CN107767659B - Shared bicycle attraction amount and occurrence amount prediction method based on ARIMA model - Google Patents
Shared bicycle attraction amount and occurrence amount prediction method based on ARIMA model Download PDFInfo
- Publication number
- CN107767659B CN107767659B CN201710952071.5A CN201710952071A CN107767659B CN 107767659 B CN107767659 B CN 107767659B CN 201710952071 A CN201710952071 A CN 201710952071A CN 107767659 B CN107767659 B CN 107767659B
- Authority
- CN
- China
- Prior art keywords
- shared bicycle
- bicycle
- time
- attraction
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
- G08G1/202—Dispatching vehicles on the basis of a location, e.g. taxi dispatching
-
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
Abstract
The invention discloses a shared bicycle attraction amount and occurrence amount prediction method based on an ARIMA model, which comprises the following steps: 1) GPS positioning data of a single-vehicle static parking position can be used in the acquisition area, and specified days are continuously acquired; 2) acquiring geographic information data of a traffic cell in an area; 3) matching the geographical position information of the shared bicycle to each traffic cell; 4) establishing a total sample of the shared bicycle trip; 5) establishing a space-time distribution thermodynamic diagram of the available vehicle distribution of the shared bicycle and a space thermodynamic diagram of the attraction occurrence times of each cell; 6) establishing a travel time sequence of each traffic cell; 7) establishing an ARIMA prediction model after parameter calibration; 8) and predicting the shared bicycle running amount of each traffic cell in the next time set interval. The demand forecasting method senses the time-space characteristics of the shared bicycle in a city by using the position data of the bicycle, forecasts the time sequence and provides data support for the operation, management and scheduling of the shared bicycle.
Description
Technical Field
The invention relates to an intelligent management method for a shared bicycle, in particular to a short-time attraction amount and occurrence amount prediction method for the shared bicycle based on an ARIMA model.
Background
At the end of 2016, a single stub-free shared vehicle begins to appear at the head and tail of each street, and can be used and parked anytime and anywhere only by scanning to pay the vehicle fee. The shared bicycle profoundly changes the trip structure of the city, the bicycles are returned to the city, the convenience of city residents in trip is brought by large-scale putting, and meanwhile, the difficulty is brought to the operation and management of government management departments and shared bicycle leasing enterprises. For example, in peak hours, due to the tidal nature of traveling, the demand shortage and the demand shortage of the shared vehicles in the area of hot traveling can occur, while the number of the shared vehicles in the area of hot attraction is too large and the shared vehicles are not used by people, so that a large amount of urban space is occupied, and the normal operation of the urban traffic system, especially the slow traveling system, is affected. The country implements a policy of encouraging development on the shared bicycle, brings the shared bicycle into the planning of the urban comprehensive transportation system, and links with the planning of urban public transportation; the method has the advantages of actively promoting the construction of the bicycle lane, perfecting the bicycle traffic network, promoting the arrangement and construction of the parking points of the bicycles, correcting illegal behaviors such as occupying non-motor lanes and the like, and guaranteeing the passing conditions of the bicycles.
The novel pile-free shared bicycle integrates the Internet of things technology, is provided with a vehicle-mounted positioning device such as a GPS module, can be used for a user to check the dynamic position of the available shared bicycle, and provides a foundation for analyzing the distribution and the use of the vehicle in a city. The sharing bicycle provides mass data at every moment, and the analysis and prediction of the total sample occurrence amount and the attraction amount of the area are possible under the data driving. However, a method for mining and predicting the occurrence amount and the attraction amount of a shared bicycle by taking a natural cell as a unit does not exist at present.
Disclosure of Invention
The purpose of the invention is as follows: based on the defects, the invention provides a method for predicting the short-time attraction amount and the generation amount of the shared bicycle based on an ARIMA model.
The technical scheme is as follows: a shared bicycle attraction amount and occurrence amount prediction method based on an ARIMA model comprises the following steps:
1) according to the urban geographic distribution characteristics, a predicted target area is defined, the static parking position GPS positioning data of the available vehicles of a single vehicle are shared in the acquisition area, and the target days are continuously acquired aiming at the target area; in order to contain more periodic laws, a longer time sequence is constructed, and data are collected for at least two weeks;
2) acquiring geographic information data of traffic cells in a target area, wherein the geographic information data comprises cell boundaries, road network information, point of interest (POI) information and natural environment information, and establishing a geographic information database by taking respective traffic cells as objects;
3) matching the geographical position information of the shared bicycle to each traffic cell: loading coordinate point data of all the positions of the single vehicles into a geographic information database by utilizing ArcGIS software, establishing a mapping relation between coordinates and cells, dividing points falling in a certain closed area into the area, and adding traffic cell attributes to the coordinates, wherein the attributes comprise the serial number of the single vehicles, the acquisition time, the longitude of the vehicles, the latitude of the vehicles and the natural traffic cell of the vehicles;
4) establishing a total sample of the shared bicycle trip: traversing all records of a shared bicycle appearing in the acquisition time by taking the shared bicycle number as a traversal object and the acquisition time as a sequence, if the position information of the shared bicycle changes twice and the movement distance exceeds a specified threshold value, regarding the record as one trip generation, and recording the bicycle number, the start time, the start position longitude, the start position latitude, the start natural traffic cell, the end time, the end position longitude, the end position latitude and the end natural traffic cell; if the position information of the two previous times and the position information of the two previous times are not changed or the moving distance is smaller than a specified threshold value, checking the next record until the trip is generated, changing the starting point information until the full sequence check is finished, and stopping, thereby generating a total trip sample of the target area sharing bicycle; wherein the designated threshold value of the moving distance of the shared bicycle is 100 m;
5) establishing a space-time distribution thermodynamic diagram of the available vehicle distribution of the shared bicycle and a space thermodynamic diagram of the attraction occurrence times of each cell: importing data into geographic information software, performing thermodynamic diagram drawing on available vehicle quantity, travel production quantity and travel attraction quantity respectively from longitude and latitude coordinate magnitude and natural traffic cell magnitude on the basis of position coordinates of a target object by utilizing nuclear density analysis and color gradation visualization of the geographic information software, and obtaining the total space-time distribution rule of a shared bicycle in a target area;
6) taking a natural traffic cell as a counting object, taking the starting time as an index, taking 5 minutes, 10 minutes, 15 minutes, 20 minutes and 30 minutes as counting intervals respectively, counting trips, and constructing a time sequence of the attraction amount and the occurrence amount of each traffic cell;
7) calibrating parameters in the ARIMA model by using SPSS software, and adjusting the parameters to enable the sequence to meet the requirements of differential white noise inspection and parameter significance inspection:
φ(B)(1-B)dy(t)＝θ0+θ(B)ε(t)
wherein y (t) is the value of the predicted next time counting interval, y (t-i) is the value of the previous ith time counting interval, and epsilon (t-j) is the residual value (the difference between the predicted value and the true value) of the previous jth time counting interval;
8) and (3) predicting the shared single-vehicle traffic volume of each traffic cell in the next time set interval: p, d, q and theta determined by training the model0And theta (B) calculates the traffic volume in a certain natural traffic cell in the next time set interval.
Has the advantages that: the method of the invention predicts the short-time suction and delivery quantity of each area by analyzing the space distribution of the available vehicles and the hot spot areas of the travel suction and delivery quantity, and provides necessary information for scheduling, management and decision-making for government management departments and leasing enterprise operation departments. The invention has the following advantages:
1. the vehicle prediction precision is high. The invention analyzes the full sample, all weather and long period data of the single vehicle without piles in the target area, and digs the difference between working days and holidays of more shared single vehicles for travelling, the characteristics of each area and the tide change rule.
2. The prediction process of the invention is simple. In the invention, mass data are only needed to be matched with an actual natural traffic cell, statistics is carried out according to a required time set, and parameters p, d, q and theta of the ARIMA model are calibrated0θ (B), the prediction can be made. The method is simple and convenient to use, high in practicability and practical in engineering application value, and helps management departments and single-car rental companies to improve operation management levels.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is an example of a prediction region according to an embodiment of the present invention.
Fig. 3 is a color level diagram of the amount of hair-up in each traffic cell according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the attached drawings.
As shown in fig. 1, the method for predicting the short-time attraction amount and the occurrence amount of the shared bicycle comprises the following steps:
step 1) according to urban geographic characteristics, a predicted target area is defined, and GPS positioning data of static parking positions of available vehicles of a single vehicle are shared in the collection area. The collected vehicle information comprises the bicycle number, the acquisition time, the longitude and the latitude of the position of the vehicle, and sample data are as follows: { "025323514", "2017/06/2321: 37:34", "object": distX ":118.73578455079466," distY ":32.04531884191313} }. Continuously collecting target days in a target area, constructing a longer time sequence for more periodic rules, and collecting data of at least two weeks.
And 2) acquiring geographic information data of the traffic cells in the target area, wherein the geographic information data comprises cell boundaries, road network information, point of interest (POI) information and natural environment information, and establishing a geographic information database by taking respective traffic cells as objects and storing the geographic information database in a geographic information file format.
Step 3), matching the geographical position information of the shared bicycle into each traffic cell: and loading all position coordinate point data of the shared bicycle into a geographic information database by utilizing ArcGIS software, establishing a mapping relation between the bicycle coordinates and a traffic cell, marking points falling in a certain closed area into the area, and adding the attribute of the traffic cell to the coordinates, wherein the attribute comprises the bicycle number, the acquisition time, the longitude of the vehicle, the latitude of the vehicle and the natural traffic cell of the vehicle.
Step 4), establishing a total sample of the shared bicycle trip: traversing all records of a shared bicycle in an acquisition time period by taking the number of the shared bicycle as a traversal object and the acquisition time as a sequence, if position information of two times before and after changes and the movement distance exceeds a specified threshold value, taking the record as one trip generation, and recording the number of the shared bicycle, the starting time, the starting position longitude, the starting position latitude, the starting natural traffic cell, the ending time, the ending position longitude, the ending position latitude and the ending natural traffic cell; and if the position information of the two previous times and the position information of the two previous times are not changed or the moving distance is lower than a specified threshold value, checking the next record until the trip is generated, changing the starting point information until the full sequence check is finished, and stopping, thereby generating a total trip sample of the target area sharing bicycle. In the present invention, the specified threshold value of the shared bicycle moving distance is set to 100 m.
Step 5) establishing a space-time distribution thermodynamic diagram of the available vehicle distribution of the shared bicycle and a space thermodynamic diagram of the attraction occurrence times of each cell: and importing the data into geographic information software, performing thermodynamic diagram drawing on the available vehicle quantity, the travel production quantity and the travel attraction quantity respectively from the longitude and latitude coordinate magnitude and the natural traffic cell magnitude based on the position coordinate of the target object by utilizing the kernel density analysis and the color gradation visualization of the geographic information software, and reflecting the total space-time distribution rule of the shared bicycle in the target area.
Step 6) establishing a travel time sequence of each traffic cell: and counting the trips by taking the natural traffic cells as a counting object, the starting time as an index and the lengths of different counting intervals as constraints, and constructing a time sequence of the attraction amount and the occurrence amount of each traffic cell. In the present invention, the length of the collection interval includes several of 5 minutes, 10 minutes, 15 minutes, 20 minutes and 30 minutes, and the collection period is two weeks, and 4032, 2016, 1344, 1008 and 672 time-series quantities are obtained respectively.
Step 7) establishing an Autoregressive Integrated Moving Average Model (ARIMA) and calibrating parameters. In order to avoid overfitting, sequence data is divided into a training set and a verification set, wherein training set data accounts for 90% of the total sample volume, verification set data accounts for 10% of the total sample volume, parameters in an ARIMA model are calibrated by using SPSS software, and the parameters are adjusted to enable the sequence to meet the requirements of differential white noise detection and parameter significance detection:
φ(B)(1-B)dy(t)＝θ0+θ(B)ε(t) (2)
wherein formula (1) is an ARMA model, and formula (2) isARIMA model, formula calculation of phii、θjAnd adjusting the values of p, d and q according to the result to enable the values to meet the inspection requirement of the model index. y (t) is the value of the predicted next time aggregation interval, y (t-i) is the value of the previous ith time aggregation interval, and epsilon (t-j) is the residual value (difference between the predicted value and the true value) of the previous jth time aggregation interval.
Step 8) forecasting the shared single-vehicle running amount of each traffic cell in the next time set interval: and calculating the traffic volume in a certain natural traffic cell in the next time set interval according to the ARIMA model parameters determined by the training model and the traffic volume in the current time set interval. Necessary information of scheduling, management and decision is provided for government management departments and leasing enterprise operation departments, and the overall management level of the shared bicycle is improved.
As shown in fig. 2, the performance of the invention in the aspects of pile-free shared-bicycle data acquisition, matching, suction-delivery amount statistics and prediction is tested by taking Nanjing inner ring as a target area. The collected data comprises the bicycle number, the collection time, the longitude of the position of the vehicle and the latitude of the position of the vehicle.
Taking a ten-minute set counting interval sequence of a natural traffic cell of a new street as an example, the existing 2016 time series data are extracted from the whole sample, the first 90% of the data are taken as a training set, 1868 pieces of data are used for calibrating the model, the remaining 148 pieces of time series data are used for testing the prediction longitude of the prediction model, and the average absolute error, the mean square error and the average absolute percentage error are taken as evaluation indexes.
And utilizing the crawled mass shared bicycle position information data, carrying out brief analysis on the shared bicycle traveling space distribution according to the steps 1) -6) of the invention, establishing a shared bicycle traveling sample, and constructing a time sequence of the suction and delivery amount of each community shared bicycle. Fig. 3 shows a color gradation graph of the amount of hair sucked in each traffic cell.
Calibrating parameters of the model according to the step 7) to meet the requirements of differential white noise inspection and parameter significance inspection, wherein the parameter values are shown in the table 1:
TABLE 1 calibration of model parameters for the examples
The model is used for predicting time sequences under different time sets of the suction and delivery quantity of each traffic district, and the prediction precision under each set of intervals is shown in table 2:
TABLE 2 example model prediction accuracy
Note: MAE: mean absolute error, MAPE: mean absolute percentage error, MSE: mean square error
As can be seen from Table 2, the error between the suction volume and the occurrence volume is the smallest in the 15-minute time set interval, the effect is the best, the accuracy rates reach 34.61% and 44.01%, and the requirements and application scenes of practical application are met.
Claims (5)
1. A shared bicycle attraction amount and occurrence amount prediction method based on an ARIMA model is characterized by comprising the following steps:
1) the method comprises the steps of defining a predicted target area, acquiring position data of available shared bicycles in the area, and continuously acquiring target days aiming at the target area, wherein the position data of the shared bicycles comprise bicycle numbers, acquisition moments, longitudes where the vehicles are located and latitudes where the vehicles are located;
2) acquiring geographic information data of traffic cells in a target area, wherein the geographic information data comprises cell boundaries, road network information, interest point information and natural environment information, and establishing a geographic information database by taking respective traffic cells as objects;
3) matching the geographical position information of the shared bicycle into each traffic cell, and establishing a mapping relation between the bicycle position and the traffic cell;
4) according to the position change condition of the shared bicycle, a total travel sample of the shared bicycle is established, and the method specifically comprises the following steps: traversing all records of a shared bicycle appearing in the acquisition time by taking the shared bicycle number as a traversal object and the acquisition time as a sequence, if the position information of the shared bicycle changes twice and the movement distance exceeds a specified threshold value, regarding the record as one trip generation, and recording the bicycle number, the start time, the start position longitude, the start position latitude, the start natural traffic cell, the end time, the end position longitude, the end position latitude and the end natural traffic cell; if the position information of the two previous times and the position information of the two previous times are not changed or the moving distance is smaller than a specified threshold value, checking the next record until the trip is generated, changing the starting point information until the full sequence check is finished, and stopping, thereby generating a total trip sample of the target area sharing bicycle;
5) establishing a sharing bicycle available vehicle distribution space-time distribution thermodynamic diagram and each cell attraction occurrence frequency space thermodynamic diagram to obtain a sharing bicycle overall space-time distribution rule in a target area;
6) counting the trips by taking the natural traffic cells as a counting object and taking the lengths of different counting intervals as constraints, and constructing a time sequence of the attraction amount and the occurrence amount of each traffic cell;
7) establishing an ARIMA model, adjusting parameters to enable the sequence to meet the requirements of differential white noise inspection and parameter significance inspection, and obtaining the ARIMA model after parameter calibration, wherein the ARIMA model has the following calculation formula:
where y (t) is the value of the predicted next time counting interval, and y (t-i) is the first previous timeiThe value of the interval is counted for each time set,
is the firstjThe residual value of the interval is counted for each time set,
is a model parameter;
8) and predicting the shared bicycle running amount of each traffic cell in the next time set interval.
2. The ARIMA model-based shared bicycle attraction and occurrence prediction method according to claim 1, characterized in that at least two weeks of data are continuously acquired in step 1) for the target area.
3. The ARIMA model-based shared bicycle attraction and occurrence prediction method according to claim 1, wherein the moving distance of the shared bicycle is specified as a threshold of 100 m.
4. The ARIMA model-based shared bicycle attraction and occurrence prediction method according to claim 1, wherein the aggregation interval length of step 6) comprises 5 minutes, 10 minutes, 15 minutes, 20 minutes and 30 minutes.
5. The ARIMA model-based shared bicycle attraction and occurrence prediction method of claim 1, further comprising dividing the sequence data into training sets as validation sets, wherein the training set data accounts for 90% of the total sample size and the validation set data accounts for 10% of the total sample size.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710952071.5A CN107767659B (en) | 2017-10-13 | 2017-10-13 | Shared bicycle attraction amount and occurrence amount prediction method based on ARIMA model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710952071.5A CN107767659B (en) | 2017-10-13 | 2017-10-13 | Shared bicycle attraction amount and occurrence amount prediction method based on ARIMA model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107767659A CN107767659A (en) | 2018-03-06 |
| CN107767659B true CN107767659B (en) | 2021-01-26 |
Family
ID=61269317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710952071.5A Active CN107767659B (en) | 2017-10-13 | 2017-10-13 | Shared bicycle attraction amount and occurrence amount prediction method based on ARIMA model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107767659B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108536652A (en) * | 2018-03-15 | 2018-09-14 | 浙江大学 | A kind of short-term vehicle usage amount prediction technique based on arma modeling |
| CN108805385A (en) * | 2018-04-02 | 2018-11-13 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and equipment of the management state of evaluation trade company |
| CN108346010B (en) * | 2018-04-23 | 2021-07-13 | 徐漫洋 | Shared automobile scheduling method based on user demand analysis |
| CN108399736B (en) * | 2018-04-27 | 2020-08-28 | 东南大学 | Service time-based method for acquiring number of effective bicycles shared by regions |
| CN108876458A (en) * | 2018-06-19 | 2018-11-23 | 湖北国网华中科技开发有限责任公司 | A kind of commodity dynamic prediction method and system based on web crawlers |
| CN108876056A (en) * | 2018-07-20 | 2018-11-23 | 广东工业大学 | A kind of shared bicycle Demand Forecast method, apparatus, equipment and storage medium |
| CN109345132B (en) * | 2018-10-16 | 2021-11-26 | 上海市城市建设设计研究总院（集团）有限公司 | Shared bicycle dynamic limit management system and operation method thereof |
| CN109583491A (en) * | 2018-11-23 | 2019-04-05 | 温州职业技术学院 | A kind of shared bicycle intelligent dispatching method |
| CN109543922B (en) * | 2018-12-20 | 2021-04-20 | 西安电子科技大学 | Time-period borrowing and returning amount prediction method for single-vehicle station group shared by piles |
| CN110059986B (en) * | 2019-05-08 | 2021-02-19 | 武汉大学 | Dynamic releasing method and system for shared bicycle |
| CN111145537B (en) * | 2019-12-02 | 2021-06-15 | 东南大学 | Travel generation amount prediction method and system |
| CN111126678B (en) * | 2019-12-09 | 2023-03-31 | 深圳市市政设计研究院有限公司 | Traffic generation prediction method based on big data |
| CN111428154B (en) * | 2020-02-29 | 2021-10-26 | 浙江工业大学 | Multi-view visual interactive analysis method for GPS data of single vehicle based on quadtree partition optimization |
| CN111581318B (en) * | 2020-05-08 | 2023-04-07 | 广州大学 | Shared bicycle riding purpose inference method and device and storage medium |
| CN111598481B (en) * | 2020-05-26 | 2023-09-01 | 山东交通学院 | Shared bicycle flow system, automatic scheduling system and method based on subarea division |
| CN111882171A (en) * | 2020-07-06 | 2020-11-03 | 湖北合纵科创能源科技有限公司 | Intelligent scheduling system and method for scenic spot sightseeing vehicle based on demand prediction |
| CN112329986A (en) * | 2020-10-13 | 2021-02-05 | 厦门市交通研究中心 | Parking management method, device and equipment for shared bicycle |
| CN112533140B (en) * | 2020-11-24 | 2021-10-12 | 天津市赛英工程建设咨询管理有限公司 | Shared bicycle distribution condition evaluation method based on index |
| CN112785371A (en) * | 2021-01-11 | 2021-05-11 | 上海钧正网络科技有限公司 | Shared device position prediction method, device and storage medium |
| CN113487910B (en) * | 2021-06-10 | 2022-12-09 | 中国汽车技术研究中心有限公司 | Performance analysis method for automobile data acquisition system used in automobile following scene |
| CN113313317B (en) * | 2021-06-11 | 2024-04-12 | 哈尔滨工业大学 | INLA algorithm-based shared bicycle use demand prediction method and prediction system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130007502A (en) * | 2012-11-23 | 2013-01-18 | 주식회사 위트콤 | Distribution management system for bicycles |
| CN103116702A (en) * | 2013-02-01 | 2013-05-22 | 东南大学 | Bicycle-mode traveling selection forecasting method based on activity chain mode |
| CN106816035A (en) * | 2015-12-02 | 2017-06-09 | 中国移动通信集团公司 | A kind of alarm method and device towards pedestrian |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101436345B (en) * | 2008-12-19 | 2010-08-18 | 天津市市政工程设计研究院 | System for forecasting harbor district road traffic requirement based on TransCAD macroscopic artificial platform |
| CN101692309B (en) * | 2009-09-04 | 2011-04-27 | 北京工业大学 | Traffic trip computing method based on mobile phone information |
| CN102595323B (en) * | 2012-03-20 | 2014-05-07 | 北京交通发展研究中心 | Method for obtaining resident travel characteristic parameter based on mobile phone positioning data |
| CN105185116B (en) * | 2015-09-15 | 2017-08-11 | 广州地理研究所 | The intensive minibus trip requirements thermodynamic chart construction method of network |
| US11087291B2 (en) * | 2015-11-24 | 2021-08-10 | Honda Motor Co., Ltd.. | Action planning and execution support device |
| CN105513351A (en) * | 2015-12-17 | 2016-04-20 | 北京亚信蓝涛科技有限公司 | Traffic travel characteristic data extraction method based on big data |
| CN105489056B (en) * | 2015-12-28 | 2018-01-26 | 中兴软创科技股份有限公司 | A kind of parking facilities' forecasting method based on OD matrixes |
| CN106251628B (en) * | 2016-09-14 | 2019-06-14 | 青岛海信网络科技股份有限公司 | A kind of method and device of the traffic trip amount of determining motor vehicle |
-
2017
- 2017-10-13 CN CN201710952071.5A patent/CN107767659B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130007502A (en) * | 2012-11-23 | 2013-01-18 | 주식회사 위트콤 | Distribution management system for bicycles |
| CN103116702A (en) * | 2013-02-01 | 2013-05-22 | 东南大学 | Bicycle-mode traveling selection forecasting method based on activity chain mode |
| CN106816035A (en) * | 2015-12-02 | 2017-06-09 | 中国移动通信集团公司 | A kind of alarm method and device towards pedestrian |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107767659A (en) | 2018-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107767659B (en) | Shared bicycle attraction amount and occurrence amount prediction method based on ARIMA model | |
| Zheng et al. | High-resolution mapping of vehicle emissions in China in 2008 | |
| CN110298500B (en) | Urban traffic track data set generation method based on taxi data and urban road network | |
| Shahidinejad et al. | Statistical development of a duty cycle for plug-in vehicles in a North American urban setting using fleet information | |
| Bandeira et al. | Impact of land use on urban mobility patterns, emissions and air quality in a Portuguese medium-sized city | |
| CN102607553B (en) | Travel track data-based stroke identification method | |
| CN101794507B (en) | Method for evaluating macroscopic road network traffic state based on floating car data | |
| Wen et al. | A data-driven method of traffic emissions mapping with land use random forest models | |
| CN111696369B (en) | All-market road time-sharing and vehicle-division type traffic flow prediction method based on multi-source geographic space big data | |
| CN111612670B (en) | Method, device and computer equipment for constructing emission list of motor vehicle | |
| Samaranayake et al. | Real‐time estimation of pollution emissions and dispersion from highway traffic | |
| Paffumi et al. | European-wide study on big data for supporting road transport policy | |
| CN108877227A (en) | A kind of global dynamic trip requirements estimation method based on multi-source traffic data | |
| Nocera et al. | Micro and Macro modelling approaches for the evaluation of the carbon impacts of transportation | |
| CN113806419A (en) | Urban area function identification model and method based on space-time big data | |
| Ayman et al. | Data-driven prediction and optimization of energy use for transit fleets of electric and ICE vehicles | |
| CN114501336B (en) | Road traffic volume measuring and calculating method and device, electronic equipment and storage medium | |
| Miller et al. | Scaling GPS trajectories to match point traffic counts: A convex programming approach and Utah case study | |
| Fitzmaurice et al. | Assessing vehicle fuel efficiency using a dense network of CO 2 observations | |
| Steenberghen et al. | Support study on data collection and analysis of active modes use and infrastructure in Europe | |
| CN109447352A (en) | A kind of anti-combined method pushed away of bus trip OD matrix | |
| Zheng et al. | A new vehicle emission inventory for China with high spatial and temporal resolution. | |
| Afshar et al. | A GIS-based air pollution modeling in Tehran | |
| CN110021164A (en) | Net based on travel time data about bus or train route net occupation rate analysis method | |
| Paffumi et al. | Big data for assessing travel behaviour in Europe: Initiating a continental scale pilot for supporting the next generation of policy makers |
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 |