CN108628991A - The analysis and visualization system that rail traffic failure influences passenger flow - Google Patents
The analysis and visualization system that rail traffic failure influences passenger flow Download PDFInfo
- Publication number
- CN108628991A CN108628991A CN201810401197.8A CN201810401197A CN108628991A CN 108628991 A CN108628991 A CN 108628991A CN 201810401197 A CN201810401197 A CN 201810401197A CN 108628991 A CN108628991 A CN 108628991A
- Authority
- CN
- China
- Prior art keywords
- data
- failure
- passenger flow
- operation event
- subsystem
- 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.)
- Withdrawn
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 44
- 238000012800 visualization Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000012517 data analytics Methods 0.000 claims abstract description 23
- 238000012795 verification Methods 0.000 claims description 28
- 230000009471 action Effects 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000013079 data visualisation Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000004044 response Effects 0.000 description 6
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 238000013459 approach Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 3
- 238000005339 levitation Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 241000736199 Paeonia Species 0.000 description 1
- 235000006484 Paeonia officinalis Nutrition 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The analysis and visualization system that the invention discloses a kind of rail traffic failures to influence passenger flow, wherein the analysis system includes：Data acquisition subsystem, data process subsystem and data analytics subsystem；The data acquisition subsystem is used for the operation event of failure data and passenger flow data of acquisition trajectory traffic；Data process subsystem is stated for storing the operation event of failure data and the passenger flow data；The data analytics subsystem is used to establish the correlation model of operation the event of failure data and the passenger flow data, and the correlation model is used to be reflected in the passenger flow situation in the case of operation event of failure occurs.Depth of the present invention excavates, analyzes passenger flow situation in the case where the operation event of failure occurs；It realizes that data are presented by big data visualization technique, intuitively reflects the analysis result of the analysis system.
Description
Technical field
Analysis that the invention belongs to field of track traffic more particularly to a kind of rail traffic failures to influence passenger flow and visual
Change system.
Background technology
Currently, rail traffic has become the vehicles of common of people's trip.At this stage, in order to grasp rail traffic
The reason of traffic-operating period can usually record each rail transportation operation failure, analysis failure, and each track of analysis are handed over
The passenger flow situation of logical circuit or website.But operation failure and passenger flow situation are all independent statistics, analyze, in the prior art
The two is not combined so that being associated between operation failure and passenger flow influence is not excavated by depth.
Invention content
The technical problem to be solved by the present invention is to excavate operation failure and passenger flow without depth in the prior art to overcome
Associated defect between influence provides analysis and visualization system that a kind of rail traffic failure influences passenger flow.
The present invention is to solve above-mentioned technical problem by the following technical programs：
A kind of analysis system that rail traffic failure influences passenger flow, the analysis system include：Data acquisition subsystem,
Data process subsystem and data analytics subsystem；
The data acquisition subsystem is used for the operation event of failure data and passenger flow data of acquisition trajectory traffic；
The data process subsystem is for storing the operation event of failure data and the passenger flow data；
What the data analytics subsystem was used to establish operation event of failure data and the passenger flow data is associated with mould
Type, the correlation model are used to be reflected in the passenger flow situation in the case of operation event of failure occurs.
Preferably, the data acquisition subsystem includes：Run event of failure data acquisition module and passenger flow data acquisition
Module；
The operation event of failure data acquisition module is for acquiring the operation event of failure data；
For the passenger flow data acquisition module for acquiring the passenger flow data, the passenger flow data includes the friendship of rail traffic
Easy data；
And/or the data acquisition subsystem further includes：Data cleansing module and data cache module；
The data cleansing module is used to extract from the operation event of failure data relevant effectively with operation failure
Element, and extracted and the relevant effective element of passenger flow from the passenger flow data；
The data cache module is used to cache the corresponding data of effective element that the data cleansing module extracts.
Preferably, the data process subsystem is additionally operable to before storing the operation event of failure data, to described
Operation event of failure data carry out completeness check and correct the operation event of failure data, then again if verification is unqualified
Secondary carry out completeness check stores the operation event of failure data if verification is qualified；
And/or the data process subsystem is additionally operable to before storing the passenger flow data, to the passenger flow data into
Row completeness check corrects the passenger flow data if verification is unqualified, then carries out completeness check again, if verification is closed
Lattice then store the passenger flow data.
Preferably, the completeness check includes at least one of following verification：
Whether verification is duplicate data, and when verifying unqualified, corresponding amendment includes deleting the data repeated；
Whether verification is incomplete data, and when verifying unqualified, corresponding amendment includes the data of completion incompleteness；
Whether verification is error data, and when verifying unqualified, corresponding amendment includes correcting the data of mistake.
Preferably, the data process subsystem is additionally operable to storing the operation event of failure data and the passenger flow number
According to the data type for before, distinguishing operation the event of failure data and the passenger flow data, the operation failure thing is being stored
When number of packages evidence and the passenger flow data, different storage modes is used for different data types.
Preferably, the data type is divided into structural data and non-/ semi-structured data；
The data process subsystem is additionally operable to when storing the operation event of failure data and the passenger flow data, right
It is stored using distributed relation database platform in the structural data, the non-/ semi-structured data is used
A kind of Hadoop (distributed system architecture) platform architecture stores.
Preferably, the operation event of failure data include：Moment occurs for operation event, failure, circuit occurs for failure, event
Hinder at least one of car number, failure spot, trouble duration, fault type and failure-description；
The data analytics subsystem is additionally operable to form theme probability Distribution Model, and the theme probability Distribution Model is used for
Classify to different fault types, obtain different classes of failure theme and forms key of the description per class failure theme
Word；
The data analytics subsystem is additionally operable to be respectively formed rail traffic failure topic model for per class failure theme,
The rail traffic failure topic model is used to, according to the operation event of failure data, predict the prediction shadow of such failure theme
Ring the time.
Preferably, the input parameter of the correlation model is the data of description operation event of failure, the correlation model
It is the passenger flow situation in the case where the operation event of failure occurs to export result, and the passenger flow situation includes directly impacted
Passenger flow situation and/or indirectly impacted passenger flow situation；
The directly impacted passenger flow situation is included in the failure and the visitor that website occurs by the failure for the moment occurs
Flow and/or Trip distribution, the estimated volume of the flow of passengers/or passenger flow for entering the failure and website occurring in the trouble duration
At least one of distribution, the Trip distribution includes the destination of passenger flow；
Indirect impacted passenger flow situation includes being intended to pass through the failure in the trouble duration website occurs
The volume of the flow of passengers and/or Trip distribution, the Trip distribution include in the departure place and destination, track circuit, website distribution of passenger flow
At least one.
Preferably, the data analytics subsystem is additionally operable to obtain the departure place and destination of trip, according to the operation
Event of failure and the passenger flow situation in the case where the operation event of failure occurs, plan trip route.
A kind of visualization system that rail traffic failure influences passenger flow, the visualization system are used for according to as described above
Rail traffic failure analysis system that passenger flow is influenced, be presented on the passenger flow situation in the case of operation event of failure occurs.
Preferably, the visualization system is additionally operable to receive the input parameter of the correlation model of the analysis system, present
The output result of the correlation model；
And/or the visualization system is additionally operable to receive the departure place and destination of trip；The data of the analysis system
Analyzing subsystem obtains the departure place and destination, and according to the operation event of failure and the operation event of failure is occurring
In the case of passenger flow situation, plan trip route；The visualization system is additionally operable to show the trip route.
Preferably, the visualization system includes front end display interface；
The front end display interface is used to show the rail traffic road network map of level-one or two level or more, the output result
It is shown in the rail traffic road network map；
And/or the front end display interface is additionally operable to show the action pane for receiving the input parameter；
And/or the front end display interface is additionally operable to the action pane that display receives the departure place and destination.
On the basis of common knowledge of the art, above-mentioned each optimum condition can be combined arbitrarily to get each preferable reality of the present invention
Example.
The positive effect of the present invention is that：The analysis system that the rail traffic failure of the present invention influences passenger flow passes through
Acquisition, the storage of operation event of failure data and passenger flow data to rail traffic, establish operation event of failure and passenger flow situation
Correlation model, depth excavate, analyze occur it is described operation event of failure in the case of passenger flow situation；The track of the present invention
Traffic faults realize that data are presented to the visualization system that passenger flow influences by big data visualization technique, intuitively reflect institute
State the analysis result of analysis system.
Description of the drawings
Fig. 1 is the schematic block diagram for the analysis system that a kind of rail traffic failure of the embodiment of the present invention 1 influences passenger flow；
Fig. 2 is the schematic block diagram of the data acquisition subsystem and data process subsystem of the embodiment of the present invention 1；
Fig. 3 is the schematic block diagram of the data analytics subsystem of the embodiment of the present invention 1；
Fig. 4 is a kind of algorithms library Organization Chart for the data analytics subsystem for realizing embodiment 1；
Fig. 5 is a kind of presentation for the visualization system that a kind of rail traffic failure of the embodiment of the present invention 2 influences passenger flow
Schematic diagram.
Specific implementation mode
It is further illustrated the present invention below by the mode of embodiment, but does not therefore limit the present invention to the reality
It applies among a range.
Embodiment 1
Fig. 1 shows the analysis system that a kind of rail traffic failure of the present embodiment influences passenger flow.Wherein, the track
Traffic can be but be not limited to subway, light rail and tramcar, and novel rail has magnetic-levitation system, monorail system
(straddle-type rail system and suspension type rail system) and the automatic rapid transit system (RTS) of passenger etc..
The analysis system includes：Data acquisition subsystem 10, data process subsystem 20 and data analytics subsystem 30.
The data acquisition subsystem 10 is used for the operation event of failure data and passenger flow data of acquisition trajectory traffic.
The data process subsystem 20 is for storing the operation event of failure data and the passenger flow data.
The data analytics subsystem 30 is used to establish being associated with for operation event of failure data and the passenger flow data
Model, the correlation model are used to be reflected in the passenger flow situation in the case of operation event of failure occurs.
Wherein, as shown in Fig. 2, the data acquisition subsystem 10 includes：Run 11 He of event of failure data acquisition module
Passenger flow data acquisition module 12.
The operation event of failure data acquisition module 11 is for acquiring the operation event of failure data.The operation event
Barrier event data may include time of failure (including date and specific time), failure generation circuit, car number, failure
Type, failure-description etc..The operation event of failure data acquisition module 11 may be used off-line files mode obtain it is above-mentioned
Run event of failure data：The data sharing of 11 timer access operation event system of the operation event of failure data acquisition module
Record is simultaneously had the operation incident file of above-mentioned operation event of failure data to be transmitted to local by catalogue using File Transfer Protocol,
The operation incident file using XML (extensible markup language) or CSV, (with plain text deposited by character separation value, file
Storage) etc. semi-structured stored in file format.
For the passenger flow data acquisition module 12 for acquiring the passenger flow data, the passenger flow data includes rail traffic
Transaction data.Using the transaction data of rail traffic as passenger flow data, passenger flow situation can be accurately reacted.
By taking rail traffic is subway as an example, the transaction data of the rail traffic may include transportation card transaction data and ground
Iron special ticket transaction data.
Wherein, the passenger flow data acquisition module 12 can be arranged dedicated for acquiring the transportation card of transportation card transaction data
Data-acquisition submodule 121.The transportation card data-acquisition submodule 121 can pass through a kind of Socket (two-way communication links
Connecing) communication interface docked with transportation card system for settling account (a kind of system of existing recording traffic card trading situation), by institute
It states transportation card data-acquisition submodule 121 and establishes socket communication connection, held using request-response (request-response)
Hand mode is interacted with the transportation card system for settling account, i.e., the described transportation card system for settling account initiates the hair of transportation card transaction data
Response is replied after sending request, the transportation card data-acquisition submodule 121 to receive transportation card transaction data.The transportation card transaction
User-defined format message form may be used in the data format of data.Transportation card transaction data may include：Traffic Card Type is handed over
Logical card card number, type of transaction (enter the station, is outbound, update), transaction website, last transaction website, exchange hour, transaction amount etc..
The passenger flow data acquisition module 12 can also be arranged to acquire the subway of subway special ticket transaction data
Special ticket data-acquisition submodule 122.The subway special ticket data-acquisition submodule 122 passes through socket communication interface and rail
The communication modes and transportation card data of road traffic score-clearing system (a kind of system of existing record subway special ticket trading situation)
It is similar to the communication modes of transportation card system for settling account to acquire submodule 121：Socket is established by special ticket data-acquisition submodule
Communication connection, is handed over using request-response (request-response) handshake methods with the rail traffic score-clearing system
Mutually, i.e., rail traffic score-clearing system initiates the transmission request that rail hands over special ticket transaction data, subway special ticket data acquisition mould
Block 122 replys response after receiving subway special ticket transaction data.The data format of the subway special ticket transaction data can adopt
With user-defined format message form.Subway special ticket transaction data at least may include：Special ticket type, is handed over special ticket card number
Easy type (enter the station, is outbound, update), transaction website, last transaction website, exchange hour, transaction amount etc..
Certainly, it is that (such as light rail and tramcar, novel rail have magnetic-levitation system to other types in rail traffic
System, monorail system and the automatic rapid transit system (RTS) of passenger etc.) when, the transaction data of the rail traffic may include such rail traffic
Respective transaction data.
In order to filter number unrelated with operation failure and passenger flow in the operation event of failure data and the passenger flow data
According to avoiding the accuracy of these data influence subsequent analysis, the data acquisition subsystem 10 that from can also including：Data cleansing mould
Block 13 and data cache module 14.
The data cleansing module 13 is used to extract from the operation event of failure data and runs that failure is relevant has
Element is imitated, and is extracted and the relevant effective element of passenger flow from the passenger flow data.The selection of the effective element can basis
The practical traffic-operating period of rail traffic or preliminary analysis determination according to operation event of failure and passenger flow correlation.
The data cache module 14 is used to cache the corresponding data of effective element of the extraction of the data cleansing module 13.
Wherein, the corresponding data of the effective element refer to the actual value of effective element described in transaction data.
Or by taking rail traffic is subway as an example, may include with the operation relevant effective element of failure：Operation event, therefore
Hinder time of origin (including date and specific time), failure occurs in circuit, car number, fault type, failure-description extremely
Few one kind；May include with the relevant effective element of passenger flow：For the traffic Card Type of transportation card, transportation card card number, transaction class
At least one of type (enter the station, is outbound, update), transaction website, last transaction website, exchange hour, transaction amount；For ground
Special ticket type, special ticket card number, type of transaction (enter the station, is outbound, update), transaction website, last transaction in iron special ticket
At least one of website, exchange hour, transaction amount.
Certainly, it is that (such as light rail and tramcar, novel rail have magnetic-levitation system to other types in rail traffic
System, monorail system and the automatic rapid transit system (RTS) of passenger etc.) when, the case where effective element can be according to such rail traffic, is specific
Analysis and selection.
The data process subsystem 20 can be also used for the data cached in the data cache module 14 being transferred to master
It is stored in data warehouse.
Wherein, in order to ensure the integrality of data, it is ensured that the accuracy of following model analysis, the data process subsystem
20 are additionally operable to before storing the operation event of failure data, and completeness check is carried out to the operation event of failure data,
If verification is unqualified, the operation event of failure data are corrected, then carry out completeness check again, if verification is qualified,
Store the operation event of failure data；
And/or the data process subsystem 20 is additionally operable to before storing the passenger flow data, to the passenger flow data
It carries out completeness check and corrects the passenger flow data if verification is unqualified, then carry out completeness check again, if verification
Qualification then stores the passenger flow data.
Wherein, the completeness check may include at least one of following verification：
Whether verification is duplicate data, and when verifying unqualified, corresponding amendment includes deleting the data repeated.Specifically
Ground, if the judgment principle for being duplicate data is to be carried out sentencing weight according to the crucial semanteme of different data, for example, transportation card number of deals
According to sentence again by judging that even same card number is in same a period of time to card number, exchange hour, the crucial semantemes of type of transaction three
Between occur transaction of the same race be then regarded as repeat transportation card transaction data, the same traffic of basis for estimation of subway special ticket transaction data
Card transaction data repeats to judge consistent.Run event of failure data repeatability then by time of failure, failure occur circuit,
Car number, fault type are judged that the same vehicle of even same circuit occurs together in the same time as crucial semanteme
Class failure is then regarded as repeating to run event of failure data.It merchandises for the transportation card transaction data, the subway special ticket that repeat
Data and operation event of failure data are deleted.
Whether verification is incomplete data, and when verifying unqualified, corresponding amendment includes the data of completion incompleteness.Incomplete number
According to verification with correct mainly for transportation card transaction data and subway special ticket transaction data.Whether be incomplete data judgement
Principle lacks for whether the value of each element in the transportation card transaction data and subway special ticket transaction data has, for incompleteness
Transportation card transaction data and subway special ticket transaction data are according to actual conditions completion.Such as：If transaction data lacks station of entering the station
Point, will be rear primary if transaction data lacks outbound website then using previous outbound website as this website that enters the station
Website enter the station as previous outbound website, it, can be according to entering the station website and outbound website calculates if lacking transaction amount
Transaction amount.
Whether verification is error data, and when verifying unqualified, corresponding amendment includes correcting the data of mistake.Number of errors
According to verification with correct equally mainly for transportation card transaction data and subway special ticket transaction data.Whether it is error data
Judgment principle is whether the value of each element in the transportation card transaction data and subway special ticket transaction data has correctly, for difference
Wrong transportation card transaction data and subway special ticket transaction data is according to actual conditions amendment.
For the data by verification, the data process subsystem 20 can also store the operation event of failure number
According to before the passenger flow data, the data type of the differentiation operation event of failure data and the passenger flow data is storing
When the operation event of failure data and the passenger flow data, different storage modes is used for different data types.
Wherein, the data type is divided into structural data and non-/ semi-structured data；Non-/semi-structured data refers to
Unstructured data or semi-structured data.
When storing the operation event of failure data and the passenger flow data, for the structural data, the number
It is stored using distributed relation database platform according to processing subsystem 20；For the non-/ semi-structured data, the data
Processing subsystem 20 is stored using Hadoop platform framework, to ensure the readability of text class data, is convenient for data analysis subsystem
System 30 carries out analysis and excavation processing.
The data analytics subsystem 30 is described further below：
As shown in figure 3, the data analytics subsystem 30 is initially formed theme probability Distribution Model, the theme probability point
Cloth model is for classifying to different fault types, obtaining different classes of failure theme and forming description per class failure master
The keyword of topic.
Specifically, it is operation event, failure that the theme probability Distribution Model, which uses non-supervisory machine learning, input parameter,
The moment occurs, circuit, fault car number, failure spot, trouble duration, fault type and failure-description occur for failure
At least one of；It is the keyword per class failure theme to export result.Such as：The line of Shanghai 9, from dispatching a car, website is reached home
The thing that website occurs runs event (including the parking etc. to each website) as primary, if break down (such as at some
Website subway door does not close, and is regarded as primary fault event), by inputting the description to fault type (door damage) and failure,
Classified to fault type and (belong to " door " class), output is the keyword of such failure theme.
Then the data analytics subsystem 30 is respectively formed rail traffic failure topic model for per class failure theme,
The rail traffic failure topic model is used to, according to the operation event of failure data, predict the prediction shadow of such failure theme
Ring the time.The specific implementation of the rail traffic failure topic model can be the operation event of failure with same keyword
Belong to a kind of failure theme, moment, failure spot, trouble duration occur for the failure excavated in the keyword, pass through
The training rail traffic failure topic model obtains the predicted impact time (predicting the duration) of such failure theme.Or
Person can be using the average value of the trouble duration of history similar fault event as when the predicted impact of such failure theme
Between.
In the present embodiment, a kind of LDA (document subject matter generation model) algorithm model may be used and establish the theme probability
Distributed model and the rail traffic failure topic model.LDA training methods are：By theme probability Distribution Model to runing thing
Part obtains each relevant word of fault type theme, and above-mentioned training is completed by way of iteration.Just as common text
Classification is the same, and the keyword of each failure theme is ultimately formed after training.The advantages of using LDA algorithm model for：It can root
According to different fault types carry out classification and for different fault type themes in such a way that probability distribution is by iteration into
Row training realizes dimensionality reduction and simplifies modeling.
Certainly, the invention is not limited in using theme probability Distribution Model and the rail described in LDA algorithm model foundation
Road traffic faults topic model.It can also be realized using other algorithms, such as：The sorting algorithms such as Bayes.
It is described in detail below for the correlation model：
The input parameter of the correlation model is the data of description operation event of failure, the output result of the correlation model
For the passenger flow situation in the case where the operation event of failure occurs.It is described in order to ensure the comprehensive and accuracy of analysis
Passenger flow situation may include direct impacted passenger flow situation and/or indirect impacted passenger flow situation.
Wherein, the data of description operation event of failure include operation event, the moment occurs for failure, circuit occurs for failure, event
Hinder car number, website, trouble duration, fault type and failure-description etc. occur for failure.Above-mentioned data can be according to need
Direct determination is asked, partial data can also be input to the theme probability Distribution Model, by the theme probability Distribution Model
Input of the output as the rail traffic topic model, then using the output of the rail traffic topic model as the pass
The input of gang mould type.For example, the trouble duration, which preferably first passes through theme probability Distribution Model, obtains the operation event
The failure theme of barrier event, then the predicted impact time by rail traffic failure topic model output.If institute is not used
Rail traffic failure topic model is stated, the trouble duration can be a preset value or discreet value.
The directly impacted passenger flow situation is included in the failure and the visitor that website occurs by the failure for the moment occurs
Flow and/or Trip distribution, the estimated volume of the flow of passengers/or passenger flow for entering the failure and website occurring in the trouble duration
At least one of distribution, the Trip distribution includes the destination of passenger flow；
The impacted passenger flow situation indirectly includes being intended to pass through the failure in the trouble duration to stand
The volume of the flow of passengers and/or Trip distribution of point, the Trip distribution include departure place and destination, track circuit, the website point of passenger flow
At least one of cloth.
The correlation model is calculated occurs process of the moment by the volume of the flow of passengers of failure generation website in the failure
For：It is calculated according to the Historic Section passenger flow data of input parameter combination road network and the moment occurs by failure hair in the failure
The volume of the flow of passengers of raw website, forms data set f1, and statistical data collection f1 obtains the output valve 1 of the correlation model：It is directly impacted
Volume of the flow of passengers R1 (number)=count (f1).
The estimated volume of the flow of passengers for entering failure generation website is predicted value, the association in the trouble duration
The prediction process of model is：It takes history to enter the passenger flow data collection that website occurs for the failure with time interval, obtains data set
F2, the destination distribution situation for counting f2 obtain the output valve 2 of the correlation model：Direct impacted Trip distribution situation R2=
{ x1, x2 }, x1 indicate that purpose website, x2 indicate impacted passenger flow to the number of the purpose website.
The volume of the flow of passengers that the failure generation website is intended to pass through in the trouble duration is similarly predicted value, described
The prediction process of correlation model is：History is calculated with will in time interval according to trouble duration combination Historic Section passenger flow
The volume of the flow of passengers of website occurs by failure, forms data set f3, statistical data collection f3 obtains output valve 3：Visitor indirectly affected
Flow (number) R3=count (f3).
The correlation model is also further combined with the OD attributes recorded in data set f3, i.e. departure place and destination, statistics
The source site of passenger flow trip and terminus point distribution, and the optimal road that website occurs without failure is obtained by road network routing table
Diameter and approach website.The Trip distribution of the above website is calculated according to data set f2 and as the output valve of the correlation model 4：Between
Receive the Trip distribution situation R4={ y1, y2 } influenced, y1 indicates that approach website, y2 indicate impacted passenger flow approach website indirectly
Number.
Above-mentioned history refers in the case that identical road network with time interval or in the same time (i.e. road network structure is identical)
Same time section or the moment (i.e. identical month, identical week, the same time section on identical date in week or mutually in the same time).
In order to dredge passenger flow in time when the operation event of failure occurs, provides good trip for passenger and suggest, institute
State data analytics subsystem 30 can be also used for obtain trip departure place and destination, according to the operation event of failure and
The passenger flow situation in the case of the operation event of failure occurs, plans trip route.The trip route of planning is preferably free of event
The optimal path and approach website of website occur for barrier.
Fig. 4 shows a kind of algorithms library Organization Chart for the data analytics subsystem 30 for realizing the present embodiment.The algorithms library
Including data interface tier, core algorithm layer and algorithm management layer.
Data interface tier, which is mainly realized, extracts various forms of data, is specifically divided into storage transportation card passenger flow data, track
The database interface of traffic special ticket passenger flow data；Store the file interface and storage auxiliary information of rail transportation operation data
Shared drive interface.
Core algorithm layer, including algorithms selection module, algorithm catalogue, algorithm calling module, computing unit, algorithm evaluation mould
Block and result output module.
Algorithm management layer, including algorithm check module, algorithm parameter setup module and algorithms library calling module.
The processing operation fault time of data analytics subsystem 30 is to pass through data interface tier on the main flow that passenger flow influences
It will operation event of failure data, passenger flow data realization convergence and storage.It selects to calculate from algorithm catalogue by algorithms selection module
Training data is sent into the progress data training of algorithm calling module and training result is calculated, finally according to algorithm evaluation by method
Module is assessed for algorithm index, is stored result data by subsystem after assessment.
Embodiment 2
Present embodiments provide a kind of visualization system that rail traffic failure influences passenger flow.The visualization system is used
In the analysis system influenced on passenger flow according to a kind of rail traffic failure in embodiment 1, it is presented on generation operation event of failure
In the case of passenger flow situation.
Specifically, the visualization system can receive the input parameter of the correlation model of the analysis system.It receives
Concrete form can be manually entered for operating personnel.The input parameter includes at least failure and website, failure generation moment occurs
And trouble duration.The output result of the correlation model is presented in calculating through the correlation model, the visualization system.
The output result may include：Direct impacted passenger flow situation and/or indirectly impacted passenger flow situation.
The mode of presentation can be varied.A kind of presentation mode provided in this embodiment, as shown in Figure 5：
Front end display interface is shown by the visualization system.The front end display interface for show level-one or two level with
On rail traffic road network map, the output result shown in the rail traffic road network map.
Rail traffic road network map can divide rank according to the size of display area, and entire city is shown as unit of city
The map of the rail traffic road network in city (such as Shanghai City) can be considered as level-one rail traffic road network map, be shown as unit of region
The map of the rail traffic road network of some city some regional (such as Xuhui District of Shanghai, Pudong New District) can be considered as secondary track
Traffic network map shows that the map of its rail traffic road network can be considered as three-level rail traffic road as unit of smaller region
Entoilage figure is incremented by step by step according to the smallerization of display area.
Wherein, level-one rail traffic road network map can be used as the main interface of the front end display interface, and two level is to get on the right track
Traffic network map can be used as the assistant interface of the front end display interface, be shown in the lower right of the main interface.
In order to distinguish and highlight, in specific present, failure can be highlighted in track traffic network map
The region and passenger flow that website occurs influence big region, and by impacted small road network region reduction display, (area reduction, path become
It is transparent), website, which occurs, for failure becomes point of scintillation, and the impacted thicker color in road network path becomes assertive colours.In the two level
Show that the impacted passenger flow in each department, passenger flow are shown in a manner of thermodynamic chart in the above rail traffic road network map, passenger flow compact district
Domain is peony, and passenger flow sparse region is light green color (not shown).
In addition, inputting the input parameter for the ease of operating personnel, the front end display interface, which can also be shown, to be used for
Receive the action pane of the input parameter.Concrete form can be：User can be selected by mouse in main interface road network figure
It selects failure and website occurs, input fault occurs the affiliated circuit of website (when website is transfer website), fault type and failure and occurs
Time.
For planning path, the visualization system can also receive the departure place and destination of trip, the analysis system
The data analytics subsystem of system is after obtaining the departure place and destination, according to the operation event of failure and described in generation
The passenger flow situation in the case of event of failure is runed, plans that trip route, the visualization system show the trip route.
Correspondingly, the departure place and destination are inputted for the ease of operating personnel, the front end display interface is for showing
Show the action pane for receiving the departure place and destination.Concrete form can be：Operating personnel are inputted by right side information bar
The departure place (starting point i.e. in figure) of trip and destination (terminal i.e. in figure), the analysis system is according to failure website situation
Again it plans trip route and is highlighted.
Right side information bar can equally show failure website, trouble duration, influence number, impacted crowd in track
The output information of the correlation model such as the distribution on each circuit.
Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that these
It is merely illustrative of, protection scope of the present invention is defined by the appended claims.Those skilled in the art is not carrying on the back
Under the premise of from the principle and substance of the present invention, many changes and modifications may be made, but these are changed
Protection scope of the present invention is each fallen with modification.
Claims (12)
1. a kind of analysis system that rail traffic failure influences passenger flow, which is characterized in that the analysis system includes：Data are adopted
Subsystem, data process subsystem and data analytics subsystem；
The data acquisition subsystem is used for the operation event of failure data and passenger flow data of acquisition trajectory traffic；
The data process subsystem is for storing the operation event of failure data and the passenger flow data；
The data analytics subsystem is used to establish the correlation model of operation the event of failure data and the passenger flow data, institute
State passenger flow situation of the correlation model for being reflected in the case of operation event of failure occurs.
2. analysis system as described in claim 1, which is characterized in that the data acquisition subsystem includes：Run failure thing
Part data acquisition module and passenger flow data acquisition module；
The operation event of failure data acquisition module is for acquiring the operation event of failure data；
For the passenger flow data acquisition module for acquiring the passenger flow data, the passenger flow data includes the number of deals of rail traffic
According to；
And/or the data acquisition subsystem further includes：Data cleansing module and data cache module；
The data cleansing module is used to extract from the operation event of failure data and runs the relevant effective element of failure,
And it is extracted and the relevant effective element of passenger flow from the passenger flow data；
The data cache module is used to cache the corresponding data of effective element that the data cleansing module extracts.
3. analysis system as described in claim 1, which is characterized in that the data process subsystem is additionally operable to described in storage
Before runing event of failure data, completeness check is carried out to the operation event of failure data and is corrected if verification is unqualified
The operation event of failure data, then carry out completeness check again, if verification is qualified, store the operation event of failure
Data；
And/or the data process subsystem is additionally operable to before storing the passenger flow data, has been carried out to the passenger flow data
Whole property verification, if verification is unqualified, corrects the passenger flow data, then carries out completeness check again, if verification is qualified,
Store the passenger flow data.
4. analysis system as claimed in claim 3, which is characterized in that the completeness check include in following verification at least
It is a kind of：
Whether verification is duplicate data, and when verifying unqualified, corresponding amendment includes deleting the data repeated；
Whether verification is incomplete data, and when verifying unqualified, corresponding amendment includes the data of completion incompleteness；
Whether verification is error data, and when verifying unqualified, corresponding amendment includes correcting the data of mistake.
5. analysis system as described in claim 1, which is characterized in that the data process subsystem is additionally operable to described in storage
Before runing event of failure data and the passenger flow data, the number of operation the event of failure data and the passenger flow data is distinguished
According to type, when storing the operation event of failure data and the passenger flow data, for different data types using different
Storage mode.
6. analysis system as claimed in claim 5, which is characterized in that the data type is divided into structural data and non-/ half
Structural data；
The data process subsystem is additionally operable to when storing the operation event of failure data and the passenger flow data, for institute
It states structural data to store using distributed relation database platform, Hadoop is used for the non-/ semi-structured data
Platform architecture stores.
7. analysis system as described in claim 1, which is characterized in that the operation event of failure data include：Operation event,
Moment occurs for failure, circuit, fault car number, failure spot, trouble duration, fault type and failure occur for failure
At least one of description；
The data analytics subsystem is additionally operable to form theme probability Distribution Model, and the theme probability Distribution Model is used for not
Same fault type is classified, and is obtained different classes of failure theme and is formed keyword of the description per class failure theme；
The data analytics subsystem is additionally operable to be respectively formed rail traffic failure topic model for per class failure theme, described
Rail traffic failure topic model is used for according to the operation event of failure data, when predicting the predicted impact of such failure theme
Between.
8. analysis system as described in claim 1, which is characterized in that the input parameter of the correlation model is description operation event
The data of barrier event, the output result of the correlation model are the passenger flow feelings in the case where the operation event of failure occurs
Condition, the passenger flow situation include direct impacted passenger flow situation and/or indirect impacted passenger flow situation；
The directly impacted passenger flow situation is included in the failure and the volume of the flow of passengers that website occurs by the failure for the moment occurs
And/or Trip distribution, the estimated volume of the flow of passengers/or Trip distribution for entering the failure and website occurring in the trouble duration
At least one of, the Trip distribution includes the destination of passenger flow；
Indirect impacted passenger flow situation includes the passenger flow for being intended to pass through the failure in the trouble duration and website occurring
Amount and/or Trip distribution, the Trip distribution include passenger flow departure place and destination, track circuit, website distribution in extremely
Few one kind.
9. analysis system as described in claim 1, which is characterized in that the data analytics subsystem is additionally operable to obtain trip
Departure place and destination, according to the operation event of failure and the passenger flow feelings in the case where the operation event of failure occurs
Condition plans trip route.
10. a kind of visualization system that rail traffic failure influences passenger flow, which is characterized in that the visualization system is used for root
According to the analysis system that the rail traffic failure described in any one of claim 1-9 influences passenger flow, it is presented on and runs
Passenger flow situation in the case of event of failure.
11. visualization system as claimed in claim 10, which is characterized in that the visualization system is additionally operable to receive described point
The output result of the correlation model is presented in the input parameter of the correlation model of analysis system；
And/or the visualization system is additionally operable to receive the departure place and destination of trip；The data analysis of the analysis system
Subsystem obtains the departure place and destination, according to the operation event of failure and in the feelings that the operation event of failure occurs
Passenger flow situation under condition plans trip route；The visualization system is additionally operable to show the trip route.
12. visualization system as claimed in claim 11, which is characterized in that the visualization system includes that front end shows boundary
Face；
The front end display interface is used to show the rail traffic road network map of level-one or two level or more, and the output result is in institute
It states and is shown in rail traffic road network map；
And/or the front end display interface is additionally operable to show the action pane for receiving the input parameter；
And/or the front end display interface is additionally operable to the action pane that display receives the departure place and destination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810401197.8A CN108628991A (en) | 2018-04-28 | 2018-04-28 | The analysis and visualization system that rail traffic failure influences passenger flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810401197.8A CN108628991A (en) | 2018-04-28 | 2018-04-28 | The analysis and visualization system that rail traffic failure influences passenger flow |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108628991A true CN108628991A (en) | 2018-10-09 |
Family
ID=63694892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810401197.8A Withdrawn CN108628991A (en) | 2018-04-28 | 2018-04-28 | The analysis and visualization system that rail traffic failure influences passenger flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108628991A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091196A (en) * | 2019-11-15 | 2020-05-01 | 佳都新太科技股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN111581394A (en) * | 2020-04-30 | 2020-08-25 | 北京印刷学院 | Large-scale knowledge topographic map drawing method |
| CN112508303A (en) * | 2020-12-22 | 2021-03-16 | 西南交通大学 | OD passenger flow prediction method, device, equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102700576A (en) * | 2012-05-18 | 2012-10-03 | 中国铁道科学研究院电子计算技术研究所 | Passenger flow monitoring method of urban rail traffic network |
| CN107194497A (en) * | 2017-04-27 | 2017-09-22 | 北京交通大学 | Urban track traffic passenger trip route planing method under a kind of accident |
| CN107274000A (en) * | 2017-04-27 | 2017-10-20 | 北京交通大学 | Urban track traffic section passenger flow forecasting under a kind of accident |
| CN107273999A (en) * | 2017-04-27 | 2017-10-20 | 北京交通大学 | A kind of Flow Prediction in Urban Mass Transit method under accident |
-
2018
- 2018-04-28 CN CN201810401197.8A patent/CN108628991A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102700576A (en) * | 2012-05-18 | 2012-10-03 | 中国铁道科学研究院电子计算技术研究所 | Passenger flow monitoring method of urban rail traffic network |
| CN107194497A (en) * | 2017-04-27 | 2017-09-22 | 北京交通大学 | Urban track traffic passenger trip route planing method under a kind of accident |
| CN107274000A (en) * | 2017-04-27 | 2017-10-20 | 北京交通大学 | Urban track traffic section passenger flow forecasting under a kind of accident |
| CN107273999A (en) * | 2017-04-27 | 2017-10-20 | 北京交通大学 | A kind of Flow Prediction in Urban Mass Transit method under accident |
Non-Patent Citations (1)
| Title |
|---|
| 李春晓: "城市轨道交通突发事件下乘客路径选择行为建模与仿真", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091196A (en) * | 2019-11-15 | 2020-05-01 | 佳都新太科技股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN111091196B (en) * | 2019-11-15 | 2022-08-02 | 佳都科技集团股份有限公司 | Passenger flow data determination method and device, computer equipment and storage medium |
| CN111581394A (en) * | 2020-04-30 | 2020-08-25 | 北京印刷学院 | Large-scale knowledge topographic map drawing method |
| CN111581394B (en) * | 2020-04-30 | 2023-06-23 | 北京印刷学院 | Large-scale knowledge topography drawing method |
| CN112508303A (en) * | 2020-12-22 | 2021-03-16 | 西南交通大学 | OD passenger flow prediction method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105279572B (en) | City track traffic passenger flow density index calculating and releasing system | |
| WO2019085807A1 (en) | Road condition information acquisition method and device thereof, and storage medium | |
| CN108242149A (en) | A kind of big data analysis method based on traffic data | |
| CN106779408A (en) | The appraisal procedure and device of public transit system service quality | |
| CN109191081A (en) | A kind of wisdom site supervision examination & approval platform | |
| CN108628991A (en) | The analysis and visualization system that rail traffic failure influences passenger flow | |
| CN105844435A (en) | Subway vehicle fault information management system based on FMECA | |
| CN105574593B (en) | Track state static detection and control system and method based on cloud computing and big data | |
| Dong et al. | Characterizing resilience of flood-disrupted dynamic transportation network through the lens of link reliability and stability | |
| Wang et al. | Resilience assessment of waterway transportation systems: Combining system performance and recovery cost | |
| CN111966746B (en) | Meteorological disaster prevention and reduction process monitoring system and monitoring method thereof | |
| CN110019569A (en) | A method of obtaining urban track traffic operation state information | |
| CN116307728A (en) | Subway line operation risk management system based on big data analysis | |
| Liu et al. | Data analytics approach for train timetable performance measures using automatic train supervision data | |
| Li et al. | Spatial-temporal correlation prediction modeling of origin-destination passenger flow under urban rail transit emergency conditions | |
| Hendren et al. | Transit travel time reliability: shifting the focus from vehicles to customers | |
| CN113344268B (en) | Urban traffic trip data analysis method | |
| Chen et al. | Innovation performance study on the construction safety of urban subway engineering based on bayesian network: a case study of BIM innovation project | |
| Hua et al. | Network survivability and recoverability in urban rail transit systems under disruption | |
| Yokoyama et al. | A framework for large-scale train trip record analysis and its application to passengers’ flow prediction after train accidents | |
| CN109784629B (en) | Transformer substation industrial control network fault positioning method based on neural network | |
| CN111708765A (en) | Internet of things cloud platform management system and method based on big data micro-service | |
| CN116090836A (en) | Global risk determination method, device, equipment and medium applied to rail transit | |
| Zhou et al. | A hierarchical network modeling method for railway tunnels safety assessment | |
| M’halla et al. | Distributed Monitoring Based on P‐Time Petri Nets and Chronicle Recognition of the Tunisian Railway Network |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181009 |
|
| WW01 | Invention patent application withdrawn after publication |