CN107657572A - Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency - Google Patents
Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency Download PDFInfo
- Publication number
- CN107657572A CN107657572A CN201710820062.0A CN201710820062A CN107657572A CN 107657572 A CN107657572 A CN 107657572A CN 201710820062 A CN201710820062 A CN 201710820062A CN 107657572 A CN107657572 A CN 107657572A
- Authority
- CN
- China
- Prior art keywords
- time
- point
- position mark
- data
- high frequency
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000003139 buffering effect Effects 0.000 claims abstract description 28
- 238000005070 sampling Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 abstract description 5
- 239000000463 material Substances 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72457—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to geographic location
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Signal Processing (AREA)
- Economics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Environmental & Geological Engineering (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency and system.Wherein, method includes:1st, the equidistant space-time trajectory data of high frequency is gathered, and data are pre-processed;2nd, position mark point is traveled through one by one, calculates the density value in the range of each position mark point certain radius buffering area;3rd, density time curve is drawn, finds peak point;4th, all peak points are traveled through one by one, finds stop central point, so that it is determined that the stop total degree of trip individual and dwell point position;5th, the instantaneous velocity of each position mark point is calculated, speed time curve is drawn, is contrasted with density time curve, determine arrival time, time departure and stay time.Accuracy of identification of the present invention is higher, and analysis meeting of its application to work such as follow-up trip mode, trip purpose, behavior predictions produces material impact, it will help important theoretical foundation is provided for urban planning administration.
Description
Technical field
The present invention relates to a kind of dwell point recognition methods and system, belong to position information process technical field, and in particular to
A kind of dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency.
Background technology
It is the basis of many applications and research to understand people's active situation.The daily routines of people, can by activity whether
Carry out in static local space and be divided into static and two classes of motion.Show as stopping and move on the space-time track of individual
Dynamic two big features.Traditional travel behaviour action message obtain be in the form of survey based on, the side of this manual research
Although formula has at home and abroad formd the survey process and specification of complete set, and adopts for many years, also always there is
Some drawbacks, as surveyee's psychological burden is heavier, and the accuracy of investigation is not high, and time cost and monetary cost are huge etc..
Due to the complexity, scope of activities and the diversity of activity time of the spatio-temporal activity feature of people, when how efficiently and accurately to obtain
Empty track data is the emphasis and difficult point of trip characteristicses extraction and dwell point identification.
In recent years, with the popularization and application of the intelligent terminal systems such as smart mobile phone and GPS navigator, we can be with low
The mode of cost easily obtains the real time position data of a large amount of traveler individuals, includes the latitude and longitude information of individual, and right
Information etc. at the time of answering, i.e. individual space-time trajectory data., can be to it by the processing to these data and deep excavation
The travel behaviour rule information and feature of implicit individual or even colony carry out extraction and analysis behind.Meanwhile we can also be from
The social networks information of individual, such as residence and place of working etc. are grasped in the result of data analysis, so as to speculate the work of individual
Make post and job specification, this is significant for the accurate push etc. of the realization of intelligent transportation, advertisement.It is in addition, a large amount of
Positional information and trip information data can for traffic programme work related foundation be provided, compared to traditional traffic study method into
This is lower, and data renewal is rapider.
In research at home and abroad at present, based on the analysis to user's space-time trajectory data, the behavior pattern of user is realized
Excavation, behavior prediction, traffic OD data acquisitions etc. have had started to numerous studies.Wherein, the identification of dwell point is to utilize shifting
Start machine track data analysis user's travel activity key link, to works such as follow-up trip mode, trip purpose, behavior predictions
The analysis meeting of work produces material impact.Its application will be helpful to urban planning administration department and reasonably be planned, and be traffic
Policy making provides new theory and technical support.
The content of the invention
The technological deficiency stopped for existing track data in the presence of the research of recognition methods, the invention discloses one kind
Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency.This method and system are using trip track APP
To obtain mobile phone location data, and the dwell point and stay time of trip individual are accurately identified based on the data, it is convenient
Subsequently to individual Trip chain and the reasonable analysis of travel activity, important theoretical foundation is provided for urban planning administration.
The above-mentioned technical problem of the present invention is mainly what is be addressed by following technical proposals:
A kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, including:
Data sampling step, the trip track data collected is treated as equidistant with the high frequency of time interval division
Space-time track position mark tally evidence;
Density calculation procedure, the position mark point data is included in different position buffering areas, calculates every tagging
Put the position mark dot density of belonging positions buffering area and as the density value of position mark point;
Position identification step, the density value and time curve of position mark point are drawn, by position mark dot density value
The alternately stop place of position corresponding to peak point.
Preferably, above-mentioned a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, the data
Sampling step further comprises:
Data acquisition sub-step, the mobile phone location data of collection trip individual are simultaneously sampled;
Data reject sub-step, based on Kalman filtering smoothing processing sampled result, rejecting abnormalities and wrong data, finally
Obtain the equidistant space-time track position mark tally evidence of high frequency.
Preferably, above-mentioned a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, the density
In calculation procedure, position mark dot density value is calculated based on following formula:
In formula, R is the buffering area radius determined;NiPosition mark point number where position mark point i in buffering area;
ρiFor the position mark dot density value corresponding to position mark point i.
Preferably, above-mentioned a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, the position
Identification step further comprises following sub-step:
Threshold value determines sub-step, and the minimum translational speed based on trip individual is determined when individual is handled in mobile status when institute
Belong to the maximum position mark point number in buffering area as mobile status threshold value;
Sub-step is screened in position, and its affiliated buffer location mark point total number is more than into the alternative of mobile status threshold value stops
Position is stayed as stop central point.
Preferably, above-mentioned a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, the movement
State threshold is calculated based on following formula:
In formula, R is buffering area radius;VminThe minimum speed of mobile status downward driving is in for trip individual;Δ t is position
The sampling time interval of tagging point;NmaxFor mobile status threshold value.
Preferably, above-mentioned a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, in addition to:
Time determination step, calculate and draw individual travel time and length velocity relation, with reference to according to alternative stop place most
The stop central point determined eventually calculates individual and reached and departure time information.
Preferably, above-mentioned a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, the time
Determination step further comprises:
Arrival time determines sub-step, the point centered on stop place, find out on the time prior to and speed on for the first time
Less than the time corresponding to the position mark point of predetermined threshold value as arrival time;
Time departure determines sub-step, the point centered on stop place, find out be later than on the time and in speed for the first time
More than the time corresponding to the position mark point of predetermined threshold value as time departure;
Stay time determines sub-step, and stay time is calculated based on the arrival time and time departure.
A kind of dwell point identification device based on the equidistant space-time trajectory data of high frequency, including:
Data sampling module, for the trip collected track data to be treated as with high frequency of time interval division etc.
Spacing space-time track position mark tally evidence;
Density Calculation Module, for the position mark point data to be included in different position buffering areas, calculate each position
The position mark dot density of mark point belonging positions buffering area and as the density value of position mark point;
Location identification module, it is for drawing the density value and time curve of position mark point, position mark point is close
The alternately stop place of position corresponding to angle value peak point.
Preferably, above-mentioned a kind of dwell point identification device based on the equidistant space-time trajectory data of high frequency, the data
Sampling module further comprises:
Data acquisition unit, for gathering the mobile phone location data of trip individual and being sampled;
Data culling unit, for based on Kalman filtering smoothing processing sampled result, rejecting abnormalities and wrong data, most
The equidistant space-time track position mark tally evidence of high frequency is obtained eventually.
Preferably, above-mentioned a kind of dwell point identification device based on the equidistant space-time trajectory data of high frequency, the density
In computing module, position mark dot density value is calculated based on following formula:
In formula, R is the buffering area radius determined;NiPosition mark point number where position mark point i in buffering area;
ρiFor the position mark dot density value corresponding to position mark point i.
Therefore, the invention has the advantages that:
(1) traditional location information acquisition method general sampling interval is longer, and the sampling interval is it is difficult to ensure that equal.And this
The equidistant space-time trajectory data of high frequency of the use of innovation and creation, sampling interval are 15 seconds, and frequency is high, interval is stable, ensures
The continuity and accuracy of sampled data, contribute to the identification of the mark and dwell point of space-time track;
(2) traditional dwell point recognition methods is generally based on the velocity amplitude of target to identify that target is mobile or locate
In inactive state.The defects of this method is when target is in a small range activity, for example to be walked about in a certain building, is passed
Dwell point can be mistakenly considered transfer point by system method.And the outstanding advantages of the present invention are exactly to use to stop based on position mark dot density
Stationary point recognition methods, trip individual can be effectively avoided to identify caused judge by accident to dwell point in a small range activity;
(3) present invention is not directly to apply the latitude and longitude information in initial data to come tagging space-time track, but
The mobile phone location data of each trip individual of track APP collections of going on a journey, and data are pre-processed, solve mobile phone positioning
Position excursion problem, track identification precision are higher.
Brief description of the drawings
Fig. 1 is the method flow schematic diagram of the present invention;
Fig. 2 is the partial data schematic diagram used in the present invention;
Fig. 3 is certain individual scatterplot schematic diagram in all position mark points some day of trip in the present invention;
Fig. 4 identifies schematic diagram for certain trip individual in the present invention in the dwell times of some day and corresponding residence time.
Embodiment
Below by embodiment, and with reference to accompanying drawing, technical scheme is described in further detail.
Embodiment:
The present invention proposes a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, flow chart such as Fig. 1
It is shown, comprise the following steps:
Step 1: the collection and pretreatment of trip track data
1), the collection of trip track data:The mobile phone location data of each trip individual is gathered based on trip track APP,
So as to obtain the position mark point data that the sampling interval is Δ t (Δ t is ultimately determined to 15s).The trip of each trip individual
Include in track data content trip individual id information, the latitude and longitude information of position mark point, the data acquisition date and
Reach the temporal information of the position mark point (temporal information is accurate to the second).Wherein, the partial data used in the present invention is shown
It is intended to as shown in Figure 2.
2), the pretreatment of trip track data:The information deficiency of data in the presence of sampled data is sieved first
Remove.Then, the smoothing processing of data, rejecting abnormalities point and wrong point data are carried out based on Kalman filtering, is finally given with 15s
For the equidistant space-time trajectory data of high frequency of time interval.Wherein, certain individual position mark point all within some day of going on a journey
Scatterplot schematic diagram is as shown in Figure 3 (figure is by taking the trip track of certain cellphone subscriber of Zhengzhou City as an example).
Step 2: the density value of calculation position mark dot buffer zone
1) buffering area radius, is determined:For individual region of going on a journey, the most jogging speed in urban area traveling is obtained
(footpace 5km/h) and prestissimo (prestissimo travelled in general city is 80km/h).Based on above-mentioned speed
Angle value, to ensure dwell point accuracy of identification, it is thus necessary to determine that suitable buffering area radius value.
2), the density value in the range of buffering area where the mark point of calculation position:Corresponding program is write, respectively to each trip
The position mark point of individual is traveled through one by one, obtains position mark of the diverse location mark point in the range of the buffering area where it
Note point sum, and the density value corresponding to each position mark point is calculated, calculation formula is as follows.
Wherein, R be step 2 1) in identified buffering area radius;NiThe radius where position mark point i is the slow of R
The total number of the position mark point rushed in the range of area;ρiFor the density value corresponding to position mark point i.
Step 3: obtain density peaks point
1) density-time plot, is drawn:It is the equidistant time data of the high frequency of time interval as abscissa using 15s,
The density value in the range of the buffering area where each position mark point obtained by using in step 2 is as ordinate, for not
Same trip individual, makes density-time plot corresponding to it respectively.
2) density peaks point, is obtained:According to above-mentioned density-time plot, find the position corresponding to peak point and stop
Point, even if trip individual is in mobile status, its velocity amplitude can also change with the time, therefore also can under mobile status
Peak point be present, that is, need further to screen peak point.
Step 4: determine to stop central point
1), calculation position mark point threshold value:For a certain peak point, determine it is to stop central point when the position mark point,
And during residence time long enough, then should have numerous position mark point around the point, i.e., density is intended to infinity.And
At the position mark point, trip individual is when being in mobile status, no matter using which kind of trip mode, corresponding to the position mark point
Density should all be less than some fixed threshold.The threshold value can be according to the minimum speed V of travelingmin(referring generally to walking speed)
To determine, formula is as follows.
Wherein, R buffer radius;VminIt is in for trip individual under mobile status, the minimum speed of traveling;Δ t is when waiting
Between spacing sampling interval;NmaxIt is in for trip individual under mobile status, position is marked in the range of the buffering area corresponding to peak point
The maximum of note point sum.
2), screening stops central point:Need to travel through peak point acquired in step 3 one by one.When the peak point
When position mark point total number in the range of buffering area is higher than threshold value, changes the time as central point is stopped, retained;And work as the peak
When position mark point total number in the range of value dot buffer zone is less than threshold value, change the time as the position mark under mobile status
Point, this peak point should be screened out.
3), dwell times and stop place:After screening, the peak point finally remained is stop center
Point.The total number of wherein remaining peak point is total dwell times;Corresponding latitude and longitude information in remaining peak value point data, i.e.,
For stop place.
Step 5: determine arrival time, time departure and stay time
1) instantaneous velocity, is calculated:For different trip individuals, it is necessary to be based on latitude and longitude information and time interval, calculate
The trip individual each position mark point Instantaneous velocity values (because time interval is smaller, can be with each sampling interval
Average speed as the instantaneous velocity in the Δ t periods).Assuming that position mark point XiLatitude and longitude information corresponding to coordinate
For (ai,bi), Xi+1Latitude and longitude information corresponding to coordinate be (ai+1,bi+1), instantaneous velocity ViCalculation formula it is as follows.
2) speed-time curve figure, is drawn:Density-time plot for being made of control step 3 kind, draw speed-when
Half interval contour figure, ensure that position mark point corresponds, as can be seen that being protected in density-time plot from two comparison diagrams
The peak point stayed, that is, zero should be leveled off to by stopping the velocity amplitude at moment corresponding to central point.
3) threshold speed, is determined:It is small because the velocity amplitude for individual of near arrival time point, going on a journey should be gradually reduced
The traveling minimum speed V 1) being previously mentioned in step 4min, until leveling off to zero;And near time departure point, velocity amplitude should
Should be by zero gradually increase, more than traveling minimum speed Vmin, until the normally travel speed of trip mode selected by trip individual.
Therefore, according to can be according to minimum speed VminSetting speed threshold value.
4), search out up to time point and time departure point, and calculate stay time:Period before central point is stopped
It is interior, it is arrival time point t at the time of corresponding when speed last time is less than threshold speed corresponding to position mark pointi1;
Stop central point after period in, corresponding to position mark point speed for the first time outpace threshold value when previous point, institute
It is time departure point t at the time of correspondingi2, stay time TstayCalculation formula it is as follows.
Tstay=ti2-ti1 (4)
Based on step 1 to step 5, the present invention may finally be based on the equidistant space-time trajectory data of the high frequency, realization pair
Dwell point of the trip individual in activity in one day, stop place, total dwell times, at the time point for reaching dwell point, carry out start-stop and stay
The time point of point and the identification of stay time, accuracy of identification are higher.Wherein, certain trip individual stops in some day in the present invention
Number and corresponding residence time is stayed to identify that schematic diagram is as shown in Figure 4.
Specific embodiment described herein is only to spirit explanation for example of the invention.Technology belonging to the present invention is led
The technical staff in domain can be made various modifications or supplement to described specific embodiment or be replaced using similar mode
Generation, but without departing from the spiritual of the present invention or surmount scope defined in appended claims.
Claims (10)
- A kind of 1. dwell point recognition methods based on the equidistant space-time trajectory data of high frequency, it is characterised in that including:Data sampling step, the equidistant space-time of high frequency that the trip track data collected is treated as dividing with time interval Track position mark tally evidence;Density calculation procedure, the position mark point data is included in different position buffering areas, calculates each position mark point institute Belong to the position mark dot density of position buffering area and as the density value of position mark point;Position identification step, by the alternately stop place of position corresponding to position mark dot density value peak point.
- 2. a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency according to claim 1, it is special Sign is that the data sampling step further comprises:Data acquisition sub-step, the mobile phone location data of collection trip individual are simultaneously sampled;Data reject sub-step, based on Kalman filtering smoothing processing sampled result, rejecting abnormalities and wrong data, finally give The equidistant space-time track position mark tally evidence of high frequency.
- 3. a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency according to claim 1, it is special Sign is, in the density calculation procedure, position mark dot density value is calculated based on following formula:<mrow> <msub> <mi>&rho;</mi> <mi>i</mi> </msub> <mo>=</mo> <mfrac> <msub> <mi>N</mi> <mi>i</mi> </msub> <mrow> <msup> <mi>&pi;R</mi> <mn>2</mn> </msup> </mrow> </mfrac> </mrow>In formula, R is the buffering area radius determined;NiPosition mark point number where position mark point i in buffering area;ρiFor Position mark dot density value corresponding to position mark point i.
- 4. a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency according to claim 1, it is special Sign is that the position identification step further comprises following sub-step:Threshold value determines sub-step, and the minimum translational speed based on trip individual determines affiliated slow when individual is handled in mobile status The maximum position mark point number rushed in area is as mobile status threshold value;Sub-step is screened in position, and its affiliated buffer location mark point total number is more than to the alternative stop place of mobile status threshold value Put as stop central point.
- 5. a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency according to claim 4, it is special Sign is that the mobile status threshold value is calculated based on following formula:<mrow> <msub> <mi>N</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mn>2</mn> <mi>R</mi> </mrow> <mrow> <msub> <mi>V</mi> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> <mo>&times;</mo> <mi>&Delta;</mi> <mi>t</mi> </mrow> </mfrac> </mrow>In formula, R is buffering area radius;VminThe minimum speed of mobile status downward driving is in for trip individual;Δ t marks for position Remember the sampling time interval of point;NmaxFor mobile status threshold value.
- 6. a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency according to claim 1, it is special Sign is, in addition to:Time determination step, individual travel time and length velocity relation are calculated and draw, with reference to finally true according to alternative stop place Fixed stop central point calculates individual and reached and departure time information.
- 7. a kind of dwell point recognition methods based on the equidistant space-time trajectory data of high frequency according to claim 6, it is special Sign is that the time determination step further comprises:Arrival time determines sub-step, the point centered on stop place, find out on the time prior to and speed on be less than for the first time The time is as arrival time corresponding to the position mark point of predetermined threshold value;Time departure determines sub-step, the point centered on stop place, finds out and is later than on the time and is more than for the first time in speed The time is as time departure corresponding to the position mark point of predetermined threshold value;Stay time determines sub-step, and stay time is calculated based on the arrival time and time departure.
- 8. a kind of dwell point identification device based on the equidistant space-time trajectory data of high frequency, including:Data sampling module, it is equidistant with the high frequency of time interval division for the trip collected track data to be treated as Space-time track position mark tally evidence;Density Calculation Module, for the position mark point data to be included in different position buffering areas, calculate every tagging Put the position mark dot density of belonging positions buffering area and as the density value of position mark point;Location identification module, for by the alternately stop place of position corresponding to position mark dot density value peak point.
- 9. a kind of dwell point identification device based on the equidistant space-time trajectory data of high frequency according to claim 8, described Data sampling module further comprises:Data acquisition unit, for gathering the mobile phone location data of trip individual and being sampled;Data culling unit, for based on Kalman filtering smoothing processing sampled result, rejecting abnormalities and wrong data, final To the equidistant space-time track position mark tally evidence of high frequency.
- 10. a kind of dwell point identification device based on the equidistant space-time trajectory data of high frequency according to claim 8, described In Density Calculation Module, position mark dot density value is calculated based on following formula:<mrow> <msub> <mi>&rho;</mi> <mi>i</mi> </msub> <mo>=</mo> <mfrac> <msub> <mi>N</mi> <mi>i</mi> </msub> <mrow> <msup> <mi>&pi;R</mi> <mn>2</mn> </msup> </mrow> </mfrac> </mrow>In formula, R is the buffering area radius determined;NiPosition mark point number where position mark point i in buffering area;ρiFor Position mark dot density value corresponding to position mark point i.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710820062.0A CN107657572A (en) | 2017-09-13 | 2017-09-13 | Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710820062.0A CN107657572A (en) | 2017-09-13 | 2017-09-13 | Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107657572A true CN107657572A (en) | 2018-02-02 |
Family
ID=61129609
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710820062.0A Pending CN107657572A (en) | 2017-09-13 | 2017-09-13 | Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107657572A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110160539A (en) * | 2019-05-28 | 2019-08-23 | 北京百度网讯科技有限公司 | Map-matching method, calculates equipment and medium at device |
CN111581531A (en) * | 2020-05-08 | 2020-08-25 | 北京思特奇信息技术股份有限公司 | Family member structure identification method and device, storage medium and electronic equipment |
CN113469600A (en) * | 2020-03-31 | 2021-10-01 | 北京三快在线科技有限公司 | Travel track segmentation method and device, storage medium and electronic equipment |
CN113742607A (en) * | 2020-05-28 | 2021-12-03 | 浙江财经大学 | Residence position recommendation method based on geographical track of party |
CN115757987A (en) * | 2022-10-30 | 2023-03-07 | 深圳市巨龙创视科技有限公司 | Method, device, equipment and medium for determining accompanying object based on trajectory analysis |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106600960A (en) * | 2016-12-22 | 2017-04-26 | 西南交通大学 | Traffic travel origin and destination identification method based on space-time clustering analysis algorithm |
CN106897420A (en) * | 2017-02-24 | 2017-06-27 | 东南大学 | A kind of resident Activity recognition method of user's trip based on mobile phone signaling data |
-
2017
- 2017-09-13 CN CN201710820062.0A patent/CN107657572A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106600960A (en) * | 2016-12-22 | 2017-04-26 | 西南交通大学 | Traffic travel origin and destination identification method based on space-time clustering analysis algorithm |
CN106897420A (en) * | 2017-02-24 | 2017-06-27 | 东南大学 | A kind of resident Activity recognition method of user's trip based on mobile phone signaling data |
Non-Patent Citations (2)
Title |
---|
ALEX RODRIGUEZ等: ""Clustering by fast search and find of density peaks"", 《SCIENCE》 * |
唐娟: ""基于手机定位数据的居民出行OD矩阵获取方法研究"", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110160539A (en) * | 2019-05-28 | 2019-08-23 | 北京百度网讯科技有限公司 | Map-matching method, calculates equipment and medium at device |
CN113469600A (en) * | 2020-03-31 | 2021-10-01 | 北京三快在线科技有限公司 | Travel track segmentation method and device, storage medium and electronic equipment |
CN111581531A (en) * | 2020-05-08 | 2020-08-25 | 北京思特奇信息技术股份有限公司 | Family member structure identification method and device, storage medium and electronic equipment |
CN111581531B (en) * | 2020-05-08 | 2023-06-09 | 北京思特奇信息技术股份有限公司 | Family member structure identification method and device, storage medium and electronic equipment |
CN113742607A (en) * | 2020-05-28 | 2021-12-03 | 浙江财经大学 | Residence position recommendation method based on geographical track of party |
CN113742607B (en) * | 2020-05-28 | 2023-12-08 | 浙江财经大学 | Stay position recommending method based on geographical track of principal |
CN115757987A (en) * | 2022-10-30 | 2023-03-07 | 深圳市巨龙创视科技有限公司 | Method, device, equipment and medium for determining accompanying object based on trajectory analysis |
CN115757987B (en) * | 2022-10-30 | 2023-08-22 | 深圳市巨龙创视科技有限公司 | Method, device, equipment and medium for determining companion object based on track analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107657572A (en) | Dwell point recognition methods and system based on the equidistant space-time trajectory data of high frequency | |
CN106197458B (en) | A kind of mobile phone user's trip mode recognition methods based on mobile phone signaling data and navigation route data | |
CN106781479B (en) | A method of highway operating status is obtained based on mobile phone signaling data in real time | |
CN103810851B (en) | A kind of traffic trip mode identification method based on mobile phone location | |
CN103646560B (en) | The extracting method in taxi wheelpath experimental knowledge path | |
CN102708698B (en) | Vehicle optimal-path navigation method based on vehicle internet | |
CN109993969A (en) | A kind of road conditions determine information acquisition method, device and equipment | |
CN111862606B (en) | Illegal operating vehicle identification method based on multi-source data | |
CN111653099B (en) | Bus passenger flow OD obtaining method based on mobile phone signaling data | |
EP3073451A1 (en) | Bus station optimization evaluation method and system | |
CN102735252B (en) | Path guide generation, method and system | |
CN104167092A (en) | Method and device for determining taxi pick-up and drop-off hot spot region center | |
CN104217593B (en) | A kind of method for obtaining road condition information in real time towards mobile phone travelling speed | |
CN105679009B (en) | A kind of call a taxi/order POI commending systems and method excavated based on GPS data from taxi | |
CN103038605A (en) | Detecting location, timetable and travel time estimations for barrier crossings in a digital map | |
CN104318781B (en) | Based on the travel speed acquisition methods of RFID technique | |
CN104636611A (en) | Urban road/ road segment vehicle speed evaluation method | |
CN102903257A (en) | Vehicle navigation method and vehicle navigation system | |
CN109816271A (en) | Cycle track service level evaluation method based on shared bicycle track data | |
CN103714694B (en) | Urban traffic information access disposal system | |
CN104504245B (en) | A kind of application GPS trip surveys data identification trip and the method for activity | |
CN1609907A (en) | Vehicle and person identification and positioning method and traffic information collecting system | |
CN104183135B (en) | The method of estimation of vehicle traveling expense and system | |
CN109615865A (en) | A method of based on the iterative estimation road section traffic volume flow of OD data increment | |
CN113079463A (en) | Tourist attraction tourist travel activity identification method based on mobile phone signaling data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180202 |