CN112990610B - Method for predicting taxi capacity demand of railway station based on multiple linear regression - Google Patents
Method for predicting taxi capacity demand of railway station based on multiple linear regression Download PDFInfo
- Publication number
- CN112990610B CN112990610B CN202110488020.8A CN202110488020A CN112990610B CN 112990610 B CN112990610 B CN 112990610B CN 202110488020 A CN202110488020 A CN 202110488020A CN 112990610 B CN112990610 B CN 112990610B
- Authority
- CN
- China
- Prior art keywords
- demand
- railway station
- touring
- passenger
- taxi
- 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 32
- 238000012417 linear regression Methods 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000003203 everyday effect Effects 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000004931 aggregating effect Effects 0.000 claims description 2
- 230000006399 behavior Effects 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 5
- 238000003064 k means clustering Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000029305 taxis Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting the transport capacity demand of a taxi in a railway station based on multiple linear regression. In order to improve the taxi connection operation efficiency of the railway station as soon as possible and effectively analyze and predict the taxi transportation capacity of the railway station, the railway station is selected as a research object, necessary data is fetched, a prediction model is designed, and knowledge storage is provided for the taxi transportation capacity allocation of the railway station. Firstly, taxi data with a date mode and passenger order data are extracted from a railway station to be researched, missing values are filled by adopting a linear interpolation method, and travel time in finished orders is counted. The number of the arriving persons with the taxi taking requirements at the railway station is predicted, and the number of the vehicle requirements is predicted by using a multiple linear regression method. The method for predicting the transport capacity demand of the taxi in the railway station can analyze and predict the taxi demand in the railway station, deploy transport capacity scheduling work, enhance operation efficiency, improve service reliability and improve passenger satisfaction.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a method for predicting the transport capacity demand of a taxi in a railway station based on multiple linear regression.
Background
In important transportation hubs such as airports, railway stations and the like, taxis are the main force for ensuring the safe and convenient trip of passengers arriving at ports, and are the problem of constant concern of leaders at all levels. The gathering and detention of passenger flow, especially at night, not only brings inconvenience to people, but also has great potential safety hazard. At present, a taxi industry competent department mainly deploys transportation capacity scheduling work by experience, and the problems of inaccurate guarantee, untimely guarantee and the like exist, for example, the scheduling deviation of passenger flow concentration periods such as major holidays and activity days is large, the transportation capacity scheduling is relatively delayed when emergencies such as extreme weather occur, and the like, and the analysis of the transportation capacity of taxis in a station and the related prediction work are urgently needed to be carried out.
The taxi mainly comprises two types of touring cars and network taxi appointments, and the touring cars and the network taxi appointments are obviously different in service modes, vehicle standards, price mechanisms and the like. The tour bus is sprayed and provided with a special taxi mark, tourists are mainly visited in a road sweeping mode, and the tourists are waited at sites such as airports, hub stations and the like, and reservation service can be provided in a telephone mode, an internet mode and the like; the appearance color and the vehicle identification of the network reservation vehicle are obviously different from those of the tour vehicle, the tour vehicle cannot sweep roads and wait for passengers at a station, and the service can be provided only by an appointment mode; the level of the network car booking vehicle is higher than that of the tour car, and differential travel service is provided for citizens; the tour vehicle is priced by government, has certain basic guarantee function, and is regulated by network appointment vehicle and guided by government when necessary.
In order to improve the taxi connection operation efficiency of the station as soon as possible and to urgently need to effectively analyze and predict the taxi transportation capacity of the station, the research selects a railway station as a research object, transfers necessary data, designs a prediction model and provides knowledge storage for station transportation capacity allocation.
Disclosure of Invention
The main problems to be solved by the invention are as follows: the invention relates to a method for efficiently dispatching taxies to meet the travel demands of passengers in a railway station.
The technical scheme of the invention is as follows: a method for predicting the transport capacity demand of a taxi in a railway station based on multiple linear regression is realized by the following steps:
(1) obtaining taxi data and passenger order data within the range of a railway station;
(2) carrying out missing value processing on the data by adopting a linear interpolation method;
(3) extracting the station entering and exiting records of the touring bus for statistics based on the shooting data of the camera of the railway station;
(4) predicting the number of arriving people with the touring car taking demand by using a multiple linear regression method;
(5) performing K-means clustering on the data of the train station entering and leaving stations based on the network car booking order data and the GPS data, and accurately simulating the network car booking operation behavior;
(6) predicting the number of arriving persons required for taking the net appointment at the railway station by using a multiple linear regression method;
(7) and analyzing and predicting the taxi transportation capacity requirement of the railway station by combining the prediction of the touring bus and the network taxi appointment demand.
Selecting a plurality of train station network appointment order quantity data as initial clustering centers according to historical data, classifying the rest data into each center according to the principle of the closest distance to obtain a first iteration result, then taking the center point of each type as the center of the next iteration, performing repeated iteration, and gradually converging the final result to approximate to an optimal solution.
The specific operation steps are as follows:
randomly selecting k points as a clustering center;
calculating the distance from each point to k clustering centers, and dividing the point to the nearest clustering center, so that k clusters can be formed;
recalculating the mass center (mean value) of each cluster;
and fourthly, repeating the steps from the first step to the second step until the position of the mass center does not change or the set iteration number is reached.
Has the advantages that:
the method can grasp the taxi transportation capacity of the railway station from the perspective of historical rules, and can efficiently predict the taxi transportation capacity demand of the station according to the analysis of historical data so as to effectively solve the problem of large passenger flow detention of the station.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a pattern diagram of the demanded quantity and date of the touring car at Beijing West station;
FIG. 3 is a diagram of a fitting result of a prediction model of the demand of a cruise vehicle;
FIG. 4 is a pattern diagram of the arrival number and date of the network appointment vehicle;
FIG. 5 is a flow chart of the K-means clustering algorithm.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person skilled in the art based on the embodiments of the present invention belong to the protection scope of the present invention without creative efforts.
According to the embodiment of the invention, as shown in fig. 1, the method for predicting the capacity demand of the taxi at the railway station based on the multiple linear regression is realized by the following steps:
(1) obtaining taxi data and passenger order data within the range of a railway station;
(2) carrying out missing value processing on the data by adopting a linear interpolation method;
(3) extracting the station entering and exiting records of the touring bus for statistics based on the shooting data of the camera of the railway station;
(4) predicting the number of arriving people with the touring car taking demand by using a multiple linear regression method;
(5) performing K-means clustering on the data of the train station entering and leaving stations based on the network car booking order data and the GPS data, and accurately simulating the network car booking operation behavior;
(6) predicting the number of arriving persons required for taking the net appointment at the railway station by using a multiple linear regression method;
(7) and analyzing and predicting the taxi transportation capacity requirement of the railway station by combining the prediction of the touring bus and the network taxi appointment demand.
According to the embodiment of the present invention, further, the patrol car passenger flow sharing ratio refers to a passenger flow ratio of all arriving passenger flows leaving a railway station with a patrol car, and assuming that the passenger carrying rate of the patrol car is P, that is, 1 patrol car can take P passengers on average, the patrol car passenger flow sharing ratio is:
that is to say that the first and second electrodes,
the method comprises the steps of measuring and calculating passenger flow volume of a railway station and data of a touring car storage pool, wherein the passenger flow volume of the railway station is calculated from ticket selling data of each car of a railway bureau, and the detail of the passenger flow data is the arrival passenger flow volume of each hour; the data of the number of the touring cars is obtained by the number of the touring cars entering and exiting the storage pool recorded by the camera of the railway station.
The passenger flow of the railway station and the output of the patrol vehicle storage pool in the period of 4:00-23:59 per day are counted at the time interval of 1 hour (almost no passenger flow of the railway station in the time period of 0:00-4: 00), the proportion of the patrol vehicle passenger flow in each hour per day can be obtained through the calculation formula, and finally, the average value of the proportion of the patrol vehicle passenger flow in the same time period on different dates is measured, so that the proportion of the patrol vehicle passenger flow in different time periods per day can be obtained.
According to the embodiment of the invention, further, based on the analysis of the passenger flow and the number of the touring cars in the railway station, the demand of the touring cars in each hour can be known, namely the sum of the number of the touring cars which are driven out in each hour and the waiting number of passengers in the storage pool at the end of the hour; the demand of the touring bus is divided into the following three conditions, and the passenger carrying rate is set as P;
if the number of touring cars exiting the storage pool in the current time period is equal to the passenger demand which is not solved at the end of the previous time period, the touring cars in the current time period are used for solving the residual passenger demand in the previous time period,
i.e. touring car demand at time t
If the number of the touring cars which exit the storage pool in the current time period is larger than the passenger demand which is not solved at the end of the previous time period, the touring cars in the current time period are proved to solve a part of the passenger demand in the current time period on the basis of solving the residual passenger demand in the previous time period,
i.e. touring car demand at time t
If the number of the touring cars which exit the storage pool in the current time period is less than the passenger demand which is not solved at the end of the previous time period, the touring cars in the current time period are not solved the residual passenger demand in the previous time period,
i.e. touring car demand at time t
The method comprises the following steps of counting the passenger flow of a railway station and the number of touring cars entering and exiting a storage pool every day by taking 1 hour as a time interval, fitting a date mode of touring car requirements, and establishing a prediction model:
that is to say that the first and second electrodes,
y- -predicted required amount of touring car (vehicle)
x1-passenger flow volume (human)
x2Itinerant vehicle demand date mode (vehicle)
And fitting by a multiple linear regression method to obtain a fitted prediction model.
According to the embodiment of the invention, further, a plurality of train station network appointment order quantity data are selected as initial clustering centers, other points are classified into the centers according to the principle of the closest distance to obtain a first iteration result, then the center point of each type is used as the center of the next iteration to carry out repeated iteration, the final result gradually converges and approaches to an optimal solution, and the number of the train station network appointment entering and leaving stations of each day counted at fixed time intervals is counted to obtain the corresponding date mode type;
the specific operation steps are as follows:
randomly selecting k points as a clustering center;
calculating the distance from each point to k clustering centers, and dividing the point to the nearest clustering center, so that k clusters can be formed;
recalculating the mass center of each cluster, namely the mean value;
and fourthly, repeating the steps from the first step to the second step until the position of the mass center does not change or the set iteration number is reached.
The number of the incoming and outgoing stations of each day of train station network appointment is counted by taking 1 hour as a time interval, and the historical curves of the number of the incoming and outgoing stations 24 hours a day are aggregated by using a k-means cluster analysis method, so that different date modes can be obtained. The flow of the k-means clustering analysis is shown in FIG. 5.
According to the clustering model result, the time distribution of the train station network taxi appointment number presents a relatively obvious date characteristic, namely, the train station network taxi appointment number can be divided into different categories according to the date characteristic from Monday to Sunday.
According to the embodiment of the invention, further, the repeated orders in the ordering data of the networked car booking passengers are removed, the removing principle is that 95% is taken as a confidence interval, the taking time in the number of the completed orders is counted, and when the taking time of all the passengers of the same passenger who continuously take the orders twice is less than the 95% confidence interval, the passengers are regarded as the repeated orders.
And (4) counting the amount of the contracted train orders (namely the required amount) of the train station network in the period of 4:00-23:59 per day at intervals of 1 hour, and aggregating the historical data by using a k-means clustering method.
Counting the passenger flow of the railway station in a period of 4:00-23:59 per day by taking 1 hour as a time interval, and establishing a prediction model:
that is to say that the first and second electrodes,
y- -predicted net appointment demand (vehicle)
x1-passenger flow volume (human)
x2-network appointment demand date mode (vehicle)
Fitting by a multiple linear regression method to obtain a prediction model.
According to a specific embodiment of the invention, the method is applied to the passenger flow demand of the Beijing Western-style station, and for the demand of touring cars at the Beijing Western-style station, the quantity of the touring cars is changed due to the influence of external factors, and if the passenger volume of the Western-style station is increased, the demand of the touring cars is increased; the demands of touring cars on different time periods in the same day, such as saturday and working day, are also obviously different, so that the time factors can also cause the demands to be changed. In the research, the influence of different influence factors (passenger flow and date mode) on the requirement of the cruise vehicle needs to be considered, and the influence factors and the influenced factors have obvious linear correlation relationship, so that the requirement of the cruise vehicle is predicted and analyzed by selecting a multiple linear regression prediction method.
The multiple linear regression prediction method is a statistical analysis method for determining the quantitative relationship of interdependence between two or more variables by using regression analysis in mathematical statistics, i.e. researching the relationship between a dependent variable y and a plurality of independent variables, and predicting y by knowing x by using the relationship. The mathematical expression is as follows:
where y is the variable to be predicted;is an independent variable that affects a predictor variable;are coefficients of respective variables, determined by least squares fitting; ε is a random perturbation term.
The measurement adopts 2019.8.1-2019.9.30 Beijing Western-style station passenger flow volume, touring car storage pool and queuing people number data, and the detail of the Beijing Western-style station passenger flow data is the arrival passenger flow volume per hour; the number data of the touring cars is obtained by counting the number of the touring cars entering and exiting the storage pool, which is recorded by a camera of the station; the number of passengers in the storage pool is obtained by the face recognition and counting of the cameras of the stations.
Counting the daily Beijing Western-style station passenger flow and the number of western-style station touring cars entering and exiting the storage pool at intervals of 1 hour, and fitting a date pattern required by the touring cars, wherein fig. 2 is a Beijing Western-style station touring car required amount date pattern diagram, and the situation that although the positions of peak points and valley points generated by a Beijing Western-style station touring car required amount curve from Monday to Sunday are similar, the number is obviously different is found, for example, the quantity difference between the touring car required amount of Saturday and the touring car required amount of Monday is larger in a time period of 11:00-15: 00.
TABLE 1 comparison table of data patterns of touring cars in Beijing west station
Counting the passenger flow of Beijing Western-style station in 4:00-23:59 period each day by taking 1 hour as a time interval, and establishing a prediction model:
that is to say that the first and second electrodes,
y- -predicted required amount of touring car (vehicle)
x1-west station passenger flow volume (man)
x2Itinerant vehicle demand date mode (vehicle)
And fitting is performed by a multiple linear regression method, and the result is shown in fig. 3.
In the figure, y represents the cruise vehicle demand, x1 represents the passenger flow volume, and x2 represents the date pattern. As can be seen from fig. 3, the prediction model that is fitted is:
that is, log (cruise vehicle demand) =0.105 × log (passenger volume) +0.924 × log (date pattern) -0.218. And goodness of fit r2=0.8147, the prediction effect is better.
The number of inbound stops of the Beijing Western-style station network appointment every day is counted by taking 1 hour as a time interval, and a historical inbound stop number curve of 24 hours a day is aggregated by using a k-means cluster analysis method, so that five date modes can be obtained.
Through measurement and calculation, five date modes of the number of arrival of taxi appointments of the Beijing Western-style station network are Monday to Thursday and Sunday respectively; friday; saturday, the second half of holiday; before and after holidays; the first half of the day is holiday. Five date patterns are shown in fig. 4; the distribution of the date patterns is shown in table 2 (the numbers in parentheses are for category distinction only).
TABLE 2 networked taxi booking and arrival number date mode distribution
According to the clustering model result, the time distribution of the number of the scheduled arrival of the vehicles in the Beijing Western-style station network presents a relatively obvious date characteristic, namely, the date characteristic can be divided into different categories according to the date characteristic from Monday to Sunday. In the half mode before holidays (4 days before eleven holidays in the data), the number of network appointment vehicles entering stations in each time period is obviously higher than that of other dates, the number of network appointment vehicles entering stations in the time period of 5:00-15:00 is basically 1000 vehicles/hour, and the maximum value in one day is reached at 6:00-7: 00; the trends of the curves before and after holidays (28-30 days in 9 months and 8-9 days in 10 months in the data) are similar to those of the before-holiday half-pattern, but the number of the curves is obviously reduced. The stage is close to the holiday, and the number of passengers taking the bus to the Beijing Western station is not as large as that of holidays, but is obviously higher than that of the passengers in the non-holiday period; the network taxi approach amount of the friday mode obviously increases after 12:00, which is just opposite to the mode of the second half of Saturday and holiday; the number of network appointment vehicles entering stations in the mode from Monday to Thursday and Sunday is the least compared with other modes, most of dates contained in the mode are working days, and the number of people leaving Beijing from Beijing Western medicine is not large because the next day of the week in non-working days is a working day. The historical rule mining can provide basis for pattern matching and prediction of taxi appointment and station entering quantity of the west station network.
According to analysis, the total demand difference between the patrol vehicle and the net appointment vehicle in the Beijing west station is large, and the demands of the patrol vehicle and the net appointment vehicle in different periods of time on different dates and the same date are obviously different. The data patterns of the touring car demand are basically consistent in the trend of the curve, no obvious difference exists among holidays, working days and saturdays, only the demand in different time periods is different, and the peak of the demand in each data pattern appears at noon; and several date modes of the network appointment vehicle demand are sensitive to date characteristics such as holidays, workdays, saturdays and the like, the curve trends in different date modes are different, and the peak of the demand of each date mode appears at night.
The design and application of the research can grasp the taxi transportation capacity of the Beijing Western-style station from the perspective of historical rules, and can efficiently predict the taxi transportation capacity demand of the station according to the analysis of historical data so as to effectively deal with the problem of large passenger flow detention of the station.
Although illustrative embodiments of the present invention have been described above to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, but various changes may be apparent to those skilled in the art, and it is intended that all inventive concepts utilizing the inventive concepts set forth herein be protected without departing from the spirit and scope of the present invention as defined and limited by the appended claims.
Claims (4)
1. A method for predicting the transport capacity demand of a taxi in a railway station based on multiple linear regression is characterized by comprising the following steps:
(1) obtaining taxi data and passenger order data within the range of a railway station;
(2) carrying out missing value processing on the data by adopting a linear interpolation method;
(3) extracting the station entering and exiting records of the touring bus for statistics based on the shooting data of the camera of the railway station;
(4) by predicting the number of arriving people with the touring car taking requirements, fitting a date mode of the touring car taking requirements by using a multivariate linear regression method, establishing a prediction model, and predicting the touring car demand; the method specifically comprises the following steps:
the method comprises the steps that on the basis of analysis of passenger flow and the number of touring cars in a railway station, the required number of the touring cars in each hour is obtained, and the required number is the sum of the number of the touring cars which are driven out in each hour and the number of passengers waiting in a storage pool at the end of each hour; the demand of the touring bus is divided into the following three conditions, and the passenger carrying rate is set as P;
if the number of touring cars exiting the storage pool in the current time period is equal to the passenger demand which is not solved at the end of the previous time period, the touring cars in the current time period are used for solving the residual passenger demand in the previous time period,
i.e. touring car demand at time t
If the number of the touring cars which exit the storage pool in the current time period is larger than the passenger demand which is not solved at the end of the previous time period, the touring cars in the current time period are proved to solve a part of the passenger demand in the current time period on the basis of solving the residual passenger demand in the previous time period,
i.e. touring car demand at time t
If the number of the touring cars which exit the storage pool in the current time period is less than the passenger demand which is not solved at the end of the previous time period, the touring cars in the current time period are not solved the residual passenger demand in the previous time period,
i.e. touring car demand at time t
Counting the passenger flow of the railway station and the number of the touring cars entering and exiting the storage pool every day by taking preset hours as time intervals, fitting a date mode of the touring car requirement, and establishing a prediction model:
that is to say that the first and second electrodes,
-cruise vehicle demand date mode; wherein the date mode comprises: monday to thursday, sunday; friday; saturday, the second half of holiday; before and after holidays; the first half of holidays; fitting by a multiple linear regression method to obtain a fitted prediction model;
(5) aggregating historical station entrance and exit quantity curves of 24 hours a day by using a k-means cluster analysis method based on network car booking order data and GPS data to obtain different date modes, and then establishing a prediction model to accurately simulate network car booking operation behaviors; the method specifically comprises the following steps:
selecting a plurality of train station network appointment order quantity data as initial clustering centers, classifying the rest points into each center according to the principle of closest distance to obtain a first iteration result, then taking the central point of each type as the center of the next iteration to carry out repeated iteration, gradually converging the final result to approximate to an optimal solution, and counting the number of stations entering and leaving the train station network appointment every day at fixed time intervals to obtain corresponding date mode types;
(6) predicting the number of arriving persons required for taking the network car appointment at a railway station, and predicting the quantity of the network car appointment demand by using a multivariate linear regression method in combination with a date mode; the date mode comprises the following steps: monday to thursday, sunday; friday; saturday, the second half of holiday; before and after holidays; the first half of holidays; the method specifically comprises the following steps:
counting the passenger flow of the railway station in a period of 4:00-23:59 per day by taking a preset hour as a time interval, and establishing a prediction model:
that is to say that the first and second electrodes,
-net appointment demand date mode; wherein the date mode comprises: monday to thursday, sunday; friday; saturday, the second half of holiday; before and after holidays; the first half of holidays;
fitting by a multiple linear regression method to obtain a prediction model;
(7) and analyzing and predicting the taxi transportation capacity requirement of the railway station by combining the prediction of the touring bus and the network taxi appointment demand.
2. The method for predicting the capacity demand of the taxi at the railway station based on the multiple linear regression as claimed in claim 1, wherein:
the passenger flow sharing proportion of the patrol cars refers to the passenger flow proportion that all passenger flows arriving at a station take patrol cars to leave a railway station, and if the passenger carrying rate of the patrol cars is P, namely 1 patrol car can take P passengers on average, the passenger flow sharing proportion of the patrol cars is as follows:
that is to say that the first and second electrodes,
the method comprises the steps of measuring and calculating passenger flow volume of a railway station and data of a touring car storage pool, wherein the passenger flow volume of the railway station is calculated from ticket selling data of each car of a railway bureau, and the detail of the passenger flow data is the arrival passenger flow volume of each hour; the data of the number of the touring cars is obtained by the number of the touring cars entering and exiting the storage pool recorded by the camera of the railway station.
3. The method for predicting the capacity demand of the taxi at the railway station based on the multiple linear regression as claimed in claim 1, wherein:
the specific operation steps are as follows:
randomly selecting k points as a clustering center;
calculating the distance from each point to k clustering centers, and dividing the point to the nearest clustering center, so that k clusters can be formed;
recalculating the mass center of each cluster, namely the mean value;
and fourthly, repeating the steps III until the position of the mass center does not change or the set iteration number is reached.
4. The method for predicting the capacity demand of the taxi at the railway station based on the multiple linear regression as claimed in claim 1, wherein:
and (3) removing repeated orders in the ordering data of the networked car booking passengers, wherein the removing principle is that the taking time in the number of the finished orders is counted by taking 95% as a confidence interval, and when the taking time of all order passengers with the same passenger twice continuous ordering time interval lower than the 95% confidence interval is regarded as the repeated orders.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110488020.8A CN112990610B (en) | 2021-05-06 | 2021-05-06 | Method for predicting taxi capacity demand of railway station based on multiple linear regression |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110488020.8A CN112990610B (en) | 2021-05-06 | 2021-05-06 | Method for predicting taxi capacity demand of railway station based on multiple linear regression |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112990610A CN112990610A (en) | 2021-06-18 |
CN112990610B true CN112990610B (en) | 2021-08-20 |
Family
ID=76336999
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110488020.8A Active CN112990610B (en) | 2021-05-06 | 2021-05-06 | Method for predicting taxi capacity demand of railway station based on multiple linear regression |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112990610B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113340320A (en) * | 2021-08-09 | 2021-09-03 | 江西鹭鹭行科技有限公司 | Route planning method and system combining subway and taxi traveling |
CN114066076B (en) * | 2021-11-22 | 2023-03-28 | 北京白龙马云行科技有限公司 | Network taxi appointment prediction method and device based on multiple tenants |
CN115619133A (en) * | 2022-09-29 | 2023-01-17 | 北京交通大学 | Airport terminal taxi transportation capacity allocation method considering driver decision |
CN116307333B (en) * | 2023-05-17 | 2023-08-08 | 华侨大学 | Method and device for acquiring round trip line and schedule of inter-city customized passenger transport |
CN117541200B (en) * | 2024-01-10 | 2024-03-29 | 福建亿安智能技术股份有限公司 | Project management method and system based on LTC flow |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761585A (en) * | 2014-01-27 | 2014-04-30 | 北京市交通运行监测调度中心 | Airport continuous transport dynamic matching, transport capacity monitoring and early warning and intelligent dispatching method |
CN108830509A (en) * | 2018-07-11 | 2018-11-16 | 宁波大学 | One kind is cruised taxi transport power scale dynamic adjusting method |
CN109671007A (en) * | 2018-12-27 | 2019-04-23 | 沈阳航空航天大学 | Taxi taking difficulty assessment method near a kind of railway station based on multi-dimensional data |
CN111354212A (en) * | 2020-03-11 | 2020-06-30 | 青岛海信网络科技股份有限公司 | Taxi dispatching method, server and dispatching equipment applied to station airport |
CN111553530A (en) * | 2020-04-27 | 2020-08-18 | 华侨大学 | Inter-city network car booking and packing travel capacity prediction and travel recommendation method and system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150032485A1 (en) * | 2013-07-25 | 2015-01-29 | Mark Nelson | Digital method For Providing Transportation Services |
CN110942220B (en) * | 2018-09-25 | 2022-06-28 | 北京嘀嘀无限科技发展有限公司 | Transport capacity scheduling method and device and server |
-
2021
- 2021-05-06 CN CN202110488020.8A patent/CN112990610B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761585A (en) * | 2014-01-27 | 2014-04-30 | 北京市交通运行监测调度中心 | Airport continuous transport dynamic matching, transport capacity monitoring and early warning and intelligent dispatching method |
CN108830509A (en) * | 2018-07-11 | 2018-11-16 | 宁波大学 | One kind is cruised taxi transport power scale dynamic adjusting method |
CN109671007A (en) * | 2018-12-27 | 2019-04-23 | 沈阳航空航天大学 | Taxi taking difficulty assessment method near a kind of railway station based on multi-dimensional data |
CN111354212A (en) * | 2020-03-11 | 2020-06-30 | 青岛海信网络科技股份有限公司 | Taxi dispatching method, server and dispatching equipment applied to station airport |
CN111553530A (en) * | 2020-04-27 | 2020-08-18 | 华侨大学 | Inter-city network car booking and packing travel capacity prediction and travel recommendation method and system |
Non-Patent Citations (1)
Title |
---|
巡游出租车运力规模动态调整回归树模型;叶骐铭等;《宁波大学学报(理工版)》;20200702(第04期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112990610A (en) | 2021-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112990610B (en) | Method for predicting taxi capacity demand of railway station based on multiple linear regression | |
CN109034566B (en) | A kind of intelligent dispatching method and device based on passenger flow above and below bus station | |
Toqué et al. | Short & long term forecasting of multimodal transport passenger flows with machine learning methods | |
Jenelius | Public transport experienced service reliability: Integrating travel time and travel conditions | |
US20170169373A1 (en) | System and method for measuring perceived impact of schedule deviation in public transport | |
Deshpande et al. | The impact of airline flight schedules on flight delays | |
Levinson et al. | Ramp meters on trial: Evidence from the Twin Cities metering holiday | |
Rupp et al. | Does competition influence airline on-time performance | |
WO2018122812A1 (en) | Grading and dynamic pricing method for parking spaces with priority given to short-term parking | |
Bischoff et al. | Simulation-based optimization of service areas for pooled ride-hailing operators | |
DE112018007300T5 (en) | ROUTE GUIDANCE WITH PERCEPTION OF THE SURROUNDINGS | |
CN107564270A (en) | A kind of intelligent public transportation dispatching method for running | |
CN110555990A (en) | effective parking space-time resource prediction method based on LSTM neural network | |
CN108694464A (en) | Passenger flow evacuation method and device | |
Yazici et al. | Modeling taxi drivers’ decisions for improving airport ground access: John F. Kennedy airport case | |
CN110991607B (en) | Subway passenger flow prediction method and device, electronic equipment and storage medium | |
Xiong et al. | Understanding operation patterns of urban online ride-hailing services: A case study of Xiamen | |
CN115953186A (en) | Network appointment demand pattern recognition and short-time demand prediction method | |
CN115409295B (en) | Bus scheduling method based on bottleneck analysis, electronic equipment and storage medium | |
CN114399099A (en) | Method and device for predicting passenger flow of urban rail transit section | |
Pandit et al. | A framework for determining commuter preference along a proposed bus rapid transit corridor | |
CN111915200A (en) | Urban public transport supply and demand state division method based on fine spatial scale of bus sharing rate | |
Attanasio et al. | Real-time fleet management at Ecourier Ltd | |
Agarwal et al. | Labor Supply Decisions of Singaporean Cab Drivers | |
Liu et al. | Understanding urban bus travel time: Statistical analysis and a deep learning prediction |
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 |