CN116757330A

CN116757330A - Method, system, equipment and medium for calculating minimum transit time of different stations in same city of railway

Info

Publication number: CN116757330A
Application number: CN202311003037.5A
Authority: CN
Inventors: 朱颖婷; 单杏花; 杨立鹏; 阎志远; 李雯; 王洪业; 梅巧玲; 纪宇宣; 易超; 李俊杰
Original assignee: Tielv Technology Co ltd; Beijing Jingwei Information Technology Co Ltd
Current assignee: Tielv Technology Co ltd; Beijing Jingwei Information Technology Co Ltd
Priority date: 2023-08-10
Filing date: 2023-08-10
Publication date: 2023-09-15
Anticipated expiration: 2043-08-10
Also published as: CN116757330B

Abstract

The application discloses a method for calculating minimum transit time of different stations in the same city of a railway, which comprises the following steps: clustering all stations of the road based on the correlation of the time-space characteristics of the arrival passenger flow, and determining the category of each station; predicting minimum time consumption for entering and exiting stations of different types of stations in different time periods in a railway pre-selling period; constructing an OD data set of the same city different stations, and predicting the time consumption of the same city different stations OD connection in different time periods in a railway pre-selling period; summing the minimum time consumption of the in-out station and the time consumption of the same-city different station OD connection to obtain a first preset value of the same-city different station OD minimum transit time; according to the accumulated distribution characteristics of the ticket returning and ticket changing passenger flow of the next section of the two sections of railway strokes, calculating second preset values of the minimum transit time of the same city and different stations OD in different time periods in the pre-selling period, and selecting the small value in the first preset values and the second preset values as the final minimum transit time of the same city and different stations. The application also discloses a system, equipment and medium for calculating the minimum transit time of the same city and different stations of the railway.

Description

Method, system, equipment and medium for calculating minimum transit time of different stations in same city of railway

Technical Field

The application relates to a transfer time calculation method, in particular to a railway same city different station minimum transfer time calculation method and a system thereof.

Background

Currently, in order to meet the travel demands of passengers without a direct car or without a direct car but without a residual ticket, 12306 provides a transfer service function comprising two sections of railway routes, and is divided into two modes of co-station transfer and co-city transfer. The arrival station of the first section of travel and the departure station of the second section of travel in the same station transfer mode are the same station, and the arrival station of the first section of travel and the departure station of the second section of travel in the same city different station transfer mode belong to two different stations in the same city. Aiming at railway transfer requirements except for abnormal conditions such as late trains and traffic jams, setting reasonable minimum transfer time between two sections of trips is a primary factor considered by railway operation enterprises, and only when the transfer time of one transfer scheme is not less than the specified minimum transfer time, the scheme can become one of candidate schemes, so that the problem that the whole trip takes too long and experiences are poor due to overlong operation disputes caused by unsmooth transfer of passengers due to too short minimum transfer time is solved as much as possible.

Calculation of minimum transit time in the field of traffic travel path planning, patent publication No.: CN114912659a patent name: the utility model provides a railway passenger transfer scheme calculation method, which discloses a railway passenger transfer scheme calculation method, comprising the following steps: an OD data set calculation step, a minimum transfer time calculation step and a transfer scheme calculation step; the railway user inputs a transfer request in real time, a transfer station is obtained based on the candidate full-path reachable OD data set query, transfer station filtering is carried out based on the residual ticket information, the minimum transfer time and preset filtering conditions, an optimal transfer scheme is obtained, and the optimal transfer scheme is displayed for the railway user.

Patent publication No.: CN114723240a, the name of which is: the system comprises an acquisition module, a statistics module and a scheduling module, wherein the acquisition module acquires the operation information of the transportation junction and the transfer information of the arrival passengers; the statistics module is used for counting transfer information of all the arrival passengers and determining initial sharing rate of each connection mode; and the scheduling module iteratively solves the optimal scheduling parameters which minimize the total transfer time of the arrival passengers by using the double-layer planning model according to the operation information and the initial sharing rate of all the connection modes.

However, there are significant challenges in computing the minimum transit time for a co-city outstation transfer in the prior art. On one hand, the minimum transit time of the transfer of different stations in the same city is influenced by a plurality of factors such as the time and flow of entering and exiting stations, the time of connection between two stations, the passenger flow scale of stations and the like, and each factor under different types of stations and cities presents seasonal, periodic and time-period dynamic change rules; on the other hand, the passengers have individual differences in natural attributes such as gender, age, personal physical strength and the like, travel attributes such as baggage, number of drivers and the like, travel attributes such as travel schedule, transfer connection transportation tool selection preference, familiarity degree of transfer routes and the like, the acceptance degree of the passengers on the minimum transfer time is different, and when the transfer time is too short and insufficient for completing transfer, the passengers usually initiate operations such as ticket returning or label changing on the second travel number of vehicles, and related data show specific time-space distribution characteristics.

Therefore, it is highly desirable to provide a method for calculating the minimum transit time for the transfer service of the same city and different city of railways in the national railway, which is based on the arrival passenger flow of the railways station and the collected public transportation travel data, comprehensively uses the methods of traditional clustering, statistics, time series prediction and the like, and calculates the minimum transit time of the transfer service of the same city and different city of railways in batch and in an offline manner under the networking condition. The method solves the technical problems that in the prior art, seasonal, periodic and time-period dynamic changes of various factors in stations and cities of different categories cannot be solved, realizes the simple calculation process of each module and the mutual independence among the modules, and provides decision basis for improving the transfer service quality of railways and the travel experience of passengers.

Disclosure of Invention

The embodiment of the application provides a method and a system for calculating minimum transit time of a same city and different stations of a railway, which are used for solving the technical problem of insufficient calculation of the minimum transit time of the same city and different stations in the prior art.

In a first aspect, an embodiment of the present application provides a method for calculating a minimum transit time of a same-city different station of a railway, where the method includes:

and (3) station entering and exiting time consumption prediction: clustering all stations of the road based on the correlation of the time-space characteristics of the arrival passenger flow, and determining the category of each station; predicting minimum time consumption of station entering and exiting of stations of different categories in different time periods in a railway pre-sale period according to the constructed station entering and exiting time consumption data set of each station in different time periods;

and (3) a time-consuming prediction step of connection: constructing an identical city different station OD data set, collecting urban traffic travel route information corresponding to the identical city different station OD at a preset frequency, analyzing and extracting time-consuming data among the identical city different stations OD, and predicting identical city different station OD connection time-consuming in different time periods in a railway pre-selling period;

and calculating the minimum transit time: summing the minimum time consumption of the in-out station and the time consumption of the same-city different station OD connection to obtain a first preset value of the same-city different station OD minimum transit time; according to the accumulated distribution characteristics of the ticket returning and ticket changing passenger flow of the next section of the two sections of railway strokes, calculating second preset values of the minimum transit time of the same city and different stations OD in different time periods in the pre-selling period, and selecting the small value in the first preset values and the second preset values as the final minimum transit time of the same city and different stations.

In the embodiment of the present invention, the step of predicting the time spent in entering and exiting the station further includes:

clustering the stations: constructing a railway arrival passenger flow data set based on railway ticketing data, calculating a clustering number initial value, clustering stations by adopting a clustering method, and marking the categories of the stations;

and (3) constructing an inbound and outbound time-consuming data set: based on the in-out data in the railway ticketing system, and combining the clustering types of stations, calculating the minimum in-out time and the minimum out-out time in different time periods, and constructing an in-out time data set;

and (3) constructing an outbound minimum time-consuming prediction model: based on the station-in and station-out time-consuming data set, a time sequence prediction algorithm is adopted to respectively construct station-in and station-out minimum time-consuming prediction models of stations of different categories in different departure time periods of each day in the pre-selling period so as to obtain station-in and station-out minimum time-consuming of the stations in the appointed day in the pre-selling period in the appointed departure time period in a prediction mode.

In the embodiment of the present invention, the step of predicting the time consumption for connection further includes:

and constructing an OD data set of the same city different stations: constructing a co-city different station OD dataset based on definition data of a city in which the railway station is located, the co-city different station OD dataset comprising: the arrival station name and station code of the last section of the two sections of the railway travel and the departure station name and station code of the next section of the railway travel;

Constructing a time-consuming data set for OD connection of different stations in the same city: the method comprises the steps of collecting travel route data of the same-city different-station OD at a preset frequency, constructing a same-city different-station OD connection time-consuming data set, and the same-city different-station OD connection time-consuming data set comprises: the arrival station name and station code of the last section of the route in the two sections of the route, the departure station name and station code of the next section of the route, the route planning category, time consumption and data acquisition date and time;

the method comprises the following steps of constructing a time-consuming prediction model for OD connection of different stations in the same city: based on the same-city different-station OD connection time-consuming data set, calculating average time consumption of different ODs in different time periods and under different path planning categories respectively, and summarizing and calculating to obtain a same-city different-station OD connection time-consuming prediction model training data set; and (3) respectively constructing connection time consumption prediction models of all the same-city different stations OD under different advanced departure days and departure time periods by adopting a time sequence prediction algorithm, and obtaining connection time consumption of the same-city different stations OD under corresponding conditions in a pre-selling period.

In the embodiment of the present invention, the step of calculating the minimum transit time further includes:

calculating a first preset value of the minimum transit time: calculating the sum of the minimum time consumption of entering and exiting the station and the time consumption of connecting the same city different stations with the OD to obtain a first preset value of the minimum transit time of the same city different stations of different types of stations in different time periods within the pre-selling period;

Calculating a second preset value of the minimum transit time: selecting transfer time length of which the accumulated passenger flow ratio of the ticket returning and the ticket changing is not higher than a preset value based on a preconfigured ticket returning and ticket changing passenger flow data set, and obtaining a second preset value of the minimum transfer time of different stations in the same city;

and (3) comparing and calculating the minimum transit time: and selecting the smaller value of the first preset value of the minimum transit time of the same-city different stations and the second preset value of the minimum transit time of the same-city different stations in different time periods in the pre-selling period as the final minimum transit time of the same-city different stations.

In the embodiment of the present invention, the step of clustering the stations further includes:

calculating the initial value of the clustering number: determining a cluster number initial value according to a railway arrival passenger flow data set;

the railway station clustering model construction step: constructing a station clustering model by adopting a clustering algorithm based on a pre-constructed daily arrival passenger flow data set of the railway to acquire the category of each station;

and (3) clustering effect optimization: and optimizing and adjusting the value of the initial value of the clustering number according to whether the daily arrival passenger flow time sequence trend of the stations of different categories visually displayed is consistent, and finally determining the clustering number of the stations and the category to which each station belongs.

In the embodiment of the present invention, the step of constructing the time-consuming data set for entering and exiting the station further includes:

minimum inbound time-consuming calculation step: extracting the travel data of passengers before stopping ticket checking, dividing the arrival time consumption according to preset interval time, sequencing, respectively counting the arrival time consumption lower passenger flow of different categories of stations on different departure dates, different time periods and different arrival time consumption, and selecting the arrival time consumption average corresponding to the maximum passenger flow to be downward rounded as the arrival minimum time consumption under the corresponding condition;

minimum outbound time-consuming calculation step: according to the station types, sorting the outbound time consumption of all passengers, respectively counting the accumulated occupancy rate of the passenger flow of stations of different types in different time periods and at the outbound time consumption, and selecting the outbound time consumption with the accumulated occupancy rate not lower than a specified threshold as the minimum outbound time consumption.

In the embodiment of the present invention, the step of constructing the station-entering and station-exiting minimum time-consuming prediction model further includes:

training data set construction: determining a data set range of a model training data set by adopting a correlation analysis method, and constructing a plurality of model training data in a rolling way to form a model training data set;

a prediction model construction step: and constructing a station entering and exiting minimum time consumption prediction model for stations of different categories by adopting a prediction algorithm, and predicting to obtain the station entering minimum time consumption and the station exiting minimum time consumption of the stations of the specified category.

In a second aspect, an embodiment of the present application provides a system for calculating a minimum transit time of a same railway city and different stations, where the method for calculating the minimum transit time of the same railway city and different stations is adopted, and the system includes:

and the station entering and exiting time consumption prediction module is used for: clustering all stations of the road based on the correlation of the time-space characteristics of the arrival passenger flow, and determining the category of each station; predicting minimum time consumption of station entering and exiting of stations of different categories in different time periods in a railway pre-sale period according to the constructed station entering and exiting time consumption data set of each station in different time periods;

the time-consuming prediction module of plugging into: constructing an identical city different station OD data set, collecting urban traffic travel route information corresponding to the identical city different station OD at a preset frequency, analyzing and extracting time-consuming data among the identical city different stations OD, and predicting identical city different station OD connection time-consuming in different time periods in a railway pre-selling period;

the minimum transit time calculation module: summing the minimum time consumption of the in-out station and the time consumption of the same-city different station OD connection to obtain a first preset value of the same-city different station OD minimum transit time; according to the accumulated distribution characteristics of the ticket returning and ticket changing passenger flow of the next section of the two sections of railway strokes, calculating second preset values of the minimum transit time of the same city and different stations OD in different time periods in the pre-selling period, and selecting the small value in the first preset values and the second preset values as the final minimum transit time of the same city and different stations.

In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the method for calculating a minimum transit time for a railway co-city and different-station as described above when the computer program is executed by the processor.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for calculating a minimum transit time for a railway co-city outstation as described above.

Compared with the related prior art, the method has the following outstanding beneficial effects:

1) The method effectively merges travel data sources of various traffic modes such as railways, buses and subways, namely, the travel route data between the arrival passenger flow of the railways and the OD of the same-city stations, establishes a unified space-time analysis dimension, and realizes the mapping between the time spent in entering and exiting the stations and the time spent in connecting the OD of the same-city stations in the transfer mode of the same-city different-city stations of the railways;

2) The method is based on analysis of the influence of the decomposition of the transfer path and the minimum transfer time of the railway on the ticket returning and changing behavior of the passengers, namely, the 'outbound-connection-inbound' is used as a transfer travel chain, so that the time consumption of each link can be ensured to be calculated independently, the transfer minimum transfer time of different stations in the same city can be optimized independently and continuously by modules, and the aim of improving the transfer service quality of the railway and the travel experience of the passengers is fulfilled;

3) The method comprehensively utilizes the traditional data structure construction, clustering, statistics, time sequence prediction and other methods, simplifies the integrated application of various machine learning methods and statistics methods by constructing the data structure, can efficiently and accurately estimate the minimum transfer time of the transfer between the same city and different stations of the railway, is applied to the transfer function in 12306, and effectively improves the passenger transfer experience.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

FIG. 1 is a schematic diagram of a method for calculating minimum transit time of a railway co-city different station;

FIG. 2 is a flowchart of a method for calculating minimum transit time of a railway co-city station according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a predictive model according to an embodiment of the application;

FIG. 4 is a schematic diagram of a system for calculating the minimum transit time of a railway co-city different station according to the present application;

fig. 5 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present application.

In the above figures:

10 inbound/outbound time-consuming prediction module 20 docking time-consuming prediction module

30 minimum transit time calculation module.

Detailed Description

The present application will be described and illustrated with reference to the accompanying drawings and examples in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. All other embodiments, which can be made by a person of ordinary skill in the art based on the embodiments provided by the present application without making any inventive effort, are intended to fall within the scope of the present application.

It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is possible for those of ordinary skill in the art to apply the present application to other similar situations according to these drawings without inventive effort. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.

Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the described embodiments of the application can be combined with other embodiments without conflict.

Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," and similar referents in the context of the application are not to be construed as limiting the quantity, but rather as singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in connection with the present application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.

The invention aims to provide a calculation method for calculating the transfer minimum transit time of the same city and different stations of railway passenger transportation in an offline batch mode under the networking condition by comprehensively utilizing traditional clustering, statistics, time sequence prediction and other methods based on the arrival passenger flow of the railway station and collected public transport travel data, which mainly comprises 3 parts: the method comprises the steps of estimating time spent in entering and exiting stations based on station clustering, predicting connection time spent between stations in the same city, and estimating minimum transfer time of transfer between stations in the same city based on ticket withdrawal and change passenger flow feature fusion. The specific contents are as follows:

(1) In order to embody the scale of the passenger flow in the railway station and describe the time-consuming correlation of the passenger flow sent to the station and the time spent in entering and exiting the station, a railway passenger flow profile data set sent to the station is constructed based on railway ticketing data, the time-space characteristic correlation of the passenger flow sent to the station is calculated, and a traditional clustering method is adopted to cluster all-way stations; constructing a station arrival and arrival time-consuming data set of the station under different dates and time periods, and estimating the arrival and arrival time-consuming of the stations of different categories under different time periods in the railway pre-sale period based on station clustering results.

(2) And constructing an OD data set of the same-city station based on basic service data of the same-city station in the railway ticketing system, collecting urban traffic travel route information corresponding to the same-city station OD at a certain frequency, analyzing and extracting time-consuming data among the same-city stations OD, and predicting the time-consuming of connection among the same-city stations OD in different time periods in a railway pre-selling period 1 day in advance.

(3) Summing the time consumption of entering and exiting the station in the first two steps and the time consumption of connecting the OD of the station in the same city to obtain a preset value 1 of the minimum transit time of the OD of the station in the same city; constructing a ticket return and change passenger flow data set of the next one of two continuous railway strokes, calculating a preset value 2 of the minimum transit time in different time intervals in a pre-selling period according to the cumulative distribution characteristics of the ticket return and change passenger flows, and taking the smaller one of the preset value 1 and the preset value 2 of the minimum transit time as the minimum transit time between the same city stations OD.

As shown in fig. 1, the embodiment of the application provides a method for calculating minimum transit time of a railway co-city different station, which comprises the following steps:

step S10 of predicting time spent in entering and exiting the station: clustering all stations of the road based on the correlation of the time-space characteristics of the arrival passenger flow, and determining the category of each station; predicting minimum time consumption of station entering and exiting of stations of different categories in different time periods in a railway pre-sale period according to the constructed station entering and exiting time consumption data set of each station in different time periods;

docking time-consuming prediction step S20: constructing an identical city different station OD data set, collecting urban traffic travel route information corresponding to the identical city different station OD at a preset frequency, analyzing and extracting time-consuming data among the identical city different stations OD, and predicting identical city different station OD connection time-consuming in different time periods in a railway pre-selling period;

Minimum transit time calculation step S30: summing the minimum time consumption of the in-out station and the time consumption of the same-city different station OD connection to obtain a first preset value of the same-city different station OD minimum transit time; according to the accumulated distribution characteristics of the ticket returning and ticket changing passenger flow of the next section of the two sections of railway strokes, calculating second preset values of the minimum transit time of the same city and different stations OD in different time periods in the pre-selling period, and selecting the small value in the first preset values and the second preset values as the final minimum transit time of the same city and different stations.

In the embodiment of the present invention, the step S10 of predicting the time for entering and exiting the station further includes:

In the embodiment of the present invention, the step S20 of predicting the docking time further includes:

In the embodiment of the present invention, the minimum transit time calculating step S30 further includes:

Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings:

the flow of the specific embodiment of the method is shown in figure 2:

the invention provides a method for calculating the minimum transfer time of transfer between a passenger train and a different station in the same city, which mainly comprises 3 parts: based on station clustering, estimating time consumption for entering and exiting stations, predicting OD connection time consumption of stations in the same city, and estimating transfer minimum transit time of stations in different cities.

1. Estimating time consumed for entering and exiting station based on station clustering

(1) Step 1: constructing a rail outbound passenger flow profile data set

Based on railway ticketing data and time-consuming investigation data of entering and exiting stations provided by business personnel at each station, the larger the time-consuming of entering and exiting stations is, the longer the time-consuming of entering and exiting stations is, and the larger the time-consuming of entering and exiting stations is, which is found out. However, there are differences in the requirements for the entrance and exit management of each railway station, if complete entrance and ticket checking time data is recorded for a part of stations, the time for entrance can be calculated according to the difference between the entrance and ticket checking time of a passenger, and the time for entrance of a check-in station (the passenger entering means that ticket checking is completed) is difficult to grasp, so that the time for entrance of a check-in station is difficult to count based on the railway ticket selling data.

Therefore, according to the analysis conclusion and the current business situation, in order to more scientifically and reasonably estimate the time spent in entering and exiting the railway station, a railway arrival passenger flow data set is constructed based on the railway ticket selling data within a specified date rangeThe system mainly comprises information such as car station names, total amount of arrival passenger flow, maximum arrival passenger flow every day, minimum arrival passenger flow every day, average arrival/same city passenger flow every day, average passenger flow every day from monday to sunday, and the like.

(2) Step 2: calculating the initial value of the clustering number

For the dataset in step 1Determining the initial value of the clustering number by adopting an elbow rule>。

(3) Step 3: constructing daily arrival passenger flow data set of railway

Constructing daily arrival passenger flow data set of railwayThe system mainly comprises information such as a station name, a departure date, a passenger flow sending, a passenger flow arriving and the like.

(4) Step 4: constructing a railway station clustering model

And constructing a station clustering model by adopting K-means or other conventional clustering algorithms to obtain the category of each station. The method of the invention can be used for classifying all railway passenger stations into 5 categories which are respectively ultra-large, medium and small stations. The stations can be clustered by referring to other rules and conventional clustering algorithms, and the station categories are marked.

(5) Step 5: visual clustering effect

Based on the station clustering result and the data set in the step 4Visually displaying daily arrival time sequences of different types of stations, wherein if arrival time sequences of various types of stations are basically consistent in trend, the stations are considered as ∈ ->Reasonable value, otherwise, it needs to be changedTaking values until the arrival passenger flow time sequence trend of various stations is basically consistent, and finally determining the clustering number of stations +.>And the category to which each station belongs.

(6) Step 6: constructing inbound and outbound time consuming datasets

Based on the station entering and exiting data in the railway ticketing system and combining the station clustering result in the step 2, constructing a time-consuming data set for entering and exitingMainly comprises a vehicle station name, a station category, a departure date and the most arrival and arrival at different time periodsSmall time consumption, etc.

The invention divides the whole-day time period by taking 1 hour as an interval, and can also divide the whole-day time period according to other rules according to service requirements.

1) Minimum time consumption for station entering of different categories under different time periodsThe calculation method of (1) is as follows:

the time consuming of entering a station in the invention refers to the time difference between ticket checking and entering a station. Extracting the travel data of passengers before stopping ticket checking according to the time requirement of each railway station on stopping ticket checking before starting, and according to each interval The time for entering the station is divided by minutes and the time is ordered from small to large, and the +.>The upper and lower limit values of the time-consuming interval are respectively +.>. Respectively counting the passenger flows of different types of stations under different departure dates, different time periods and different arrival time consumption, and selecting the arrival time consumption average corresponding to the maximum passenger flow as the downward rounding of the arrival time consumption average corresponding to the maximum passenger flow as the +.>I.e. pair ofRounding down to get +.>. In the present invention->The default value is 5, and the +.A.A. can also be determined by adopting other statistical and machine learning methods according to the actual needs>And estimate +.>Values.

2) Minimum time consumption for different types of stations to exit at different time periodsThe calculation method of (1) is as follows:

the time consuming of the outbound in the invention refers to the time interval of the train arrival and the outbound ticket checking links. Sorting the outbound time consumption of all passengers from small to large according to the types of the stations, respectively counting the accumulated occupancy rate of the passenger flow of the stations of different types in different time periods when the stations are outbound, and selecting the accumulated occupancy rate to be not lower thanIs taken as->. The threshold value is specified in the specific embodiment of the invention>The value defaults to 90%, and other values can be taken according to actual needs.

(7) Step 7: constructing a railway outbound/inbound minimum time consumption prediction model

Based on time-consuming data set for entering and exiting station By adopting LSTM, decision tree and other conventional time sequence prediction algorithms, station entering and exiting minimum time consumption prediction models of different types of railway stations in different departure periods of each day in a pre-selling period are respectively constructed>As schematically shown in FIG. 3, i.e. minimum time-consuming historical data of multiple entrances and exits at a certain time period in a certain type of stationFor model input, predicting and obtaining the minimum time consumption of entering and exiting the station of the class on a certain day in the pre-selling period in the period>。

Taking the example of predicting the minimum time spent for entering and exiting a certain station in a preset selling period in each day in a specific period, if a series of historical time spent data for entering and exiting the station in the period areThe method comprises the steps of carrying out a first treatment on the surface of the The pre-selling period is T days, namely 1 st day and 2 … … T days respectively, and the day before 1 st day can acquire all passenger flow data from a ticketing system; meanwhile, based on correlation analysis results of time-consuming data of entering and exiting, the following model construction steps are obtained:

1) Constructing a model training dataset according to FIG. 3, the basic structure isWherein，/>，/>For the last input variable (equivalent to the last arrival time data obtained and calculated from the system at the time of actual prediction) that is desirable in the history data>Is the value to be measured;

2) Is determined by adopting a pearson correlation coefficient calculation method and other conventional correlation analysis methods Is defined, i.e. maximum length of the input variable +.>The values are rolled to construct a plurality of model training data, and a model training data set is formed;

3) Based on LSTM structure prediction model, bayesian optimization is adoptedThe model parameters are optimized by conventional methods such as genetic algorithm, and mainly comprise hidden layer size, characteristic dimension, batch processing number and the like, and other conventional prediction algorithms can be adopted to construct station entering and exiting minimum time consumption prediction models for stations of different categories, so that the station entering minimum time consumption of the stations of the specified category is predicted to beMinimum outbound time is +.>。

2. Predicting connection time consumption of OD of same city station

(1) Step 1: constructing same city station OD data set

Constructing an OD data set of the same city station based on the definition data of the city in which the railway station is locatedThe system mainly comprises information such as a car station name 1, a car station name 2, a station code 1, a station code 2, a city name, a city code and the like. The objects indicated by the car station name 1 and the station code 1 are arrival stations of the last section of the two sections of the railway strokes which are connected, and the objects indicated by the car station name 2 and the station code 2 are departure stations of the next section of the railway strokes.

For example, there are the following 2 records in the definition data of the city in which the railway station is located: (station name 1, station code 1, city name 1) and (station name 2, station code 2, city code 1, city name 1), then according to the principle that the station name 1 and station name 2 are located in the same city, in the data set There will be 2 pieces of data, namely (station name 1, station name 2, station code 1, station code 2, city name, city code) and (station name 2, station name 1, station code 2, station code 1, city name, city code), respectively corresponding to 2 pairs of co-city station OD, namely station name 1→station name 2, station name 2→station name 1.

(2) Step 2: constructing an OD docking time-consuming dataset for co-city stations

Based on the data set in step 1Writing a data acquisition program, acquiring the OD travel route data of the same city station from the Internet at a certain frequency, and constructing an OD connection time-consuming data set of the same city station +.>The system mainly comprises information such as a bus station name 1, a bus station name 2, a station code 1, a station code 2, a path planning category (such as travel modes of buses, driving, riding, walking and the like), time consumption, date and time of data acquisition and the like. The data acquisition time and frequency should ensure to cover the period range of step 6 in the step of 1 and estimating the time spent entering and exiting based on station clustering.

(3) Step 3: constructing OD connection time-consuming prediction model of co-city station

Time-consuming data set based on OD connection of same city stationAverage time consumption of different OD in different time periods and different path planning categories is calculated respectively, uncertainty factors of railway ticket pre-selling days and different connection modes selected by passengers are considered, and the training data set of the OD connection time consumption prediction model of the same city station is obtained through summarizing calculation >The system mainly comprises information such as a station name 1, a station name 2, a station code 1, a station code 2, a departure date, a departure time period, maximum average time consumption and the like. Wherein departure date and departure time are from the data set +.>Intercepting a data acquisition date and time field to obtain; if a certain pair of OD is in period->There is->Category of species path planning, item iAverage time consumption of the seed path planning class is +.>The OD is +.>The maximum average time consumption is。

Based on LSTM, decision tree and other conventional time sequence prediction algorithms, according to the model construction step of step 7 in step 1 in estimating the arrival and departure time based on station clustering, respectively constructing connection time prediction models of all the same city station OD under different advanced departure days and departure time periods to obtain the same city station OD connection time under corresponding conditions in the pre-selling period。

3. Estimating minimum transit time for transfer between different stations in same city

(1) Step 1: first preset value of minimum transit time

Based on the results of '1' and '2' and 'predicting the OD connection time of the same-city station', the two are summed to obtain the preset value of the minimum transfer time of the same-city different stations in different periods of the pre-selling period of different types of stations I.e. +.>. Wherein (1)>Indicating the minimum estimated time for outbound from the last railway trip to the station, +.>Indicating a minimum estimated time for an inbound station to go to the outbound station for the next leg trip.

(2) Step 2: construction of ticket-returning and ticket-changing passenger flow data set

Based on railway ticketing system data, sorting the transit time of all passengers from small to large according to transfer stations OD (i.e. arrival station of the last railway journey to departure station of the next railway journey), respectively counting the cumulative passenger flow ratio of ticket returning and ticket changing under different time periods and transit time periods of different transfer stations OD, and constructing a ticket returning and ticket changing passenger flow data setThe system mainly comprises information such as a bus station name 1, a bus station name 2, a bus station code 1, a bus station code 2, a departure date, a transit time length, a ticket returning and label changing accumulated passenger flow ratio and the like. The method for calculating the accumulated passenger flow ratio of the ticket returning and the ticket changing comprises the following steps: and under the condition of designating two co-city and off-site transfer stations and departure dates, the ratio of the accumulated number of the transfer ticket and change tickets of the co-city and off-site transfer stations to the total number of the transfer ticket and change tickets of the co-city and off-site transfer stations.

(3) Step 3: calculating a second preset value of the minimum transit time

Passenger flow data set based on ticket returning and ticket changingSelecting a ticket refund slip cumulative passenger flow ratio not higher than + ->As- >。/>The default value is 30%, and other values can be taken according to actual needs.

(4) Step 4: obtaining the minimum transit time by comparison and calculation

Based on the first preset value of the minimum transit timeAnd a second preset value of the minimum transit time +.>The value is +.o.m. for the minimum transit time of the same city station transfer at different time periods in the pre-selling period for all the same city stations OD>And->Smaller values of (a), i.e。

In a second aspect, an embodiment of the present application provides a system for calculating a minimum transit time of a same railway city and different stations, where the method for calculating the minimum transit time of the same railway city and different stations is as described above, as shown in fig. 4, where the system includes:

the time-consuming prediction module 10 for entering and exiting: clustering all stations of the road based on the correlation of the time-space characteristics of the arrival passenger flow, and determining the category of each station; predicting minimum time consumption of station entering and exiting of stations of different categories in different time periods in a railway pre-sale period according to the constructed station entering and exiting time consumption data set of each station in different time periods;

docking time-consuming prediction module 20: constructing an identical city different station OD data set, collecting urban traffic travel route information corresponding to the identical city different station OD at a preset frequency, analyzing and extracting time-consuming data among the identical city different stations OD, and predicting identical city different station OD connection time-consuming in different time periods in a railway pre-selling period;

Minimum transit time calculation module 30: summing the minimum time consumption of the in-out station and the time consumption of the same-city different station OD connection to obtain a first preset value of the same-city different station OD minimum transit time; according to the accumulated distribution characteristics of the ticket returning and ticket changing passenger flow of the next section of the two sections of railway strokes, calculating second preset values of the minimum transit time of the same city and different stations OD in different time periods in the pre-selling period, and selecting the small value in the first preset values and the second preset values as the final minimum transit time of the same city and different stations.

In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements a method for calculating a minimum transit time for a railway co-city and different-station as described above when the computer program is executed by the processor.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for calculating a minimum transit time for a railway co-city outstation as described above.

In addition, the method for calculating the minimum transit time of the railway co-city and different-station according to the embodiment of the application described in connection with fig. 1 can be realized by computer equipment. Fig. 5 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present application.

The computer device may include a processor 81 and a memory 82 storing computer program instructions.

In particular, the processor 81 may comprise a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or may be configured as one or more integrated circuits that implement embodiments of the present application.

Memory 82 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 82 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, solid state Drive (Solid State Drive, SSD), flash memory, optical Disk, magneto-optical Disk, tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. The memory 82 may include removable or non-removable (or fixed) media, where appropriate. The memory 82 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 82 is a Non-Volatile (Non-Volatile) memory. In a particular embodiment, the Memory 82 includes Read-Only Memory (ROM) and random access Memory (Random Access Memory, RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable Programmable Read-Only Memory, abbreviated EPROM), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (Electrically Alterable Read-Only Memory, abbreviated EAROM), or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be Static Random-Access Memory (SRAM) or dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory (Fast Page Mode Dynamic Random Access Memory FPMDRAM), extended data output dynamic Random-Access Memory (Extended Date Out Dynamic Random Access Memory EDODRAM), synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory SDRAM), or the like, as appropriate.

Memory 82 may be used to store or cache various data files that need to be processed and/or communicated, as well as possible computer program instructions for execution by processor 81.

The processor 81 reads and executes the computer program instructions stored in the memory 82 to implement any one of the methods for calculating the minimum transit time for the railway out-of-city stops in the above embodiments.

In some of these embodiments, the computer device may also include a communication interface 83 and a bus 80. As shown in fig. 5, the processor 81, the memory 82, and the communication interface 83 are connected to each other through the bus 80 and perform communication with each other.

The communication interface 83 is used to enable communication between modules, devices, units and/or units in embodiments of the application. Communication port 83 may also enable communication with other components such as: and the external equipment, the image/data acquisition equipment, the database, the external storage, the image/data processing workstation and the like are used for data communication.

Bus 80 includes hardware, software, or both, coupling components of the computer device to each other. Bus 80 includes, but is not limited to, at least one of: data Bus (Data Bus), address Bus (Address Bus), control Bus (Control Bus), expansion Bus (Expansion Bus), local Bus (Local Bus). By way of example, and not limitation, bus 80 may include a graphics acceleration interface (Accelerated Graphics Port), abbreviated AGP, or other graphics Bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) Bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an industry standard architecture (Industry Standard Architecture, ISA) Bus, a wireless bandwidth (InfiniBand) interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a micro channel architecture (Micro Channel Architecture, abbreviated MCa) Bus, a peripheral component interconnect (Peripheral Component Interconnect, abbreviated PCI) Bus, a PCI-Express (PCI-X) Bus, a serial advanced technology attachment (Serial Advanced Technology Attachment, abbreviated SATA) Bus, a video electronics standards association local (Video Electronics Standards Association Local Bus, abbreviated VLB) Bus, or other suitable Bus, or a combination of two or more of the foregoing. Bus 80 may include one or more buses, where appropriate. Although embodiments of the application have been described and illustrated with respect to a particular bus, the application contemplates any suitable bus or interconnect.

Compared with the prior art, the method provided by the application provides a calculation method for calculating the transfer minimum transit time of the railway passenger transportation co-city different stations in an offline batch mode under the networking condition by comprehensively utilizing the traditional clustering, statistics, time sequence prediction and other methods based on the passenger flow sent to the station by the railway station and the acquired public transportation travel data.

The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.

Claims

1. A method for calculating minimum transit time of a same city different station of a railway, the method comprising:

and (3) station entering and exiting time consumption prediction: clustering all stations of the road based on the correlation of the time-space characteristics of the arrival passenger flow, and determining the category of each station; predicting minimum time consumption of the station in and out of different categories of stations in different time periods in a railway pre-selling period according to the constructed station in and out time consumption data sets of the stations in different time periods;

And (3) a time-consuming prediction step of connection: constructing an OD data set of the same city and different station, collecting urban traffic travel route information corresponding to the OD of the same city and different station at a preset frequency, analyzing and extracting time-consuming data among the OD of the same city and different station, and predicting the time-consuming of the OD of the same city and different station in different time periods in a railway pre-selling period;

and calculating the minimum transit time: summing the minimum time consumption of the in-out station and the docking time consumption of the same-city different station OD to obtain a first preset value of the minimum transit time of the same-city different station OD; according to the accumulated distribution characteristics of the ticket returning and ticket changing passenger flow of the next section of the two sections of railway strokes, calculating second preset values of the same-city different station OD minimum transit time in different time periods in the pre-selling period, and selecting the small value of the first preset values and the second preset values as the final same-city different station minimum transit time.

2. The method for calculating the minimum transit time of the same-city and different-city railway stations according to claim 1, wherein the step of predicting the time for entering and exiting the station further comprises:

clustering the stations: constructing a railway arrival passenger flow data set based on railway ticketing data, calculating a clustering number initial value, clustering the stations by adopting a clustering method, and marking the categories of the stations;

And (3) constructing an inbound and outbound time-consuming data set: based on the in-out data in the railway ticketing system, and combining the clustering types of the stations, calculating the minimum time consumption of in-coming and minimum time consumption of out-coming in different periods, and constructing an in-coming and out-coming time consumption data set;

and (3) constructing an outbound minimum time-consuming prediction model: based on the station-in and station-out time-consuming data set, a time sequence prediction algorithm is adopted to respectively construct station-in and station-out minimum time-consuming prediction models of different types of stations in different departure time periods of each day in a pre-selling period so as to obtain the station-in and station-out minimum time-consuming of the stations in the appointed day in the pre-selling period under the appointed departure time period in a prediction mode.

3. The method for calculating the minimum transit time of the same-city and different-city railway station according to claim 1, wherein the step of predicting the docking time further comprises:

and constructing an OD data set of the same city different stations: constructing a co-city different station OD data set based on definition data of a city in which the railway station is located, wherein the co-city different station OD data set comprises: the arrival station name and station code of the last section of the two sections of the railway travel and the departure station name and station code of the next section of the railway travel;

constructing a time-consuming data set for OD connection of different stations in the same city: the method comprises the steps of collecting travel route data of the same-city different-station OD at a preset frequency, and constructing a same-city different-station OD connection time-consuming data set, wherein the same-city different-station OD connection time-consuming data set comprises: the arrival station name and station code of the last section of the route in the two sections of the route, the departure station name and station code of the next section of the route, the route planning category, time consumption and data acquisition date and time;

The method comprises the following steps of constructing a time-consuming prediction model for OD connection of different stations in the same city: based on the same-city different-station OD connection time-consuming data set, calculating average time consumption of different ODs in different time periods and under different path planning categories respectively, and summarizing and calculating to obtain a same-city different-station OD connection time-consuming prediction model training data set; and respectively constructing connection time consumption prediction models of all the same-city different stations OD under different advanced departure days and departure time periods by adopting a time sequence prediction algorithm, and obtaining the connection time consumption of the same-city different stations OD under corresponding conditions in a pre-selling period.

4. The method for calculating the minimum transit time of the same railway city and different station according to claim 3, wherein the step of calculating the minimum transit time further comprises:

calculating a first preset value of the minimum transit time: calculating the sum of the minimum time consumption of entering and exiting stations and the OD docking time consumption of the same-city different stations to obtain first preset values of the minimum transit time of the same-city different stations of different categories of stations in different time periods within a pre-selling period;

5. The method for calculating the minimum transit time of the same-city and different-station railways according to claim 2, wherein the step of clustering stations further comprises:

calculating the initial value of the clustering number: determining a cluster number initial value according to the railway arrival passenger flow data set;

the railway station clustering model construction step: constructing a station clustering model by adopting a clustering algorithm based on a pre-constructed daily arrival passenger flow data set of the railway, and acquiring the category of each station;

6. The method for calculating the minimum transit time for the same-city and different-city railways according to claim 5, wherein the step of constructing the time-consuming data set for the in-out station further comprises:

Minimum inbound time-consuming calculation step: extracting the travel data of the passengers before stopping ticket checking, dividing the arrival time consumption according to preset interval time, sequencing, respectively counting the arrival time consumption of different categories of stations on different departure dates, different time periods and different arrival time consumption, and selecting the arrival time consumption average corresponding to the maximum passenger flow to be downward rounded as the arrival minimum time consumption under the corresponding condition;

minimum outbound time-consuming calculation step: sorting the outbound time consumption of all passengers according to the types of the stations, respectively counting the accumulated occupancy rate of the passenger flow of the stations of different types in different time periods and at the outbound time consumption, and selecting the outbound time consumption with the accumulated occupancy rate not lower than a specified threshold as the minimum outbound time consumption.

7. The method for calculating the minimum transit time of the same-city and different-city railway stations according to claim 6, wherein the step of constructing the station-entering and station-exiting minimum time-consuming prediction model further comprises the steps of:

a prediction model construction step: and constructing a station entering and exiting minimum time consumption prediction model facing different types of stations by adopting a prediction algorithm, and predicting to obtain the station entering minimum time consumption and the station exiting minimum time consumption of the specified types of stations.

8. A system for calculating minimum transit time of a same railway city and different stations, which adopts the method for calculating the minimum transit time of the same railway city and different stations according to any one of claims 1 to 7, and is characterized in that the system comprises:

and the station entering and exiting time consumption prediction module is used for: clustering all stations of the road based on the correlation of the time-space characteristics of the arrival passenger flow, and determining the category of each station; predicting minimum time consumption of the station in and out of different categories of stations in different time periods in a railway pre-selling period according to the constructed station in and out time consumption data sets of the stations in different time periods;

the time-consuming prediction module of plugging into: constructing an OD data set of the same city and different station, collecting urban traffic travel route information corresponding to the OD of the same city and different station at a preset frequency, analyzing and extracting time-consuming data among the OD of the same city and different station, and predicting the time-consuming of the OD of the same city and different station in different time periods in a railway pre-selling period;

the minimum transit time calculation module: summing the minimum time consumption of the in-out station and the docking time consumption of the same-city different station OD to obtain a first preset value of the minimum transit time of the same-city different station OD; according to the accumulated distribution characteristics of the ticket returning and ticket changing passenger flow of the next section of the two sections of railway strokes, calculating second preset values of the same-city different station OD minimum transit time in different time periods in the pre-selling period, and selecting the small value of the first preset values and the second preset values as the final same-city different station minimum transit time.

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method of calculating a minimum transit time for a railway out-of-city station of any of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements a method for calculating a minimum transit time for a railway out-of-city station according to any one of claims 1 to 7.