CN111126713B - Space-time hot spot prediction method and device based on bayonet data and controller - Google Patents
Space-time hot spot prediction method and device based on bayonet data and controller Download PDFInfo
- Publication number
- CN111126713B CN111126713B CN201911405121.3A CN201911405121A CN111126713B CN 111126713 B CN111126713 B CN 111126713B CN 201911405121 A CN201911405121 A CN 201911405121A CN 111126713 B CN111126713 B CN 111126713B
- Authority
- CN
- China
- Prior art keywords
- time
- space
- vehicle
- sample point
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000000694 effects Effects 0.000 claims abstract description 124
- 101100100125 Mus musculus Traip gene Proteins 0.000 claims abstract description 94
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000005311 autocorrelation function Methods 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005314 correlation function Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000029305 taxis Effects 0.000 description 2
- 208000012661 Dyskinesia Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009499 grossing Methods 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
- 230000003287 optical effect Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000001744 unit root test Methods 0.000 description 1
Images
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application provides a space-time hot spot prediction method, a device and a controller based on traffic gate data, which relate to the field of traffic, and generate traffic sample point data by using traffic source data acquired based on road traffic gate, wherein the sample point data at least comprises: vehicle information, vehicle passing position and vehicle passing time; calculating a trip activity index of each vehicle according to the sample point data, wherein the trip activity index is used for evaluating the activity degree distribution of the vehicle in the time dimension and/or the space dimension; evaluating the sample point data by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in each space-time scale range, wherein a trip activity index is introduced into the space-time kernel density estimation method as a trip activity weight of the sample point data and is used for adjusting and generating the space-time kernel density estimation values; and predicting the space-time hot spot of the future time period according to the space-time kernel density estimated value. According to the scheme, urban space-time hot spots can be accurately predicted based on the activity degree of each user in actual travel.
Description
Technical Field
The application belongs to the traffic field, and particularly relates to a spatial-temporal hot spot prediction method, a spatial-temporal hot spot prediction device and a spatial-temporal hot spot prediction controller based on bayonet data.
Background
At present, the study of urban space-time hot spots is mostly carried out on all collected taxi tracks, the tracks are divided according to space-time cube units by adopting a Getis-Ord Gi statistical method, and hot spot units covered by all track data are calculated to be used as urban space-time hot spots. However, this method has limitations:
1. because the specific gravity of the taxis in urban vehicles is smaller, the track of the taxis is limited in urban coverage and monitoring range, and all the passing data of the city cannot be truly reflected;
2. lacking an accurate interpretation of the heat of the urban "hot spot" area by the corresponding index, only the number of passes is insufficient to account for the heat of the area (heat is relative and if there are many passes through each place, it cannot be accounted for that each place is a hot spot).
Disclosure of Invention
In order to more accurately predict urban space-time hot spots to at least a certain extent, the application provides a bayonet data-based space-time hot spot prediction method, a bayonet data-based space-time hot spot prediction device and a bayonet data-based controller, and the urban space-time hot spots can be accurately predicted based on the activity degree of actual traveling of each vehicle owner.
In order to achieve the above purpose, the present application adopts the following technical scheme:
in a first aspect, a spatial-temporal hot spot prediction method based on bayonet data is provided, including:
generating passing sample point data based on passing source data acquired by a road gate, wherein the sample point data at least comprises: vehicle information, vehicle passing position and vehicle passing time;
calculating the trip activity index of each vehicle according to the sample point data, wherein the trip activity index is used for evaluating the activity degree distribution of the vehicles in the time dimension and/or the space dimension;
the sample point data is evaluated by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in various space-time scale ranges, and the travel activity index is introduced into the space-time kernel density estimation method to serve as travel activity weight of the sample point data and used for adjusting and generating the space-time kernel density estimation values;
and predicting the space-time hot spot of the future time period according to the space-time kernel density estimated value.
In a second aspect, a spatial-temporal hot spot prediction apparatus based on bayonet data is provided, including:
the data generation module is used for generating passing sample point data based on passing source data acquired by the road gate, and the sample point data at least comprises: vehicle information, vehicle passing position and vehicle passing time;
the activity index calculation module is used for calculating the trip activity index of each vehicle according to the sample point data, and the trip activity index is used for evaluating the activity degree distribution of the vehicles in the time dimension and/or the space dimension;
the density estimation module is used for estimating the sample point data by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in various space-time scale ranges, wherein the travel activity index is introduced into the space-time kernel density estimation method to serve as travel activity weight of the sample point data, and the travel activity index is used for adjusting and generating the space-time kernel density estimation values;
and the hot spot prediction module is used for predicting the space-time hot spot of the future time period according to the space-time nuclear density estimated value.
In a third aspect, a controller is provided for performing a spatiotemporal hotspot prediction method based on bayonet data as described in any of the above.
According to the space-time hot spot prediction method, the device and the controller based on the gate data, which are provided by the embodiment of the invention, the passing sample point data is generated based on the passing source data acquired by the road gate, and the sample point data at least comprises the following steps: vehicle information, vehicle passing position and vehicle passing time; calculating a trip activity index of each vehicle according to the sample point data, wherein the trip activity index is used for evaluating the activity degree distribution of the vehicle in the time dimension and/or the space dimension; evaluating the sample point data by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in each space-time scale range, wherein a trip activity index is introduced into the space-time kernel density estimation method as a trip activity weight of the sample point data and is used for adjusting and generating the space-time kernel density estimation values; and predicting the space-time hot spot of the future time period according to the space-time kernel density estimated value.
In the scheme, the trip activity index is introduced to represent the activity degree distribution trend of the vehicle in the time dimension and/or the space dimension so as to distinguish the influence of trip modes of different vehicle owners on the space-time heat, thereby greatly eliminating the influence of the frequency of passing vehicles on the whole space-time heat trend caused by sporadic (such as high frequency of passing vehicles of a single person on a certain place) passing vehicle events.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.
FIG. 1 is a flowchart of a spatial-temporal hot spot prediction method based on bayonet data in an embodiment of the present application;
FIG. 2 is a schematic diagram of a kernel density estimation algorithm in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a spatial-temporal hot spot prediction device based on bayonet data in an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail below. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, based on the examples herein, which are within the scope of the protection sought by those of ordinary skill in the art without undue effort, are intended to be encompassed by the present application.
Example 1
The embodiment of the invention provides a spatial-temporal hot spot prediction method based on bayonet data, as shown in fig. 1, which comprises the following steps:
s110, generating passing sample point data based on passing source data acquired by the road gate, wherein the sample point data at least comprises: vehicle information, passing vehicle position, and passing vehicle time.
The method comprises the steps that vehicle passing source data on a road are collected through a gate arranged in an urban road, and the vehicle passing source data recorded by the gate are image data; performing image recognition on the image data, and extracting vehicle information; and taking the bayonet position as an passing vehicle position, and taking the data acquisition time as an passing vehicle time to generate passing vehicle sample point data.
For example, information such as license plate numbers of vehicles passing through the blocking area can be obtained by processing the blocking photo data through algorithms such as license plate positioning, license plate character segmentation, license plate character recognition and the like in the passing source data containing the automobile image. And then cleaning, correlating and integrating the information with information such as the time of passing the vehicle through the gate, the lane where the vehicle is located, the longitude and latitude of the gate and the like to obtain data of the sample point of passing the vehicle through the gate within a period of time. Each sample point data at least comprises: vehicle information (such as license plate number for identifying vehicle owner), passing vehicle position (bayonet number, longitude, latitude), and passing vehicle time (including date, time); but may of course also include direction of travel, vehicle speed, etc.
And S120, calculating the trip activity index of each vehicle according to the sample point data, wherein the trip activity index is used for evaluating the activity degree distribution of the vehicle in the time dimension and/or the space dimension.
In particular, the trip activity index of the vehicle in the present solution is intended to evaluate the activity level distribution of each vehicle in the time dimension and/or the space dimension. For example, for office workers, their vehicles have higher activity indexes during commute peak hours than during other hours; the activity index is higher in the commute pathway region compared to other regions. However, the travel activity profile of their vehicle is different for different owners, and accordingly its contribution to a certain spatiotemporal zone being evaluated as a hot spot zone is also different. When most of the vehicle owners have corresponding trip active indexes of the vehicles, the hot spot area is significant only when the hot spot area is represented by a certain space-time area. It is obviously not comprehensive and lacks certain rationality to measure that a space-time zone is a hot spot zone by only measuring the overall passing frequency without distinguishing the vehicle liveness.
The trip activity index provided in the scheme can precisely reflect the distinguishing contribution of the trip mode of each vehicle (vehicle owner) to whether the space-time area is a hot spot area or not. The index can eliminate the influence of the frequency of passing vehicles on the whole space-time heat trend, which is sporadic (such as that a single person goes out in a certain place with high frequency).
In a specific embodiment, the trip activity index may include a trip period activity index for evaluating an activity level distribution of the vehicle in a time dimension.
Specifically, the sample point data amount of each vehicle at different time periods can be extracted from the sample point data; and then taking the ratio of the data quantity of the sample points of each vehicle in different time periods to the average value of the data quantity of the sample points of the corresponding vehicle in the whole time period as the trip time period activity index of the vehicle.
For example, the trip period activity index may be a ratio of a frequency of a vehicle owner (vehicle) passing through a gate for an hour (period) in a set period (e.g., week, month, year, etc.) to a mean of the frequency of vehicle passing through the full period.
For example, the travel period activity index may be calculated by equation (1):
wherein T is c,q Representing vehicle c (c e (c) 1 、c 2 ，.....，c n ) At the q (q.epsilon.q 1 、q 2 ，.....，q n ) Period activity of period f) c,q Indicating the frequency of passing vehicles c through all bayonets in the q-th period of the unit cycle (week, month, year, etc.); g is the total number of time periods contained in a unit cycle.
In addition, in an embodiment, the trip activity index may also include a trip area activity index for evaluating an activity level distribution of the vehicle in a spatial dimension.
Specifically, the sample point data amount of each vehicle in different bayonet areas can be extracted from the sample point data; and then taking the ratio of the data quantity of the sample points of each vehicle in different gate areas to the average value of the data quantity of the sample points of the corresponding vehicle in all gate areas as the trip area activity index of the vehicle.
For example, the trip area activity index may be a ratio of a frequency of passing a certain gate by an owner (vehicle) in a set period (such as week, month, year, etc.) to a mean value of the frequency of passing the gate by all gates.
For example, the trip zone activity index may be calculated by equation (2):
wherein K is c,m Indicating that the vehicle c is traveling through the mth (mE (m 1 、m 2 ，.....，m n ) Area activity at bayonet; f (f) c,m The frequency of passing of the vehicle c through the mth gate in a unit period (week, month, year, etc.), j being the total number of gates in the investigation region.
In an actual application scene, any one of the trip period activity index and the trip area activity index can be used as the trip activity index, and the trip activity index can be obtained by comprehensively evaluating the two indexes again. Namely: and calculating and obtaining the final trip activity index of each vehicle based on the trip period activity index and the trip area activity index.
For example, the trip zone activity index may be calculated by equation (3):
A c,q,m ＝T c,q +K c,m ………………………………(3)
wherein A is c,q,m Representing vehicle c (c e (c) 1 、c 2 ，.....，c n ) In unit period (week, month, year, etc.) at the q (q.epsilon (q) 1 、q 2 ，.....，q n ) The period passes through m (m E (m) 1 、m 2 ，.....，m n ) Trip activity index at bayonet). Namely: taking the sum of the trip period activity index and the trip area activity index as a trip out valueRow activity index.
It can be seen from formulas (1), (2) and (3) that in practice, for each sample point data (three-dimensional data) such a trip activity index corresponds. The trip activity index can be used for evaluating the distribution frequency of the vehicle owners corresponding to the trip event.
And S130, evaluating the sample point data by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in various space-time scale ranges, and introducing a trip activity index into the space-time kernel density estimation method as a trip activity weight of the sample point data for regulating and generating the space-time kernel density estimation values.
With respect to the principle of kernel density estimation, as shown in fig. 2, a probability density function or continuous surface may characterize the distribution of a set of data points, which are implemented by different density estimation or data smoothing techniques, with the most widely applied kernel density estimation method. The kernel density estimation method (Kernel Density Estimation) is a non-parametric estimation method commonly used in spatial analysis for calculating the density of an element in its surrounding vicinity.
Because the density surface may show where the point elements or line elements are more concentrated, the kernel density estimation method is typically used for "hot spot" analysis in geographic information systems (Geographic Information System or Geo-Information system, GIS). The calculation formula of the nuclear density estimation method is as follows:
wherein p (x) represents a spatial kernel density estimate, s represents the number of point elements contained within a range of distance scales, K (·) represents a kernel density function, h is a spatial distance threshold (spatial bandwidth), d (x, x) i ) Representing the estimated point x to the sample point x i Euclidean distance between them.
Regarding the core density estimation principle, because the travel time-space hot spot has a characteristic of 'hot spot' in time (such as early and late peaks, etc.), the time information is introduced into the core density hot spot calculation to expand the core density estimation in the time dimension, so that the time-space variation trend of the travel hot spot density distribution is represented. The calculation formula of the space-time kernel density estimation method is as follows:
wherein p (x) represents a space-time kernel density estimate, h t Is a time distance threshold (time bandwidth), d (t, t i ) Representing the estimated point time t to the sample point time t i The time distance between them.
The space-time nuclear density analysis method firstly divides an analysis area into grid units (a three-dimensional grid, a horizontal plane represents a space dimension and an ordinate represents a time dimension), and then calculates sample point data around each grid unit, namely bayonet coordinate points (according to the characteristics of passing data, one sample point is calculated when each passing is input, N times of passing are used for calculating N sample point data, and the like). Conceptually, each point element is covered with a smooth surface. The surface value is highest at the position where the sample point is located, gradually decreases as the distance from the sample point increases, and becomes zero at the position where the distance from the sample point is equal to the bandwidth (including the spatial bandwidth and the temporal bandwidth). The volume of the space surrounded by the smooth curved surface and the lower plane is equal to 1 (representing one pass). The output density of each grid cell is the sum of the values of all the nuclear surfaces superimposed in the center of the grid pixel.
In the process of using nuclear density analysis, bandwidths h and h t The value is particularly important. Different space-time bandwidth scales can cause different kernel density estimation results, so that in specific calculation, comparison tests are needed to be carried out on different space-time bandwidth values for a plurality of times, and the optimal space-time bandwidth is selected from the comparison tests.
Regarding a space-time kernel density estimation formula for introducing the trip-activity index, on the basis of the space kernel density estimation method, the scheme expands from space dimension to form the space-time kernel density estimation method, and simultaneously introduces the trip-activity index as weight to measure the influence value of different frequency trip-in events on heat, so that the space-time kernel density estimation method based on the trip-activity index is finally formed. The mathematical expression is as follows:
wherein p (x) represents a space-time kernel density estimation value, s represents the number of stuck vehicle events (i.e. the number of sample points in a grid unit) in a space-time scale range, K (·) represents a kernel density function, a Gaussian kernel function, an Epanechnikov kernel function, and the like are taken, A i And (5) representing the trip activity index corresponding to the ith sample point.
According to the scheme, by introducing the space-time kernel density estimation method of the trip activity index, in the process of estimating the kernel density value of the sample space, the curve estimated values estimated based on different sample point data can be adjusted through the activity degree distribution of the car outgoing frequency of the car owner in the time dimension and/or the space dimension, so that the space-time kernel density estimated values in each space-time scale range can be finally adjusted, and the influence of the passing frequency caused by sporadic (such as high trip frequency of a single person) passing events on the whole space-time heat trend can be greatly eliminated.
And S140, predicting the space-time hot spot of the future time period according to the space-time kernel density estimated value.
Based on the calculated space-time kernel density value, the space-time kernel density value of a period of time can be used as time series data to be input, and the space-time kernel density value in a future period of time is predicted, so that the space-time hot spot is determined.
For example, an ARIMA model can be constructed with the estimated space-time kernel density of the past time period as a time series data sample, and the estimated space-time kernel density of the future time period can be predicted based on the ARIMA model; a spatio-temporal hot spot for the future time period is then determined based on the predicted spatio-temporal kernel density estimates for the future time period.
The ARIMA model (Autoregressive Integrated Moving Average model, integrated moving average autoregressive model) is a time series prediction method, which is simple and easy to use, and only needs endogenous variables without the help of other exogenous variables. Equation parameters of the ARIMA model are expressed as ARIMA (p, d, q), where p is an autoregressive term, q is the number of moving average terms, and d is the number of differences made in the time series from jerkiness to plateau. The process of constructing the ARIMA model for prediction comprises the following steps: (1) judging sequence stability, (2) estimating model parameters, (3) checking residual sequence, and (4) predicting model.
(1) Sequence stability determination
Whether the nuclear density time series has stationarity or not is judged by calculating the mean value, standard deviation and the like of the nuclear density time series, and if the time series is a non-stationary time series, the time series can be changed into a stationary time series by logarithmic transformation, difference and the like. After conversion to a stable sequence, unit root test is required, and the P <0.05 represents that no unit root exists in the sequence, namely the stable sequence. The d value (number of differences) in the model can be determined in this step.
(2) Model parameter estimation
The time series data of the stationarity kernel density value is input into an autocorrelation function and a partial correlation function to respectively obtain an autocorrelation function diagram and a partial correlation function diagram, an optimal model is determined according to a red pool information criterion, and values of p and q in the model are determined. Substituting the parameter values into the model to obtain a fitting curve.
(3) Residual sequence checking
And comparing the fitting value with the actual value to obtain a residual sequence, and performing white noise test on the residual, namely observing whether the continuous prediction error of the model has autocorrelation or not and whether the average value is zero and the variance is constant.
(4) Model prediction
And predicting the nuclear density estimated value of the future time period by using the constructed ARIMA model, and obtaining the corresponding space-time hot spot through threshold classification.
For example, determining a spatio-temporal hotspot for a future time period based on the predicted spatio-temporal kernel density estimate for the future time period may include:
and determining a time-space domain which is greater than a preset density threshold in the predicted time-space kernel density estimated value in the future time period as a time-space hot spot in the future time period.
According to the space-time hot spot prediction method based on the gate data, which is provided by the embodiment of the invention, the passing sample point data is generated based on the passing source data acquired by the road gate, and the sample point data at least comprises the following steps: vehicle information, vehicle passing position and vehicle passing time; calculating a trip activity index of each vehicle according to the sample point data, wherein the trip activity index is used for evaluating the activity degree distribution of the vehicle in the time dimension and/or the space dimension; evaluating the sample point data by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in each space-time scale range, wherein a trip activity index is introduced into the space-time kernel density estimation method as a trip activity weight of the sample point data and is used for adjusting and generating the space-time kernel density estimation values; and predicting the space-time hot spot of the future time period according to the space-time kernel density estimated value.
In the scheme, the trip activity index is introduced to represent the activity degree distribution trend of the vehicle in the time dimension and/or the space dimension so as to distinguish the influence of trip modes of different vehicle owners on the space-time heat, thereby greatly eliminating the influence of the frequency of passing vehicles on the whole space-time heat trend caused by sporadic (such as high frequency of passing vehicles of a single person on a certain place) passing vehicle events.
In addition, the actual trip rule of personnel is reflected by using the gate monitoring passing data as a data source, trip activity indexes are introduced to measure trip activity degrees of different car owners, trip space-time nuclear density estimated values of areas are obtained, urban space-time hot spots are predicted based on the space-time nuclear density estimated values, and accuracy is higher.
Example two
In order to cooperate with implementing the spatial-temporal hot spot prediction method based on the bayonet data, an embodiment of the present invention provides a spatial-temporal hot spot prediction device based on the bayonet data, as shown in fig. 3, the device includes:
the data generating module 310 is configured to generate driving sample point data based on driving source data collected by the road junction, where the sample point data at least includes: vehicle information, vehicle passing position and vehicle passing time;
the activity index calculation module 320 is configured to calculate a trip activity index of each vehicle according to the sample point data, where the trip activity index is used to evaluate an activity degree distribution of the vehicle in a time dimension and/or a space dimension;
the density estimation module 330 is configured to evaluate the sample point data by using a space-time kernel density estimation method, to obtain space-time kernel density estimation values in each space-time scale range, and introduce a trip activity index as a trip activity weight of the sample point data in the space-time kernel density estimation method, to adjust and generate the space-time kernel density estimation values;
the hotspot prediction module 340 is configured to predict a spatio-temporal hotspot in a future time period according to the spatio-temporal kernel density estimation value.
In a specific embodiment, the activity index calculation module 320 is specifically configured to extract, from the sample point data, sample point data amounts of each vehicle in different periods; and taking the ratio of the data quantity of the sample points of each vehicle in different time periods to the average value of the data quantity of the sample points of the corresponding vehicle in the whole time period as the trip time period activity index of the vehicle.
In a specific embodiment, the activity index calculation module 320 is specifically configured to extract, from the sample point data, sample point data amounts of each vehicle in different bayonet areas; and taking the ratio of the data quantity of the sample points of each vehicle in different gate areas to the average value of the data quantity of the sample points of the corresponding vehicle in all gate areas as the trip area activity index of the vehicle.
In a specific embodiment, the activity index calculation module 320 is specifically configured to calculate a final trip activity index of each vehicle based on the trip period activity index and the trip area activity index.
In a specific embodiment, the hotspot prediction module 340 is specifically configured to take the estimated space-time kernel density value of the past time period as a time series data sample, construct an ARIMA model, and predict the estimated space-time kernel density value of the future time period based on the ARIMA model; and determining a space-time hot spot of the future time period according to the predicted space-time nuclear density estimated value in the future time period.
In a specific embodiment, the hotspot prediction module 340 is specifically configured to determine, as the spatio-temporal hotspot of the future time period, a space-time domain in the estimated space-time kernel density value within the predicted future time period that is greater than the preset density threshold.
In a specific embodiment, the data generating module 310 is specifically configured to collect driving source data based on a road junction, where the driving source data is image data; performing image recognition on the image data, and extracting vehicle information; and taking the bayonet position as an passing vehicle position, and taking the data acquisition time as an passing vehicle time to generate passing vehicle sample point data.
Further, the embodiment also provides a controller, which is used for executing the spatial-temporal hot spot prediction method based on the bayonet data.
According to the space-time hot spot prediction method, the device and the controller based on the gate data, which are provided by the embodiment of the invention, the passing sample point data is generated based on the passing source data acquired by the road gate, and the sample point data at least comprises the following steps: vehicle information, vehicle passing position and vehicle passing time; calculating a trip activity index of each vehicle according to the sample point data, wherein the trip activity index is used for evaluating the activity degree distribution of the vehicle in the time dimension and/or the space dimension; evaluating the sample point data by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in each space-time scale range, wherein a trip activity index is introduced into the space-time kernel density estimation method as a trip activity weight of the sample point data and is used for adjusting and generating the space-time kernel density estimation values; and predicting the space-time hot spot of the future time period according to the space-time kernel density estimated value.
In the scheme, the trip activity index is introduced to represent the activity degree distribution trend of the vehicle in the time dimension and/or the space dimension so as to distinguish the influence of trip modes of different vehicle owners on the space-time heat, thereby greatly eliminating the influence of the frequency of passing vehicles on the whole space-time heat trend caused by sporadic (such as high frequency of passing vehicles of a single person on a certain place) passing vehicle events.
In addition, the actual trip rule of personnel is reflected by using the gate monitoring passing data as a data source, trip activity indexes are introduced to measure trip activity degrees of different car owners, trip space-time nuclear density estimated values of areas are obtained, urban space-time hot spots are predicted based on the space-time nuclear density estimated values, and accuracy is higher.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.
It should be noted that in the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present application, unless otherwise indicated, the meaning of "plurality" means at least two.
Any process or method description in a flowchart or otherwise described herein may be understood as: means, segments, or portions of code representing executable instructions including one or more steps for implementing specific logical functions or processes are included in the preferred embodiments of the present application, in which functions may be executed out of order from that shown or discussed, including in a substantially simultaneous manner or in an inverse order, depending upon the functionality involved, as would be understood by those skilled in the art to which the embodiments of the present application pertains.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (10)
1. A spatial-temporal hot spot prediction method based on bayonet data is characterized by comprising the following steps:
generating passing sample point data based on passing source data acquired by a road gate, wherein the sample point data at least comprises: vehicle information, vehicle passing position and vehicle passing time;
calculating the trip activity index of each vehicle according to the sample point data, wherein the trip activity index is used for evaluating the activity degree distribution of the vehicles in the time dimension and/or the space dimension;
the sample point data is evaluated by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in various space-time scale ranges, and the travel activity index is introduced into the space-time kernel density estimation method to serve as travel activity weight of the sample point data and used for adjusting and generating the space-time kernel density estimation values;
and predicting the space-time hot spot of the future time period according to the space-time kernel density estimated value.
2. The method of claim 1, wherein calculating a trip activity index for each vehicle from the sample point data comprises:
extracting sample point data amounts of each vehicle in different time periods from the sample point data;
and taking the ratio of the data quantity of the sample points of each vehicle in different time periods to the average value of the data quantity of the sample points of the corresponding vehicle in the whole time period as the trip time period activity index of the vehicle.
3. The method of claim 1, wherein calculating a trip activity index for each vehicle from the sample point data comprises:
extracting sample point data amounts of vehicles in different bayonet areas from the sample point data;
and taking the ratio of the data quantity of the sample points of each vehicle in different gate areas to the average value of the data quantity of the sample points of the corresponding vehicle in all gate areas as the trip area activity index of the vehicle.
4. The method of claim 2, wherein calculating a trip activity index for each vehicle from the sample point data comprises:
extracting sample point data amounts of vehicles in different bayonet areas from the sample point data;
and taking the ratio of the data quantity of the sample points of each vehicle in different gate areas to the average value of the data quantity of the sample points of the corresponding vehicle in all gate areas as the trip area activity index of the vehicle.
5. The method according to claim 4, wherein the method further comprises:
and calculating the final trip activity index of each vehicle based on the trip period activity index and the trip area activity index.
6. The method of claim 1, wherein predicting a spatio-temporal hotspot for a future time period from the spatio-temporal kernel density estimate comprises:
taking the space-time nuclear density estimated value of the past time period as a time sequence data sample, constructing an ARIMA model, and predicting the space-time nuclear density estimated value in the future time period based on the ARIMA model;
and determining a space-time hot spot of the future time period according to the predicted space-time nuclear density estimated value in the future time period.
7. The method of claim 6, wherein determining a spatiotemporal hotspot for the future time period based on the predicted spatiotemporal kernel density estimate for the future time period comprises:
and determining a time-space domain which is greater than a preset density threshold in the predicted time-space kernel density estimated value in the future time period as a time-space hot spot in the future time period.
8. The method of claim 1, wherein generating passing sample point data based on passing source data collected at a roadway gate comprises:
acquiring vehicle passing source data based on a road gate, wherein the vehicle passing source data is image data;
performing image recognition on the image data, and extracting vehicle information; and taking the bayonet position as a passing vehicle position, and taking the data acquisition time as a passing vehicle time to generate the passing vehicle sample point data.
9. A bayonet data-based spatio-temporal hotspot prediction apparatus, comprising:
the data generation module is used for generating passing sample point data based on passing source data acquired by the road gate, and the sample point data at least comprises: vehicle information, vehicle passing position and vehicle passing time;
the activity index calculation module is used for calculating the trip activity index of each vehicle according to the sample point data, and the trip activity index is used for evaluating the activity degree distribution of the vehicles in the time dimension and/or the space dimension;
the density estimation module is used for estimating the sample point data by adopting a space-time kernel density estimation method to obtain space-time kernel density estimation values in various space-time scale ranges, wherein the travel activity index is introduced into the space-time kernel density estimation method to serve as travel activity weight of the sample point data, and the travel activity index is used for adjusting and generating the space-time kernel density estimation values;
and the hot spot prediction module is used for predicting the space-time hot spot of the future time period according to the space-time nuclear density estimated value.
10. A controller configured to perform a bayonet data-based spatiotemporal hotspot prediction method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911405121.3A CN111126713B (en) | 2019-12-31 | 2019-12-31 | Space-time hot spot prediction method and device based on bayonet data and controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911405121.3A CN111126713B (en) | 2019-12-31 | 2019-12-31 | Space-time hot spot prediction method and device based on bayonet data and controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111126713A CN111126713A (en) | 2020-05-08 |
| CN111126713B true CN111126713B (en) | 2023-05-09 |
Family
ID=70506105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911405121.3A Active CN111126713B (en) | 2019-12-31 | 2019-12-31 | Space-time hot spot prediction method and device based on bayonet data and controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126713B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017429B (en) * | 2020-07-10 | 2021-11-09 | 中山大学 | Overload control monitoring stationing method based on truck GPS data |
| CN112598030B (en) * | 2020-12-08 | 2023-03-24 | 山东科技大学 | Non-stationary process monitoring method based on recursive covariance analysis and elastic weight consolidation |
| CN112559507B (en) * | 2020-12-22 | 2024-07-02 | 安徽百诚慧通科技股份有限公司 | Method for correcting passing data |
| CN112818216B (en) * | 2021-01-13 | 2021-09-28 | 平安科技（深圳）有限公司 | Client recommendation method and device, electronic equipment and storage medium |
| CN114547228B (en) * | 2022-04-22 | 2022-07-19 | 阿里云计算有限公司 | Track generation method, device, equipment and storage medium |
| CN116862097B (en) * | 2023-06-08 | 2024-05-31 | 深圳市蕾奥规划设计咨询股份有限公司 | Information determination method and equipment |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402715A (en) * | 2010-09-13 | 2012-04-04 | 方正国际软件有限公司 | Method and device for presenting incident hotspot region |
| CN103236163A (en) * | 2013-04-28 | 2013-08-07 | 北京航空航天大学 | Traffic jam avoiding prompting system based on collective intelligence network |
| CN103839065A (en) * | 2014-02-14 | 2014-06-04 | 南京航空航天大学 | Extraction method for dynamic crowd gathering characteristics |
| CN104574965A (en) * | 2015-01-11 | 2015-04-29 | 杭州电子科技大学 | City traffic hot spot region partition method based on massive traffic flow data |
| CN104794790A (en) * | 2015-04-23 | 2015-07-22 | 南京信息工程大学 | Scenic spot tourist counting and evacuating method |
| CN105008860A (en) * | 2013-01-18 | 2015-10-28 | 通腾发展德国公司 | Method and apparatus for creating map data |
| CN107170247A (en) * | 2017-06-06 | 2017-09-15 | 青岛海信网络科技股份有限公司 | One kind determines intersection queue length method and device |
| CN108876124A (en) * | 2018-06-02 | 2018-11-23 | 南京工业大学 | Data-driven crowd congestion risk analysis method for evacuation bottleneck |
| CN109165245A (en) * | 2018-09-19 | 2019-01-08 | 北京航空航天大学 | The motion track of multisource data fusion generates the spatiotemporal mode method for digging of model |
| CN109272756A (en) * | 2018-11-07 | 2019-01-25 | 同济大学 | A kind of signal-control crossing queue length estimation method |
| CN109543883A (en) * | 2018-10-26 | 2019-03-29 | 上海城市交通设计院有限公司 | A kind of hinge flow space-time distribution prediction modeling method based on multisource data fusion |
| CN109597923A (en) * | 2018-11-05 | 2019-04-09 | 东软集团股份有限公司 | Density Estimator method, apparatus, storage medium and electronic equipment |
| CN110298500A (en) * | 2019-06-19 | 2019-10-01 | 大连理工大学 | A kind of urban transportation track data set creation method based on taxi car data and city road network |
| CN110299011A (en) * | 2019-07-26 | 2019-10-01 | 长安大学 | A kind of traffic flow forecasting method of the highway arbitrary cross-section based on charge data |
| CN110533038A (en) * | 2019-09-04 | 2019-12-03 | 广州市交通规划研究院 | A method of urban vitality area and inner city Boundary Recognition based on information data |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170011299A1 (en) * | 2014-11-13 | 2017-01-12 | Purdue Research Foundation | Proactive spatiotemporal resource allocation and predictive visual analytics system |
| US11276015B2 (en) * | 2017-04-20 | 2022-03-15 | Capital One Services, Llc | Machine learning artificial intelligence system for predicting hours of operation |
| US11037064B2 (en) * | 2017-10-19 | 2021-06-15 | International Business Machines Corporation | Recognizing recurrent crowd mobility patterns |
-
2019
- 2019-12-31 CN CN201911405121.3A patent/CN111126713B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402715A (en) * | 2010-09-13 | 2012-04-04 | 方正国际软件有限公司 | Method and device for presenting incident hotspot region |
| CN105008860A (en) * | 2013-01-18 | 2015-10-28 | 通腾发展德国公司 | Method and apparatus for creating map data |
| CN103236163A (en) * | 2013-04-28 | 2013-08-07 | 北京航空航天大学 | Traffic jam avoiding prompting system based on collective intelligence network |
| CN103839065A (en) * | 2014-02-14 | 2014-06-04 | 南京航空航天大学 | Extraction method for dynamic crowd gathering characteristics |
| CN104574965A (en) * | 2015-01-11 | 2015-04-29 | 杭州电子科技大学 | City traffic hot spot region partition method based on massive traffic flow data |
| CN104794790A (en) * | 2015-04-23 | 2015-07-22 | 南京信息工程大学 | Scenic spot tourist counting and evacuating method |
| CN107170247A (en) * | 2017-06-06 | 2017-09-15 | 青岛海信网络科技股份有限公司 | One kind determines intersection queue length method and device |
| CN108876124A (en) * | 2018-06-02 | 2018-11-23 | 南京工业大学 | Data-driven crowd congestion risk analysis method for evacuation bottleneck |
| CN109165245A (en) * | 2018-09-19 | 2019-01-08 | 北京航空航天大学 | The motion track of multisource data fusion generates the spatiotemporal mode method for digging of model |
| CN109543883A (en) * | 2018-10-26 | 2019-03-29 | 上海城市交通设计院有限公司 | A kind of hinge flow space-time distribution prediction modeling method based on multisource data fusion |
| CN109597923A (en) * | 2018-11-05 | 2019-04-09 | 东软集团股份有限公司 | Density Estimator method, apparatus, storage medium and electronic equipment |
| CN109272756A (en) * | 2018-11-07 | 2019-01-25 | 同济大学 | A kind of signal-control crossing queue length estimation method |
| CN110298500A (en) * | 2019-06-19 | 2019-10-01 | 大连理工大学 | A kind of urban transportation track data set creation method based on taxi car data and city road network |
| CN110299011A (en) * | 2019-07-26 | 2019-10-01 | 长安大学 | A kind of traffic flow forecasting method of the highway arbitrary cross-section based on charge data |
| CN110533038A (en) * | 2019-09-04 | 2019-12-03 | 广州市交通规划研究院 | A method of urban vitality area and inner city Boundary Recognition based on information data |
Non-Patent Citations (3)
| Title |
|---|
| Minsi Ao等.Revealing the User Behavior Pattern Using HNCORS RTK Location Big Data.IEEE Access.2019,(第7期),全文. * |
| 杨丹.基于商务与商业空间活跃度的上海城市中央活动区区域识别研究.中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑.2018,(2018年第2期),全文. * |
| 高悦尔 ; 陈舒婷 ; 郑承于 ; 边经卫 ; .基于浮动车数据的旅游景点周边路网容量研究――以厦门岛为例.地理科学进展.2016,(第12期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111126713A (en) | 2020-05-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126713B (en) | Space-time hot spot prediction method and device based on bayonet data and controller | |
| CN109544932B (en) | Urban road network flow estimation method based on fusion of taxi GPS data and gate data | |
| CN106503840B (en) | Available parking space prediction method and system for parking lot | |
| CN105513354A (en) | Video-based urban road traffic jam detecting system | |
| CN111489008B (en) | Traffic accident influencing factor space effect analysis method and application thereof | |
| Afghari et al. | Contrasting case-wise deletion with multiple imputation and latent variable approaches to dealing with missing observations in count regression models | |
| CN108877226B (en) | Scenic spot traffic travel prediction method and early warning system | |
| KR101255736B1 (en) | Method for classifying meteorological/non-meteorological echoes using single polarization radars | |
| Daraghmi et al. | Crowdsourcing-based road surface evaluation and indexing | |
| Wang et al. | Estimating travel speed of a road section through sparse crowdsensing data | |
| CN103714238A (en) | System and method for rating computer model relative to empirical results for dynamic systems | |
| Holder et al. | Data-driven derivation of requirements for a lidar sensor model | |
| CN106960433B (en) | It is a kind of that sonar image quality assessment method is referred to based on image entropy and the complete of edge | |
| Du et al. | A lifelong framework for data quality monitoring of roadside sensors in cooperative vehicle-infrastructure systems | |
| Shen et al. | Traffic velocity prediction using GPS data: IEEE ICDM contest task 3 report | |
| Tabibiazar et al. | Kernel-based modeling and optimization for density estimation in transportation systems using floating car data | |
| Mahajan et al. | Treating noise and anomalies in vehicle trajectories from an experiment with a swarm of drones | |
| KR102558609B1 (en) | Method for evaluating wind speed patterns to ensure structural integrity of buildings, and computing apparatus for performing the method | |
| CN108920655B (en) | Method and device for quantifying space-time coverage range of road weather information system | |
| CN116311889A (en) | High-ranking road section identification method, device, equipment and medium | |
| Brunauer et al. | Deriving driver-centric travel information by mining delay patterns from single GPS trajectories | |
| Andrieu et al. | Estimation of space-speed profiles: A functional approach using smoothing splines | |
| El Esawey et al. | Using buses as probes for neighbor links travel time estimation in an urban network | |
| Richardson et al. | Network stratification method by travel time variation | |
| Shen et al. | Real-time traffic prediction using GPS data with low sampling rates: a hybrid approach |
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 |