CN115691164A - Intelligent traffic management method and system based on big data - Google Patents
Intelligent traffic management method and system based on big data Download PDFInfo
- Publication number
- CN115691164A CN115691164A CN202211188349.3A CN202211188349A CN115691164A CN 115691164 A CN115691164 A CN 115691164A CN 202211188349 A CN202211188349 A CN 202211188349A CN 115691164 A CN115691164 A CN 115691164A
- Authority
- CN
- China
- Prior art keywords
- time
- traffic flow
- traffic
- data
- flow data
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 55
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 51
- 230000008569 process Effects 0.000 claims abstract description 20
- 210000002569 neuron Anatomy 0.000 claims description 28
- 230000007613 environmental effect Effects 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000002123 temporal effect Effects 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000011217 control strategy Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000011084 recovery Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 13
- 238000004891 communication Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 238000010219 correlation analysis Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005311 autocorrelation function Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides an intelligent traffic management method and system based on big data, which can dynamically allocate vehicles at intersections in a target area by analyzing the spatial correlation and the time correlation of traffic flow data of the target area based on the analysis result of the spatial correlation and the time correlation, reduce the traffic pressure at the intersections, improve the traffic environment of the target area, improve the vehicle traffic efficiency of the target area, effectively dredge the possibly-occurring congestion areas at upstream intersections in the target area and downstream intersections in the target area, and accelerate the relief of the congestion areas. And the missing traffic flow data can be repaired, so that the analysis result of the method is more accurate. Meanwhile, the method and the device can allocate the driving relation between the vehicle and the passenger in the target area, improve the passenger searching efficiency of the vehicles such as the network taxi appointment and the taxi and reduce the waiting time of the passenger in the riding process; the number of vehicles borne by the road can be reasonably distributed, and traffic pressure is reduced.
Description
Technical Field
The invention relates to the technical field of traffic management control, in particular to an intelligent traffic management method and system based on big data.
Background
At present, with the gradual improvement of the living standard of people, automobiles become indispensable transportation tools in people's lives, the number of automobiles is increased dramatically, with the increase of automobile holding capacity in cities, the roads in the cities are more and more congested, and the problem of urban traffic congestion is also one of important problems which puzzle people to go out. The intelligent traffic is a high and new IT technology integrated with the Internet of things, cloud computing, big data, mobile internet and the like, and traffic information is collected through the high and new technology to provide traffic information service under real-time traffic data. The urban road traffic can be timely, accurately and efficiently managed through the intelligent traffic management system based on the big data, the bearing capacity of the road traffic is improved, and the traffic management efficiency is improved.
At present, the number of roads and vehicles running on the roads is increased, so that huge traffic data is formed. However, a technical solution for performing statistical analysis on the traffic data is lacking at present, so that the traffic data is not fully utilized, and the effect of intelligent traffic management cannot be achieved.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide an intelligent traffic management method and system based on big data, which is used to solve the problem that the prior art cannot sufficiently analyze traffic data.
To achieve the above and other related objects, the present invention provides a smart traffic management method based on big data, the method comprising the steps of:
acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, wherein the target area comprises a traffic road area determined in advance or in real time;
calculating the spatial correlation and the time correlation of the traffic flow data, and performing intelligent traffic management on the upstream intersection and the downstream intersection based on the spatial correlation and the time correlation;
wherein the calculation process of the spatial correlation of the traffic flow data comprises the following steps:
processing the traffic flow data into a traffic flow time sequence with the same time interval, and marking the traffic flow time sequence of an upstream crossing as q i And the time sequence of the traffic flow at the downstream intersection is marked as q j ；
Calculating the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j Cross correlation coefficient C of ij As the spatial correlation of the traffic flow data, there are:
in the formula, D (q) i ) Time sequence q of traffic flow for upstream crossing i The variance of (a);
D(q j ) Time sequence q of traffic flow for downstream crossing j The variance of (a);
cov (i, j) is the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j The covariance of (a);
the calculation process of the time correlation of the traffic flow data includes:
obtaining a traffic data set of a crossroad formed by the upstream intersection and the downstream intersection and recording the data set as a traffic data set
N is a positive integer;
calculating the traffic data set
The covariance of (a) is:
wherein d is a time step, d =0,1,2,3.. N-1; i =1,2,3.. N;
obtaining the traffic data set
Is a function of autocorrelation r (i) (d) The method comprises the following steps:
at the autocorrelation coefficient r (i) (d) When reaching 0 for the first time, the autocorrelation coefficient r (i) (d) D (i);
when d is less than or equal to d (i) When the time is longer than the preset time, the time relation between the previous d time steps and the traffic flow data at the current moment is shown, and d is more than d (i) And if so, indicating that the previous d time steps are not related to the traffic flow data at the current moment in time.
Optionally, after acquiring traffic flow data of an upstream intersection and a downstream intersection in the target area, the method further comprises: the data missing in the traffic flow data are repaired, and the method comprises the following steps:
in the formula, a s A weight representing traffic flow data;
y (h) represents traffic flow data at the time of data loss;
y (h-m) represents the traffic flow data at the h-m th moment;
y (h-1) represents traffic flow data at the h-1 th moment;
y (h + 1) represents the traffic flow data at the h +1 th moment;
y (h + m) represents the traffic flow data at the h + m-th time.
Optionally, after acquiring traffic flow data of an upstream intersection and a downstream intersection in the target area, the method further comprises:
acquiring a position point set formed by the longitude and the latitude of the position of the target vehicle and the current time, and recording as:
p＝{longitue，latitude，time}；
moving the target vehicle from a starting point p u To the destination p v Is recorded as a driving event
trip (u, v), and
trip(u，v)＝{p u time，p v time，p u location，p v location, state }; wherein u represents a starting point of a corresponding driving event; v represents the end of the corresponding driving event; p is a radical of formula u time represents the starting time p of the corresponding driving event v time represents the end time p of the corresponding driving event u location indicates corresponding drivingThe starting location of the event; p is a radical of v location represents a terminal position of the corresponding driving event;
state represents the state of the target vehicle during the occurrence of the corresponding driving event; if it is
state =0, then it means that the target vehicle is in a passenger carrying state; if the state =0, the target vehicle is in a passenger searching state; when p is u For passenger boarding points, p v When the passenger gets off the bus, the target vehicle is a passenger-carrying driving event; when p is u For passenger disembarking points, p v When the passenger is at the boarding point, the target vehicle is a passenger searching driving event;
mapping the driving event trip (u, v) of the target vehicle to a first one h of the target areas u And a second region h v Acquiring the target vehicle in a time period t k From the first region h u To the second area h v The shortest driving time of
Optionally, the process of determining the target vehicle comprises:
receiving a riding request initiated by a target client on a pre-established intelligent traffic management platform;
in response to the ride request, and presenting to the target customer a plurality of estimated ride rates and a plurality of vehicle types associated with the ride request;
generating a vehicle calling request based on the estimated riding cost and the vehicle type selected by the target customer, and pushing the vehicle calling request to a plurality of vehicle terminals;
and when a certain vehicle terminal triggers the vehicle calling request, taking the vehicle corresponding to the certain vehicle terminal as the target vehicle.
Optionally, before obtaining traffic flow data of an upstream intersection and a downstream intersection in the target area, the method further comprises:
initializing a network structure of a self-organizing mapping neural network, the number of neurons and a weight vector, and setting a learning rate and a field function; wherein, one neuron corresponds to one environmental influence factor;
normalizing the weight vector and the input vector, calculating the similarity degree between each neuron and the weight vector, and selecting a winning neuron;
updating the weight vector of the winning neuron, updating the learning rate and the field function, and judging whether the learning rate is smaller than a preset value or whether the updating times reach preset iteration times or not after the updating is finished;
if the learning rate is smaller than a preset value or the updating times reach a preset iteration time, marking each neuron, and searching an environmental influence shadow of the traffic flow data based on the marked neurons;
and if the learning rate is greater than or equal to a preset value and the updating times do not reach the preset iteration times, carrying out normalization processing on the weight vector and the input vector again, and continuously judging the learning rate or the updating times until the environment influence shadow of the traffic flow data is found.
Optionally, the environmental impact shadow of the traffic flow data comprises at least one of: road environment, signal lamp control strategy, weather, accident, traffic flow, vehicle speed.
The application also provides an wisdom traffic management system based on big data, the system including:
the data acquisition module is used for acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, and the target area comprises a traffic road area determined in advance or in real time;
the correlation calculation module is used for calculating the spatial correlation and the time correlation of the traffic flow data;
the intelligent traffic management module is used for performing intelligent traffic management on the upstream intersection and the downstream intersection according to the spatial correlation and the temporal correlation;
wherein the process of the correlation calculation module calculating the spatial correlation of the traffic flow data includes:
processing the traffic flow data into a traffic flow time sequence with the same time interval, and marking the traffic flow time sequence of an upstream crossing as q i And the time sequence of the traffic flow at the downstream intersection is marked as q j ；
Calculating the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j Cross correlation coefficient C of ij As the spatial correlation of the traffic flow data, there are:
in the formula, D (q) i ) Time sequence q of traffic flow for upstream crossing i The variance of (a);
D(q j ) Time sequence q of traffic flow for downstream crossing j The variance of (a);
cov (i, j) is the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j The covariance of (a);
the process of the correlation calculation module calculating the time correlation of the traffic flow data includes:
obtaining a traffic data set of a crossroad formed by the upstream intersection and the downstream intersection and recording the data set as a traffic data set
calculating the traffic data set
Has the following covariance:
wherein d is the time step, d =0,1,2,3.. N-1; i =1,2,3.. N;
obtaining the traffic data set
Is a function of autocorrelation r (i) (d) The method comprises the following steps:
at the autocorrelation coefficient r (i) (d) When reaching 0 for the first time, the autocorrelation coefficient r (i) (d) D (i);
when d is less than or equal to d (i) When the time is longer than the preset time, the time relation between the previous d time steps and the traffic flow data at the current moment is shown, and d is more than d (i) And if so, indicating that the previous d time steps are not related to the traffic flow data at the current moment in time.
Optionally, the system further includes a data recovery module, configured to recover missing data in the traffic flow data after acquiring the traffic flow data of the upstream intersection and the downstream intersection in the target area, where the data recovery module includes:
in the formula, a s A weight representing traffic flow data;
y (h) represents traffic flow data at the time of data loss;
y (h-m) represents the traffic flow data at the h-m th moment;
y (h-1) represents traffic flow data at the h-1 th moment;
y (h + 1) represents traffic flow data at the h +1 th time;
y (h + m) represents the traffic flow data at the h + m-th time.
Optionally, the system further includes a driving matching module, configured to, after acquiring traffic flow data of an upstream intersection and a downstream intersection in the target area, acquire a position point set formed by a longitude, a latitude, and a current time of a position of the target vehicle, and record as: p = { longitue, latitude, time };
taking the target vehicle from the starting point p u To the destination p v Is recorded as a driving event
trip (u, v), and
trip(u，v)＝{p u time，p v time，p u location，p v location, state }; wherein u represents a starting point of a corresponding driving event; v represents the end of the corresponding driving event; p is a radical of u time represents the starting time p of the corresponding driving event v time represents the end time p of the corresponding driving event u location represents a starting location of the corresponding driving event; p is a radical of formula v location represents an end position of the corresponding driving event;
state represents the state of the target vehicle during the occurrence of the corresponding driving event; if it is
state =0, then it means that the target vehicle is in a passenger carrying state; if the state =0, indicating that the target vehicle is in a passenger searching state; when p is u For passenger boarding points, p v When the vehicle is a passenger getting-off point, the target vehicle is a passenger-carrying driving event; when p is u For passenger disembarking points, p v When the passenger is at the boarding point, the target vehicle is a passenger searching driving event;
mapping the driving event trip (u, v) of the target vehicle to a first one h of the target areas u And a second region h v Acquiring the target vehicle in a time period t k From said first area h u To the second area h v The shortest driving time of
Optionally, the process of the ride matching module determining the target vehicle comprises:
receiving a riding request initiated by a target client on a pre-established intelligent traffic management platform;
in response to the ride request, and presenting to the target customer a plurality of estimated ride costs and a plurality of vehicle types associated with the ride request;
generating a vehicle calling request based on the estimated riding cost and the vehicle type selected by the target customer, and pushing the vehicle calling request to a plurality of vehicle terminals;
and when a certain vehicle terminal triggers the vehicle calling request, taking the vehicle corresponding to the certain vehicle terminal as the target vehicle.
As described above, the present invention provides a smart traffic management method and system based on big data, which has the following advantages:
by analyzing the spatial correlation and the temporal correlation of the traffic flow data of the target area, the traffic flow data of the intersection in the target area can be dynamically allocated based on the analysis result of the spatial correlation and the temporal correlation, and the traffic pressure of the vehicles at the intersection is reduced, so that the traffic environment of the target area can be improved, the traffic efficiency of the target area is improved, the possible congestion areas at the upstream intersection in the target area and the downstream intersection in the target area are effectively dredged, and the removal of the congestion areas is accelerated. And the missing traffic flow data can be repaired, so that the analysis result of the method is more accurate. Meanwhile, the method and the device can allocate the driving relation between the vehicle and the passenger in the target area, improve the passenger searching efficiency of the vehicles such as the network taxi appointment and the taxi and reduce the waiting time of the passenger in the riding process; the traffic pressure is reduced to carry out wisdom traffic management to the target area, provide omnidirectional traffic information service, can provide more convenient, high-efficient, swift, economy, safety, humanized, intelligent traffic service.
Drawings
Fig. 1 is a schematic flowchart illustrating a method for intelligent traffic management based on big data according to an embodiment of the present application;
fig. 2 is a schematic diagram illustrating a hardware structure of a big data based intelligent traffic management system according to an embodiment of the present application;
fig. 3 is a schematic circuit diagram of a hardware structure of a data acquisition module according to an embodiment of the present disclosure.
Detailed Description
The following embodiments of the present invention are provided by way of specific examples, and other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
Referring to fig. 1, the present invention provides a smart traffic management method based on big data, including the following steps:
s110, acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, wherein the target area comprises a traffic road area determined in advance or in real time;
and S120, calculating the spatial correlation and the time correlation of the traffic flow data. Specifically, the calculation process of the spatial correlation of the traffic flow data includes: processing the traffic flow data into a traffic flow time sequence with the same time interval, and recording the traffic flow time sequence of the upstream intersection as q i And the time sequence of the traffic flow at the downstream intersection is recorded as q j (ii) a Calculating the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow with downstream crossing j Cross correlation coefficient C of ij As the spatial correlation of the traffic flow data, there are:
in the formula, D (q) i ) Time sequence q of traffic flow for upstream crossing i The variance of (a); d (q) j ) Time sequence q for traffic flow of downstream crossing j The variance of (a); cov (i, j) is the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j The covariance of (a).
Specifically, the calculation process of the time correlation of the traffic flow data includes: obtaining a traffic data set of the intersection formed by the upstream intersection and the downstream intersection, and recording the data set as the traffic data set
calculating the traffic data set
The covariance of (a) is:
wherein d is the time step, d =0,1,2,3.. N-1; n =1,2,3.;
obtaining the traffic data set
Is the autocorrelation function r (i) (d) The method comprises the following steps:
at the autocorrelation coefficient r (i) (d) When reaching 0 for the first time, the autocorrelation coefficient r (i) (d) D (i);
when d is less than or equal to d (i) When represents the front dThe time step length has time correlation with the traffic flow data at the current moment, and d is more than d (i) And if so, indicating that the previous d time steps are not related to the traffic flow data at the current moment in time.
And S130, performing intelligent traffic management on the upstream intersection and the downstream intersection based on the spatial correlation and the time correlation of the traffic flow data.
In an urban road network, congestion occurs at a certain intersection, and congestion occurs at adjacent intersections to a certain extent along with accumulation of time. The congestion condition of the intersection is weakened by optimizing a signal lamp control strategy, manually dredging and the like, and the congestion state of adjacent intersections is relieved, so that certain correlation necessarily exists between the intersections. The correlation between intersections is represented by: when the radiation capacity of a certain intersection is large, such as a large business district, a station, an enterprise office area and other areas with dense human mouths nearby, the fluctuation of the traffic flow data of the intersection can affect the traffic conditions of a plurality of adjacent intersections, and even cause large congestion. The traffic state at an intersection may be affected by a number of external factors with uncertainty, such as sudden traffic accidents, temporary activities, road construction, etc. If a certain intersection is affected, the surrounding intersections are also congested. The bearing capacity of a certain intersection in a city road network is greatly unbalanced with the actual traffic flow, and the traffic state of the intersection at the next moment can be changed due to slight change of traffic flow data. The spatial correlation between different intersections can be quantified by a cross-correlation coefficient, and on the other hand, the autocorrelation coefficient can represent the time correlation of traffic flow data.
Therefore, in the embodiment, by analyzing the spatial correlation and the temporal correlation of the traffic flow data of the target area, the vehicles at the intersections in the target area can be dynamically allocated based on the analysis results of the spatial correlation and the temporal correlation, and the traffic pressure at the intersections is reduced, so that the traffic environment of the target area can be improved, the vehicle traffic efficiency of the target area is improved, the congestion areas which may occur at the upstream intersections in the target area and the downstream intersections in the target area are effectively dredged, and the removal of the congestion areas is accelerated.
In an exemplary embodiment, after obtaining traffic flow data for an upstream intersection and a downstream intersection in the target area, the method further comprises: the data missing in the traffic flow data are repaired, and the method comprises the following steps:
in the formula, a s A weight representing traffic flow data;
y (h) represents traffic flow data at the time of data loss;
y (h-m) represents the traffic flow data at the h-m th moment;
y (h-1) represents traffic flow data at the h-1 th moment;
y (h + 1) represents traffic flow data at the h +1 th time;
y (h + m) represents the traffic flow data at the h + m-th time.
In this embodiment, missing data refers to data missing or partial key content missing at a certain time due to equipment failure, weather influence, human misoperation and the like. Meanwhile, data in the urban traffic field generally has a missing phenomenon, so that the data has a problem in time dimension, and accurate information cannot be provided for scientific research. Therefore, on the basis that the data missing in the traffic flow data are repaired, the analysis can be performed based on all the traffic flow data, the analysis result is more accurate, and higher accuracy can be provided for intelligent traffic management in the later period.
In an exemplary embodiment, after obtaining traffic flow data for an upstream intersection and a downstream intersection in the target area, the method further comprises:
acquiring a position point set formed by the longitude and the latitude of the position of the target vehicle and the current time, and recording as:
p＝{longitue，latitude，time}；
taking the target vehicle from the starting point p u To the destination p v Is recorded as a driving event
trip (u, v), and
trip(u，v)＝{p u time，p v time，p u location，p v location, state }; wherein u represents a starting point of a corresponding driving event; v represents the end of the corresponding driving event; p is a radical of u time represents the starting time p of the corresponding driving event v time represents the end time p of the corresponding driving event u location represents a starting location of the corresponding driving event; p is a radical of v location represents a terminal position of the corresponding driving event;
state represents the state of the target vehicle during the occurrence of the corresponding driving event; if it is
state =0, then it means that the target vehicle is in a passenger carrying state; if the state =0, the target vehicle is in a passenger searching state; when p is u For passenger boarding points, p v When the passenger gets off the bus, the target vehicle is a passenger-carrying driving event; when p is u For passenger disembarking points, p v When the passenger is at the boarding point, the target vehicle is a passenger searching driving event;
mapping the driving event trip (u, v) of the target vehicle to a first one h of the target areas u And a second region h v Acquiring the target vehicle at a time period t k From said first area h u To the second area h v The shortest driving time of
According to the above description, the process of determining the target vehicle of the present embodiment includes: receiving a riding request initiated by a target client on a pre-established intelligent traffic management platform; in response to the ride request, and presenting to the target customer a plurality of estimated ride costs and a plurality of vehicle types associated with the ride request; generating a vehicle calling request based on the estimated riding cost and the vehicle type selected by the target customer, and pushing the vehicle calling request to a plurality of vehicle terminals; and when a certain vehicle terminal triggers the vehicle calling request, taking the vehicle corresponding to the certain vehicle terminal as the target vehicle. The target vehicles of the embodiment include, but are not limited to, a network appointment car, a taxi and other vehicles.
Therefore, the driving relation between the vehicle and the passenger in the target area can be adjusted, when the passenger wants to take the vehicle in the target area, the passenger only needs to initiate a taking request on a pre-established intelligent traffic management platform and then selects and estimates the taking cost and the vehicle type, and the intelligent traffic management platform can match the corresponding network appointment vehicle or taxi for the passenger, so that the passenger searching efficiency of the vehicles such as the network appointment vehicle and the taxi can be improved, and the waiting time of the passenger for taking the vehicle is also reduced; meanwhile, the number of vehicles borne by the road can be reasonably distributed, and the traffic pressure is reduced.
In an exemplary embodiment, prior to obtaining traffic flow data for an upstream intersection and a downstream intersection in the target area, the method further comprises:
initializing a network structure of a self-organizing mapping neural network, the number of neurons and a weight vector, and setting a learning rate and a domain function; wherein, one neuron corresponds to one environmental influence factor;
normalizing the weight vector and the input vector, calculating the similarity degree between each neuron and the weight vector, and selecting a winning neuron;
updating the weight vector of the winning neuron, updating the learning rate and the field function, and judging whether the learning rate is less than a preset value or whether the updating times reach preset iteration times or not after the updating is finished;
if the learning rate is smaller than a preset value or the updating times reach preset iteration times, marking each neuron, and searching an environmental influence shadow of the traffic flow data based on the marked neurons;
and if the learning rate is greater than or equal to a preset value and the updating times do not reach the preset iteration times, carrying out normalization processing on the weight vector and the input vector again, and continuously judging the learning rate or the updating times until the environment influence shadow of the traffic flow data is found. In this embodiment, the shadow of the environmental impact of the traffic flow data includes, but is not limited to: road environment, signal light control strategy, weather, accident, traffic flow, vehicle speed, etc.
Due to the complexity of urban traffic scenes, infrastructure around urban intersections, road environments, signal lamp control strategies, weather and accidents are all important factors influencing traffic states. The traditional traffic state estimation is determined by empirical numerical division of traffic parameters such as traffic flow, average speed, occupancy and the like, and the influence of various factors is not comprehensively considered. Factors such as road environment, weather and the like are difficult to collect and are represented by specific numerical values, but the influence of the factors can be reflected in a large amount of data, so that the method and the device can determine the environmental influence molecules of the traffic flow data in the target area by carrying out cluster analysis on the intersection flow data, defining the clustered result as the environmental influence factors and predicting the traffic flow under different environmental influence factors, and are convenient for eliminating corresponding interference noise when analyzing the traffic flow data in the target area in the later period.
In summary, the present invention provides an intelligent traffic management method based on big data, which performs spatial correlation and temporal correlation analysis on traffic flow data in a target area, and can dynamically allocate vehicles at intersections in the target area based on the spatial correlation and temporal correlation analysis results, thereby reducing vehicle traffic pressure at the intersections, improving traffic environment in the target area, increasing vehicle traffic efficiency in the target area, effectively dredging possible congestion areas at upstream intersections in the target area and downstream intersections in the target area, and accelerating the release of congestion areas. In addition, the method can also repair the missing traffic flow data, so that the analysis result of the method is more accurate. Meanwhile, the method can allocate the driving relation between the vehicle and the passenger in the target area, improve the passenger searching efficiency of the vehicles such as the network taxi appointment and the taxi, and reduce the waiting time of the passenger during riding; the method can reasonably distribute the number of vehicles borne by roads and reduce traffic pressure, thereby carrying out intelligent traffic management on the target area, providing all-around traffic information service and providing more convenient, efficient, quick, economic, safe, humanized and intelligent traffic service.
As shown in fig. 2, the present application further provides a smart traffic management system based on big data, the system includes:
the data acquisition module 210 is configured to acquire traffic flow data of an upstream intersection and a downstream intersection in a target area, where the target area includes a traffic road area determined in advance or in real time. The traffic flow data acquisition mode in this embodiment may be an existing mode, and this embodiment does not limit the data acquisition mode. As an example, a hardware circuit for collecting traffic flow data in the present embodiment is shown in fig. 3, and in fig. 3, the circuit mainly includes a dc voltage-stabilized power supply circuit, a minimum system board composed of a core board S3C2440 and a development board, and a 485 communication circuit. Firstly, a 5V direct-current stabilized power supply is adopted by the direct-current stabilized power supply part, and 5V power supply voltage is converted into 3.3V power supply voltage through the LM1117 stabilized power supply to supply power for the S3C2440 development board. And secondly, an S3C2440 processor, a clock circuit, a reset source, a power circuit, a standard SD card interface, a standard 256M NAND Flash storage device and a plurality of programmable full-duplex serial communication interfaces which take an ARM920T chip as a core form a S3C2440 minimum system. In addition, the 485 communication circuit is used for leading out an RS-485 communication interface of the S3C23440 development board, so that 485 data communication between the lower computer collector and the conversion module is realized. The MAX485 chip mainly utilizes a driver and a receiver as an input end of the driver and an output end of the receiver respectively, and when the MAX485 chip is connected with an S3C2440 development board, only RXD and TXD on the S3C2440 development board need to be connected respectively.
And a correlation calculation module 220 for calculating a spatial correlation and a temporal correlation of the traffic flow data. Specifically, the process of the correlation calculation module 220 calculating the spatial correlation of the traffic flow data includes: processing the traffic flow data into a traffic flow time sequence with the same time intervalAnd recording the time sequence of the traffic flow at the upstream intersection as q i And the time sequence of the traffic flow at the downstream intersection is marked as q j (ii) a Calculating the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j Cross correlation coefficient C of ij As the spatial correlation of the traffic flow data, there are:
in the formula, D (q) i ) Time sequence q of traffic flow for upstream crossing i The variance of (a); d (q) j ) Time sequence q of traffic flow for downstream crossing j The variance of (a); cov (i, j) is the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j Of the measured data.
Wherein the process of the correlation calculation module 220 calculating the time correlation of the traffic flow data includes: obtaining a traffic data set of a crossroad formed by the upstream intersection and the downstream intersection and recording the data set as a traffic data set
calculating the traffic data set
Has the following covariance:
wherein d is the time step, d =0,1,2,3.. N-1; n =1,2,3.;
obtaining the traffic data set
Is the autocorrelation function r (i) (d) The method comprises the following steps:
at the autocorrelation coefficient r (i) (d) When reaching 0 for the first time, the autocorrelation coefficient r (i) (d) D (i);
when d is less than or equal to d (i) When the time is longer than the preset time, the time relation between the previous d time steps and the traffic flow data at the current moment is shown, and d is more than d (i) And if so, indicating that the former d time steps are not related to the traffic flow data at the current moment in time.
And the intelligent traffic management module 230 is configured to perform intelligent traffic management on the upstream intersection and the downstream intersection according to the spatial correlation and the temporal correlation.
Therefore, in the embodiment, by analyzing the spatial correlation and the temporal correlation of the traffic flow data of the target area, the vehicles at the intersections in the target area can be dynamically allocated based on the analysis results of the spatial correlation and the temporal correlation, and the traffic pressure at the intersections is reduced, so that the traffic environment of the target area can be improved, the vehicle traffic efficiency of the target area is improved, the congestion areas which may occur at the upstream intersections in the target area and the downstream intersections in the target area are effectively dredged, and the removal of the congestion areas is accelerated.
In an exemplary embodiment, the system further includes a data restoration module, configured to restore missing data in the traffic flow data after acquiring the traffic flow data of the upstream intersection and the downstream intersection in the target area, where:
in the formula, a s A weight representing traffic flow data;
y (h) represents traffic flow data at the time of data loss;
y (h-m) represents the traffic flow data at the h-m th moment;
y (h-1) represents the traffic flow data at the h-1 th moment;
y (h + 1) represents the traffic flow data at the h +1 th moment;
y (h + m) represents the traffic flow data at the h + m-th time.
In this embodiment, missing data refers to data missing or partial key content missing at a certain time due to equipment failure, weather influence, human operation error, and the like. Meanwhile, the data in the urban traffic field generally has a deletion phenomenon, so that the data has a problem in time dimension, and accurate information cannot be provided for scientific research. Therefore, on the basis that the data missing in the traffic flow data are repaired, the analysis can be performed based on all the traffic flow data, the analysis result is more accurate, and higher accuracy can be provided for intelligent traffic management in the later period.
In an exemplary embodiment, the system further comprises a ride matching module for, after acquiring traffic flow data for an upstream intersection and a downstream intersection in the target area, acquiring a set of location points formed by the longitude, latitude and current time of the location of the target vehicle, noted as: p = { longitue, latitude, time };
moving the target vehicle from a starting point p u To the destination p v Is recorded as a driving event
trip (u, v), and
trip(u，v)＝{p u time，p v time，p u location，p v location, state }; wherein u represents a starting point of a corresponding driving event; v represents the end of the corresponding driving event; p is a radical of u time represents the starting time p of the corresponding driving event v time represents the end time p of the corresponding driving event u location represents a starting location of the corresponding driving event; p is a radical of formula v location represents an end position of the corresponding driving event;
state represents the state of the target vehicle during the occurrence of the corresponding driving event; if it is
state =0, indicating that the target vehicle is in a passenger carrying state; if state =0, it indicates the target vehicleThe client is in a client searching state; when p is u For passenger boarding points, p v When the vehicle is a passenger getting-off point, the target vehicle is a passenger-carrying driving event; when p is u For passenger disembarking points, p v When the passenger is at the boarding point, the target vehicle is a passenger searching driving event;
mapping the driving event trip (u, v) of the target vehicle to a first one h of the target areas u And a second region h v Acquiring the target vehicle at a time period t k From said first area h u To the second area h v The shortest driving time of
According to the above description, the process of determining the target vehicle of the present embodiment includes: receiving a riding request initiated by a target client on a pre-established intelligent traffic management platform; in response to the ride request, and presenting to the target customer a plurality of estimated ride costs and a plurality of vehicle types associated with the ride request; generating a vehicle calling request based on the estimated riding cost and the vehicle type selected by the target client, and pushing the vehicle calling request to a plurality of vehicle terminals; and when a certain vehicle terminal triggers the vehicle calling request, taking the vehicle corresponding to the certain vehicle terminal as the target vehicle. The target vehicles of the embodiment include, but are not limited to, a network appointment car, a taxi and other vehicles.
Therefore, the driving relation between the vehicle and the passenger in the target area can be allocated, when the passenger wants to take the vehicle in the target area, the passenger only needs to initiate a taking request on a pre-established intelligent traffic management platform, then selects and estimates the taking cost and the vehicle type, and the intelligent traffic management platform can match the corresponding network car reservation or taxi for the passenger, so that the passenger searching efficiency of the vehicles such as the network car reservation, the taxi and the like can be improved, and the waiting time for the passenger to take the vehicle is also reduced; meanwhile, the number of vehicles borne by the road can be reasonably distributed, and the traffic pressure is reduced.
In an exemplary embodiment, prior to obtaining traffic flow data for an upstream intersection and a downstream intersection in the target area, the system further comprises:
initializing a network structure of a self-organizing mapping neural network, the number of neurons and a weight vector, and setting a learning rate and a field function; wherein, one neuron corresponds to one environmental influence factor;
normalizing the weight vector and the input vector, calculating the similarity degree between each neuron and the weight vector, and selecting a winning neuron;
updating the weight vector of the winning neuron, updating the learning rate and the field function, and judging whether the learning rate is smaller than a preset value or whether the updating times reach preset iteration times or not after the updating is finished;
if the learning rate is smaller than a preset value or the updating times reach a preset iteration time, marking each neuron, and searching an environmental influence shadow of the traffic flow data based on the marked neurons;
and if the learning rate is greater than or equal to a preset value and the updating times do not reach the preset iteration times, normalizing the weight vector and the input vector again, and continuously judging the learning rate or the updating times until the environment influence shadow of the traffic flow data is found. In this embodiment, the shadow of the environmental impact of the traffic flow data includes, but is not limited to: road environment, signal light control strategy, weather, accident, traffic flow, vehicle speed, etc.
Due to the complexity of urban traffic scenes, infrastructure, road environment, signal lamp control strategies, weather and accidents around urban intersections are all important factors influencing traffic states. The traditional traffic state estimation is determined by empirical numerical division of traffic parameters such as traffic flow, average speed and occupancy, and the influence of various factors is not comprehensively considered. Factors such as road environment, weather and the like are difficult to collect and are represented by specific numerical values, but the influence of the factors can be reflected in a large amount of data, so that the method and the device can determine the environmental influence molecules of the traffic flow data in the target area by carrying out cluster analysis on the intersection flow data, defining the clustered result as the environmental influence factors and predicting the traffic flow under different environmental influence factors, and are convenient for eliminating corresponding interference noise when analyzing the traffic flow data in the target area in the later period.
In summary, the present invention provides an intelligent traffic management system based on big data, which performs spatial correlation and temporal correlation analysis on traffic flow data in a target area, and can dynamically allocate vehicles at intersections in the target area based on the analysis results of the spatial correlation and the temporal correlation, so as to reduce the traffic pressure at the intersections, thereby improving the traffic environment in the target area, improving the vehicle traffic efficiency in the target area, effectively dredging congested areas that may occur at upstream intersections in the target area and downstream intersections in the target area, and accelerating the relief of congested areas. And the system can also repair the missing traffic flow data, so that the analysis result of the system is more accurate. Meanwhile, the system can allocate the driving relation between the vehicle and the passenger in the target area, improve the passenger searching efficiency of the vehicles such as the network taxi appointment and the taxi, and reduce the waiting time for the passenger to take the bus; the system can reasonably distribute the number of vehicles borne by roads and reduce traffic pressure, thereby carrying out intelligent traffic management on target areas, providing all-around traffic information service and providing more convenient, efficient, quick, economic, safe, humanized and intelligent traffic service.
It should be noted that the intelligent traffic management system based on big data provided in the foregoing embodiment and the intelligent traffic management method based on big data provided in the foregoing embodiment belong to the same concept, wherein specific ways of executing operations by the modules and units have been described in detail in the method embodiments, and are not described herein again. In practical applications, the intelligent traffic management system based on big data provided in the above embodiment may distribute the above functions by different function modules according to needs, that is, the internal structure of the system is divided into different function modules to complete all or part of the above described functions, which is not limited herein.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Those skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which may be made by those skilled in the art without departing from the spirit and scope of the present invention as defined in the appended claims.
Claims (10)
1. An intelligent traffic management method based on big data is characterized by comprising the following steps:
acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, wherein the target area comprises a traffic road area determined in advance or in real time;
calculating the spatial correlation and the time correlation of the traffic flow data, and performing intelligent traffic management on the upstream intersection and the downstream intersection based on the spatial correlation and the time correlation;
wherein the calculation process of the spatial correlation of the traffic flow data comprises the following steps:
processing the traffic flow data into a traffic flow time sequence with the same time interval, and marking the traffic flow time sequence of an upstream crossing as q i And the time sequence of the traffic flow at the downstream intersection is recorded as q j ；
Calculating the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j Cross correlation coefficient C of ij As the spatial correlation of the traffic flow data, there are:
in the formula, D (q) i ) Time series q of traffic flow for upstream crossing i The variance of (a);
D(q j ) Time sequence q for traffic flow of downstream crossing j The variance of (a);
cov (i, j) is the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow with downstream crossing j The covariance of (a);
the calculation process of the time correlation of the traffic flow data comprises the following steps:
obtaining a traffic data set of a crossroad formed by the upstream intersection and the downstream intersection and recording the data set as a traffic data set
N is a positive integer;
calculating the traffic data set
Has the following covariance:
wherein d is a time step, d =0,1,2,3.. N-1; i =1,2,3.. N;
obtaining the traffic data set
Is a function of autocorrelation r (i) (d) The method comprises the following steps:
at the autocorrelation coefficient r (i) (d) When reaching 0 for the first time, the autocorrelation coefficient r (i) (d) D (i);
when d is less than or equal to d (i) When the time is longer than the preset time, the time relation between the previous d time steps and the traffic flow data at the current moment is shown, and d is more than d (i) Then, it represents the d previous time steps and the traffic flow data of the current timeThere is no time correlation.
2. The intelligent traffic management method based on big data according to claim 1, wherein after acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, the method further comprises: the data missing in the traffic flow data are repaired, and the method comprises the following steps:
in the formula, a s A weight representing traffic flow data;
y (h) represents traffic flow data at the time of data loss;
y (h-m) represents the traffic flow data at the h-m th moment;
y (h-1) represents traffic flow data at the h-1 th moment;
y (h + 1) represents traffic flow data at the h +1 th time;
y (h + m) represents the traffic flow data at the h + m-th time.
3. The intelligent traffic management method based on big data according to claim 1 or 2, wherein after acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, the method further comprises:
acquiring a position point set formed by the longitude and the latitude of the position of the target vehicle and the current time, and recording as: p = { longitue, latitude, time };
moving the target vehicle from a starting point p u To the destination p v Is marked as trip (u, v), and trip (u, v) = { p u time，p v time，p u location，p v location, state }; wherein u represents a starting point of a corresponding driving event; v represents the end of the corresponding driving event; p is a radical of u time represents the starting time p of the corresponding driving event v time represents the end time p of the corresponding driving event u location represents a starting location of the corresponding driving event; p is a radical of v location represents a terminal position of the corresponding driving event;
state represents the state of the target vehicle during the occurrence of the corresponding driving event; if the state =0, indicating that the target vehicle is in a passenger carrying state; if the state =0, indicating that the target vehicle is in a passenger searching state; when p is u For passenger boarding points, p v When the passenger gets off the bus, the target vehicle is a passenger-carrying driving event; when p is u For the passenger to get off, p v When the passenger is at the boarding point, the target vehicle is a passenger searching driving event;
mapping the driving event trip (u, v) of the target vehicle to a first one h of the target areas u And a second region h v Acquiring the target vehicle at a time period t k From said first area h u To the second area h v Shortest driving time of
4. The intelligent traffic management method based on big data according to claim 3, wherein the process of determining the target vehicle comprises:
receiving a riding request initiated by a target client on a pre-established intelligent traffic management platform;
in response to the ride request, and presenting to the target customer a plurality of estimated ride rates and a plurality of vehicle types associated with the ride request;
generating a vehicle calling request based on the estimated riding cost and the vehicle type selected by the target client, and pushing the vehicle calling request to a plurality of vehicle terminals;
and when a certain vehicle terminal triggers the vehicle calling request, taking the vehicle corresponding to the certain vehicle terminal as the target vehicle.
5. The intelligent big-data-based traffic management method according to claim 1, wherein before acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, the method further comprises:
initializing a network structure of a self-organizing mapping neural network, the number of neurons and a weight vector, and setting a learning rate and a domain function; wherein, one neuron corresponds to one environmental influence factor;
normalizing the weight vector and the input vector, calculating the similarity degree between each neuron and the weight vector, and selecting a winning neuron;
updating the weight vector of the winning neuron, updating the learning rate and the field function, and judging whether the learning rate is less than a preset value or whether the updating times reach preset iteration times or not after the updating is finished;
if the learning rate is smaller than a preset value or the updating times reach preset iteration times, marking each neuron, and searching an environmental influence shadow of the traffic flow data based on the marked neurons;
and if the learning rate is greater than or equal to a preset value and the updating times do not reach the preset iteration times, normalizing the weight vector and the input vector again, and continuously judging the learning rate or the updating times until the environment influence shadow of the traffic flow data is found.
6. The intelligent traffic management method based on big data according to claim 5, wherein the shadow of the environmental impact of the traffic flow data comprises at least one of: road environment, signal lamp control strategy, weather, accident, traffic flow, vehicle speed.
7. An intelligent traffic management system based on big data, which is characterized in that the system comprises:
the data acquisition module is used for acquiring traffic flow data of an upstream intersection and a downstream intersection in a target area, wherein the target area comprises a traffic road area determined in advance or in real time;
the correlation calculation module is used for calculating the spatial correlation and the time correlation of the traffic flow data;
the intelligent traffic management module is used for performing intelligent traffic management on the upstream intersection and the downstream intersection according to the spatial correlation and the temporal correlation;
wherein the process of the correlation calculation module calculating the spatial correlation of the traffic flow data includes:
processing the traffic flow data into a traffic flow time sequence with the same time interval, and recording the traffic flow time sequence of the upstream intersection as q i And the time sequence of the traffic flow at the downstream intersection is recorded as q j ；
Calculating the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j Cross correlation coefficient C of ij As the spatial correlation of the traffic flow data, there are:
in the formula, D (q) i ) Time sequence q of traffic flow for upstream crossing i The variance of (a);
D(q j ) Time sequence q of traffic flow for downstream crossing j The variance of (a);
cov (i, j) is the traffic flow time sequence q of the upstream crossing i Time sequence q of traffic flow at downstream crossing j The covariance of (a);
the process of the correlation calculation module calculating the time correlation of the traffic flow data includes:
obtaining a traffic data set of the intersection formed by the upstream intersection and the downstream intersection, and recording the data set as the traffic data set
N is a positive integer;
calculating the traffic data set
The covariance of (a) is:
wherein d is the time step, d =0,1,2,3.. N-1; i =1,2,3.. N;
obtaining the traffic data set
Is a function of autocorrelation r (i) (d) The method comprises the following steps:
at the autocorrelation coefficient r (i) (d) When reaching 0 for the first time, the autocorrelation coefficient r (i) (d) D (i);
when d is less than or equal to d (i) When the time is longer than the preset time, the time correlation exists between the previous d time steps and the traffic flow data at the current moment, and d is greater than d (i) And if so, indicating that the previous d time steps are not related to the traffic flow data at the current moment in time.
8. The intelligent traffic management system based on big data according to claim 7, further comprising a data recovery module for recovering missing data in traffic flow data after obtaining traffic flow data at upstream and downstream intersections in the target area, comprising:
in the formula, a s A weight representing traffic flow data;
y (h) represents traffic flow data at the time of data loss;
y (h-m) represents the traffic flow data at the h-m th moment;
y (h-1) represents traffic flow data at the h-1 th moment;
y (h + 1) represents traffic flow data at the h +1 th time;
y (h + m) represents the traffic flow data at the h + m-th time.
9. The intelligent big data-based traffic management system according to claim 7 or 8, wherein the system further comprises a driving matching module for acquiring a position point set formed by longitude, latitude and current time of the position of the target vehicle after acquiring the traffic flow data of the upstream intersection and the downstream intersection in the target area, and the position point set is recorded as: p = { longitue, latitude, time };
taking the target vehicle from the starting point p u To the destination p v Is marked as trip (u, v), and trip (u, v) = { p u time，p v time，p u location，p v location, state }; wherein u represents a starting point of a corresponding driving event; v represents the end of the corresponding driving event; p is a radical of u time represents the starting time p of the corresponding driving event v time represents the end time p of the corresponding driving event u location represents a starting location of the corresponding driving event; p is a radical of v location represents a terminal position of the corresponding driving event; state represents the state of the target vehicle during the occurrence of the corresponding driving event; if the state =0, indicating that the target vehicle is in a passenger carrying state; if the state =0, the target vehicle is in a passenger searching state; when p is u For passenger boarding points, p v When the passenger gets off the bus, the target vehicle is a passenger-carrying driving event; when p is u For passenger disembarking points, p v When the passenger is at the boarding point, the target vehicle is a passenger searching driving event;
mapping the driving event trip (u, v) of the target vehicle to a first one h of the target areas u And a second region h v Acquiring the target vehicle at a time period t k From the first region h u To the second area h v Is shortestDriving time, is recorded as
10. The intelligent big data-based traffic management system of claim 9, wherein the process of the ride matching module determining a target vehicle comprises:
receiving a riding request initiated by a target client on a pre-established intelligent traffic management platform;
in response to the ride request, and presenting to the target customer a plurality of estimated ride costs and a plurality of vehicle types associated with the ride request;
generating a vehicle calling request based on the estimated riding cost and the vehicle type selected by the target customer, and pushing the vehicle calling request to a plurality of vehicle terminals;
and when a certain vehicle terminal triggers the vehicle calling request, taking the vehicle corresponding to the certain vehicle terminal as the target vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211188349.3A CN115691164B (en) | 2022-09-27 | 2022-09-27 | Intelligent traffic management method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211188349.3A CN115691164B (en) | 2022-09-27 | 2022-09-27 | Intelligent traffic management method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115691164A true CN115691164A (en) | 2023-02-03 |
| CN115691164B CN115691164B (en) | 2024-05-03 |
Family
ID=85064602
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211188349.3A Active CN115691164B (en) | 2022-09-27 | 2022-09-27 | Intelligent traffic management method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115691164B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN104408913A (en) * | 2014-11-03 | 2015-03-11 | 东南大学 | Traffic flow three parameter real time prediction method taking regard of space-time correlation |
| CN111583649A (en) * | 2020-05-15 | 2020-08-25 | 重庆大学 | Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data |
| US20200334979A1 (en) * | 2017-09-15 | 2020-10-22 | Velsis Sistemas E Tecnologia Viaria S/A | Predictive, integrated and intelligent system for control of times in traffic lights |
-
2022
- 2022-09-27 CN CN202211188349.3A patent/CN115691164B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971520A (en) * | 2014-04-17 | 2014-08-06 | 浙江大学 | Traffic flow data recovery method based on space-time correlation |
| CN104408913A (en) * | 2014-11-03 | 2015-03-11 | 东南大学 | Traffic flow three parameter real time prediction method taking regard of space-time correlation |
| US20200334979A1 (en) * | 2017-09-15 | 2020-10-22 | Velsis Sistemas E Tecnologia Viaria S/A | Predictive, integrated and intelligent system for control of times in traffic lights |
| CN111583649A (en) * | 2020-05-15 | 2020-08-25 | 重庆大学 | Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115691164B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570678B (en) | Method and device for predicting total travel time of bus from starting point to end point | |
| CN109191845B (en) | Bus arrival time prediction method | |
| CN104424812B (en) | A kind of public transport arrival time forecasting system and method | |
| Li et al. | Public bus arrival time prediction based on traffic information management system | |
| CN108364464B (en) | Probability model-based public transport vehicle travel time modeling method | |
| CN110363985B (en) | Traffic data analysis method, device, storage medium and equipment | |
| CN106971546B (en) | Road section bus permeability estimation method based on bus GPS data | |
| CN110472999B (en) | Passenger flow mode analysis method and device based on subway and shared bicycle data | |
| CN114435138A (en) | Vehicle energy consumption prediction method and device, vehicle and storage medium | |
| CN114418606B (en) | Network vehicle order demand prediction method based on space-time convolution network | |
| CN111199247A (en) | Bus operation simulation method | |
| CN112507624A (en) | Intercity highway trip mode identification model construction and identification method and device | |
| CN115601983A (en) | Method, device, equipment and storage medium for determining cycle duration of traffic signal lamp | |
| CN110189537B (en) | Parking guidance method, device and equipment based on space-time characteristics and storage medium | |
| CN112669604B (en) | Urban traffic scheduling method and device | |
| CN114036411A (en) | Route planning method, device, equipment and medium | |
| CN116824868B (en) | Method, device, equipment and medium for identifying illegal parking points and predicting congestion of vehicles | |
| CN109671007A (en) | Taxi taking difficulty assessment method near a kind of railway station based on multi-dimensional data | |
| CN115691164B (en) | Intelligent traffic management method and system based on big data | |
| Xu et al. | Research on estimation method of mileage power consumption for electric vehicles | |
| CN115273468B (en) | Traffic jam control strategy generation method and device | |
| CN116704783A (en) | Bus stop and expressway exit optimization layout method and device based on CIM | |
| CN110046535B (en) | Intelligent travel time prediction system, method and storage medium based on machine learning | |
| CN115099716A (en) | Method and system for dispatching bus in large station and bus in whole process for different lines | |
| CN113723761B (en) | Multi-dimensional urban public transportation operation service reliability evaluation method based on operation data |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240408 Address after: Room 3, Office, 25th Floor, Green Space Business Center, No. 2588 Hongguangshan Road, Shuimogou District, Urumqi, Xinjiang Uygur Autonomous Region, 830000, 202-203 Applicant after: Xinjiang Beiying beichuang Information Technology Co.,Ltd. Country or region after: China Address before: Room 7f, 2nd Floor, No. 2, Ezhangtan Street, Baiyun District, Guangzhou, Guangdong Province (self declaration) Applicant before: Guangzhou Yuxin Information Technology Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |