CN102208132B - Traffic predicting device, traffic predicting method - Google Patents
Traffic predicting device, traffic predicting method Download PDFInfo
- Publication number
- CN102208132B CN102208132B CN201110081677.9A CN201110081677A CN102208132B CN 102208132 B CN102208132 B CN 102208132B CN 201110081677 A CN201110081677 A CN 201110081677A CN 102208132 B CN102208132 B CN 102208132B
- Authority
- CN
- China
- Prior art keywords
- traffic
- mentioned
- changing pattern
- data
- volume
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The invention provides a traffic predicting device which can decrease the computational complexity and track the change trend of every moment. The traffic predicting device (10) comprises an average speed data storing part (12); a change pattern chart storing part (14) for storing a plurality of change pattern charts generated by traffics on predetermined time points and illustrating the traffic changes through a matrix composed of tracked predetermined time points and the traffics at the tracked time points; a change pattern chart updating part (19) for updating the values of the matrix elements corresponding to the obtained average speed change data after reading the change pattern charts from the change pattern chart storing part (14); a predicted traffic calculating part (20) for reading the latest traffic change data from the average speed data storing part (12), calculating the estimation values of the plurality of change pattern charts according to the matrix element values corresponding to the read change data and making the traffic corresponding to the change patter chart with the highest estimation value as the predicted traffic; and a display (16) for outputting the predicted traffic.
Description
Technical field
The present invention relates to the device of prognosis traffic volume.
Background technology
In the method for prognosis traffic volume, have and carry out the method for long-term forecasting and the method for carrying out short-term forecasting.For long-term forecasting, mostly adopt with statistical and obtain per diem or the method for the mean value of the attribute of period etc., and the method is practical.For short-term forecasting, known have the method for predicting with time series data in the past or a method (patent documentation 1,2) of carrying out the rote learning based on pattern.
Prior art document:
Patent documentation 1: TOHKEMY 2001-307278 communique
Patent documentation 2: TOHKEMY 2002-298281 communique
Summary of the invention
Long-term forecasting can be applicable to long-term between the prediction of (for example, more than 1 hour), in contrast, short-term forecasting is subject to dynamic tendency institute left and right every day, is therefore difficult to predict.
The method of predicting with the time series data in past or the method for pattern base are because calculated amount is very large, so be not suitable for large scale network to predict.For example, in nearest neighbor method, pattern more increases that the comparison calculated amount between pattern is more.In addition, in above-mentioned prior art, do not consider the variation of dynamic trend (trend), in order to follow the trail of the trend at every moment changing, need to carry out continually the renewal (update) of data.
Therefore, in view of above-mentioned background, the object of the present invention is to provide and a kind ofly can reduce calculated amount, and can follow the trail of the traffic predicting device of the trend at every moment changing.
Traffic predicting device of the present invention comprises: traffic data obtaining section, obtains the data of the volume of traffic of the road of predetermined interval; Traffic data storage part, stores obtained traffic data; Changing pattern figure storage part, store a plurality of changing pattern figure that the volume of traffic on schedule generates, this changing pattern figure represents that by matrix the volume of traffic that reaches above-mentioned each volume of traffic changes, and this matrix is by the Traffic composition of the time of reviewing from predetermined point of time with the time point of tracing back to; Changing pattern figure renewal portion, when obtaining above-mentioned traffic data, from above-mentioned changing pattern figure storage part, read the changing pattern figure corresponding with obtained traffic data, and from above-mentioned traffic data storage part, read the delta data of the above-mentioned volume of traffic, upgrade the value of the matrix key element of the above-mentioned changing pattern figure corresponding with read delta data; Prognosis traffic volume calculating part, from above-mentioned traffic data storage part, read the delta data of the up-to-date volume of traffic, for a plurality of changing pattern figure, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate, and obtain with above-mentioned evaluation of estimate as the volume of traffic corresponding to the highest changing pattern figure is as prognosis traffic volume; And efferent, export above-mentioned prognosis traffic volume.Above-mentioned traffic data obtaining section can receive the data of the relevant vehicle sending from probe vehicles, and the data of the average velocity of the vehicle of obtaining according to these data are used as to above-mentioned traffic data.
Like this, the volume of traffic on schedule generates rectangular a plurality of changing pattern figure of the changing pattern of the volume of traffic that represents to reach this volume of traffic in advance, according to the value of matrix key element corresponding to the delta data with up-to-date, obtain the evaluation of estimate of each changing pattern figure, thereby can alleviate, calculate the computing burden which changing pattern figure up-to-date delta data approaches most, rapidly prognosis traffic volume.In addition, according to the structure of upgrading changing pattern figure when obtaining traffic data, can follow the trail of the trend at every moment changing.
In traffic predicting device of the present invention, above-mentioned changing pattern figure renewal portion can be before the value of matrix key element of upgrading above-mentioned changing pattern figure, by all matrix key element multiplication by constants E (0 < E < 1) of above-mentioned changing pattern figure.Like this, by by the value multiplication by constants E of all matrix key elements of changing pattern figure, can reduce the impact of legacy data on changing pattern figure.
In traffic predicting device of the present invention, above-mentioned changing pattern figure renewal portion can upgrade the value of the matrix key element of the above-mentioned changing pattern figure corresponding with above-mentioned delta data, and also upgrades the value of the matrix key element that its volume of traffic is adjacent with the volume of traffic of above-mentioned corresponding matrix key element.Like this, by also upgrading the value of the matrix key element that the volume of traffic is adjacent, owing to adding value in many matrix key elements, therefore can suitably predict.Can, for the adjacent matrix key element of the volume of traffic, with the little ratio of matrix key element meeting than the volume of traffic, upgrade value.
In traffic predicting device of the present invention, above-mentioned prognosis traffic volume calculating part is multiplied by the matrix key element long with time of reviewing from predetermined point of time by the short matrix key element of time of reviewing from predetermined point of time to be compared the weight coefficient that weight is large and obtains above-mentioned evaluation of estimate.According to this structure, by the traffic data to up-to-date, be weighted, can carry out more suitable traffic volume forecast.
In traffic predicting device of the present invention, the traffic data of the above-mentioned predetermined point of time that above-mentioned changing pattern figure comprises other intervals different from above-mentioned predetermined interval is as matrix key element, above-mentioned changing pattern figure renewal portion is when obtaining above-mentioned predetermined interval and above-mentioned other interval traffic datas, from above-mentioned changing pattern figure storage part, read the changing pattern figure corresponding with the traffic data of above-mentioned predetermined interval, and from above-mentioned traffic data storage part, read the delta data of the volume of traffic of above-mentioned predetermined interval, upgrade the value of the matrix key element of the above-mentioned changing pattern figure corresponding with read delta data, and the value of the matrix key element that renewal is corresponding with above-mentioned other interval traffic datas, above-mentioned prognosis traffic volume calculating part is read the delta data of the up-to-date volume of traffic in above-mentioned other intervals from above-mentioned traffic data storage part, a plurality of changing pattern figure for above-mentioned other intervals, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate, and obtain with above-mentioned evaluation of estimate as the volume of traffic corresponding to the highest changing pattern figure is as above-mentioned other interval prognosis traffic volumes, from above-mentioned traffic data storage part, read the delta data of the up-to-date volume of traffic of above-mentioned predetermined interval, a plurality of changing pattern figure for above-mentioned predetermined interval, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate with the value of matrix key element corresponding to above-mentioned prognosis traffic volume data with obtaining for above-mentioned other intervals, and to obtain with above-mentioned evaluation of estimate be the prognosis traffic volume of the volume of traffic corresponding to the highest changing pattern figure as above-mentioned predetermined interval.At this, other intervals can be both the intervals adjacent with above-mentioned predetermined interval, can also be the intervals with the changing pattern figure larger than predetermined threshold with the similar degree of the changing pattern figure of above-mentioned predetermined interval.Distance (quadratic sum of difference etc.) between the mutual sequential of changing pattern of the enough average velocity of similar degree energy is obtained.
Because the volume of traffic of road influences each other, thus other interval traffic datas different from predetermined interval also used, thus can improve the precision of prediction of the volume of traffic of predetermined interval.
Traffic volume forecasting method of the present invention is used traffic predicting device prognosis traffic volume, and it comprises the following steps: above-mentioned traffic predicting device is obtained the step of traffic data of the road of predetermined interval; Above-mentioned traffic predicting device is stored in the step in traffic data storage part by obtained traffic data; Above-mentioned traffic predicting device is prepared the step of changing pattern figure storage part, a plurality of changing pattern figure that the volume of traffic that this changing pattern figure storage portion stores is put on schedule generates, this changing pattern figure represents that by matrix the volume of traffic that reaches above-mentioned each volume of traffic changes, and this matrix is by the Traffic composition of the time of reviewing from predetermined point of time with the time point of tracing back to; Above-mentioned traffic predicting device is read the changing pattern figure corresponding with obtained traffic data from above-mentioned changing pattern figure storage part when obtaining above-mentioned traffic data, and from above-mentioned traffic data storage part, read the delta data of the above-mentioned volume of traffic, upgrade the step of value of the matrix key element of the above-mentioned changing pattern figure corresponding with read delta data; Above-mentioned traffic predicting device is read the delta data of the up-to-date volume of traffic from above-mentioned traffic data storage part, for a plurality of changing pattern figure, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate, and to obtain with above-mentioned evaluation of estimate be the step of the volume of traffic corresponding to the highest changing pattern figure as prognosis traffic volume; And above-mentioned traffic predicting device is exported the step of above-mentioned prognosis traffic volume.
Program of the present invention is the program of prognosis traffic volume, makes computing machine carry out following steps: the step of traffic data that obtains the road of predetermined interval; Obtained traffic data is stored in to the step in traffic data storage part; Guarantee the generation of the volume of traffic on schedule of storage a plurality of changing pattern figure region and prepare the step of changing pattern figure storage part, this changing pattern figure represents that by matrix the volume of traffic that reaches above-mentioned each volume of traffic changes, and this matrix is by the Traffic composition of the time of reviewing from predetermined point of time with the time point of tracing back to; When obtaining above-mentioned traffic data, from above-mentioned changing pattern figure storage part, read the changing pattern figure corresponding with obtained traffic data, and from above-mentioned traffic data storage part, read the delta data of the above-mentioned volume of traffic, upgrade the step of value of the matrix key element of the above-mentioned changing pattern figure corresponding with read delta data; From above-mentioned traffic data storage part, read the delta data of the up-to-date volume of traffic, for a plurality of changing pattern figure, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate, and to obtain with above-mentioned evaluation of estimate be the step of the volume of traffic corresponding to the highest changing pattern figure as prognosis traffic volume; And the step of exporting above-mentioned prognosis traffic volume.
Traffic volume forecasting method of the present invention and program and traffic predicting device of the present invention are same, can alleviate computing burden, rapidly prognosis traffic volume.In addition, can be by the various structure applications of traffic predicting device of the present invention in Traffic volume forecasting method of the present invention and program.
According to the present invention, by the volume of traffic put on schedule, use rectangular a plurality of changing pattern figure of pattern of the delta data of the volume of traffic that represents to reach this volume of traffic, can alleviate and calculate up-to-date delta data close to the computing burden of which changing pattern figure, and prognosis traffic volume rapidly.
Accompanying drawing explanation
Fig. 1 means the figure of structure of the traffic predicting device of the first embodiment.
Fig. 2 means the figure of the example that is stored in the data in changing pattern figure storage part.
Fig. 3 means the figure of the delta data of average velocity in the past.
(a) of Fig. 4 means the figure of the example of the changing pattern figure before renewal.(b) be for the figure of the renewal of changing pattern figure is described.
Fig. 5 is for the figure of the renewal of changing pattern figure is described.
Fig. 6 means the figure of example of the up-to-date delta data of average velocity.
Fig. 7 means the figure of the calculated example of obtaining changing pattern figure the highest with the consistent degree of delta data in a plurality of changing pattern figure.
Fig. 8 means the figure of hardware configuration of the traffic predicting device of the first embodiment.
Fig. 9 means the figure of the work that the changing pattern figure based on traffic predicting device of the first embodiment upgrades.
Figure 10 means the figure of work of the traffic volume forecast based on traffic predicting device of the first embodiment.
Figure 11 is the figure for illustrating that the changing pattern figure of the second embodiment upgrades.
Figure 12 means the figure of work of the traffic volume forecast based on traffic predicting device of the second embodiment.
Figure 13 is for the figure of Forecasting Methodology of the volume of traffic based on traffic predicting device of the 3rd embodiment is described.
(a) of Figure 14 means the figure of the example that is stored in the changing pattern figure in changing pattern figure storage part.(b) mean the figure of road construction.
Figure 15 is the figure for illustrating that the changing pattern figure of the 4th embodiment upgrades.
Figure 16 means the figure of work of the traffic volume forecast based on traffic predicting device of the 4th embodiment.
Figure 17 (a) means the figure with respect to the adjacent interval in self interval.(b) mean the figure of the example of changing pattern figure.
Figure 18 means the figure of structure of the traffic predicting device 10a of the 6th embodiment.
Figure 19 means the figure of example of the adjacent interval of the 6th embodiment.
Label declaration:
10 traffic predicting devices
11 vehicle data acceptance divisions
12 average velocity data store
13 road-map storage parts
14 changing pattern figure storage parts
15 control parts
16 displays
17 input parts
18 average velocity calculating parts
19 changing pattern figure renewal portions
20 prognosis traffic volume calculating parts
21 display parts
22a, 22e, 23a changing pattern figure
24 adjacent interval determination portions
Embodiment
The traffic predicting device of embodiment of the present invention is described with reference to accompanying drawing below.
(the first embodiment)
Fig. 1 means the figure of structure of the traffic predicting device 10 of the first embodiment.Traffic predicting device 10 is for example arranged on traffic information center, receives the various data of vehicle from probe vehicles (Probe Car) P travelling throughout the country.Use in the present embodiment the position data and the speed data that from probe vehicles P, receive to carry out prognosis traffic volume.
The volume of traffic of predetermined interval can be grasped according to the average velocity of the vehicle travelling at this predetermined interval.For example, the average velocity of vehicle is compared with legal limit and is more more illustrated that road is crowded, the volume of traffic is large.Therefore, in the present embodiment, the data of car speed are processed as the data that represent the volume of traffic.In the present embodiment, take and come prognosis traffic volume to describe as example according to the data that obtain from probe vehicles P, but also can utilize additive method to obtain the data of the volume of traffic.For example, also can use the traffic data of being collected by the wagon detector being arranged on road.
Fig. 2 means the figure of the example that is stored in the changing pattern figure in changing pattern figure storage part 14.Changing pattern figure shown in Fig. 2 means the data of changing pattern of the average velocity data of predetermined interval.Changing pattern figure storage part 14 stores and the changing pattern figure group as shown in Figure 2 of wanting the interval equal number of prognosis traffic volume.
As shown in Figure 2, changing pattern figure storage part 14 stores a plurality of changing pattern Figure 22 a～22e to each interval.Each changing pattern Figure 22 a～22e is illustrated in the changing pattern that predetermined point of time reaches predetermined average velocity.So-called predetermined point of time refers to the up-to-date time point of obtaining data, is recited as " now " in Fig. 2.For example, changing pattern Figure 22 a is illustrated in the changing pattern that predetermined point of time average velocity is " 40km/h～", and changing pattern Figure 22 e is illustrated in predetermined point of time average velocity for the changing pattern of " 0～10km/h ".Changing pattern figure forms by dividing for the numerical range to be scheduled to so every 10km/h the matrix that the elements combination stipulated forms for every 10 minutes, average velocity as the time.Utilize this changing pattern figure, can significantly cut down the data volume of performance changing pattern.
Changing pattern figure renewal portion 19 updates stored in the changing pattern figure in changing pattern figure storage part 14 according to the average velocity data that calculated by average velocity calculating part 18 and the data that are stored in average velocity data store 12.At this, the processing of changing pattern figure renewal portion 19 is described with concrete example.When average velocity calculating part 18 calculates the average velocity data of predetermined interval according to the vehicle data from probe vehicles P, the changing pattern figure corresponding with these average velocity data reads in changing pattern figure renewal portion 19.In this embodiment, when average velocity data are taken as " 40km/h～", read changing pattern Figure 22 a that the average velocity data of " now " are " 40km/h～".In addition, the average velocity data in the past in this interval are read by changing pattern figure renewal portion 19 from average velocity data store 12.
Fig. 3 means the figure of the delta data of read past average velocity.(a) of Fig. 4 means the figure of the changing pattern Figure 22 a before renewal, is the figure that has reprinted the changing pattern Figure 22 a shown in Fig. 2.(b) of Fig. 4 and Fig. 5 are for the figure of the renewal of changing pattern Figure 22 a is described.Changing pattern figure renewal portion 19 is used the delta data (with reference to Fig. 3) of reading to upgrade changing pattern figure (Fig. 4 (a)).Changing pattern figure integral body be first multiplied by the constant E (0 < E < 1) that is less than 1 in changing pattern figure renewal portion 19.(b) of Fig. 4 represents changing pattern figure integral body to be multiplied by 0.9 example.Like this, by by the whole multiplication by constants E of changing pattern figure, reduce the impact of legacy data on changing pattern figure.
In the example shown in Fig. 3, when with the same average velocity that represents to reach " 40km/h～" of changing pattern figure till process time, before 10 minutes, be " 30～40km/h ", before 20 minutes, be " 20～30km/h ", before 30 minutes, be " 20～30km/h " before 40 minutes, to be " 10～20km/h ".The situation that becomes the average velocity of " 40km/h～" through such process is added in the corresponding matrix key element of changing pattern figure.Particularly, as shown in Figure 5, in changing pattern matrix, append the number of times (1 time) of having reviewed each matrix key element.
Then, prognosis traffic volume calculating part 20 is described.Prognosis traffic volume calculating part 20 is read the delta data of up-to-date average velocity from average velocity data store 12, the predicted average speed of calculating predetermined interval according to the delta data of read up-to-date average velocity and changing pattern figure is prognosis traffic volume.
Fig. 6 means the figure of example of the delta data of immediate average velocity.When delta data with shown in the same presentation graphs 6 of changing pattern figure, being now " 20～30km/h ", was " 20～30km/h " before 10 minutes, was " 10～20km/h " before 20 minutes, before 30 minutes, be " 20～30km/h " before 40 minutes, to be " 10～20km/h ".Prognosis traffic volume calculating part 20 is obtained in a plurality of changing pattern figure the changing pattern figure the highest with the consistent degree of the delta data in the past shown in Fig. 6, and obtains the average velocity data corresponding with this changing pattern figure and be used as prognosis traffic volume.
Fig. 7 means the figure of the calculated example of obtaining changing pattern figure the highest with the consistent degree of the delta data shown in Fig. 6 in a plurality of changing pattern figure.As shown in Figure 7, prognosis traffic volume calculating part 20 adds up to obtain by the value of the matrix key element consistent with the up-to-date delta data shown in Fig. 6 the evaluation of estimate that represents consistent degree.Prognosis traffic volume calculating part 20 is obtained average velocity in the future, therefore, make the matrix key element of the average velocity " 20～30km/h " of " now " of up-to-date delta data and " 20～30km/h " of changing pattern figure " before 10 minutes " corresponding, make the matrix key element of the average velocity " 20～30km/h " of " before 10 minutes " of up-to-date delta data and " 20～30km/h " of changing pattern figure " before 20 minutes " corresponding, identical below, make it corresponding with the matrix key element that has respectively moved forward.
In the example shown in Fig. 7, the evaluation of estimate of changing pattern Figure 22 a be " 90 " ... the evaluation of estimate of changing pattern Figure 22 e is " 66 ".In this embodiment, for example, when the evaluation of estimate of changing pattern Figure 22 a is maximum, prognosis traffic volume calculating part 20 is obtained the average velocity " 40km/h～" corresponding with changing pattern Figure 22 a as prognosis traffic volume.
Fig. 8 means the figure of hardware configuration of the traffic predicting device 10 of present embodiment.Traffic predicting device 10 comprises CPU30, storer 31, input part 32, hard disk 33, display 34 and communication interface 35, and these inscapes connect by bus 36.In storer 31, store the program 37 of the function of the traffic predicting device 10 of realizing present embodiment.By CPU30 read routine 37, carry out, realize the function of traffic predicting device 10, carry out processing as described below.In hard disk 33, store average velocity data, road-map and changing pattern figure.That is, hard disk 33 forms average velocity data store 12, road-map storage part 13 and changing pattern figure storage part 14.
Fig. 9 means the figure of renewal work of changing pattern figure of the traffic predicting device 10 of the first embodiment.First traffic predicting device 10 receives vehicle data (S10) from probe vehicles P, calculates and store the average velocity (S12) of vehicle of the predetermined interval of road according to the vehicle data receiving.When a plurality of probe vehicles P from travelling at predetermined interval receive vehicle data, with a plurality of vehicle datas, calculate average velocity.As the computing method of average velocity, length that both can predetermined interval, divided by by the needed time of predetermined interval, in the time of also can having many probe vehicles P in predetermined interval averages the data of the travel speed receiving from many probe vehicles P.
Then, the changing pattern figure (S14) corresponding with the average velocity data that calculate selected and read to traffic predicting device 10 from changing pattern figure storage part 14.For example, when the average velocity data that calculate are " 40km/h～", read changing pattern Figure 22 a (with reference to Fig. 2).At this, the changing pattern figure reading becomes upgating object.All data multiplication by constants E of 10 couples of changing pattern figure that read of traffic predicting device (0 < E < 1) (S16).In the present embodiment, use 0.9 as constant E.
Figure 10 means the figure of work of the traffic volume forecast based on traffic predicting device 10 of the first embodiment.First, traffic predicting device 10 is read the delta data (S30) of the interval up-to-date average velocity of wanting prognosis traffic volume from average velocity data store 12.Afterwards, traffic predicting device 10 is obtained each of interval a plurality of changing pattern figure that will predict and the consistent degree of delta data.Particularly, traffic predicting device 10 is read the value of the matrix key element corresponding with up-to-date delta data in each of a plurality of changing pattern figure, the value reading is added up to calculate the evaluation of estimate (S32) representing with the consistent degree of up-to-date delta data.Traffic predicting device 10 determines that evaluation of estimate is the highest changing pattern figure (S34), obtains the average velocity data corresponding with determined changing pattern figure as prognosis traffic volume (S36).The data (S38) of the prognosis traffic volume of obtaining from display 16 outputs of traffic predicting device 10.At this, enumerated from the example of the data of display 16 prediction of output volume of traffic, but also can send as requested the data of the prognosis traffic volume of obtaining, or broadcast near this predetermined interval.Structure and the work of the traffic predicting device 10 of the first embodiment have been described above.
The traffic predicting device 10 of the first embodiment average velocity data on schedule, generate rectangular a plurality of changing pattern figure of the pattern of the delta data represented to reach the average velocity till this average velocity in advance.Then, by the value of matrix key element corresponding to the delta data with up-to-date being added up to obtain the evaluation of estimate of each changing pattern figure, can alleviate and calculate up-to-date delta data and the immediate computing burden of which changing pattern figure, can fast prediction represent the average velocity of the volume of traffic.
(the second embodiment)
The traffic predicting device 10 of the second embodiment of the present invention then, is described.The basic structure identical with the first embodiment (with reference to Fig. 1) of the traffic predicting device 10 of the second embodiment, but the traffic predicting device 10 of the second embodiment and the difference of the first embodiment are the update methods of changing pattern figure.
Figure 11 is the figure for illustrating that the changing pattern figure of the second embodiment upgrades.In the second embodiment, except upgrading the processing of the matrix key element that average velocity is corresponding with delta data in the past, be also handled as follows: the matrix key element corresponding with respect to the delta data with the past, also upgrade the matrix key element that average velocity is adjacent.Particularly, traffic predicting device 10 adds " 1 " in corresponding matrix key element, and adds " 0.5 " in adjacent matrix key element.
Figure 12 means the figure of renewal work of changing pattern figure of the traffic predicting device 10 of the second embodiment.Traffic predicting device 10 is from probe vehicles P receives vehicle data, in changing pattern figure, in matrix key element corresponding to the average velocity data with the past, add " 1 ", the work (S10～S20) till renewal changing pattern figure is identical with the first embodiment.In the traffic predicting device 10 of the second embodiment, also in the average velocity matrix key element adjacent with corresponding matrix key element, add " 0.5 ", upgrade changing pattern figure (S22).The traffic predicting device 10 of the second embodiment has been described above.
The traffic predicting device 10 of the second embodiment by also upgrade the matrix key element that average velocity is adjacent value and in a plurality of key elements of matrix introducing be worth.Therefore, data are in the past few and have in the situation of damaged value or transition value and also can utilize these damaged values of adjacent Data Update or transition value, therefore can suitably average the prediction of speed.
(the 3rd embodiment)
The traffic predicting device 10 of the 3rd embodiment then, is described.The basic structure identical with the first embodiment (with reference to Fig. 1) of the traffic predicting device 10 of the 3rd embodiment, the traffic predicting device 10 of the 3rd embodiment and the difference of the first embodiment are the Forecasting Methodologies of having used the volume of traffic of changing pattern figure.
Figure 13 is for the Forecasting Methodology of the volume of traffic based on traffic predicting device 10 of the 3rd embodiment is described.In the traffic predicting device 10 of the 3rd embodiment, when obtaining the evaluation of estimate representing with the consistent degree of delta data in the past, be multiplied by with present nearer matrix key element the weight coefficient that weight is larger.Particularly, the value of the matrix key element before 10 minutes is multiplied by weight coefficient " 1.0 ", the value of the matrix key element before 20 minutes is multiplied by weight coefficient " 0.9 ", the value of the matrix key element before 30 minutes is multiplied by weight coefficient " 0.8 ", the value of the matrix key element before 40 minutes is multiplied by weight coefficient " 0.7 ", resulting value is added up to obtain evaluation of estimate.
Usually, the volume of traffic is in the future to more relevant with the volume of traffic of present nearer period, and therefore, the mode larger by the weight of the matrix key element with now nearer is weighted the value of matrix key element, can carry out suitable prediction.
(the 4th embodiment)
The traffic predicting device 10 of the 4th embodiment then, is described.The basic structure identical with the first embodiment (with reference to Fig. 1) of the traffic predicting device 10 of the 4th embodiment, the traffic predicting device 10 of the 4th embodiment and the difference of the first embodiment are, when the average velocity of prediction predetermined interval, also use the interval average velocity data adjacent with predetermined interval.For convenience of explanation, predetermined interval that will predicted average speed is called " self interval ".
In addition, in the traffic predicting device 10 of above-mentioned the 4th embodiment, be stored in the changing pattern figure of changing pattern figure storage part 14 except thering is the delta data of average velocity in self interval, also there are the average velocity data of adjacent interval.The average velocity data of adjacent interval are also same with the average velocity data in self interval, by the numerical range of every 10km/h, represent.In the present embodiment, for the adjacent interval of changing pattern figure, only comprise present average velocity data, do not comprise the delta data till average velocity until now.
(a) of Figure 14 means the figure of the example that is stored in the changing pattern Figure 23 a in changing pattern figure storage part 14.In (a) of Figure 14, only show changing pattern Figure 23 a that in a plurality of changing pattern figure in self interval, average velocity is " 40km/h～".Changing pattern Figure 23 a shown in Figure 14 (a) for to being connected with respectively the changing pattern figure of average velocity data in road construction prediction self interval of adjacent interval 1,2 as shown in Figure 14 (b) at the two ends in self interval.
As shown in Figure 14 (a), in changing pattern Figure 23 a of present embodiment, except the changing pattern of the average velocity in identical with above-mentioned embodiment self interval, also there are the average velocity data with self interval adjacent two adjacent interval 1,2.These data are data of the average velocity of the average velocity in self interval adjacent interval during for " 40km/h～".For example, when self is interval while being " 40km/h～", " 40km/h～" of adjacent interval 1 is " 47 ", when self is interval while being " 30～40km/h ", " 30～40km/h " of adjacent interval 1 is " 26 ", when self is interval while being " 20～30km/h ", " 20～30km/h " of adjacent interval 1 is " 2 ".Hence one can see that, and when the average velocity of adjacent interval is " 40km/h～", often the average velocity in self interval is also " 40km/h～".
Figure 15 means the figure of renewal work of changing pattern figure of the traffic predicting device 10 of the 4th embodiment.First traffic predicting device 10 receives vehicle data (S40) from probe vehicles P, calculates and store the average velocity (S42) of the vehicle of the interval and adjacent interval of self of road according to the vehicle data receiving.When a plurality of probe vehicles P from travelling at predetermined interval receive vehicle data, also can calculate average velocity with a plurality of vehicle datas.
Then, the changing pattern figure (S44) corresponding with the average velocity data that calculate selected and read to traffic predicting device 10 from changing pattern figure storage part 14.For example, when the average velocity data that calculate are " 40km/h～", read changing pattern Figure 23 a (with reference to Figure 14).The changing pattern Figure 23 a reading is upgating object.All data multiplication by constants E of changing pattern Figure 23 a that 10 pairs of traffic predicting devices are read (0 < E < 1) (S46).In the present embodiment, use 0.9 as constant E.
Figure 16 means the figure of work of the traffic volume forecast based on traffic predicting device 10 of the 4th embodiment.First, traffic predicting device 10 is read self delta data of up-to-date average velocity in interval and delta data (S60) of the average velocity data of this adjacent interval of wanting prognosis traffic volume from average velocity data store 12.Afterwards, traffic predicting device 10 is obtained each and the consistent degree of delta data of a plurality of changing pattern figure of adjacent interval.Particularly, traffic predicting device 10, in each of a plurality of changing pattern figure of adjacent interval, reads the value of the matrix key element corresponding with the delta data of adjacent interval, and the value reading is added up to calculate the evaluation of estimate (S62) that represents consistent degree.Traffic predicting device 10 determines that evaluation of estimate is the highest changing pattern figure (S64), obtains the average velocity data corresponding with determined changing pattern figure as the predicted average speed data (S66) of adjacent interval.
Afterwards, traffic predicting device 10 is obtained self a plurality of changing pattern figure in interval and the consistent degree of delta data.Particularly, traffic predicting device 10 reads the value of the matrix key element corresponding with the delta data in self interval and the predicted average speed data of adjacent interval in each of a plurality of changing pattern figure in self interval, and the value reading is added up to calculate the evaluation of estimate (S68) that represents consistent degree.Traffic predicting device 10 determines that evaluation of estimate is the highest changing pattern figure (S70), obtains the average velocity data corresponding with determined changing pattern figure as the predicted average speed data (S72) in self interval.The predicted average speed data (S74) that traffic predicting device 10 outputs are obtained.Explanation herein, has illustrated the example of the average velocity of predicting self interval.When the average velocity of the above-mentioned adjacent interval of prediction, adjacent interval is replaced as to self interval, and carries out work same as described above.Structure and the work of the traffic predicting device 10 of the 4th embodiment have been described above.
The traffic predicting device 10 of the 4th embodiment is except being used the delta data of average velocity in self interval, also use the average velocity data of interactive adjacent interval in road network, thereby can improve the precision of prediction of the volume of traffic in self interval.In addition, in the 4th embodiment, adjacent interval is only used predicted data (the average velocity data of current point in time) and do not used delta data, therefore can suppress calculated load.
(the 5th embodiment)
The traffic predicting device 10 of fifth embodiment of the invention then, is described.The basic structure of the traffic predicting device 10 of the 5th embodiment is identical with the 4th embodiment, but the difference of the traffic predicting device 10 of the 5th embodiment is, be not only and self interval direct-connected interval, also use its next interval average velocity data, obtain the average velocity data in the future in self interval.
Figure 17 (a) means the figure with respect to the adjacent interval in self interval, and (b) of Figure 17 means the figure of the example of changing pattern figure.As shown in Figure 17 (b), with self interval direct-connected interval be adjacent interval 1～5 and adjacent interval 8, but in the present embodiment, the adjacent interval 6 connecting via adjacent interval 3 and the adjacent intervals 7 that are connected via adjacent interval 5 also use act on the adjacent interval of the average velocity of predicting self interval, record these average velocity data.The method of average velocity of predicting self interval with the update method of this changing pattern figure and changing pattern figure is identical with the 4th embodiment.
In the 5th embodiment, be not only and self interval direct-connected interval, also that it is next interval as adjacent interval, also consider the average velocity data that this is interval, thereby can more suitably predict the average velocity data in self interval.In the present embodiment, direct-connected interval and its are next interval as adjacent interval, but may not be to till the next one as the scope of adjacent interval.For example, can be both two below, can be also more than it.In addition, can also will be positioned at the road interval of self zone distance preset range as adjacent interval.
(the 6th embodiment)
The traffic predicting device 10 of sixth embodiment of the invention then, is described.The basic structure of the traffic predicting device 10 of the 6th embodiment is identical with the 5th embodiment, but difference is, in the 6th embodiment, there is following function: according to the variation tendency of each interval average velocity data, obtain there is similar tendency road interval as adjacent interval.The similar interval of delta data may not be adjacent with self interval, but generally speaking, adjacent interval situation is more, is therefore called in this manual " adjacent interval ".
Figure 18 means the figure of structure of the traffic predicting device 10a of the 6th embodiment.The traffic predicting device 10a of the 6th embodiment, except the structure of the 5th embodiment, also has adjacent interval determination portion 24.Adjacent interval determination portion 24 is carried out cluster using the delta data of average velocity as parameter, and the interval that is categorized as same group is processed as adjacent interval.Cluster can be used known method, for example, can use K-means method.
Figure 19 means the figure of example of the adjacent interval of the 6th embodiment.In the example shown in Figure 19, interval 1, interval 2 and interval 7 is the adjacent intervals in self interval.That is, these adjacent intervals 1,2,7 and self interval 4 interval are altogether sorted in same group.With respect to interval 1, interval 2, interval 7 and self interval also become adjacent interval.Clustering processing based on adjacent interval determination portion 24 does not need to carry out at every turn, for example, during being scheduled to (1 month).
In the 6th embodiment, by similarly intervally processing as adjacent interval delta data and self are interval, can predict accurately the average velocity data in self interval.In the present embodiment, in order to find delta data and self interval similarly interval, carry out cluster, but find that similarly interval method is not limited to cluster, also can adopt additive method.
Above, enumerate embodiment and describe traffic predicting device of the present invention in detail, but the invention is not restricted to above-mentioned embodiment.
In the above-described embodiment, the usually example of predicted average speed data of matrix till up-to-date delta data is applied to before 10 minutes of changing pattern figure has been described, but also the delta data till the average velocity data that dope further can be applied to changing pattern figure, has carried out multistage prediction.
Industrial utilizability
The present invention has can alleviate computing burden can obtain fast the such effect of prognosis traffic volume, such as being useful to traffic congestion center, traffic control system, auto-navigation system, Web Map Services etc.
Claims (9)
1. a traffic predicting device, it comprises:
Traffic data obtaining section, it obtains the data of the volume of traffic of the road of predetermined interval;
Traffic data storage part, it stores obtained traffic data;
Changing pattern figure storage part, it stores a plurality of changing pattern figure that the volume of traffic on schedule generates, this changing pattern figure represents to reach the changing pattern of the volume of traffic till above-mentioned each volume of traffic by matrix, this matrix is by the Traffic composition of the time of reviewing from predetermined point of time and the time point traced back to;
Changing pattern figure renewal portion, it reads the changing pattern figure corresponding with obtained traffic data when obtaining above-mentioned traffic data from above-mentioned changing pattern figure storage part, and from above-mentioned traffic data storage part, read the delta data of the above-mentioned volume of traffic, and upgrade the value of the matrix key element of the above-mentioned changing pattern figure corresponding with read delta data; And
Prognosis traffic volume calculating part, it reads the delta data of the up-to-date volume of traffic from above-mentioned traffic data storage part, for a plurality of changing pattern figure, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate, at this, the value of matrix key element is larger, and described evaluation of estimate is larger, and obtains with above-mentioned evaluation of estimate and be used as prognosis traffic volume for the volume of traffic corresponding to the highest changing pattern figure; And
Efferent, it exports above-mentioned prognosis traffic volume.
2. traffic predicting device according to claim 1, is characterized in that,
Above-mentioned traffic data obtaining section receives the data of the relevant vehicle sending from probe vehicles, and uses the average velocity data of the vehicle of obtaining according to these data to be used as above-mentioned traffic data.
3. traffic predicting device according to claim 1 and 2, is characterized in that,
Above-mentioned changing pattern figure renewal portion, before the value of matrix key element of upgrading above-mentioned changing pattern figure, carries out the multiplying of multiplication by constants E to the value of all matrix key elements of above-mentioned changing pattern figure, wherein 0 < E < 1.
4. traffic predicting device according to claim 1 and 2, is characterized in that,
Above-mentioned changing pattern figure renewal portion upgrades the value of the matrix key element of the above-mentioned changing pattern figure corresponding with above-mentioned delta data, and upgrades the value of the matrix key element that its volume of traffic is adjacent with the volume of traffic of above-mentioned corresponding matrix key element.
5. traffic predicting device according to claim 1 and 2, is characterized in that,
Above-mentioned prognosis traffic volume calculating part is multiplied by the matrix key element long with time of reviewing from predetermined point of time by the short matrix key element of time of reviewing from predetermined point of time to be compared the weight coefficient that weight is large and obtains above-mentioned evaluation of estimate.
6. traffic predicting device according to claim 1 and 2, is characterized in that,
The traffic data of the above-mentioned predetermined point of time that above-mentioned changing pattern figure comprises other intervals different from above-mentioned predetermined interval is used as matrix key element,
Above-mentioned changing pattern figure renewal portion is when obtaining above-mentioned predetermined interval and above-mentioned other interval traffic datas, from above-mentioned changing pattern figure storage part, read the changing pattern figure corresponding with the traffic data of above-mentioned predetermined interval, and from above-mentioned traffic data storage part, read the delta data of the volume of traffic of above-mentioned predetermined interval, upgrade the value of the matrix key element of the above-mentioned changing pattern figure corresponding with read delta data, and the value of the matrix key element that renewal is corresponding with above-mentioned other interval traffic datas
Above-mentioned prognosis traffic volume calculating part is read the delta data of the up-to-date volume of traffic in above-mentioned other intervals from above-mentioned traffic data storage part, a plurality of changing pattern figure for above-mentioned other intervals, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate, and obtain with above-mentioned evaluation of estimate and be used as above-mentioned other interval prognosis traffic volumes for the volume of traffic corresponding to the highest changing pattern figure, from above-mentioned traffic data storage part, read the delta data of the up-to-date volume of traffic of above-mentioned predetermined interval, a plurality of changing pattern figure for above-mentioned predetermined interval, according to the value of matrix key element corresponding to the delta data with read and with for the value of matrix key element corresponding to above-mentioned other interval above-mentioned prognosis traffic volume data of obtaining, obtain evaluation of estimate, and obtain with above-mentioned evaluation of estimate and be used as the prognosis traffic volume of above-mentioned predetermined interval for the volume of traffic corresponding to the highest changing pattern figure.
7. traffic predicting device according to claim 6, is characterized in that,
Use the interval adjacent with above-mentioned predetermined interval to be used as above-mentioned other intervals.
8. traffic predicting device according to claim 6, is characterized in that,
The interval that use has following changing pattern figure is used as above-mentioned other intervals:
Be greater than the changing pattern figure of predetermined threshold with the similar degree of the changing pattern figure of above-mentioned predetermined interval.
9. a Traffic volume forecasting method, it carrys out prognosis traffic volume by traffic predicting device, and the method comprises:
Above-mentioned traffic predicting device is obtained the step of traffic data of the road of predetermined interval;
Above-mentioned traffic predicting device is stored in the step in traffic data storage part by obtained traffic data;
Above-mentioned traffic predicting device is prepared the step of changing pattern figure storage part, a plurality of changing pattern figure that the volume of traffic that wherein this changing pattern figure storage portion stores is put on schedule generates, this changing pattern figure represents to reach the changing pattern of the volume of traffic till above-mentioned each volume of traffic by matrix, this matrix is by the Traffic composition of the time of reviewing from predetermined point of time and the time point traced back to;
Above-mentioned traffic predicting device is read the changing pattern figure corresponding with obtained traffic data when obtaining above-mentioned traffic data from above-mentioned changing pattern figure storage part, and from above-mentioned traffic data storage part, read the delta data of the above-mentioned volume of traffic, and upgrade the step of value of the matrix key element of the above-mentioned changing pattern figure corresponding with read delta data;
Above-mentioned traffic predicting device is read the delta data of the up-to-date volume of traffic from above-mentioned traffic data storage part, for a plurality of changing pattern figure, according to the value of matrix key element corresponding to the delta data with read, obtain evaluation of estimate, at this, the value of matrix key element is larger, described evaluation of estimate is larger, and obtains with above-mentioned evaluation of estimate and be used as the step of prognosis traffic volume for the volume of traffic corresponding to the highest changing pattern figure; And
Above-mentioned traffic predicting device is exported the step of above-mentioned prognosis traffic volume.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2010-074591 | 2010-03-29 | ||
| JP2010074591A JP5388924B2 (en) | 2010-03-29 | 2010-03-29 | Traffic volume prediction device, traffic volume prediction method and program |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102208132A CN102208132A (en) | 2011-10-05 |
| CN102208132B true CN102208132B (en) | 2014-01-29 |
Family
ID=44696940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110081677.9A Expired - Fee Related CN102208132B (en) | 2010-03-29 | 2011-03-29 | Traffic predicting device, traffic predicting method |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP5388924B2 (en) |
| CN (1) | CN102208132B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5615312B2 (en) * | 2012-03-26 | 2014-10-29 | 株式会社デンソーアイティーラボラトリ | Traffic jam prediction method and traffic jam prediction device |
| JP5917280B2 (en) * | 2012-05-07 | 2016-05-11 | 住友電気工業株式会社 | Traffic data analysis apparatus and computer program |
| CN104848871B (en) * | 2015-06-09 | 2018-11-16 | 刘光明 | Map and traffic route with traffic condition variation tendency |
| CN105387868A (en) * | 2015-12-25 | 2016-03-09 | 小米科技有限责任公司 | Method and device for making prompt for road information |
| WO2018142566A1 (en) * | 2017-02-03 | 2018-08-09 | 本田技研工業株式会社 | Passage gate determination device, vehicle control system, passage gate determination method, and program |
| US20200041299A1 (en) * | 2017-02-03 | 2020-02-06 | Honda Motor Co., Ltd. | Passing gate determining device, vehicle control system, passing gate determining method, and program |
| KR102083952B1 (en) * | 2018-05-03 | 2020-04-23 | 장현호 | Method for calculating road traffic volumes using moving-probe information |
| JP7172491B2 (en) * | 2018-11-19 | 2022-11-16 | 沖電気工業株式会社 | Traffic flow prediction device, traffic flow prediction method and program |
| CN112053570B (en) * | 2020-08-11 | 2021-07-20 | 江苏纬信工程咨询有限公司 | Urban traffic road network running state monitoring and evaluating method and system |
| CN115034478B (en) * | 2022-06-14 | 2023-06-23 | 西南交通大学 | Traffic flow prediction method based on field self-adaption and knowledge migration |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005241519A (en) * | 2004-02-27 | 2005-09-08 | Xanavi Informatics Corp | Device for predicting traffic information |
| CN200990147Y (en) * | 2006-05-19 | 2007-12-12 | 北京微视新纪元科技有限公司 | Intelligent video traffic monitoring system based on multi-view point |
| CN101231789A (en) * | 2007-01-26 | 2008-07-30 | 株式会社查纳位资讯情报 | Traffic information distribution method, traffic information distribution apparatus and in-vehicle terminal |
| CN101625796A (en) * | 2008-07-10 | 2010-01-13 | 现代自动车株式会社 | Estimation method of traffic information |
| CN101673463A (en) * | 2009-09-17 | 2010-03-17 | 北京世纪高通科技有限公司 | Traffic information predicting method based on time series and device thereof |
| CN101676689A (en) * | 2008-08-21 | 2010-03-24 | 爱信艾达株式会社 | Driving evaluation system and driving evaluation method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4919635A (en) * | 1988-12-19 | 1990-04-24 | The Ritvik Group Inc. | Toy construction assembly |
| JP2002298281A (en) * | 2001-03-30 | 2002-10-11 | Foundation For The Promotion Of Industrial Science | Traffic volume prediction device, traffic volume prediction method, traffic information center and onboard navigation system |
| JP4177228B2 (en) * | 2003-10-24 | 2008-11-05 | 三菱電機株式会社 | Prediction device |
| JP4899756B2 (en) * | 2006-09-29 | 2012-03-21 | アイシン・エィ・ダブリュ株式会社 | Traffic information creation device and traffic information creation method |
-
2010
- 2010-03-29 JP JP2010074591A patent/JP5388924B2/en not_active Expired - Fee Related
-
2011
- 2011-03-29 CN CN201110081677.9A patent/CN102208132B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005241519A (en) * | 2004-02-27 | 2005-09-08 | Xanavi Informatics Corp | Device for predicting traffic information |
| CN200990147Y (en) * | 2006-05-19 | 2007-12-12 | 北京微视新纪元科技有限公司 | Intelligent video traffic monitoring system based on multi-view point |
| CN101231789A (en) * | 2007-01-26 | 2008-07-30 | 株式会社查纳位资讯情报 | Traffic information distribution method, traffic information distribution apparatus and in-vehicle terminal |
| CN101625796A (en) * | 2008-07-10 | 2010-01-13 | 现代自动车株式会社 | Estimation method of traffic information |
| CN101676689A (en) * | 2008-08-21 | 2010-03-24 | 爱信艾达株式会社 | Driving evaluation system and driving evaluation method |
| CN101673463A (en) * | 2009-09-17 | 2010-03-17 | 北京世纪高通科技有限公司 | Traffic information predicting method based on time series and device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| JP5388924B2 (en) | 2014-01-15 |
| CN102208132A (en) | 2011-10-05 |
| JP2011209818A (en) | 2011-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102208132B (en) | Traffic predicting device, traffic predicting method | |
| CN108197739B (en) | Urban rail transit passenger flow prediction method | |
| CN111670340B (en) | Method for acquiring remaining driving mileage of vehicle, electronic equipment and vehicle | |
| JP4932524B2 (en) | Travel time prediction apparatus, travel time prediction method, traffic information providing system and program | |
| JP4506663B2 (en) | Traffic situation prediction apparatus, method and program, route search system, and traffic situation provision system | |
| JP2011138487A (en) | Method and system for traffic prediction based on space-time relation | |
| CN108458716A (en) | A kind of electric vehicle charging air navigation aid based on the prediction of charging pile dynamic occupancy | |
| US8825352B2 (en) | Traffic data prediction device, traffic data prediction method and computer program | |
| CN104346925B (en) | The method and system of prediction running time | |
| CN108496059A (en) | A kind of bearing calibration, device, terminal device and the storage medium of inertia sensor | |
| CN104121916A (en) | Method and system for map matching | |
| JPWO2011074369A1 (en) | Cost evaluation system, method and program | |
| CN102610091B (en) | Method and device for acquiring travelling service information | |
| CN104599002A (en) | Order value predicting method and equipment | |
| CN112818036A (en) | Electric vehicle remaining mileage estimation method and device based on cloud big data | |
| EP3875976A1 (en) | Electricity storage element evaluating device, computer program, electricity storage element evaluating method, learning method, and creation method | |
| CN111862583B (en) | Traffic flow prediction method and device | |
| Guo et al. | Integrated multistep Markov-based velocity predictor of energy consumption prediction model for battery electric vehicles | |
| CN114596709A (en) | Data processing method, device, equipment and storage medium | |
| CN108985966B (en) | Electric quantity consumption calculation method and device, vehicle and computer readable storage medium | |
| CN113593243B (en) | Method and device for predicting toll vehicle type traffic volume in toll road operation period | |
| CN110322046A (en) | A kind of goods amount prediction technique and system eliminating abnormal goods amount and influencing | |
| CN113420942B (en) | Sanitation vehicle real-time route planning method based on deep Q learning | |
| CN113071336B (en) | Range extender control method and system for vehicle and vehicle | |
| CN107645707A (en) | A kind of update method and system of the positioning file based on intelligent terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140129 Termination date: 20210329 |