CN104050551B - A kind of intelligent goods dispatch method and system predicted based on vehicle destination - Google Patents
A kind of intelligent goods dispatch method and system predicted based on vehicle destination Download PDFInfo
- Publication number
- CN104050551B CN104050551B CN201410223027.7A CN201410223027A CN104050551B CN 104050551 B CN104050551 B CN 104050551B CN 201410223027 A CN201410223027 A CN 201410223027A CN 104050551 B CN104050551 B CN 104050551B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- similarity
- goods
- sample
- alternative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of intelligent goods dispatch method and system predicted based on vehicle destination, is related to intelligent goods dispatch field.Methods described includes:According to the message data of each vehicle, each sample vehicle and each alternative vehicle are determined;The sample vehicle is to leave for the vehicle of destination from goods starting point;The alternative vehicle is the vehicle through goods starting point to destination on the way each province;The number of administrative areas at the county level for count distance travelled number in the first time period of each sample vehicle and each alternative vehicle, passing through;The similarity of each alternative vehicle and each sample vehicle is calculated according to the number of the distance travelled number in first time period, the administrative areas at the county level passed through;According to the sample vehicle and the similarity of alternative vehicle, each target vehicle is determined from alternative vehicle;The goods delivery information of the goods is sent to target vehicle.The present invention can accurately recognize target vehicle, improve the precision sent with goods information, it is to avoid the wasting of resources, can avoid significantly the resentment of target vehicle.
Description
Technical field
The present invention relates to intelligent goods dispatch field, and in particular to it is a kind of based on vehicle destination predict intelligent goods dispatch method and
System.
Background technology
With the development of technology, goods transport vehicle also can be being registered with goods system, also can intelligently to driver or car with goods system
It is main to provide with goods information, it is existing with the following thinking of goods technological means Main Basiss:
1. vehicle of all vehicle registration ownership place in Distribution Area domain is inquired about.
2. send with goods information to all vehicles.
Prior art is not enough:
Goods of the prior art for a departure place, simply simply with the vehicle of vehicle registration ownership place, if its
In the Distribution Area domain that the goods is located, then send with goods information to all these vehicles.Prior art distinguishes whether car owner can connect
It is very low by the resolution with goods, exist it is a large amount of it is unmatched send with goods information, although the such as vehicle registration of certain several vehicle
Ground belongs to departure place in Distribution Area domain, but which is not transported for a long time in the Distribution Area domain in fact, is simply passed by once in a while, then
The vehicle is not target vehicle, therefore prior art sends information to excessive non-targeted vehicle, not only wastes many operations
Cost, Internet resources are wasted, and non-targeted user can be made to produce resentment, affect the reputation with goods system, from long-range
On be unfavorable for the development with goods business.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome the problems referred to above or at least in part solve on
State the intelligent goods dispatch system predicted based on vehicle destination and the corresponding intelligent goods dispatch predicted based on vehicle destination of problem
Method.
According to one aspect of the present invention, there is provided a kind of intelligent goods dispatch method predicted based on vehicle destination, including:
According to the message data of each vehicle, each sample vehicle and each alternative vehicle are determined;The sample vehicle is from goods
The vehicle of destination is left in starting point;The alternative vehicle is the vehicle through goods starting point to destination on the way each province;
Count distance travelled number in the first time period of each sample vehicle and each alternative vehicle, the administrative areas at the county level passed through
Number;
According to the number of the distance travelled number in first time period, the administrative areas at the county level passed through calculate each alternative vehicle with it is each
The similarity of sample vehicle;
According to the sample vehicle and the similarity of alternative vehicle, each target vehicle is determined from alternative vehicle;
The goods delivery information of the goods is sent to target vehicle.
Alternatively, also include:
Goods confirmation is matched somebody with somebody in the acceptance for receiving target vehicle transmission, and the forward N number of target vehicle of selected and sorted is matched somebody with somebody
Goods.
Alternatively, in the first time period for counting each sample vehicle and each alternative vehicle distance travelled number, process
The number of administrative areas at the county level include:
For a sample vehicle or alternative vehicle, counted in four seasons respectively, car described in each week in each season
Distance travelled number and process administrative areas at the county level number.
Alternatively, the distance travelled number according in first time period, the number of administrative areas at the county level passed through calculate each
Alternative vehicle is included with the similarity of each sample vehicle:
Using logistic regression algorithm according to the distance travelled number and process of vehicle described in season, each week in each season
The number of administrative areas at the county level, calculates the similarity of each alternative vehicle and each sample vehicle.
Alternatively, the employing logistic regression algorithm is according in the traveling of vehicle described in season, each week in each season
The number of the administrative areas at the county level of number of passes and process, calculates the similarity of each alternative vehicle and each sample vehicle, including:
For each vehicle i, in a season, with all arrays into primary vector X1, with the mileage array for travelling weekly
Into secondary vector X2, the 3rd vector X is constituted with the number of the administrative areas at the county level passed through weekly3;
Using R language regression function lm (), with the primary vector X1, secondary vector X2, the 3rd vector X3Prediction fitting is public
Formula Y=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, the value of B, C, D, E, F;
For the place week number x of m weekly1, the mileage number x of traveling2, number x of the administrative areas at the county level of process3, by t=
1/(1+e^(-1*(A x1+Bx4+C x2+Dx5+E x3+Fx6)) calculate the sub- Similarity value t in each weekm;Wherein, the x4=
x1 2, x5=x2 2, x6=x3 2;
By the t in each weekmIt is added, obtains similarities of the vehicle i in the season.
Alternatively, it is described with the primary vector X1, secondary vector X2, the 3rd vector X3Prediction fitting formula Y=AX1+
BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, B, the value of C, D, E, F includes:
Using R language regression function lm (), with vectorial X1,X1 2,X2,X2 2,X3,X3 2The matrix of composition as predictor variable,
With unit vector as target variable, lm () method is substituted into, A, the value of B, C, D, E, F is calculated.
Alternatively, it is described according to the sample vehicle and the similarity of alternative vehicle, each target is determined from alternative vehicle
Vehicle includes:
The similarity of the sample vehicle and alternative vehicle is carried out into normal state, and similarity probability after normal state is more than
Vehicle in 30% alternative vehicle is defined as target vehicle.
Alternatively, the similarity by the sample vehicle and alternative vehicle carries out normal state, and by phase after normal state
Being defined as target vehicle like the vehicle in alternative vehicle of the degree probability more than 30% includes:
By all sample vehicles and similarity y of alternative vehicleiSet { the y of composition0,y1,...,yn, carry out normal state
Obtain obeying the set U={ u of standard normal distribution0,u1,....,un};
For corresponding to each sample vehicle ui, with uiCorresponding probability P (ui), if P is (ui)>0.5, then calculate Pmin=P
(ui) -0.3, and according to the PminDetermine umin;If P is (ui)<0.5, then Pmax=P (ui)+0.3, and according to the PmaxIt is determined that
umax;
With uiAnd uminThe interval of composition, or uiAnd umaxBetween the interval of composition, y is determinediSimilarity select interval;
Select interval to take union the similarity of all sample vehicles, obtain total similarity and select interval;And select yi to exist
It is target vehicle that total similarity selects the alternative vehicle in interval range.
The invention also discloses a kind of intelligent goods dispatch system predicted based on vehicle destination, including:
Vehicle selecting module, is suitable to the message data according to each vehicle, determines each sample vehicle and each alternative vehicle;It is described
Sample vehicle is to leave for the vehicle of destination from goods starting point;The alternative vehicle is to destination edge through goods starting point
The vehicle of way each province;
Statistical module, is suitable to count distance travelled number in the first time period of each sample vehicle and each alternative vehicle, Jing
The number of the administrative areas at the county level crossed;
Similarity calculation module, be suitable to according to the distance travelled number in first time period, pass through administrative areas at the county level
Number calculates the similarity of each alternative vehicle and each sample vehicle;
Target vehicle computing module, is suitable to the similarity according to the sample vehicle and alternative vehicle, from alternative vehicle
Determine each target vehicle;
Goods delivery information sending module, is suitable to target vehicle send the goods delivery information of the goods.
Alternatively, also include:
With goods module, goods confirmation, and the forward N number of mesh of selected and sorted are matched somebody with somebody in the acceptance for being suitable to receive target vehicle transmission
Mark vehicle is carried out with goods..
The intelligent goods dispatch method predicted based on vehicle destination of the invention, has had car using traffic and transportation sector
The operation systems such as supervision/monitoring, during these systems are runed for a long time, can persistently receive numerous vehicle terminations and send
The vehicle message data based on position data.Based on the message data, selected with the starting point of the delivery of goods and destination
A collection of sample vehicle and substantial amounts of alternative vehicle are selected, each alternative vehicle and sample vehicle drive behavior similarity is then analyzed, from
And may be selected and the most like vehicle of sample vehicle drive behavior, go to be transmitted with goods information.Thus the present invention can be accurate
Identification target vehicle, such that it is able to reduce it is meaningless send behavior with goods information, improve the precision sent with goods information, it is to avoid
The wasting of resources, and the resentment of target vehicle can be avoided significantly, the reputation with goods system is improved, is more beneficial for goods industry
The development of business.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of description, and in order to allow the above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the specific embodiment of the present invention.
Description of the drawings
By the detailed description for reading hereafter preferred implementation, various other advantages and benefit are common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for the purpose for illustrating preferred implementation, and is not considered as to the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical part.In the accompanying drawings:
Fig. 1 shows a kind of intelligent goods dispatch method predicted based on vehicle destination according to an embodiment of the invention
Schematic flow sheet;
Fig. 2 shows a kind of intelligent goods dispatch method predicted based on vehicle destination according to an embodiment of the invention
Schematic flow sheet;And
Fig. 3 shows a kind of intelligent goods dispatch system predicted based on vehicle destination according to an embodiment of the invention
Structural representation.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should not be by embodiments set forth here
Limited.On the contrary, there is provided these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
With reference to Fig. 1, the flow process that it illustrates a kind of intelligent goods dispatch method predicted based on vehicle destination of the present invention is shown
It is intended to, can specifically includes:
Step 110, according to the message data of each vehicle, determines each sample vehicle and each alternative vehicle;The sample vehicle
It is to leave for the vehicle of destination from goods starting point;The alternative vehicle is through goods starting point to destination on the way each province
Vehicle;
Traffic and transportation sector has had the operation systems such as vehicle supervision/monitoring at present, in the mistake for runing these systems for a long time
Cheng Zhong, can persistently receive the vehicle message data based on position data that numerous vehicle terminations send, these message datas
Become mass data through accumulation.The present invention for certain batch goods carry out with goods when, with the starting point of the shipments and purpose
Ground, determines sample vehicle and each alternative vehicle from message data.Such as obtain in first time period, leave for from goods starting point
The vehicle of destination is sample vehicle;Obtain in first time period, through the car of goods starting point to destination on the way each province
Be alternative vehicle.
Certainly, in the embodiment of the present invention, certain period of time can be in units of year, it is also possible to which season is unit.
Distance travelled number, the county passed through in the first time period of step 120, each sample vehicle of statistics and each alternative vehicle
The number in level administrative area;
After sample vehicle and alternative vehicle is determined, then inquire about all running orbits of each vehicle of first time period.It is right
In each car, the number of the administrative areas at the county level of the mileage number and process of vehicle traveling in first time period is counted, will at that time
Between section, the mileage number of traveling and process administrative areas at the county level number as the follow-up parameter value for calculating similarity.
Preferably, in the first time period for counting each sample vehicle and each alternative vehicle distance travelled number, process
The number of administrative areas at the county level include:
Step A122, for a sample vehicle or alternative vehicle, is counted in four seasons, each week in each season respectively
Described in vehicle distance travelled number and process administrative areas at the county level number.
The sample vehicle that can be inquired about in nearest 1 year in the present invention and the driving trace of alternative vehicle, so as to exist respectively
In four seasons, count each season each week the vehicle distance travelled number and process administrative areas at the county level number.
Such as car A1, statistical result can be:Spring, (the 1st week, 300 kilometers are travelled, through district number 8;2nd
In week, 600 kilometers are travelled, the 12nd week through district number 13 ..., travel 500 kilometers, through district number 10), it is similar to statistics
Summer, fall and winter.
Step 130, calculates each alternative according to the number of the distance travelled number in first time period, the administrative areas at the county level passed through
The similarity of vehicle and each sample vehicle;
The week that can be counted of the invention, mileage number, district number are that parameter calculates each alternative vehicle and each sample vehicle
Similarity, so as to target vehicle is determined in subsequent step.
Preferably, the distance travelled number according in first time period, the number of administrative areas at the county level passed through calculate each
Alternative vehicle is included with the similarity of each sample vehicle:
Step A132, using logistic regression algorithm according to season, each season it is each week described in vehicle distance travelled
Number and the number of the administrative areas at the county level passed through, calculate the similarity of each alternative vehicle and each sample vehicle.
LogisticRegression algorithms (logistic regression algorithm) are adopted in the present invention, according to season, each season
Each week described in vehicle distance travelled number and process administrative areas at the county level number, calculate each alternative vehicle and each sample car
Similarity.
Further, traveling of the employing logistic regression algorithm according to vehicle described in season, each week in each season
The number of the administrative areas at the county level of mileage number and process, calculates the similarity of each alternative vehicle and each sample vehicle, including:
Step S10, for each vehicle i, in a season, with all arrays into primary vector X1, with what is travelled weekly
Mileage number constitutes secondary vector X2, the 3rd vector X is constituted with the number of the administrative areas at the county level passed through weekly3;
For each season, it is assumed that the variable of all numbers of expression is X1, represent that the variable of mileage number is X2, represent district number
Variable is X3, wherein each variable is the vector of certain car data value composition in a season weekly.Such as X1It is exactly week
Number [1,2 ... .] primary vector that constitutes, X2Be [first week mileage, second week mileage ... .] secondary vector that constitutes,
X3Be [first week through district number, second week through district number ...] and constitute it is the 3rd vectorial.
Step S12, using R language regression function lm (), with the primary vector X1, secondary vector X2, the 3rd vector X3In advance
Survey fitting formula Y=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, the value of B, C, D, E, F;
Hypothesis similarity is Y, can an approximate fitting formula Y=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2, wherein X1 2By
Vectorial X1In each value square vector composition, X2 2、X3 2Similar same process.The fitting formula is based on so, can basis
The X in the known season1, X2, X3Go to be fitted A, the value of B, C, D, E, F.Preferably, it is described with the primary vector X1, secondary vector
X2, the 3rd vector X3Prediction fitting formula Y=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, B, the value bag of C, D, E, F
Include:
Step S121, using R language regression function lm (), with vectorial X1, the matrix of X12, X2, X22, X3, X32 composition is made
For predictor variable, with unit vector as target variable, lm () method is substituted into, A, the value of B, C, D, E, F is calculated.
Lm () usage is as follows:
Lm (fromula, data, subset, weights, na.action, method=" qr ", model=TRUE, x=
FALSE, y=FALSE, qr=TRUE, singular.ok=TRUE, contrasts=NULL, offset ...)
Explanation:Formula is to show regression model, and data is data frame, and subset is the subset of sample view,
Weights is the weighing vector for fitting, and whether na.action video datas include missing values, method be point out for
The method of fitting, model, x, y, qr are logical expressions, if TRUE, should return its value, except first option
Formula is essential option, and other are all options.With regard to lm () function, in the model of my present invention, usage is substantially such as
Under, by the data in unit vector Y=[1,1,1.....] and X1, X11, X2, X22, X3, X33 these vector composition R language
Collection, i.e., the one matrix values=[Y, X1, X12, X2, X22, X3, X32] being made up of each vector, then using function lm (Y
~X1+X12+X2+X22+X3+X32, data=values), the return value of this function is an object, is had inside the object
One array for being called Coefficients, this array contain 6 elements, are exactly X1 successively, X12, X2, X22, X3, X32
Corresponding coefficient.
Step S14, for the place week number x of m weekly1, the mileage number x of traveling2, number x of the administrative areas at the county level of process3,
By t=1/ (1+e^ (- 1* (A x1+Bx4+C x2+Dx5+E x3+Fx6)) calculate the sub- Similarity value t in each weekm;Wherein, institute
State x4=x1 2, x5=x2 2, x6=x3 2;
After the value for obtaining A, B, C, D, E, F, for data x weekly1,x2,x3If, x4=x1 2, x5=x2 2, x6=x3 2,
The similarity in this week can pass through formula t=1/ (1+e^ (- 1* (A x1+Bx4+Cx2+Dx5+E x3+Fx6)) calculated.So
For a season, typically there are 12 similarities t1To t12。
Step S16, by the t in each weekmIt is added, obtains similarities y of the vehicle i in the seasoni。
So for a season, by the t in individual weekmAdd up, that is, obtain similarities yi of the vehicle i in the season.
Step 140, according to the sample vehicle and the similarity of alternative vehicle, determines each target carriage from alternative vehicle
;
After the similarity of sample vehicle and alternative vehicle is obtained, you can determined from alternative vehicle according to these similarities
Target vehicle.
Preferably, it is described according to the sample vehicle and the similarity of alternative vehicle, each target is determined from alternative vehicle
Vehicle includes:
The similarity of the sample vehicle and alternative vehicle is carried out normal state by step A141, and will be similar after normal state
Degree probability is defined as target vehicle more than the vehicle in 30% alternative vehicle.
The similarity of all vehicles is carried out by normal state using the method for normal state, a normal distribution is obtained, then
The vehicle that similarity similarity probability after integration with sample vehicle is more than in 30% alternative vehicle is defined as into target carriage
.
Further, the similarity by the sample vehicle and alternative vehicle carries out normal state, and by after normal state
Similarity probability is defined as target vehicle more than the vehicle in 30% alternative vehicle to be included:
Step S20, by all sample vehicles and similarity y of alternative vehicleiSet { the y of composition0,y1,...,yn, enter
Row normal state obtains the set U={ u for obeying standard normal distribution0,u1,....,un};
For a season or year, it is assumed that the similarity of each vehicle is yi, then the similarity of all alternative vehicles
Set is { y0, y1 ..., yn }.By the method that this similarity set carries out normal state it is:Calculate the equal of the similarity set
It is worth for μ, variance is σ, if u=(y- μ)/σ, now u is exactly the variable for obeying standard normal distribution, calculates the u of each similarity y
Value, one set U=of composition u0, u1 ...., and un }, standard normal distribution is obeyed in the set.
Step S22, for correspondence each sample vehicle ui, with uiCorresponding probability P (ui), if P is (ui)>0.5, then calculate
Pmin=P (ui) -0.3, and according to the PminDetermine umin;If P is (ui)<0.5, then Pmax=P (ui)+0.3, and according to the Pmax
Determine umax;
Step S24, with uiAnd uminThe interval of composition, or uiAnd umaxBetween the interval of composition, y is determinediSimilarity choosing
Select interval;
The similarity of all sample vehicles is selected interval to take union by step S26, is obtained total similarity and is selected interval;And
It is target vehicle to select yi to select the alternative vehicle in interval range in total similarity.
Assume that certain value of sample vehicle in set U is ui, the corresponding probability of ui values is P (ui), if P (ui)>
0.5, then Pmin=P (ui) -0.3 is set, corresponding u values umin of Pmin is obtained according to standard normal distribution table, if P (ui)<0.5,
Pmax=P (ui)+0.3 is then set, corresponding u values umax of Pmax is obtained according to standard normal distribution table, due to u=(y- μ)/σ, institute
With the interval constituted according to u and umin or u and umax, the scope of similarity y is always can determine.Vehicle similarity set
In previous step determine y in the range of vehicle be exactly target vehicle.
Step 150, sends the goods delivery information of the goods to target vehicle.
After determining target vehicle, you can send goods delivery information to the goods delivery terminal of target vehicle.
Preferably, also include:Receive the acceptance that target vehicle sends and match somebody with somebody goods confirmation, and forward N number of of selected and sorted
Target vehicle is carried out with goods.
I.e. in the present invention, each target vehicle can install goods delivery terminal in advance, receive goods delivery information, if driver
Or car owner determines delivery, then acceptance can be sent with goods confirmation to goods system platform (server), with goods system platform
Goods confirmation is matched somebody with somebody in the acceptance for receiving target vehicle transmission, and the forward N number of target vehicle of selected and sorted is carried out with goods.
The intelligent goods dispatch method predicted based on vehicle destination of the invention, has had car using traffic and transportation sector
The operation systems such as supervision/monitoring, during these systems are runed for a long time, can persistently receive numerous vehicle terminations and send
The vehicle message data based on position data.Based on the message data, selected with the starting point of the delivery of goods and destination
A collection of sample vehicle and substantial amounts of alternative vehicle are selected, each alternative vehicle and sample vehicle drive behavior similarity is then analyzed, from
And may be selected and the most like vehicle of sample vehicle drive behavior, go to be transmitted with goods information.Thus the present invention can be accurate
Identification target vehicle, such that it is able to reduce it is meaningless send behavior with goods information, improve the precision sent with goods information, it is to avoid
The wasting of resources, and the resentment of target vehicle can be avoided significantly, the reputation with goods system is improved, is more beneficial for goods industry
The development of business.
With reference to Fig. 2, the stream of a kind of currently preferred intelligent goods dispatch method predicted based on vehicle destination is it illustrates
Journey schematic diagram, can specifically include:
Step 210, leaves for the vehicle of destination as sample vehicle using nearest 1 year from goods starting point;
Step 212, using nearest 1 year vehicle through goods starting point to destination on the way each province as target vehicle;
Step 214, inquires about the driving trace of nearest 1 year sample vehicle and alternative vehicle;
Step 216, travels through all vehicles;
Step 218, driving trace was grouped according to season;
Step 220, for a vehicle, counts the administrative areas at the county level of each week vehicle mileage and process in each season
Number;
Step 222, using LogisticRegression algorithms according to the district of season, week, mileage number and the state in this year
Number calculates vehicle similarity;
Using logistic regression algorithm according to the distance travelled number and process of vehicle described in season, each week in each season
The number of administrative areas at the county level, calculates the similarity of each alternative vehicle and each sample vehicle.
Step 224, for the similarity in each season, collects the similarity of various quarters, similarity is carried out normal state then
Change, and using vehicle of the similarity more than 30% as target vehicle;
Step 226, sends with goods information to target vehicle;
Step 228, is carried out with goods to receiving the vehicle with goods earliest.
The embodiment of the present invention accurately under season time dimension can be carried out accurately to the alternative vehicle in identical season
Identification, obtains target vehicle, so as to carry out with goods.
With reference to Fig. 3, a kind of structural representation of the intelligent goods dispatch system predicted based on vehicle destination of the present invention is it illustrates
Figure, including:
Vehicle selecting module 310, is suitable to the message data according to each vehicle, determines each sample vehicle and each alternative vehicle;
The sample vehicle is to leave for the vehicle of destination from goods starting point;The alternative vehicle is to purpose through goods starting point
The vehicle of ground each province on the way;
Statistical module 320, be suitable to count distance travelled number in the first time period of each sample vehicle and each alternative vehicle,
Through administrative areas at the county level number;
Similarity calculation module 330, is suitable to according to distance travelled number in first time period, the administrative areas at the county level passed through
Number calculates the similarity of each alternative vehicle and each sample vehicle;
Target vehicle computing module 340, is suitable to the similarity according to the sample vehicle and alternative vehicle, from alternative vehicle
It is middle to determine each target vehicle;
Goods delivery information sending module 350, is suitable to target vehicle send the goods delivery information of the goods.
Preferably, also include:
With goods module, goods confirmation, and the forward N number of mesh of selected and sorted are matched somebody with somebody in the acceptance for being suitable to receive target vehicle transmission
Mark vehicle is carried out with goods.
Preferably, the statistical module includes:
First statistical module, is suitable to, for a sample vehicle or alternative vehicle, be counted in four seasons respectively, each season
The number of the administrative areas at the county level of the distance travelled number and process of vehicle described in each week of degree.
Preferably, the similarity calculation module includes:
Logistic regression computing module, is suitable for use with logistic regression algorithm according to car described in season, each week in each season
Distance travelled number and process administrative areas at the county level number, calculate the similarity of each alternative vehicle and each sample vehicle.
Preferably, the logistic regression computing module includes:
Vector generation module, is suitable to for each vehicle i, in a season, with all arrays into primary vector X1, with every
The mileage number composition secondary vector X that week travels2, the 3rd vector X is constituted with the number of the administrative areas at the county level passed through weekly3;
Regression parameter confirms module, is suitable for use with R language regression function lm (), with the primary vector X1, secondary vector
X2, the 3rd vector X3Prediction fitting formula Y=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, the value of B, C, D, E, F;
Sub- similarity calculation module, is suitable to the place week number x for m weekly1, the mileage number x of traveling2, the row at county level of process
Number x of administrative division3, by t=1/ (1+e^ (- 1* (A x1+Bx4+C x2+Dx5+Ex3+Fx6)) calculate the sub- similarity in each week
Value tm;Wherein, the x4=x1 2, x5=x2 2, x6=x3 2;
First similarity calculation module, is suitable to the t in each weekmIt is added, obtains vehicle i similar in the season
Degree.
Preferably, the regression parameter confirms that module includes:
First regression parameter confirms module, is suitable for use with R language regression function lm (), with vectorial X1,X1 2,X2,X2 2,X3,
X3 2The matrix of composition with unit vector as target variable, substitutes into lm () method, is calculated A, B, C, D as predictor variable,
The value of E, F.
Preferably, the target vehicle computing module includes:
First object vehicle computing module, is suitable to for the similarity of the sample vehicle and alternative vehicle to carry out normal state,
And the vehicle in alternative vehicle of the similarity probability after normal state more than 30% is defined as into target vehicle.
Preferably, the first object vehicle computing module includes:
Normal state module, is suitable to similarity y by all sample vehicles and alternative vehicleiSet { the y of composition0,y1,...,
yn, carry out normal state and obtain obeying the set U={ u of standard normal distribution0,u1,....,un};
First range computation module, is suitable to for correspondence each sample vehicle ui, with uiCorresponding probability P (ui), if P
(ui)>0.5, then calculate Pmin=P (ui) -0.3, and according to the PminDetermine umin;If P is (ui)<0.5, then Pmax=P (ui)+
0.3, and according to the PmaxDetermine umax;
First selects interval determination module like degree, is suitable to uiAnd uminThe interval of composition, or uiAnd umaxThe interval of composition
Between, determine yiSimilarity select interval;
It is total to select interval determination module like degree, it is suitable to select interval to take union the similarity of all sample vehicles, obtains
Total similarity selects interval;And select alternative vehicles of the yi in total similarity selection interval range to be target vehicle.
Certainly, similarity summarizing module is may also include, is suitable to be collected for the similarity in each season of a vehicle,
Similarity y after being collectedi。
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together based on teaching in this.As described above, construct required by this kind of system
Structure be obvious.Additionally, the present invention is also not for any certain programmed language.It is understood that, it is possible to use it is various
Programming language realizes the content of invention described herein, and the description done to language-specific above is to disclose this
Bright preferred forms.
In description mentioned herein, a large amount of details are illustrated.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case where not having these details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help understand one or more in each inventive aspect, exist
Above to, in the description of the exemplary embodiment of the present invention, each feature of the present invention is grouped together into single enforcement sometimes
In example, figure or descriptions thereof.However, should the method for the disclosure be construed to reflect following intention:I.e. required guarantor
The more features of feature is expressly recited in each claim by the application claims ratio of shield.More precisely, such as following
Claims it is reflected as, inventive aspect is less than all features of single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as the separate embodiments of the present invention.
Those skilled in the art are appreciated that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more different from embodiment equipment.Can be the module or list in embodiment
Unit or component are combined into a module or unit or component, and can be divided in addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit is excluded each other, can adopt any
Combine to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (includes adjoint power
Profit is required, summary and accompanying drawing) disclosed in each feature can it is identical by offers, be equal to or the alternative features of similar purpose carry out generation
Replace.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments
In some included features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment required for protection appoint
One of meaning can in any combination mode using.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference markss between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element listed in the claims or step.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can come real by means of the hardware for including some different elements and by means of properly programmed computer
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and be run after fame
Claim.
Claims (8)
1. it is a kind of based on vehicle destination predict intelligent goods dispatch method, it is characterised in that include:
According to the message data of each vehicle, each sample vehicle and each alternative vehicle are determined;The sample vehicle is from goods starting
Ground leaves for the vehicle of destination;The alternative vehicle is the vehicle through goods starting point to destination on the way each province;
Count distance travelled number in the first time period of each sample vehicle and each alternative vehicle, pass through administrative areas at the county level
Number;
Each alternative vehicle and each sample are calculated according to the number of the distance travelled number in first time period, the administrative areas at the county level passed through
The similarity of vehicle;
Wherein, specifically include:
For each vehicle i, in a season, with all arrays into primary vector X1, with the mileage number composition second for travelling weekly
Vectorial X2, the 3rd vector X is constituted with the number of the administrative areas at the county level passed through weekly3;
Using R language regression function lm (), with the primary vector X1, secondary vector X2, the 3rd vector X3Prediction fitting formula Y
=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, the value of B, C, D, E, F;
For the place week number x of m weekly1, the mileage number x of traveling2, number x of the administrative areas at the county level of process3, by t=1/ (1+
e^(-1*(Ax1+Bx4+Cx2+Dx5+Ex3+Fx6)) calculate the sub- Similarity value t in each weekm;Wherein, the x4=x1 2, x5=
x2 2, x6=x3 2;
By the t in each weekmIt is added, obtains similarities of the vehicle i in the season;
According to the sample vehicle and the similarity of alternative vehicle, each target vehicle is determined from alternative vehicle;
Wherein, specifically include:
By all sample vehicles and similarity y of alternative vehicleiSet { the y of composition0,y1,...,yn, carry out normal state and taken
From the set U={ u of standard normal distribution0,u1,....,un};
For corresponding to each sample vehicle ui, with uiCorresponding probability P (ui), if P is (ui)>0.5, then calculate Pmin=P (ui)-
0.3, and according to the PminDetermine umin;If P is (ui)<0.5, then Pmax=P (ui)+0.3, and according to the PmaxDetermine umax;
With uiAnd uminThe interval of composition, or uiAnd umaxBetween the interval of composition, y is determinediSimilarity select interval;
Select interval to take union the similarity of all sample vehicles, obtain total similarity and select interval;And select yiDescribed total
It is target vehicle that similarity selects the alternative vehicle in interval range;
The goods delivery information of the goods is sent to target vehicle.
2. the method for claim 1, it is characterised in that also include:
Goods confirmation is matched somebody with somebody in the acceptance for receiving target vehicle transmission, and the forward N number of target vehicle of selected and sorted is carried out with goods.
3. the method for claim 1, it is characterised in that each sample vehicle of statistics and each alternative vehicle first when
Between distance travelled number in section, the number of administrative areas at the county level passed through include:
For a sample vehicle or alternative vehicle, counted in four seasons respectively, vehicle described in each week in each season
The number of the administrative areas at the county level of distance travelled number and process.
4. method as claimed in claim 3, it is characterised in that the distance travelled number according in first time period, pass through
The number of administrative areas at the county level calculate each alternative vehicle and include with the similarity of each sample vehicle:
Using logistic regression algorithm according to the at county level of the distance travelled number and process of vehicle described in season, each week in each season
The number in administrative area, calculates the similarity of each alternative vehicle and each sample vehicle.
5. the method for claim 1, it is characterised in that described with the primary vector X1, secondary vector X2, three-dimensional
Amount X3Prediction fitting formula Y=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, B, the value of C, D, E, F includes:
Using R language regression function lm (), with vectorial X1,X1 2,X2,X2 2,X3,X3 2The matrix of composition as predictor variable, with list
Bit vector is target variable, substitutes into lm () method, is calculated A, the value of B, C, D, E, F.
6. the method as described in claim 3 or 4, it is characterised in that described according to the sample vehicle and the phase of alternative vehicle
Like spending, determine that each target vehicle includes from alternative vehicle:
The similarity of the sample vehicle and alternative vehicle is carried out into normal state, and similarity probability after normal state is more than into 30%
Alternative vehicle in vehicle be defined as target vehicle.
7. it is a kind of based on vehicle destination predict intelligent goods dispatch system, it is characterised in that include:
Vehicle selecting module, is suitable to the message data according to each vehicle, determines each sample vehicle and each alternative vehicle;The sample
Vehicle is to leave for the vehicle of destination from goods starting point;The alternative vehicle is each on the way to destination through goods starting point
The vehicle in province;
Statistical module, is suitable to count distance travelled number in the first time period of each sample vehicle and each alternative vehicle, passes through
The number of administrative areas at the county level;
Similarity calculation module, is suitable to the number meter according to the distance travelled number in first time period, the administrative areas at the county level passed through
Calculate the similarity of each alternative vehicle and each sample vehicle;
Wherein, specifically include:
For each vehicle i, in a season, with all arrays into primary vector X1, with the mileage number composition second for travelling weekly
Vectorial X2, the 3rd vector X is constituted with the number of the administrative areas at the county level passed through weekly3;
Using R language regression function lm (), with the primary vector X1, secondary vector X2, the 3rd vector X3Prediction fitting formula Y
=AX1+BX1 2+CX2+DX2 2+EX3+FX3 2Regression parameter A, the value of B, C, D, E, F;
For the place week number x of m weekly1, the mileage number x of traveling2, number x of the administrative areas at the county level of process3, by t=1/ (1+
e^(-1*(Ax1+Bx4+Cx2+Dx5+Ex3+Fx6)) calculate the sub- Similarity value t in each weekm;Wherein, the x4=x1 2, x5=x2 2,
x6=x3 2;
By the t in each weekmIt is added, obtains similarities of the vehicle i in the season;
Target vehicle computing module, is suitable to the similarity according to the sample vehicle and alternative vehicle, determines from alternative vehicle
Each target vehicle;
Wherein, specifically include:
By all sample vehicles and similarity y of alternative vehicleiSet { the y of composition0,y1,...,yn, carry out normal state and taken
From the set U={ u of standard normal distribution0,u1,....,un};
For corresponding to each sample vehicle ui, with uiCorresponding probability P (ui), if P is (ui)>0.5, then calculate Pmin=P (ui)-
0.3, and according to the PminDetermine umin;If P is (ui)<0.5, then Pmax=P (ui)+0.3, and according to the PmaxDetermine umax;
With uiAnd uminThe interval of composition, or uiAnd umaxBetween the interval of composition, y is determinediSimilarity select interval;
Select interval to take union the similarity of all sample vehicles, obtain total similarity and select interval;And select yiDescribed total
It is target vehicle that similarity selects the alternative vehicle in interval range;
Goods delivery information sending module, is suitable to target vehicle send the goods delivery information of the goods.
8. system as claimed in claim 7 is characterized in that, also include:
With goods module, goods confirmation, and the forward N number of target carriage of selected and sorted are matched somebody with somebody in the acceptance for being suitable to receive target vehicle transmission
Carry out with goods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410223027.7A CN104050551B (en) | 2014-05-23 | 2014-05-23 | A kind of intelligent goods dispatch method and system predicted based on vehicle destination |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410223027.7A CN104050551B (en) | 2014-05-23 | 2014-05-23 | A kind of intelligent goods dispatch method and system predicted based on vehicle destination |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104050551A CN104050551A (en) | 2014-09-17 |
CN104050551B true CN104050551B (en) | 2017-03-29 |
Family
ID=51503360
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410223027.7A Active CN104050551B (en) | 2014-05-23 | 2014-05-23 | A kind of intelligent goods dispatch method and system predicted based on vehicle destination |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104050551B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8874477B2 (en) | 2005-10-04 | 2014-10-28 | Steven Mark Hoffberg | Multifactorial optimization system and method |
CN105300402B (en) * | 2015-09-08 | 2018-03-09 | 北京北大千方科技有限公司 | Vehicle mileage statistical method and device |
CN106022700A (en) * | 2016-06-14 | 2016-10-12 | 深圳深若科技有限公司 | Ad-hoc-network-communication-based cargo sorting and allocation control method and control system |
CN108268678B (en) * | 2016-12-30 | 2021-07-23 | 上海擎感智能科技有限公司 | Driving behavior analysis method, device and system |
CN110428193B (en) * | 2019-06-14 | 2022-03-04 | 上海中旖能源科技有限公司 | Multi-mode liquefied natural gas transport vehicle screening method based on vehicle track data |
CN113205300B (en) * | 2021-07-05 | 2021-09-21 | 北京每日优鲜电子商务有限公司 | Distribution vehicle scheduling method and device, electronic equipment and computer readable medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6711496B2 (en) * | 2001-11-01 | 2004-03-23 | Jack A. Denton | System and method of monitoring cargo container mobility and efficiency |
CN102592208A (en) * | 2011-12-31 | 2012-07-18 | 上海物鼎传感技术有限公司 | Intelligent package tracing system for refrigerated medicament and implementation method thereof |
CN103632245A (en) * | 2013-11-15 | 2014-03-12 | 东莞市艾炜特电子有限公司 | Cloud service-based intelligent production system and implementation method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040111308A1 (en) * | 2002-12-09 | 2004-06-10 | Brighthaul Ltd. | Dynamic resource allocation platform and method for time related resources |
-
2014
- 2014-05-23 CN CN201410223027.7A patent/CN104050551B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6711496B2 (en) * | 2001-11-01 | 2004-03-23 | Jack A. Denton | System and method of monitoring cargo container mobility and efficiency |
CN102592208A (en) * | 2011-12-31 | 2012-07-18 | 上海物鼎传感技术有限公司 | Intelligent package tracing system for refrigerated medicament and implementation method thereof |
CN103632245A (en) * | 2013-11-15 | 2014-03-12 | 东莞市艾炜特电子有限公司 | Cloud service-based intelligent production system and implementation method |
Non-Patent Citations (1)
Title |
---|
第三方物流运输调度信息化解决方案研究;华志明;《中国优秀硕士学位论文全文数据库 经济与管理科学辑》;20101015(第10期);第14-44页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104050551A (en) | 2014-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104050551B (en) | A kind of intelligent goods dispatch method and system predicted based on vehicle destination | |
Aqib et al. | Rapid transit systems: smarter urban planning using big data, in-memory computing, deep learning, and GPUs | |
CN104134349B (en) | A kind of public transport road conditions disposal system based on traffic multisource data fusion and method | |
CN108346292B (en) | Urban expressway real-time traffic index calculation method based on checkpoint data | |
EP2750087A1 (en) | Methods and systems for determining estimated package delivery/pick-up times | |
CN107389085B (en) | Method and device for determining road traffic attributes, computer and storage medium | |
CN105206057B (en) | Detection method and system based on Floating Car resident trip hot spot region | |
Wan et al. | A generic data-driven recommendation system for large-scale regular and ride-hailing taxi services | |
CN113570864B (en) | Method and device for matching running path of electric bicycle and storage medium | |
CN106097717A (en) | The signalized intersections average transit time method of estimation merged based on two class floating car datas | |
Ram et al. | SMARTBUS: A web application for smart urban mobility and transportation | |
Levashev et al. | Modelling parking based trips | |
Macioszek et al. | A back-of-queue model of a signal-controlled intersection approach developed based on analysis of vehicle driver behavior | |
CN106251628B (en) | A kind of method and device of the traffic trip amount of determining motor vehicle | |
Ciancia et al. | Data verification for collective adaptive systems: spatial model-checking of vehicle location data | |
CN110851490A (en) | Vehicle travel common stay point mining method and device based on vehicle passing data | |
CN111062556A (en) | Method and system for judging value of new airline | |
CN111161545B (en) | Intersection region traffic parameter statistical method based on video | |
CN107331164B (en) | A kind of prediction technique of freeway toll station entrance vehicle number | |
CN110659774B (en) | Big data method driven parking demand prediction method | |
CN115164922A (en) | Path planning method, system, equipment and storage medium | |
CN111369810A (en) | Vehicle travel characteristic acquisition method and device, electronic equipment and storage medium | |
M. Abed et al. | The neural network classifier works efficiently on searching in DQN using the autonomous Internet of Things hybridized by the metaheuristic techniques to reduce the EVs’ service scheduling time | |
Xia et al. | A distributed EMDN-GRU model on Spark for passenger waiting time forecasting | |
CN104376712B (en) | Lack transport information complementing device and its method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |