CN113869550A - Taxi scheduling method based on grid division and graph analysis - Google Patents

Taxi scheduling method based on grid division and graph analysis Download PDF

Info

Publication number
CN113869550A
CN113869550A CN202110957469.4A CN202110957469A CN113869550A CN 113869550 A CN113869550 A CN 113869550A CN 202110957469 A CN202110957469 A CN 202110957469A CN 113869550 A CN113869550 A CN 113869550A
Authority
CN
China
Prior art keywords
grid
vehicles
scheduling
graph analysis
dispatched
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
Application number
CN202110957469.4A
Other languages
Chinese (zh)
Inventor
李烨星
韩梦飞
郭建国
肖萌萌
孙浩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhengzhou Tiamaes Technology Co ltd
Original Assignee
Zhengzhou Tiamaes Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhengzhou Tiamaes Technology Co ltd filed Critical Zhengzhou Tiamaes Technology Co ltd
Priority to CN202110957469.4A priority Critical patent/CN113869550A/en
Publication of CN113869550A publication Critical patent/CN113869550A/en
Pending legal-status Critical Current

Links

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
    • G06F16/29—Geographical information databases
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • 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
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/02—Resource partitioning among network components, e.g. reuse partitioning
    • H04W16/12—Fixed resource partitioning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Databases & Information Systems (AREA)
  • Operations Research (AREA)
  • Remote Sensing (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention belongs to the technical field of traffic, and particularly relates to a taxi scheduling method based on grid division and graph analysis. The method comprises the steps of dividing a road network area, calculating and analyzing the order quantity and the empty number of each grid at each moment, calculating the passing time among the grids by adopting a KSP algorithm, selecting the average value of the passing time of the first 3 shortest paths as the path time, calculating the balance of each grid by using a balance coefficient, distributing and scheduling vehicles among the grids according to supply and demand requirements, finishing vehicle scheduling while ensuring the relative balance of orders and the number of the vehicles of each grid, and simplifying the calculation complexity.

Description

Taxi scheduling method based on grid division and graph analysis
Technical Field
The invention belongs to the technical field of traffic, and particularly relates to a taxi scheduling method based on grid division and graph analysis.
Background
Smart cities are an emerging technology, aiming at applying a new generation of information and communication technology to various industries in cities, coordinating city development and improving urban efficiency and quality of life of citizens in operation conditions. The intelligent transportation is the indispensable part in intelligent city, aims at improving traffic system's operation efficiency, make full use of traffic resources, ensures traffic safety. The intelligent traffic system plays a vital role in the life of citizens and the operation of the whole city, and nowadays, traffic jam, frequently occurring accidents, energy waste, air pollution and other ubiquitous problems of the city can be well solved through intelligent traffic.
With the rapid development of wireless communication technology and the internet of things (IoT), it becomes simple and fast to collect trajectory records of moving objects, which makes intelligent transportation possible. Various devices embedded with GPS are ubiquitous in our lives, such as smart phones, private cars and public transportation. Location information is more readily available and a large amount of trajectory data is collected daily. The trajectory data has spatial and temporal attributes; it becomes the main research object of the spatio-temporal data mining technology. The application of trajectory data can not only provide location-based services to users, but also assist in city planning and intelligent transportation. Collecting and analyzing these large-scale real-world digital traces provides us with an unprecedented opportunity to master city dynamics and better understand social and economic patterns.
However, as the number of taxis increases, corresponding operation strategies are not developed, and there still exist many disadvantages, such as difficulty in finding taxis during peak hours, uneven distribution of taxis, and taxi driver refusal service strategies.
Many studies have been made to solve these problems from the driver's point of view, but basically, these local optimization methods may cause shortages in some fields. Therefore, it can not provide guidance for taxi dispatching from a global perspective, nor can it provide better riding experience for passengers.
Disclosure of Invention
Aiming at the defects and problems existing at present, the invention provides a taxi scheduling method based on grid division and graph analysis. The method can calculate the number of vehicles which can be currently served and predict the future demand, and can achieve the balance between scheduling and scheduled.
The technical scheme adopted by the invention for solving the technical problems is as follows: a taxi dispatching method based on grid division and graph analysis is characterized in that: the method comprises the following steps:
step one, selecting a road network region, determining the shape and size of a grid, and dividing the road network region into N grids;
step two, dispersing 1 day into 24 time steps, and calculating the order quantity D of the grid i (i is 1,2, … p, q … N) in the t (t is 1,2, …, 24) periodiAnd the number S of empty vehiclesiJudging whether the vehicles in the grid i need to be called in or out according to the order quantity and the empty vehicle quantity, and simultaneously predicting the order quantity D 'of the grid i in the t +1 time period'i；
Step three, generating a time matrix T of N by N according to the quantity of the road network grids,
Figure BDA0003217801060000021
calling an API (application program interface) of map software, adopting a KSP (K singular value decomposition) algorithm, and calling an average value of time required by K shortest paths between a grid i and a field grid thereof as path time tij；
Taking a grid i capable of calling out vehicles as a center, and acquiring a neighborhood grid j of the grid i;
1. if tij≥Tthreshold，TthresholdIf the time threshold is the time threshold, the grid i and the grid j are considered to be unreachable and not taken as a scheduling consideration object;
2. if tij<TthresholdIf the grid i and the grid j are reachable, the grid i and the grid j can be taken as a scheduling consideration object; the equalization coefficient alpha of the grid i is then calculatedi＝Di/Si，
If α isiIf the number of the vehicles can be dispatched, the grid j is determined to be less than or equal to 1.5, and the number of the vehicles which can be dispatched is xi＝Si-Di1.5; judging the balance coefficient alpha of the grid j which can be taken as the object to be considered in the dispatching in the neighborhood gridj＝Dj/Sj(ii) a Screening out alphaj>1.5 grid jpRespectively calculating the number of vehicles to be dispatched in each grid, yjp＝Djp/1.5-Sjp；
Step five, the vehicle dispatched from the grid i is dispatched to the grid j of the vehicle needing to be dispatchedpThe distribution principle is as follows:
Figure BDA0003217801060000031
in the formula j1+…jp+…+jnRepresenting the total demand number of vehicles required to be called in the neighborhood grid of the grid i;
step six, pre-scheduling the vehicles in the grids in the area according to the scheduling mode in the step five, and calculating the number S' of empty vehicles in each grid after pre-scheduling;
step seven, calculating the equilibrium coefficient beta of each grid in the area after pre-dispatching as D/S',
Figure BDA0003217801060000032
Figure BDA0003217801060000033
according to the taxi dispatching method based on grid division and graph analysis, the grid shape can be selected as a condition that each area can be covered seamlessly or in a non-overlapping mode, and the grid shape can be any one of a regular triangle, a positive direction or a regular hexagon.
According to the taxi dispatching algorithm based on grid division and graph analysis, the grid is in a regular hexagon shape.
In the taxi scheduling method based on grid division and graph analysis, the grid radius R is the average road length L of the urban road as reference, and R is more than or equal to 0.8L and less than or equal to 1.2L.
In the taxi dispatching method based on grid division and graph analysis, grid j is a field grid with grid i in the range of mR, and m belongs to Z, wherein Z is 1,2, … n.
The taxi scheduling algorithm based on grid division and graph analysis is characterized in that: m-1, m-2, or m-3.
The invention has the beneficial effects that:
1. according to the invention, the regular hexagonal grids are selected for grid division during grid construction, so that not only can uniform grids be inlaid, but also sample deviation caused by the boundary effect of the grid shape can be reduced, the neighborhood can be searched more directly, and meanwhile, curves in a data mode can be represented naturally.
2. The invention adopts KSP algorithm to calculate the passing time between grids, and selects the average value of the passing time of the first 3 shortest paths as the path time.
3. The invention calculates the balance of each grid through the balance coefficient, and distributes and dispatches the vehicles among the grids according to the supply and demand requirements, thereby completing the vehicle dispatching while ensuring the relative balance of the orders and the number of the vehicles of each grid, and simplifying the calculation complexity.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of an alternative grid type for use with the present invention.
Fig. 3 is a schematic diagram of a grid domain search.
In the area of fig. 4 is a schematic diagram of a regular hexagonal grid.
FIG. 5 is a schematic view of vehicle assignments.
Fig. 6 is a schematic diagram of a convex hull region overlay grid.
FIG. 7 is a schematic illustration of different grid vehicle demand displays.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
Example 1: the embodiment provides a taxi dispatching method based on grid division and graph analysis, and as shown in fig. 1, the method integrally includes the following steps.
1. Carrying out grid division on the regional map, determining the shape and the size of a grid, and dividing the road network region into N grids;
wherein:
(1) selection standard of the grid: whether it can cover each block area seamlessly or without overlap. As shown in fig. 2, the grid shape may be an equilateral triangle, a square, or a regular hexagon.
Regular hexagons are preferred in the present invention because hexagons have a very low area to perimeter ratio (although circles have the lowest ratio, they cannot be tessellated to form a continuous mesh), hexagons not only reduce sample variation due to the boundary effect of the mesh shape, but also are the most rounded polygons, which can be tessellated to form a uniform mesh.
The circular nature of hexagonal grids makes it possible to represent curves in the data pattern more naturally than square grids. When comparing polygons having equal areas, the closer the polygon is to the circle, the closer the point near the boundary is to the centroid (especially the point near the break point). This means that any point within a hexagon is closer to the centroid of the hexagon than any given point in a square or triangle of equal area (because squares and triangles have smaller internal angles than hexagons).
When the analysis includes connectivity or movement paths, hexagons are a better choice. Because of the linear nature of rectangles, fishing meshes can focus us on straight, continuous, parallel lines that may suppress the underlying pattern of data. Hexagons tend to break straight lines and can make all curvatures in the data pattern more clearly visible. The breaking of the artificial linear pattern will also reduce the directional deviation that can be observed in the fishing net mesh, in the spacious areas the hexagonal mesh will be less affected by distortion than the fishing net mesh shape due to the curvature of the earth.
As shown in fig. 3, it is more direct to find neighborhoods by using a hexagonal grid, and since the contact angle and the side length of each side are the same, the centroid of each neighborhood is equal, and more neighborhoods can be obtained in calculation by selecting regular hexagons.
(2) Size of the grid:
when the regular sextupole radius R is set, the average road length L of the urban road needs to be referred to, and the general radius selection standard is as follows:
0.8L≤R≤1.2L。
2. the day is equally divided into a plurality of time periods simultaneously, and the time interval of two continuous scheduling decisions can be set to be 1h in specific operation, so that the time of the day is dispersed into 24 time steps, and the order quantity D of a grid i (i is 1,2, … p, q … N) in t (t is 1,2, …, 24) time period is calculatediAnd the number S of empty vehiclesiAnd judging whether the vehicles in the grid i need to be called in or out according to the order number and the empty vehicle number.
Meanwhile, the order quantity of the user at the t +1 moment is predicted by adopting a simple time series prediction method such as LSTM.
3. Generating a time matrix T of N based on the number of the road network grids,
Figure BDA0003217801060000071
then, the estimated time of the path from the point A to the point B can be obtained through an API provided by map software (such as a Gauss map, an Tencent map and the like), a field grid around a grid range 2R is recorded based on the condition, an API interface of the Gauss map is called, K shortest paths are called by adopting a KSP algorithm, (the lengths of the three shortest paths before the AB point are returned by inputting the longitude and the latitude of the AB point, and the estimated passing time is averaged), and the time of the first 3 shortest paths is selected and averaged to be used as the path time.
4. Taking a grid i capable of dispatching a vehicle as a center, and acquiring a field grid j of the grid i; calculating the path time t between grid i and grid jij；
If tij≥Tthreshold，TthresholdConsidering grid i and grid j as time threshold value, and not considering the relation between the two grids during scheduling, wherein T isthresholdThe threshold value set for the current road network is shown, and the experimental value here is 15 minutes.
If tij<TthresholdIf the grid i and the grid j are reachable, the grid i and the grid j can be taken as a scheduling consideration object; the equalization coefficient alpha of the grid i is then calculatedi＝Di/SiIf α isiIf the number of the vehicles can be dispatched, the grid j is determined to be less than or equal to 1.5, and the number of the vehicles which can be dispatched is xi＝Si-Di/1.5；
Judging the balance coefficient alpha of the grid j which can be taken as the object to be considered in the dispatching in the neighborhood gridj＝Dj/Sj(ii) a Screening out alphaj>1.5 grid jpRespectively calculating the number of vehicles to be dispatched in each grid, yjp＝Djp/1.5-Sjp；
5. The vehicle dispatched from grid i is like grid j needing to be dispatched into the vehiclepThe distribution principle is as follows:
Figure BDA0003217801060000081
in the formula j1+…jp+…+jnRepresenting the total number of demands requiring vehicle calls in the neighborhood grid of grid i.
As shown in fig. 5, with grid a as the center, the domain grid of grid a is searched for with a grid radius R,
suppose that only grid B, C, D satisfies T around grid AthresholdThe time limit requirement of (2) we are to grid A, B,C. D, respectively calculating.
D of grid a is 10, S is 15, α is D/S is 0.67<1.5, and the number of vehicles that grid a (at most) can dispatch is N-S-D/1.5 is 8;
d ═ 20, S ═ 10, α ═ 20/10 for grid B, then the number of vehicles that grid a (at most) can dispatch is N ═ D/1.5-S ═ 4;
d ═ 20, S ═ 8, α ═ 20/8 for grid C, then the number of vehicles that grid a (at most) can dispatch is N ═ D/1.5-S ═ 6;
d of the grid D is 15, S is 10, α is D/S is 1.5, and scheduling in and out is not normally required.
From the above calculation, it can be seen that 8 empty vehicles should be called from grid a and called into grids B and C, but the demand vehicles for grids B and C are 4 and 6 respectively, and then the vehicles called out from grid a need to be allocated, the allocation principle is as follows:
Figure BDA0003217801060000082
Figure BDA0003217801060000083
the following can be obtained: the number of vehicles in grid a to grid B is 3, and the number of vehicles in grid a to grid C is 5.
6. After the scheduling is finished, the equilibrium coefficient alpha of each grid in the region is calculated as D/S',
Figure BDA0003217801060000091
Figure BDA0003217801060000092
therefore, the condition after scheduling is evaluated, and whether the scheduling is relatively optimized compared with the scheduling before is judged.

Claims (6)

1. A taxi dispatching method based on grid division and graph analysis is characterized in that: the method comprises the following steps:
step one, selecting a road network region, determining the shape and size of a grid, and dividing the road network region into N grids;
step two, dispersing 1 day into 24 time steps, and calculating the order quantity D of the grid i (i is 1,2, … p, q … N) in the t (t is 1,2, …, 24) periodiAnd the number S of empty vehiclesiJudging whether the vehicles in the grid i need to be called in or out according to the order quantity and the empty vehicle quantity, and simultaneously predicting the order quantity D 'of the grid i in the t +1 time period'i；
Step three, generating a time matrix T of N by N according to the quantity of the road network grids,
Figure FDA0003217801050000011
calling an API (application program interface) of map software, adopting a KSP (K singular value decomposition) algorithm, and calling an average value of time required by K shortest paths between a grid i and a field grid thereof as path time tij；
Taking a grid i capable of calling out vehicles as a center, and acquiring a neighborhood grid j of the grid i;
(1) if tij≥Tthreshold，TthresholdIf the time threshold is the time threshold, the grid i and the grid j are considered to be unreachable and not taken as a scheduling consideration object;
(2) if tij<TthresholdIf the grid i and the grid j are reachable, the grid i and the grid j can be taken as a scheduling consideration object; the equalization coefficient alpha of the grid i is then calculatedi＝Di/Si，
If α isiIf the number of the vehicles can be dispatched, the grid j is determined to be less than or equal to 1.5, and the number of the vehicles which can be dispatched is xi＝Si-Di/1.5；
Judging the balance coefficient alpha of the grid j which can be taken as the object to be considered in the dispatching in the neighborhood gridj＝Dj/Sj(ii) a SieveSelecting alphaj>1.5 grid jpRespectively calculating the number of vehicles to be dispatched in each grid, yjp＝Djp/1.5-Sjp；
Step five, the vehicle dispatched from the grid i is dispatched to the grid j of the vehicle needing to be dispatchedpThe distribution principle is as follows:
Figure FDA0003217801050000021
in the formula j1+…jp+…+jnRepresenting the total demand number of vehicles required to be called in the neighborhood grid of the grid i;
step six, pre-scheduling the vehicles in the grids in the area according to the scheduling mode in the step five, and calculating the number S' of empty vehicles in each grid after pre-scheduling;
step seven, calculating the equilibrium coefficient beta of each grid in the area after pre-dispatching as D/S',
Figure FDA0003217801050000022
Figure FDA0003217801050000023
。
2. the taxi dispatching method based on meshing and graph analysis as claimed in claim 1, wherein: the mesh shape is selected so that it can cover each area seamlessly or without overlapping, and may be any of a regular triangle, a regular direction, or a regular hexagon.
3. The taxi dispatching algorithm based on meshing and graph analysis of claim 2, wherein: the grid shape is regular hexagon.
4. The taxi dispatching method based on meshing and graph analysis as claimed in claim 1, wherein: the grid radius R is the average road length L of the urban road as reference, and R is more than or equal to 0.8L and less than or equal to 1.2L.
5. The taxi dispatching method based on meshing and graph analysis as claimed in claim 1, wherein: and the grid j is a domain grid with the grid i in the range of mR, and m belongs to Z, wherein Z is 1,2 and … n.
6. The taxi dispatching algorithm based on meshing and graph analysis of claim 1, wherein: m-1, m-2, or m-3.
CN202110957469.4A 2021-08-18 2021-08-18 Taxi scheduling method based on grid division and graph analysis Pending CN113869550A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110957469.4A CN113869550A (en) 2021-08-18 2021-08-18 Taxi scheduling method based on grid division and graph analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110957469.4A CN113869550A (en) 2021-08-18 2021-08-18 Taxi scheduling method based on grid division and graph analysis

Publications (1)

Publication Number Publication Date
CN113869550A true CN113869550A (en) 2021-12-31

Family

ID=78990691

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110957469.4A Pending CN113869550A (en) 2021-08-18 2021-08-18 Taxi scheduling method based on grid division and graph analysis

Country Status (1)

Country Link
CN (1) CN113869550A (en)

Similar Documents

Publication Publication Date Title
Xiao et al. An optimization model for electric vehicle charging infrastructure planning considering queuing behavior with finite queue length
Amirgholy et al. Optimal design of sustainable transit systems in congested urban networks: A macroscopic approach
Alexander et al. Assessing the impact of real-time ridesharing on urban traffic using mobile phone data
CN109087502B (en) Vehicle scheduling method, scheduling system and computer equipment based on order distribution
CN105070044A (en) Dynamic scheduling method for customized buses and car pooling based on passenger appointments
CN103854472A (en) Taxi cloud-intelligent scheduling method and system
CN111397620B (en) Electric vehicle charging navigation method and system in fast charging/slow charging mode
Zahabi et al. Spatio-temporal analysis of car distance, greenhouse gases and the effect of built environment: A latent class regression analysis
CN108388970B (en) Bus station site selection method based on GIS
CN108806250A (en) A kind of area traffic jamming evaluation method based on speed sampling data
Qu et al. Location optimization for urban taxi stands based on taxi GPS trajectory big data
Tu et al. Real-time route recommendations for E-taxies leveraging GPS trajectories
CN114819414B (en) Block demand prediction method, system and computer storage medium
CN106130110B (en) The electric taxi charging station constant volume method on trip ground is selected based on stratified probability
CN111801701A (en) System and method for scheduling service providers
Wang et al. Cost-oriented optimization of the location and capacity of charging stations for the electric Robotaxi fleet
Wu et al. A utility-based subcontract method for sensing task in mobile crowd sensing
Deqi et al. A simulation framework for emergency response of highway traffic accident
CN113869550A (en) Taxi scheduling method based on grid division and graph analysis
CN112949987A (en) Taxi dispatching and matching method, system, equipment and medium based on prediction
JP6914298B2 (en) Systems and programs that manage vehicle allocation
Kmetec et al. Electric vehicle charging stations coverage: a study of Slovenia
Liqun et al. Research on taxi drivers' passenger hotspot selecting patterns based on GPS data: A case study in Wuhan
Leigh et al. Police officer dynamic positioning for incident response and community presence-using maximum demand coverage and kernel density estimation to plan patrols
Saha et al. Optimal sizing and efficient routing of electric vehicles for a vehicle-on-demand system

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
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Li Yexing

Inventor after: Xing Jin

Inventor after: Wang Zhonghang

Inventor after: Guo Jianguo

Inventor after: Xiao Mengmeng

Inventor after: Han Mengfei

Inventor after: Sun Hao

Inventor before: Li Yexing

Inventor before: Han Mengfei

Inventor before: Guo Jianguo

Inventor before: Xiao Mengmeng

Inventor before: Sun Hao