CN109740823B - Taxi taking decision method and system oriented to real-time scene calculation - Google Patents
Taxi taking decision method and system oriented to real-time scene calculation Download PDFInfo
- Publication number
- CN109740823B CN109740823B CN201910074065.3A CN201910074065A CN109740823B CN 109740823 B CN109740823 B CN 109740823B CN 201910074065 A CN201910074065 A CN 201910074065A CN 109740823 B CN109740823 B CN 109740823B
- Authority
- CN
- China
- Prior art keywords
- probability
- taxi
- current position
- arrival
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000004364 calculation method Methods 0.000 title claims abstract description 16
- 230000004927 fusion Effects 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 230000029305 taxis Effects 0.000 description 14
- 238000013178 mathematical model Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 229920006068 Minlon® Polymers 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of traffic and discloses a taxi taking decision method and a taxi taking decision system for real-time scene calculation. According to the invention, through large-scale historical taxi passenger carrying data and space-time environmental factors of the user, objective road facilities, traffic information, passenger carrying psychology of a driver and the like are considered, and the user can know the arrival probability of the taxi at the current position accurately in real time, so that a decision is made whether to wait continuously or not.
Description
Technical Field
The invention belongs to the technical field of traffic, and particularly relates to a taxi taking decision method and a taxi taking decision system for real-time scene calculation.
Background
Currently, the current state of the art commonly used in the industry is as follows:
with the rapid development of economy and society, the urban scale is rapidly enlarged, the population is rapidly increased, the traffic problem is becoming more serious, and taxis become vehicles for more and more people to travel. For taxi drivers, it is their primary purpose to obtain more revenue. To obtain more benefit, it is necessary to avoid passing through certain traffic jams or frequent traffic light lines so as not to take too much time to get on traffic jams and the like. This also results in that it is very difficult or even impossible for citizens to encounter taxis on certain road segments. Thus, to avoid endless waiting, citizens need to know the probability of taxi taking at the current location to decide whether to continue waiting for the arrival of taxis at that location.
Most of the traditional taxi taking probability models are formed by combining taxi track data with a mathematical model, and the taxi taking probability of the current position is calculated. For example, wang Zhaoyuan et al combine taxi GPS trajectory data with experience profiles in a taxi probability and waiting time prediction model based on experience profiles, ji Guande et al combine taxi GPS trajectory data with poisson profiles in a passenger waiting time prediction model based on taxi trajectory data mining. There are several problems with using mathematical models to calculate the probability of getting a car: the accuracy is not high, and the arrival rule of the taxi is difficult to be completely summarized by a mathematical model; the taxi arrival probability cannot be calculated in real time, the calculation efficiency is low, and the time is slow; the space-time characteristics are not considered and no dynamic decision can be made.
In summary, the problems of the prior art are:
in the prior art, a mathematical model in taxi taking probability calculation is difficult to completely summarize the arrival rule of a taxi, so that the accuracy is low.
The prior art does not consider the influence of time on riding probability, and the probability of one place does not change with time. The space-time characteristics are not considered and no dynamic decision can be made.
In the prior art, the arrival probability of the taxi cannot be calculated in real time, the calculation efficiency is low, and the time is slow.
The difficulty of solving the technical problems is as follows:
the track data of the taxis are huge, errors exist, and the track data are required to be preprocessed. It is difficult to calculate the taxi arrival probability in real time.
The space-time characteristics cannot be combined, the probability is calculated dynamically, the probability of one place can change along with time, and the calculation efficiency is low.
Meaning of solving the technical problems:
the taxi arrival probability is calculated based on map meshing by utilizing multi-source data such as taxi track data, urban POI data and the like and combining psychological subjective factors and objective space-time characteristics of a driver, the accuracy is higher than that of the taxi arrival probability calculated by only using a mathematical model, the probability changes along with time, and the taxi arrival probability meets objective rules. When the user uses the invention, the riding probability of the current time of the current position of the user can be calculated in real time, so that the user can decide whether to wait continuously or not. Therefore, has great practical value.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a taxi taking decision method and an APP for real-time scene calculation.
The invention is realized in such a way that the taxi taking decision method facing to the real-time scene calculation comprises the following steps:
first, the map is gridded.
And secondly, calculating the distance between the hot spot area and the local point.
And thirdly, analyzing the congestion condition of the current position.
And fourthly, analyzing the infrastructure condition of the road.
And fifthly, calculating the arrival proportion of the historical empty vehicles.
And sixthly, probability fusion.
Further, the first step of meshing the map specifically includes:
the map is divided into grids by using an arcgis tool, four factors of each grid and total taxi taking probability are calculated, and the probability of each grid is relatively independent and does not affect each other.
Further, the calculating the distance between the hot spot area and the local spot in the second step specifically includes:
according to analysis of passenger carrying psychology of a driver, taxi drivers are often willing to go to areas of urban hotspots, and because of large people flow in the hotspot areas, more citizens need to taxi. Therefore, the closer the grid of the waiting place is to the hot spot area, the higher the probability of waiting for the car. As shown in formula (1):
where Dmax represents a threshold value of the distance, dc represents the distance of the current location from the hot spot area, and when the location exceeds the threshold value, the probability of the factor is 0. In the invention, a hot spot area in taxi GPS track data is mined by a DBSCAN clustering method.
Further, the analyzing the congestion condition of the current location in the third step specifically includes:
the congestion condition of the current position is also one of psychological factors considered by taxi drivers in tour, and when a certain position is too congested, the cost of the drivers to the places is too high, so that many drivers do not want to remove the congested places. At present, common parameters for evaluating traffic congestion include speed, flow, service level, occupancy, queuing length, delay rate and the like. Of these parameters, the speed accounted for 90% of the total survey. The invention selects the average speed of the current position as the index of the current position congestion condition, and the average speed can reflect the speed condition because the speed is smoothly changed and does not suddenly decrease or increase, thereby indirectly representing the current position congestion condition. As shown in formula (2):
wherein c is the current time point, t is the time interval, and in the invention, the average speed of the vehicle track points of t minutes before and after the current time point is used for indicating the average vehicle number of the current position. And compared with the Chinese congestion standard, the more congestion is, the lower the probability of the factor is.
Further, the analyzing the infrastructure condition of the road in the fourth step specifically includes:
because the bus stops are not stopped within 30 meters, the number of traffic lights in one grid and the number of bus stops are too large, so that drivers are not willing to pass, and the probability is low. As shown in formula (3):
where Tmax is the maximum number of traffic facilities in a grid and when this number is exceeded the probability is 0.
Further, the calculating the historical empty arrival proportion in the fifth step specifically includes:
the historical track has great reference value, and a position has a plurality of taxis to arrive in a previous period, so that a plurality of taxis are likely to arrive in a later period. In the invention, the more days the taxi arrives at the local place within the maximum tolerance time, the greater the probability that the taxi arrives at the local place is considered. As shown in formula (4):
wherein da is the number of days that the taxi arrives, ds is the total number of days of taxi track data.
Further, the probability fusion in the sixth step specifically includes:
and giving a certain weight to four factors influencing the arrival probability of the taxi, and fusing to obtain the arrival probability P of the taxi. As shown in formula (5), pd is the distance from the hot spot area to the local point, ps is the congestion condition of the current position, pt is the traffic facility condition of the current grid, ph is the arrival proportion of the historical empty vehicles, and the weights are 0.15, 0.35, 0.25 and 0.25 respectively.
P＝0.15*P d +0.35*P s +0.25*P t +0.25*P h (5)。
According to the specific technical scheme, the map is meshed, each grid is independent, and the taxi taking probability of each grid is calculated by combining multi-source data such as taxi GPS track data, urban POI data, traffic light data and the like, so that the fusion of the multi-source data is realized. Objective road facilities, traffic information, passenger carrying psychology of drivers and the like are considered, and factors affecting taxi taking probability of each grid are decomposed into the following four real-time scene factors by considering space-time environment factors of users: the distance from the hot spot area to the local point, the congestion condition of the current position, the road infrastructure and the historical empty car arrival proportion.
And excavating and analyzing the time and the position of the user by utilizing historical taxi track big data, so as to calculate the probability that the user possibly waits for leaving the taxi. The core design is that objective road facilities, traffic information, passenger carrying psychology of drivers and the like are considered through large-scale historical taxi passenger carrying data and space-time environmental factors of users, and the users can know the arrival probability of taxis at the current position accurately in real time, so that a decision is made whether to wait continuously or not.
The invention further aims to provide a taxi taking decision control system for real-time scene computation, which implements the taxi taking decision method for real-time scene computation.
In summary, the invention has the advantages and positive effects that:
after various taxi taking software appears, the difficult taxi taking problem is indeed relieved, but due to traffic facilities at some positions, road conditions and the like, the cost of drivers to places is too high, so that many drivers do not want to connect to sheets at places. Therefore, a plurality of people can encounter the problem of difficult driving every day. At present, a method and application for specially solving the problem of difficult driving are hardly available in the market.
Firstly, the number of taxis is limited, and taxi service cannot be provided anytime and anywhere; the travel requirements of passengers can occur anytime and anywhere, so that the passengers need to wait; secondly, unlike buses, taxis are not fixed in service and have certain contingency, so that the probability of waiting is difficult to predict.
The method utilizes multi-source data to analyze and calculate the arrival probability of the taxi from a multi-dimensional angle, solves the problem that a single mathematical model cannot completely summarize the law of the taxi, and improves the accuracy. The invention not only considers objective road facilities, traffic information and the like, but also considers subjective passenger psychology of taxi drivers, and can realize dynamic decision based on space-time perception. The method and the system can provide real-time computing service for the user, and through gridding of the map, the probability of certain factors affecting the arrival of the taxi is calculated in advance, so that the real-time computing pressure of the user is reduced, and the computing efficiency is improved. When the driving probability of the current position is lower, the position with higher driving probability nearby can be recommended to the user. Therefore, the invention can effectively solve the problem of difficult driving.
In simulation experiments, we used real trajectory data (173073051 pieces of data) of a taxi in martial arts for 72 days to predict the probability of waiting for passengers and evaluate the model through simulation. Firstly, dividing historical track data of a taxi into a working day and a holiday, acquiring urban hot spot areas in different time periods by using a DBSCAN clustering algorithm, calculating the distance from the urban hot spot area in a corresponding time period according to the current time period of a user, and converting the distance into response probability; analyzing the congestion condition of the current position of the user and the infrastructure condition of the road; calculating the arrival proportion of the historical empty vehicles; and giving a certain weight to four factors influencing the arrival probability of the taxi, and fusing to obtain the arrival probability of the taxi. The prediction model is evaluated by using real data and combining a simulation method, and the prediction accuracy of the waiting probability is found to be more than 90%.
Drawings
Fig. 1 is a flowchart of a taxi taking decision method facing to real-time scene calculation provided by an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the prior art, a mathematical model in taxi taking calculation is difficult to completely summarize the arrival rule of a taxi.
The taxi arrival probability cannot be calculated in real time, the calculation efficiency is low, and the time is slow.
The space-time characteristics are not considered and no dynamic decision can be made.
In order to solve the above problems, the application principle of the present invention will be described in detail with reference to specific embodiments.
As shown in fig. 1, the taxi taking decision method facing to real-time scene computation provided by the embodiment of the invention comprises the following steps:
s101: the map is gridded.
S102: and calculating the distance between the hot spot area and the local point.
S103: and analyzing the congestion condition of the current position.
S104: and analyzing the infrastructure condition of the road.
S105: and calculating the historical empty vehicle arrival proportion.
S106: and (5) probability fusion.
The principle of application of the invention is further described below in connection with specific embodiments.
Example 1
The taxi taking decision method facing to the real-time scene calculation provided by the embodiment of the invention specifically comprises the following steps of:
step one, gridding the map.
The map is divided into grids by using an arcgis tool, four factors of each grid and total taxi taking probability are calculated, and the probability of each grid is relatively independent and does not affect each other.
And step two, calculating the distance between the hot spot area and the local point.
According to analysis of passenger carrying psychology of a driver, taxi drivers are often willing to go to areas of urban hotspots, and because of large people flow in the hotspot areas, more citizens need to taxi. Therefore, the closer the grid of the waiting place is to the hot spot area, the higher the probability of waiting for the car. As shown in formula (1):
where Dmax represents a threshold value of the distance, dc represents the distance of the current location from the hot spot area, and when the location exceeds the threshold value, the probability of the factor is 0. In the invention, a hot spot area in taxi GPS track data is mined by a DBSCAN clustering method.
And thirdly, analyzing the congestion condition of the current position.
The congestion condition of the current position is also one of psychological factors considered by taxi drivers in tour, and when a certain position is too congested, the cost of the drivers to the places is too high, so that many drivers do not want to remove the congested places. At present, common parameters for evaluating traffic congestion include speed, flow, service level, occupancy, queuing length, delay rate and the like. Of these parameters, the speed accounted for 90% of the total survey. The invention selects the average speed of the current position as the index of the current position congestion condition, and the average speed can reflect the speed condition because the speed is smoothly changed and does not suddenly decrease or increase, thereby indirectly representing the current position congestion condition. As shown in formula (2):
wherein c is the current time point, t is the time interval, and in the invention, the average speed of the vehicle track points of t minutes before and after the current time point is used for indicating the average vehicle number of the current position. And compared with the Chinese congestion standard, the more congestion is, the lower the probability of the factor is.
And step four, analyzing the infrastructure condition of the road.
Because the bus stops are not stopped within 30 meters, the number of traffic lights in one grid and the number of bus stops are too large, so that drivers are not willing to pass, and the probability is low. As shown in formula (3):
where Tmax is the maximum number of traffic facilities in a grid and when this number is exceeded the probability is 0.
And fifthly, calculating the arrival proportion of the historical empty vehicles.
The historical track has great reference value, and a position has a plurality of taxis to arrive in a previous period, so that a plurality of taxis are likely to arrive in a later period. In the invention, the more days the taxi arrives at the local place within the maximum tolerance time, the greater the probability that the taxi arrives at the local place is considered. As shown in formula (4):
wherein da is the number of days that the taxi arrives, ds is the total number of days of taxi track data.
Step six, probability fusion;
and giving a certain weight to four factors influencing the arrival probability of the taxi, and fusing to obtain the arrival probability P of the taxi. As shown in formula (5), pd is the distance from the hot spot area to the local point, ps is the congestion condition of the current position, pt is the traffic facility condition of the current grid, ph is the arrival proportion of the historical empty vehicles, and the weights are 0.15, 0.35, 0.25 and 0.25 respectively.
P＝0.15*P d +0.35*P s +0.25*P t +0.25*P h (5)
According to the specific technical scheme, the map is meshed, each grid is independent, and the taxi taking probability of each grid is calculated by combining multi-source data such as taxi GPS track data, urban POI data, traffic light data and the like, so that the fusion of the multi-source data is realized. Objective road facilities, traffic information, passenger carrying psychology of drivers and the like are considered, and factors affecting taxi taking probability of each grid are decomposed into the following four real-time scene factors by considering space-time environment factors of users: the distance from the hot spot area to the local point, the congestion condition of the current position, the road infrastructure and the historical empty car arrival proportion.
And excavating and analyzing the time and the position of the user by utilizing historical taxi track big data, so as to calculate the probability that the user possibly waits for leaving the taxi. The core design is that objective road facilities, traffic information, passenger carrying psychology of drivers and the like are considered through large-scale historical taxi passenger carrying data and space-time environmental factors of users, and the users can know the arrival probability of taxis at the current position accurately in real time, so that a decision is made whether to wait continuously or not.
Example 2
Taking the martial arts as an example:
1) Map gridding: the arcgis tool is used for dividing the administrative region of the Wuhan city into grids, the size of each grid is 50m and 50m, the total number of the grids is 11029348, and the probability of each grid is relatively independent and does not affect each other.
2) Calculating influence factors of decomposition: distance of hot spot area from local site: and obtaining a hot spot area of the Wuhan city by utilizing taxi track data of the Wuhan city and combining a DBSCAN clustering algorithm. And calculating the distance between the current position of the user and the central point of the hot spot area, taking the nearest distance between the current position of the user and all the hot spot areas, and calculating the probability of the current factor by combining the formula (1). Where the threshold Dmax of distance takes 1 km.
Congestion status of current location: in formula (2), t is taken for 2.5 minutes. I.e. the average speed of history taxis passing by 2.5 minutes before and after the current point in time of the user. And compared to the chinese congestion criteria as shown in table 1. The probability of each stage is 0.33, the probability of the factor is 1 when the system is unblocked, and the probability is 0 when the system is severely congested.
TABLE 1 Chinese Congestion Standard
Infrastructure condition of the road: in equation (3), tmax takes 4, and when the number of traffic facilities in one grid exceeds 4, taxi drivers often do not choose to pass through the grid.
Historical empty vehicle arrival ratio: the maximum tolerated time of the user is set to 15 minutes. In the historical data, when a user passes through a free car within the time point t to t+15 minutes, the taxi is considered to arrive on the day, and otherwise, no free car is considered to arrive.
3) Probability fusion: and (3) fusing the four factors of the decomposition by using the formula (5) to obtain the arrival probability of the taxi of the grid where the user is located at the current time.
The embodiment of the invention provides a taxi taking decision control system oriented to real-time scene calculation, which comprises an APP.
The invention is further described below in connection with specific embodiments.
The taxi track raw data comprise taxi track data of the Wuhan city from 1 st in 2014 to 1 st in 2014 and 12 th in 3 rd in the Mysql database. After data cleansing, there were a total of 173073051 pieces of data. The main fields include t_targetid (taxi ID), t_utcttime (UTC time), t_longitude (Longitude), t_latitude (Latitude), t_speed, t_status (passenger Status).
The data is too large to be read in mysql. In this case, a MongoDB database is therefore employed. In the MongoDB database, information of each grid (11029348 grids in total) is stored, and taxi track data is stored in time periods with a grid ID as a primary key.
The gird is the ID of the current grid, maxLon, minLon, maxLat, minLat is the maximum and minimum longitude and latitude of the current grid, the range of the grid is determined, trafficNum is the number of traffic facilities in the grid, vocationPoints and weekPoints are track data of taxis, workdays and weekends are stored separately, the inner part is 0-23 hours, and the riding probability is calculated by using space-time perception, so that the taxi is convenient to read.
And calculating the data of the boarding and disembarking points in the Wuchang area according to the passenger carrying state in the taxi track data, wherein the total number of the boarding and disembarking points is 3510862. And clustering according to the getting-on and getting-off points by using a DBSCAN clustering algorithm according to time intervals to obtain the urban hot spot area. The hot spot area is defined as an area with frequent taxi occurrence in a certain time period, and the area has large people flow and is often an important position in a city.
The hot spot areas of a city change with time, the hot spot areas of one city in the morning and the hot spot areas of the afternoon are often different, and the hot spot areas of the workday and the rest day are also often different. According to the travel rule of citizens, the invention divides the working day and the rest day into five different time slices, clusters the different time slices by using the DBSCAN to form ten hot spot areas in different time periods of the Wuhan city, and calculates the distance by using the hot spot areas in the corresponding time periods according to the current time of the user. The meaning of each time period and representation is as follows:
working day:
the citizens and taxies in the early morning of 00-07 are less.
07-09 is the peak period of the citizen's office work in the morning, easy traffic jam.
The citizens at noon start working, eat and break at noon, and have certain travel demands.
The peak period of the school of the citizens in the afternoon is 16-19, and the traffic jam is easy.
More people play outside at 19-24 night.
Rest day:
on the rest days, the number of traveling vehicles is small from 00 to 10.
The use of 10-14 is stressed during the peak period of eating middle-warmer meal.
Fewer citizens 14-18 will use their cars, often at home, or have arrived at their destination.
The use of the bicycle is stressed in the peak period of 18-20 dinner.
20-24 more people play outside.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (2)
1. The taxi taking decision method for the real-time scene calculation is characterized by comprising the following steps of:
step one, gridding a map;
secondly, calculating the distance between the hot spot area and the local point;
thirdly, analyzing the congestion condition of the current position;
fourth, analyzing the infrastructure condition of the road;
fifthly, calculating the arrival proportion of the historical empty vehicles;
sixth, probability fusion;
the first step of meshing the map specifically includes:
dividing the map into grids by using an arcgis tool, and calculating four factors of each grid and total taxi taking probability;
the calculating the distance between the hot spot area and the local spot in the second step specifically includes:
wherein D is max Threshold value representing distance, D c Representing the distance from the current location to the hot spot area, wherein when the location exceeds a threshold value, the probability of the factor is 0;
the third step of analyzing the congestion condition of the current position specifically includes:
the average speed of the current position is selected as an index of the congestion condition of the current position, and the following formula is adopted:
wherein c is the current time point, and t is the time interval; indicating the average speed of the vehicle at the current position by the average speed of the vehicle track points t minutes before and after the current time point; after calculating the average speed of the vehicle at the current position, comparing according to the Chinese congestion standardIn comparison, the congestion condition P of the current position with the average vehicle speed of less than 10km/h is judged s The probability of (2) is 0, and the congestion condition P of the current position is when the average speed of the vehicle at the current position is 10km/h-20km/h s The probability of (2) is 0.33, and the congestion condition P of the current position is when the average speed of the vehicle at the current position is 20km/h-30km/h s The probability of (2) is 0.67, and the congestion condition P of the current position when the average vehicle speed of the current position is more than 30km/h s The probability of (1);
the fourth step of analyzing the infrastructure condition of the road specifically includes:
the following formula is adopted:
wherein T is max For the most number of traffic facilities in a grid, the probability is 0 when the number is exceeded;
the fifth step of calculating the historical empty arrival proportion specifically comprises the following steps:
the following formula is adopted:
wherein d a D is the number of days of taxi arrival s The total number of days of taxi track data;
the probability fusion in the sixth step specifically includes:
giving a certain weight to four factors influencing the arrival probability of the taxi, and fusing to obtain the arrival probability P of the taxi; the following formula is adopted, wherein P d P is the distance from the hot spot area to the local site s P is the congestion condition of the current position t P is the traffic facility condition of the current grid h For the arrival proportion of the historical empty vehicles, the weights are 0.15, 0.35, 0.25 and 0.25 respectively;
P＝0.15*P d +0.35*P s +0.25*P t +0.25*P h 。
2. a real-time scene computation oriented taxi taking decision control system implementing the real-time scene computation oriented taxi taking decision method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910074065.3A CN109740823B (en) | 2019-01-25 | 2019-01-25 | Taxi taking decision method and system oriented to real-time scene calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910074065.3A CN109740823B (en) | 2019-01-25 | 2019-01-25 | Taxi taking decision method and system oriented to real-time scene calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109740823A CN109740823A (en) | 2019-05-10 |
| CN109740823B true CN109740823B (en) | 2023-05-02 |
Family
ID=66366238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910074065.3A Active CN109740823B (en) | 2019-01-25 | 2019-01-25 | Taxi taking decision method and system oriented to real-time scene calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109740823B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111143779B (en) * | 2019-12-31 | 2023-07-25 | 斑马网络技术有限公司 | Method, device, electronic equipment and storage medium for obtaining commute rule |
| CN111445091B (en) * | 2020-04-21 | 2022-08-12 | 南京邮电大学 | Intelligent decision-making method for taxi driver in passenger transport center |
| CN113962752B (en) * | 2021-12-21 | 2022-03-08 | 华南理工大学 | Electric taxi individual behavior analysis decision-making system based on multivariate information interaction |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632532A (en) * | 2012-08-22 | 2014-03-12 | 北京掌城科技有限公司 | Taxi taxi-taking inducing method |
| WO2015136742A1 (en) * | 2014-03-12 | 2015-09-17 | 株式会社日立製作所 | Train station congestion prediction device and train station congestion information provision system |
| CN105741537A (en) * | 2016-03-29 | 2016-07-06 | 福建工程学院 | Vehicle passenger-seeking state identification method and system |
| CN105825310A (en) * | 2016-04-11 | 2016-08-03 | 湖南科技大学 | Taxi passenger-searching path recommendation method based on information entropy |
-
2019
- 2019-01-25 CN CN201910074065.3A patent/CN109740823B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632532A (en) * | 2012-08-22 | 2014-03-12 | 北京掌城科技有限公司 | Taxi taxi-taking inducing method |
| WO2015136742A1 (en) * | 2014-03-12 | 2015-09-17 | 株式会社日立製作所 | Train station congestion prediction device and train station congestion information provision system |
| CN105741537A (en) * | 2016-03-29 | 2016-07-06 | 福建工程学院 | Vehicle passenger-seeking state identification method and system |
| CN105825310A (en) * | 2016-04-11 | 2016-08-03 | 湖南科技大学 | Taxi passenger-searching path recommendation method based on information entropy |
Non-Patent Citations (6)
| Title |
|---|
| "互联网+"时代的出租车资源配置模型;杜剑平等;《数学建模及其应用》;20151215(第04期);全文 * |
| Predicting imbalanced taxi and passenger queue contexts in airport;MS Rahaman;《Twenty First Pacific Asia Conference on Information Systems》;20171231;全文 * |
| 基于人工鱼群算法的出租车智能调度;谢榕等;《系统工程理论与实践》;20171125(第11期);全文 * |
| 基于出租车轨迹数据挖掘的推荐模型研究;赵苗苗;《中国优秀硕士学位论文全文数据库》;20160215;全文 * |
| 基于泊松过程的寻找空驶出租车的算法;樊里略;《湖南科技大学学报(自然科学版)》;20160320(第01期);全文 * |
| 基于深圳市出租车轨迹数据的高效益寻客策略研究;刘丽等;《浙江大学学报(理学版)》;20180110(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109740823A (en) | 2019-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102081859B (en) | Control method of bus arrival time prediction model | |
| CN102819955B (en) | Road network operation evaluation method based on vehicle travel data | |
| CN108564226B (en) | Bus route optimization method based on taxi GPS and mobile phone signaling data | |
| Alexander et al. | Assessing the impact of real-time ridesharing on urban traffic using mobile phone data | |
| CN102737504B (en) | Method for estimating bus arrival time in real time based on drive characteristics | |
| Dion et al. | Evaluation of potential transit signal priority benefits along a fixed-time signalized arterial | |
| CN113902011A (en) | Urban rail transit short-time passenger flow prediction method based on cyclic neural network | |
| CN105096643B (en) | Real-time public transport arrival time Forecasting Methodology based on multi-line front truck service data | |
| CN103956050A (en) | Road network running evaluation method based on vehicle travel data | |
| CN107490384B (en) | Optimal static path selection method based on urban road network | |
| CN106781490A (en) | Urban highway traffic analysis ＆ appraisement on operation system | |
| CN109740823B (en) | Taxi taking decision method and system oriented to real-time scene calculation | |
| Li et al. | Public bus arrival time prediction based on traffic information management system | |
| Loulizi et al. | Steady‐State Car‐Following Time Gaps: An Empirical Study Using Naturalistic Driving Data | |
| CN104778834A (en) | Urban road traffic jam judging method based on vehicle GPS data | |
| CN103366224B (en) | Passenger demand prediction system and method based on public transport network | |
| CN104200649A (en) | System and method for dispatching and distributing peak traffic hour route resources based on application in advance | |
| CN113506013B (en) | Multi-source data-based comprehensive benefit evaluation method for medium-traffic volume public transportation system | |
| CN105868861A (en) | Bus passenger flow evolution analysis method based on time-space data fusion | |
| Zhou et al. | Research on traffic situation analysis for urban road network through spatiotemporal data mining: a case study of Xi’an, China | |
| CN104408948A (en) | Vehicle-mounted-GPS-based public transport priority signal control method of urban road traffic | |
| CN110633558A (en) | Urban traffic system modeling system | |
| Kan et al. | Understanding space-time patterns of vehicular emission flows in urban areas using geospatial technique | |
| CN109671007A (en) | Taxi taking difficulty assessment method near a kind of railway station based on multi-dimensional data | |
| CN111126878A (en) | Urban traffic operation evaluation method based on ecological index |
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 |