CN114239929A - Taxi traffic demand characteristic prediction method based on random forest - Google Patents
Taxi traffic demand characteristic prediction method based on random forest Download PDFInfo
- Publication number
- CN114239929A CN114239929A CN202111442665.4A CN202111442665A CN114239929A CN 114239929 A CN114239929 A CN 114239929A CN 202111442665 A CN202111442665 A CN 202111442665A CN 114239929 A CN114239929 A CN 114239929A
- Authority
- CN
- China
- Prior art keywords
- taxi
- grid
- traffic
- passenger carrying
- random forest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000011160 research Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 13
- 238000003066 decision tree Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000010200 validation analysis Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000000926 separation method Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 description 9
- 230000001419 dependent effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Traffic Control Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a taxi traffic demand characteristic prediction method based on random forests, which comprises the following steps of: firstly, collecting historical taxi order data, interest point data and city street administrative district division data in a research area; then extracting the origin-destination points of all taxi trips, and carrying out grid division on the research area; carrying out space matching on the basic data and the grids, extracting grid space-time characteristics and constructing a sample set; and (4) constructing a random forest regression model and predicting taxi demand characteristics. The method has higher popularization value, can accurately describe and predict the change condition of taxi demand characteristics along with the regional space-time characteristics, and provides reference for urban traffic management and control.
Description
Technical Field
The invention belongs to the technical field of data-driven urban traffic demand analysis, and particularly relates to a taxi traffic demand characteristic prediction method based on random forests.
Background
The taxi is one of important transportation modes for urban residents to go out, the demand of the taxi is unbalanced in time and space, and therefore the traffic demand characteristics of the urban residents can be reflected practically. The development and application of technologies such as vehicle-mounted GPS equipment, electronic map interest point extraction, space map matching and the like lay a foundation for extraction and analysis of taxi order track information, urban land utilization types, land utilization strength and the like.
At present, many scholars at home and abroad pay attention to application of taxi GPS data and research on predicting taxi requirements based on multivariate historical data is not lacked, but most of the prior research places attention on how to improve the prediction precision of traffic occurrence and traffic attraction, and no literature focuses on researching the relation between the overall demand characteristics of an area formed by the difference between the overall traffic demand and the traffic requirements and urban land utilization, development intensity and time sequence, and the traffic demand characteristics can embody comprehensive traffic demand hotspots and demand gaps, so that the method plays an important role in guiding urban traffic management and control and taxi running paths.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems, the invention provides a taxi traffic demand characteristic prediction method based on a random forest.
The technical scheme is as follows: in order to realize the purpose of the invention, the technical scheme adopted by the invention is as follows: a taxi traffic demand characteristic prediction method based on random forests specifically comprises the following steps:
step 1, obtaining taxi order data, city interest point data and city street division data in a research city;
step 2, obtaining the position data of the origin-destination point of each passenger carrying journey of the taxi according to the taxi order data in the step 1;
step 3, carrying out equidistant grid division on the research city;
step 4, respectively carrying out space matching on the urban interest point data and the urban street division data in the step 1 and the origin-destination point data of each passenger carrying travel of the taxi in the step 2 with the grids obtained by division in the step 3, extracting the space-time characteristic of each grid, and calculating the demand characteristic according to the space-time characteristic of each grid; the space-time characteristics comprise urban interest point characteristics, urban street division characteristics and taxi demand characteristics, and the demand characteristics comprise overall traffic demands and traffic demand differences;
step 5, dividing the space-time characteristics and the demand characteristics of each grid in the step 4 into a training set, a verification set and a test set according to a certain proportion;
step 6, constructing a random forest regression model, taking the space-time characteristics as input and the demand characteristics as output, and training the random forest regression model by using the training set in the step 5 to obtain a trained random forest regression model; predicting the random forest regression model by using the verification set in the step 5 to obtain a predicted value corresponding to the verification set, calculating a decision coefficient of a fitting effect of the reaction model according to the predicted value and the actual value corresponding to the verification set, and verifying the trained random forest regression model;
and 7, predicting the trained random forest regression model in the step 6 by using the test set in the step 5 to obtain a prediction result.
Further, the taxi order data, the city interest point data and the city street division data in the step 1 adopt the same projection coordinate system.
Further, the taxi order data in the step 1 comprises a vehicle number, a vehicle position and a passenger carrying state;
the city interest point data comprises city interest point types and city interest point positions, and the interest point types comprise 6 types, specifically catering services, business residences, shopping services, company enterprises, sports and leisure services and traffic facility services;
the city street division data includes administrative street boundary information.
Further, the step 1 of obtaining taxi order data in a research city includes:
periodically acquiring vehicle numbers at certain time intervals, and vehicle positions and passenger carrying states of the same vehicle number at continuous time intervals; the corresponding passenger carrying state is 1 when the taxi carries passengers, and the corresponding passenger carrying state is 0 when the taxi does not carry passengers.
Further, the method of step 2 specifically comprises the following steps:
step 2.1, taking the order data of which the passenger carrying states of the same vehicle number are 1 at continuous time intervals as a passenger carrying journey by using the taxi order data in the step 1, and extracting all the passenger carrying journeys;
step 2.2, calculating travel time for all the passenger carrying trips extracted in the step 2.1, sequencing the passenger carrying trips according to the travel time from small to large, and obtaining a lower quartile Q1 and an upper quartile Q3 of the sequenced passenger carrying trips and a quartile distance IQR (equal to Q3-Q1) by using a box type diagram quartile distance method; removing passenger carrying trips with the trip time being more than Q3+1.5IQR and less than Q1-1.5IQR to obtain the passenger carrying trips meeting the requirements;
and 2.3, extracting the origin-destination position data of each passenger carrying journey which meets the requirements.
Further, the method of step 4 specifically comprises the following steps:
step 4.1, extracting the number of the types of the interest points of each city in each grid according to the grids obtained by dividing in the step 3;
step 4.2, judging the relation between each grid and the administrative street boundary, including an inclusion relation, an intersection relation and a separation relation; when a certain grid only comprises a single street boundary, the street corresponding to the street boundary is the street to which the grid belongs; when a certain grid spans a plurality of street boundaries, selecting a street occupying the largest area of the grid as a street to which the grid belongs;
4.3, counting the number of the starting points of the passenger carrying trips in each grid per hour by taking the hour as a unit according to the starting point and destination point position data of each passenger carrying trip extracted in the step 2, namely obtaining the traffic occurrence of each grid in different time periods; counting the number of the destination points of the passenger carrying journey in each grid per hour, namely obtaining the traffic attraction of each grid in different time periods;
4.4, calculating the demand characteristics of each grid in different time periods according to the traffic occurrence amount and the traffic attraction amount of each grid in different time periods;
the calculation formula of the total traffic demand is as follows: the total traffic demand is traffic occurrence and traffic attraction;
the calculation formula of the traffic demand difference is as follows: traffic demand difference is traffic attraction-traffic occurrence.
Further, in the step 6, the mean square error is used as a branch quality standard of a single decision tree in the training process; when the mean square error is smaller than a set threshold, finishing the training of a single decision tree; and when all the decision trees are trained, finishing the construction of the random forest regression model.
Further, the parameters in the random forest regression model established in the step 6 have the following values:
using the mean square error as a branch quality standard of a single decision tree; the maximum depth value of a single decision tree is not limited; the number of decision tree based learners in the random forest is 100.
Further, the decision coefficient of the fitting effect of the reaction model in step 6 is calculated by the following formula:
in the formula, R2Representing the decision coefficient of the fitting effect of the reaction model, SSR representing the regression sum of squares, SST representing the sum of the squares of the total deviations,
a predictor representing an ith validation set sample; y isiRepresenting the actual value of the ith validation set sample,
represents the average of the actual values of all validation set samples.
Has the advantages that: compared with the prior art, the technical scheme of the invention has the following obvious advantages:
the concept of demand characteristics is introduced, and the activity of the region and the taxi demand gap can be reflected from a more comprehensive and visual angle; meanwhile, the invention explains the relation between the demand characteristics in different time periods and the urban land utilization and development strength by establishing a random forest regression model, realizes the prediction of the demand characteristics on the basis of the relation, and provides reference information for urban traffic management and control.
Drawings
FIG. 1 is a flow chart of a taxi demand characteristic prediction method based on random forest according to an embodiment of the invention;
FIG. 2 shows the results of an example of a grid partitioning study of a city.
Detailed Description
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
The invention relates to a taxi traffic demand characteristic prediction method based on random forest, which takes a metropolis as an example and refers to a figure 1, and concretely comprises the following steps:
(1) data acquisition: taxi order data of eight working days of 8 months in 2014, city interest point data and street division data are collected. The taxi order data comprises four fields of a vehicle number, a position, a passenger carrying state and time; the interest point data comprises interest point types and interest point positions, wherein the interest point types are divided into 6 categories: catering, business housing, shopping, corporate enterprises, sports leisure services, traffic facility services; the metropolis street division data was subject to 2014.
(2) Taxi origin-destination extraction: the method comprises three steps of passenger carrying travel extraction, abnormal travel screening and origin-destination position extraction. Regarding a running track set with the same vehicle-mounted passenger state being 1 continuously as a passenger carrying travel, and extracting all passenger carrying travels; screening abnormal travel time by using box type diagram four-bit distance (IQR) and reserving effective travel; extracting the time period and the origin-destination position of each effective stroke, as shown in table 1 and table 2:
TABLE 1 taxi passenger-carrying journey starting point number
| Time | Position of |
| 6 | (104.05736，30.69315) |
| 6 | (104.12486，30.60523) |
| 7 | (104.12390，30.67212) |
| …… | …… |
| 23 | (104.03951，30.64321) |
| 23 | (104.06420，30.63841) |
TABLE 2 taxi passenger-carrying journey destination point data
(3) Grid division: the study area is divided equally by a grid with the side length of 550 meters with the central part area of the metropolis as the main study range, and a 20 × 20 grid is obtained, which is shown in fig. 2.
(4) Grid feature extraction: the method comprises three steps of urban interest point feature extraction, urban street division feature extraction and taxi demand feature extraction. And extracting the number of interest points of each category in each grid. And extracting the street to which each grid belongs by judging the inclusion or intersection relationship between the grid and the administrative area boundary, and taking the street occupying the largest area of the grid as the street to which the grid belongs when the grid spans a plurality of streets. Accumulating the number of starting points in each grid according to hours, and corresponding to the traffic occurrence of the grids in different time periods; accumulating the number of the destination points in each grid according to hours, and corresponding to the traffic attraction of the grids in different time periods; calculating the requirement characteristics: overall traffic demand, traffic demand difference.
(5) Constructing a sample set: the method comprises two steps of extracting a total sample set, and dividing a training set and a test set. Constructing a total sample set containing 65600 samples by using the grid space-time characteristics extracted in the step (4), wherein the number of interest points of each category, the street to which the interest points belong and the time period are used as independent variables, and the difference between the total traffic demand and the traffic demand is used as a dependent variable, as shown in a table 3; and (3) adding the following components in percentage by weight of 7: a ratio of 3 randomly divides the total sample set into a training set and a test set.
TABLE 3 Overall sample set
(6) Constructing a model: constructing a random forest regression model, and respectively modeling dependent variable overall traffic demand and traffic demand difference by using the training set extracted in the step (5), wherein the parameter values of the model are as follows: the number of base learner decision trees is 100.
(7) Forecasting the demand characteristics: and (4) predicting the test set extracted in the step (5) by using the random forest regression model established in the step (6), wherein the decision coefficients of the overall traffic demand and the traffic demand difference are 0.95 and 0.81 respectively, and the random forest regression model established by the method can be used for better explaining the whole variation of the dependent variable by the independent variable.
Claims (8)
1. A taxi traffic demand characteristic prediction method based on random forests is characterized by comprising the following steps:
step 1, obtaining taxi order data, city interest point data and city street division data in a research city;
step 2, obtaining the position data of the origin-destination point of each passenger carrying journey of the taxi according to the taxi order data in the step 1;
step 3, carrying out equidistant grid division on the research city;
step 4, respectively carrying out space matching on the urban interest point data and the urban street division data in the step 1 and the origin-destination point data of each passenger carrying travel of the taxi in the step 2 with the grids obtained by division in the step 3, extracting the space-time characteristic of each grid, and calculating the demand characteristic according to the space-time characteristic of each grid; the space-time characteristics comprise urban interest point characteristics, urban street division characteristics and taxi demand characteristics, and the demand characteristics comprise overall traffic demands and traffic demand differences;
step 5, dividing the space-time characteristics and the demand characteristics of each grid in the step 4 into a training set, a verification set and a test set according to a certain proportion;
step 6, constructing a random forest regression model, taking the space-time characteristics as input and the demand characteristics as output, and training the random forest regression model by using the training set in the step 5 to obtain a trained random forest regression model; predicting the random forest regression model by using the verification set in the step 5 to obtain a predicted value corresponding to the verification set, calculating a decision coefficient of a fitting effect of the reaction model according to the predicted value and the actual value corresponding to the verification set, and verifying the trained random forest regression model;
and 7, predicting the trained random forest regression model in the step 6 by using the test set in the step 5 to obtain a prediction result.
2. The method for predicting taxi traffic demand characteristics based on the random forest as claimed in claim 1, wherein the taxi order data, the city interest point data and the city street division data in the step 1 adopt the same projection coordinate system.
3. The method for predicting taxi traffic demand characteristics based on the random forest as claimed in claim 1, wherein the taxi order data in the step 1 comprises a vehicle number, a vehicle position and a passenger carrying state;
the city interest point data comprises city interest point types and city interest point positions, and the interest point types comprise 6 types, specifically catering services, business residences, shopping services, company enterprises, sports and leisure services and traffic facility services;
the city street division data includes administrative street boundary information.
4. The method for predicting taxi traffic demand characteristics based on the random forest as claimed in claim 3, wherein the step 1 of obtaining and researching taxi order data in the city comprises the following specific steps:
periodically acquiring vehicle numbers at certain time intervals, and vehicle positions and passenger carrying states of the same vehicle number at continuous time intervals; the corresponding passenger carrying state is 1 when the taxi carries passengers, and the corresponding passenger carrying state is 0 when the taxi does not carry passengers.
5. The method for predicting taxi traffic demand characteristics based on the random forest as claimed in claim 4, wherein the method in the step 2 is specifically as follows:
step 2.1, taking the order data of which the passenger carrying states of the same vehicle number are 1 at continuous time intervals as a passenger carrying journey by using the taxi order data in the step 1, and extracting all the passenger carrying journeys;
step 2.2, calculating travel time for all the passenger carrying trips extracted in the step 2.1, sequencing the passenger carrying trips according to the travel time from small to large, and obtaining a lower quartile Q1 and an upper quartile Q3 of the sequenced passenger carrying trips and a quartile distance IQR (equal to Q3-Q1) by using a box type diagram quartile distance method; removing passenger carrying trips with the trip time being more than Q3+1.5IQR and less than Q1-1.5IQR to obtain the passenger carrying trips meeting the requirements;
and 2.3, extracting the origin-destination position data of each passenger carrying journey which meets the requirements.
6. The method for predicting taxi traffic demand characteristics based on the random forest as claimed in claim 3, wherein the method in the step 4 is specifically as follows:
step 4.1, extracting the number of the types of the interest points of each city in each grid according to the grids obtained by dividing in the step 3;
step 4.2, judging the relation between each grid and the administrative street boundary, including an inclusion relation, an intersection relation and a separation relation; when a certain grid only comprises a single street boundary, the street corresponding to the street boundary is the street to which the grid belongs; when a certain grid spans a plurality of street boundaries, selecting a street occupying the largest area of the grid as a street to which the grid belongs;
4.3, counting the number of the starting points of the passenger carrying trips in each grid per hour by taking the hour as a unit according to the starting point and destination point position data of each passenger carrying trip extracted in the step 2, namely obtaining the traffic occurrence of each grid in different time periods; counting the number of the destination points of the passenger carrying journey in each grid per hour, namely obtaining the traffic attraction of each grid in different time periods;
4.4, calculating the demand characteristics of each grid in different time periods according to the traffic occurrence amount and the traffic attraction amount of each grid in different time periods;
the calculation formula of the total traffic demand is as follows: the total traffic demand is traffic occurrence and traffic attraction;
the calculation formula of the traffic demand difference is as follows: traffic demand difference is traffic attraction-traffic occurrence.
7. The method for predicting taxi traffic demand characteristics based on the random forest as claimed in claim 1, wherein in the step 6, a mean square error is used as a single decision tree branch quality standard in a training process; when the mean square error is smaller than a set threshold, finishing the training of a single decision tree; and when all the decision trees are trained, finishing the construction of the random forest regression model.
8. The method for predicting taxi traffic demand characteristics based on random forests as claimed in claim 1, wherein the decision coefficient of the fitting effect of the reaction model in step 6 is calculated by the formula:
in the formula, R2Representing the decision coefficient of the fitting effect of the reaction model, SSR representing the regression sum of squares, SST representing the sum of the squares of the total deviations,
a predictor representing an ith validation set sample; y isiRepresenting the actual value of the ith validation set sample,
represents the average of the actual values of all validation set samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442665.4A CN114239929A (en) | 2021-11-30 | 2021-11-30 | Taxi traffic demand characteristic prediction method based on random forest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442665.4A CN114239929A (en) | 2021-11-30 | 2021-11-30 | Taxi traffic demand characteristic prediction method based on random forest |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114239929A true CN114239929A (en) | 2022-03-25 |
Family
ID=80752144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111442665.4A Pending CN114239929A (en) | 2021-11-30 | 2021-11-30 | Taxi traffic demand characteristic prediction method based on random forest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114239929A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115472008A (en) * | 2022-08-30 | 2022-12-13 | 东南大学 | Network appointment travel time-space characteristic analysis method based on k-means clustering |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201711408D0 (en) * | 2016-12-30 | 2017-08-30 | Maxu Tech Inc | Early entry |
| WO2018214675A1 (en) * | 2017-05-24 | 2018-11-29 | 大连理工大学 | Quantified analysis method of influence on road travel time from urban built-up environment |
| CN111507762A (en) * | 2020-04-15 | 2020-08-07 | 中国科学院自动化研究所 | Urban taxi demand prediction method based on multi-task co-prediction neural network |
| CN112949939A (en) * | 2021-03-30 | 2021-06-11 | 福州市电子信息集团有限公司 | Taxi passenger carrying hotspot prediction method based on random forest model |
-
2021
- 2021-11-30 CN CN202111442665.4A patent/CN114239929A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201711408D0 (en) * | 2016-12-30 | 2017-08-30 | Maxu Tech Inc | Early entry |
| WO2018214675A1 (en) * | 2017-05-24 | 2018-11-29 | 大连理工大学 | Quantified analysis method of influence on road travel time from urban built-up environment |
| CN111507762A (en) * | 2020-04-15 | 2020-08-07 | 中国科学院自动化研究所 | Urban taxi demand prediction method based on multi-task co-prediction neural network |
| CN112949939A (en) * | 2021-03-30 | 2021-06-11 | 福州市电子信息集团有限公司 | Taxi passenger carrying hotspot prediction method based on random forest model |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115472008A (en) * | 2022-08-30 | 2022-12-13 | 东南大学 | Network appointment travel time-space characteristic analysis method based on k-means clustering |
| CN115472008B (en) * | 2022-08-30 | 2023-09-19 | 东南大学 | Network vehicle travel space-time characteristic analysis method based on k-means clustering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102044149B (en) | City bus operation coordinating method and device based on time variant passenger flows | |
| CN110288212B (en) | Improved MOPSO-based electric taxi newly-built charging station site selection method | |
| CN109492950B (en) | Prediction method capable of meeting space saturation load of large area range based on GIS technology | |
| CN113902011A (en) | Urban rail transit short-time passenger flow prediction method based on cyclic neural network | |
| CN109978224B (en) | Method for analyzing and acquiring traffic trip rates of buildings with different properties | |
| CN107563540A (en) | A kind of public transport in short-term based on random forest is got on the bus the Forecasting Methodology of the volume of the flow of passengers | |
| CN105809962A (en) | Traffic trip mode splitting method based on mobile phone data | |
| CN110836675B (en) | Decision tree-based automatic driving search decision method | |
| CN111696369A (en) | Whole-city road time-division vehicle type traffic flow prediction method based on multi-source geographic space big data | |
| CN106327867B (en) | Bus punctuation prediction method based on GPS data | |
| CN113222271B (en) | Medium and small airport site selection layout method under comprehensive transportation system | |
| CN114139251B (en) | Integral layout method for land ports of border regions | |
| CN109840272B (en) | Method for predicting user demand of shared electric automobile station | |
| CN114819305B (en) | Path planning method based on carbon emission measurement scale | |
| CN109460937B (en) | Process and method for evaluating connection level of slow traffic system around track station | |
| Nam et al. | Analysis of grid cell–based taxi ridership with large-scale GPS data | |
| CN111612223B (en) | Population employment distribution prediction method and device based on land and traffic multisource data | |
| CN114239929A (en) | Taxi traffic demand characteristic prediction method based on random forest | |
| CN106980942A (en) | Calculate method of the bicycle free way to the coverage of public bicycles lease point | |
| CN116415756B (en) | Urban virtual scene experience management system based on VR technology | |
| CN113435777A (en) | Planning method and system for electric operating vehicle charging station | |
| CN113449780B (en) | Intra-road berth occupancy prediction method based on random forest and LSTM neural network | |
| CN111785024B (en) | Urban vehicle working condition construction method based on regions and time domains | |
| CN115345351A (en) | Electric vehicle charging load prediction method based on user behaviors | |
| CN114742131A (en) | Method for identifying urban excessive tourism area based on pattern mining |
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 |