CN107943920A - A kind of trip crowd recognition method based on subway brushing card data - Google Patents
A kind of trip crowd recognition method based on subway brushing card data Download PDFInfo
- Publication number
- CN107943920A CN107943920A CN201711163466.3A CN201711163466A CN107943920A CN 107943920 A CN107943920 A CN 107943920A CN 201711163466 A CN201711163466 A CN 201711163466A CN 107943920 A CN107943920 A CN 107943920A
- Authority
- CN
- China
- Prior art keywords
- elasticity
- travel
- crowd
- subway
- trip
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000001680 brushing effect Effects 0.000 title abstract 5
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000012216 screening Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 4
- 238000013139 quantization Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 238000004445 quantitative analysis Methods 0.000 abstract 2
- 230000015572 biosynthetic process Effects 0.000 abstract 1
- 238000007781 pre-processing Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of trip crowd recognition method based on subway brushing card data, ticket sale system is examined automatically to subway（AFC）The brushing card data of collection is pre-processed, basis of formation data；And the data are based on, consider rigid crowd's trip characteristics, perfect rigidity crowd is identified using the method for peak period site match；Elasticity concept and model are introduced at the same time, the crowd that other are failed with identification carries out model quantitative analysis, calculates individual trip elasticity size and " perfect rigidity ", " part rigidity ", " partial elastic ", " perfect elasticity " four type section；The trip crowd of comprehensive identification subway brushing card data.Compared with prior art, it is of the invention to construct quantitative analysis model for unordered, multidimensional, substantial amounts of subway brushing card data, have a wide range of application, technical know-how is sufficient, can provide good technical support for analysis subway trip crowd and its effect characteristics.
Description
Technical Field
The invention relates to a travel crowd identification method based on subway card swiping data, and belongs to the technical field of traffic data analysis and modeling.
Background
The resident trip data is often used for reflecting urban traffic development conditions and guiding urban traffic management and planning, and the subway card swiping data contains a large number of resident trip records due to great passenger flow attraction and can extract and reflect behavior characteristics of subway trip users; with the recent development of traffic information technology, how to discover effective traffic characteristic data from multi-dimensional and disordered original data becomes an important problem to be solved urgently.
In the prior art, survey data is mostly relied on for auxiliary analysis, so that crowd identification is carried out on subway card swiping data, questionnaire survey is time-consuming and labor-consuming, a large amount of real information is difficult to reflect, and secondly, the existing identification method only focuses on identification and characteristic analysis of commuter crowds, analysis of elastic crowds and elasticity degree of the elastic crowds is insufficient, and characteristics of the elastic crowds in the process of trip selection fluctuation are difficult to analyze.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a travel crowd identification method based on subway card swiping data, which can analyze crowds with different elasticity degrees from a large amount of real travel record data, reduce traffic survey cost, analyze travel characteristics, guide traffic management and planning, and meanwhile can lay a theoretical foundation for analyzing the influence and change of subway travel users by other factors.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides a travel crowd identification method based on subway card swiping data, which comprises the following steps of:
step 1) screening subway card swiping data acquired by an automatic subway inspection and ticketing system (AFC) by using an Access database to construct basic data;
step 2) carrying out station matching of entering and leaving stations during morning and evening peaks on individual travel records, which specifically comprises the following steps:
2-1) determining an analysis time period based on subway trip peak time;
2-2) realizing site matching of travel records in an analysis time period according to the Access database, identifying the travel records as 'complete rigidity' if the travel records meet the conditions, and otherwise, performing the step 3;
step 3) quantitatively identifying the types of the crowds which do not meet the site matching conditions based on the elasticity model, specifically comprising the following steps:
3-1) introducing an elasticity concept and constructing an elasticity model;
3-2) analyzing the crowd division types based on the elasticity model, and determining elasticity intervals of various types;
3-3) quantizing the model parameters by using the basic data preprocessed in the step 1), calculating the individual trip elasticity, and identifying the rest crowd types in the step 2) corresponding to each type of elasticity interval;
and 4) integrating the crowd identification results of the step 2) and the step 3) to determine the class of the subway card swiping crowd.
As a further technical scheme of the invention, the screening treatment in the step 1) is as follows: and rejecting data of weekend travel records and system acquisition errors, wherein the data of the system acquisition errors comprise data of stations which are equal to the same station, data of which the station entry time is later than the station exit time, and data of which the travel records are not completely acquired.
As a further technical solution of the present invention, the determination of the analysis period in step 2-1) specifically comprises the following steps:
a. counting passenger flow data of subway full-day travel, and analyzing morning and evening peak time of subway travel;
b. determining the analysis period as: early peak before it, late peak after it.
As a further technical scheme of the invention, the station matching in the step 2-2) is as follows: any two travel records A and B of the same individual in the analysis period determined in 2-1) satisfy the condition that the inbound site of the A-time travel = the outbound site of the B-time travel and the outbound site of the A-time travel = the inbound site of the B-time travel.
As a further technical scheme of the invention, the elasticity model constructed in the step 3-1) is as follows;
wherein K (D) is the degree of elasticity; n is the number of selected limbs; p i Is the selected probability of selecting limb i.
As a further technical solution of the present invention, when the probabilities of all the selected limbs are the same, the degree of elasticity is maximum and K (D) =1; when the probability of one of the selected limbs is 1, the degree of elasticity is minimum and K (D) =0.
As a further technical solution of the present invention, the step 3-2) of classifying the crowd into types and determining the elasticity intervals of each type specifically includes:
a. if n is more than or equal to 4, the crowd is divided into four types: "completely rigid", "partially elastic", and "completely elastic";
the elasticity intervals of each type are as follows:
wherein p is the lowest threshold value of the probability that a traveler has rigid selection demand on a certain selection limb;
b. if n =3, the population is divided into three categories: "completely rigid", "partially rigid", and "partially elastic";
the elasticity intervals of each type are:
c. if n =1 or 2, the travel population is divided into two categories of "completely rigid" or "completely elastic", specifically:
(1) when n =1, K (D) =0, then "fully rigid";
(2) when n =2 and the probability of alternatives for both selected limbs is the same, K (D) =1, then "fully elastic";
(3) when n =2 but the alternative probabilities of the two selected limbs are different, it is "completely elastic" if the alternative probability of the presence of one selected limb is less than p, and "completely rigid" otherwise.
As a further technical scheme of the invention, the quantification of the model parameters in the step 3-3) is as follows: all travel records of a certain card number in the whole month are selected and traversed, the station entering and the station exiting are combined into a travel path in the same way without considering the station entering and exiting time, the number of each path in the whole month is counted, and the total travel path obtained by summing the number of each path is a parameter n in an elasticity model; the ratio of each path to the total travel path is a parameter p in the elasticity model i 。
As a further technical solution of the present invention, the step 4) is specifically: merging the 'completely rigid' crowd in the step 2) with the 'completely rigid' crowd in the step 3) to determine the 'completely rigid', 'partially elastic' and 'completely elastic' crowds.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects: the method is based on a large amount of real non-integrated subway trip data, a crowd type identification model is constructed, the elasticity degree of the pedestrian group is analyzed in a quantitative mode, and a large amount of manpower and material resources are saved for subway resident trip investigation; and secondly, the identified travel population can further analyze travel characteristics for guiding traffic planning and management, particularly can research the change rule of travel selection influenced by other factors, provides theoretical basis for actual operation management, and has profound theoretical and practical significance.
Drawings
Fig. 1 is a flow chart of a travel crowd identification method based on subway card swiping data.
Fig. 2 shows the recognition result of the first line population of the 12-month Nanjing subway in 2012.
Detailed Description
For a better understanding of the present invention, reference should now be made to the following examples, which are set forth to illustrate, but are not to be construed as limiting the scope of the present invention, which are set forth in the following claims and are intended to be limiting in any way.
The invention relates to a travel crowd identification method based on subway card swiping data, which comprises the following steps of:
1) The method comprises the following steps of preprocessing data, namely simply screening and processing original data acquired by an automatic subway inspection and ticketing system (AFC) by using an Access database to construct basic data;
2) Site matching, wherein site matching of entering and leaving sites during morning and evening peaks is carried out on individual travel records:
2-1) determining an analysis time period based on subway trip peak time;
2-2) realizing site matching of the travel records in the analysis time period according to the Access database, identifying complete rigidity if the conditions are met, and continuing the next step if the conditions are not met;
3) And quantitatively identifying the types of the rest crowds based on the elasticity model:
3-1) introducing an elasticity concept and constructing an elasticity model;
3-2) analyzing the crowd division types based on the elasticity model, and determining elasticity intervals of various types;
3-3) quantifying the model parameters by using subway card swiping data, calculating the individual trip elasticity, corresponding to each type elasticity interval, and identifying the rest crowd types in the step 2);
4) And (3) integrating the crowd identification results in the step 2) and the step 3), briefly analyzing, and determining the class of the subway card swiping crowd.
In the step 1), data preprocessing is to eliminate weekend trips and system acquisition error record data in order to ensure the significance of application and the effectiveness of analysis of the crowd identification method, and the latter includes data of the same station when entering the station, data of the time when entering the station is later than the time when leaving the station, and data which is not completely acquired by a trip record.
The determination of the analysis time period in the step 2-1) specifically comprises the following steps:
a. counting the passenger flow data of the subway in the whole day, and analyzing the morning and evening peak time of the subway in the trip;
b. the analysis period for identifying the crowd not only needs to consider the site matching during the peak period, but also considers the rigid trips existing earlier than the early peak and later than the late peak, and determines the analysis period as the early peak and the early peak, the late peak and the later peak.
The meaning of the station matching in the step 2-2) is that any two trip records of the same individual which enter and exit the station within the analysis time period determined by 2-1) are exactly opposite to each other, that is, a certain card number records a and B within the analysis time period determined by 2-1) are taken twice, and the conditions that the entry station of a trip is = the exit station of B trips and the exit station of a trip is = the entry station of B trips are met, so that the station matching is realized.
And 3-1), constructing the elasticity model, wherein a plurality of probability statistical models representing elasticity are provided, convenience in calculation is considered, and the size of the elasticity K (D) is represented by adopting a probability statistical standard deviation to construct the elasticity model.
Therefore, it is
Then, the degree of elasticity K (D) is defined as:
wherein n is the number of selected limbs; i is a selected limb; p i A selected probability of selecting limb i; sigma (P) i ) Criteria for selecting limbs for nA difference; k (D) is the degree of elasticity; r (D) is the degree of rigidity.
The defined elasticity K (D) has two characteristics: (1) when the probability of all the selected limbs is the same, the elasticity is the maximum and is 1; (2) when the probability of a selected limb is 1, the elasticity is minimum and is 0.
Step 3-2) the crowd division types comprise four types of complete rigidity, partial elasticity and complete elasticity, the elasticity degree interval of each type of crowd is determined, model parameters and the applicability thereof are considered, and the size of the limb n is selected for division, and the method specifically comprises the following three conditions:
a. for n greater than or equal to 4, the population can be divided into four complete categories, with the various categories of elasticity intervals, see table 1.
TABLE 1 selection of various elasticity intervals when limbs are greater than or equal to 4
b. For the case where n is equal to 3, the population can be divided into complete 3 classes, each class of elasticity interval, see table 2.
TABLE 2 selection of various elasticity intervals with limbs equal to 3
Wherein p is the lowest threshold value of the probability that a traveler has a rigid selection requirement for a certain selection limb
c. If n =1 or 2, the travel population is classified as "completely rigid" or "completely elastic".
(1) When n =1, i.e. when only one selection case of a limb is selected, K (D) =0, then "fully rigid";
(2) when n =2 and the probability of alternatives for both selected limbs is the same, both 0.5, K (D) =1, then "fully elastic";
(3) when n =2 but the alternative probabilities of the two selection limbs are different, if a certain selection limb i exists, the alternative probability P i &And when p is lower than the threshold, the elastic rubber is completely elastic, otherwise, the elastic rubber is completely rigid.
Quantification of model parameters in step 3-3): the number (n) of the selected limbs represents an optional sample of a certain decision variable, for example, the sample of an optional transportation mode for a certain trip is roughly public transportation, a private car, a bicycle, walking and the like, the limbs are selected according to the trip path measurement in all trip records of a certain card number, the difference degree of a certain passenger in a plurality of paths (including rigid trips such as office work and school, and elastic trips such as shopping and leisure) for selecting a subway trip is analyzed, and the elastic trip degree of the subway for a pedestrian group is represented. Correspondingly, the frequency of each path time relative to the total travel time is approximately regarded as the selected probability P of the selected limb i . The p value is generally determined by related empirical parameters or experts, and can also be obtained by analyzing the data, the data analysis method can adopt the proportion of the number of people with the trip times accumulated frequency reaching a certain threshold value as the size of the p value at this time, namely, the number of card number trips contained in the data statistics of swiping the card by using a subway is utilized, the frequency of the card number trips is calculated, a trip times accumulated frequency curve is drawn, a certain threshold value is used as the upper frequency limit (such as 90% or 95%) of the control type, the ratio of the number of the card number meeting the threshold value range to the number of the card number of the full sample is calculated, and the size of the p value is represented by the ratio.
Step 4) four types of people, namely 'complete rigidity', 'partial elasticity' and 'complete elasticity', can be identified. The "complete rigidity" and the "partial rigidity" can also be combined to identify the type of the passing people.
Examples
In this embodiment, the data of swiping cards of the one-line subway of the Nanjing subway in 12 months of 2012 is used for analysis, and the data information includes information such as card numbers, station entering and exiting time, station entering and exiting stations, and specific codes and meanings thereof, which are shown in Table 3.
TABLE 3 subway card swiping data codes and corresponding meaning description
| Code | Means of | Code | Means of |
| TICKETENGRAVEDID | Card number | STATIONID | Outbound site |
| ENTRYDATETIME | Time of arrival | LINEID | Line code |
| ENTRYSTATIONID | Station of entering station | TICKETTYPE | Card number type |
| TRANSACTIONDATETIME | Time of departure |
Fig. 1 is a flowchart of a travel population identification method based on subway card swiping data in an embodiment of the present invention, where the method includes the following steps:
the first step is as follows: and (4) preprocessing data.
Firstly, analyzing data to be extracted or eliminated, and specifically comprising the following steps:
(1) The weekend trips are mostly elastic trips, and the weekend trips have a small proportion and do not have strong analytical significance in the trips of one month, so the weekend trips are rejected;
(2) Because the subway automatic ticket checking system is not specially used for traffic data analysis, on one hand, data acquisition errors of the system exist; on the other hand, there is often some error data also at the time of data conversion. The method comprises the following steps of carrying out preliminary analysis and inspection on original data acquired by AFC, and rejecting the data with the following problems: (1) the same data of the station entering and exiting; (2) the inbound time is later than the outbound time data; (3) and incomplete data is recorded in the traveling of part of users.
Secondly, the data volume is large, the data volume is stored in an Access database, the data are eliminated by using an SQL query statement of the Access database in consideration of the convenience and effectiveness of data preprocessing, and the data preprocessing work is completed.
The second step is that: and (5) site matching analysis.
Firstly, carrying out statistical analysis on the full-day passenger flow data of the subway in Nanjing city, making a passenger flow fluctuation curve, and determining that the early peak time and the late peak time of the travel of the Nanjing subway are about 8.
Secondly, in order to consider rigid travel crowd who go to work before part of the early peak or delay to go to work after the late peak, the travel record data before 9.
Finally, querying any two trip records (assumed to be A and B) in the peak trip record of the same card number through an SQL statement, wherein the two trip records meet the following conditions: A. inbound site = b. outbound site And a. outbound site = b. inbound site, i.e. a.instigation site = b.stationid a.stationid = b.instigation site And a.ticktienggraved a.ticketgrade = b.tickletensind. The number of people who are identified as the population with complete rigidity and match the site matching line of Nanjing subway in 12 months in 2012 is about 18.8% of the total number of people.
The third step: model parameter and elasticity calculation
Firstly, the number n of selected limbs and the selected probability p in the elasticity model are calibrated i . Traversing all travel records of a certain card number in the whole month, combining the station of entering and the station of leaving the station into a travel path without considering the time of entering and leaving the station, counting the number of each path in the whole month, adding the number of each path to calibrate the parameter n in the elasticity model, and calibrating the parameter p in the elasticity model by using the ratio of each path to the total travel path i 。
Secondly, the elasticity model parameter p is calibrated. Because the subway card swiping data can reflect a large amount of real travel records, the p value is determined by the card swiping data, and the accuracy of model application is improved. By analyzing the accumulated frequency of the trip times of each crowd, the rigidity degree can be measured to a certain extent, the proportion of the number of people with the accumulated frequency of the trip times of more than 95 percent to the number of people of a whole sample is taken as the p value of the time, and the p value of the first line of the Nanjing subway in 12 months in 2012 is 0.7.
And finally, calculating the value of the elasticity K (D) of the full-month trip of each card number by using a formula (2), and calculating elasticity intervals of various types according to the number n of the selected limbs and corresponding to different conditions, thereby identifying the crowd category to which the card number belongs.
Because the travel record data volume is large and the travel record data volume is mostly repeated calculation work of the same method, in order to consider the convenience and quickness of calculation, the process of the crowd identification method is realized by utilizing Python language programming.
The fourth step: and (5) identifying the crowd.
Firstly, summing the site matching crowd in the second step and the completely rigid crowd identified in the third step to form a comprehensive completely rigid crowd;
next, the numbers of "completely rigid", "partially elastic", and "completely elastic" were counted, and the ratios thereof were analyzed to be 40%, 21%, 11%, and 28%, respectively, as shown in fig. 2. Wherein about 40% of the people on the south Jing subway line I are rigid people on duty, go to school and the like, 28% of the people on leisure, shopping and the like are elastic people, and the rest people contain about 32% of partial rigid or elastic people which are large fluctuation people when the attraction of the subway changes. In addition, the result can be used for analyzing the characteristics of commuting crowds, the amount of the crowd with certain rigidity for going out can be measured as 'commuting crowds', the proportion of the commuting crowds accounts for about 61% in the analysis data, and the situation that the Nanjing subway one-line has obvious commuting and going out attractiveness is shown.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can understand that the modifications or substitutions are included in the scope of the present invention disclosed in the present invention, and therefore, the scope of the present invention should be subject to the protection scope of the claims.
Claims (9)
1. A travel crowd identification method based on subway card swiping data is characterized by comprising the following steps:
step 1) screening subway card swiping data acquired by an automatic subway inspection and ticketing system (AFC) by using an Access database to construct basic data;
step 2) carrying out station matching of entering and leaving stations in the morning and evening peak periods on the individual trip records, specifically comprising the following steps:
2-1) determining an analysis time period based on the subway trip peak time;
2-2) site matching is carried out on the travel records in the analysis time period according to the Access database, if the conditions are met, the travel records are identified as 'complete rigidity', and if the conditions are not met, the step 3 is carried out;
step 3) quantitatively identifying the types of the crowds which do not meet the site matching conditions based on the elasticity model, specifically comprising the following steps:
3-1) introducing an elasticity concept and constructing an elasticity model;
3-2) analyzing the crowd division types based on the elasticity model, and determining elasticity intervals of various types;
3-3) quantizing the model parameters by using the basic data preprocessed in the step 1), calculating the individual trip elasticity, and identifying the rest crowd types in the step 2) corresponding to each type of elasticity interval;
and 4) integrating the crowd identification results of the step 2) and the step 3) to determine the class of the subway card swiping crowd.
2. A travel population identification method based on subway card swiping data according to claim 1, wherein the screening process in the step 1) is as follows: and rejecting weekend travel records and data of system acquisition errors, wherein the data of the system acquisition errors comprise data of the same station when the station is accessed, data of the station-accessing time which is later than the station-accessing time, and data of incomplete travel records.
3. A travel population identification method based on subway card swiping data according to claim 1, wherein the determination of the analysis time period in step 2-1) specifically comprises the following steps:
a. counting passenger flow data of subway full-day travel, and analyzing morning and evening peak time of subway travel;
b. determining the analysis period as: early peak before it, late peak after it.
4. A travel crowd identification method based on subway card swiping data according to claim 1, wherein the station matching in step 2-2) is: any two travel records A and B of the same individual in the analysis period determined in 2-1) satisfy the condition that the inbound site of the A trip = the outbound site of the B trip and the outbound site of the A trip = the inbound site of the B trip.
5. A travel crowd identification method based on subway card swiping data according to claim 1, wherein the elasticity degree model constructed in the step 3-1) is;
wherein K (D) is the degree of elasticity; n is the number of selected limbs; p is i Is the selected probability of selecting limb i.
6. A travel crowd identification method based on subway card swiping data according to claim 5, characterized in that when the probability of all the selected limbs is the same, the elasticity is maximum and K (D) =1; when the probability of one of the selected limbs is 1, the degree of elasticity is minimum and K (D) =0.
7. A travel crowd identification method based on subway card swiping data according to claim 5, wherein in the step 3-2), the crowd classification type and the determination of each type elasticity degree interval specifically comprise:
a. if n is more than or equal to 4, the crowd is divided into four types: "completely rigid", "partially elastic", and "completely elastic";
the elasticity intervals of each type are as follows:
wherein p is the lowest threshold value of the rigid selection demand probability of a traveler for a certain selection limb;
b. if n =3, the population is divided into three categories: "completely rigid", "partially rigid" and "partially elastic";
the elasticity intervals of each type are as follows:
c. if n =1 or 2, the travel population is divided into two categories of "completely rigid" or "completely elastic", specifically:
(1) when n =1, K (D) =0, then "fully rigid";
(2) when n =2 and the candidate probabilities of the two selected limbs are the same, K (D) =1, then "fully elastic";
(3) when n =2 but the alternative probabilities of the two selected limbs are different, if the alternative probability of the presence of one selected limb is less than p, the selection is "completely elastic", otherwise, the selection is "completely rigid".
8. A travel population identification method based on subway card swiping data according to claim 1, characterized in that the quantization of model parameters in step 3-3) is: all travel records of a certain card number in the whole month are selected and traversed, the station entering and the station exiting are combined into a travel path in the same way without considering the time of entering and exiting, counting the number of each path in the whole month, and taking the total travel path obtained by summing the number of each path as a parameter n in the elasticity model; the ratio of each path to the total travel path is a parameter p in the elasticity model i 。
9. The travel crowd identification method based on subway card swiping data according to claim 1, wherein the step 4) is specifically as follows: combining the population of "complete rigidity" in step 2) with the population of "complete rigidity" in step 3), and determining the population of "complete rigidity", "partial elasticity" and "complete elasticity".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711163466.3A CN107943920A (en) | 2017-11-21 | 2017-11-21 | A kind of trip crowd recognition method based on subway brushing card data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711163466.3A CN107943920A (en) | 2017-11-21 | 2017-11-21 | A kind of trip crowd recognition method based on subway brushing card data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107943920A true CN107943920A (en) | 2018-04-20 |
Family
ID=61929448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711163466.3A Pending CN107943920A (en) | 2017-11-21 | 2017-11-21 | A kind of trip crowd recognition method based on subway brushing card data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107943920A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147913A (en) * | 2019-06-18 | 2019-08-20 | 八维通科技有限公司北京分公司 | A kind of subway trip control system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766146A (en) * | 2015-04-24 | 2015-07-08 | 陆化普 | Traffic demand forecasting method and system |
| CN105718946A (en) * | 2016-01-20 | 2016-06-29 | 北京工业大学 | Passenger going-out behavior analysis method based on subway card-swiping data |
| CN106384022A (en) * | 2016-11-23 | 2017-02-08 | 东软集团股份有限公司 | Travel behavior forecasting method and device |
| CN107066458A (en) * | 2016-08-26 | 2017-08-18 | 北京车网互联科技有限公司 | A kind of Spatial dimensionality user portrait analysis method based on car networking data |
-
2017
- 2017-11-21 CN CN201711163466.3A patent/CN107943920A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766146A (en) * | 2015-04-24 | 2015-07-08 | 陆化普 | Traffic demand forecasting method and system |
| CN105718946A (en) * | 2016-01-20 | 2016-06-29 | 北京工业大学 | Passenger going-out behavior analysis method based on subway card-swiping data |
| CN107066458A (en) * | 2016-08-26 | 2017-08-18 | 北京车网互联科技有限公司 | A kind of Spatial dimensionality user portrait analysis method based on car networking data |
| CN106384022A (en) * | 2016-11-23 | 2017-02-08 | 东软集团股份有限公司 | Travel behavior forecasting method and device |
Non-Patent Citations (1)
| Title |
|---|
| 云美萍 等: "出行弹性概念及其应用", 《同济大学学报（自然科学版）》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147913A (en) * | 2019-06-18 | 2019-08-20 | 八维通科技有限公司北京分公司 | A kind of subway trip control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600960B (en) | Travel origin-destination point identification method based on space-time clustering analysis algorithm | |
| WO2019214248A1 (en) | Risk assessment method and apparatus, terminal device, and storage medium | |
| CN110400215B (en) | Method and system for constructing enterprise family-oriented small micro enterprise credit assessment model | |
| CN106779429B (en) | Track transfer station passenger flow congestion risk evaluation method based on AFC card swiping data | |
| CN109784970B (en) | Service recommendation method and device based on AFC passenger riding data | |
| CN106650774A (en) | Method for obtaining the regression relationship between the dependant variable and the independent variables during data analysis | |
| Egu et al. | How comparable are origin-destination matrices estimated from automatic fare collection, origin-destination surveys and household travel survey? An empirical investigation in Lyon | |
| CN109684373A (en) | Emphasis party based on trip and call bill data analysis has found method | |
| CN105701180A (en) | Commuting passenger feature extraction and determination method based on public transportation IC card data | |
| Jafari Kang et al. | A procedure for public transit OD matrix generation using smart card transaction data | |
| CN110889092A (en) | Short-time large-scale activity peripheral track station passenger flow volume prediction method based on track transaction data | |
| CN108596664B (en) | Method, system and device for determining unilateral transaction fee of electronic ticket | |
| CN112116256A (en) | Data asset management method | |
| CN110097264A (en) | A kind of measure of group of cities space and economic relation intensity | |
| CN107818415B (en) | General recognition method based on subway card swiping data | |
| CN111291216B (en) | Method and system for analyzing foothold based on face structured data | |
| CN106372964A (en) | Behavior loyalty identification and management method, system and terminal | |
| CN107943920A (en) | A kind of trip crowd recognition method based on subway brushing card data | |
| CN114416686B (en) | Vehicle equipment fingerprint CARID identification system and identification method | |
| Shi et al. | Second-order destination inference using semi-supervised self-training for entry-only passenger data | |
| CN112699955A (en) | User classification method, device, equipment and storage medium | |
| CN107886374B (en) | Bus body advertisement delivery route scheme evaluation method and electronic equipment | |
| Bass et al. | Utility-scale Building Type Assignment Using Smart Meter Data | |
| Wyer et al. | Smartphones and urban transportation mode choice | |
| AU2018101529A4 (en) | A device of evaluating the dewing conditions of a house |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |
|
| RJ01 | Rejection of invention patent application after publication |