CN111681421B - Mobile phone signaling data-based external passenger transport hub centralized-sparse space distribution analysis method - Google Patents
Mobile phone signaling data-based external passenger transport hub centralized-sparse space distribution analysis method Download PDFInfo
- Publication number
- CN111681421B CN111681421B CN202010525189.1A CN202010525189A CN111681421B CN 111681421 B CN111681421 B CN 111681421B CN 202010525189 A CN202010525189 A CN 202010525189A CN 111681421 B CN111681421 B CN 111681421B
- Authority
- CN
- China
- Prior art keywords
- time
- point
- base station
- track
- population
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/42—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for mass transport vehicles, e.g. buses, trains or aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses an analysis method for distribution of sparse-concentrated space of an external passenger transport hub based on mobile phone signaling data, which is characterized in that the mobile phone signaling data are utilized to aim at urban hubs such as high-speed rail stations, railway stations and the like, according to the travel characteristics of various populations, a departure population and an arrival population are identified through the total stay time of a user in a target city on the same day, the stay time of a user in a hub station in a travel track chain on the same day and the logical relationship between the hub station and other stop points in the travel track chain on the same day, then the stop points are judged according to the transfer speed, the stay time and the transfer distance of a base station to identify a travel OD pair, and finally the sparse-concentrated space distribution of the hub population is obtained according to the occurrence time of the departure population and the arrival population at the hub station. The method has universal applicability to multiple cities, is high in accuracy, and plays an important role in analysis, prediction and planning of urban junction traffic.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a method for analyzing the distribution of an external passenger transport hub collecting and distributing space based on mobile phone signaling data.
Background
With the economic growth and the increase of the population flow among cities, the traffic pressure related to urban passenger hubs increases day by day, and particularly, the pressure of hub traffic reaches the peak during holidays. Conventionally, the distribution of the collecting and distributing space of the external passenger transport hub is mainly completed based on the OD survey of the hub station, but because the residence time of the external passenger flow is basically short, especially the passenger flow arriving at the hub station, the transfer mode is selected to the destination at the first time after arriving, and the passenger coordination degree is not high. Therefore, in order to meet the gathering and dredging requirements of the terminal station, a large amount of manpower, material resources and time are needed for large-scale traditional OD survey, and the defects that the precision is not high, the data volume is small, the updating period is long, and only data in a specific time period can be obtained exist. The traditional OD survey is more and more difficult to adapt to the requirement of the external passenger flow volume distribution in a new period, and with the evolution of a big data technology, a big sample is carried out on the hub volume distribution and long-term analysis becomes possible.
The method is characterized in that the starting population and the arriving population of the junction station are different in travel purpose, the selected travel mode and the occupation of road resources are different, the distribution mode of the junction at different time intervals is also different, the passenger flow and the distribution of the collecting and distributing space of the external passenger transport junction of the city are analyzed, the total transport capacity matching condition of each station is combined, the departure shift or the vehicle capacity is adjusted to reduce the waiting time, the occurrence frequency and the time consumption of the retention phenomenon are reduced, and the matching capacity and the dispatching level of the junction station when the junction station deals with the burst flow are improved. Meanwhile, the centralized and sparse mode of the passengers at the junction station can be further analyzed, the sharing rate of public transportation service is analyzed, whether the distribution of the travel modes is reasonable or not is evaluated, the centralized and sparse transport efficiency of the comprehensive transportation junction is improved, the centralized and sparse distance and time of the junction station are shortened, the connection design of a centralized and sparse system is optimized, meanwhile, the method has important significance on the effective management of bus route planning, bus arrangement and taxi configuration at the junction station, and the important fulcrum function of the pivot point in the urban external transportation is fully exerted.
The prior art related to the urban transportation hub mainly focuses on the prediction and modeling of the passenger flow and the prediction of the transportation mode. Hu-Shi et al in 2013 disclose a comprehensive passenger transport hub multi-traffic mode prediction method and system (CN201310446931.X), Duoming et al in 2018 disclose a hub passenger flow space-time distribution prediction modeling method (201811258765.X) based on multi-source data fusion, and a research method for hub collection space-time distribution is still vacant at present.
Disclosure of Invention
In view of the lack of research on a hub collection-sparse space distribution type discrimination method in the prior art, the invention provides an external passenger transport hub collection-sparse space distribution analysis method based on mobile phone signaling data. The invention aims to obtain a target hub base station based on the relation between the geographic information of the hub station and the service range of the base station of an operator aiming at a specific urban hub such as a high-speed rail station, a train station and the like. The method comprises the steps of obtaining a user travel track occupying a hub base station by utilizing time-space information of mobile phone signaling data, identifying and judging types of different populations according to different characteristics of the various populations in space and time and through a logical relation between each staying point and the hub base station in a travel track chain, then judging the staying point according to the transfer speed, the staying time and the transfer distance of the base station to identify travel OD pairs, and finally obtaining the sparse row spatial distribution of the hub population according to the occurrence time of a departure population and an arrival population at the hub station.
The technical scheme is as follows:
a method for analyzing the distribution of an external passenger transport hub collecting and distributing space based on mobile phone signaling data comprises the following specific steps:
s1, obtaining base station information of the target city, and constructing a Thiessen polygon for all base stations of the target city by taking each base station as a central point to divide the service range of each base station; acquiring geographic position information of a target junction station, extracting all base station coordinates covering the service range of the target junction station by contrasting the constructed service range of the urban base station, and defining the extracted base station as a junction base station;
s2, acquiring mobile phone signaling data of all mobile phone users in a target city in a research time period, and preprocessing the signaling data to obtain effective track data of each user every day;
s3, screening target data, identifying the effective movement track of each user every day obtained in S2, filtering out mobile phone users who do not have the target hub base station extracted in S1 in the track of the day, and obtaining track data of the circulating population of the hub station;
s4, clustering track points of each user in the data obtained in S3, located at the hub station in a continuous time period, combining all track points of the users located at different hub base stations in the continuous time period to construct a new virtual hub base station A, defining the geographic position of the virtual base station A as the gravity center point of all the hub base stations extracted in S1, defining the start time start _ time of the track data on the virtual base station A after combination as the start time start _ time of the first track point of the track data of the continuous hub base station which is combined currently, and defining the end time end _ time as the end time end _ time of the last track point of the hub base station;
S5, calculating the staying time at each geographical position of each user according to the track data of each user after the processing of S4, defining the staying time as the time difference between the starting time of the current track data, and the starting time of the next track data, and if the current track point is the last track data of the user, defining the staying time of the user at the current base station, starting time of the current base station, and ending time of the current base station, as the time difference between the starting time of the current base station, and ending time of the current base station, respectively; if the stay time stay _ time is greater than the stop point time threshold T, determining that the geographic position is a stop point of the user, otherwise, determining that the geographic position is a displacement point of the user;
s6, calculating the total stay time total _ state _ time of each user in the target city every day, and defining the total stay time total _ state _ time to be equal to the sum of the stay time state _ time of the user at all the geographical positions of the day;
s7, aiming at the current day track and the stay time static _ time obtained in S5 of each user and the total stay time total _ stay _ time in the target city on the current day obtained in S6, identifying the population type of each user;
S8, obtaining a departure population and an arrival population from S7, extracting the current travel track of the departure population and the arrival population according to S2, judging the stagnation point of the travel track according to three parameters of space velocity, space distance and stay time, and analyzing the stagnation point according to the concept of OD to obtain the travel OD track;
and S9, generating a hub station population travel OD according to the OD track and the departure time and the arrival time of the departure population and the arrival population.
Preferably, the mobile phone signaling data in S2 is trace data provided by an operator, which is cleaned and integrated to record information such as time and space of activities of a mobile phone user in a power-on state, and the same MSID trace data is recorded as a set P i ＝{p 1 ,p 2 ,...,p n Indicating that the ith person has n position recording points, wherein the main field in each position point comprises a mobile phone identification code ID, a timestamp, a base station number base, a base station longitude lng and a base station latitude lat; wherein the time stamp includes a start time start _ time and an end time end _ time.
Preferably, S2 specifically includes the following steps:
s21, deleting repeated data and data with missing fields;
s22, sequencing the mobile phone signaling data of each mobile phone identification code every day according to the starting time of the signaling by taking a mobile phone user as a unit;
S23, merging drift data: aiming at moving track points of each user located on different base stations in adjacent time periods every day, if the distance between the two base stations is smaller than a drift distance threshold Ds, the user is considered to move at the same geographic position in the time period, and data are combined;
s24, merging ping-pong data: aiming at two pieces of track data of each user in discontinuous time periods every day, if the distance between the base stations corresponding to the two pieces of track data is smaller than a ping-pong distance threshold value D j And the interval time of the two pieces of track data is less than ping-pong time threshold T j Then, thenAnd considering that the user moves on the same geographical position from the starting time of the first piece of track data to the ending time of the second piece of track data, and merging the data.
Preferably, S7 specifically includes the following steps:
s71, judging railway transit population: meeting that the total lingering time total _ state _ time in the target city is less than the city total lingering time threshold ST;
s72, judging the railway departure population: the total lingering time total _ state _ time in the target city is larger than the city total lingering time threshold ST, the lingering time state _ time in the virtual junction base station A is larger than the junction station lingering time threshold sigma, and a stopping point exists in a track before A and no stopping point exists in a track after A;
S73, judging railway arrival population: the method comprises the following steps that the total stay time total _ state _ time in a target city is larger than a city total stay time threshold ST, the stay time state _ time in a virtual junction base station A is larger than a junction station stay time threshold sigma, no stay point exists in a track before A, and a stay point exists in a track after A;
s74, judging the railway round-trip population: the method comprises the steps that the total lingering time total _ state _ time in a target city is larger than a city total lingering time threshold ST, virtual hub base stations are occupied at least twice, the lingering time state _ time at the virtual hub base stations is larger than a hub station lingering time threshold sigma each time, the time interval of occupying the virtual hub base stations twice is larger than 2 hours, and the time interval of occupying the virtual hub base stations at the first virtual hub base station A is larger than 2 hours 1 Second virtual base station a of the previous track neutralization 2 Then there is no stop point in the trace and it is at the virtual hub base station A 1 And A 2 There are other dwell points in the trajectory between; or the total lingering time total _ state _ time in the target city is larger than the city total lingering time threshold ST, the virtual hub base station is occupied at least twice, the lingering time at the virtual hub base station is larger than the hinge station lingering time threshold sigma each time, the time interval of occupying the virtual hub base station twice is larger than 2 hours, and the virtual hub base station A is occupied for the first time 1 Second virtual base station a of the previous track neutralization 2 Then all exist in the trackStay at the virtual hub base station A 1 And A 2 There are no stop points in the trace between;
s75, judging city route population: the method comprises the following steps that the total lingering time total _ state _ time in a target city is larger than a city total lingering time threshold ST, the lingering time of a virtual junction base station A is smaller than a junction station lingering time threshold sigma, and lingering points exist in tracks before A and after A;
s76, judging non-railway transit population: the method meets the condition that the total lingering time total _ state _ time in the target city is larger than the city total lingering time threshold ST, the lingering time of the virtual junction base station A is smaller than the junction station lingering time threshold sigma, and no lingering point exists in the tracks before A and after A.
Preferably, S8 specifically includes the following steps:
s81, extracting the sunrise orbit data P of the users from the result of the step S2 according to the departure population and the arrival population judged in the step S7 i Obtaining the important field set according to the main fields of the adjacent position points
p j ＝{start_time j ,end_time j ,ID j ,t j ,d j ,v j }，j＝1,2,...,n，
Wherein: start _ time j Triggering a start time for an event;
end_time j the last time at the base station (after which time a transition is made to the next base station);
ID i A base station site ID;
t j the time spent at the base station in min is calculated as:
t j ＝start_time j+1 -start_time j ，
d j the unit of the spatial distance transferred from the base station point j to the base station point j +1 is m, and the calculation formula is as follows:
d j ＝6371.004*ACOS(SIN(lat j *PI()/180)*SIN(lat j+1 *PI()/180)+ COS(lat j *PI()/180)*COS(lat j+1 *PI()/180)*COS((lng j -lng j+1 )*PI()/180))*1000
where ACOS is the inverse cosine sign, PI () is the circulant value returning latitude and longitude, lat i Is the latitude, lng, of base station point i i Is the latitude of base station i;
v j for the space velocity transferred from base station point j to base station point j +1, the unit is km/h, and the calculation formula is as follows:
s82, identifying the motion state of each piece of signaling data
T for each position point j 、v j Make a judgment if t j If the current position point is more than or equal to 40(min), the current position point is a determined stop point; if t is not more than 10 j ＜40(min)，v j The < 8(km/h) is a possible stopping point, otherwise, is a displacement point;
and S83, correcting and determining a stop point.
Preferably, step S83 further determines whether merging is required for the consecutive stop points obtained in step S82, and further determines whether the possible stop points are determined to be the stop points, which includes the following specific steps:
(1) determination of whether continuous stopover points need to be merged
The set of the determined stopping points and the possible stopping points judged by the analysis S81-S82 is
The set indicates that the ith person has l stop points, including continuous determined stop points and possible stop points; firstly, to 
The consecutive decision stop points in the set are judged,
if no continuous determined stopping point set exists, jumping to (2);
if a continuous determined stopping point set exists, setting the continuous stopping point set as a, setting the number of the determined stopping points in each set as b,
the a sets are sequentially judged,
when b is 2, q is set to each i ,q i+ 1 ；
Calculating the distance between the two points
A. If it is
Merging the two determined stop points; the merging rule is as follows: a. judging the lingering time of the two points; if the residence times are equal, q is retained i (ii) a If the lingering time is unequal, reserving a larger signaling record; b. adding the two residence times; c. let start _ time i+1 ＝start_time i ，end_time i ＝end_time i+1 (ii) a Taking the time with smaller start _ time and the time with larger end _ time, and d, deleting the record or mark between the merging points as 3;
B. if it is
The two determined stopping points are not merged;
if b is larger than 2, sequentially judging two continuous stop points in the set according to the method of the first step;
after the judgment is finished in sequence, the
Updating to obtain new stop point set
(2) To pair
The possible stop points in (1) are judged in turn,
if q is i For possible stopping point, calculating the distance from the last determined stopping point
If it is
The point is considered as a dwell point; if it is
Then the point is considered as a displacement point; obtaining a set S of determined stop points i ＝{s 1 ,...,s m A set indicating that the ith person has m stop points;
(3) repeating the step (1) until all the continuous stopping points are met
All the parking points of the user are obtained at the moment, and the adjacent parking points form a pair of OD pairs.
Preferably, in step (2), the possible dwell point q is i When the stopping point is not determined before, calculating the distance between the stopping point and the determined stopping point after the stopping point is determined
As a basis for judging whether the point is a stop point or a displacement point.
Preferably, the step of generating the terminal station population travel OD at S9 specifically includes:
s91, aiming at the railway departure population, searching a stop point with end _ time earlier than start _ time of a terminal station and the shortest time interval in the OD track of the current day as a starting point O, and taking the terminal station as a terminal point D; if the point O cannot be found in the current-day track, taking the last stop point of the previous day of the user as a starting point O;
s92, aiming at a railway arrival population, searching a stop point which is later in start _ time than end _ time of a terminal station and has the shortest time interval in an OD track of the current day as an end point D, and taking the terminal station as a start point O; if the point D cannot be found in the current day track, taking the first stop point of the user in the next day as an end point D;
s93, if the start point O found in S91 and the end point D found in S92 satisfy the following conditions at the same time:
a. Forming an OD trip distance of 800m with the hub station;
b. the OD trip time formed with the hub station is less than 6 min;
c. the starting point O and the end point D are both pivot stations;
then the next stop point is searched forward or backward to be the O point/D point, namely: updating the starting point O as the previous stop point aiming at the starting population; updating the terminal point D as the next stop point aiming at the arrival population;
and S94, generating a junction station population OD chain by taking the base station at the point O as a departure base station, taking the start _ time as departure time, taking the base station at the point D as an arrival base station and taking the end _ time as arrival time.
The invention has the advantages of
The data source mobile phone signaling data has the characteristics of high sample size, low cost and wide coverage range, the acquisition mode is stable and mature, the spatio-temporal information of the activity track of a user every day can be recorded and tracked more completely, and the data source mobile phone signaling data is a high-quality data source for urban traffic analysis. The method utilizes the travel characteristics of various circulating population of the hub station in space and time, identifies the population types through the logical relationship between the travel track hub button base station obtained through mobile phone signaling data and other stop points in one day, then identifies the travel OD pairs according to the travel track of one day, and obtains the starting point and the destination according to the starting time of the starting population and the arrival time of the arrival population.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The invention is further illustrated by the following examples, without limiting the scope of the invention:
with reference to fig. 1, a method for analyzing the distribution of the collective and sparse spaces of an external passenger transport hub based on mobile phone signaling data includes the following specific steps:
s1, obtaining base station information of the target city, and constructing a Thiessen polygon for all base stations of the target city by taking each base station as a central point to divide the service range of each base station; acquiring geographic position information of a target junction station, extracting all base station coordinates covering the service range of the target junction station by contrasting the constructed service range of the urban base station, and defining the extracted base station as a junction base station;
s2, mobile phone signaling data of all mobile phone users in a target city in a research time period are acquired (the mobile phone signaling data are communication data which are provided by an operator and used for recording information such as time and space of the mobile phone users in the starting state after being cleaned and integrated, and the communication data comprise mobile phone identification codes (IDs), timestamps (including start time, end time, base station number, base station longitude, base station latitude lat and other fields), and the signaling data are preprocessed to acquire effective track data of each user every day;
S3, screening target data, identifying the effective movement track of each user obtained in S2 every day, filtering out mobile phone users who do not have the target junction base station extracted in S1 in the track of the day, and obtaining track data of the circulating population of the junction station;
s4, clustering track points of each user in the data obtained in S3, located at the hub station in a continuous time period, combining all track points of the users located at different hub base stations in the continuous time period to construct a new virtual hub base station A, defining the geographic position of the virtual base station A as the gravity center point of all the hub base stations extracted in S1, defining the start time start _ time of the track data on the virtual base station A after combination as the start time start _ time of the first track point of the track data of the continuous hub base station which is combined currently, and defining the end time end _ time as the end time end _ time of the last track point of the hub base station;
s5, calculating the linger time start _ time of each user at each geographical position (distinguished by different base station numbers base) after the processing of S4, defining the linger time start _ time as the time difference between the start time start _ time of the current track data and the start time start _ time of the next track data, and if the current track point is the last data of the user on the current day, defining the linger time start _ time of the user at the current base station as the time difference between the start time start _ time and the end time end _ time of the signaling data; if the stay time stay _ time is greater than the stop point time threshold T, determining that the geographic position is a stop point of the user, otherwise, determining that the geographic position is a displacement point of the user; in the implementation, the time threshold T of the dwell point can be 10-40 min.
S6, calculating the total stay time total _ state _ time of each user in the target city every day, and defining the total stay time total _ state _ time to be equal to the sum of the stay time state _ time of the user at all the geographical positions of the day;
s7, identifying the population type of each user for the day' S track and stay time, stay _ time, obtained in S5, and the total stay time, total _ stay _ time, in the target city, obtained in S6 for the day;
s8, obtaining a departure population and an arrival population from S7, extracting the current travel track of the departure population and the arrival population according to S2, judging the stagnation point of the travel track according to three parameters of space velocity, space distance and stay time, and analyzing the stagnation point according to the concept of OD to obtain the travel OD track;
and S9, generating a hub station population travel OD according to the OD track and the departure time and the arrival time of the departure population and the arrival population.
Preferably, the mobile phone signaling data in S2 is trace data provided by an operator, which is cleaned and integrated to record information such as time and space of activities of a mobile phone user in a power-on state, and the same MSID trace data is recorded as a set P i ＝{p 1 ,p 2 ,...,p n Indicating that the ith person has n position recording points, wherein the main field in each position point comprises a mobile phone identification code ID, a timestamp, a base station number base, a base station longitude lng and a base station latitude lat; wherein the time stamp includes a start time start _ time and an end time end _ time.
Preferably, S2 specifically includes the following steps:
s21, deleting repeated data and data with missing fields;
s22, sequencing the mobile phone signaling data of each mobile phone identification code every day according to the starting time of the signaling by taking a mobile phone user as a unit;
s23, merging drift data: aiming at moving track points of each user, which are positioned on different base stations in adjacent time periods, every day, if the distance between the two base stations is smaller than a drift distance threshold Ds, the user is considered to move on the same geographical position in the time period, and data are combined; in practice, the drift distance threshold Ds is 100 m;
s24, merging ping-pong data: aiming at two pieces of track data of each user in discontinuous time periods every day, if the distance between the base stations corresponding to the two pieces of track data is smaller than a ping-pong distance threshold value D j And the interval time of the two pieces of track data is less than ping-pong time threshold T j And considering that the user is active at the same geographical position from the starting time of the first piece of track data to the ending time of the second piece of track data, and merging the data. In practice, ping-pong distance threshold D j Taking a ping-pong time threshold T of 100m j Take 120 s.
Preferably, S7 specifically includes the following steps:
S71, judging railway transit population: meeting that the total lingering time total _ state _ time in the target city is less than the city total lingering time threshold ST;
s72, judging the railway departure population: satisfying that the total linger time total _ state _ time in the target city is greater than the city total linger time threshold ST, the linger time state _ time at the virtual hub base station a is greater than the hub station linger time threshold σ, and there is a stop point in the trajectory before a and no stop point in the trajectory after a;
s73, judging railway arrival population: the method comprises the following steps that the total stay time total _ state _ time in a target city is larger than a city total stay time threshold ST, the stay time state _ time in a virtual junction base station A is larger than a junction station stay time threshold sigma, no stay point exists in a track before A, and a stay point exists in a track after A;
s74, judging the railway round-trip population: meeting total stay in target cityThe total _ time is larger than the total urban stay time threshold ST, the virtual hub base station is occupied at least twice, the stay time at the virtual hub base station is larger than the stay time threshold sigma, the time interval of occupying the virtual hub base station twice is larger than 2 hours, and the time interval at the first virtual hub base station A is larger than the total urban stay time threshold ST 1 Second virtual base station a of the previous track neutralization 2 Then there is no stop point in the trace and it is at the virtual hub base station A 1 And A 2 There are other dwell points in the trajectory between; or the total lingering time total _ state _ time in the target city is larger than the city total lingering time threshold ST, the virtual hub base station is occupied at least twice, the lingering time at the virtual hub base station is larger than the hinge station lingering time threshold sigma each time, the time interval of occupying the virtual hub base station twice is larger than 2 hours, and the virtual hub base station A is occupied for the first time 1 Second virtual base station a of the previous track neutralization 2 Then, the remaining points exist in the track and are positioned at the virtual junction base station A 1 And A 2 There are no stop points in the trace between;
s75, judging city route population: the method comprises the following steps that the total lingering time total _ state _ time in a target city is larger than a city total lingering time threshold ST, the lingering time of a virtual junction base station A is smaller than a junction station lingering time threshold sigma, and lingering points exist in tracks before A and after A;
s76, judging non-railway transit population: the method meets the condition that the total lingering time total _ state _ time in the target city is larger than the city total lingering time threshold ST, the lingering time of the virtual junction base station A is smaller than the junction station lingering time threshold sigma, and no lingering point exists in the tracks before A and after A. In the implementation, the residence time threshold sigma of the junction station can be 75 s-10 min, and the total residence time threshold ST of the city can be 30-90 min.
Preferably, S8 specifically includes the following steps:
s81, extracting the sunrise orbit data P of the users from the result of the step S2 according to the departure population and the arrival population judged in the step S7 i Obtaining the important field set according to the main fields of the adjacent position points
p j ＝{start_time j ,end_time j ,ID j ,t j ,d j ,v j }，j＝1,2,...,n，
Wherein: start _ time j Triggering a start time for an event;
end_time j the last time at the base station (after which time a transition is made to the next base station);
ID i a base station site ID;
t j the time spent at the base station in min is calculated as:
t j ＝start_time j+1 -start_time j ，
d j the unit of the spatial distance transferred from the base station point j to the base station point j +1 is m, and the calculation formula is as follows:
d j ＝6371.004*ACOS(SIN(lat j *PI()/180)*SIN(lat j+1 *PI()/180)+ COS(lat j *PI()/180)*COS(lat j+1 *PI()/180)*COS((lng j -lng j+1 )*PI()/180))*1000
where ACOS is the inverse cosine sign, PI () is the circulant value returning latitude and longitude, lat i Is the latitude, lng, of base station point i i Is the latitude of base station i;
v j for the space velocity transferred from base station point j to base station point j +1, the unit is km/h, and the calculation formula is as follows:
s82, identifying the motion state of each piece of signaling data
T for each position point j 、v j Make a judgment if t j If the current position point is more than or equal to 40(min), the current position point is a determined stop point; if t is not more than 10 j ＜40(min)，v j The < 8(km/h) is a possible stopping point, otherwise, is a displacement point;
and S83, correcting and determining a stop point.
Preferably, step S83 further determines whether merging is required for the consecutive stop points obtained in step S82, and further determines whether the possible stop points are determined to be the stop points, which includes the following specific steps:
(1) Determination of whether successive stopping points need to be merged
The set of the determined stopping points and the possible stopping points judged by the analysis S81-S82 is
The set indicates that the ith person has l stop points, including consecutive definite and possible stop points (including definite and possible); firstly, to
The consecutive decision stop points in the set are judged,
if no continuous determined stopping point set exists, jumping to (2);
if a continuous determined stopping point set exists, setting the continuous stopping point set as a, setting the number of the determined stopping points in each set as b,
the a sets are sequentially judged,
when b is 2, q is set to each i ,q i+ 1 ；
Calculating the distance between the two points
A. If it is
Merging the two determined stop points; the merging rule is as follows: a. judging the lingering time of the two points; if the residence times are equal, q is retained i (ii) a If the lingering time is unequal, reserving a larger signaling record; b. adding the two residence times; c. let start _ time i+1 ＝start_time i ，end_time i ＝end_time i+1 (ii) a Taking the time with smaller start _ time and the time with larger end _ time, and d, deleting the record or mark between the merging points as 3;
B. if it is
The two determined stop points are not merged;
if b is larger than 2, sequentially judging two continuous stop points in the set according to the method I;
After the judgment is finished in sequence, the
Updating to obtain new stop point set
(2) To pair
The possible stop points in (1) are judged in turn,
if q is i For possible stopping point, calculating the distance from the last determined stopping point
If it is
The point is considered as a dwell point; if it is
Then the point is considered as a displacement point; obtaining a set S of determined stop points i ＝{s 1 ,...,s m Represents the ith person has m stop points;
(3) repeating step (1) until all the continuous stopping points are met
All the parking points of the user are obtained at the moment, and the adjacent parking points form a pair of OD pairs. In an example, λ is 800 m.
Preferably, in step (2), the point q may be left i When the stopping point is not determined before, calculating the distance between the stopping point and the determined stopping point after the stopping point is determined
As a basis for judging whether the point is a stop point or a displacement point.
Preferably, the step of generating the terminal station population travel OD at S9 specifically includes:
s91, aiming at the railway departure population, searching a stop point with end _ time earlier than start _ time of a terminal station and the shortest time interval in the OD track of the current day as a starting point O, and taking the terminal station as a terminal point D; if the point O cannot be found in the current-day track, taking the last stop point of the previous day of the user as a starting point O;
s92, aiming at a railway arrival population, searching a stop point which is later in start _ time than end _ time of a terminal station and has the shortest time interval in an OD track of the current day as an end point D, and taking the terminal station as a start point O; if the point D cannot be found in the current day track, taking the first stop point of the user in the next day as an end point D;
S93, if the start point O found in S91 and the end point D found in S92 satisfy the following conditions at the same time:
a. forming an OD trip distance of 800m with the hub station;
b. the OD trip time formed with the hub station is less than 6 min;
c. the starting point O and the end point D are both pivot stations;
then the next stop point is searched forward or backward to be the O point/D point, namely: updating the starting point O as the previous stop point aiming at the starting population; updating the terminal point D as the next stop point aiming at the arrival population;
and S94, generating a junction station population OD chain by taking the base station at the point O as a departure base station, taking the start _ time as departure time, taking the base station at the point D as an arrival base station and taking the end _ time as arrival time.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (6)
1. A method for analyzing the distribution of the collection and distribution space of an external passenger transport hub based on mobile phone signaling data is characterized by comprising the following specific steps:
s1, obtaining base station information of the target city, and constructing a Thiessen polygon for all base stations of the target city by taking each base station as a central point to divide the service range of each base station; acquiring geographic position information of a target junction station, extracting all base station coordinates covering the service range of the target junction station by contrasting the constructed service range of the urban base station, and defining the extracted base station as a junction base station;
S2, acquiring mobile phone signaling data of all mobile phone users in a target city in a research time period, and preprocessing the signaling data to obtain effective track data of each user every day;
s3, screening target data, identifying the effective movement track of each user obtained in S2 every day, filtering out mobile phone users who do not have the target junction base station extracted in S1 in the track of the day, and obtaining track data of the circulating population of the junction station;
s4, clustering track points of each user in the data obtained in S3, located at the hub station in a continuous time period, combining all track points of the users located at different hub base stations in the continuous time period to construct a new virtual hub base station A, defining the geographic position of the virtual base station A as the gravity center point of all the hub base stations extracted in S1, defining the start time start _ time of the track data on the virtual base station A after combination as the start time start _ time of the first track point of the track data of the continuous hub base station which is combined currently, and defining the end time end _ time as the end time end _ time of the last track point of the hub base station;
s5, calculating the staying time at each geographical position of each user according to the track data of each user after the processing of S4, defining the staying time as the time difference between the starting time of the current track data, and the starting time of the next track data, and if the current track point is the last track data of the user, defining the staying time of the user at the current base station, starting time of the current base station, and ending time of the current base station, as the time difference between the starting time of the current base station, and ending time of the current base station, respectively; if the stay time stay _ time is larger than the stop point time threshold T, the geographic position is determined to be a stop point of the user, otherwise, the geographic position is determined to be a displacement point of the user;
S6, calculating the total stay time total _ state _ time of each user in the target city every day, and defining the total stay time total _ state _ time to be equal to the sum of the stay time state _ time of the user at all the geographical positions of the day;
s7, identifying the population type of each user for the day' S track and stay time, stay _ time, obtained in S5, and the total stay time, total _ stay _ time, in the target city, obtained in S6 for the day;
s8, obtaining a departure population and an arrival population from S7, extracting the current day travel track of the departure population and the arrival population according to S2, judging a parking point of the travel track according to three parameters of space velocity, space distance and residence time, and analyzing the parking point according to the OD concept to obtain a travel OD track; s8 specifically includes the following steps:
s81, extracting the sunrise orbit data P of the users from the result of the step S2 according to the departure population and the arrival population judged in the step S7 i Obtaining the important field set according to the main fields of the adjacent position points
p j ＝{start_time j ,end_time j ,ID j ,t j ,d j ,v j }，j＝1,2,...,n，
Wherein: start _ time j Triggering a start time for an event;
end_time j is the last time at the base station;
ID i a base station site ID;
t j the time spent at the base station in min is calculated as:
t j ＝start_time j+1 -start_time j ，
d j For transfer from base station point j to base stationThe spatial distance of the point j +1 is in m, and the calculation formula is as follows:
d j ＝6371.004*ACOS(SIN(lat j *PI()/180)*SIN(lat j+1 *PI()/180)+COS(lat j *PI()/180)*COS(lat j+1 *PI()/180)*COS((lng j -lng j+1 )*PI()/180))*1000
where ACOS is the inverse cosine sign, PI () is the circulant value returning latitude and longitude, lat i Is the latitude, lng, of base station point i i Is the latitude of the base station i;
v j for the space velocity transferred from base station point j to base station point j +1, the unit is km/h, and the calculation formula is as follows:
s82, identifying the motion state of each piece of signaling data
T for each position point j 、v j Make a judgment if t j If the current position point is more than or equal to 40 in unit of min, the current position point is a determined stop point; if t is not more than 10 j < 40 in units of min, v j If the value is less than 8, the unit km/h is a possible stopping point, otherwise, the value is a displacement point;
s83, correcting and determining a stopping point;
s9, generating a hub station population trip OD according to the OD track and the departure time and the arrival time of the departure population and the arrival population, and S9 generating the hub station population trip OD specifically comprises the following steps:
s91, aiming at the railway departure population, searching a stop point with end _ time earlier than start _ time of a terminal station and the shortest time interval in the OD track of the current day as a starting point O, and taking the terminal station as a terminal point D; if the point O cannot be found in the current-day track, taking the last stop point of the previous day of the user as a starting point O;
s92, aiming at a railway arrival population, searching a stop point which is later in start _ time than end _ time of a terminal station and has the shortest time interval in an OD track of the current day as an end point D, and taking the terminal station as a start point O; if the point D cannot be found in the current day track, taking the first stop point of the user in the next day as an end point D;
S93, if the start point O found in S91 and the end point D found in S92 satisfy the following conditions at the same time:
a. forming an OD trip distance of 800m with the hub station;
b. the OD trip time formed with the hub station is less than 6 min;
c. the starting point O and the end point D are both pivot stations;
then the next stop point is searched forward or backward to be the O point/D point, namely: updating the starting point O as the previous stop point aiming at the starting population; updating the terminal point D as the next stop point aiming at the arrival population;
and S94, generating a junction station population OD chain by taking the base station at the point O as a departure base station, taking the start _ time as departure time, taking the base station at the point D as an arrival base station and taking the end _ time as arrival time.
2. The method of claim 1, wherein the mobile phone signaling data in S2 is trace data provided by an operator, which is cleaned and integrated to record the time-space information of the mobile phone user' S activity in the power-on state, and the same MSID trace data is recorded as a set P i ＝{p 1 ,p 2 ,...,p n Indicating that the ith person has n position recording points, wherein the main field in each position point comprises a mobile phone identification code ID, a timestamp, a base station number base, a base station longitude lng and a base station latitude lat; wherein the time stamp includes a start time start _ time and an end time end _ time.
3. The method according to claim 1, wherein S2 specifically comprises the steps of:
s21, deleting repeated data and data with missing fields;
s22, sequencing the mobile phone signaling data of each mobile phone identification code every day according to the starting time of the signaling by taking a mobile phone user as a unit;
s23, merging drift data: aiming at moving track points of each user, which are positioned on different base stations in adjacent time periods, every day, if the distance between the two base stations is smaller than a drift distance threshold Ds, the user is considered to move on the same geographical position in the time period, and data are combined;
s24, merging ping-pong data: aiming at two pieces of track data of each user in discontinuous time periods every day, if the distance between the base stations corresponding to the two pieces of track data is smaller than a ping-pong distance threshold value D j And the interval time of the two pieces of track data is less than ping-pong time threshold T j And considering that the user is active at the same geographical position from the starting time of the first piece of track data to the ending time of the second piece of track data, and merging the data.
4. The method according to claim 1, wherein S7 specifically comprises the steps of:
s71, judging railway transit population: meeting that the total lingering time total _ state _ time in the target city is less than the city total lingering time threshold ST;
S72, judging railway departure population: satisfying that the total linger time total _ state _ time in the target city is greater than the city total linger time threshold ST, the linger time state _ time at the virtual hub base station a is greater than the hub station linger time threshold σ, and there is a stop point in the trajectory before a and no stop point in the trajectory after a;
s73, judging railway arrival population: the method comprises the following steps that the total stay time total _ state _ time in a target city is larger than a city total stay time threshold ST, the stay time state _ time in a virtual junction base station A is larger than a junction station stay time threshold sigma, no stay point exists in a track before A, and a stay point exists in a track after A;
s74, judging the railway round-trip population: the method comprises the steps that the total lingering time total _ state _ time in a target city is larger than a city total lingering time threshold ST, virtual hub base stations are occupied at least twice, the lingering time state _ time at the virtual hub base stations is larger than a hub station lingering time threshold sigma each time, the time interval of occupying the virtual hub base stations twice is larger than 2 hours, and the time interval of occupying the virtual hub base stations at the first virtual hub base station A is larger than 2 hours 1 Second virtual base station a of the previous track neutralization 2 There is no stop in the subsequent traceIn virtual hub base station A 1 And A 2 There are other dwell points in the trajectory between; or the total lingering time total _ state _ time in the target city is larger than the city total lingering time threshold ST, the virtual hub base station is occupied at least twice, the lingering time at the virtual hub base station is larger than the hinge station lingering time threshold sigma each time, the time interval of occupying the virtual hub base station twice is larger than 2 hours, and the virtual hub base station A is occupied for the first time 1 Second virtual base station a of the previous track neutralization 2 Then, the remaining points exist in the track and are positioned at the virtual junction base station A 1 And A 2 There are no stop points in the trace between;
s75, judging city route population: the method comprises the following steps that the total lingering time total _ state _ time in a target city is larger than a city total lingering time threshold ST, the lingering time of a virtual junction base station A is smaller than a junction station lingering time threshold sigma, and lingering points exist in tracks before A and after A;
s76, judging non-railway transit population: the method meets the condition that the total lingering time total _ state _ time in the target city is larger than the city total lingering time threshold ST, the lingering time of the virtual junction base station A is smaller than the junction station lingering time threshold sigma, and no lingering point exists in the tracks before A and after A.
5. The method of claim 1, wherein the step S83 further determines whether merging is required for the consecutive stop points obtained in S82, and whether determining the stop points is required for the possible stop points, according to the following method:
(1) determination of whether successive stopping points need to be merged
The set of the determined stopping points and the possible stopping points judged by the analysis S81-S82 is
The set indicates that the ith person has l stop points, including continuous determined stop points and possible stop points; firstly, to
The consecutive decision stop points in the set are judged,
if no continuous determined stopping point set exists, jumping to (2);
if a continuous determined stopping point set exists, setting the continuous stopping point set as a, setting the number of the determined stopping points in each set as b,
the a sets are sequentially judged,
when b is 2, q is set to each i ,q i+1 ；
Calculating the distance between the two points
A. If it is
Merging the two determined stop points; the merging rule is as follows: a. judging the lingering time of the two points; if the residence times are equal, q is retained i (ii) a If the lingering time is unequal, reserving a larger signaling record; b. adding the two residence times; c. let start _ time i+1 ＝start_time i ，end_time i ＝end_time i+1 (ii) a Taking the time with smaller start _ time and the time with larger end _ time, and d, deleting the record or mark between the merging points as 3;
B. If it is
The two determined stop points are not merged;
if b is larger than 2, sequentially judging two continuous stop points in the set according to the method of the first step;
after the judgment is finished in sequence, the
Updating to obtain new stop point set
(2) To pair
The possible stop points in (1) are judged in turn,
if q is i For possible stopping point, calculating the distance from the last determined stopping point
If it is
The point is considered as a dwell point; if it is
Then the point is considered as a displacement point; obtaining a set S of determined stop points i ＝{s 1 ,...,s m Represents the ith person has m stop points;
(3) repeating step (1) until all the continuous stopping points are met
All the parking points of the user are obtained at the moment, and the adjacent parking points form a pair of OD pairs.
6. The method of claim 5, wherein in step (2), the possible stopping point q is i When the stopping point is not determined before, calculating the distance between the stopping point and the determined stopping point after the stopping point is determined
As a basis for judging whether the point is a stop point or a displacement point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010525189.1A CN111681421B (en) | 2020-06-10 | 2020-06-10 | Mobile phone signaling data-based external passenger transport hub centralized-sparse space distribution analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010525189.1A CN111681421B (en) | 2020-06-10 | 2020-06-10 | Mobile phone signaling data-based external passenger transport hub centralized-sparse space distribution analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111681421A CN111681421A (en) | 2020-09-18 |
| CN111681421B true CN111681421B (en) | 2022-07-29 |
Family
ID=72454383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010525189.1A Active CN111681421B (en) | 2020-06-10 | 2020-06-10 | Mobile phone signaling data-based external passenger transport hub centralized-sparse space distribution analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111681421B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112637781B (en) * | 2020-11-23 | 2023-10-03 | 广州大学 | User traffic mode distinguishing method based on base station track |
| CN112543427B (en) * | 2020-12-01 | 2021-11-09 | 江苏欣网视讯软件技术有限公司 | Method and system for analyzing and identifying urban traffic corridor based on signaling track and big data |
| CN112822639A (en) * | 2020-12-18 | 2021-05-18 | 河北师范大学 | Method for demarcating airport abdominal area of passengers entering and exiting port based on mobile phone signaling |
| CN112770278B (en) * | 2020-12-22 | 2021-09-07 | 智慧足迹数据科技有限公司 | Mobile phone signaling analysis method and device, computer equipment and storage medium |
| CN112732778B (en) * | 2020-12-28 | 2023-06-20 | 江苏欣网视讯软件技术有限公司 | Traffic hub passenger flow direction identification method based on mobile phone signaling, computer system, server and storage medium |
| CN113473398B (en) * | 2021-06-02 | 2022-08-30 | 中山大学 | Mobile phone signaling data stop point identification method, device and storage medium |
| CN113573238B (en) * | 2021-06-11 | 2022-08-26 | 北京交通大学 | Method for identifying trip passenger trip chain based on mobile phone signaling |
| CN114141008B (en) * | 2021-10-29 | 2023-05-12 | 东南大学 | Shared public transportation service area selection method based on mobile phone signaling data |
| CN114139251B (en) * | 2021-11-14 | 2023-01-17 | 深圳市规划国土发展研究中心 | Integral layout method for land ports of border regions |
| CN115334453A (en) * | 2022-10-17 | 2022-11-11 | 西南交通大学 | High-speed rail station area crowd data processing and identifying method |
| CN116980845B (en) * | 2023-09-18 | 2023-12-26 | 天津市城市规划设计研究总院有限公司 | Method for extracting travel chain information of railway passengers from mobile phone signaling data |
| CN117745108B (en) * | 2024-02-20 | 2024-05-07 | 中国民用航空飞行学院 | Passenger flow demand prediction method and system for advanced air traffic |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117789A (en) * | 2015-07-29 | 2015-12-02 | 西南交通大学 | Resident trip mode comprehensive judging method based on handset signaling data |
| CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
| CN107040894A (en) * | 2017-04-21 | 2017-08-11 | 杭州市综合交通研究中心 | A kind of resident trip OD acquisition methods based on mobile phone signaling data |
| CN108961134A (en) * | 2018-09-05 | 2018-12-07 | 北京工业大学 | Airport passenger travelling OD recognition methods based on mobile phone signaling data |
| CN109905845A (en) * | 2018-12-10 | 2019-06-18 | 华南理工大学 | A kind of bus passenger flow OD acquisition methods based on mobile phone signaling |
| CN110113718A (en) * | 2019-05-31 | 2019-08-09 | 南京瑞栖智能交通技术产业研究院有限公司 | A kind of railway traffic hinge type of population recognition methods based on mobile phone signaling data |
| CN110310477A (en) * | 2019-05-14 | 2019-10-08 | 浙江工业大学之江学院 | Bus passenger flow detection method based on public transport GPS Yu mobile phone signaling data |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013020611A1 (en) * | 2011-08-05 | 2013-02-14 | Telefonaktiebolaget L M Ericsson (Publ) | Generating an od matrix |
-
2020
- 2020-06-10 CN CN202010525189.1A patent/CN111681421B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117789A (en) * | 2015-07-29 | 2015-12-02 | 西南交通大学 | Resident trip mode comprehensive judging method based on handset signaling data |
| CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
| CN107040894A (en) * | 2017-04-21 | 2017-08-11 | 杭州市综合交通研究中心 | A kind of resident trip OD acquisition methods based on mobile phone signaling data |
| CN108961134A (en) * | 2018-09-05 | 2018-12-07 | 北京工业大学 | Airport passenger travelling OD recognition methods based on mobile phone signaling data |
| CN109905845A (en) * | 2018-12-10 | 2019-06-18 | 华南理工大学 | A kind of bus passenger flow OD acquisition methods based on mobile phone signaling |
| CN110310477A (en) * | 2019-05-14 | 2019-10-08 | 浙江工业大学之江学院 | Bus passenger flow detection method based on public transport GPS Yu mobile phone signaling data |
| CN110113718A (en) * | 2019-05-31 | 2019-08-09 | 南京瑞栖智能交通技术产业研究院有限公司 | A kind of railway traffic hinge type of population recognition methods based on mobile phone signaling data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111681421A (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111681421B (en) | Mobile phone signaling data-based external passenger transport hub centralized-sparse space distribution analysis method | |
| CN110113718B (en) | Railway transportation junction population type identification method based on mobile phone signaling data | |
| CN107241512B (en) | Intercity Transportation trip mode judgment method and equipment based on data in mobile phone | |
| CN112150796B (en) | Customized bus stop layout method based on mobile phone signaling data | |
| CN108320501B (en) | Bus route identification method based on user mobile phone signaling | |
| CN105608505B (en) | Resident rail transit trip mode identification method based on mobile phone signaling data | |
| CN108322891B (en) | Traffic area congestion identification method based on user mobile phone signaling | |
| CN111653099B (en) | Bus passenger flow OD obtaining method based on mobile phone signaling data | |
| CN112133090A (en) | Multi-mode traffic distribution model construction method based on mobile phone signaling data | |
| CN112288131B (en) | Bus stop optimization method, electronic device and computer-readable storage medium | |
| CN104766473A (en) | Traffic trip feature extraction method based on multi-mode public transport data matching | |
| CN108961134B (en) | Airport passenger travel OD (origin-destination) identification method based on mobile phone signaling data | |
| CN111091720A (en) | Congestion road section identification method and device based on signaling data and floating car data | |
| CN109035787B (en) | Method for identifying vehicle category by using mobile communication data | |
| CN109729518B (en) | Mobile phone signaling-based urban traffic early peak congestion source identification method | |
| CN110880238B (en) | Road congestion monitoring method based on mobile phone communication big data | |
| CN112511982B (en) | Subway passenger track real-time tracing and restoring method with automatic trip semantic annotation | |
| CN108806301A (en) | A kind of automatic identifying method of public bus information | |
| CN115168529B (en) | Hub passenger flow tracing method based on mobile phone positioning data | |
| CN114446048A (en) | Rail transit traveler full trip chain analysis method based on mobile phone signaling data | |
| CN115714957A (en) | Subway trip identification method, device, equipment and medium based on mobile phone signaling | |
| CN109493601B (en) | Bus branch line setting method | |
| CN113573238B (en) | Method for identifying trip passenger trip chain based on mobile phone signaling | |
| CN113079463A (en) | Tourist attraction tourist travel activity identification method based on mobile phone signaling data | |
| CN111931968B (en) | Method for optimizing public bicycle station layout by using mobile phone GPS data |
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 |