CN113393029B - Method and equipment for predicting rail transit passenger flow - Google Patents
Method and equipment for predicting rail transit passenger flow Download PDFInfo
- Publication number
- CN113393029B CN113393029B CN202110651976.5A CN202110651976A CN113393029B CN 113393029 B CN113393029 B CN 113393029B CN 202110651976 A CN202110651976 A CN 202110651976A CN 113393029 B CN113393029 B CN 113393029B
- Authority
- CN
- China
- Prior art keywords
- time
- historical
- target
- station
- probability
- 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 17
- 230000003203 everyday effect Effects 0.000 claims description 8
- 238000009826 distribution Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (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 application discloses a method and equipment for predicting rail transit passenger flow, wherein the method comprises the following steps: determining a target flow mode according to the passenger flow characteristic elements at the future target moment; determining a first probability of entering from each station and exiting from a target station on a rail intersection line, time consumption of people and time consumption average difference according to passenger flow data corresponding to a target flow mode in a preset history time; determining a second probability of inbound from each station at a historical inbound time and outbound from the target station at the historical target time according to average time, average time difference and historical intra-station time consumption between the historical inbound time and the historical target time; and determining the number of people who get out of the target station at the future target moment according to the first probability, the second probability and the historical number of people who get in from the stations at the historical arrival moment, so that a passenger flow prediction value accurate to extremely fine time granularity can be obtained, and the accuracy and efficiency of rail traffic passenger flow prediction are improved.
Description
Technical Field
The application relates to the technical field of rail transit big data processing, in particular to a method and equipment for predicting rail transit passenger flow.
Background
With the rapid development of cities, people have a wider and wider range of motion in urban life, and rail transit plays an increasingly important role in urban traffic. Passenger flow analysis and prediction models based on big data of user riding behaviors are a very important ring of operation management and passenger service of rail transit enterprises, and are also an important demonstration project in intelligent rail traffic development schema. Scientific data are provided for each related department, so that resources and manpower can be effectively distributed, and the safety, comfort and economic benefit of the whole traffic system are improved. The method can provide effective data support and decision basis for related departments to process emergency events, especially when large-scale activities are organized, the prediction of passenger flow can help the rail traffic operation units to adjust and match the corresponding passenger transportation capacity, so that smooth running of the activities can be ensured, and influence on other residents can be reduced.
There are various methods for predicting the traffic flow of the track, and conventional methods include a historical average algorithm, an ARIMA (Autoregressive Integrated Moving Average model) algorithm, an integrated moving average autoregressive model, and the like. Recently, due to the rise of machine learning, there are new algorithms using Long Short-Term Memory (LSTM) and its variant DCRNN (Diffusion Convolutional Recurrent Neural Network ) and the like. For the traditional method, only traffic flow information of traffic flow acquisition points is taken as a reference to give prediction, so that the accuracy is insufficient, the deviation is large, and the method is poor in response to emergency; for the novel machine learning algorithm, because a large amount of computing resources and computing time are needed, and the prediction length of the general machine learning algorithm is short, such as 1 hour, the requirement of traffic prediction on high speed, long time and high efficiency cannot be met.
Therefore, how to improve accuracy and efficiency of rail traffic passenger flow prediction is a technical problem to be solved at present.
Disclosure of Invention
The application provides a method for predicting rail traffic, which is used for solving the technical problems of insufficient precision, larger deviation and low efficiency when the rail traffic is predicted in the prior art, and comprises the following steps:
determining a target flow mode according to the passenger flow characteristic elements at the future target moment;
determining a first probability of entering from each station and exiting from a target station on a rail intersection line, time consumption of people and average difference of time consumption according to passenger flow data corresponding to the target flow mode in a preset history time;
determining a second probability of inbound from each of the sites at the historical inbound time and outbound from the target site at the historical target time according to the average time consumption of the people, the average difference of the time consumption and the historical intra-site time consumption between the historical inbound time and the historical target time;
determining the number of people who are outbound from the target site at the future target time according to the first probability, the second probability and the historical number of people who are inbound from the sites at the historical inbound time;
the passenger flow characteristic elements are determined according to preset dimension characteristics and preset time marks which influence passenger flow, the historical arrival time is the time of arrival from each station in the target flow mode in the preset historical time, and the historical target time is the time corresponding to the future target time every day in the preset historical time.
Preferably, the first probability of entering from each station and exiting from the target station on the rail transit route, the average time consumption of people and the average difference of time consumption are determined according to the passenger flow data corresponding to the target flow mode in the preset history time length, specifically:
determining the first probability according to the ratio of the number of inbound persons from each station to the number of outbound persons from each station and outbound from the target station in the passenger flow volume data;
determining the average time consumption of the people according to the ratio of the total time consumption in the station of the number of the people out of the station to the number of the people out of the station;
and determining the average difference of the time consumption according to the average time consumption of people and the time consumption in the station of entering from each station and exiting from the target station.
Preferably, the second probability is determined according to a first formula, wherein the first formula is specifically:
wherein,for the second probability, σ (Z m ，Z i ) Mu (Z for the time-consuming mean difference m ，Z i ) Time consuming +.>Time consuming within the historic station.
Preferably, the number of people who get out of the target site at the future target time is determined according to the first probability, the second probability and the historical number of people who get in from the sites at the historical time, specifically:
determining all historical outbound people who come in from each station at the historical inbound moment and come out from the target station at the historical target moment according to the first probability, the second probability and the historical inbound people;
summing the historical outbound population from each historical inbound time to the historical target time, and determining the population outbound from the target site at the future target time according to the summation result.
Preferably, the historical number of people who go out is determined according to a formula II, wherein the formula II specifically comprises:
wherein out (Z i ，t x ，t w ) For the historical outbound population, m represents each of the sites, n is the number of sites,for the historical number of people who are standing, P (Z m ，Z i ) For the first probability, Z i Representing the target site i, t x Representing historical arrival times x, t w Representing the historical target moment w.
Correspondingly, the application also provides a prediction device of the rail transit passenger flow, which comprises:
the first determining module is used for determining a target flow mode according to the passenger flow characteristic elements at the future target moment;
the second determining module is used for determining a first probability of entering from each station and exiting from the target station on the rail intersection according to the passenger flow data corresponding to the target flow mode in the preset history time, and average time consumption and average difference of time consumption;
a third determining module, configured to determine a second probability of entering from each of the sites at the historical entering time and exiting from the target site at the historical target time according to the average time consumption of people, the average time consumption and the historical intra-site consumption between the historical entering time and the historical target time;
a fourth determining module configured to determine a number of people who have arrived from the target site at the future target time based on the first probability, the second probability, and the historical number of people who have arrived from each of the sites at the historical arrival time;
the passenger flow characteristic elements are determined according to preset dimension characteristics and preset time marks which influence passenger flow, the historical arrival time is the time of arrival from each station in the target flow mode in the preset historical time, and the historical target time is the time corresponding to the future target time every day in the preset historical time.
Preferably, the second determining module is specifically configured to:
determining the first probability according to the ratio of the number of inbound persons from each station to the number of outbound persons from each station and outbound from the target station in the passenger flow volume data;
determining the average time consumption of the people according to the ratio of the total time consumption in the station of the number of the people out of the station to the number of the people out of the station;
and determining the average difference of the time consumption according to the average time consumption of people and the time consumption in the station of entering from each station and exiting from the target station.
Preferably, the third determining module is specifically configured to:
determining the second probability according to a first formula, wherein the first formula is specifically:
wherein,for the second probability, σ (Z m ，Z i ) Mu (Z for the time-consuming mean difference m ，Z i ) Time-consuming for the person in question,/->Time consuming within the historic station.
Preferably, the fourth determining module is specifically configured to:
determining all historical outbound people who come in from each station at the historical inbound moment and come out from the target station at the historical target moment according to the first probability, the second probability and the historical inbound people;
summing the historical outbound population from each historical inbound time to the historical target time, and determining the population outbound from the target site at the future target time according to the summation result.
Preferably, the fourth determining module is further specifically configured to:
determining the historical number of people who go out according to a formula II, wherein the formula II specifically comprises:
wherein out (Z i ，t x ，t w ) For the historical outbound population, m represents each of the sites, n is the number of sites,for the historical number of people who are standing, P (Z m ，Z i ) For the first probability, Z i Representing the target site i, t x Representing historical arrival times x, t w Representing the historical target moment w.
Compared with the prior art, the application has the following beneficial effects:
by applying the technical scheme, a target flow mode is determined according to the passenger flow characteristic elements at the future target moment; determining a first probability of entering from each station and exiting from a target station on a rail intersection line, time consumption of people and average difference of time consumption according to passenger flow data corresponding to the target flow mode in a preset history time; determining a second probability of inbound from each of the sites at the historical inbound time and outbound from the target site at the historical target time according to the average time consumption of the people, the average difference of the time consumption and the historical intra-site time consumption between the historical inbound time and the historical target time; determining the number of people who are outbound from the target site at the future target time according to the first probability, the second probability and the historical number of people who are inbound from the sites at the historical inbound time; the passenger flow characteristic elements are determined according to preset dimension characteristics and preset time marks affecting passenger flow, the historical arrival time is the arrival time of each station from each station in the target flow mode in the preset historical time, the historical target time is the time corresponding to the future target time every day in the preset historical time, the outbound passenger flow is obtained in a mode of applying probability density in the arrival passenger flow and the flow mode on the basis of combining the passenger flow characteristic elements, and therefore the passenger flow predicted value accurate to extremely fine time granularity can be obtained, accuracy of rail transit passenger flow prediction is improved, dependence on external data is less, and prediction efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for predicting traffic flow according to an embodiment of the present application;
FIG. 2 illustrates a schematic diagram of different flow patterns in an embodiment of the application;
FIG. 3 is a schematic diagram of the probability of entering and exiting a station in an embodiment of the application;
FIG. 4 shows a table of inbound/outbound probability distributions in an embodiment of the application;
FIG. 5 shows a schematic diagram of average time consumption in an embodiment of the application;
FIG. 6 shows a table of average time consumption distribution in an embodiment of the application;
FIG. 7 shows a time-consuming mean deviation diagram in an embodiment of the application;
FIG. 8 shows a time-consuming mean difference distribution table in an embodiment of the application;
FIG. 9 illustrates a time-consuming distribution profile in an embodiment of the application;
fig. 10 shows a schematic structural diagram of a prediction apparatus for traffic flow according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides a method for predicting the traffic flow of rail transit, as shown in fig. 1, comprising the following steps:
step S101, determining a target flow mode according to the passenger flow characteristic elements at the future target time.
Rail transit, i.e. rail traffic, is to predict the passenger flow of the future target moment of departure from the target station at a future preset date, wherein the future target moment is the moment of a certain day (e.g. 13: 00), the passenger flow of each station on the rail traffic line is related to various factors, the passenger flow characteristic elements are determined according to preset dimension characteristics affecting the passenger flow and preset time marks, the preset dimension characteristics comprise date, weather, holidays and activity days, the activity days can comprise large conference holding days, large sports holding days, large singing holding days, large exhibition holding days and the like, and the preset time marks comprise early peak, late peak and daily time.
Optionally, the passenger flow characteristic element is a characteristic element related to the target station or a characteristic element related to the rail transit line. Specifically, when the distance of the rail transit line is longer, the distance of each station is longer, and certain passenger flow characteristic elements such as large-scale sports activities may only affect part of the stations, at this time, the passenger flow characteristic elements are characteristic elements related to the target station; when the distance between the rail crossing lines is short, the passenger flow volume characteristic elements influence the passenger flow volume of the whole rail crossing lines, and the passenger flow volume characteristic elements are characteristic elements related to the rail crossing lines.
In this embodiment, a plurality of preset flow modes, such as a workday and sunny day flow mode, a holiday and overcast and rainy day flow mode, are determined in advance according to different combinations of passenger flow characteristic elements, corresponding relations between different passenger flow characteristic elements and the preset flow modes are established, and a target flow mode is determined from the plurality of preset flow modes according to passenger flow characteristic elements at a future target moment and the corresponding relations.
Those skilled in the art can determine a variety of preset flow patterns according to actual needs.
Step S102, determining a first probability of entering from each station and exiting from the target station on the rail intersection line, and time consumption difference of people average according to passenger flow data corresponding to the target flow mode in a preset history time.
In this embodiment, historical passenger flow data in a preset historical duration may be obtained from a historical database, where the historical passenger flow data may include passenger flow data in multiple traffic modes, passenger flow data corresponding to a target traffic mode is selected from the historical passenger flow data, and a first probability of entering from each station and exiting from the target station on an intersection line, average time consumption and average difference of time consumption are determined according to the passenger flow data.
In order to accurately determine the first probability, average time consumption and average time consumption, in a preferred embodiment of the present application, the first probability, average time consumption and average time consumption of entering from each station and exiting from the target station on the rail transit route are determined according to the passenger flow data corresponding to the target flow pattern in the preset history time length, specifically:
determining the first probability according to the ratio of the number of inbound persons from each station to the number of outbound persons from each station and outbound from the target station in the passenger flow volume data;
determining the average time consumption of the people according to the ratio of the total time consumption in the station of the number of the people out of the station to the number of the people out of the station;
and determining the average difference of the time consumption according to the average time consumption of people and the time consumption in the station of entering from each station and exiting from the target station.
In this embodiment, the number of inbound persons who inbound from each station and the number of outbound persons who inbound from each station and outbound from the target station are determined according to the passenger flow volume data, and the first probability can be determined according to the ratio of the two; the total station consumption time of the number of people out of the station is determined according to the passenger flow data, and the average time consumption can be determined according to the ratio of the total station consumption time to the number of people out of the station; the average difference in time consumption can be determined according to the average time consumption of people and the time consumption in the station from each station to the destination station.
It should be noted that, the solution of the above preferred embodiment is only one specific implementation solution provided by the present application, and other ways of determining the first probability, average time consumption and average difference of time consumption according to the passenger flow data are all within the protection scope of the present application.
In order to accurately determine the time-consuming mean difference, in a preferred embodiment of the present application, the time-consuming mean difference is determined according to a formula four, wherein the formula four is specifically:
wherein x is i Representing the time consumption in the station, N represents the number of time consumption in the station, sigma represents the average difference of the time consumption, and mu represents the average time consumption of the person.
And step S103, determining a second probability of entering from each station at the historical entering moment and exiting from the target station at the historical target moment according to the average time consumption of people, the average time consumption difference and the historical intra-station time consumption between the historical entering moment and the historical target moment.
In this embodiment, the historical arrival time is the arrival time of each station in a target flow mode within a preset historical time, the historical target time is the time corresponding to the future target time every day within the preset historical time, for example, the future target time is 13:00, and the historical target time is also 13:00. The time consumed during the station, i.e. the time consumed in the history station, enters from each history entering moment and exits from the corresponding history target moment. And determining a second probability of entering from each station at the historical entering moment and exiting from the target station at the historical target moment according to the average time consumption, the average time consumption and the time consumption in the historical station.
In order to accurately determine the second probability, in a preferred embodiment of the present application, the second probability is determined according to a formula one, which is specifically:
wherein,for the second probability, σ (Z m ，Z i ) Mu (Z for the time-consuming mean difference m ，Z i ) Time-consuming for the person in question,/->Time consuming within the historic station.
It should be noted that, the solution of the above preferred embodiment is only one specific implementation solution provided by the present application, and other ways of determining the second probability according to average time consumption, average time consumption and historical intra-station time consumption are all within the protection scope of the present application.
Step S104, determining the number of people who get out of the target station at the future target time according to the first probability, the second probability and the historical number of people who get in from each station at each historical arrival time.
In this embodiment, the number of historic inbound persons who are inbound from each station at each historic inbound time is determined according to the passenger flow volume data, and the number of people who are outbound from the target station at the future target time can be determined according to the first probability, the second probability and the historic inbound persons.
In order to accurately determine the number of people who get out of the target site at the future target time, in a preferred embodiment of the present application, the number of people who get out of the target site at the future target time is determined according to the first probability, the second probability and the historical number of people who get in from the target site at the historical arrival time, specifically:
determining all historical outbound people who come in from each station at the historical inbound moment and come out from the target station at the historical target moment according to the first probability, the second probability and the historical inbound people;
summing the historical outbound population from each historical inbound time to the historical target time, and determining the population outbound from the target site at the future target time according to the summation result.
In this embodiment, all the historical outbound people who come in from each station at the historical inbound time and come out from the target station at the historical target time are determined according to the first probability, the second probability and the historical inbound people, and the historical outbound people from each historical inbound time to the historical target time are summed, and then the summed result is used as the people who come out from the target station at the future target time.
It should be noted that the solution of the above preferred embodiment is only one specific implementation solution provided by the present application, and other ways of determining the number of people who get out of the target site at the future target time according to the first probability, the second probability and the historical number of people who get in the target site are all within the scope of the present application.
In order to accurately determine the number of historical outbound persons, in a preferred embodiment of the present application, the number of historical outbound persons is determined according to a formula II, wherein the formula II specifically includes:
wherein out (Z i ，t x ，t w ) For the historical outbound population, m represents each of the sites, n is the number of sites,for the historical number of people who are standing, P (Z m ，Z i ) For the first probability, Z i Representing the target site i, t x Representing historical arrival times x, t w Representing the historical target moment w.
It should be noted that, the scheme of the above preferred embodiment is only one specific implementation scheme provided by the present application, and other ways of determining the historical attendance according to the first probability, the second probability and the historical attendance all belong to the protection scope of the present application.
In order to accurately determine the number of people who are out of a target site at a future target time, in a preferred embodiment of the present application, the number of people who are out of the target site at the future target time is determined according to the formula three, which is specifically:
wherein out (Z i ，t w ) And the number of people who are out of the target site for the future target moment.
By applying the technical scheme, a target flow mode is determined according to the passenger flow characteristic elements at the future target moment; determining a first probability of entering from each station and exiting from a target station on a rail intersection line, time consumption of people and average difference of time consumption according to passenger flow data corresponding to the target flow mode in a preset history time; determining a second probability of inbound from each of the sites at the historical inbound time and outbound from the target site at the historical target time according to the average time consumption of the people, the average difference of the time consumption and the historical intra-site time consumption between the historical inbound time and the historical target time; determining the number of people who are outbound from the target site at the future target time according to the first probability, the second probability and the historical number of people who are inbound from the sites at the historical inbound time; the passenger flow characteristic elements are determined according to preset dimension characteristics and preset time marks affecting passenger flow, the historical arrival time is the arrival time of each station from each station in the target flow mode in the preset historical time, the historical target time is the time corresponding to the future target time every day in the preset historical time, the outbound passenger flow is obtained in a mode of applying probability density in the arrival passenger flow and the flow mode on the basis of combining the passenger flow characteristic elements, and therefore the passenger flow predicted value accurate to extremely fine time granularity can be obtained, accuracy of rail transit passenger flow prediction is improved, dependence on external data is less, and prediction efficiency is improved.
In order to further explain the technical idea of the application, the technical scheme of the application is described with specific application scenarios.
The embodiment of the application provides a method for predicting the traffic flow of rail transit, which comprises the following steps:
and (I) acquiring passenger flow data in a preset historical time.
(two) traffic pattern
Based on passenger flow data in a preset history time length, dimensional characteristics such as date, weather, holiday and the like are added, and time (morning and evening peak and daily time) marks are introduced, so that different flow mode groups are constructed, as shown in fig. 2.
(III) probability of entering and exiting station
P (Zi, zj) is the secondary station Z i Further station Z j Probability of outbound, e.g.Fig. 3 shows a schematic view of the probability of entering and exiting a station.
Calculating slave Z in different traffic patterns i Inbound and slave station Z j Probability of outbound:
wherein:
N Zi for an entry station Z within a preset history period i Is the number of people who enter the station;
M(Z i ，Z j ) For a slave station Z within a preset history period i Inbound and slave station Z j The number of people who are out of the station.
As shown in fig. 4, is an entry and exit probability distribution table.
(IV) Stroke time consuming distribution
1. Average time consumption
μ(Z i ，Z j ): slave station Z i To station Z j The average time consumption of (2) is shown in fig. 5 as a schematic diagram of average time consumption.
Calculating slave Z in different traffic patterns i Inbound and slave station Z j Average time spent outbound:
wherein:
sum (time) slave station Z i Inbound and slave station Z j Sum of time consumption of all outbound people;
M(Z i ，Z j ): slave station Z within preset history time i Inbound and slave station Z j The number of people who are out of the station.
An average time consumption distribution table is shown in fig. 6.
2. Time-consuming average difference
σ(Z i ，Z j ): slave station Z i Inbound and slave station Z j The average difference of the outbound time-consuming distributions is shown in fig. 7 as a time-consuming average difference diagram.
Wherein x is i And (3) representing time consumption in each station, wherein N represents the number of time consumption in each station, sigma represents the average difference of the time consumption, and mu represents the average time consumption of the person.
A time-consuming mean-deviation distribution table is shown in fig. 8.
3. Time-consuming distribution features
By analyzing the time-consuming distribution, it was found that the normal distribution was substantially conformed, as shown in fig. 9.
Fifth, outbound traffic prediction
The target flow rate mode is determined according to the passenger flow rate characteristic element of the future 'certain moment w', and each parameter in the following steps is determined based on passenger flow rate data corresponding to the target flow rate mode.
Wherein,the probability of coming in from station m at time x and coming out from station i at time w is the second probability;
σ(Z m ，Z i ) Time consumption for the secondary station m to enter and the secondary station i to exit is poor;
μ(Z m ，Z i ) People who enter from station m and exit from station i are time-consuming;
for from time t x By time t w Duration, namely time consumption in the history station;
m is more than or equal to 1 and less than or equal to n, wherein n is the number of stations.
Wherein out (Z i ，t x ，t w ) The historical outbound population is the population that all the stations come in from each station at the moment x and come out from the station i at the moment w;
to at time t x The number of people who get into the station from station m, namely the historical number of people who get into the station;
P(Z m ，Z i ) The probability of being the secondary station m going in and the secondary station i going out, namely the first probability;
Z i representing the target site i;
t x representing historical arrival times x, t w Represents the historical target time w, time x is time t x Instant t at instant w w 。
Wherein out (Z i ，t w ) The number of people who are outbound from "station i" for a future "certain moment w", i.e. the number of people who are outbound from the target station at the future target moment.
Corresponding to the method for predicting the traffic flow in the embodiment of the present application, the embodiment of the present application further provides a device for predicting the traffic flow, as shown in fig. 10, where the device includes:
a first determining module 201, configured to determine a target traffic pattern according to a feature factor of a passenger traffic at a future target time;
a second determining module 202, configured to determine a first probability of entering from each station and exiting from the target station on the rail transit line according to the passenger flow data corresponding to the target flow pattern in the preset history duration, average time consumption and average difference of time consumption;
a third determining module 203, configured to determine a second probability of entering from each of the sites at the historical entering time and exiting from the target site at the historical target time according to the average time consumption of people, the average time consumption and the historical intra-site consumption between the historical entering time and the historical target time;
a fourth determining module 204, configured to determine, according to the first probability, the second probability, and each of the historical arrival times, a number of people that have arrived from the target site at the future target time, from a historical number of people that have arrived from each of the sites;
the passenger flow characteristic elements are determined according to preset dimension characteristics and preset time marks which influence passenger flow, the historical arrival time is the time of arrival from each station in the target flow mode in the preset historical time, and the historical target time is the time corresponding to the future target time every day in the preset historical time.
In a specific application scenario of the present application, the second determining module 202 is specifically configured to:
determining the first probability according to the ratio of the number of inbound persons from each station to the number of outbound persons from each station and outbound from the target station in the passenger flow volume data;
determining the average time consumption of the people according to the ratio of the total time consumption in the station of the number of the people out of the station to the number of the people out of the station;
and determining the average difference of the time consumption according to the average time consumption of people and the time consumption in the station of entering from each station and exiting from the target station.
In a specific application scenario of the present application, the third determining module 203 is specifically configured to:
determining the second probability according to a first formula, wherein the first formula is specifically:
wherein,for the second probability, σ (Z m ，Z i ) For the consumption ofAverage difference in time, mu (Z) m ，Z i ) Time-consuming for the person in question,/->Time consuming within the historic station.
In a specific application scenario of the present application, the fourth determining module 204 is specifically configured to:
determining all historical outbound people who come in from each station at the historical inbound moment and come out from the target station at the historical target moment according to the first probability, the second probability and the historical inbound people;
summing the historical outbound population from each historical inbound time to the historical target time, and determining the population outbound from the target site at the future target time according to the summation result.
In a specific application scenario of the present application, the fourth determining module 204 is further specifically configured to:
determining the historical number of people who go out according to a formula II, wherein the formula II specifically comprises:
wherein out (Z i ，t x ，t w ) For the historical outbound population, m represents each of the sites, n is the number of sites,for the historical number of people who are standing, P (Z m ，Z i ) For the first probability, Z i Representing the target site i, t x Representing historical arrival times x, t w Representing the historical target moment w.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be appreciated by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (2)
1. A method for predicting traffic flow, the method comprising:
determining a target flow mode according to the passenger flow characteristic elements at the future target moment;
determining a first probability of entering from each station and exiting from a target station on a rail intersection line, time consumption of people and average difference of time consumption according to passenger flow data corresponding to the target flow mode in a preset history time;
specifically, the first probability is determined according to the ratio of the number of inbound persons from each station to the number of outbound persons from each station and from the target station in the passenger flow volume data; determining the average time consumption of the people according to the ratio of the total time consumption in the station of the number of the people out of the station to the number of the people out of the station; determining the average difference of the time consumption according to the average time consumption of people and the time consumption in stations which enter from each station and exit from the target station;
determining a second probability of inbound from each of the sites at the historical inbound time and outbound from the target site at the historical target time according to the average time consumption of the people, the average difference of the time consumption and the historical intra-site time consumption between the historical inbound time and the historical target time;
determining the second probability according to equation one, in particular
Wherein,for the second probability, σ (Zm, zi) is the average difference in time consumption, μ (Zm, zi) is the average time consumption of the person, +.>Time consuming within the historic station;
determining the number of people who are outbound from the target site at the future target time according to the first probability, the second probability and the historical number of people who are inbound from the sites at the historical inbound time;
determining all historical outbound people who get in from each station at the historical inbound moment and get out from the target station at the historical target moment according to the first probability, the second probability and the historical inbound people; summing the historical outbound population from each historical inbound time to the historical target time, and determining the population outbound from the target site at the future target time according to the summation result;
determining the historical number of people who go out according to a formula II, wherein the formula II specifically comprises:
where out (Zi, tx, tw) is the historical number of outbound persons, m represents each of the sites, n is the number of sites,for the historical number of inbound persons, P (Zm, zi) is the first probability, zi represents the target site i, tx represents a historical inbound time x, and tw represents the historical target time w;
the passenger flow characteristic elements are determined according to preset dimension characteristics and preset time marks which influence passenger flow, the historical arrival time is the time of arrival from each station in the target flow mode in the preset historical time, and the historical target time is the time corresponding to the future target time every day in the preset historical time.
2. A prediction apparatus of traffic flow, the apparatus comprising:
the first determining module is used for determining a target flow mode according to the passenger flow characteristic elements at the future target moment;
the second determining module is used for determining a first probability of entering from each station and exiting from the target station on the rail intersection according to the passenger flow data corresponding to the target flow mode in the preset history time, and average time consumption and average difference of time consumption;
a third determining module, configured to determine a second probability of entering from each of the sites at the historical entering time and exiting from the target site at the historical target time according to the average time consumption of people, the average time consumption and the historical intra-site consumption between the historical entering time and the historical target time;
a fourth determining module configured to determine a number of people who have arrived from the target site at the future target time based on the first probability, the second probability, and the historical number of people who have arrived from each of the sites at the historical arrival time;
the passenger flow characteristic elements are determined according to preset dimension characteristics and preset time marks which influence passenger flow, the historical arrival time is the arrival time of each station in the target flow mode in the preset historical time, and the historical target time is the time corresponding to the future target time every day in the preset historical time;
the second determining module is specifically configured to determine the first probability according to a ratio of a number of people who enter from each station to a number of people who enter from each station and exit from the target station in the passenger flow volume data; determining the average time consumption of the people according to the ratio of the total time consumption in the station of the number of the people out of the station to the number of the people out of the station; determining the average difference of the time consumption according to the average time consumption of people and the time consumption in stations which enter from each station and exit from the target station;
determining the second probability according to equation one, in particular
Wherein,for the second probability, σ (Zm, zi) is the average difference in time consumption, μ (Zm, zi) is the average time consumption of the person, +.>Time consuming within the historic station;
the fourth determining module is specifically configured to determine, according to the first probability, the second probability, and the historical inbound population, all historical outbound population inbound from each site at the historical inbound time and outbound from the target site at the historical target time;
summing the historical outbound population from each historical inbound time to the historical target time, and determining the population outbound from the target site at the future target time according to the summation result;
determining the historical number of people who go out according to a second formula, wherein the second formula is specifically as follows
Where out (Zi, tx, tw) is the historical number of outbound persons, m represents each of the sites, n is the number of sites,for the historical number of inbound persons, P (Zm, zi) is the first probability, zi represents the target station i, tx represents the historical inbound time x, and tw represents the historical target time w.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110651976.5A CN113393029B (en) | 2021-06-11 | 2021-06-11 | Method and equipment for predicting rail transit passenger flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110651976.5A CN113393029B (en) | 2021-06-11 | 2021-06-11 | Method and equipment for predicting rail transit passenger flow |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113393029A CN113393029A (en) | 2021-09-14 |
| CN113393029B true CN113393029B (en) | 2023-11-17 |
Family
ID=77620407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110651976.5A Active CN113393029B (en) | 2021-06-11 | 2021-06-11 | Method and equipment for predicting rail transit passenger flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113393029B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808184B (en) * | 2024-02-29 | 2024-05-10 | 成都汇辙科技有限公司 | Urban rail transit service management system driven by full production elements |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485359A (en) * | 2016-10-13 | 2017-03-08 | 东南大学 | A kind of urban track traffic section passenger flow estimation method based on train schedule |
| WO2020019976A1 (en) * | 2018-07-27 | 2020-01-30 | 阿里巴巴集团控股有限公司 | Expected duration interval determining method and apparatus, and travel verification method and apparatus |
| CN111582605A (en) * | 2020-05-21 | 2020-08-25 | Oppo广东移动通信有限公司 | Method and device for predicting destination site, electronic equipment and storage medium |
| CN112488388A (en) * | 2020-11-30 | 2021-03-12 | 佳都新太科技股份有限公司 | Outbound passenger flow prediction method and device based on probability distribution |
| CN112686417A (en) * | 2019-10-18 | 2021-04-20 | 深圳先进技术研究院 | Subway large passenger flow prediction method and system and electronic equipment |
-
2021
- 2021-06-11 CN CN202110651976.5A patent/CN113393029B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485359A (en) * | 2016-10-13 | 2017-03-08 | 东南大学 | A kind of urban track traffic section passenger flow estimation method based on train schedule |
| WO2020019976A1 (en) * | 2018-07-27 | 2020-01-30 | 阿里巴巴集团控股有限公司 | Expected duration interval determining method and apparatus, and travel verification method and apparatus |
| CN112686417A (en) * | 2019-10-18 | 2021-04-20 | 深圳先进技术研究院 | Subway large passenger flow prediction method and system and electronic equipment |
| CN111582605A (en) * | 2020-05-21 | 2020-08-25 | Oppo广东移动通信有限公司 | Method and device for predicting destination site, electronic equipment and storage medium |
| CN112488388A (en) * | 2020-11-30 | 2021-03-12 | 佳都新太科技股份有限公司 | Outbound passenger flow prediction method and device based on probability distribution |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113393029A (en) | 2021-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Goldberg et al. | A simulation model for evaluating a set of emergency vehicle base locations: Development, validation, and usage | |
| CN103632212B (en) | System and method for predicating time-varying user dynamic equilibrium network-evolved passenger flow | |
| Chen et al. | Uncertainty in urban mobility: Predicting waiting times for shared bicycles and parking lots | |
| CN109034566B (en) | A kind of intelligent dispatching method and device based on passenger flow above and below bus station | |
| CN102044149B (en) | City bus operation coordinating method and device based on time variant passenger flows | |
| CN110599767A (en) | Long-term and short-term prediction method based on network taxi appointment travel demands | |
| CN109872535A (en) | A kind of current prediction technique of wisdom traffic, device and server | |
| Tang et al. | A data-driven timetable optimization of urban bus line based on multi-objective genetic algorithm | |
| CN113920769B (en) | Intelligent scheduling list generation method based on public transportation multi-source data analysis | |
| Li et al. | Deep learning based parking prediction on cloud platform | |
| CN110555990A (en) | effective parking space-time resource prediction method based on LSTM neural network | |
| Haghani et al. | Real-time emergency response fleet deployment: concepts, systems, simulation & case studies | |
| CN110444008B (en) | Vehicle scheduling method and device | |
| CN110046824B (en) | Operation time interval dividing method for urban public transport line | |
| CN113723659A (en) | Urban rail transit full-scene passenger flow prediction method and system | |
| CN111507762A (en) | Urban taxi demand prediction method based on multi-task co-prediction neural network | |
| CN113393029B (en) | Method and equipment for predicting rail transit passenger flow | |
| CN114037158A (en) | Passenger flow prediction method based on OD path and application method | |
| CN111882097A (en) | Vehicle maintenance personnel scheduling method and system | |
| Liu et al. | Understanding urban bus travel time: Statistical analysis and a deep learning prediction | |
| CN114118593A (en) | Population mobility prediction method and power grid load prediction method thereof | |
| CN112819228A (en) | Task processing method and device, storage medium and electronic equipment | |
| Brar et al. | Ensuring service fairness in taxi fleet management | |
| Rusca et al. | Algorithm for traffic allocation when are developed park and ride facilities | |
| Tu et al. | Analysis and forecast of passenger flow based on public transportation IC card and GPS data |
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 |