CN109979190A - A kind of prediction technique and device of road traffic state - Google Patents
A kind of prediction technique and device of road traffic state Download PDFInfo
- Publication number
- CN109979190A CN109979190A CN201711450559.4A CN201711450559A CN109979190A CN 109979190 A CN109979190 A CN 109979190A CN 201711450559 A CN201711450559 A CN 201711450559A CN 109979190 A CN109979190 A CN 109979190A
- Authority
- CN
- China
- Prior art keywords
- user
- type
- trip
- traffic
- road
- 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
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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The present invention provides the prediction technique and device of a kind of road traffic state.If method includes: that cell-phone number user is third type of user, according to carrier data, with determining the trip purpose of third type of user；Carrier data includes the message registration of cell-phone number user, internet behavior data and social software Content of Communication；According to the trip purpose of third type of user, the trip optimal route of third type of user is obtained；According to trip optimal route, the traffic path of first kind user and the traffic path of Second Type user of third type of user, the traffic behavior of road is predicted.Method and device provided by the invention predicts the action of its own next step according to the behavior of cell-phone number user, to predict road traffic state.Carrier data is taken full advantage of, the precision of road traffic state prediction is improved.
Description
Technical field
The present invention relates to traffic status prediction technical fields, more particularly, to a kind of prediction side of road traffic state
Method and device.
Background technique
Traffic congestion has become the bottleneck for restricting urban economy and social development, it directly contributes the overall operation in city
Efficiency reduces, and short -board effect during urban development is increasingly apparent.
Currently, electronic map is widely used in mobile application or desktop application.As long as network support, people can be at any time
Electronic map is checked everywhere, searches the destination oneself wanted to know about.Current traffic condition can be shown on electronic map.Example
Such as, green represents unimpeded section, and yellow represents low running speed section, red then represent congested link.People when driving to go on a journey,
Can traffic condition to be shown in Reference Map, on the one hand can have certain in-mind anticipation to stroke, on the other hand can be
Select to a certain extent relatively smoothly route to avoid congestion.
But people often see map before trip, to be understood stroke or to be planned.That is, seeing
Traffic condition when map and not equal to practical trip to some section when traffic condition.
The method of existing prediction road traffic state are as follows: using the state array of associated road, predict road to be predicted
When the state to be predicted inscribed and associated road state array between probabilistic relation, to calculate predicted state；Either according to each
The facilities such as equipment such as sensor are planted to predict traffic route situation, there is a problem that forecasting inaccuracy is true.
Summary of the invention
The present invention provides a kind of the pre- of the road traffic state for overcoming the problems, such as that existing road traffic state forecasting inaccuracy is true
Survey method and device.
According to an aspect of the present invention, a kind of prediction technique of road traffic state is provided, comprising:
If cell-phone number user is third type of user, according to carrier data, going out for the third type of user is determined
Row destination；Wherein, the cell-phone number user includes first kind user, Second Type user and the third type of user,
The first kind user is specific trip software user, and the Second Type user is the vehicle with fixed traffic route
Main, the third type of user is accidental trip passenger；The carrier data include the cell-phone number user message registration,
Internet behavior data and social software Content of Communication；
According to the trip purpose of the third type of user, the trip optimal route of the third type of user is obtained；
According to the trip optimal route of the third type of user, the traffic path and described the of the first kind user
The traffic path of two type of user predicts the traffic behavior of road.
According to another aspect of the present invention, a kind of prediction meanss of road traffic state are provided, comprising:
Trip purpose ground determination module, if being that third type of user is sentenced according to carrier data for cell-phone number user
The trip purpose of the fixed third type of user；Wherein, the cell-phone number user includes first kind user, Second Type use
Family and the third type of user, the first kind user are specific trip software user, and the Second Type user is
Car owner with fixed traffic route, the third type of user are accidental trip passenger；The carrier data includes described
Message registration, internet behavior data and the social software Content of Communication of cell-phone number user；
Optimal route of going on a journey obtains module, for the trip purpose according to the third type of user, obtains described the
The trip optimal route of three type of user；
Traffic status prediction module, for the trip optimal route according to the third type of user, the first kind
The traffic path of the traffic path of user and the Second Type user, predicts the traffic behavior of road.
According to a further aspect of the invention, a kind of non-transient computer readable storage medium, the non-transient meter are provided
Calculation machine readable storage medium storing program for executing stores computer instruction, and the computer instruction makes the computer execute above-mentioned method.
The prediction technique and device of a kind of road traffic state provided by the invention determine accidental according to carrier data
With going on a journey the trip purpose of passenger；According to the trip purpose of accidental trip passenger, predict that the trip of accidental trip passenger is optimal
Route；According to the trip optimal route of accidental trip passenger, the traffic path of specific trip software user and with fixed row
The traffic path of the car owner of bus or train route line predicts the traffic behavior of road.According to the behavior of cell-phone number user, predict that its own is next
The action of step, to predict road traffic state.Carrier data is taken full advantage of, the essence of road traffic state prediction is improved
Degree.
Detailed description of the invention
Fig. 1 is according to a kind of prediction technique flow chart of road traffic state provided in an embodiment of the present invention；
Fig. 2 is according to a kind of prediction meanss schematic diagram of road traffic state provided in an embodiment of the present invention；
Fig. 3 is the block schematic illustration according to a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Fig. 1 is according to a kind of prediction technique flow chart of road traffic state provided in an embodiment of the present invention, such as Fig. 1 institute
Show, this method comprises:
If cell-phone number user is third type of user, according to carrier data, going out for the third type of user is determined
Row destination；Wherein, the cell-phone number user includes first kind user, Second Type user and the third type of user,
The first kind user is specific trip software user, and the Second Type user is the vehicle with fixed traffic route
Main, the third type of user is accidental trip passenger；The carrier data include the cell-phone number user message registration,
Internet behavior data and social software Content of Communication.
According to the trip purpose of the third type of user, the trip optimal route of the third type of user is obtained.
According to the trip optimal route of the third type of user, the traffic path and described the of the first kind user
The traffic path of two type of user predicts the traffic behavior of road.
Cell-phone number user is divided into: specific trip software user, the car owner with fixed traffic route and accidental trip
Passenger.
Specific trip software includes call a taxi class software and digital map navigation class software etc..It should be noted that being beaten for using
The cell-phone number user of vehicle class software needs the driver by cell-phone number user and carrying cell-phone number user can be regarded as and multiplies one together
Vehicle；Also, for the cell-phone number user for using digital map navigation class software, " self-driving " mode of digital map navigation class software will be only triggered
Cell-phone number user as specific trip software user.The trip purpose of the type user and traffic path be it is specific,
It can directly be exported by specific trip software.
Car owner with fixed traffic route need to meet the following conditions: 1, there is an automobile-used family, 2, there is fixed traffic route.
It will neither be specific trip software user, also the cell-phone number user not for the car owner with fixed traffic route makees
For accidental trip passenger.The travel behaviour of accidental trip passenger tends to accidentally occur, and its traffic path is not advised specifically
Rule.
It should be noted that it is what the information obtained based on big data was classified that cell-phone number user, which is carried out classification,.
Method provided in this embodiment, according to carrier data, with determining the trip purpose of accidental trip passenger；According to idol
With issuing the trip purpose of row passenger, the trip optimal route of accidental trip passenger is predicted；According to the trip of accidental trip passenger
The traffic path of optimal route, the traffic path of specific trip software user and the car owner with fixed traffic route, prediction
The traffic behavior of road.According to the behavior of cell-phone number user, the action of its own next step is predicted, to predict road traffic shape
State.Carrier data is taken full advantage of, the precision of road traffic state prediction is improved.
Based on the above embodiment, if the cell-phone number user is third type of user, according to carrier data, determine institute
With stating the trip purpose of third type of user, before further include:
Determine type belonging to the cell-phone number user；The cell-phone number user is according to priority divided into institute from high to low
State first kind user, the Second Type user and the third type of user；Wherein, if the cell-phone number user is full simultaneously
The cell-phone number user is then included into the high type of priority by sufficient multiple types.
It should be noted that when cell-phone number user is included into corresponding types, pay the utmost attention to be divided into specific trip soft
Cell-phone number user is divided into the type without considering if cell-phone number user belongs to the type just by part user's type
It is classified to other types.
Such as there is car owner of fixed traffic route to input * * woman institute using map for certain, then determine the user be it is specific go out
Row software user is trip purpose * * woman institute.
For another example 6 points of evening one day, certain cell-phone number user is determined neither specific trip software user, nor having
The car owner of fixed traffic route, analyzes the internet behavior data of cell-phone number user, it is found that it searched for * * chafing dish for 40 minutes at 5 points
Shop, while dividing again with the higher same sex relationship cycle of cohesion index of ages by phone, and according to short message content with it
Analyse the * * chafing dish restaurant searched for before it has been purchased by group.So determine that cell-phone number user is accidental trip passenger, trip purpose
Ground is * * chafing dish restaurant.It should be noted that if the displacement of the good friend associated and cell-phone number user, speed, track are equal
It is similar, then consider two people while riding, excludes the judgement for carrying out trip purpose ground to the good friend.
Based on the above embodiment, if the cell-phone number user is third type of user, according to carrier data, determine institute
With stating the trip purpose of third type of user, it specifically includes:
The action trail for obtaining the third type of user obtains the third type of user according to the action trail
First appear the time of one of road in office.The action trail of accidental trip passenger is locating at any one time comprising its own
The step of location information, the action trail of the acquisition accidental trip passenger are as follows: for any road, by described any
The direction of road combs the longitude and latitude of any road；According to the longitude and latitude of any road, any road is combed
Base station group sequence；According to the base station group of any road sequence, the action trail of the accidental trip passenger is obtained.
The third type of user is first appeared into the time on any road as time separation, is obtained
In time interval comprising the time separation, message registration, internet behavior data and the social activity of the third type of user
Software communication content.It should be noted that the length of time interval can be adjusted according to concrete application scene, the present embodiment
This is not construed as limiting.
According to the message registration of the third type of user, internet behavior data and social software Content of Communication, institute is portrayed
The static portrait and dynamic image for stating third type of user, carry out label for the static portrait and the dynamic image respectively
Change.
According to the dynamic image of the static portrait and labeling of labeling, the trip mesh of the third type of user is identified
's.
According to the POI data of the trip purpose of the third type of user and GIS, going out for the third type of user is determined
Row destination.
Specifically, accidental trip passenger is first appeared into the time in certain road as time separation, divided toward m is pushed forward
Clock further obtains message registration, internet behavior data and social software Content of Communication of the accidental trip passenger in m minutes；
The static portrait and dynamic image that accidental trip passenger is portrayed using machine learning algorithm, static state portrait and dynamic image are distinguished
Carry out labeling；Based on pass then algorithm is associated with, using the dynamic image of the static portrait and labeling of labeling, identification is accidental out
The trip purpose of row passenger；The POI data of trip purpose and GIS further according to accidental trip passenger, determines accidental trip passenger
Trip purpose.
If the above process is with not can recognize that trip purpose and the trip purpose of accidental trip passenger, then when capturing again
Between after separation, accidental trip passenger generated message registration, internet behavior data within X meters of vehicle movement of period
With social software Content of Communication, repeat it is above-mentioned according to message registration, internet behavior data and social software Content of Communication,
Obtain the process on the trip purpose ground of accidental trip passenger.
It should be noted that the value of m and X can be adjusted according to concrete application scene, the present embodiment specifically takes it
Value is not construed as limiting.
Based on the above embodiment, the trip purpose according to the third type of user, obtains the third type
The trip optimal route of user, specifically includes:
According to the trip purpose of the third type of user, all traffic paths of the third type of user are obtained.
According to the distance, duration and oil consumption of each traffic path, the optimal road of trip in all traffic paths is obtained
Line.
Wherein, the distance, duration and oil consumption according to each traffic path obtains going out in all traffic paths
Row optimal route, specifically includes:
For each traffic path, defining evaluation function Y is,
Y=w1×(s)+w2×(t)+w3× (q),
Wherein, w1、w2And w3For weight, s is range normalization, and t is duration standardization, and q is oil consumption standardization.
According to GIS, the distance of each traffic path is obtained；According to the historical data of each traffic path, obtain described every
The history duration and history oil consumption of one traffic path；According to the distance of each traffic path, history duration and history oil consumption, obtain
The ideal evaluation function value of each traffic path in the ideal case.
The weight is adjusted, prediction and evaluation functional value of each traffic path under prediction case is obtained.
Loss function is defined, according to the ideal evaluation function value and prediction and evaluation functional value of each traffic path, determines damage
Lose functional value；When the loss function value is greater than preset threshold, the weight is adjusted, until the loss function value is less than institute
State preset threshold.
When the loss function value is less than the preset threshold, using corresponding prediction and evaluation functional value as final prediction
Evaluation function value.
It is in the final prediction and evaluation functional value of all traffic paths, the smallest final prediction and evaluation functional value is corresponding
Traffic path is as the trip optimal route.
Specifically, during obtaining trip optimal route, for each traffic path, variable in need of consideration refers to
The oil consumption for being designated as the distance of traffic path, having travelled duration and traffic path that traffic path is consumed.
According to the distance of traffic path, the oil consumption of duration and traffic path that traffic path is consumed, definition evaluation are travelled
Function Y is,
Y=w1×(s)+w2×(t)+w3× (q),
Wherein, w1、w2And w3For weight, s is range normalization, and t is duration standardization, and q is oil consumption standardization.
It should be noted that the formula, which meets prisoner for drivers ' behavior, is in compliance with rule, in the case where win-win
Formula, otherwise each index continues to continue lower brill modeling by inserting the factors such as vehicle, lane change.
According to the distance of each traffic path, history duration and history oil consumption, each traffic path is obtained in ideal situation
Under ideal evaluation function value.Wherein, the distance of every traffic path is that can calculate on GIS, can also be called given data；
History duration and history oil consumption are obtained by the historical data of this traffic path.
Define w={ w1,w2,w3, defining loss function J (w) is
Wherein, y(i)For ideal evaluation function value,For prediction and evaluation functional value, the value of i is the integer in 1~n, n
For the adjustment number of w, n usually not more than 20.
Appoint and take w, bring above formula into, determine loss function value, when loss function value is greater than preset threshold, adjust w, until damage
It loses functional value and is less than preset threshold.Wherein, the formula of w is adjusted every time are as follows:
Wherein, J be loss function J (w), η be learning rate namely step-length, η as the case may be depending on,It is J (w)
Gradient.
When loss function value is less than the preset threshold, using corresponding prediction and evaluation functional value as final prediction and evaluation
Functional value；
It is in the final prediction and evaluation functional value of all traffic paths, the smallest final prediction and evaluation functional value is corresponding
Traffic path is as trip optimal route.
Based on the above embodiment, described to be used according to the trip optimal route of the third type of user, the first kind
The traffic path of the traffic path at family and the Second Type user, predicts the traffic behavior of road, specifically includes:
According to the trip optimal route of the third type of user, the traffic path and described the of the first kind user
The traffic path of two type of user obtains the road vehicle sum and traffic density；
According to road vehicle sum and traffic density, judge the traffic behavior of the road for congestion, crowded
Or it is unimpeded.
Specifically, by it is accidental trip passenger trip optimal route, it is specific trip software user traffic path and
The traffic path of car owner with fixed traffic route, after calculating X minutes, what the unit length section on certain road will appear
Vehicle fleet and traffic density, and judge the traffic behavior in the unit length section for congestion, crowded or unimpeded.
Will be in the vehicle fleet that observation section occurs after X minutes if Q is, N is the number of track-lines for observing section, then every public affairs
In wagon flow metric density K are as follows:
K=Q/ (N × L),
Wherein, L is the length for observing section, unit km.
As K > a, congestion in road is determined；As b < K < a, determine that road is crowded；As K < b, the coast is clear is determined.
Wherein, threshold value a and threshold value b is obtained by historical data training, and N can be obtained by GIS.Learning cell-phone number user's by bus
On the basis of traffic path, while the speed of the cell-phone number user to be ridden by time series forecasting, and then obtain hand by bus
Machine user is the location of after X minutes, so as to know the vehicle fleet Q of specified observation section appearance.
Wherein, the step of obtaining the traffic path of the car owner with fixed traffic route is as follows:
By the message registration of the cell-phone number user and vehicle insurance phone, with the message registrations of brand 4S customer clothes, installation
The number of APP relevant to vehicle and the access APP be input to it is trained have in automobile-used family decision model, tied according to output
Fruit determines whether the cell-phone number user is to have automobile-used family.
If the cell-phone number user is to have automobile-used family, by there is the change of the position at automobile-used family described in position signaling data acquisition
Change, there will be automobile-used family to be determined as the Second Type user with fixed driving rule.
According to the fixed driving rule of the Second Type user, the traffic path of the Second Type user is obtained.
Specifically, there is automobile-used family decision model to be based primarily upon associated vehicle class APP and web, and with vehicle insurance phone and automobile
The call list data in the shop 4S, by having training and modeling of the automobile-used family as sample progress characteristic, using machine learning
Algorithm identifies car owners user.Modeling index may be selected: take with the message registration of vehicle insurance phone, with brand 4S customer logical
Words record, the APP relevant to vehicle of installation and the number for accessing the APP etc..Wherein message registration is counted by carrier data
It obtains, APP related data is obtained by cooperation party database.
By by user mobile phone number to be measured be input to it is trained have automobile-used family decision model, that is, can recognize certain cell-phone number use
Whether family is to have automobile-used family.
For there is automobile-used family, determine its daily driving rule, i.e., on ordinary days periodically (modelling phase can with it is shorter when
Between unit acquire) by its change in location of position signaling data acquisition, have automobile-used family true to be capable of forming fixed driving rule
Fixed its is that these car owners can determine with the road location of specific time with the car owner of fixed traffic route.
Fig. 2 is according to a kind of prediction meanss schematic diagram of road traffic state provided in an embodiment of the present invention, such as Fig. 2 institute
Show, which includes:
Trip purpose ground determination module, if being that third type of user is sentenced according to carrier data for cell-phone number user
The trip purpose of the fixed third type of user；Wherein, the cell-phone number user includes first kind user, Second Type use
Family and the third type of user, the first kind user are specific trip software user, and the Second Type user is
Car owner with fixed traffic route, the third type of user are accidental trip passenger；The carrier data includes described
Message registration, internet behavior data and the social software Content of Communication of cell-phone number user.
Optimal route of going on a journey obtains module, for the trip purpose according to the third type of user, obtains described the
The trip optimal route of three type of user.
Traffic status prediction module, for the trip optimal route according to the third type of user, the first kind
The traffic path of the traffic path of user and the Second Type user, predicts the traffic behavior of road.
The device of the embodiment of the present invention, the prediction technique that can be used for executing a kind of road traffic state shown in FIG. 1 are implemented
The technical solution of example, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Fig. 3 is the block schematic illustration according to a kind of electronic equipment provided in an embodiment of the present invention.
Referring to Fig. 3, the electronic equipment, comprising: processor (processor) 601, memory (memory) 602 and total
Line 603；
Wherein, the processor 601 and memory 602 complete mutual communication by the bus 603；
The processor 601 is used to call the program instruction in the memory 602, to execute above-mentioned each method embodiment
Provided method, for example, if cell-phone number user is third type of user, according to carrier data, determine described the
The trip purpose of three type of user；Wherein, the cell-phone number user includes first kind user, Second Type user and described
Third type of user, the first kind user are specific trip software user, and the Second Type user is with fixation
The car owner of traffic route, the third type of user are accidental trip passenger；The carrier data includes that the cell-phone number is used
Message registration, internet behavior data and the social software Content of Communication at family；According to the trip purpose of the third type of user,
Obtain the trip optimal route of the third type of user；According to the trip optimal route of the third type of user, described
The traffic path of the traffic path of one type of user and the Second Type user, predicts the traffic behavior of road.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is calculated
When machine executes, computer is able to carry out method provided by above-mentioned each method embodiment, for example, if cell-phone number user is the
Three type of user, then according to carrier data, with determining the trip purpose of the third type of user；Wherein, the cell-phone number
User includes first kind user, Second Type user and the third type of user, the first kind user be it is specific go out
Row software user, the Second Type user are the car owner with fixed traffic route, and the third type of user is accidental
Go on a journey passenger；The carrier data includes that message registration, internet behavior data and the social software of the cell-phone number user is logical
Believe content；According to the trip purpose of the third type of user, the trip optimal route of the third type of user is obtained；Root
According to the trip optimal route of the third type of user, the traffic path of the first kind user and the Second Type user
Traffic path, predict the traffic behavior of road.
Another embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer is readable
Storage medium stores computer instruction, and the computer instruction executes the computer provided by above-mentioned each method embodiment
Method, for example, if cell-phone number user is third type of user, according to carrier data, determine that the third type is used
The trip purpose at family；Wherein, the cell-phone number user includes first kind user, Second Type user and the third type
User, the first kind user are specific trip software user, and the Second Type user is with fixed traffic route
Car owner, the third type of user be accidental trip passenger；The carrier data includes the call of the cell-phone number user
Record, internet behavior data and social software Content of Communication；According to the trip purpose of the third type of user, described in acquisition
The trip optimal route of third type of user；It is used according to the trip optimal route of the third type of user, the first kind
The traffic path of the traffic path at family and the Second Type user, predicts the traffic behavior of road.
Those of ordinary skill in the art will appreciate that: realize that above equipment embodiment or embodiment of the method are only schematic
, wherein the processor and the memory can be physically separate component may not be it is physically separated, i.e.,
It can be located in one place, or may be distributed over multiple network units.It can select according to the actual needs therein
Some or all of the modules achieves the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creative labor
In the case where dynamic, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of prediction technique of road traffic state characterized by comprising
If cell-phone number user determines the trip mesh of the third type of user according to carrier data for third type of user
Ground；Wherein, the cell-phone number user includes first kind user, Second Type user and the third type of user, described
First kind user is specific trip software user, and the Second Type user is the car owner with fixed traffic route, institute
Stating third type of user is accidental trip passenger；The carrier data includes the message registration of the cell-phone number user, online
Behavioral data and social software Content of Communication；
According to the trip purpose of the third type of user, the trip optimal route of the third type of user is obtained；
According to the trip optimal route of the third type of user, the traffic path of the first kind user and second class
The traffic path of type user predicts the traffic behavior of road.
2. the method according to claim 1, wherein if the cell-phone number user is third type of user, root
According to carrier data, with determining the trip purpose of the third type of user, before further include:
Determine type belonging to the cell-phone number user；The cell-phone number user is according to priority divided into described from high to low
One type of user, the Second Type user and the third type of user；Wherein, if satisfaction is more simultaneously by the cell-phone number user
The cell-phone number user is then included into the high type of priority by seed type.
3. the method according to claim 1, wherein if the cell-phone number user is third type of user, root
It is specifically included with determining the trip purpose of the third type of user according to carrier data:
The action trail for obtaining the third type of user obtains the third type of user for the first time according to the action trail
Appear in the time on any road；
The third type of user is first appeared into the time on any road as time separation, obtain comprising
In the time interval of the time separation, message registration, internet behavior data and the social software of the third type of user
Content of Communication；
According to the message registration of the third type of user, internet behavior data and social software Content of Communication, described is portrayed
The static portrait and dynamic image of three type of user, carry out labeling for the static portrait and the dynamic image respectively；
According to the dynamic image of the static portrait and labeling of labeling, the trip purpose of the third type of user is identified；
According to the POI data of the trip purpose of the third type of user and GIS, the trip mesh of the third type of user is determined
Ground.
4. according to the method described in claim 3, it is characterized in that, the action trail for obtaining the third type of user,
It specifically includes:
The longitude and latitude of any road is combed by the direction of any road for any road；
According to the longitude and latitude of any road, the base station group sequence of any road is combed；
According to the base station group of any road sequence, the action trail of the third type of user is obtained.
5. the method according to claim 1, wherein the trip purpose according to the third type of user
Ground obtains the trip optimal route of the third type of user, specifically includes:
According to the trip purpose of the third type of user, all traffic paths of the third type of user are obtained；
According to the distance, duration and oil consumption of each traffic path, the trip optimal route in all traffic paths is obtained.
6. according to the method described in claim 5, it is characterized in that, the distance, duration and oil according to each traffic path
Consumption obtains the trip optimal route in all traffic paths, specifically includes:
For each traffic path, defining evaluation function Y is,
Y=w1×(s)+w2×(t)+w3× (q),
Wherein, w1、w2And w3For weight, s is range normalization, and t is duration standardization, and q is oil consumption standardization；
According to GIS, the distance of each traffic path is obtained；According to the historical data of each traffic path, obtain it is described it is each go out
The history duration and history oil consumption of walking along the street line；According to the distance of each traffic path, history duration and history oil consumption, obtain each
The ideal evaluation function value of traffic path in the ideal case；
The weight is adjusted, prediction and evaluation functional value of each traffic path under prediction case is obtained；
Loss function is defined, according to the ideal evaluation function value and prediction and evaluation functional value of each traffic path, determines loss letter
Numerical value；When the loss function value is greater than preset threshold, the weight is adjusted, until the loss function value is less than described pre-
If threshold value；
When the loss function value is less than the preset threshold, using corresponding prediction and evaluation functional value as final prediction and evaluation
Functional value；
In the final prediction and evaluation functional value of all traffic paths, by the corresponding trip of the smallest final prediction and evaluation functional value
Route is as the trip optimal route.
7. the method according to claim 1, wherein the optimal road of trip according to the third type of user
The traffic path of line, the traffic path of the first kind user and the Second Type user, predicts the traffic behavior of road,
It specifically includes:
According to the trip optimal route of the third type of user, the traffic path of the first kind user and second class
The traffic path of type user obtains the road vehicle sum and traffic density；
According to road vehicle sum and traffic density, judge the traffic behavior of the road for congestion, crowded or smooth
It is logical.
8. the method according to claim 1, wherein the step of obtaining the traffic path of the Second Type user
It is as follows:
By the message registration of the cell-phone number user and vehicle insurance phone, with the message registration of brand 4S customer clothes, installation and vehicle
The number of relevant APP and the access APP be input to it is trained have in automobile-used family decision model, according to output as a result,
Determine whether the cell-phone number user is to have automobile-used family；
It, will by there is the change in location at automobile-used family described in position signaling data acquisition if the cell-phone number user is to have automobile-used family
There is automobile-used family to be determined as the Second Type user with fixed driving rule；
According to the fixed driving rule of the Second Type user, the traffic path of the Second Type user is obtained.
9. a kind of prediction meanss of road traffic state characterized by comprising
Trip purpose ground determination module, according to carrier data, determines institute if being third type of user for cell-phone number user
With stating the trip purpose of third type of user；Wherein, the cell-phone number user include first kind user, Second Type user and
The third type of user, the first kind user be specific trip software user, the Second Type user be with
The car owner of fixed traffic route, the third type of user are accidental trip passenger；The carrier data includes the mobile phone
Message registration, internet behavior data and the social software Content of Communication of number user；
Trip optimal route obtains module and for the trip purpose according to the third type of user obtains the third class
The trip optimal route of type user；
Traffic status prediction module, for the trip optimal route according to the third type of user, the first kind user
Traffic path and the Second Type user traffic path, predict the traffic behavior of road.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute method as described in any of the claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711450559.4A CN109979190B (en) | 2017-12-27 | 2017-12-27 | Road traffic state prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711450559.4A CN109979190B (en) | 2017-12-27 | 2017-12-27 | Road traffic state prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109979190A true CN109979190A (en) | 2019-07-05 |
| CN109979190B CN109979190B (en) | 2020-11-20 |
Family
ID=67071864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711450559.4A Active CN109979190B (en) | 2017-12-27 | 2017-12-27 | Road traffic state prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109979190B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742569A (en) * | 2021-01-08 | 2022-07-12 | 广州视源电子科技股份有限公司 | User life stage prediction method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007218684A (en) * | 2006-02-15 | 2007-08-30 | Fujitsu Ten Ltd | Navigation system and computer-executable program |
| CN103164953A (en) * | 2011-12-19 | 2013-06-19 | 联想(北京)有限公司 | Method and terminal for displaying routes |
| CN104121918A (en) * | 2013-04-25 | 2014-10-29 | 北京搜狗信息服务有限公司 | Real-time path planning method and system |
| CN106504577A (en) * | 2016-11-23 | 2017-03-15 | 青岛海信网络科技股份有限公司 | A kind of park and shift traffic path method and device for planning |
| CN107480784A (en) * | 2017-06-28 | 2017-12-15 | 青岛科技大学 | A kind of mobile phone signaling data pedestrian traffic trajectory predictions method based on deep learning |
-
2017
- 2017-12-27 CN CN201711450559.4A patent/CN109979190B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007218684A (en) * | 2006-02-15 | 2007-08-30 | Fujitsu Ten Ltd | Navigation system and computer-executable program |
| CN103164953A (en) * | 2011-12-19 | 2013-06-19 | 联想(北京)有限公司 | Method and terminal for displaying routes |
| CN104121918A (en) * | 2013-04-25 | 2014-10-29 | 北京搜狗信息服务有限公司 | Real-time path planning method and system |
| CN106504577A (en) * | 2016-11-23 | 2017-03-15 | 青岛海信网络科技股份有限公司 | A kind of park and shift traffic path method and device for planning |
| CN107480784A (en) * | 2017-06-28 | 2017-12-15 | 青岛科技大学 | A kind of mobile phone signaling data pedestrian traffic trajectory predictions method based on deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742569A (en) * | 2021-01-08 | 2022-07-12 | 广州视源电子科技股份有限公司 | User life stage prediction method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109979190B (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Alexander et al. | Assessing the impact of real-time ridesharing on urban traffic using mobile phone data | |
| CN104331422B (en) | A kind of road segment classification estimation method | |
| EP3411817B1 (en) | Designing preferred vehicle routes based on driving scores from other vehicles | |
| Mazloumi et al. | An integrated framework to predict bus travel time and its variability using traffic flow data | |
| CN109754594A (en) | A kind of road condition information acquisition method and its equipment, storage medium, terminal | |
| EP3410348A1 (en) | Method and apparatus for building a parking occupancy model | |
| Lyu et al. | Research on the big data of traditional taxi and online car-hailing: A systematic review | |
| CN110517492A (en) | Based on the traffic route recommended method of parallel integrated study, system, device | |
| JP2010048655A (en) | System and program for evaluating driving situation | |
| Huang et al. | Travel time prediction using tree-based ensembles | |
| CN109642800A (en) | Route searching method and route searching device | |
| Fagan et al. | Intelligent time of arrival estimation | |
| CN111461489A (en) | Route generation method and device, electronic equipment and readable storage medium | |
| Longhi et al. | Car telematics big data analytics for insurance and innovative mobility services | |
| Liu et al. | Themis: A participatory navigation system for balanced traffic routing | |
| Habtie et al. | Artificial neural network based real-time urban road traffic state estimation framework | |
| Rani et al. | Smart bike sharing system to make the city even smarter | |
| CN106133802A (en) | For estimating the apparatus and method of travel speed | |
| Saputra et al. | Accessibility model of BRT stop locations using Geographically Weighted regression (GWR): A case study in Banjarmasin, Indonesia | |
| CN106295868A (en) | Traffic trip data processing method and device | |
| Reggiani et al. | Bicycle network needs, solutions, and data collection systems: A theoretical framework and case studies | |
| CN110986992A (en) | Navigation method and device for unmanned vending vehicle, electronic equipment and storage medium | |
| CN109979190A (en) | A kind of prediction technique and device of road traffic state | |
| CN105825675B (en) | A kind of road trip time calculation method and device based on big data | |
| Oehlerking | StreetSmart: modeling vehicle fuel consumption with mobile phone sensor data through a participatory sensing framework |
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 |