CN102201000A - Method for constructing and updating pedestrian traffic data long-term development mode - Google Patents
Method for constructing and updating pedestrian traffic data long-term development mode Download PDFInfo
- Publication number
- CN102201000A CN102201000A CN 201110109072 CN201110109072A CN102201000A CN 102201000 A CN102201000 A CN 102201000A CN 201110109072 CN201110109072 CN 201110109072 CN 201110109072 A CN201110109072 A CN 201110109072A CN 102201000 A CN102201000 A CN 102201000A
- Authority
- CN
- China
- Prior art keywords
- pedestrian traffic
- data
- long
- development pattern
- run development
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for constructing and updating a pedestrian traffic data long-term development mode. The method comprises the following steps: acquiring and storing pedestrian traffic historical data for several days for at least one position; correcting time scale for the pedestrian traffic historical data; screening a pedestrian traffic historical data sequence which is arranged according to a time order at an arbitrary day for the same position to serve as a transverse time sequence, screening a pedestrian traffic historical data sequence which is arranged according to a time sequence on the same time scale at a specific day for the same position to serve as a longitudinal time sequence, and constructing the pedestrian traffic data long-term development mode on the basis of the two sequences; preprocessing sampled pedestrian traffic real time data; and comparing the preprocessed pedestrian traffic real time data with the pedestrian traffic historical data in the longitudinal time sequence, and updating the longitudinal time sequence according to the comparison result. By the method, the long-term data law and short term pedestrian traffic law can be constructed.
Description
Technical field
The present invention relates to a kind of data construct and update method, relate in particular to a kind of structure and update method of pedestrian traffic data long-run development pattern.
Background technology
Crowded place density of personnel early warning system, be to rely on the video equipment that is installed in the different location, gather the video image of monitored area in real time, by the real-time crowd's passenger flow that reflects in the video image is carried out data statistics and analysis, thereby realize the crowd density early warning prediction of crowded place.The structure and the update method that need a kind of pedestrian traffic data long-run development pattern in actual applications, make its can intellectual analysis equipment the pedestrian traffic state real time data of output, and be stored in the database, can inquire about dynamically and calculate, setting up the real-time judge model of the different pedestrian's traffic behaviors of crowd (unimpeded, gradual change unusual, unexpected abnormality, block up etc.), the crowd massing risk in the crowd is dense place reached monitor and control effect preferably.
Summary of the invention
The objective of the invention is to propose a kind of structure and update method of pedestrian traffic data long-run development pattern,, make up long term data rule and pedestrian traffic rule in short-term by accumulation pedestrian traffic data.
In order to achieve the above object, the invention provides a kind of structure and update method of pedestrian traffic data long-run development pattern, described pedestrian traffic data have time scale and time scale, and comprise pedestrian traffic historical data and pedestrian traffic real time data, this method comprises: step S1: obtain many days pedestrian traffic historical data at least one position and storage; Step S2: described pedestrian traffic historical data is carried out time scale proofread and correct; Step S3: arbitrary day pedestrian traffic historical data sequence of arranging in chronological order of screening same position and conduct be time series laterally, the pedestrian traffic historical data sequence of the same time scale of arranging in chronological order of screening same position certain day and as vertical time series, based on described two sequences to make up pedestrian traffic data long-run development pattern; Step S4: sampling pedestrian traffic real time data is also carried out pre-service; Step S5: the pedestrian traffic historical data in pretreated pedestrian traffic real time data and the described vertical time series is compared and upgrade vertical time series according to comparison result; Step S6: repeating step S4 and step S5, thus finish the structure and the renewal of pedestrian traffic data long-run development pattern.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, wherein said pedestrian traffic data comprise flow, regional number, density and speed.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, wherein said step S2 comprises: with a time scale is benchmark, is step-length with a time yardstick, with not on the same day pedestrian traffic historical data time scale alignment of same position.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, the benchmark of wherein said time scale are 00:00:00 every day, and described time scale is 5 minutes.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, wherein said step S3 comprises: the screening secular trend similar continuous a plurality of week the phase same date the pedestrian traffic historical data and as vertical time series.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, continuous a plurality of weeks of wherein said screening are 4-5 week.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, wherein said step S3 comprises: adopt the cluster analysis technology with same position not the data sequence of same date sort out, and form the long-run development pattern of pedestrian traffic data with similar a plurality of dates; If there is difference in the cluster result in different weeks, then analyzes the data in a plurality of weeks, and adopt the principle of comforming to obtain final classification results.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, wherein said step S3 comprises: be the pedestrian traffic data long-run development pattern that the cycle makes up technical dates with the year; For the preliminary stage of system operation,, then quote the long-run development pattern of adjacent nonworkdays if do not obtain effective technical dates of historical data as yet; Wherein, comprise red-letter day, holiday described technical dates.
The structure and the update method of pedestrian traffic data long-run development pattern of the present invention, wherein said step S5 comprises: if the pedestrian traffic real time data is normal pedestrian's traffic data, then upgrade the long-run development pattern, reject data the earliest in the middle of the original long-run development pattern simultaneously with real time data; If the pedestrian traffic real time data for lose, mistake or unusual pedestrian traffic data, then keep original long-run development pattern constant.
The present invention is by accumulation pedestrian traffic data, make up long term data rule and pedestrian traffic rule in short-term, the real-time judge model of the different pedestrian's traffic behaviors of the crowd that can set up (unimpeded, gradual change unusual, unexpected abnormality, block up etc.), and the prediction Early-warning Model of the pedestrian traffic state of following 10 minutes of prediction each point position even farther time point.
Description of drawings
Fig. 1 is the structure and the update method process flow diagram of pedestrian traffic data long-run development pattern of the present invention.
Embodiment
In conjunction with the embodiments the present invention is further elaborated with reference to the accompanying drawings.
As shown in Figure 1, structure and update method process flow diagram for pedestrian traffic data long-run development pattern of the present invention, described pedestrian traffic data have time scale and time scale, and comprise pedestrian traffic historical data and pedestrian traffic real time data, this method comprises: step S1: obtain many days pedestrian traffic historical data at least one position and storage; Step S2: described pedestrian traffic historical data is carried out time scale proofread and correct; Step S3: arbitrary day pedestrian traffic historical data sequence of arranging in chronological order of screening same position and conduct be time series laterally, the pedestrian traffic historical data sequence of the same time scale of arranging in chronological order of screening same position certain day and as vertical time series, based on described two sequences to make up pedestrian traffic data long-run development pattern; Step S4: sampling pedestrian traffic real time data is also carried out pre-service; Step S5: the pedestrian traffic historical data in pretreated pedestrian traffic real time data and the described vertical time series is compared and upgrade vertical time series according to comparison result; Step S6: repeating step S4 and step S5, thus finish the structure and the renewal of pedestrian traffic data long-run development pattern.
Described step S2 also comprises: arbitrary day pedestrian traffic historical data sequence of arranging in chronological order of screening same position and conduct be time series laterally.Described pedestrian traffic data comprise flow, regional number, density and speed.Described step S2 comprises: with a time scale is benchmark, is step-length with a time yardstick, with not on the same day pedestrian traffic historical data time scale alignment of same position.The benchmark of described time scale is 00:00:00 every day, and described time scale is 5 minutes.Described step S3 comprises: the screening secular trend similar continuous a plurality of week the phase same date the pedestrian traffic historical data and as vertical time series.Continuous a plurality of weeks of described screening are 4-5 week.Described step S5 comprises: if the pedestrian traffic real time data is normal pedestrian's traffic data, then upgrade the long-run development pattern with real time data, reject data the earliest in the middle of the original long-run development pattern simultaneously; If the pedestrian traffic real time data for lose, mistake or unusual pedestrian traffic data, then keep original long-run development pattern constant.
One embodiment of the invention are for accumulating the pedestrian traffic data of each monitoring location of Xidan commercial district, make up long term data rule and pedestrian traffic rule in short-term.
According to time organizational form difference, the present invention is divided into horizontal time series and vertical time series two classes with the time series of pedestrian traffic data.Wherein, laterally time series is meant the data sequence of arranging by arbitrary day time sequencing; Vertically time series is meant in chronological sequence pedestrian traffic data sequence of same period of series arrangement certain day.
The pedestrian traffic data time sequence of particular spatial location has secular trend, the short-term trend of the times and random fluctuation three specific characters usually.(1) secular trend, the specific region generally has more stable socio-economic activity pattern, promptly go to work, go to school, activity such as shopping has certain rules in time and spatial distributions, causes different same date in week (Monday, Tuesdays ... Sunday) pedestrian traffic pattern has stronger similarity.The present invention is not with same monitoring position, the characteristics of the same supplemental characteristic time series of same date with similarity are called secular trend.(2) the short-term trend of the times, because the influence of factors such as pedestrian traffic incident, the phenomenon of secular trend may appear departing from pedestrian's rule of specific region in short-term, the present invention is referred to as the pedestrian traffic seasonal effect in time series short-term trend of the times.(3) random fluctuation, except secular trend, the short-term trend of the times, also there is tangible random fluctuation in the pedestrian traffic data, in order to eliminate random fluctuation to the influence that the pedestrian traffic management decision produces, it suitably should be carried out filtering.
For a certain date, if the evolution of pedestrian traffic data time sequence relatively meets the long-run development pattern, then think a kind of normal pedestrian's traffic behavior, otherwise, be called unusual pedestrian traffic state.The predictability of normal pedestrian's traffic behavior is stronger, can carry out early warning to it, and unusual pedestrian traffic state generally be difficult to prediction, can only carry out Realtime Alerts to it.
For reliable information basis being provided can for the judgement of pedestrian traffic state, the present invention is by analyzing the vertical time series of pedestrian traffic data, and the off-line of design data long-run development pattern makes up and the online updating method.
By observing the pedestrian traffic data as can be known, often there is difference in same position not on the same day data time scale, causes data long-run development pattern to be difficult to extract.Therefore, the present invention proofreaies and correct the time scale of historical data earlier, is benchmark with 00:00:00 promptly, is step-length with the time scale, with same position not on the same day pedestrian traffic historical data time scale artificially align.For example time series 00:00:04,00:00:10,00:00:16, carry out index correction according to the 6s time scale after, become 00:00:06,00:00:12,00:00:18.
For a certain monitoring position, different weeks, of even date pedestrian traffic pattern was more similar, and in view of the above, the present invention's design is based on the long-run development mode construction method on nature date.Specifically, at arbitrary sampling time interval, the screening secular trend comparatively similar continuous some weeks the phase same date the pedestrian traffic data, and with it as judging whether next week of even date data meet the foundation of secular trend.
Long-run development pattern that it should be noted that the pedestrian traffic data is a relative notion, can be not unalterable, but have certain evolution property in season.That is to say that for relatively contiguous week, the long-run development pattern of pedestrian traffic data is more stable, but for time span for bigger week, the long-run development pattern of pedestrian traffic data has bigger difference.Therefore, make up the long-run development pattern week quantity can not be excessive, generally adopt 4-5 week to be advisable.
Except the long-run development mode construction method based on the nature date, the present invention also designs long-run development mode construction method respectively at two kinds of special case:
(1) based on the long-run development mode construction method of cluster analysis
For a certain monitoring position, if the data variation similar trend on same some date in week then can be considered as it same natural date, so that reduce the evolution property in season of long-run development pattern.Specifically, adopt the cluster analysis technology with same monitoring position not the data sequence of same date sort out, and form the long-run development pattern of pedestrian traffic data with similar some dates.If there is difference in the cluster result in different weeks, then need analyzes the data in a plurality of weeks, and adopt the principle of comforming to obtain final classification results.
The core content of cluster analysis is " distance " calculated between the different variablees, and the present invention adopts Euclidean distance as the estimating of " distance " between the same date pedestrian traffic data time sequence not of same week, specifically suc as formula shown in (4-1).
In the formula: R (x, y)---the Euclidean distance between two variablees;
(x, y)---the same individual not pedestrian traffic data time sequence of same date;
P---sample size.
(2) based on the long-run development mode construction method of technical dates:
For some technical dates, for example important red-letter day, holiday etc., because the pedestrian traffic pattern of this moment is comparatively special, utilize nature date or cluster analysis may be difficult to make up rational long-run development pattern, therefore, the present invention is the pedestrian traffic data long-run development pattern that the cycle makes up technical dates with the year.For the preliminary stage of system operation,, can quote the adjacent nonworkdays long-run development pattern on (Saturday, Sunday) if do not obtain effective technical dates of historical data as yet.
Along with the passing of vertical time, when producing new measured data,, need carry out real-time update to it in order to keep the ageing of pedestrian traffic data long-run development pattern.The present invention upgrades pedestrian traffic data long-run development pattern in different ways according to the quality category under each sampling time interval data, and concrete grammar is as follows:
(1) if the measured data of certain sampling time interval for lose, mistake or unusual pedestrian traffic status data, then should keep original long-run development pattern constant;
(2) if the measured data of certain sampling time interval is normal pedestrian's traffic state data, then upgrade the long-run development pattern with measured data, reject data the earliest in the middle of the original long-run development pattern simultaneously.
The above only is preferred embodiment of the present invention, non-limitation protection scope of the present invention, and the equivalent structure that all utilizations instructions of the present invention and accompanying drawing content are done changes, and all is contained in protection scope of the present invention.
Claims (9)
1. the structure and the update method of a pedestrian traffic data long-run development pattern, described pedestrian traffic data have time scale and time scale, and comprise pedestrian traffic historical data and pedestrian traffic real time data, it is characterized in that this method comprises:
Step S1: obtain many days pedestrian traffic historical data at least one position and storage;
Step S2: described pedestrian traffic historical data is carried out time scale proofread and correct;
Step S3: arbitrary day pedestrian traffic historical data sequence of arranging in chronological order of screening same position and conduct be time series laterally, the pedestrian traffic historical data sequence of the same time scale of arranging in chronological order of screening same position certain day and as vertical time series, based on described two sequences to make up pedestrian traffic data long-run development pattern;
Step S4: sampling pedestrian traffic real time data is also carried out pre-service;
Step S5: the pedestrian traffic historical data in pretreated pedestrian traffic real time data and the described vertical time series is compared and upgrade vertical time series according to comparison result;
Step S6: repeating step S4 and step S5, thus finish the structure and the renewal of pedestrian traffic data long-run development pattern.
2. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 1 is characterized in that described pedestrian traffic data comprise flow, regional number, density and speed.
3. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 1, it is characterized in that, described step S2 comprises: with a time scale is benchmark, is step-length with a time yardstick, with not on the same day pedestrian traffic historical data time scale alignment of same position.
4. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 3 is characterized in that, the benchmark of described time scale is 00:00:00 every day, and described time scale is 5 minutes.
5. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 1, it is characterized in that described step S3 comprises: the screening secular trend similar continuous a plurality of week the phase same date the pedestrian traffic historical data and as vertical time series.
6. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 5 is characterized in that, continuous a plurality of weeks of described screening are 4-5 week.
7. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 1, it is characterized in that, described step S3 comprises: adopt the cluster analysis technology with same position not the data sequence of same date sort out, and form the long-run development pattern of pedestrian traffic data with similar a plurality of dates; If there is difference in the cluster result in different weeks, then analyzes the data in a plurality of weeks, and adopt the principle of comforming to obtain final classification results.
8. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 1 is characterized in that described step S3 comprises: be the pedestrian traffic data long-run development pattern that makes up in the cycle with the year; For the preliminary stage of system operation,, then quote the long-run development pattern of adjacent nonworkdays if do not obtain effective technical dates of historical data as yet; Wherein, comprise red-letter day, holiday described technical dates.
9. the structure and the update method of pedestrian traffic data long-run development pattern as claimed in claim 1, it is characterized in that, described step S5 comprises: if the pedestrian traffic real time data is normal pedestrian's traffic data, then upgrade the long-run development pattern, reject data the earliest in the middle of the original long-run development pattern simultaneously with real time data; If the pedestrian traffic real time data for lose, mistake or unusual pedestrian traffic data, then keep original long-run development pattern constant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110109072 CN102201000A (en) | 2011-04-28 | 2011-04-28 | Method for constructing and updating pedestrian traffic data long-term development mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110109072 CN102201000A (en) | 2011-04-28 | 2011-04-28 | Method for constructing and updating pedestrian traffic data long-term development mode |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102201000A true CN102201000A (en) | 2011-09-28 |
Family
ID=44661675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110109072 Pending CN102201000A (en) | 2011-04-28 | 2011-04-28 | Method for constructing and updating pedestrian traffic data long-term development mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102201000A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424294A (en) * | 2013-09-02 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Information processing method and information processing device |
| CN104737152A (en) * | 2012-06-01 | 2015-06-24 | 兰屈克有限公司 | A system and method for transferring information from one data set to another |
-
2011
- 2011-04-28 CN CN 201110109072 patent/CN102201000A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104737152A (en) * | 2012-06-01 | 2015-06-24 | 兰屈克有限公司 | A system and method for transferring information from one data set to another |
| US9519910B2 (en) | 2012-06-01 | 2016-12-13 | Rentrak Corporation | System and methods for calibrating user and consumer data |
| US11004094B2 (en) | 2012-06-01 | 2021-05-11 | Comscore, Inc. | Systems and methods for calibrating user and consumer data |
| CN104424294A (en) * | 2013-09-02 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Information processing method and information processing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102169630B (en) | Quality control method of road continuous traffic flow data | |
| CN109657844B (en) | Electric power short-term load prediction method and device | |
| US20110085649A1 (en) | Fluctuation Monitoring Method that Based on the Mid-Layer Data | |
| CN102568205B (en) | Traffic parameter short-time prediction method based on empirical mode decomposition and classification combination prediction in abnormal state | |
| CN109615226A (en) | A kind of operation indicator method for monitoring abnormality | |
| CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
| CN102867221A (en) | Method for dynamically and transversely correcting medium and long-term electric quantity forecasting | |
| CN104573877A (en) | Power distribution network equipment demand prediction and quantitative method and system | |
| CN110232515A (en) | A kind of BIM project real-time monitoring system and evaluation method | |
| CN102129776A (en) | Automatic detection method and system of abnormal pedestrian traffic state | |
| Chen et al. | Vulnerability modeling, assessment, and improvement in urban metro systems: A probabilistic system dynamics approach | |
| CN111008727A (en) | Power distribution station load prediction method and device | |
| CN202075864U (en) | Abnormal traffic state automatic detection system | |
| CN108154276A (en) | Attendance analysis method based on image identification and machine learning | |
| CN103002165A (en) | Method for predicting short-term telephone traffic of power supply service center | |
| CN104408525A (en) | Quantitative evaluation and control method of job shop scheduling risks | |
| CN102201000A (en) | Method for constructing and updating pedestrian traffic data long-term development mode | |
| CN102184638B (en) | Method for preprocessing pedestrian traffic data | |
| CN102142192B (en) | Method and system for forewarning pedestrian traffic congestion based on combined multi-step prediction | |
| CN108345996B (en) | System and method for reducing wind power assessment electric quantity | |
| CN102156822A (en) | Pedestrian traffic data assembly multi-step forecasting method | |
| JP5561643B2 (en) | Demand forecasting device and water operation monitoring system | |
| CN105260948A (en) | City water supply system daily plan scheduling decision-making method | |
| CN110988783A (en) | Intelligent electric meter precision online monitoring method and device | |
| CN110163668A (en) | A kind of Products Show method based on correlation rule and collaborative filtering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110928 |