CN112488388B - Outbound passenger flow prediction method and device based on probability distribution - Google Patents

Outbound passenger flow prediction method and device based on probability distribution Download PDF

Info

Publication number
CN112488388B
CN112488388B CN202011371303.6A CN202011371303A CN112488388B CN 112488388 B CN112488388 B CN 112488388B CN 202011371303 A CN202011371303 A CN 202011371303A CN 112488388 B CN112488388 B CN 112488388B
Authority
CN
China
Prior art keywords
station
time
outbound
probability
arrival
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
Application number
CN202011371303.6A
Other languages
Chinese (zh)
Other versions
CN112488388A (en
Inventor
曾明
丁保剑
秦伟
李逸帆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
PCI Technology Group Co Ltd
PCI Technology and Service Co Ltd
Original Assignee
PCI Technology Group Co Ltd
PCI Technology and Service Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by PCI Technology Group Co Ltd, PCI Technology and Service Co Ltd filed Critical PCI Technology Group Co Ltd
Priority to CN202011371303.6A priority Critical patent/CN112488388B/en
Publication of CN112488388A publication Critical patent/CN112488388A/en
Application granted granted Critical
Publication of CN112488388B publication Critical patent/CN112488388B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/219—Managing data history or versioning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Computational Linguistics (AREA)
  • Marketing (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Train Traffic Observation, Control, And Security (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The embodiment of the application discloses an outbound passenger flow prediction method and device based on probability distribution. According to the technical scheme provided by the embodiment of the application, the passengers in the stations of the line network are counted based on the given prediction time period by acquiring the real-time passenger flow operation data of the line network, and the probability distribution information of the inter-station operation time of any two stations is counted based on the historical passenger flow operation data. And further determining the arrival probability of the time when the passengers in the station arrive at each outbound station based on the inter-station running time probability distribution information, determining the arrival probability of the station when the passengers in the station arrive at each outbound station, and calculating the outbound passenger flow of the predicted station in the predicted time period based on the given predicted time period, the predicted station and the corresponding number of the passengers in the station by using the arrival probability of the time and the arrival probability of the station. By adopting the technical means, the influence of different arrival time, arrival stations and individual behavior habits of passengers on the outbound passenger flow prediction can be combined, and more accurate outbound passenger flow prediction is realized.

Description

Outbound passenger flow prediction method and device based on probability distribution
Technical Field
The embodiment of the application relates to the technical field of intelligent traffic, in particular to a method and a device for predicting outbound passenger flow based on probability distribution.
Background
As an important transportation trip mode, the subway brings great convenience to people when people go out along with the rapid development of urban public transport, and also brings great development and promotion effects to the economy of the country and the region. As more people ride on the subway, the accompanying problems are increased. How to combine the subway and the passenger, realize giving the passenger more reasonable trip route selection, avoid traffic jams, extract and deploy the problem such as website security measure, become the problem of subway operation primary consideration, and along with the current big data, machine learning, artificial intelligence's etc. quick development, how to use these technologies deeply to subway trade helping future city safety trip, also become social's focus.
Currently, in a subway operation scene, a main outbound passenger flow prediction method includes prediction based on a time series method and prediction based on a machine learning algorithm and a deep learning algorithm. The prediction methods are influenced by different arrival time, arrival stations and individual behavior habits of passengers, and the accuracy of the outbound passenger flow prediction is relatively low.
Disclosure of Invention
The method and the device for predicting the outbound passenger flow based on the probability distribution can predict the outbound passenger flow by combining the probability distribution of the arrival time and the probability distribution of the arrival site, improve the accuracy of predicting the outbound passenger flow and ensure the reliability of predicting the outbound passenger flow.
In a first aspect, an embodiment of the present application provides an outbound passenger flow prediction method based on probability distribution, including:
the method comprises the steps of obtaining real-time passenger flow operation data of a line network, counting passengers in stations of the line network based on a given prediction time period, and counting probability distribution information of the inter-station operation time of any two stations based on historical passenger flow operation data;
determining time thresholds of the stations for passengers to reach each outbound station of a network based on the inter-station running time probability distribution information, and determining the arrival probability of the stations for the passengers to reach each outbound station based on the comparison of the time thresholds and the predicted time period, wherein the time thresholds comprise the fastest arrival time and the slowest arrival time;
according to historical passenger flow operation data, first in-and-out probability distribution information of each od pair in an out-line network and second in-and-out probability distribution information of each od pair of the in-station passengers are counted, and the station arrival probability of the in-station passengers reaching each out-of-station is determined by using the first in-and-out probability distribution information, the second in-and-out probability distribution information or the current riding record of the in-station passengers based on the passenger types of the in-station passengers, wherein the passenger types comprise new users and old users;
and calculating the outbound passenger flow of the predicted station in the predicted time period by using the time arrival probability and the station arrival probability based on the given predicted time period, the predicted station and the corresponding number of passengers in the station.
Further, statistics of probability distribution information of the inter-station running time of any two stations based on historical passenger flow running data includes:
all od pairs of a wire network are obtained based on historical passenger flow operation data, and the inter-station operation time of any two stations corresponding to each passenger is counted based on each od pair;
and counting the number of arriving people of any two stations in each time period based on the inter-station running time, and determining the inter-station running time probability distribution information of any two stations according to the number of arriving people.
Further, determining the probability distribution information of the inter-station running time of any two stations according to the number of the arriving people, which comprises the following steps:
and calculating the corresponding inter-station running time probability according to the number of the arriving people, and extracting the inter-station running time probability with the set number from large to small as the corresponding inter-station running time probability distribution information.
Further, determining a time threshold for the in-station passenger to reach each outbound site of the net based on the inter-site runtime probability distribution information includes:
extracting the arrival time information of passengers in the station, determining the arrival stations of the passengers in each station, and matching the arrival stations with the outbound stations of the line network;
and inquiring the probability distribution of the inter-station running time based on the inbound station and the outbound station, and determining the fastest arrival time and the slowest arrival time of the passengers in the station to arrive at the outbound station.
Further, determining the arrival probability of the passengers arriving at each outbound station based on the time threshold and the predicted time period includes:
comparing the fastest arrival time with the slowest arrival time, and if the fastest arrival time and/or the slowest arrival time are/is in the prediction time, determining the corresponding time probability of the passengers in the station to arrive at the outbound station;
and counting the time probability, and determining the arrival probability of the passengers in each station at the time of arriving at each outbound station.
Further, determining the corresponding time probability of the in-station passenger arriving at the outbound site includes:
circularly taking out the inter-station running time from the corresponding inter-station running time probability distribution information, and calculating to obtain corresponding arrival time based on the arrival time information of passengers in the stations and the inter-station running time;
and comparing the arrival time with the prediction time period, and if the arrival time is in the prediction time period, extracting the corresponding inter-station running time probability as a time probability of the passengers in the station arriving at the outbound station.
Further, counting the time probability, and determining the arrival probability of the time when each in-station passenger arrives at each outbound station includes:
and performing superposition statistics on the time probabilities determined by the inter-station running times in the inter-station running time probability distribution information, determining the arrival probability of the time when a passenger in the station arrives at an outbound station, circulating each outbound station and each passenger in the station, and determining the arrival probability of the time when the passenger in the station arrives at each outbound station.
Further, determining a station arrival probability of the in-station passenger reaching each outbound station based on the passenger type of the in-station passenger by using the first in-and-out probability distribution information, the second in-and-out probability distribution information or the current-day riding record of the in-station passenger, wherein the passenger type comprises a new user and an old user, and the method comprises the following steps:
if the passenger type of the passenger in the station is a new user, determining the station arrival probability of the corresponding passenger in the station to arrive at each outbound station by using the first inbound and outbound probability distribution information;
and if the passenger type of the passengers in the station is old users, determining the corresponding station arrival probability of the passengers in the station to arrive at each outbound station by using the riding record of the passengers in the station on the same day, the second inbound and outbound probability distribution information or the first inbound and outbound probability distribution information.
Further, if the passenger type of the in-station passenger is a new user, determining the station arrival probability of the corresponding in-station passenger arriving at each outbound station by using the first inbound and outbound probability distribution information includes:
and inquiring first probability information of the corresponding od pairs based on the first station in-and-out probability distribution information, and determining station arrival probability of the corresponding in-station passengers to reach each outbound station according to the first probability information.
Further, if the passenger type of the in-station passenger is an old user, determining a station arrival probability that the corresponding in-station passenger arrives at each outbound station by using the in-station passenger's in-day riding record, the second in-and-out probability distribution information, or the first in-and-out probability distribution information, includes:
if the arrival time of the passengers in the station is greater than or equal to the designated time point, comparing the corresponding stations out of the station according to the daily riding record of the passengers in the station, and determining the station arrival probability of the corresponding passengers in the station to arrive at each station out of the station;
if the arrival time of the passengers in the station is smaller than the appointed time point, judging whether the corresponding outbound station appears in a historical outbound list of the passengers in the station, if so, inquiring second probability information of a corresponding od pair based on the first probability distribution information of the arrival station, determining the arrival probability of the corresponding passengers in the station to arrive at each outbound station according to the second probability information, if not, inquiring first probability information of the corresponding od pair based on the first probability distribution information of the arrival station, and determining the arrival probability of the corresponding passengers in the station to arrive at each outbound station according to the first probability information.
Further, the outbound passenger flow calculation formula of the predicted station in the predicted time period is as follows:
Figure BDA0002806790130000041
among them, predict exit_number For the predicted outbound passenger flow of the station in the predicted time period, N is the number of passengers in the station, time _ arive _ prob i For the time-of-arrival probability of the ith in-station passenger arriving at the predicted site, station _ array _ prob i The station arrival probability for the ith said in-station passenger to arrive at said predicted station.
In a second aspect, an embodiment of the present application provides an outbound passenger flow prediction apparatus based on probability distribution, including:
the statistical module is used for acquiring the real-time passenger flow operation data of the line network, counting passengers in stations of the line network based on a given prediction time period, and counting the probability distribution information of the inter-station operation time of any two stations based on historical passenger flow operation data;
a first probability calculation module, configured to determine, based on the inter-station operating time probability distribution information, a time threshold for the in-station passenger to reach each outbound station of the network, and determine, based on comparison between the time threshold and the prediction time period, an arrival probability at a time when the in-station passenger reaches each outbound station, where the time threshold includes a fastest arrival time and a slowest arrival time;
the second probability calculation module is used for counting first in-and-out probability distribution information of each od pair in an out-line network and second in-and-out probability distribution information of each od pair of the in-station passengers according to historical passenger flow operation data, and determining station arrival probability of the in-station passengers reaching each out-of-station based on passenger types of the in-station passengers by using the first in-and-out probability distribution information, the second in-and-out probability distribution information or the current-day riding records of the in-station passengers, wherein the passenger types comprise new users and old users;
and the prediction module is used for calculating the outbound passenger flow of the predicted station in the prediction time period by using the time arrival probability and the station arrival probability based on the given prediction time period, the predicted station and the corresponding number of passengers in the station.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a probability distribution based outbound passenger flow prediction method as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a storage medium containing computer-executable instructions for performing the method for probability distribution based outbound passenger flow prediction according to the first aspect when executed by a computer processor.
According to the method and the system, the real-time passenger flow operation data of the network are obtained, the passengers in the stations of the network are counted based on the given prediction time period, and the probability distribution information of the inter-station operation time of any two stations is counted based on the historical passenger flow operation data. And further determining the arrival probability of the time when the passengers in the station arrive at each outbound station based on the inter-station running time probability distribution information, determining the arrival probability of the station when the passengers in the station arrive at each outbound station, and calculating the outbound passenger flow of the predicted station in the predicted time period based on the given predicted time period, the predicted station and the corresponding number of the passengers in the station by using the arrival probability of the time and the arrival probability of the station. By adopting the technical means, the influence of different arrival time, arrival stations and individual behavior habits of passengers on the outbound passenger flow prediction can be combined, more accurate outbound passenger flow prediction is realized, and the reliability of the outbound passenger flow prediction is guaranteed.
Drawings
Fig. 1 is a flowchart of an outbound passenger flow prediction method based on probability distribution according to an embodiment of the present application;
FIG. 2 is a flow chart of outbound passenger flow prediction based on time of arrival probability and station arrival probability according to an embodiment of the present application;
FIG. 3 is a flowchart of determining probability distribution information of inter-station operation time in one embodiment of the present application;
FIG. 4 is a flowchart illustrating inter-station runtime probability calculation according to a first embodiment of the present disclosure;
FIG. 5 is a flowchart of time threshold determination in the first embodiment of the present application;
fig. 6 is a flowchart of time arrival probability determination in the first embodiment of the present application;
fig. 7 is a flowchart of determining a station arrival probability in the first embodiment of the present application;
fig. 8 is a schematic structural diagram of an outbound passenger flow prediction apparatus based on probability distribution according to a second embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The method for predicting the outbound passenger flow based on the probability distribution aims to predict the outbound passenger flow according to different inbound time, inbound stations and influences of individual passenger behavior habits, and predict the outbound passenger flow according to the probability distribution by determining the arrival probability and the station arrival probability of each passenger corresponding to each station, so that the accuracy of the outbound passenger flow prediction is improved. Compared with the traditional outbound passenger flow prediction method, the method generally adopts a time series method for prediction or a machine learning and deep learning algorithm for prediction when the outbound passenger flow prediction is carried out. When using conventional traffic prediction models for outbound traffic prediction, the models typically assume that traffic rules are recurring within a statistical time frame, and are not considered from inbound and outbound relationships. Because all passengers coming out of the subway consist of passengers coming in, the passengers coming in from the same station have different time for entering the station and different time for exiting the station and corresponding time for exiting the station, and therefore, the behavior of passengers coming in the station has great influence on the passengers exiting the station in a certain sense. In addition, the existing outbound passenger flow prediction model is not considered from the perspective of the individual passengers. Outbound passenger flow is a behavior composed of a plurality of individual passengers, and the specific behavior habits of different passengers are different. Different individual behaviors also directly result in different numbers of people leaving each site at different time periods. Obviously, for different arrival times, arrival stations and individual behavior habits of passengers, the outbound passenger flow is directly influenced. Therefore, the outbound passenger flow prediction based on the probability distribution is provided to solve the problem of accuracy of the existing outbound passenger flow prediction.
The first embodiment is as follows:
fig. 1 is a flowchart of an outbound passenger flow prediction method based on probability distribution according to an embodiment of the present invention, where the outbound passenger flow prediction method based on probability distribution provided in this embodiment may be executed by an outbound passenger flow prediction device based on probability distribution, the outbound passenger flow prediction device based on probability distribution may be implemented in software and/or hardware, and the outbound passenger flow prediction device based on probability distribution may be formed by two or more physical entities or may be formed by one physical entity. Generally, the outbound passenger flow prediction device based on probability distribution can be a passenger flow operation background server, a computer, a server host and other computing devices.
The following description will be given taking the probability distribution-based outbound passenger flow prediction apparatus as an example of a main body that executes the probability distribution-based outbound passenger flow prediction method. Referring to fig. 1, the outbound passenger flow prediction method based on probability distribution specifically includes:
s110, obtaining real-time passenger flow operation data of the line network, counting passengers in stations of the line network based on a given prediction time period, and counting probability distribution information of inter-station operation time of any two stations based on historical passenger flow operation data.
In the embodiment of the application, considering the influence of different inbound stops, inbound time and individual behavior of passengers on outbound passenger flow, referring to fig. 2, according to the embodiment of the application, by counting passengers in a network stop, the calculation of the time arrival probability and the stop arrival probability of each stop corresponding to each inbound passenger is further performed according to the inter-stop running time probability distribution information and the classification of the passengers, and then the outbound passenger flow prediction is performed based on the time arrival probability and the stop arrival probability, so that the outbound passenger flow prediction based on probability distribution in the embodiment of the application is completed.
Specifically, before the time arrival probability and the station arrival probability are calculated, statistics of passengers in the station is performed by acquiring network passenger flow operation data (such as passenger card swiping information for entering and exiting the station). On the basis of a given prediction time period, assuming that the prediction time period is a 10-minute interval time period of '2019-01-2108: 00: 00-2019-01-2108: 10: 00', firstly screening all passengers who enter the station on the same day according to the wire network passenger flow operation data by intercepting the starting time and the ending time of the time period, and if the time of leaving the station of a certain passenger is more than or equal to '2019-01-2108: 00: 00', determining the certain passenger as the passenger in the station; or if the inbound time of a passenger is less than '2019-01-2108: 10: 00' and the outbound behavior does not occur, determining that the passenger is the in-station passenger. Through the steps, passengers of the outbound network who are in the stations in real time and have not been outbound in a given prediction time period can be counted.
And on the other hand, the probability distribution information of the inter-station running time of any two stations is calculated to be used for calculating the arrival probability of the subsequent time. Referring to fig. 3, the process of determining the inter-station runtime probability distribution information includes:
s1101, acquiring all od pairs of a wire network based on historical passenger flow operation data, and counting the inter-station operation time of any two stations corresponding to each passenger based on each od pair;
s1102, counting the number of arriving people of any two stations in each time period based on the inter-station running time, and determining the inter-station running time probability distribution information of any two stations according to the number of arriving people.
The subway train passenger train is characterized in that the train is controlled by a controller, wherein the controller is used for controlling the train to run, and the controller is used for controlling the train to run. The arrival time at the same station B may be different for different passengers from the same station a. For a given predicted time period, a passenger may arrive any minute or even any second within this predicted time period, but the probability of arrival is not the same for different time periods. Therefore, statistics are carried out through historical passenger flow operation data of the network so as to determine probability distribution information of the operation time between any two stations. Specifically, referring to fig. 4, based on historical passenger flow operation data of the network, all od pairs (traffic volume) information is obtained according to all stations (including uplink stations and downlink stations) of the network. And acquiring the station entering and exiting information of each passenger of the wire network according to the od pair information, wherein the station entering and exiting information specifically comprises core information such as station entering, station entering time, station exiting time and the like. Furthermore, according to the obtained information of the station entering station, the station entering time, the station leaving station and the station leaving time of the passengers, the riding time of each passenger between any two stations can be calculated. Dividing the riding time into specific time periods (taking minutes as a unit) according to the counted riding time of each passenger between any two stations, so as to obtain the number distribution of arriving people between any two stations in different time periods. Further, calculating the corresponding inter-station running time probability according to the number of the arriving people, and extracting the inter-station running time probability with the set number from large to small as the corresponding inter-station running time probability distribution information. The probability corresponding to each time interval can be calculated by counting the number of the arriving people in each time interval and sequencing the people from big to small according to the number of the people. And considering that most of people's behaviors are in accordance with normal distribution, the time probability distribution of the top ten is taken as the inter-station running time probability distribution information, so that the inter-station running time probability distribution corresponding to any two stations can be obtained. For example, the probability distribution of the runtime between the A site and the B site is {43 minutes: 0.046; 0.076 in 44 minutes; 0.122 in 45 minutes; 0.13 part in 46 minutes; 0.119 part in 47 minutes; 0.114 in 48 minutes; 0.099 part at 49 min; 0.097 in 50 minutes; 0.077 in 51 min; 0.053 in 52 min; 0.06, wherein the probability of arriving at the 43 th minute (including less than 43 minutes) is 0.046, the probability of arriving at the 44 th minute is 0.076, the probability of arriving at the 45 th minute is 0.122, and so on, after extracting the time probability distribution of the first ten times of the ranking, most passengers on the net can be covered basically, and for each passenger, the time probability distribution can be ignored, so that the flow of determining the interstation running time probability distribution information of any two stops is completed.
S120, determining time thresholds of the passengers arriving at each outbound station of the network of the in-station passenger based on the inter-station running time probability distribution information, and determining the arrival probability of the passengers arriving at each outbound station at the moment based on the time thresholds and the predicted time period, wherein the time thresholds comprise the fastest arrival time and the slowest arrival time.
After determining the inter-station run time probability distribution information for any two stations, to determine whether a passenger may arrive at the corresponding outbound station within a predicted time period. At the moment, the arrival time information of passengers in the station is determined according to all the passengers in the station in the prediction time period counted before, so that the time probability that the passengers reach each station, namely the instant arrival probability, is calculated.
Before that, the time threshold value of each outbound station of the network which passengers in the station arrive is calculated according to the probability distribution information of the inter-station running time. Referring to fig. 5, the time threshold determination process includes:
s1201, extracting the arrival time information of the passengers in the station, determining the arrival stations of the passengers in each station, and matching the arrival stations with the outbound stations of the line network;
s1202, inquiring the probability distribution of the inter-station running time based on the inbound station and the outbound station, and determining the fastest arrival time and the slowest arrival time of passengers arriving at the outbound station.
The time arrival probabilities of the in-station passengers for all the stations are initialized to 0 by initializing the time arrival probabilities of the in-station passengers for all the stations. And further circulating all the sites of the network, wherein the sites are all possible outbound sites of the passenger in the network in the site, and matching all the sites of the network into all the outbound sites corresponding to the inbound sites. And for a certain fixed outbound station id, extracting the probability distribution information of the od pairs of inter-station operating time by inquiring the corresponding inter-station operating time probability distribution information according to the inbound station id and the outbound station id of the passenger in the station. And calculating the fastest arrival time and the latest arrival time of passengers in the station to the outbound station id from the acquired inter-station running time probability distribution information so as to finish the calculation of the time threshold.
Further, the time arrival probability is calculated correspondingly based on the time threshold. The process of determining the time arrival probability based on the time threshold comprises the following steps:
s1203, comparing the fastest arrival time with the slowest arrival time, and if the fastest arrival time and/or the slowest arrival time are/is in the prediction time, determining the corresponding time probability of the passengers in the station to arrive at the outbound station;
s1204, counting the time probability, and determining the arrival probability of the passengers at each station at the time of arrival at each outbound station.
Specifically, referring to fig. 6, a flow of determining the time of arrival probability is provided. For a given prediction time period and the arrival time information of passengers in a given station, if the fastest arrival time of the corresponding time threshold is found to be greater than the end time in the prediction time period or the slowest arrival time is found to be less than the start time in the prediction time period, the fact that the passengers in the station cannot arrive at the corresponding station within the prediction time period specified by us to exit the station is indicated, and the probability value of the passengers exiting the station is updated to be 0 at the moment. Otherwise, the passenger in the station is shown to have a certain probability of arriving at the station for exiting. At the moment, circularly taking out the inter-station running time from the corresponding inter-station running time probability distribution information, and calculating to obtain corresponding arrival time based on the arrival time information of passengers in the stations and the inter-station running time; and comparing the arrival time with the prediction time period, and if the arrival time is in the prediction time period, extracting the corresponding inter-station running time probability as a time probability of the passengers in the station arriving at the outbound station. When the time probability of passengers exiting the station in the station is calculated, the operating time between stations of the probability distribution information of the operating time between stations is arranged from small to large, the passengers are circularly taken out in sequence, and the time of passengers entering the station in the corresponding station is added with the operating time between stations which is circularly taken out, namely the corresponding time of arrival. And comparing the calculated corresponding arrival time with the end time of the prediction time period, and if the arrival time is a value in the prediction time period, indicating that the corresponding arrival time can reach the outbound station within the prediction time period. And further performing superposition statistics on the time probabilities determined by the inter-station running times in the corresponding inter-station running time probability distribution information, determining the arrival probability of the time when one passenger in the station arrives at one outbound station, circulating each outbound station and each passenger in the station, and determining the arrival probability of the time when each passenger in the station arrives at each outbound station. The arrival time probability of the passengers in the station corresponding to the station which is out of the station at the final moment can be obtained by accumulating the time probabilities corresponding to the reachable operation time. After all the sites are cycled, the time arrival probability of the passenger in one site to all the sites of the network can be obtained. By analogy, all passengers in the station can obtain the arrival probability of all the passengers in the station to the all the outbound stations of the network by utilizing the flow.
S130, counting first in-and-out probability distribution information of each od pair in an outbound network and second in-and-out probability distribution information of each od pair of the passengers in the station according to historical passenger flow operation data, and determining station arrival probability of the passengers in the station to arrive at each outbound station based on passenger types of the passengers in the station by using the first in-and-out probability distribution information, the second in-and-out probability distribution information or the current-day riding records of the passengers in the station, wherein the passenger types comprise new users and old users.
When the station arrival probability calculation is carried out, the station arrival probability is determined through the classification of passengers in the station. And comparing the counted id of the passenger in the current station with the id list of the passenger in the current station based on the id list of all the passengers counted by the historical passenger flow operation data, so that the passenger in the station can be distinguished as a new user and an old user. It will be appreciated that if the id of the passenger currently at the station does not appear on the id list, it is determined to be a new user, and vice versa, an old user.
Further, the first station access probability distribution information of each od pair in the outgoing line network and the second station access probability distribution information of each od pair of passengers in the current station are counted based on historical passenger flow operation data, and the station arrival probability is determined. If the passenger type of the passenger in the station is a new user, determining the station arrival probability of the corresponding passenger in the station to arrive at each outbound station by using the first inbound and outbound probability distribution information; and if the passenger type of the in-station passenger is an old user, determining the corresponding station arrival probability of the in-station passenger for reaching each outbound station by using the in-station passenger's in-day riding record, the second in-and-out probability distribution information or the first in-and-out probability distribution information.
Specifically, referring to fig. 7, based on a given predicted time period and given arrival time information of the in-station passenger, the station arrival probabilities of the in-station passenger for all stations are initialized first, and the station arrival probabilities of the in-station passenger for all stations are initialized to 0. Corresponding to each outbound station id, firstly, according to the historical passenger riding record, counting the in-and-out probability distribution information of each od pair of the outbound network and the in-and-out probability distribution information of each od pair of passengers in the station, wherein the in-and-out probability distribution information is counted corresponding to the probability distribution of the outbound station. Further, by judging the type of the passenger in the station, if the passenger in the station is a new user, inquiring first probability information of the corresponding od pair based on the first station-entering and station-exiting probability distribution information, and determining the station arrival probability of the corresponding passenger in the station to arrive at each station of the stations of the station according to the first probability information. And because the new user does not have any historical riding information, the probability distribution information of the passengers going in and out of the station of each od pair of the wire network is obtained, and the probability of the passengers going out of the station of the current station is updated. If the passenger in the station is an old user, the passenger in the station has historical riding information. Judging whether the arrival time of the passengers in the station is greater than or equal to a specified time point (18: 00 is taken here), if the arrival time of the passengers in the station is greater than or equal to the specified time point, comparing the corresponding stations according to the daily riding record of the passengers in the station, and determining the station arrival probability of the corresponding passengers in the station to each station; if the arrival time of the passengers in the station is less than the designated time point, judging whether the corresponding outbound stations appear in a historical outbound list of the passengers in the station, if so, inquiring second probability information of corresponding od pairs based on the first probability distribution information of the passengers in the station, determining the station arrival probability of the corresponding passengers in the station to reach each outbound station according to the second probability information, if not, inquiring first probability information of the corresponding od pairs based on the first probability distribution information of the passengers in the station, and determining the station arrival probability of the corresponding passengers in the station to reach each outbound station according to the first probability information. Specifically, if the arrival time of the passenger at the station is greater than or equal to the specified time point, it indicates that the passenger at the station may have other riding records on the same day. Consider that the probability of going back in the evening is very large if there are multiple ride records for a day for a passenger at that station. And taking out the earliest inbound and outbound record of the current passenger day in the station to obtain the inbound site of the current passenger day, wherein the inbound site may correspond to the outbound site of the current passenger night return trip in the station, comparing the inbound site with the current predicted outbound site id, if the inbound site id and the current predicted outbound site id are the same, updating the site arrival probability value of the outbound site id to be 1, and if the inbound site id and the current predicted outbound site id are different, updating the site arrival probability value of the outbound site id to be 0. In addition, if the arrival time of the passengers in the station is less than the designated time point, whether the station id of the station appears in the historical station-out list of the passengers in the corresponding station is judged according to the historical riding record of the passengers in the station. If so, acquiring an od pair corresponding to the outbound site id of the passenger in the station, and updating the site arrival probability of the passenger in the station to the outbound site id according to the in-out probability distribution of the od pair; and if not, referring to the processing flow of the new user, acquiring an od pair corresponding to the outbound site id in the net, and updating the site arrival probability of the outbound site id reached by the passengers in the station according to the in-and-out probability distribution of the od pair in the net. Thus, the station arrival probability of the passenger in the corresponding station to reach the outbound station id can be determined.
Further, after all stations have been cycled through, the station arrival probability for all outbound stations of the network for the passenger at that station can be obtained. By analogy, for all passengers in the station, the station arrival probability of all stations of the network of passengers in the station can be obtained by utilizing the set of flow.
S140, based on the given prediction time period, the prediction station and the corresponding number of passengers in the station, calculating the outbound passenger flow of the prediction station in the prediction time period by using the time arrival probability and the station arrival probability.
Finally, the outbound passenger volume can be predicted based on the arrival probability at the time when the passenger arrives at each outbound site and the site arrival probability determined in steps S120 and S130. Wherein. The outbound passenger flow calculation formula of the predicted station in the predicted time period is as follows:
Figure BDA0002806790130000121
among them, predict exit_number For the predicted outbound passenger flow of the station in the predicted time period, N is the number of passengers in the station, time _ arive _ prob i For the time-of-arrival probability of the ith in-station passenger arriving at the predicted site, station _ array _ prob i The station arrival probability for the ith said in-station passenger to arrive at said predicted station. And inputting the relevant parameters into the outbound passenger flow calculation formula according to the determined prediction time period, the predicted station and the corresponding number of passengers in the station, so as to obtain the outbound passenger flow data of the predicted station in the given prediction time period, thereby finishing the outbound passenger flow prediction.
According to the method and the device, the outbound information is predicted by utilizing the inbound information based on the association relationship between the inbound and outbound of the passenger, and the outbound station is predicted according to the inbound information of the passenger because the inbound passenger is going to be outbound after all, so that the accuracy of outbound prediction can be improved. In addition, because the subway passenger flow is formed by the aggregation of individual travel behaviors, each individual behavior has extremely high regularity (for example, fixed work attendance events), the robustness of the outbound passenger flow prediction can be improved by taking the individual behavior as a reference, and the outbound passenger flow prediction precision can be further improved by fully considering the influence of individual behavior habits on the outbound passenger flow prediction.
The method comprises the steps of acquiring real-time passenger flow operation data of the line network, counting passengers in stations of the line network based on a given prediction time period, and counting probability distribution information of inter-station operation time of any two stations based on historical passenger flow operation data. And further determining the arrival probability of the time when the passengers in the station arrive at each outbound station based on the inter-station running time probability distribution information, determining the arrival probability of the station when the passengers in the station arrive at each outbound station, and calculating the outbound passenger flow of the predicted station in the predicted time period based on the given predicted time period, the predicted station and the corresponding number of the passengers in the station by using the arrival probability of the time and the arrival probability of the station. By adopting the technical means, the influence of different arrival time, arrival stations and individual behavior habits of passengers on the outbound passenger flow prediction can be combined, more accurate outbound passenger flow prediction is realized, and the reliability of the outbound passenger flow prediction is guaranteed.
Example two:
based on the above embodiments, fig. 8 is a schematic structural diagram of an outbound passenger flow prediction apparatus based on probability distribution according to a second embodiment of the present application. Referring to fig. 8, the outbound passenger flow prediction apparatus based on probability distribution provided in this embodiment specifically includes: a statistics module 21, a first probability calculation module 22, a second probability calculation module 23 and a prediction module 24.
The statistical module 21 is configured to obtain real-time passenger flow operation data of a line network, count passengers in stations of the line network based on a given prediction time period, and count probability distribution information of inter-station operation time of any two stations based on historical passenger flow operation data;
a first probability calculation module 22, configured to determine, based on the inter-station operating time probability distribution information, time thresholds at which the in-station passengers arrive at each outbound station of the network, and determine, based on comparison between the time thresholds and the predicted time periods, arrival probabilities at which the in-station passengers arrive at each outbound station, where the time thresholds include a fastest arrival time and a slowest arrival time;
a second probability calculation module 23, configured to count first in-and-out probability distribution information of each od pair in an outbound network and second in-and-out probability distribution information of each od pair of the in-station passengers according to historical passenger flow operation data, and determine, based on a passenger type of the in-station passenger, a station arrival probability that the in-station passenger arrives at each outbound station using the first in-and-out probability distribution information, the second in-and-out probability distribution information, or a current-day riding record of the in-station passenger, where the passenger type includes a new user and an old user;
and the prediction module 24 is used for calculating the outbound passenger flow of the predicted station in the prediction time period by using the time arrival probability and the station arrival probability based on the given prediction time period, the predicted station and the corresponding number of passengers in the station.
The method comprises the steps of acquiring real-time passenger flow operation data of the line network, counting passengers in stations of the line network based on a given prediction time period, and counting probability distribution information of inter-station operation time of any two stations based on historical passenger flow operation data. And further determining the arrival probability of the passengers in the station at the time when the passengers arrive at each outbound station based on the inter-station running time probability distribution information, determining the arrival probability of the passengers in the station at each outbound station, and calculating the outbound passenger flow of the predicted station in the predicted time period based on the given predicted time period, the predicted station and the corresponding number of the passengers in the station by using the arrival probability of the time and the arrival probability of the station. By adopting the technical means, the influence of different arrival time, arrival stations and individual behavior habits of passengers on the outbound passenger flow prediction can be combined, more accurate outbound passenger flow prediction is realized, and the reliability of the outbound passenger flow prediction is guaranteed.
The outbound passenger flow prediction device based on probability distribution provided by the second embodiment of the present application can be used for executing the outbound passenger flow prediction method based on probability distribution provided by the first embodiment of the present application, and has corresponding functions and beneficial effects.
Example three:
an embodiment of the present application provides an electronic device, and with reference to fig. 9, the electronic device includes: a processor 31, a memory 32, a communication module 33, an input device 34, and an output device 35. The number of processors in the electronic device may be one or more, and the number of memories in the electronic device may be one or more. The processor, memory, communication module, input device, and output device of the electronic device may be connected by a bus or other means.
The memory, as a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the probability distribution based outbound passenger flow prediction method described in any of the embodiments of the present application (e.g., the statistics module, the first probability calculation module, the second probability calculation module, and the prediction module in the probability distribution based outbound passenger flow prediction apparatus). The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to use of the device, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The communication module is used for data transmission.
The processor executes various functional applications of the device and data processing by running software programs, instructions and modules stored in the memory, namely, the outbound passenger flow prediction method based on probability distribution is realized.
The input device may be used to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device may include a display device such as a display screen.
The electronic device provided above can be used to execute the method for predicting outbound passenger flow based on probability distribution provided in the first embodiment above, and has corresponding functions and advantages.
Example four:
embodiments of the present application further provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a probability distribution-based outbound passenger flow prediction method, including: the method comprises the steps of obtaining real-time passenger flow operation data of a line network, counting passengers in stations of the line network based on a given prediction time period, and counting probability distribution information of the inter-station operation time of any two stations based on historical passenger flow operation data; determining time thresholds of the stations for passengers to reach each outbound station of a network based on the inter-station running time probability distribution information, and determining the arrival probability of the stations for the passengers to reach each outbound station based on the comparison of the time thresholds and the predicted time period, wherein the time thresholds comprise the fastest arrival time and the slowest arrival time; according to historical passenger flow operation data, first in-and-out probability distribution information of each od pair in an out-line network and second in-and-out probability distribution information of each od pair of the in-station passengers are counted, and the station arrival probability of the in-station passengers reaching each out-of-station is determined by using the first in-and-out probability distribution information, the second in-and-out probability distribution information or the current riding record of the in-station passengers based on the passenger types of the in-station passengers, wherein the passenger types comprise new users and old users; and calculating the outbound passenger flow of the predicted station in the predicted time period by using the time arrival probability and the station arrival probability based on the given predicted time period, the predicted station and the corresponding number of passengers in the station.
Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations, e.g., in different computer systems connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium containing computer-executable instructions provided in the embodiments of the present application is not limited to the outbound passenger flow prediction method based on probability distribution as described above, and may also perform related operations in the outbound passenger flow prediction method based on probability distribution as provided in any embodiment of the present application.
The outbound passenger flow prediction device, the storage medium, and the electronic device based on probability distribution provided in the foregoing embodiments may execute the outbound passenger flow prediction method based on probability distribution provided in any embodiment of the present application, and reference may be made to the outbound passenger flow prediction method based on probability distribution provided in any embodiment of the present application without detailed technical details described in the foregoing embodiments.
The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.

Claims (12)

1. An outbound passenger flow prediction method based on probability distribution is characterized by comprising the following steps:
the method comprises the steps of obtaining real-time passenger flow operation data of a line network, counting passengers in stations of the line network based on a given prediction time period, and counting probability distribution information of the inter-station operation time of any two stations based on historical passenger flow operation data;
determining time thresholds of passengers arriving at each outbound station of the in-station passenger arrival network based on the inter-station running time probability distribution information, and determining arrival probabilities of the passengers arriving at each outbound station based on the time thresholds and the prediction time period comparison, wherein the method comprises the steps of extracting arrival time information of the passengers arriving at each station, determining arrival stations of the passengers arriving at each station, matching the arrival stations with the outbound stations of the linear network, querying the inter-station running time probability distribution based on the arrival stations and the outbound stations, determining the fastest arrival time and the slowest arrival time of the passengers arriving at the outbound stations, and comparing the fastest arrival time and the slowest arrival time with the prediction time period if the fastest arrival time and/or the slowest arrival time is/are in the prediction time period, determining the corresponding time probability of the passengers in the station reaching the outbound station, counting the time probability, and determining the arrival probability of the passengers in the station reaching the outbound station, wherein the time threshold comprises the fastest arrival time and the slowest arrival time;
according to historical passenger flow operation data, first in-and-out probability distribution information of each od pair in an out-line network and second in-and-out probability distribution information of each od pair of the in-station passengers are counted, and the station arrival probability of the in-station passengers reaching each out-of-station is determined by using the first in-and-out probability distribution information, the second in-and-out probability distribution information or the current riding record of the in-station passengers based on the passenger types of the in-station passengers, wherein the passenger types comprise new users and old users;
and calculating the outbound passenger flow of the predicted station in the predicted time period by using the time arrival probability and the station arrival probability based on the given predicted time period, the predicted station and the corresponding number of passengers in the station.
2. The probability distribution-based outbound passenger flow prediction method according to claim 1, wherein the statistics of the probability distribution information of the inter-station operating time of any two stations based on the historical passenger flow operation data comprises:
all od pairs of a wire network are obtained based on historical passenger flow operation data, and the inter-station operation time of any two stations corresponding to each passenger is counted based on each od pair;
and counting the number of arriving people of any two stations in each time period based on the inter-station running time, and determining the inter-station running time probability distribution information of any two stations according to the number of arriving people.
3. The method of claim 2, wherein determining the probability distribution information of the inter-station operating time of any two stations according to the number of arriving people comprises:
and calculating the corresponding inter-station running time probability according to the number of the arriving people, and extracting the inter-station running time probability with the set number from large to small as the corresponding inter-station running time probability distribution information.
4. The probability distribution-based outbound passenger flow prediction method of claim 1, wherein determining the time probability that the corresponding on-board passenger arrives at the outbound site comprises:
circularly taking out the inter-station running time from the corresponding inter-station running time probability distribution information, and calculating to obtain corresponding arrival time based on the arrival time information of passengers in the stations and the inter-station running time;
and comparing the arrival time with the prediction time period, and if the arrival time is in the prediction time period, extracting the corresponding inter-station running time probability as a time probability of the passengers in the station arriving at the outbound station.
5. The method of claim 4, wherein the step of counting the time probabilities and determining the arrival time probabilities of passengers arriving at the outbound stations comprises:
and performing superposition statistics on the time probabilities determined by the inter-station running times in the inter-station running time probability distribution information, determining the arrival probability of the time when a passenger in the station arrives at an outbound station, circulating each outbound station and each passenger in the station, and determining the arrival probability of the time when the passenger in the station arrives at each outbound station.
6. The probability distribution-based outbound passenger flow predicting method according to claim 1, wherein a station arrival probability of the in-station passenger arriving at each of the outbound stations is determined using the first in-out probability distribution information, the second in-out probability distribution information, or a current-day riding record of the in-station passenger based on a passenger type of the in-station passenger, the passenger type including a new user and an old user, comprising:
if the passenger type of the passenger in the station is a new user, determining the station arrival probability of the corresponding passenger in the station to arrive at each outbound station by using the first inbound and outbound probability distribution information;
and if the passenger type of the in-station passenger is an old user, determining the corresponding station arrival probability of the in-station passenger for reaching each outbound station by using the in-station passenger's in-day riding record, the second in-and-out probability distribution information or the first in-and-out probability distribution information.
7. The method of claim 6, wherein if the passenger type of the on-station passenger is a new user, determining a station arrival probability that the corresponding on-station passenger arrives at each of the outbound stations using the first inbound and outbound probability distribution information comprises:
and inquiring first probability information of the corresponding od pairs based on the first station in-and-out probability distribution information, and determining station arrival probability of the corresponding in-station passengers to reach each outbound station according to the first probability information.
8. The probability distribution-based outbound passenger flow prediction method according to claim 6, wherein if the passenger type of the in-station passenger is an old user, determining a corresponding station arrival probability that the in-station passenger arrives at each outbound station using the current-day riding record of the in-station passenger, the second in-out probability distribution information, or the first in-out probability distribution information, comprises:
if the arrival time of the passengers in the station is greater than or equal to the designated time point, comparing the corresponding stations out of the station according to the daily riding record of the passengers in the station, and determining the station arrival probability of the corresponding passengers in the station to arrive at each station out of the station;
if the arrival time of the passengers in the station is less than the designated time point, judging whether the corresponding outbound stations appear in a historical outbound list of the passengers in the station, if so, inquiring second probability information of corresponding od pairs based on the first probability distribution information of the passengers in the station, determining the station arrival probability of the corresponding passengers in the station to reach each outbound station according to the second probability information, if not, inquiring first probability information of the corresponding od pairs based on the first probability distribution information of the passengers in the station, and determining the station arrival probability of the corresponding passengers in the station to reach each outbound station according to the first probability information.
9. The probability distribution-based outbound passenger flow prediction method of claim 1, wherein the outbound passenger flow calculation formula of the predicted stop in the prediction time period is as follows:
Figure FDA0003669737790000031
among them, predict exit_number For the predicted outbound passenger flow of the station in the predicted time period, N is the number of passengers in the station, time _ arive _ prob i For the time-of-arrival probability of the ith in-station passenger arriving at the predicted site, station _ array _ prob i The station arrival probability for the ith said in-station passenger to arrive at said predicted station.
10. An outbound passenger flow prediction apparatus based on probability distribution, comprising:
the statistical module is used for acquiring the real-time passenger flow operation data of the line network, counting passengers in stations of the line network based on a given prediction time period, and counting the probability distribution information of the inter-station operation time of any two stations based on historical passenger flow operation data;
a first probability calculation module, configured to determine a time threshold for an in-station passenger to reach each outbound station of the wire network based on the inter-station runtime probability distribution information, determine an arrival probability at a time when the in-station passenger reaches each outbound station based on the time threshold comparison and the prediction time period, wherein the method includes extracting arrival time information of the in-station passenger, determining an arrival station of the in-station passenger, determining a fastest arrival time and a slowest arrival time for the in-station passenger to reach each outbound station of the wire network for each outbound station of the in-station, querying the inter-station runtime probability distribution based on the arrival station and the outbound station, comparing the fastest arrival time and the slowest arrival time with the prediction time period, and if the fastest arrival time and/or the slowest arrival time is in the prediction time period, determining the corresponding time probability of the passengers in the station reaching the outbound station, counting the time probability, and determining the arrival probability of the passengers in the station reaching the outbound station, wherein the time threshold comprises the fastest arrival time and the slowest arrival time;
the second probability calculation module is used for counting first in-and-out probability distribution information of each od pair in an out-line network and second in-and-out probability distribution information of each od pair of the in-station passengers according to historical passenger flow operation data, and determining station arrival probability of the in-station passengers reaching each out-of-station based on passenger types of the in-station passengers by using the first in-and-out probability distribution information, the second in-and-out probability distribution information or the current-day riding records of the in-station passengers, wherein the passenger types comprise new users and old users;
and the prediction module is used for calculating the outbound passenger flow of the predicted station in the prediction time period by using the time arrival probability and the station arrival probability based on the given prediction time period, the predicted station and the corresponding number of passengers in the station.
11. An electronic device, comprising:
a memory and one or more processors;
the memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the probability distribution based outbound passenger flow prediction method of any of claims 1-9.
12. A storage medium containing computer-executable instructions for performing the probability distribution based outbound passenger flow prediction method of any one of claims 1-9 when executed by a computer processor.
CN202011371303.6A 2020-11-30 2020-11-30 Outbound passenger flow prediction method and device based on probability distribution Active CN112488388B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011371303.6A CN112488388B (en) 2020-11-30 2020-11-30 Outbound passenger flow prediction method and device based on probability distribution

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011371303.6A CN112488388B (en) 2020-11-30 2020-11-30 Outbound passenger flow prediction method and device based on probability distribution

Publications (2)

Publication Number Publication Date
CN112488388A CN112488388A (en) 2021-03-12
CN112488388B true CN112488388B (en) 2022-08-02

Family

ID=74937190

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011371303.6A Active CN112488388B (en) 2020-11-30 2020-11-30 Outbound passenger flow prediction method and device based on probability distribution

Country Status (1)

Country Link
CN (1) CN112488388B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113393029B (en) * 2021-06-11 2023-11-17 上海逸迅信息科技有限公司 Method and equipment for predicting rail transit passenger flow
CN114580787B (en) * 2022-04-02 2023-07-14 佳都科技集团股份有限公司 Passenger flow prediction method and device based on bus subway connection station

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779190A (en) * 2016-12-02 2017-05-31 东南大学 A kind of urban track traffic passenger trip route suggesting method and system
CN106875314A (en) * 2017-01-31 2017-06-20 东南大学 A kind of Urban Rail Transit passenger flow OD method for dynamic estimation
CN107358319A (en) * 2017-06-29 2017-11-17 深圳北斗应用技术研究院有限公司 Flow Prediction in Urban Mass Transit method, apparatus, storage medium and computer equipment
CN109961164A (en) * 2017-12-25 2019-07-02 比亚迪股份有限公司 Passenger flow forecast method and device

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140289003A1 (en) * 2013-03-25 2014-09-25 Amadeus S.A.S. Methods and systems for detecting anomaly in passenger flow
CN103310287B (en) * 2013-07-02 2016-07-06 北京航空航天大学 Predict that passenger goes on a journey the track traffic for passenger flow Forecasting Methodology of probability based on SVM

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106779190A (en) * 2016-12-02 2017-05-31 东南大学 A kind of urban track traffic passenger trip route suggesting method and system
CN106875314A (en) * 2017-01-31 2017-06-20 东南大学 A kind of Urban Rail Transit passenger flow OD method for dynamic estimation
CN107358319A (en) * 2017-06-29 2017-11-17 深圳北斗应用技术研究院有限公司 Flow Prediction in Urban Mass Transit method, apparatus, storage medium and computer equipment
CN109961164A (en) * 2017-12-25 2019-07-02 比亚迪股份有限公司 Passenger flow forecast method and device

Also Published As

Publication number Publication date
CN112488388A (en) 2021-03-12

Similar Documents

Publication Publication Date Title
CN112700072B (en) Traffic condition prediction method, electronic device, and storage medium
CN106875066B (en) Vehicle travel behavior prediction method, device, server and storage medium
CN112488388B (en) Outbound passenger flow prediction method and device based on probability distribution
CN110874668B (en) Rail transit OD passenger flow prediction method, system and electronic equipment
CN106777703A (en) A kind of bus passenger real-time analyzer and its construction method
CN110991390B (en) Identity information retrieval method and device, service system and electronic equipment
CN111582605B (en) Method and device for predicting destination site, electronic equipment and storage medium
CN112435469B (en) Vehicle early warning control method and device, computer readable medium and electronic equipment
CN105046303A (en) Distributed data interaction based biological identification method and system
CN112896242B (en) Passenger riding behavior state updating method and device for rail transit
CN112418518A (en) Passenger flow prediction method and device based on time characteristic weight and network topology
CN110472999B (en) Passenger flow mode analysis method and device based on subway and shared bicycle data
CN113096435B (en) Shared parking place determining method, device, equipment and storage medium
CN112129315B (en) Method and device for recommending parking lot, electronic equipment and storage medium
Wu et al. Data-driven inverse learning of passenger preferences in urban public transits
Rodriguez-Deniz et al. Robust real-time delay predictions in a network of high-frequency urban buses
CN112116811B (en) Method and device for identifying and determining riding path
Mrazovic et al. Understanding and predicting trends in urban freight transport
Zheng et al. Metro OD matrix prediction based on multi-view passenger flow evolution trend modeling
CN112529294A (en) Training method, medium and equipment for individual random trip destination prediction model
WO2023241388A1 (en) Model training method and apparatus, energy replenishment intention recognition method and apparatus, device, and medium
CN115965163A (en) Rail transit short-time passenger flow prediction method for generating countermeasures to loss based on space-time diagram
CN109191595B (en) Temporary parking vehicle floating charging method based on parking space sharing
CN113536493A (en) Effective path generation method based on clustering reverse thrust and section passenger flow estimation method
CN112133093A (en) Method and device for rapidly confirming riding path

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
CB02 Change of applicant information

Address after: Room 306, zone 2, building 1, Fanshan entrepreneurship center, Panyu energy saving technology park, No. 832 Yingbin Road, Donghuan street, Panyu District, Guangzhou City, Guangdong Province

Applicant after: Jiadu Technology Group Co.,Ltd.

Applicant after: PCI TECHNOLOGY & SERVICE Co.,Ltd.

Address before: Room 306, zone 2, building 1, Fanshan entrepreneurship center, Panyu energy saving technology park, No. 832 Yingbin Road, Donghuan street, Panyu District, Guangzhou City, Guangdong Province

Applicant before: PCI-SUNTEKTECH Co.,Ltd.

Applicant before: PCI TECHNOLOGY & SERVICE Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant