually;
the congestion early warning module is used for inputting the real-time data into an offline model library to predict congestion and sending out an early warning signal;
wherein, the data conversion module comprises:
the length data conversion module is used for calculating an approximate value of the current queuing length according to the sum of the length of the standard compact car and the distance between heads of the compact car, and comparing the result with the length of the road section to obtain the first traffic flow space density of the road section;
and the speed data conversion module is used for comparing the time interval of two continuous vehicles passing through the fixed point with the road section free flow speed to obtain a distance interval, and comparing the distance interval with the road section length to obtain a second traffic flow space density of the road section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210770647.7A CN115331425B (en) | 2022-06-30 | 2022-06-30 | Traffic early warning method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210770647.7A CN115331425B (en) | 2022-06-30 | 2022-06-30 | Traffic early warning method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115331425A true CN115331425A (en) | 2022-11-11 |
| CN115331425B CN115331425B (en) | 2023-12-19 |
Family
ID=83917088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210770647.7A Active CN115331425B (en) | 2022-06-30 | 2022-06-30 | Traffic early warning method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115331425B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115809768A (en) * | 2022-11-16 | 2023-03-17 | 上海卓冶机电科技有限公司 | Smart city information resource display system and method |
| CN116386336A (en) * | 2023-05-29 | 2023-07-04 | 四川国蓝中天环境科技集团有限公司 | Road network traffic flow robust calculation method and system based on bayonet license plate data |
| CN116453333A (en) * | 2023-03-24 | 2023-07-18 | 阿波罗智联(北京)科技有限公司 | Method for predicting main traffic flow path and model training method |
| CN117576908A (en) * | 2023-11-21 | 2024-02-20 | 青岛格仑特新能源车辆制造有限公司 | Intelligent police vehicle-mounted control system and method based on Internet of things |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008217309A (en) * | 2007-03-02 | 2008-09-18 | Nec Corp | Flexible network system, and information collection apparatus and method using the same |
| JP2011039574A (en) * | 2009-08-06 | 2011-02-24 | Shouwa Dengiken Kk | System and method for distributing congestion state |
| US8566030B1 (en) * | 2011-05-03 | 2013-10-22 | University Of Southern California | Efficient K-nearest neighbor search in time-dependent spatial networks |
| CN103531024A (en) * | 2013-10-28 | 2014-01-22 | 武汉旭云科技有限公司 | Dynamic traffic network urban road feature model and modeling method thereof |
| CN105825677A (en) * | 2016-05-31 | 2016-08-03 | 武汉大学 | City traffic jam prediction method based on improved BML model |
| CN106846805A (en) * | 2017-03-06 | 2017-06-13 | 南京多伦科技股份有限公司 | A kind of dynamic road grid traffic needing forecasting method and its system |
| CN107610469A (en) * | 2017-10-13 | 2018-01-19 | 北京工业大学 | A kind of day dimension regional traffic index forecasting method for considering multifactor impact |
| US20180091981A1 (en) * | 2016-09-23 | 2018-03-29 | Board Of Trustees Of The University Of Arkansas | Smart vehicular hybrid network systems and applications of same |
| CN111553539A (en) * | 2020-05-09 | 2020-08-18 | 上海大学 | Driving path planning method based on probabilistic model inspection |
| CN111932036A (en) * | 2020-09-23 | 2020-11-13 | 中国科学院地理科学与资源研究所 | Fine spatio-temporal scale dynamic population prediction method and system based on position big data |
| CN112365708A (en) * | 2020-09-29 | 2021-02-12 | 西北大学 | Scenic spot traffic volume prediction model establishing and predicting method based on multi-graph convolution network |
| CN112950940A (en) * | 2021-02-08 | 2021-06-11 | 中冶南方城市建设工程技术有限公司 | Traffic diversion method in road construction period |
| CN113034913A (en) * | 2021-03-22 | 2021-06-25 | 平安国际智慧城市科技股份有限公司 | Traffic congestion prediction method, device, equipment and storage medium |
| DE102020202342A1 (en) * | 2020-02-24 | 2021-08-26 | Zf Friedrichshafen Ag | Cloud platform for automated mobility and computer-implemented method for providing cloud-based data enrichment for automated mobility |
| CN114202917A (en) * | 2021-12-02 | 2022-03-18 | 安徽庐峰交通科技有限公司 | Construction area traffic control and induction method based on dynamic traffic flow short-time prediction |
| CN114495489A (en) * | 2021-12-30 | 2022-05-13 | 中智行(上海)交通科技有限公司 | Method for generating topological connection relation of road junction lanes |
-
2022
- 2022-06-30 CN CN202210770647.7A patent/CN115331425B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008217309A (en) * | 2007-03-02 | 2008-09-18 | Nec Corp | Flexible network system, and information collection apparatus and method using the same |
| JP2011039574A (en) * | 2009-08-06 | 2011-02-24 | Shouwa Dengiken Kk | System and method for distributing congestion state |
| US8566030B1 (en) * | 2011-05-03 | 2013-10-22 | University Of Southern California | Efficient K-nearest neighbor search in time-dependent spatial networks |
| CN103531024A (en) * | 2013-10-28 | 2014-01-22 | 武汉旭云科技有限公司 | Dynamic traffic network urban road feature model and modeling method thereof |
| CN105825677A (en) * | 2016-05-31 | 2016-08-03 | 武汉大学 | City traffic jam prediction method based on improved BML model |
| US20180091981A1 (en) * | 2016-09-23 | 2018-03-29 | Board Of Trustees Of The University Of Arkansas | Smart vehicular hybrid network systems and applications of same |
| CN106846805A (en) * | 2017-03-06 | 2017-06-13 | 南京多伦科技股份有限公司 | A kind of dynamic road grid traffic needing forecasting method and its system |
| CN107610469A (en) * | 2017-10-13 | 2018-01-19 | 北京工业大学 | A kind of day dimension regional traffic index forecasting method for considering multifactor impact |
| DE102020202342A1 (en) * | 2020-02-24 | 2021-08-26 | Zf Friedrichshafen Ag | Cloud platform for automated mobility and computer-implemented method for providing cloud-based data enrichment for automated mobility |
| CN111553539A (en) * | 2020-05-09 | 2020-08-18 | 上海大学 | Driving path planning method based on probabilistic model inspection |
| CN111932036A (en) * | 2020-09-23 | 2020-11-13 | 中国科学院地理科学与资源研究所 | Fine spatio-temporal scale dynamic population prediction method and system based on position big data |
| CN112365708A (en) * | 2020-09-29 | 2021-02-12 | 西北大学 | Scenic spot traffic volume prediction model establishing and predicting method based on multi-graph convolution network |
| CN112950940A (en) * | 2021-02-08 | 2021-06-11 | 中冶南方城市建设工程技术有限公司 | Traffic diversion method in road construction period |
| CN113034913A (en) * | 2021-03-22 | 2021-06-25 | 平安国际智慧城市科技股份有限公司 | Traffic congestion prediction method, device, equipment and storage medium |
| CN114202917A (en) * | 2021-12-02 | 2022-03-18 | 安徽庐峰交通科技有限公司 | Construction area traffic control and induction method based on dynamic traffic flow short-time prediction |
| CN114495489A (en) * | 2021-12-30 | 2022-05-13 | 中智行(上海)交通科技有限公司 | Method for generating topological connection relation of road junction lanes |
Non-Patent Citations (2)
| Title |
|---|
| 刘宜成等: "基于DTW算法的时空图卷积路网交通流量预测研究", pages 1 - 17 * |
| 谭健妹;刘清君;邹小梅;: "基于GIS的交通事故信息***研究", 山西科技, no. 01 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115809768A (en) * | 2022-11-16 | 2023-03-17 | 上海卓冶机电科技有限公司 | Smart city information resource display system and method |
| CN116703122A (en) * | 2022-11-16 | 2023-09-05 | 上海卓冶机电科技有限公司 | Smart city information resource display system and method |
| CN115809768B (en) * | 2022-11-16 | 2023-09-29 | 大同市规划设计研究总院有限责任公司 | Smart city information resource display system and method |
| CN116703122B (en) * | 2022-11-16 | 2024-01-19 | 上海张江智荟科技有限公司 | Smart city information resource display system and method |
| CN116453333A (en) * | 2023-03-24 | 2023-07-18 | 阿波罗智联(北京)科技有限公司 | Method for predicting main traffic flow path and model training method |
| CN116453333B (en) * | 2023-03-24 | 2024-04-16 | 阿波罗智联(北京)科技有限公司 | Method for predicting main traffic flow path and model training method |
| CN116386336A (en) * | 2023-05-29 | 2023-07-04 | 四川国蓝中天环境科技集团有限公司 | Road network traffic flow robust calculation method and system based on bayonet license plate data |
| CN116386336B (en) * | 2023-05-29 | 2023-08-08 | 四川国蓝中天环境科技集团有限公司 | Road network traffic flow robust calculation method and system based on bayonet license plate data |
| CN117576908A (en) * | 2023-11-21 | 2024-02-20 | 青岛格仑特新能源车辆制造有限公司 | Intelligent police vehicle-mounted control system and method based on Internet of things |
| CN117576908B (en) * | 2023-11-21 | 2024-04-26 | 青岛格仑特新能源车辆制造有限公司 | Intelligent police vehicle-mounted control system and method based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115331425B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115331425B (en) | Traffic early warning method, device and system | |
| CN109544932B (en) | Urban road network flow estimation method based on fusion of taxi GPS data and gate data | |
| WO2022247677A1 (en) | Urban-region road network vehicle-passage flow prediction method and system based on hybrid deep learning model | |
| CN108269401B (en) | Data-driven viaduct traffic jam prediction method | |
| Innamaa | Short-term prediction of travel time using neural networks on an interurban highway | |
| Kim et al. | Diagnosis and prediction of traffic congestion on urban road networks using Bayesian networks | |
| Li et al. | Identifying important variables for predicting travel time of freeway with non-recurrent congestion with neural networks | |
| CN110176139A (en) | A kind of congestion in road identification method for visualizing based on DBSCAN+ | |
| CN108091132B (en) | Traffic flow prediction method and device | |
| Carli et al. | Automated evaluation of urban traffic congestion using bus as a probe | |
| CN107146409B (en) | The identification of equipment detection time exception and true time difference evaluation method in road network | |
| CN112669594A (en) | Method, device, equipment and storage medium for predicting traffic road conditions | |
| Habtie et al. | Artificial neural network based real-time urban road traffic state estimation framework | |
| EP4060642A1 (en) | Method and system of predictive traffic flow and of traffic light control | |
| CN117935561B (en) | Intelligent traffic flow analysis method based on Beidou data | |
| Vanajakshi | Estimation and prediction of travel time from loop detector data for intelligent transportation systems applications | |
| Liu et al. | Developments and applications of simulation-based online travel time prediction system: traveling to Ocean City, Maryland | |
| Wang et al. | Short-term travel time estimation and prediction for long freeway corridor using NN and regression | |
| Farid et al. | Estimation of short-term bus travel time by using low-resolution automated vehicle location data | |
| CN116597649B (en) | Road network traffic flow deduction method based on expressway charging system | |
| Lusiandro et al. | Implementation of the advanced traffic management system using k-nearest neighbor algorithm | |
| Wu | Measuring reliability in dynamic and stochastic transportation networks | |
| CN112199454A (en) | Directed graph-based method and device for setting interception points of control vehicles | |
| Fahs et al. | Traffic congestion prediction based on multivariate modelling and neural networks regressions | |
| CN109448379A (en) | A kind of identification of sporadic traffic events of social media data and localization method |
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 |