CN115098564A - Passenger travel demand analysis method and system - Google Patents
Passenger travel demand analysis method and system Download PDFInfo
- Publication number
- CN115098564A CN115098564A CN202210844948.XA CN202210844948A CN115098564A CN 115098564 A CN115098564 A CN 115098564A CN 202210844948 A CN202210844948 A CN 202210844948A CN 115098564 A CN115098564 A CN 115098564A
- Authority
- CN
- China
- Prior art keywords
- passenger
- time
- passengers
- travel
- data
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 40
- 230000006399 behavior Effects 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000012546 transfer Methods 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 10
- 235000019580 granularity Nutrition 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000001788 irregular Effects 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 26
- 230000008569 process Effects 0.000 abstract description 16
- 238000007418 data mining Methods 0.000 abstract description 10
- 238000012545 processing Methods 0.000 description 10
- 238000010276 construction Methods 0.000 description 7
- 238000005065 mining Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 6
- 238000013475 authorization Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 230000002123 temporal effect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000007670 refining Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000029305 taxis Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Game Theory and Decision Science (AREA)
- Remote Sensing (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
Abstract
The invention discloses a passenger travel demand analysis method and a system, wherein the method comprises the following steps: collecting and preprocessing historical trip data of passengers; performing clustering analysis on the preprocessed historical travel data of the passengers to obtain a passenger classification result; and analyzing the space requirement and the time requirement of the passenger according to the actual travel data of the passenger. Data such as riding consumption, paths and positions, safety check, safety behaviors and the like generated in the traveling process of passengers are utilized, data mining is used as a main technical means, the passengers are classified by selecting appropriate classification indexes and combining a clustering algorithm, and further the space requirements and the time requirements of the passengers are deeply mined.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a passenger travel demand analysis method and system based on data mining.
Background
With the continuous development and growth of cities in China, the traffic pressure caused by dense population is becoming more and more serious. The rail transit has the advantages of large transportation volume, high speed, dense shift, safety, comfort, high punctuation rate, all weather, low transportation cost, energy conservation, environmental protection and the like, so that the rail transit is developed and constructed rapidly in large and medium-sized cities in China.
The huge passenger flow generates a great deal of travel data, including data of bus consumption, paths and positions, security check, safety behaviors and the like. However, due to the lack of valuable data mining and demand analysis processes for passenger data in the current urban rail transit construction process, the utilization value of a large amount of data resources is low, the passenger demand cannot be mined in combination with the data to improve the passenger service level, the passenger experience improvement driven by big data is realized, differentiated accurate service cannot be provided by constructing passenger figures, and the service expansibility is poor.
In the prior art, chinese patent CN202010441009.1 of the invention proposes a passenger portrait system suitable for urban rail transit and a construction method thereof, and the principle is that passenger portrait is constructed by acquiring passenger portrait basic information and passenger portrait extension information and refining the extension information, so as to provide data support for deep analysis of travel rules of rail transit passengers, and provide accurate, differentiated personalized service and basic data for passengers.
The method for realizing user portrait construction in the patent comprises the following steps: and classifying the passenger portrait basic information and the portrait basic expansion information by acquiring the passenger portrait basic information and the passenger portrait basic expansion information. Under each classification, calculating the quantity of the basic expansion information of the portrait; when the number is larger than a threshold value, passenger portrait refinement expansion information corresponding to the passenger portrait basic expansion information is generated; and then constructing the passenger portrait according to the passenger portrait basic information, the passenger portrait basic expansion information and the passenger portrait refined expansion information.
The prior art has the following defects:
(1) in the aspect of information acquisition: the passenger portrait multi-source information includes: passenger face information, passenger iris information, passenger overall information, and passenger surrounding environment information. The sensors and systems related to face information, iris information, passenger overall information and environment perception are needed, the needed data are various, more hardware facilities are needed, and the cost is high.
(2) In the aspect of classification index system: the passenger portrait basic information comprises: name, gender, age, face, fingerprint, identification card, special certificate, bank card, credit information, frequent getting on or off of bus station, hobbies, etc.; in addition, the extension information includes: the passenger portrait refinement and expansion information comprises two parts, namely passenger portrait basic expansion information and passenger portrait refinement expansion information. The extension information includes: classifying the manual service requirement, consultation and complaint, information service requirement and connection requirement into passenger service information, classifying the riding frequency information, riding station information, riding time information and riding transfer information into passenger ticketing information, classifying the security inspection system, external information, security protection information and special information into passenger security protection information, and classifying the authorization level, the authorization range, the authorization content and the authorization time into access authorization information; the refining and expanding information comprises: frequent passengers, staff of cooperative units, important attention passengers and important service passengers. Classifying the passenger portrait basic information according to a first-level classification; the passenger representation base information is then classified according to a second level of classification. The data is various, the data is difficult to unify, and the passenger classification standard and the system are complex. The portrait construction method comprises the following steps: the portrait construction process is not perfect enough, only smart card transaction data are selected on the data, passengers who pay trip expenses in other modes (such as mobile phone code scanning payment groups) are neglected, and the portrait construction process is not comprehensive enough and cannot represent a wide passenger group; only the temporal and spatial regularity of passengers is included in the classification, and the safety behavior data is not fully considered and utilized.
In addition, the prior art is not enough in the degree of attention of the passenger demand data processing and demand mining part, only draws a portrait for the passenger, but does not promote the passenger service level according to the established portrait, is more inclined to stand at the angle of the subway operator, focuses on promoting the subway operation management, does not start from the angle of the passenger, considers the passenger demand, and can not provide better service for the passenger.
Disclosure of Invention
In view of the above, the invention provides a passenger travel demand analysis method and system based on data mining, which utilize data such as riding consumption, paths and positions, security check, safety behavior and the like generated in the passenger travel process, take data mining as a main technical means, select appropriate classification indexes, combine a space-time clustering algorithm to classify passengers, further deeply mine passenger demands, fully release and utilize data resource values, and achieve the purposes of improving services and optimizing operation.
The invention provides a passenger travel demand analysis method in a first aspect, which comprises the following steps: collecting and preprocessing historical trip data of passengers; performing clustering analysis on the preprocessed historical travel data of the passengers to obtain a passenger classification result; and analyzing the space requirement and the time requirement of the passenger according to the actual travel data of the passenger.
Further, the historical travel data of the passenger at least comprises passenger consumption, path and position, security check and safety behavior data.
Further, the step of preprocessing the historical trip data of the passenger comprises: cleaning historical trip data of passengers; sequencing passenger consumption data in the historical travel data of the passengers to obtain passenger consumption conditions; counting position data of passenger traveling, including a starting position and a final position; and establishing a relation among consumption data, position data, security check and safety behavior data of passengers.
Further, the step of performing cluster analysis on the preprocessed historical travel data of the passengers to obtain a passenger classification result includes: extracting consumption data of each passenger, counting travel days of each passenger, and judging whether the travel days of each passenger are smaller than a threshold value; if the travel days of the passengers are less than the threshold value, outputting a category 1: low frequency trip passengers; if the travel days of the passengers are larger than the threshold value, calculating the most intensive time period and time intensive probability based on a time user travel rule algorithm, and judging whether the passengers are time-regular passengers or not; if the passenger is a passenger with regular time, judging whether the trip place is regular in space or not in the most intensive time period based on a spatial user trip rule algorithm, and if the trip place is regular in space, outputting the category 4: temporal and spatial regularity, otherwise output category 2: a single-time regular passenger; if the passengers are irregular passengers in time, judging whether the travel places are regular in space within the whole day time based on a spatial user travel rule algorithm, and if so, outputting a category 3: single spatial regularity passenger, otherwise output category 5: both time and space are irregular passengers.
Further, the step of calculating the most intensive time period and the time intensive probability by using the time-based user travel law algorithm includes: setting time interval, and calculating riding states of all time periods each day; calculating the time period and the time intensive probability of the most concentrated consumption behaviors; if the time-intensive probability is greater than the time density threshold, then the passenger is a time-regular passenger; if the time-intensive probability is less than the time density threshold, then the time-irregular passenger is identified.
Further, the step of judging whether the trip location is spatially regular based on the spatial user trip rule algorithm includes: inquiring all riding records in each time period, and counting the riding days to form a data record set ODLIST (O, D, daynum, timelst), wherein O is an entrance station, D is an exit station, daynum is the riding days, and timelst is a time set; clustering the riding records by adopting a user travel rule algorithm, and judging the similarity between the two stations; if the two sites are adjacent sites, the similarity is 1, otherwise, the similarity is 0; taking out the total days of the largest cluster, and calculating the space dense probability; if the space density probability is larger than the space density threshold value, the passengers are regular passengers; otherwise, it is a space irregularity passenger.
Further, the step of analyzing the space requirement and the time requirement of the passenger according to the actual travel data of the passenger includes: acquiring actual travel data of passengers, and judging the type of information service required by the passengers and traffic information of travel destinations; acquiring the flow situation of personnel entering and exiting the station and the distribution situation of waiting personnel, analyzing the passenger flow distribution situation of each area of the station, and collecting and counting according to the granularity in a certain time to obtain a passenger flow OD matrix;
when the station is taken as a unit, summing up each row of the passenger flow OD matrix to obtain the passenger flow entering each station, and summing up each column of the passenger flow OD matrix to obtain the passenger flow leaving each station; when the line is taken as a unit, counting the passenger flow OD matrix according to the line set to obtain a passenger flow OD matrix of a line layer, and analyzing the passenger flow transfer amount among different lines; when the stations are taken as a unit, after the passenger flow OD pairs are summed in rows and columns, each station can obtain an inbound passenger flow time sequence and an outbound time sequence; when the line is taken as a unit, the passenger flow OD matrixes under n time granularities are placed according to a time sequence, and the demand change of passenger flow transfer between lines along with the time change is analyzed.
Further, the step of determining the type of information service required by the passenger and the traffic location information of the travel destination includes: acquiring actual travel data of passengers to obtain travel destinations of the passengers; judging the type of information service required by the passenger according to the traveling destination of the passenger, wherein the type of information service comprises a riding place position information service, a traffic transfer information service or a comprehensive traffic information service; and acquiring traffic information of transportation means and riding places of the passenger traveling destinations, wherein the traffic information comprises position information, transfer information, arrival and departure time points.
Further, the method also comprises the following steps: and obtaining environmental factors in the station, the crowdedness of train passenger flow and the density of people in each train, and feeding back to the terminals of passengers.
A second aspect of the present invention provides a passenger travel demand analysis system, including: a memory for storing a computer program; and the processor is used for realizing the steps of the passenger travel demand analysis method when executing the computer program.
The passenger trip demand analysis method is more perfect in the aspects of passenger demand data processing and demand mining, not only improves the subway operation effect, but also comprehensively provides suggestions for improving the service quality for the subway operator according to the results constructed by passenger portrayal and the mining results of the passenger trip demand, and meanwhile can perform timely feedback on the passenger trip demand, and meanwhile, the improvement of the passenger service quality and the improvement of the subway operation level are considered.
Drawings
For purposes of illustration and not limitation, the present invention will now be described in accordance with its preferred embodiments, particularly with reference to the accompanying drawings, in which:
fig. 1 is a first flowchart of a passenger travel demand analysis method according to an embodiment of the present invention;
fig. 2 is a second flowchart of a passenger travel demand analysis method according to an embodiment of the present invention;
fig. 3 is a third flowchart of a passenger travel demand analysis method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a passenger travel demand analysis system according to another embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.
In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention, and the described embodiments are merely a subset of the embodiments of the present invention, rather than a complete embodiment. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
The noun explains:
data mining: datamining is a cross-discipline computer discipline branch. It is a computational process that uses artificial intelligence, machine learning, statistics, and database interleaving to discover patterns in relatively large data sets.
Drawing: proposed by alan cooper is a method of mapping target users on marketing plans or commercial designs, often in a variety of combinations, for the convenience of the planner to analyze and set his or her policies developed for different user types. In the user representation, simple people may only have age, occupation and a basic description, complex people may have population, attitude, income, use of articles, preferences and behavior, and the like.
User portrait: the basic attributes, behavior characteristics, social network preferences and the like of the users are subjected to tagging processing, so that the differences in behaviors, viewpoints and the like among people can be distinguished, and other users can be distinguished, such as basic demographic information, geographic positions and the like. User portrayal is an in-depth mining of character characteristics, and some objective attribute tags are basic features of characters.
Data processing: data is a form of expression for facts, concepts, or instructions that may be processed by human or automated means. Data becomes information after being interpreted and given a certain meaning. Data processing (dataprocessing) is the collection, storage, retrieval, processing, transformation, and transmission of data. The basic purpose is to extract and deduce data that is valuable and meaningful to certain people from a large, cluttered, unintelligible amount of data.
Fig. 1 is a flowchart of a passenger travel demand analysis method according to an embodiment of the present invention. The passenger travel demand analysis method utilizes data such as riding consumption, paths, positions, safety check and safety behaviors generated in the passenger travel process, takes data mining as a main technical means, classifies passenger travel data by selecting proper classification indexes and combining a space-time clustering algorithm, further deeply mines passenger demands, fully releases and utilizes data resource values, and therefore the purposes of improving service and optimizing operation are achieved.
Referring to fig. 1, the passenger travel demand analysis method includes the following steps:
and S100, collecting historical trip data of passengers and preprocessing the historical trip data.
In this embodiment, the specific implementation manner of step S100 is as follows:
s101, collecting historical trip data of a plurality of passengers.
In this embodiment, the historical travel data of the passenger includes data such as passenger consumption, route and location, security check, safety behavior, and the like.
The security inspection and safety behavior data comprise data of people with bad record of ticket evasion and ticket leakage uploaded by a ticketing system, data of people with bad records of subway lewd behavior, fighting, advertising leaflet, dealer and entrepreneur, discussion art and the like uploaded from a video monitoring system or recorded by a station, six types of people data uploaded from a public security system, and other data (such as epidemic prevention data and the like) acquired from other external systems.
S102, the historical trip data of the passengers are preprocessed.
Referring to fig. 2, a specific implementation manner of preprocessing the historical travel data of the passenger is as follows:
and S1021, cleaning historical travel data of passengers.
The embodiment cleans data of riding consumption, paths, positions, security check, safety behavior and the like, removes invalid data, such as missing key fields of GPS timestamps, longitudes and latitudes and the like, obviously wrong positioning information deviating from a research area, repeated invalid information generated in the operation process of various devices and the like, and adopts a measure of discarding the whole data record containing the above situation to ensure that each piece of data is complete and available.
And S1022, sequencing passenger consumption data in the historical travel data of the passengers to obtain the passenger consumption condition.
In this embodiment, the passenger consumption situation includes the passenger consumption situation as a whole and the passenger consumption situation as a single.
Sequencing all passenger consumption data according to consumption time to obtain the overall consumption condition of a passenger group; and meanwhile, counting the riding data of each passenger, and sequencing the results according to time to obtain the consumption condition of each passenger.
And S1023, counting the position data of the passenger going out.
In this embodiment, the position data includes a start position and a final position. And counting the traveling position data of the whole passengers and the traveling position data of the single passenger. Additional statistics are then made for intermediate stations that are generated by the transfer behavior.
S1024, establishing a relation among the consumption data, the position data, the security check data and the safety behavior data of the passengers.
The data relation is established among the consumption data, the position data, the security check and the safety behavior data of the passengers through the real-name authentication information of each platform, and the matching and intercommunication of various trip data of the passengers are realized, so that the problem that the data cannot be coordinated and consistent due to the fact that the position data and the consumption data cannot be matched on the body of a single passenger is solved.
The embodiment is more scientific and practical in data selection, organization and utilization. And selecting the critical data with less types of riding consumption, paths and positions, security check and safety behavior, and preprocessing the critical data to ensure the integrity, consistency and availability of each piece of data.
And S200, performing cluster analysis on the preprocessed historical travel data of the passengers to obtain a passenger classification result.
Referring to fig. 3, the specific implementation manner of step S200 is as follows:
s201, extracting consumption data of each passenger, and counting travel days of each passenger.
In this embodiment, consumption transaction record data of the smart card of each passenger is extracted from historical travel data of the passenger, and the number of travel days of each passenger is counted.
S202, judging whether the travel days of each passenger are smaller than a threshold value, if so, outputting a category 1: low-frequency trip passengers, and the step S206 is turned to; otherwise, step S203 is executed.
S203, calculating the most intensive time period Sm and the most intensive time probability Pt by using a user travel rule algorithm (Tm-ODCluster) based on time, judging whether the time is a regular time, if so, turning to the step S204, otherwise, turning to the step S205.
In this embodiment, the specific implementation manner of calculating the most intensive time period Sm and the time intensive probability Pt based on the time user travel rule algorithm (Tm-cluster) is as follows:
and S2031, calculating the riding state of all time periods of each day by taking the day as a cycle and taking 10 minutes as a time interval.
Every 10 minutes is denoted by I, the adjacent three 10 minutes are denoted by I, and the adjacent three 10 minutes riding days TI are calculated, with 144 time periods for the whole day: t1, T2, T3 …, T48, i.e. 0:00-0:30, 0:30-1:00, … 23:30-0: 00.
S2032, a time period Sm in which the consumption behavior is most concentrated is calculated, and a time-intensive probability Pt is calculated as Sm/Dnum, where Dnum is the total number of transaction days.
S2034, if Pt is greater than time density threshold Thrt, it is a time regular passenger, and go to step S204; if Pt is less than the time density threshold Thrt, it is a time irregularity passenger, and the process goes to step S205.
S204, in the most intensive time period Sm, judging whether the travel place is in a space regular mode or not by utilizing a space-based user travel rule algorithm (Sp-ODCluster), and if so, outputting a category 4: temporal and spatial regularity, otherwise output category 2: a single-time regular passenger; and then turns to S206.
The user travel rule algorithm Sp-ODCluster based on the space comprises the following steps:
s2041, inquiring all riding records in the time period T, marking the riding records with (O, D), wherein O is an entrance station, D is an exit station, counting the riding days entering from the O and exiting from the O, and forming a data record set ODLIST (O, D, daynum, timelst), wherein daynum is the riding days, and timelst is a time set.
S2042, clustering the riding record OD by adopting a user travel rule algorithm OD-cluster, and judging the similarity between the two stations; if the two stations are adjacent stations, the similarity is 1, otherwise, the similarity is 0.
The user travel rule algorithm OD-cluster comprises the following steps:
(1) and (3) sequentially extracting the objects P from the data record set ODLIST, judging whether clusters exist, if so, turning to the step (2), and if not, establishing the clusters.
And establishing a new cluster C by taking the object P as the center and taking the total days as the days of the object P, adding the object P into the new cluster C, and identifying the object P as processed.
(2) The distance of the object P from the center of each cluster is calculated.
And if the center of a certain cluster Ci and the object P meet the similarity standard, classifying the object P into the cluster Ci, wherein the total days of the cluster Ci are the total days + the days of the object P (the number of members intersected by the time set of the object P and the time set in the cluster Ci), otherwise, establishing a new cluster C with the object P as the center and the total days as the days of the object P, and adding the object P into the new cluster C.
(3) The above steps are repeated until all records have been processed and grouped into a cluster Ci, and all clusters Ci are sorted from large to small by total days.
S2043, taking out the total days Dmax of the largest cluster, and calculating space-intensive probability Ps as Dmax/DNUM, wherein DNUM is the total days of passenger consumption; if Ps is larger than the space density threshold Thrs, the passenger is a space regularity passenger; otherwise, it is a space irregularity passenger.
And S2044, ending the spatial regularity analysis.
S205, judging whether the travel places are in a space rule within the whole day time by using the space-based user travel rule algorithm Sp-ODCluster, and if yes, outputting a category 3: single spatial regularity passenger, otherwise output category 5: both time and space are irregular passengers.
And S206, judging whether the consumption data of all passengers are processed, if so, turning to S207, and otherwise, turning to S201.
And S207, returning the classification result of the passenger.
And S208, refining the passenger classification result, and adding a label to the passenger with the security check and safety behavior data record.
And S209, returning the classification result and the passenger information with the label.
This embodiment simplifies the classification system, through set up categorised label in advance, utilizes the space-time data based on the passenger trip, divides into 5 types with the passenger: 1. low-frequency trip passengers, 2 time regular passengers, 3 space regular passengers, 4 space-time regular passengers and 5 high-frequency trip passengers. And then the travel path preference of the passengers can be analyzed by combining the spatial regularity according to a large amount of position information accumulated by the passengers in the long-time travel. Through a large amount of time data generated in the passenger traveling process, the traveling time preference of the passenger can be obtained through analysis in combination with the time regularity.
In the aspect of operation safety, in combination with the dangerous goods detection records, whether a dangerous announcement safety behavior violating management exists in the riding process or not, and in combination with the social credit investigation records and the public transportation credit investigation records, personal passenger labels are added, and therefore people of the type need to pay attention.
And S300, analyzing the travel demand of the passenger according to the actual travel data of the passenger.
In this embodiment, the specific implementation manner of step S300 is as follows:
s301, acquiring actual travel data of the passenger, judging the type of information service required by the passenger and the traffic information of the travel destination, and pushing the information service type and the traffic information to the terminal of the passenger.
Specifically, the specific implementation manner of step S301 is as follows:
s3011, actual travel data of the passengers are obtained, and travel destinations of the passengers are obtained.
And after uploading the trip data of the passenger under the condition that the passenger is informed, obtaining the departure place and the destination in the trip data of the passenger according to the obtained actual trip data of the passenger.
And S3012, judging the type of the information service required by the passenger according to the traveling destination of the passenger, and pushing the type of the information service to the terminal of the passenger.
In this embodiment, the information service types include a riding place position information service, a traffic transfer information service, or a comprehensive traffic information service. And judging the type of the information service required by the passenger according to the traveling destination of the passenger, and pushing corresponding information to the passenger.
S3013, specific position information of taxies at travel destinations of the passengers and riding places of public transport in cities is obtained and sent to the terminals of the passengers, or arrival and departure time points, transfer information and comprehensive traffic information of each shift are obtained and sent to the terminals of the passengers.
The method comprises the steps of obtaining specific position information of taxis at passenger travel destinations and riding places of urban public transport, and sending the specific position information of the taxis at the passenger travel destinations and the riding places of the urban public transport to passenger terminals.
Or reporting the arrival and departure time points of each bus (bus, subway), acquiring transfer information (line transfer, peripheral bus stations, high-speed railway stations, subway terminal buildings and the like), acquiring comprehensive traffic information (bus shift, arrival and departure time of high-speed railway trains, flight entrance and exit information and the like) and providing intelligent guiding service.
According to the embodiment, specific position information of taxies at a departure place and a destination in the passenger travel information and riding places of public transport in cities is acquired according to the passenger travel information of the passengers and is sent to the passenger terminal, arrival and departure time points of each bus (bus and subway) are reported to the passenger terminal, meanwhile, transfer information (line transfer, peripheral bus stations, high-speed railway stations, subway station buildings and the like) and comprehensive traffic information (bus shift, arrival and departure time of a high-speed railway train, flight entrance and exit information and the like) are acquired, and intelligent guiding service is provided.
And S302, analyzing the travel demand of the passenger.
Taking the passenger demand ride tool as an example of a subway, the specific implementation manner of step S302 is as follows:
s3021, the number of passengers in queue at each security inspection port of the subway station and the article carrying condition of each passenger are obtained.
In this embodiment, video data acquired by a camera in a subway operation environment is input to the video monitoring and image analysis processing unit, and the number of passengers queuing at each security inspection opening and the article carrying condition of each passenger are acquired.
And S3022, analyzing the passenger flow distribution situation of each area of the station.
AFC data are extracted, OD matrixes are obtained according to a certain time granularity set, and space requirement analysis and time requirement analysis can be carried out. And analyzing subway scheduling information according to the acquired flow conditions of the personnel entering and leaving the station and the distribution condition of the waiting personnel waiting at each place, and predicting the change condition of the follow-up waiting personnel in the station.
And S30221, analyzing the space requirement.
When taking a station as a unit, each station is regarded as a node and represents an OD matrix in the current time granularity. Summing each row of the OD matrix can obtain inbound traffic for each site, and summing each column of the OD matrix can obtain outbound traffic for each site. Based on the time interval, the demand situation of the station can be analyzed, and therefore management and control measures are set for the station with short supply and short demand in the time interval.
When the line is taken as a unit, one line is taken as a node in the network, if a transfer station exists between two lines, a connecting edge exists between the two lines, the OD is counted according to the line set to obtain an OD matrix of a line layer, the passenger flow transfer amount between different lines can be analyzed, and the passenger flow pressure condition of the transfer station is explored from the line perspective.
And S30222, analyzing time requirements.
From a site-by-site perspective, placing the OD matrices at n time granularities in time series, for each OD pair, the change in demand in that direction over time can be observed. After the OD pairs are summed in rows and columns, each station can obtain the time sequence of the incoming passenger flow and the time sequence of the outgoing passenger flow. The temporal demand of the site may be mined. From the point of view of taking the line as a unit, the OD matrixes under the n time granularities are placed according to the time sequence, and the change of the demand of the inter-line passenger flow transfer along with the change of time can be analyzed, namely the change of the passenger flow pressure of the transfer station along with the change of time.
And S3023, acquiring the environmental factors of the subway station.
Through the staff positioning communication navigation head on the key path of staff's location communication navigation head combination, through video monitoring and image analysis technique, acquire environmental factors such as staff's distribution situation in the inside room of subway station.
And S3024, obtaining train state information.
Train state information including the congestion degree of train passenger flow and the density of people in each train is obtained by accessing a train operation system.
S3025, according to the information, obtaining the passenger flow distribution condition of each area of the station, the passenger flow crowding degree condition of the train, subscribing abnormal crowd behaviors (such as falling, trampling, passenger flow surge and the like), counting and predicting the passenger flow OD, and simultaneously providing the passenger flow condition of the station, the queuing and congestion condition of each area, the vehicle arrival information, the personnel density degree in each train and the like in time, so that the passenger flow is dispersed.
S303, health care.
According to the weather condition, comparing the weather condition of the whole course from the place where the passenger is located to the destination, and sending health care service information to the passenger terminal to remind the passenger to add or reduce clothes.
The passenger trip demand analysis method is more perfect in the aspects of passenger demand data processing and demand mining, not only improves the subway operation effect, but also comprehensively provides suggestions for improving the service quality for the subway operator according to the results constructed by passenger portrayal and the mining results of the passenger trip demand, and meanwhile can perform timely feedback on the passenger trip demand, and meanwhile, the improvement of the passenger service quality and the improvement of the subway operation level are considered.
According to the passenger travel demand analysis method, the passengers are classified through the data mining method, the passenger demand mining and demand data processing are considered, and the resource value of the large time-space data generated in the passenger travel process is deeply mined. The method combines the leading-edge thought and technology, senses the passenger requirements through data, reduces the subjectivity of people, and can more objectively find the passenger requirements.
The passenger travel demand analysis method is more effective and targeted in the aspect of data selection, and the consistency among data is more definite; the diversity and the availability of data are fully considered in the data acquisition and preprocessing processes; in the passenger classification process, a more definite portrait construction criterion is adopted, a better classification index system is achieved through iteration, meanwhile, safety inspection and safety behavior information is given to each passenger in an additional label mode, and complexity of the passenger classification system is avoided; and finally, in the passenger demand data processing process, the value behind the data is fully utilized, the passenger demand perception is more perfect, and more abundant and diversified information feedback and real-time service are provided.
In correspondence to the above method embodiment, referring to fig. 4, fig. 4 is a schematic diagram of a passenger travel demand analysis system provided by the present invention, where the system 400 may include:
a memory 401 for storing a computer program;
the processor 402, when executing the computer program stored in the memory 401, may implement the following steps:
collecting and preprocessing historical trip data of passengers; clustering and analyzing the preprocessed historical trip data of the passengers to obtain a passenger classification result; and analyzing the space requirement and the time requirement of the passenger according to the actual travel data of the passenger.
For the introduction of the device provided by the present invention, please refer to the above method embodiment, which is not described herein again.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A passenger travel demand analysis method is characterized by comprising the following steps:
collecting and preprocessing historical trip data of passengers;
performing clustering analysis on the preprocessed historical travel data of the passengers to obtain a passenger classification result;
and analyzing the space requirement and the time requirement of the passenger according to the actual travel data of the passenger.
2. The passenger travel demand analysis method according to claim 1, wherein the passenger's historical travel data includes at least passenger consumption, path and location, security check and safety behavior data.
3. The passenger travel demand analysis method according to claim 1, wherein the step of preprocessing the passenger's historical travel data includes:
cleaning historical trip data of passengers;
sequencing passenger consumption data in historical trip data of passengers to obtain passenger consumption conditions;
counting position data of passenger driving, including a starting position and a final position;
and establishing a relation among consumption data, position data, security check and safety behavior data of passengers.
4. The passenger travel demand analysis method according to claim 1, wherein the step of performing cluster analysis on the preprocessed passenger historical travel data to obtain a passenger classification result comprises:
the consumption data of each passenger are extracted, the traveling days of each passenger are counted, and whether the traveling days of each passenger are smaller than a threshold value or not is judged;
if the travel days of the passengers are less than the threshold value, outputting a category 1: low-frequency trip passengers;
if the travel days of the passengers are larger than the threshold value, calculating the most intensive time period and time intensive probability based on a time user travel rule algorithm, and judging whether the passengers are time-regular passengers or not;
if the passenger is a passenger with regular time, judging whether the trip place is regular in space or not in the most intensive time period based on a spatial user trip rule algorithm, and if the trip place is regular in space, outputting the category 4: temporally and spatially regular passengers, otherwise category 2: a single-time regular passenger;
if the passengers are irregular passengers in time, judging whether the travel places are regular in space within the whole day time based on a spatial user travel rule algorithm, and if so, outputting a category 3: single spatial regularity passenger, otherwise output category 5: both time and space are irregular passengers.
5. The passenger travel demand analysis method according to claim 4, wherein the step of calculating the most intensive time period and the time intensive probability by the time-based user travel law algorithm comprises:
setting time interval, and calculating riding states of all time periods each day;
calculating the time period and the time intensive probability of the most concentrated consumption behaviors;
if the time-intensive probability is greater than the time density threshold, then the passenger is a time-regular passenger;
if the time-intensive probability is less than the time density threshold, then the time-irregular passenger is identified.
6. The passenger travel demand analysis method according to claim 4, wherein the step of judging whether the travel location is spatially regular based on the spatial user travel rule algorithm includes:
inquiring all riding records in each time period, and counting the riding days to form a data record set ODLIST (O, D, daynum, timelst), wherein O is an entrance station, D is an exit station, daynum is the riding days, and timelst is a time set;
clustering the riding records by adopting a user travel rule algorithm, and judging the similarity between the two stations; if the two sites are adjacent sites, the similarity is 1, otherwise, the similarity is 0;
taking out the total days of the largest cluster, and calculating the space intensive probability; if the space density probability is larger than the space density threshold value, the passengers are regular passengers; otherwise, it is a space irregularity passenger.
7. The passenger travel demand analysis method according to claim 1, wherein the step of analyzing the space demand and the time demand of the passenger based on the actual travel data of the passenger includes:
acquiring actual travel data of passengers, and judging the type of information service required by the passengers and traffic information of travel destinations;
acquiring the traffic situation of people entering and leaving the station and the distribution situation of people waiting for the airplane, analyzing the passenger flow distribution situation of each area of the station, and collecting and counting the passenger flow OD matrix according to the granularity in a certain time;
when the station is taken as a unit, summing each row of the passenger flow OD matrix to obtain the inbound passenger flow of each station, and summing each column of the passenger flow OD matrix to obtain the outbound passenger flow of each station; when the line is taken as a unit, the passenger flow OD matrix is counted according to the line set to obtain the passenger flow OD matrix of the line layer, and the passenger flow transfer volume between different lines is analyzed;
when stations are taken as a unit, after row-column summation is carried out on the passenger flow OD pairs, each station can obtain an inbound passenger flow time sequence and an outbound time sequence; and when the line is taken as a unit, placing the passenger flow OD matrixes under n time granularities according to a time sequence, and analyzing the change of the demand of passenger flow transfer among lines along with the change of time.
8. The passenger travel demand analysis method according to claim 7, wherein the step of determining the type of information service required by the passenger and the traffic location information of the travel destination comprises:
acquiring actual travel data of passengers to obtain travel destinations of the passengers;
judging the type of information service required by the passenger according to the traveling destination of the passenger, wherein the type of information service comprises a riding place position information service, a traffic transfer information service or a comprehensive traffic information service;
and acquiring traffic information of transportation means and riding places of the passenger traveling destinations, wherein the traffic information comprises position information, transfer information, arrival and departure time points.
9. The passenger travel demand analysis method according to claim 8, further comprising:
and obtaining environmental factors in the station, the crowdedness of train passenger flow and the density of people in each train, and feeding back to the terminals of passengers.
10. A passenger travel demand analysis system, comprising:
a memory for storing a computer program;
a processor for implementing the steps of a passenger travel demand analysis method according to any one of claims 1 to 9 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210844948.XA CN115098564A (en) | 2022-07-18 | 2022-07-18 | Passenger travel demand analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210844948.XA CN115098564A (en) | 2022-07-18 | 2022-07-18 | Passenger travel demand analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115098564A true CN115098564A (en) | 2022-09-23 |
Family
ID=83298903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210844948.XA Pending CN115098564A (en) | 2022-07-18 | 2022-07-18 | Passenger travel demand analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115098564A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011888A (en) * | 2023-03-20 | 2023-04-25 | 北京华录高诚科技有限公司 | Method and system for relieving pressure of hub people stream |
| CN117472987A (en) * | 2023-12-25 | 2024-01-30 | 水发科技信息(山东)有限公司 | Data integration analysis system based on Internet public information |
-
2022
- 2022-07-18 CN CN202210844948.XA patent/CN115098564A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116011888A (en) * | 2023-03-20 | 2023-04-25 | 北京华录高诚科技有限公司 | Method and system for relieving pressure of hub people stream |
| CN116011888B (en) * | 2023-03-20 | 2023-05-26 | 北京华录高诚科技有限公司 | Method and system for relieving pressure of hub people stream |
| CN117472987A (en) * | 2023-12-25 | 2024-01-30 | 水发科技信息(山东)有限公司 | Data integration analysis system based on Internet public information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Understanding commuting patterns using transit smart card data | |
| Shambour et al. | Progress of IoT research technologies and applications serving Hajj and Umrah | |
| Zhang et al. | Understanding taxi service strategies from taxi GPS traces | |
| CN108242149B (en) | Big data analysis method based on traffic data | |
| Kieu et al. | A modified density-based scanning algorithm with noise for spatial travel pattern analysis from smart card AFC data | |
| Cao et al. | Comparing importance-performance analysis and three-factor theory in assessing rider satisfaction with transit | |
| Yu et al. | Analysing the spatial-temporal characteristics of bus travel demand using the heat map | |
| El-Diraby et al. | Linking social, semantic and sentiment analyses to support modeling transit customers’ satisfaction: Towards formal study of opinion dynamics | |
| Lee et al. | Trip purpose inference using automated fare collection data | |
| Camacho-Collados et al. | A multi-criteria police districting problem for the efficient and effective design of patrol sector | |
| Lu et al. | A review of big data applications in urban transit systems | |
| CN115098564A (en) | Passenger travel demand analysis method and system | |
| Maciejewski et al. | Large-scale microscopic simulation of taxi services. Berlin and Barcelona case studies | |
| CN106529711A (en) | Method and apparatus for predicting user behavior | |
| Shao et al. | Estimating taxi demand-supply level using taxi trajectory data stream | |
| CN106875670A (en) | Taxi concocting method based on gps data under Spark platforms | |
| Guo et al. | Mining commuting behavior of urban rail transit network by using association rules | |
| Rahaman et al. | Wait time prediction for airport taxis using weighted nearest neighbor regression | |
| Ma et al. | Public transportation big data mining and analysis | |
| Zhao et al. | Recognizing metro-bus transfers from smart card data | |
| Guo et al. | Exploring potential travel demand of customized bus using smartcard data | |
| CN111797926A (en) | Inter-city migration behavior recognition method and device, computer equipment and storage medium | |
| Wang et al. | A data driven approach to assessing the reliability of using taxicab as probes for real-time route selections | |
| Verma et al. | Extracting spatiotemporal commuting patterns from public transit data | |
| Lee et al. | Taxi vacancy duration: a regression analysis |
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 |