CN109063727A - Calculate method, apparatus, storage medium and the electronic equipment of track frequency - Google Patents
Calculate method, apparatus, storage medium and the electronic equipment of track frequency Download PDFInfo
- Publication number
- CN109063727A CN109063727A CN201810631466.XA CN201810631466A CN109063727A CN 109063727 A CN109063727 A CN 109063727A CN 201810631466 A CN201810631466 A CN 201810631466A CN 109063727 A CN109063727 A CN 109063727A
- Authority
- CN
- China
- Prior art keywords
- track
- similarity
- tracks
- frequency
- similar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This disclosure relates to a kind of method, apparatus, storage medium and electronic equipment for calculating track frequency.This method comprises: obtaining the track set of mobile object；Clustering based on track similarity is carried out to each track in the set of track, obtain track group, and, obtain the quantity of track not similar with any other track in the set of track, according to track gather in total number of tracks amount and track frequency be positively correlated, the other group quantity of trajectory set and track frequency are negatively correlated, the quantity and track frequency negative correlation of track not similar with any other track calculate track frequency, track frequency of the mobile object on the frequent route representated by these groups can accurately be calculated, for mobile object behavioural analysis, security risk evaluation and test etc. provides new quantizating index.
Description
Technical field
This disclosure relates to data processing field, and in particular, to it is a kind of calculate track frequency method, apparatus, storage
Medium and electronic equipment.
Background technique
With the fast development of technology of Internet of things, a large amount of trip data of mobile object is had accumulated.For example, being led in car networking
Domain just has accumulated a large amount of travelling data of user.Currently, generally passing through the travel time in travelling data, mileage, speed, road
Line state come carry out user behavioural analysis, security risk assessment.
And for for example private mobile objects such as car owner or fleet, with the accumulation of data, the distribution meeting of track
Certain routes are concentrated on, frequent route can be referred to as.The frequency of frequent route and the trip rule of mobile object cease manner of breathing
It closes, is to decide one of mobile object behavior, the factor of security risk.
But there is presently no the frequencies that method can enter and leave frequent route to mobile object to quantify.Therefore, mesh
It is preceding can not also using track frequency as behavioural analysis, security risk because usually analyzing, be mobile object behavioural analysis, safety
Risk evaluation and test etc. brings very big difficulty.
Summary of the invention
In view of this, present disclose provides a kind of method, apparatus, storage medium and electronics for calculating track frequency to set
It is standby, to realize the purpose for accurately calculating track frequency of the mobile object on frequent route.
In the first aspect of the embodiment of the present disclosure, a kind of method for calculating track frequency is provided.This method packet
It includes: obtaining the track set of mobile object；Cluster based on track similarity is carried out to each track in the set of the track
It divides, obtains track group, and, the quantity of track not similar with any other track in the track set is obtained,
In, each track group includes at least two similar tracks；It is frequent according to total number of tracks amount and track in the set of the track
Degree is positively correlated, the other group quantity of the trajectory set and track frequency negative correlation, it is described not with any other track phase
As track quantity and the track frequency it is negatively correlated, calculate the track frequency.
Optionally, obtain based on the clustering of track similarity in each track in the set of track
Before the group of track, further includes: for the track set in every track, judge targeted track starting point whether with
The distance between starting point of at least one track meets between the requirement and terminal of default starting point distance threshold in other tracks
Distance meets the requirement of default terminal distance threshold；If it is not, then targeted track is deleted from the set of the track.
Optionally, it is described according to track gather in total number of tracks amount and track frequency be positively correlated, the trajectory set it is other
Quantity and the track of group quantity and the track frequency negative correlation, the track not similar with any other track
Frequency is negatively correlated, and calculating the track frequency includes: according to total number of tracks amount in the set of the track divided by the rail
The other group quantity of mark group and the quotient that the sum of the quantity of the track or not similar any other track obtains are described to determine
Track frequency.
Optionally, each track in the set of the track obtained based on the clustering of track similarity
It include: that every track in the set of the track and its are calculated by following any similarity calculation mode to track group
One-to-one track similarity between his track, the track similarity include road according to used similarity calculation mode
Line geography similarity, route geography time similarity, period similarity or comprehensive similarity；It will be similar according to calculated track
Degree is determined as that similar track is divided into same track group；The similarity calculation mode includes: route geography similarity meter
Calculation mode: according to the adjacent vital point of two tracks, the proportion in two tracks determines the route geography similarity；
Route geography time similarity calculates mode: in stroke by the time error absolute value mean value of the adjacent vital point of two tracks
In the case where the requirement for meeting prefixed time interval threshold value, the route geography time similarity is adjacent heavy according to two tracks
Main points proportion in two tracks determines；In stroke by the time error absolute value of the adjacent vital point of two tracks
In the case that mean value is unsatisfactory for the requirement of the prefixed time interval threshold value, the route geography time similarity is according to two rails
The adjacent vital point of mark proportion and the prefixed time interval threshold value and stroke in two tracks pass through two tracks
The ratio of the time error absolute value mean value of adjacent vital point determines；Period similarity calculation mode: in going out for two tracks
In the case that the hair time meets same period, the period similarity is default first similarity value, in setting out for two tracks
In the case that time does not meet same period, the period similarity is default second similarity value, and described default first is similar
Angle value is different numerical value from default second similarity value；Route period comprehensive similarity calculates mode: the synthesis is similar
Degree is determined according to the product of the route geography time similarity and the period similarity, alternatively, the comprehensive similarity
It is determined according to the product of the route geography similarity and the period similarity.
In the second aspect of the embodiment of the present disclosure, a kind of device for calculating track frequency is provided.The device packet
It includes: obtaining module, be configured as obtaining the track set of mobile object.Track division module is configured as to the track collection
Each track in conjunction carries out the clustering based on track similarity, obtains track group, wherein each track group is at least
Include two similar tracks.Noise calculation module, be configured as obtaining in the track set not with any other track phase
As track quantity.Frequency computing module is configured as frequent according to total number of tracks amount and track in the set of the track
Degree is positively correlated, the other group quantity of the trajectory set and track frequency negative correlation, it is described not with any other track phase
As track quantity and the track frequency it is negatively correlated, calculate the track frequency.
Optionally, device further include: judgment module is configured as in the track division module in the set of track
Each track carries out the clustering based on track similarity, before obtaining track group, for every in the set of the track
Track, judges whether the starting point of targeted track meets with the distance between the starting point of at least one track in other tracks
The requirement of default starting point distance threshold and the requirement of the default terminal distance threshold of the distance between terminal satisfaction.Removing module, quilt
If be configured to the judgment module be determined as it is no, by targeted track from the track set in delete.
Optionally, the frequency computing module is configured as according to total number of tracks amount in the set of the track divided by described
The quotient that the other group quantity of trajectory set and the sum of the quantity of the track or not similar any other track obtain is to determine
State track frequency.
Optionally, the track division module includes: similarity calculation submodule, is configured as by following any similar
Calculating mode is spent, one-to-one track similarity between the every track and other tracks in the track set is calculated,
The track similarity according to used similarity calculation mode include route geography similarity, route geographical time it is similar
Degree, period similarity or comprehensive similarity.Group divides submodule, is configured as to be determined according to calculated track similarity
Same track group is divided into for similar track.The similarity calculation mode includes: route geography similarity calculation mode:
According to the adjacent vital point of two tracks, the proportion in two tracks determines the route geography similarity；Route is geographical
Time similarity calculates mode: meeting in stroke by the time error absolute value mean value of the adjacent vital point of two tracks and presets
In the case where the requirement of time interval threshold value, the route geography time similarity is according to the adjacent vital point of two tracks two
Proportion determines in track；It is discontented by the time error absolute value mean value of the adjacent vital point of two tracks in stroke
In the case where the requirement of the foot prefixed time interval threshold value, the route geography time similarity is adjacent according to two tracks
Vital point in two tracks proportion and the prefixed time interval threshold value and stroke by the adjacent important of two tracks
The ratio of the time error absolute value mean value of point determines；Period similarity calculation mode: the departure time symbol two tracks
In the case where closing same period, the period similarity is default first similarity value, and the departure time two tracks is not inconsistent
In the case where closing same period, the period similarity is default second similarity value, default first similarity value and institute
Stating default second similarity value is different numerical value；Route period comprehensive similarity calculates mode: the comprehensive similarity is according to institute
The product of route geography time similarity and the period similarity is stated to determine, alternatively, the comprehensive similarity is according to
The product of route geography similarity and the period similarity determines.
In the third aspect of the embodiment of the present disclosure, a kind of computer readable storage medium is provided, is stored thereon with
Computer program realizes the step of any embodiment the method in the disclosure first aspect when program is executed by processor
Suddenly.
In the 4th aspect of the embodiment of the present disclosure, a kind of electronic equipment is provided, comprising: in terms of disclosure third
Computer readable storage medium described in embodiment；And one or more processor, it is described computer-readable for executing
Program in storage medium.
Through the above technical solutions, since the disclosure carries out based on track similarity each track in the set of track
Clustering obtains track group, and, the quantity of track not similar with any other track in the set of track is obtained, and
Go on a journey track total quantity it is more, be the precondition that route can be more frequent, with frequent angle value be positively correlated, not with any track
Similar track is fewer, and track frequency is higher, belongs to negative correlation, and a track group represents a frequent route, group
Number is fewer, illustrates that track concentration degree is higher, and the track on the frequent route of single is more, and track frequency is also higher, belongs to
In negative correlation, therefore, the disclosure according to track gather in total number of tracks amount and track frequency be positively correlated, the other group of trajectory set
Quantity and the quantity of negatively correlated, not similar with any other track track of the track frequency and the track frequency are negative
The track frequency that correlometer calculates, it is frequent on the frequent route representated by these groups can accurately to embody mobile object
Degree.As it can be seen that the method that the disclosure provides can quantify the frequency of frequent route.And the track frequency of frequent route
It is closely bound up with the trip rule of mobile object, it is to decide one of mobile object behavior, the factor of security risk.Therefore this public affairs
It opens and provides new quantizating index for mobile object behavioural analysis, security risk evaluation and test etc., to realize more accurate movement
Object behavior analysis, security risk evaluation and test etc..
Other feature and advantage of the disclosure will the following detailed description will be given in the detailed implementation section.
Detailed description of the invention
Attached drawing is and to constitute part of specification for providing further understanding of the disclosure, with following tool
Body embodiment is used to explain the disclosure together, but does not constitute the limitation to the disclosure.In the accompanying drawings:
Fig. 1 is the flow chart according to the method for the calculating track frequency shown in an exemplary embodiment of the disclosure.
Fig. 2 is the flow chart according to the method for the calculating track frequency shown in the another exemplary embodiment of the disclosure.
Fig. 3 is the block diagram according to the device of the calculating track frequency shown in an exemplary embodiment of the disclosure.
Fig. 4 is the block diagram according to the device of the calculating track frequency shown in the another exemplary embodiment of the disclosure.
Fig. 5 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Specific embodiment
It is described in detail below in conjunction with specific embodiment of the attached drawing to the disclosure.It should be understood that this place is retouched
The specific embodiment stated is only used for describing and explaining the disclosure, is not limited to the disclosure.
Fig. 1 is the flow chart according to the method for the calculating track frequency shown in an exemplary embodiment of the disclosure.Such as
Shown in Fig. 1, this method be may comprise steps of:
In step 110, the track set of mobile object is obtained.
In the disclosure, the mobile object can refer to the user etc. of vehicle, handheld mobile device.Track for example can be
The wheelpath of vehicle, data can be obtained by GPS device, a series of longitude of location points that passes through including driving, latitude, when
Between etc. information.The continuous position point passed through in driving conditions constitutes track according to time series, by unique track ID in number
According to being identified in library.For another example vehicle launch (data start to acquire) to vehicle stall (adopt by data stopping in some scenes
Collection) track that is formed during this section also can be considered a track.
It can significantly if each point is involved in operation due to that generally in longer track can include many tracing points
Increase and calculate memory and reduce computational efficiency, therefore, the disclosure can will can characterize the main position in track in several tracks
Confidence breath and the vital point of the direction of motion extract, and it is each to form several tracks according to the temporal information of each vital point
From new track sets Li={ p1,p2,…,pn(i), to obtain track set.N (i) indicates of i-th track vital point
Number, p={ longitude, latitude, time }, that is, the GPS longitude and latitude acquired, temporal information.Vital point for example may include
The starting point of track, terminal, turning point.It is of course also possible to extract the next or several tracing point and terminal of such as starting point
Previous or several tracing points and turning point obtain track as vital point and gather, and the disclosure is to this and is not limited.
Wherein, the identification of turning point can be realized based on GPS bearing data, and turning Rule of judgment can refer to following public affairs
Formula, wherein thres is parameter preset, and the size of parameter preset thres depends on the bend curvature to be identified, such as curvature
It is bigger, thres value can be set bigger, if curvature is smaller, thres value can be set smaller, that is to say, that thres
Preset value is smaller, and the turning identified will be more, and road similitude matching accuracy can be higher, but computational efficiency can phase
To lower, therefore, can be preset according to actual needs；Δ bearing is azimuthal variation amount, when Δ bearing is accumulative
Into a certain range section, it can differentiate that vehicle is turned.Formula are as follows:
In the step 120, each track in the set of the track obtained based on the clustering of track similarity
To track group, and, obtain the quantity of track not similar with any other track in the track set, wherein each
Track group includes at least two similar tracks.
It should be noted that the disclosure is to the calculating mode of track similarity and is not limited.For example, a possible reality
It applies in mode, every track in the set of the track and other can be calculated by following any similarity calculation mode
One-to-one track similarity between track, the track similarity include route according to used similarity calculation mode
Geographical similarity, route geography time similarity, period similarity or comprehensive similarity.It will be according to calculated track similarity
It is determined as that similar track is divided into same track group.
Wherein, the similarity calculation mode may include: route geography similarity calculation mode, the geographical time phase of route
Mode is calculated like degree calculating mode, period similarity calculation mode, route period comprehensive similarity.It is illustrated separately below:
Route geography similarity calculation mode: the route geography similarity is according to the adjacent vital point of two tracks two
Proportion determines in track.Wherein, adjacent vital point refer in two tracks in chronological order in identical precedence and
Vital point of the distance in default neighbor distance threshold range, default neighbor distance threshold range can be rule of thumb arranged.Phase
Adjacent vital point proportion in two tracks can be obtained by a variety of calculations, and the disclosure is to this and is not limited.
For example, the vital point number of two tracks can be counted respectively, the vital point of wherein the largest number of tracks of vital point is taken
Number n, in two tracks it is each pair of it is adjacent it is important count one group, take the adjacent vital point group number m in two tracks, then the phase of two tracks
Adjacent vital point proportion in two tracksFor another example the total of the vital point number of two tracks can be counted
Number, counts the sum of the adjacent vital point number in two tracks, then the adjacent vital point of two tracks institute's accounting in two tracks
The quotient that example can obtain for the sum of the adjacent vital point number in two tracks divided by the sum of the vital point number of two tracks.
Route geography time similarity calculates mode: exhausted by the time error of the adjacent vital point of two tracks in stroke
In the case where the requirement for meeting prefixed time interval threshold value to value mean value, the route geography time similarity is according to two tracks
Adjacent vital point in two tracks proportion determine；It is missed in stroke by the time of the adjacent vital point of two tracks
In the case that poor absolute value mean value is unsatisfactory for the requirement of the prefixed time interval threshold value, the route geography time similarity root
According to the adjacent vital point of two tracks, proportion and the prefixed time interval threshold value and stroke pass through two in two tracks
The ratio of the time error absolute value mean value of the adjacent vital point of track determines.
For example, route geography time similarity calculates mode can be indicated with following formula:
Wherein, n is the maximum value of vital point number in two tracks, for example, the important of two tracks can be counted respectively
Point number, taking the vital point number of wherein the largest number of tracks of vital point is n, and m is each pair of adjacent heavy in two tracks
The adjacent vital point group number in two tracks in the case where counting one group, E (Δ T) are the adjacent vital point that stroke passes through two tracks
Time error absolute value mean value, TCFor prefixed time interval threshold value, (chronomere is greater than 0, such as can be set to 10 points
Clock), characterize the acceptable time difference of two adjacent vital points.Adjacent vital point refers to exist in chronological order in two tracks
In identical precedence and distance is presetting the vital point in neighbor distance threshold range, and presetting neighbor distance threshold range can basis
Experience setting.The conditional expression that the distance of the adjacent vital point of two tracks need to meet is d=| | pi-pj| |≤ε, ε: default
Neighbor distance threshold value can be rule of thumb arranged.Adjacent vital point two o'clock distance can use following formula (1) calculating:
Assuming that in geographical space two points latitude and longitude coordinates be respectively (startlng, startLat), (endLng,
EndLat), latitude and longitude value is converted into radian value by following formula (2):
Radian=angle * (π/180 °) (2)
Coordinate (slng, slat), (elng, the elat) of two points are obtained after conversion.It substitutes into formula (1) and obtains distance between two points
From.Wherein radius is earth radius (KM), and value is about 6378.137.
By the above route geography time similarity calculate mode as it can be seen that route geography time similarity include section and when
Between two confinement dimensions similitude, characterize similarity degree of two tracks on room and time, numerical intervals are [0,1].
It can embody two tracks the similarity degree of vital point spatial position and by track vital point it is temporal similar
Degree, calculated track similarity can be divided into same section and same time, go the same way in the case where determining the similar situation in two tracks
Section two kinds of similar situations of different time.When E (Δ T) is less than or equal to TCWhen, time interval, which meets, is expected, it is believed that two tracks exist
Meet interval threshold on time dimension, then time match similarity is 1, i.e. the time is upper completely similar.When E (Δ T) is greater than TCWhen,
Threshold range is exceeded, beyond more, error amount is bigger, then similarity value is smaller.TCAs constant, E (Δ T) is as change
Amount, ratio be formed by monotonic decreasing function can the most directly, simply characterize this relationship.Therefore, the disclosure provides
Route similarity calculation mode can accurately calculate similarity of the route in two confinement dimensions in section and time.
Period similarity calculation mode: in the case where the departure time of two tracks meeting same period, the period
Similarity is default first similarity value, in the case where the departure time of two tracks not meeting same period, the period
Similarity is default second similarity value, and default first similarity value is different numbers from default second similarity value
Value.
For example, period similarity calculation mode can be indicated with following formula:
Wherein, T (LiT(start),LjT(start)) referring to the departure time, R is for judging whether the departure time is same period
Rule.
Period similarity calculation mode can be the constraint for calculating mode to route geography time similarity and expand, the period
The similarity that similarity calculation mode computation goes out is there are two types of situation, in one cycle or not in one cycle.For example, default
First similarity value and default second similarity value can be indicated by numerical value 0 and 1, be 1 with the period, different cycles 0.
For example, for judging whether the departure time is that the rule of same period may include:
(1) fixed time period in one day is set out.
Departure time refers to for same period: can not be on the same day, but the period is identical, for example, being all 2 to point out in the afternoon
Hair, then be same period.
(2) the fixation week in one week sets out.
Departure time refers to for same period: it can not be on the same day, but week is identical, for example, being gone out on Thursday
Hair, then be same period.
(3) fixed dates in January sets out.
Departure time refers to for same period, can not be on the same day, but the date is identical, for example, being all the 2 of a middle of the month
It number sets out, is then same period.
By the above period similarity calculation mode as it can be seen that period similarity can accurately be embodied from the periodicity of track
The similarity degree of mobile object travel time.
Route period comprehensive similarity calculate mode: the comprehensive similarity according to the route geography time similarity with
The product of the period similarity determines, alternatively, the comprehensive similarity is according to the route geography similarity and the week
The product of phase similarity determines.
Route period comprehensive similarity calculates mode and can be indicated with following formula:
S*=S'S
Mode is calculated by the above route period comprehensive similarity as it can be seen that the track similarity that the mode computation goes out is determining
In the similar situation in two tracks, the fixed route fixed cycle can be divided into, fixed route is not fixed the period, it is solid to be not fixed route
Three kinds of similar situations of fixed cycle are to measure rail from the geographical temporal similitude of route and trip two dimensions of periodical similarity
The similarity of mark, it is more accurate that track similarity calculation obtains.
It should be noted that the disclosure obtains the quantity of track not similar with any other track in the track set
Implementation it is unlimited.For example, can when carrying out group division, will not track similar with any other track, also will
Any group of other track is not belonging to add up.For another example can be after completing group and dividing, by the track number in all groups
Amount carries out adding up to obtain all total number of tracks amounts with similar track, and the total number of tracks amount of second hand rail trace set subtracts tool
There is the total number of tracks amount of similar track, obtains the quantity of track not similar with any other track in the set of track.
In step 130, it is positively correlated according to total number of tracks amount and track frequency in the set of the track, the trajectory set
Other group quantity and the quantity of negatively correlated, the described track not similar with any other track of the track frequency with it is described
Track frequency is negatively correlated, calculates the track frequency.
It, can be other divided by the trajectory set according to total number of tracks amount in the set of the track in one possible embodiment
Quotient that group quantity and the sum of the quantity of the track or not similar any other track obtain determines that the track is frequent
Degree.The embodiment by track gather in total number of tracks amount and the other group quantity of the trajectory set and it is described not with it is any its
That the ratio of the sum of the quantity of the similar track in his track comes is accurate, directly, simply characterize positive and negative correlativity, obtain track
Frequency, it is high-efficient.It is of course also possible to characterize above-mentioned positive and negative correlativity by other expression formulas, the disclosure to this not
It is limited.
For example, the track frequency in the embodiment can be calculated with following formula:
M is total number of tracks amount in the set of track, and l is group quantity, and f is trace number in certain classification i.
Through the above technical solution as it can be seen that due to the disclosure to track set in each track carry out based on track it is similar
The clustering of degree obtains track group, and, obtain the number of track not similar with any other track in the set of track
Amount, and the total quantity for track of going on a journey is more, is the precondition that route can be more frequent, is positively correlated with frequent angle value, not with appoint
What similar track in track is fewer, and track frequency is higher, belongs to negative correlation, and a track group represents a frequent road
Line, group number is fewer, illustrates that track concentration degree is higher, and the track on the frequent route of single is more, and track frequency is also
It is higher, belong to negative correlation, therefore, the disclosure according to track gather in total number of tracks amount and track frequency be positively correlated, trajectory set
Quantity and the track of other group quantity and the track frequency negative correlation, track not similar with any other track
The negatively correlated calculated track frequency of frequency, can accurately embody mobile object frequent route representated by these groups
On track frequency.And frequently the track frequency of route and the trip rule of mobile object are closely bound up, are to decide shifting
One of dynamic object behavior, factor of security risk.For example, carry out in the evaluation and test of driving safety risk, it can be by the rail of frequent route
The driving characteristics such as mark frequency and driving duration, mileage, speed, bad steering behavior, road condition are collectively as independent variable spy
It levies vector and carries out data analysis, improve the driving risks and assumptions of driving safety risk evaluation and test function, improve driving safety risk and comment
The accuracy of survey, that is, the accuracy of risk identification.Therefore, the disclosure is mobile object behavioural analysis, security risk evaluation and test
Etc. providing new quantizating index, to realize more accurate mobile object behavioural analysis, security risk evaluation and test etc..
In order to improve the computational efficiency of track frequency, in a possible embodiment, the disclosure is in gathering track
Each track carry out the clustering based on track similarity, before obtaining track group, the track collection can also be directed to
Whether every track in conjunction judges the starting point of targeted track between the starting point of at least one track in other tracks
Distance meets the requirement of default starting point distance threshold and the distance between terminal meets the requirement for presetting terminal distance threshold.Such as
Fruit is no, then deletes targeted track from the set of the track.In order to understand the embodiment more easily, below again
In conjunction with Fig. 2, which is described in detail.
Fig. 2 is the flow chart according to the method for the calculating track frequency shown in an exemplary embodiment of the disclosure.Such as
Shown in Fig. 2, this method be may comprise steps of:
In step 210, the track set D of mobile object, all unmarked group in all tracks are obtained.
Wherein,M is trace number
In a step 220, appoint from set D and take a track L, traverse residual track in D.
In step 220a, judge whether that the starting point distance of the track currently traversed and track L are less than default start point distance
From threshold value, and terminal distance is less than default terminal distance threshold.
In step 220b, if the starting point of the track currently traversed and track L distance are more than or equal to default start point distance
It is more than or equal to default terminal distance threshold with a distance from threshold value or terminal, judges whether D set still has residual track not traverse
It arrives.If not, entering step 220k.
In step 220c, if it is, continuing to traverse, and back in step 220a.
In step 220d, if the starting point of the track currently traversed and track L distance are less than default starting point apart from threshold
Value, and terminal distance is less than default terminal distance threshold, then carries out track similarity meter to the track and track L that currently traverse
It calculates, obtains track similarity.
In step 220e, judge whether calculated track similarity is greater than default similarity threshold.If not, into
Step 220f.If it is, entering step 220h.
In step 220f, judge whether D set still has residual track not traverse.
In step 220g, if D set still has residual track not traverse, continue to traverse, and return to step
In 220a.If D set residual track has been completed to traverse, 220k is entered step.
In step 220h, if calculated track similarity is greater than default similarity threshold, two tracks are determined
It is similar.
In step 220i, if the track currently traversed is similar to track L, and track L does not do group label, then creates
New track group is built, is determined as that similar track is added in newly created track group by track L and with L, enters step
220f, to continue to traverse.
It should be noted that being determined as that similar track is added to newly created track by track L and with L in step 220i
It after group, can continue to traverse, can also terminate to traverse.Because being determined as that similar track is added to new creation by track L and with L
Track group when, not by track similar with L from D gather delete, that is to say, that track similar with L is still present in D
In set.Namely: in the case where terminating traversal, other similar tracks can be in subsequent similar comparison, due to identical as L
The track of classification is similar and is grouped into same category, has no effect on division classification, but efficiency is relatively low；The case where not terminating traversal
Under, the last item track can be traversed always, to all be divided into making the complete traversal of track similar with track L one time same
One classification, it is more efficient.
In step 220j, if two tracks are similar, and the existing group label of track L, then it will be determined as to L similar
Track be added in the affiliated track group of L, and do group label for the similar track, return to step 220f, so as to after
Continuous traversal.
It is understood that it is similar to continue the effect traversed after continuing effect and the step 220i of traversal after step 220j,
This will not be repeated here.
In step 220k, track L is deleted from set D, judges whether D set is empty.If set D is not sky, weigh
Newly enter step 220.
In step 220l, if set D is sky, one or more track groups are obtained, it will be in all track groups
Tracking quantity added up to obtain all total number of tracks amounts with similar track, the total number of tracks amount of second hand rail trace set subtracts
The total number of tracks amount with similar track is gone, the quantity of track not similar with any other track is obtained.
In step 230, by the track set in total number of tracks amount divided by the other group quantity of trajectory set and it is described not
The sum of the quantity of track similar with any other track, obtains track frequency.
In this embodiment, by the scalping of the distance between starting point between track and terminal gone out not with any track phase
As track, reduce the tracking quantity for needing to carry out track similarity calculation, improve the computational efficiency of track frequency.
Fig. 3 is the block diagram according to the device 300 of the calculating track frequency shown in an exemplary embodiment of the disclosure.Such as
Shown in Fig. 3, the apparatus may include: it obtains module 310, track division module 320, Noise calculation module 330, frequency and calculates
Module 340.
The acquisition module 310 can be configured as the track set for obtaining mobile object.
The track division module 320 can be configured as and carry out each track in the set of the track based on track
The clustering of similarity obtains track group, wherein each track group includes at least two similar tracks.
The Noise calculation module 330 can be configured as not similar to any other track in the acquisition track set
Track quantity.
The frequency computing module 340 can be configured as according to total number of tracks amount in the set of the track and track frequency
Numerous degree is positively correlated, the other group quantity of the trajectory set and the track frequency are negatively correlated, it is described not with any other track
The quantity of similar track and the track frequency are negatively correlated, calculate the track frequency.
Through the above technical solution as it can be seen that due to the disclosure to track set in each track carry out based on track it is similar
The clustering of degree obtains track group, and, obtain the number of track not similar with any other track in the set of track
Amount, and the total quantity for track of going on a journey is more, is the precondition that route can be more frequent, is positively correlated with frequent angle value, not with appoint
What similar track in track is fewer, and track frequency is higher, belongs to negative correlation, and a track group represents a frequent road
Line, group number is fewer, illustrates that track concentration degree is higher, and the track on the frequent route of single is more, and track frequency is also
It is higher, belong to negative correlation, therefore, the disclosure according to track gather in total number of tracks amount and track frequency be positively correlated, trajectory set
Quantity and the track of other group quantity and the track frequency negative correlation, track not similar with any other track
The negatively correlated calculated track frequency of frequency, can accurately embody mobile object frequent route representated by these groups
On frequency, for mobile object behavioural analysis, security risk evaluate and test etc. provide more accurate quantizating index.
Fig. 4 is the block diagram according to the device 400 of the calculating track frequency shown in the another exemplary embodiment of the disclosure.
As shown in figure 4, the device can also include: judgment module 350, can be configured as in the track division module to track collection
Each track in conjunction carries out the clustering based on track similarity, before obtaining track group, gathers for the track
In every track, judge targeted track starting point whether between the starting point of at least one track in other tracks away from
From the requirement that the requirement and the distance between terminal for meeting default starting point distance threshold meet default terminal distance threshold.It deletes
Module 351 is determined as no, targeted track is gathered from the track if can be configured as the judgment module 350
Middle deletion.
In this embodiment, by the scalping of the distance between starting point between track and terminal gone out not with any track phase
As track, reduce the tracking quantity for needing to carry out track similarity calculation, improve the computational efficiency of track frequency.
In one possible embodiment, the frequency computing module 340 can be configured as to be gathered according to the track
Middle total number of tracks amount divided by the other group quantity of the trajectory set and the track or not similar any other track quantity
The sum of obtained quotient determine the track frequency.The embodiment passes through total number of tracks amount and the track in the set of track
The other group quantity of group carrys out accurate, direct, letter with the ratio of the sum of the quantity of the track or not similar any other track
Single positive and negative correlativity of characterization, obtains track frequency, high-efficient.It is of course also possible on being characterized by other expression formulas
Positive and negative correlativity is stated, the disclosure is to this and is not limited.
As shown in figure 4, the track division module 320 of the device may include: similarity calculation submodule 321, it can
To be configured as calculating the every track and other tracks in the track set by following any similarity calculation mode
Between one-to-one track similarity, the track similarity includes route geography according to used similarity calculation mode
Similarity, route geography time similarity, period similarity or comprehensive similarity.Group divides submodule 322, can be configured
For that will be determined as that similar track is divided into same track group according to calculated track similarity.
Wherein, the similarity calculation mode includes:
Route geography similarity calculation mode: the route geography similarity is according to the adjacent vital point of two tracks two
Proportion determines in track.
Route geography time similarity calculates mode: exhausted by the time error of the adjacent vital point of two tracks in stroke
In the case where the requirement for meeting prefixed time interval threshold value to value mean value, the route geography time similarity is according to two tracks
Adjacent vital point in two tracks proportion determine；It is missed in stroke by the time of the adjacent vital point of two tracks
In the case that poor absolute value mean value is unsatisfactory for the requirement of the prefixed time interval threshold value, the route geography time similarity root
According to the adjacent vital point of two tracks, proportion and the prefixed time interval threshold value and stroke pass through two in two tracks
The ratio of the time error absolute value mean value of the adjacent vital point of track determines.
Period similarity calculation mode: in the case where the departure time of two tracks meeting same period, the period
Similarity is default first similarity value, in the case where the departure time of two tracks not meeting same period, the period
Similarity is default second similarity value, and default first similarity value is different numbers from default second similarity value
Value.
Route period comprehensive similarity calculate mode: the comprehensive similarity according to the route geography time similarity with
The product of the period similarity determines, alternatively, the comprehensive similarity is according to the route geography similarity and the week
The product of phase similarity determines.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Fig. 5 is the block diagram of a kind of electronic equipment 500 shown according to an exemplary embodiment.As shown in figure 5, the electronics is set
Standby 500 may include: processor 501, memory 502.The electronic equipment 500 can also include multimedia component 503, input/
Export one or more of (I/O) interface 504 and communication component 505.
Wherein, processor 501 is used to control the integrated operation of the electronic equipment 500, to complete above-mentioned calculating track frequency
All or part of the steps in the method for numerous degree.Memory 502 is for storing various types of data to support to set in the electronics
Standby 500 operation, these data for example may include any application or method for operating on the electronic equipment 500
Instruction and the relevant data of application program, such as contact data, the message of transmitting-receiving, picture, audio, video etc..It should
Memory 502 can be realized by any kind of volatibility or non-volatile memory device or their combination, such as static state
Random access memory (Static Random Access Memory, abbreviation SRAM), electrically erasable programmable read-only memory
(Electrically Erasable Programmable Read-Only Memory, abbreviation EEPROM), erasable programmable
Read-only memory (Erasable Programmable Read-Only Memory, abbreviation EPROM), programmable read only memory
(Programmable Read-Only Memory, abbreviation PROM), and read-only memory (Read-Only Memory, referred to as
ROM), magnetic memory, flash memory, disk or CD.Multimedia component 503 may include screen and audio component.Wherein
Screen for example can be touch screen, and audio component is used for output and/or input audio signal.For example, audio component may include
One microphone, microphone is for receiving external audio signal.The received audio signal can be further stored in storage
Device 502 is sent by communication component 505.Audio component further includes at least one loudspeaker, is used for output audio signal.I/O
Interface 504 provides interface between processor 501 and other interface modules, other above-mentioned interface modules can be keyboard, mouse,
Button etc..These buttons can be virtual push button or entity button.Communication component 505 is for the electronic equipment 500 and other
Wired or wireless communication is carried out between equipment.Wireless communication, such as Wi-Fi, bluetooth, near-field communication (Near Field
Communication, abbreviation NFC), 2G, 3G or 4G or they one or more of combination, therefore corresponding communication
Component 505 may include: Wi-Fi module, bluetooth module, NFC module.
In one exemplary embodiment, electronic equipment 500 can be by one or more application specific integrated circuit
(Application Specific Integrated Circuit, abbreviation ASIC), digital signal processor (Digital
Signal Processor, abbreviation DSP), digital signal processing appts (Digital Signal Processing Device,
Abbreviation DSPD), programmable logic device (Programmable Logic Device, abbreviation PLD), field programmable gate array
(Field Programmable Gate Array, abbreviation FPGA), controller, microcontroller, microprocessor or other electronics member
Part is realized, for executing the above-mentioned method for calculating track frequency.
In a further exemplary embodiment, a kind of computer readable storage medium including program instruction is additionally provided, it should
The step of method of above-mentioned calculating track frequency is realized when program instruction is executed by processor.For example, this is computer-readable
Storage medium can be the above-mentioned memory 502 including program instruction, and above procedure instruction can be by the processor of electronic equipment 500
501 methods executed to complete above-mentioned calculating track frequency.
In a further exemplary embodiment, a kind of computer readable storage medium including program instruction is additionally provided, it should
The step of method of above-mentioned calculating track frequency is realized when program instruction is executed by processor.For example, this is computer-readable
Storage medium can be the above-mentioned memory 502 including program instruction, and above procedure instruction can be by the processor of electronic equipment 500
501 methods executed to complete above-mentioned calculating track frequency.
The preferred embodiment of the disclosure is described in detail in conjunction with attached drawing above, still, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, a variety of letters can be carried out to the technical solution of the disclosure
Monotropic type, these simple variants belong to the protection scope of the disclosure.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, it can be combined in any appropriate way.In order to avoid unnecessary repetition, the disclosure to it is various can
No further explanation will be given for the combination of energy.
In addition, any combination can also be carried out between a variety of different embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought equally should be considered as disclosure disclosure of that.
Claims (10)
1. a kind of method for calculating track frequency characterized by comprising
Obtain the track set of mobile object；
Clustering based on track similarity is carried out to each track in the set of the track, obtains track group, and,
Obtain the quantity of track not similar with any other track in the track set, wherein each track group includes at least
Two similar tracks；
According to total number of tracks amount in the set of the track and the positive correlation of track frequency, the other group quantity of the trajectory set and institute
State track frequency negative correlation, the quantity of the track not similar with any other track and the track frequency negative
It closes, calculates the track frequency.
2. the method according to claim 1, wherein being based in each track in the set of track
The clustering of track similarity, before obtaining track group, further includes:
For every track in the set of the track, judge the starting point of targeted track whether in other tracks at least one
The distance between starting point of track meets the requirement of default starting point distance threshold and the distance between terminal meets default terminal
The requirement of distance threshold；
If it is not, then targeted track is deleted from the set of the track.
3. the method according to claim 1, wherein it is described according to track gather in total number of tracks amount and track frequency
Numerous degree is positively correlated, the other group quantity of the trajectory set and the track frequency are negatively correlated, it is described not with any other track
The quantity of similar track and the track frequency are negatively correlated, and calculating the track frequency includes:
According to the track set in total number of tracks amount divided by the other group quantity of the trajectory set and it is described not with any other
The quotient that the sum of the quantity of the similar track in track obtains determines the track frequency.
4. the method according to claim 1, wherein each track in the set of the track carries out base
In the clustering of track similarity, obtaining track group includes:
By following any similarity calculation mode, calculate one between the every track and other tracks in the track set
One corresponding track similarity, the track similarity include that route geography is similar according to used similarity calculation mode
Degree, route geography time similarity, period similarity or comprehensive similarity；
It will be determined as that similar track is divided into same track group according to calculated track similarity；
The similarity calculation mode includes:
Route geography similarity calculation mode: the route geography similarity is according to the adjacent vital point of two tracks in two rails
Proportion determines in mark；
Route geography time similarity calculates mode: in stroke by the time error absolute value of the adjacent vital point of two tracks
In the case that mean value meets the requirement of prefixed time interval threshold value, the route geography time similarity is according to the phases of two tracks
Adjacent vital point proportion in two tracks determines；It is exhausted by the time error of the adjacent vital point of two tracks in stroke
In the case where the requirement for being unsatisfactory for the prefixed time interval threshold value to value mean value, the route geography time similarity is according to two
The adjacent vital point of track proportion and the prefixed time interval threshold value and stroke in two tracks pass through two rails
The ratio of the time error absolute value mean value of the adjacent vital point of mark determines；
Period similarity calculation mode: in the case where the departure time of two tracks meeting same period, the period is similar
Degree is default first similarity value, and in the case where the departure time of two tracks not meeting same period, the period is similar
Degree is default second similarity value, and default first similarity value is different numerical value from default second similarity value；
Route period comprehensive similarity calculate mode: the comprehensive similarity according to the route geography time similarity with it is described
The product of period similarity determines, alternatively, the comprehensive similarity is according to the route geography similarity and the period phase
It is determined like the product of degree.
5. a kind of device for calculating track frequency characterized by comprising
Module is obtained, is configured as obtaining the track set of mobile object；
Track division module, each track being configured as in gathering the track carry out the cluster based on track similarity and draw
Point, obtain track group, wherein each track group includes at least two similar tracks；
Noise calculation module is configured as obtaining the quantity of track not similar with any other track in the track set；
Frequency computing module is configured as according to total number of tracks amount in the set of the track and the positive correlation of track frequency, institute
State the number of the other group quantity of trajectory set with negatively correlated, the described track not similar with any other track of the track frequency
Amount is negatively correlated with the track frequency, calculates the track frequency.
6. device according to claim 5, which is characterized in that further include:
Judgment module is configured as carrying out each track in the set of track in the track division module similar based on track
The clustering of degree before obtaining track group, for every track in the set of the track, judges targeted track
Starting point whether with the distance between the starting point of at least one track in other tracks meet default starting point distance threshold requirement and
The distance between terminal meets the requirement of default terminal distance threshold；
Removing module, if be configured as the judgment module be determined as it is no, by targeted track from the track set in
It deletes.
7. device according to claim 5, which is characterized in that the frequency computing module is configured as according to the rail
Whether total number of tracks amount divided by the other group quantity of the trajectory set and the track or not similar any other track in trace set
The sum of quantity obtained quotient determine the track frequency.
8. device according to claim 5, which is characterized in that the track division module includes:
Similarity calculation submodule is configured as calculating in the track set by following any similarity calculation mode
Every track and other tracks between one-to-one track similarity, the track similarity is according to used similarity
Calculating mode includes route geography similarity, route geography time similarity, period similarity or comprehensive similarity；
Group divides submodule, is configured as being determined as that similar track is divided into according to calculated track similarity same
Track group；
The similarity calculation mode includes:
Route geography similarity calculation mode: the route geography similarity is according to the adjacent vital point of two tracks in two rails
Proportion determines in mark；
Route geography time similarity calculates mode: in stroke by the time error absolute value of the adjacent vital point of two tracks
In the case that mean value meets the requirement of prefixed time interval threshold value, the route geography time similarity is according to the phases of two tracks
Adjacent vital point proportion in two tracks determines；It is exhausted by the time error of the adjacent vital point of two tracks in stroke
In the case where the requirement for being unsatisfactory for the prefixed time interval threshold value to value mean value, the route geography time similarity is according to two
The adjacent vital point of track proportion and the prefixed time interval threshold value and stroke in two tracks pass through two rails
The ratio of the time error absolute value mean value of the adjacent vital point of mark determines；
Period similarity calculation mode: in the case where the departure time of two tracks meeting same period, the period is similar
Degree is default first similarity value, and in the case where the departure time of two tracks not meeting same period, the period is similar
Degree is default second similarity value, and default first similarity value is different numerical value from default second similarity value；
Route period comprehensive similarity calculate mode: the comprehensive similarity according to the route geography time similarity with it is described
The product of period similarity determines, alternatively, the comprehensive similarity is according to the route geography similarity and the period phase
It is determined like the product of degree.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claim 1-4 the method is realized when row.
10. a kind of electronic equipment characterized by comprising
Computer readable storage medium described in claim 9；And
One or more processor, for executing the program in the computer readable storage medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810631466.XA CN109063727B (en) | 2018-06-19 | 2018-06-19 | Method and device for calculating track frequency, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810631466.XA CN109063727B (en) | 2018-06-19 | 2018-06-19 | Method and device for calculating track frequency, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109063727A true CN109063727A (en) | 2018-12-21 |
| CN109063727B CN109063727B (en) | 2021-02-05 |
Family
ID=64820589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810631466.XA Active CN109063727B (en) | 2018-06-19 | 2018-06-19 | Method and device for calculating track frequency, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063727B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443288A (en) * | 2019-07-19 | 2019-11-12 | 浙江大学城市学院 | A kind of track similarity calculation method based on sequence study |
| CN111078810A (en) * | 2019-11-29 | 2020-04-28 | 北京三快在线科技有限公司 | Empirical route generation method and apparatus, storage medium, and electronic device |
| CN113254013A (en) * | 2021-07-16 | 2021-08-13 | 电子科技大学 | Reusable component mining method for complex business process |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110055212A1 (en) * | 2009-09-01 | 2011-03-03 | Cheng-Fa Tsai | Density-based data clustering method |
| CN105258704A (en) * | 2014-06-16 | 2016-01-20 | 中国科学院沈阳自动化研究所 | Multi-scale space-time hot point path detection method based on rapid road network modeling |
| CN107122461A (en) * | 2017-04-27 | 2017-09-01 | 东软集团股份有限公司 | One kind trip method of trajectory clustering, device and equipment |
-
2018
- 2018-06-19 CN CN201810631466.XA patent/CN109063727B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110055212A1 (en) * | 2009-09-01 | 2011-03-03 | Cheng-Fa Tsai | Density-based data clustering method |
| CN105258704A (en) * | 2014-06-16 | 2016-01-20 | 中国科学院沈阳自动化研究所 | Multi-scale space-time hot point path detection method based on rapid road network modeling |
| CN107122461A (en) * | 2017-04-27 | 2017-09-01 | 东软集团股份有限公司 | One kind trip method of trajectory clustering, device and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 吴俊伟等: "基于网格聚类的热点路径探测", 《吉林大学学报(工学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443288A (en) * | 2019-07-19 | 2019-11-12 | 浙江大学城市学院 | A kind of track similarity calculation method based on sequence study |
| CN111078810A (en) * | 2019-11-29 | 2020-04-28 | 北京三快在线科技有限公司 | Empirical route generation method and apparatus, storage medium, and electronic device |
| CN113254013A (en) * | 2021-07-16 | 2021-08-13 | 电子科技大学 | Reusable component mining method for complex business process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109063727B (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bierlaire et al. | A probabilistic map matching method for smartphone GPS data | |
| Gong et al. | Inferring trip purposes and uncovering travel patterns from taxi trajectory data | |
| Mun et al. | PEIR, the personal environmental impact report, as a platform for participatory sensing systems research | |
| Jiang et al. | A review of urban computing for mobile phone traces: current methods, challenges and opportunities | |
| CN109033011B (en) | Method and device for calculating track frequency, storage medium and electronic equipment | |
| EP3080724B1 (en) | Generating elevation data for maps | |
| CN104331422B (en) | A kind of road segment classification estimation method | |
| CN102762957B (en) | Historial traffic data compression | |
| US20120317066A1 (en) | Interest level measurement system, interest level measurement device, interest level measurement method, and interest level measurement program | |
| CN109063727A (en) | Calculate method, apparatus, storage medium and the electronic equipment of track frequency | |
| US10754040B2 (en) | System and method for graph encoding of physical activity data | |
| CN108053240B (en) | Method and device for generating vehicle-mounted advertisement delivery bus route scheme | |
| WO2011109180A1 (en) | Relevancy ranking for map-related search | |
| CN105910612A (en) | Personalized navigation method and system | |
| Jia et al. | Trips and their CO2 emissions to and from a shopping center | |
| Cesario et al. | An approach for the discovery and validation of urban mobility patterns | |
| US20230245002A1 (en) | Stationary Classifier for Geographic Route Trace Data | |
| Bierlaire et al. | Modeling route choice behavior from smartphone GPS data | |
| TWI479122B (en) | Method, apparatus, and computer program product for estimating and displaying destination | |
| JP5331719B2 (en) | Method, apparatus and program for determining action situation | |
| CN113008242A (en) | User behavior data processing method, device, equipment and storage medium | |
| US10743090B2 (en) | Filtering noise values from telemetry data | |
| CN110956800B (en) | Road section traffic data preprocessing method and device and electronic equipment | |
| Chen | Modeling route choice behavior using smartphone data | |
| CN111854791B (en) | Motion trail determination method and device, terminal equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |