CN112348230B - Subway passenger travel path identification method - Google Patents
Subway passenger travel path identification method Download PDFInfo
- Publication number
- CN112348230B CN112348230B CN202011094717.9A CN202011094717A CN112348230B CN 112348230 B CN112348230 B CN 112348230B CN 202011094717 A CN202011094717 A CN 202011094717A CN 112348230 B CN112348230 B CN 112348230B
- Authority
- CN
- China
- Prior art keywords
- witness
- path
- route
- witnesses
- passenger
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012546 transfer Methods 0.000 claims description 32
- 238000009826 distribution Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000013459 approach Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 15
- 238000012545 processing Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000011664 signaling Effects 0.000 description 7
- 238000011835 investigation Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000007781 signaling event Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a subway passenger travel path identification method. The method comprises the following steps: searching witnesses entering, transferring and exiting the station on each path in the obtained reasonable path set, and forming paths and the number of train number chains of witness evidence chains, wherein the witness evidence chains indicate that witnesses exist at the entering station, the transferring and the exiting station and the train numbers of the witnesses can form series connection, and the witnesses indicate passengers of which travel paths are determined; and determining a travel path of the target passenger based on the witness evidence chain. According to the invention, the passengers with the determined travel routes and train numbers are used as witnesses to make evidences for the travel routes of the target passengers, so that the travel routes of the subway passengers can be accurately, conveniently and efficiently identified, and the selection rules of the travel routes of the subway passengers can be mastered.
Description
Technical Field
The invention relates to the technical field of passenger flow monitoring, in particular to a subway passenger travel path identification method.
Background
The condition that the travel path of the passenger is known is the premise that the subway operation management level is improved, and only by fully mastering the path selection rule and characteristics of the passenger in a road network, the driving plan and the operation management and control scheme can be reasonably formulated and optimized. For an urban rail transit system with a plurality of operation units, the real travel route of the passenger is mastered, so that the accurate clearing and clearing can be realized, and an effective incentive mechanism is favorably established to promote operators to improve the line service level.
In the prior art, methods for identifying travel paths of passengers mainly include three types:
the first is to build a path selection model. The path selection model is based on a random utility theory, each travel scheme in the traffic network is considered to have a determined utility value, the utility of the travel scheme is influenced by individual differences of passengers and random factors, the random factors are assumed to obey certain distribution, a non-ensemble model is established according to the distribution, and the passengers select the paths considered to be optimal based on different perception costs. Generally, the influence factors considered by the model on the passenger selecting the route include travel time, transfer times, walking distance, carriage congestion degree and the like, sample data is obtained through field investigation or questionnaire and model parameters are estimated, and then the route distribution is carried out on the travel passenger by using the model.
The second type is using AFC (Automatic corner Collection System) data. The AFC data belongs to full sample data, can reflect the station-entering and station-exiting time and space information of each passenger entering and exiting the track system, but cannot directly reflect the track of the passenger in the track system. The existing methods are divided into two types: firstly, AFC data and a path selection model are combined, travel time recorded by the AFC data is used as an observed value, and parameters of the path selection model are calibrated. And secondly, judging according to the time element of AFC, assuming that the platform is not detained, passengers arriving at the platform can sit on the first train encountered by the passengers, assuming that the passenger traveling time follows normal distribution and the passenger arrival time follows random distribution, and searching for a path with the highest matching degree according to the passenger traveling time.
The third category is using handset signaling data. The mobile phone signaling data can reflect the track of switching base stations by people, but can not determine whether the mobile phone is a subway trip or not. The passenger travel path identification based on the mobile phone signaling data is mainly realized by screening subway travel through a travel station matching algorithm and a path validity judging method.
Through analysis, the three technical schemes for identifying the passenger travel path mainly have the following defects:
there are three key problems to the method of path selection model that are difficult to solve. One is that some of the attributes in the model are difficult to measure accurately. Accurate routing requires the input of stage attributes that affect the perceived cost of passengers, such as waiting time, time in the car, transfer time, etc., which are difficult to evaluate accurately in crowded situations. Secondly, the investigation cost is high. In order to obtain the riding Preference data of the passengers, experimenters need to carry out field investigation at a site, inquire the origin-destination (origin-destination) and the riding route of the passengers, namely behavior investigation (modified Preference), or issue a riding path selection intention questionnaire, namely intention investigation (conditioned Preference), and both ways of investigating and processing the data are time-consuming and labor-consuming, and the obtained data are easy to have errors. And thirdly, the parameters have no universality. Road network structures and path attributes among different OD pairs are different, parameters in the model are also different, limited survey data are difficult to serve for a large-scale road network, and calibrated uniform parameters cannot be accurately suitable for the OD pairs.
With the existing method of using AFC data, neither the path selection model nor the time distribution can reflect the real travel path of the passenger. The passengers select a certain path, so that the passengers have the path selection feature, but not select a certain path due to the path selection feature, and the passengers with different characters and different traveling speeds travel in different paths at different travel times to form travel time distribution instead of the travel time distribution, so that the passengers travel in a certain path. For example, when travel time distributions of several routes are obtained, the actual travel route of a certain passenger cannot be estimated, and even the probability of traveling on a certain route is difficult to estimate, because the number of people traveling on several routes is different, and the number of people traveling on each route is just the result of the selection of the passenger route, and therefore the passenger falls into a trap of the circulation demonstration. Moreover, the assumption set by the existing method is difficult to satisfy in reality, and obstacles can be encountered in the practical application process.
For the method using the mobile phone signaling data, although mobile phone signaling data mining provides a possibility for directly acquiring a travel route of a passenger, since a communication signal is not in a 100% stable state at any time, a behavior of crossing a location area may occur in a travel process, and a base station does not record a signaling event of updating the location area, so that a large error exists. In addition, the passenger travel path obtained by mining the mobile phone signaling data cannot reflect the arrival time and the departure time. In addition, the mobile phone signaling data belongs to a mobile operator, and a data acquisition channel is limited, so that the method cannot be widely applied to daily operation of the subway.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method for identifying trip paths of subway passengers, which aims at a subway network, particularly a complex subway network, and accurately identifies each trip path of each passenger by mining AFC data so as to completely recover the trip chain of each passenger.
The technical scheme of the invention is that the method for identifying the travel path of the subway passenger comprises the following steps:
searching witnesses entering the station, transferring and exiting the station on each path in a centralized manner on the obtained reasonable paths to form paths of witness evidence chains and the number of train number chains, wherein the witness evidence chains indicate that witnesses exist at the station entering, transferring and exiting the station and the train numbers of the witnesses can form series connection, and the witnesses indicate passengers of which travel paths are determined;
and determining a travel path of the target passenger based on the witness evidence chain, wherein if the path and the number of the train number chains of the witness evidence chain are both equal to 1, the path is taken as the travel path of the target passenger, the train number chain is taken as the travel train number chain of the target passenger, and if the path and the number of the train number chains of the witness evidence chain are more than 1, the travel path of the target passenger is determined by using a voting mechanism.
Compared with the prior art, the method has the advantages that the passenger capable of directly determining the travel route and the train number is used as a witness, evidences are made for the travel route of the target passenger, and the witness evidence chain is used for recovering all elements of the subway passenger travel chain, including station-entering time, waiting time, riding route, train number, station-leaving time and the like. By the method, the trip path of the subway passenger can be accurately, conveniently and efficiently identified, the selection rule of the trip path of the subway passenger is mastered, and the subway operation management is guided.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic diagram of a typical trip chain for a subway passenger;
fig. 2 is a schematic diagram illustrating recovery of a passenger traveling process according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a witness entering, transferring, and exiting a station according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of the off-site peak settling time of five-way residences of Beijing Hai lake according to one embodiment of the invention;
FIG. 5 is a schematic diagram of a five-way off-peak hours of the Beijing Haitai lake according to one embodiment of the invention;
fig. 6 is a flowchart of a subway passenger travel path identification method according to one embodiment of the present invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as exemplary only and not as limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be discussed further in subsequent figures.
At present, the real path of each passenger for each trip cannot be identified only by means of surface information such as AFC data and train schedules. Aiming at the problem, the invention provides a subway passenger travel path identification method. Briefly, the method comprises: searching witnesses entering, transferring and exiting the station on each path in the obtained reasonable path set, and forming paths and the number of train number chains of witness evidence chains, wherein the witness evidence chains indicate that witnesses exist at the entering station, the transferring and the exiting station and the train numbers of the witnesses can form series connection, and the witnesses indicate passengers of which travel paths are determined; and determining a travel path of the target passenger based on the witness evidence chain, wherein for the condition that the path and the number of train number chains of the witness evidence chain are both equal to 1, the path is taken as the travel path of the target passenger, the train number chain is taken as the travel train number chain of the target passenger, and for the condition that the path and the number of train number chains of the witness evidence chain are more than 1, the travel path of the target passenger is determined by utilizing a voting mechanism.
Specifically, the invention uses the passenger with the determined travel path as a witness and uses a witness evidence chain to recover the travel path of the subway passenger. The inventor notices that in the process of subway travelling, passengers are not isolated travelling, and there are generally co-travelers in a train, and although the co-travelers do not know each other, some relation can be established between the co-travelers, one person can make a presence certificate for the other person, and the presence certificate can add more information to help find out the real travelling path of the traveler. By utilizing the rule, the invention converts the visual angle under the background of big data, solves the complex problem by utilizing a brand new simple rule and realizes the recovery and reconstruction of the real travel path of the subway passengers.
For ease of understanding, the basic principles of the present invention are first described. Referring to fig. 1, a typical subway trip consists of (1) entering and swiping a card, (2) walking to a platform for waiting, (3) taking a bus, (4) transferring and waiting, (5) taking a bus, (6) walking to a gate, and (7) swiping a card for exiting. (1) The times of (1) and (7) may be obtained and determined directly from the AFC data; (3) the time of (5) and (5) can obtain the optional riding interval through the train timetable, but can not determine which riding interval is; the walking speed of each passenger is different, and the walking distance of the passengers is different due to different positions of the lower carriage; (6) the time of (a) cannot be directly determined; (2) the time of (4) and (4) is actually composed of walking time and waiting time, wherein the walking time and the waiting time have the same characteristics as those of (6) and have differences, and the waiting time has uncertainty because passengers are detained due to the fact that the carriages are crowded and cannot take the bus. Therefore, the times of (2) to (6) are actually uncertain except the times of (1) and (7), which makes it difficult to know the real travel path and each section time of the passenger.
Fortunately, even in particularly complex subway networks, the travel routes of some passengers can be determined. For example, if the travel time of the passenger is less than the shortest travel time of other travel paths, meaning that the passenger cannot travel in other paths, the passenger must select the path. After the riding routes of some people are determined, the train number of riding passengers can be judged through the train timetable, and information such as walking time to a platform, waiting time and walking time to exit is further calculated, so that a complete trip chain is restored. For example, on 26 months in 2018, passenger a swiped at 17.
The whole travel process of the passenger A reveals important information which is helpful for analyzing travel paths of other passengers. Important information disclosed includes: (1) A card is swiped to a west station of a public workshop of the train before the time of 17; (2) Swiping a card to enter a station at a west station of a public village, and walking to reach the station in 1 minute and 22 seconds; (3) The card can be swiped and the like for 1 minute and 42 seconds after the Haihe five-way station is got off. When another passenger B swipes a card to a station in the west station of the public bank before 17.
In the above case, the passenger a is called a witness, and there are many witnesses similar to a that provide a proof of taking a certain train number after getting in for a target passenger, a proof of taking a certain train number after getting out, and a proof of taking a certain train number before transferring another train number. As shown in fig. 3, for line1 (subway No.1 line), witnesses who entered the station a little earlier at station 1 successfully ride M1 trains, but witnesses who followed the station can only ride M2 trains. When the target passenger arrives at the station, if more witnesses of the M1 trains are met, the more probable witnesses the target passenger can possibly take the M1 trains, otherwise, the higher probability is that the target passenger takes the M2 trains. When the station 3 changes, part of witnesses of the M1 trains overtake N1 trains of Line2 (subway No. 2) by the change, and part of witnesses take the next N2 trains in some cases, for example, passengers may be detained due to long walking distance of the change due to long car position, slow walking speed, or too crowded N1 trains. The specific situation type does not need to be distinguished, and only the target passenger who takes the train of M1 times can take the train of N1 times and also can take the train of N2 times, and the larger the proportion of the witness who transfers the train to the train of N1 times through the train of M1 times, the higher the possibility of taking the train of N1 times by the target passenger. As with the inbound, the more witnesses riding the M1 trains are encountered by the target passenger when the passenger is outbound, the greater the likelihood that the passenger will ride the M1 trains.
The greater the proportion of witnesses that can give a target passenger presence indication on a particular route for a particular number of cars, the greater the likelihood that the target passenger will travel that number of cars on that route. If witnesses cannot form a chain of evidence from departure to transfer to departure on a certain route, the target passenger cannot travel on that route.
In some embodiments, the travel path of the passenger is determined and a witness is found based on the following basic assumptions.
Suppose 1 that the passenger will exit the vehicle as soon as possible after getting off the vehicle.
The factors influencing the passenger outbound time are many, the walking speed of each passenger is different, and the different positions of the carriages of the getting-off vehicle also cause different outbound walking distances, so that the same-wave passengers are different in outbound time, but the passengers generally can be outbound as soon as possible after getting-off. According to previous studies, the same wave passenger outbound time distribution follows an extremum distribution. When the extremum distribution interval is smaller than the departure interval, the outbound crowd will exhibit a significant interval, and it is very easy to know which train the outbound passenger gets off from, as shown in fig. 4 (departure interval is 6 minutes). When the departure interval is so short as to be less than the extreme distribution interval, the outbound persons may be in a continuous state as shown in fig. 5 (the departure interval is 2 minutes 44 seconds). This can present some difficulties in determining which train the passenger is coming from, but can also be addressed, as will be explained later.
Suppose 2, when a certain route is the only one-way direct route between origin and destination and is the shortest route, the passenger must select the route.
In a subway network, multiple reachable paths may exist between the same OD pair, but only a few reasonable paths are available, that is, people generally only select a reasonable path with low impedance utility, but not select an unreasonable path with characteristics of detour, long trip time, multiple transfer times and the like. When a certain route is the only one-line direct route between a certain origin and destination and is the shortest route, the route has absolute advantages no matter travel time or transfer times, and passengers can select the route.
Two conditions of the only one-line direct and shortest path in the assumption must exist at the same time to exclude special situations when a ring line or a semi-ring line exists in the subway network.
Suppose 3, when there is no single-line direct route at a certain origin-destination, and a route is the only 1 route that is changed 1 times and is the shortest route, the passenger must select the route.
When there is no single-line direct path between an OD pair, and one transfer is added on the basis of the hypothesis 2, it is possible to obtain the inference that if a path is the only 1 transfer 1 path and is the shortest path, the passenger must select the path. In this case, the route has absolute advantage regardless of travel time or transfer times, and thus is the only travel route of the OD pair.
In some embodiments, the present invention is defined below in relation to finding a witness and determining a travel path for a passenger.
According to the assumption 1, the passenger does not stop and exit after getting off the vehicle. Therefore, the number of cars taken by the passenger can be determined according to the departure time of the passenger, and the definition of 'directly determined number of cars taken' is satisfied. According to the assumption 2, when a certain route is the only direct route of a single line between a certain origin and destination and is the shortest route, the passenger must select the route. Thus, these express passengers may satisfy the "directly determinable travel path" in the definition, herein, defined as a category of witnesses.
According to assumption 3, when there is no single-line direct route at a certain origin-destination, and a route is the only 1 route for 1 transfer and is the shortest route, the passenger must select the route. Thus, these transfer passengers may satisfy the "directly determinable travel path" in the definition, herein, defined as a category two witnesses.
According to assumption 1, the number of cars when the second type witnesses are out of the station can be determined, and thus the number of cars before transfer can be deduced in reverse. However, in a peak congestion state, the passengers may be detained, and it is necessary to wait for a plurality of trains to smoothly take a bus. Therefore, when the number of cars before transfer of the second category witnesses cannot be determined, the possible numbers of cars are all marked, which is also very useful for the transfer behavior of the following witness target passenger.
Definition 3, minimum outbound time
The minimum time from getting off a station to exiting a station by swiping a card.
And counting the time from the time of getting off the vehicle to the time of card swiping and exiting the vehicle from the station at the peak-balancing moment of a large number of witnesses, wherein the minimum time is the minimum exiting time, which means the time from the time of getting off the vehicle to the time of card swiping and exiting the vehicle at the shortest walking distance and the fastest walking speed. The moment when the train arrives at the station and the minimum time when the train leaves the station are taken as division points, witnesses leaving the station at any moment can be distinguished, and the number of the trains which the witnesses leave the station can be defined.
Definition 4, minimum inbound time
Minimum time from card swipe in to station to get on board.
The time from card swiping to the arrival of a large number of witnesses at the station to the arrival of the large number of witnesses is counted, and the minimum time is the minimum arrival time, which means that passengers can directly get on the vehicle from the card swiping to the arrival of the large number of witnesses at the shortest walking distance and the fastest walking speed without waiting.
Definition 5, minimum transfer time
-minimum time from alighting to transfer to boarding. />
Determination of minimum transfer time: the minimum time from the station to the transfer of the two types of witnesses is counted, which means that the passengers can directly transfer the vehicles without waiting at the shortest walking distance and the fastest walking speed after the vehicles are dropped.
Definition 6, minimum travel time T min From an inbound to a passenger on a certain pathA theoretical minimum travel time out.
The minimum travel time is determined as: after a certain passenger enters the station, the passenger always enters the station, transfers and exits at the shortest distance and the fastest speed, and the passenger can smoothly ride the travel time of the closest train on each line.
Definition 7, witness search scope S — the search scope of witnesses that a target passenger may encounter while entering or exiting a station and transferring.
The determination of the search range of a type of witness when the user leaves the station is as follows: make the target passenger get out at the time t Go out When the train arrives at the time T, the arrival time of the previous train is T previous The outbound distribution 95% confidence interval is T 95 . If it is
One category of witness search range is [ t ] Go out -T 95 /2，t Go out +T 95 /2](ii) a Otherwise, the search range of a type of witness is [ t ] Go out -T 95 /2，t Go out ]。
The determination method of the searching range of the two types of witnesses during the change of the riding is as follows: after the class of witnesses is determined while they are out of the station, the number of cars they take is also determined. No matter where the starting and ending points of the second type witnesses are, the second type witnesses who are transferred to the train number taken by the first type witnesses in the possible travel path of the target passenger are the second type witnesses when the target passenger changes the train number. When the transfer times are more than 1, the number of the vehicles determined by the two types of witnesses of the next transfer is used as the basis for searching the witnesses in the previous transfer.
The determination mode of the searching range of the witness in the approach is as follows: make the target passenger enter the station at the time t Go into When the departure interval of the target line is T interval The departure time of the next train is T next . If it is
One category of witness search range is [ t ] Go into -T interval /2，t Into +T interval /2](ii) a Otherwise, the search range of a type of witness is [ t ] Into ，t Go into +T interval /2]。
Based on the above assumptions and definitions, in one embodiment, with reference to fig. 6, the method for identifying a travel path of a subway passenger is provided, which includes the following steps:
step S1, in a given OD pair, a reasonable path set R is generated by using a public transportation recommended route of a Baidu map API, and the included paths are alternative paths which are generally selected by passengers in daily travel.
And S2, judging whether the minimum travel time of each path is less than the travel time of the target passenger or not, and if the travel time of the target passenger is less than the minimum travel time of a certain path, the path is invalid.
And S3, judging whether the paths can form witness evidence chains or not, namely witnesses exist in the processes of entering, transferring and exiting, and the train numbers of the witnesses can form series connection to form the witness evidence chains. If a witness chain cannot be formed, the path is invalid.
And S4, judging the path and the number of train number chains capable of forming the witness evidence chain. If the number of the paths and the number of the train number chains are both equal to 1, the paths are the only possible travel paths of the target passengers, and the train number chains are the only possible travel train number chains of the passengers, which means that the travel of the target passengers is directly recovered. If the number of the paths and the train number chains is larger than 1, triggering a voting mechanism, and taking the path with the maximum number of votes and the train number chains as the travel path of the target passenger.
And S5, preferentially, taking the target passenger capable of directly restoring the travel route as a witness for determining the route and the train number chain, and bringing the target passenger into the witness search range for iteration.
In one embodiment, the voting mechanism is as follows:
a) One type of witness and two types of witnesses all have voting rights.
B) The closer the card swiping time of the witness class and the target passenger is, the greater the voting weight is, the number of the witness class is set to be N, and the nth card swiping time of the witness class X is close to the target passenger, the weight w of the witness class X is X ＝N-n+ 1。
C) The two types of witness votes do not differentiate weights.
D) The voting result of a certain train number chain of a certain path is as follows:
when the outbound route and the outbound direction of the alternative route are the same, the voting result of a certain route train number chain = (the number of the first-class witness votes entering the route train number of the route train number chain, the number of the second-class witness votes transferred by the route train number chain, the number of the first-class witness votes exiting the route train number of the route train number)/(the total number of the first-class witness votes entering the route, the total number of the second-class witness votes transferred by the route, and the total number of the first-class witness votes exiting the route).
When the outbound lines or directions of the alternative paths are different, calculating the probability P of the outbound of a certain train number chain of a certain path at a target moment according to the outbound distribution, wherein the voting result = Px (the number of the witness votes of the first class of the inbound of the train number chain of the path is multiplied by the number of the witness votes of the second class of the transfer of the train number chain of the path)/(the total number of the witness votes of the first class of the inbound of the path is multiplied by the total number of the witness votes of the second class of the transfer of the path).
In conclusion, the invention can directly determine the passengers of the travel route and the train number as witnesses and make evidences for the travel route of the target passenger; counting the minimum outbound time, the minimum inbound time and the minimum transfer time of each station by using witnesses; and directly restoring the real travel path of the subway passenger by using the witness evidence chain or judging the possible travel path by witness voting. By the method, the trip path of the subway passenger can be accurately, conveniently and efficiently identified, and the selection rule of the trip path of the subway passenger is mastered, so that effective guidance is provided for subway operation management.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer-readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be interpreted as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or an electrical signal transmitted through an electrical wire.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
Computer program instructions for carrying out operations of the present invention may be assembler instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the market, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.
Claims (8)
1. A subway passenger travel path identification method comprises the following steps:
searching witnesses entering, transferring and exiting the station on each path in the obtained reasonable path set, and forming paths and the number of train number chains of witness evidence chains, wherein the witness evidence chains indicate that witnesses exist at the entering station, the transferring and the exiting station and the train numbers of the witnesses can form series connection, and the witnesses indicate passengers of which travel paths are determined;
determining a travel path of a target passenger based on the witness evidence chain, wherein for the condition that the path and the number of train number chains of the witness evidence chain are both equal to 1, the path is taken as the travel path of the target passenger, the train number chain is taken as the travel train number chain of the target passenger, and for the condition that the path and the number of train number chains of the witness evidence chain are greater than 1, the travel path of the target passenger is determined by using a voting mechanism;
wherein the witness evidence chain is formed according to the following steps:
in a given OD pair, generating a reasonable path set by using the public transportation recommended route, wherein the reasonable path set comprises alternative paths selected by passengers in daily travel;
judging whether the minimum travel time of each alternative path is less than the travel time of the target passenger, if the travel time of the target passenger is less than the minimum travel time of the alternative path, considering the alternative path as invalid, and further screening out an effective alternative path;
forming witness evidence chains based on the screened effective alternative paths;
wherein, searching the witnesses of entering station, transferring and exiting station on each path in the obtained reasonable path set comprises:
determining a first type of witness and a second type of witness, wherein the first type of witness is a direct passenger determining a travel path and a train number, and the second type of witness is a 1-time transfer passenger determining the travel path and the train number;
the search range of a type of witness when the station is out is determined as: if it is
Witness search rangeIs enclosed as [ t Go out -T 95 /2，t Go out +T 95 /2](ii) a Otherwise, the search range of a type of witness is [ t ] Go out -T 95 /2，t Go out ]Wherein the target passenger is made to be out of station at the time t Go out The time of the target passenger leaving the station and the time of the last train arrival is T previous The interval of confidence intervals of outbound distribution at a set threshold is T 95 ，/>
Is the minimum outbound time;
the search range of two kinds of witnesses during changing the ride is determined as follows: taking the second type witnesses transferred to the number of cars taken by the first type witnesses in the route where the target passenger possibly travels as the second type witnesses when the target passenger takes the second type witnesses, and when the transfer times are more than 1, taking the number of cars determined by the second type witnesses which are transferred at the next time as the basis for searching for witnesses at the previous time;
the search range of a witness in the approach is determined as follows: make the target passenger enter the station at the time t Into When the departure interval of the target line is T interval The departure time of the next train is T next If at all
One category of witness search range is [ t ] Go into -T interval /2，t Into +T interval /2]Otherwise, the search range of a type of witness is [ t ] Into ，t Go into +T interval /2]Wherein->
Is the minimum time to arrive at the station.
2. The method according to claim 1, wherein determining the travel path of the target passenger using a voting mechanism comprises the sub-steps of:
when the outbound route and the outbound direction of the alternative route are the same, the voting result of a certain route train number chain is expressed as (the number of the first-class witness votes entering the route train number chain of the route x the number of the second-class witness votes transferred by the route train number chain of the route x the number of the first-class witness votes exiting the route train number of the route)/(the total number of the first-class witness votes entering the route x the total number of the second-class witness votes transferred by the route x the total number of the first-class witness votes exiting the route);
when the outbound lines or directions of the alternative paths are different, calculating the probability P of outbound of a certain train number chain of a certain path at a target moment according to outbound distribution, wherein the voting result is represented as Px (the number of the witness votes of the train number chain of the path in the first class of the inbound route is multiplied by the number of the witness votes of the train number chain of the path in the second class of the transfer) (the total number of the witness votes of the train number chain of the path in the first class of the inbound route is multiplied by the total number of the witness votes of the path in the second class of the transfer);
and taking the path and train number chain with the maximum ticket number as the travel path of the target passenger.
3. The method according to claim 1, wherein the minimum time to exit is determined by counting the time from when the category of witnesses alight leaves the station to when the category of witnesses exits the station by swiping a card, and the minimum time to enter is determined by counting the time from when the category of witnesses enters the station by swiping a card to when the category of witnesses enters the station by swiping a card.
4. The method of claim 1, wherein determining a category of witnesses comprises: determining the number of the passengers to take according to the time for the passengers to leave the station under the condition that the passengers leave the station without stopping after getting off the station; determining a riding route of a class of witnesses by taking a passenger as a principle that the passenger selects a route as a rule when the route is a unique single-line direct route between a certain origin-destination point and is a shortest route;
determining two types of witnesses includes: when a certain origin-destination point has no single-line direct route, a certain route is the only 1 route for 1 transfer and is the shortest route, and the riding route of the second type of witnesses is determined by taking the route selected by the passenger as a principle; and for the condition that the passengers do not stop after getting off the bus, namely get off the bus, determining the number of the passengers to take according to the time for the passengers to get off the bus, and recording all possible numbers of the passengers to take for the passengers who cannot determine the number of the passengers.
5. The method of claim 1, further comprising: and taking the target passenger directly recovering the travel path as a witness determining the path and the train number chain under the condition that the number of the path and the train number chain of the witness evidence chain are both equal to 1, and taking the target passenger into a witness searching range for iteration.
6. The method of claim 2, wherein the weight of a type of witness ' vote is determined based on the proximity of the witness to the target passenger's card swipe time, with witness X's vote weight denoted as w X N-N +1, N is a category of witness number, which approaches the target passenger at time N of the witness X card swipe.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
8. A computer device comprising a memory and a processor, on which memory a computer program is stored which is executable on the processor, characterized in that the processor realizes the steps of the method of any one of claims 1 to 6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011094717.9A CN112348230B (en) | 2020-10-14 | 2020-10-14 | Subway passenger travel path identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011094717.9A CN112348230B (en) | 2020-10-14 | 2020-10-14 | Subway passenger travel path identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112348230A CN112348230A (en) | 2021-02-09 |
| CN112348230B true CN112348230B (en) | 2023-04-07 |
Family
ID=74360735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011094717.9A Active CN112348230B (en) | 2020-10-14 | 2020-10-14 | Subway passenger travel path identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112348230B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320998A (en) * | 2015-09-22 | 2016-02-10 | 中山大学 | IC card swiping data based optimal bus travel route acquisition method |
| CN110309936A (en) * | 2019-04-03 | 2019-10-08 | 广州市交通规划研究院 | A kind of sub-interchange recognition methods combined based on mobile phone location data and path estimating |
| CN110942198A (en) * | 2019-11-27 | 2020-03-31 | 重庆市交通规划研究院 | Passenger path identification method and system for rail transit operation |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714391A (en) * | 2012-09-29 | 2014-04-09 | 国际商业机器公司 | Method and device for reckoning transfer routes in public transport system |
| CN105890600A (en) * | 2016-04-14 | 2016-08-24 | 南京大学 | Subway passenger position inferring method based on mobile phone sensors |
| CN109726842A (en) * | 2017-10-30 | 2019-05-07 | 比亚迪股份有限公司 | Determining method of path and its device by bus |
| CN108055645A (en) * | 2018-01-19 | 2018-05-18 | 深圳技术大学（筹） | A kind of path identification method and system based on mobile phone signaling data |
| US11164335B2 (en) * | 2018-11-06 | 2021-11-02 | International Business Machines Corporation | Passenger travel route inferencing in a subway system |
| CN110674974A (en) * | 2019-08-28 | 2020-01-10 | 南京理工大学 | Effective path set generation method for urban rail transit passenger travel |
-
2020
- 2020-10-14 CN CN202011094717.9A patent/CN112348230B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105320998A (en) * | 2015-09-22 | 2016-02-10 | 中山大学 | IC card swiping data based optimal bus travel route acquisition method |
| CN110309936A (en) * | 2019-04-03 | 2019-10-08 | 广州市交通规划研究院 | A kind of sub-interchange recognition methods combined based on mobile phone location data and path estimating |
| CN110942198A (en) * | 2019-11-27 | 2020-03-31 | 重庆市交通规划研究院 | Passenger path identification method and system for rail transit operation |
Non-Patent Citations (1)
| Title |
|---|
| 孙延硕 ; 徐瑞华 ; .基于AFC数据的城市轨道交通乘客出行路径推算.交通与运输(学术版).2011,(02),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112348230A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112598182A (en) | Intelligent scheduling method and system for rail transit | |
| CN109115237B (en) | Riding position recommendation method and server | |
| Li et al. | Public bus arrival time prediction based on traffic information management system | |
| KR101582283B1 (en) | Method for estimating route of passenger in a metro network | |
| CN109903555B (en) | Bus passenger getting-off data prediction method and system based on big data | |
| US9372086B2 (en) | Control system for indicating if people can reach locations that satisfy a predetermined set of conditions and requirements | |
| CN112507624A (en) | Intercity highway trip mode identification model construction and identification method and device | |
| JP6307376B2 (en) | Traffic analysis system, traffic analysis program, and traffic analysis method | |
| CN113344268B (en) | Urban traffic trip data analysis method | |
| CN112348230B (en) | Subway passenger travel path identification method | |
| JP6267276B2 (en) | Route guidance method, route guidance device, and computer program | |
| CN114694850B (en) | Epidemic situation tight-seal crowd tracing method for subway network | |
| JP5955580B2 (en) | Route guidance method, route guidance device, and computer program | |
| CN114971085B (en) | Method and system for predicting accessibility of bus station and storage medium | |
| JP2021064020A (en) | Boarding/alighting determination device, boarding/alighting determination method, and boarding/alighting determination program | |
| CN116451867A (en) | Subway short-time passenger flow prediction method based on space-time travel path calibration | |
| Zhao et al. | A method for classifying red signal approaches using train operational data | |
| CN112101677B (en) | Public transport travel path planning method, device, equipment and storage medium | |
| JP7425680B2 (en) | Navigation device and navigation method | |
| JP7095892B2 (en) | Information processing system, information processing method and information processing program | |
| CN111754760B (en) | Method and device for determining bus getting-off station and upper computer | |
| CN107121145A (en) | A kind of information processing method and device | |
| CN113657725A (en) | Bus route and scheduling optimization method, system, device and medium | |
| Xie et al. | Data-driven identification and analysis of passenger riding paths in megacity metro system | |
| Tan et al. | Enhancing urban metro system resilience under disruptive events through multi-agent reinforcement learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |