WO2015096400A1 - 一种利用移动通信数据挖掘进行公交规划的方法 - Google Patents

一种利用移动通信数据挖掘进行公交规划的方法 Download PDF

Info

Publication number
WO2015096400A1
WO2015096400A1 PCT/CN2014/079385 CN2014079385W WO2015096400A1 WO 2015096400 A1 WO2015096400 A1 WO 2015096400A1 CN 2014079385 W CN2014079385 W CN 2014079385W WO 2015096400 A1 WO2015096400 A1 WO 2015096400A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
crowd
point
data
parking point
Prior art date
Application number
PCT/CN2014/079385
Other languages
English (en)
French (fr)
Inventor
刘淑霞
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to US15/107,438 priority Critical patent/US20170032291A1/en
Publication of WO2015096400A1 publication Critical patent/WO2015096400A1/zh

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/20Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047Optimisation of routes or paths, e.g. travelling salesman problem
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0631Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125Traffic data processing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/023Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • G06Q50/40

Definitions

  • the invention relates to the application of big data mining in the field of mobile communication in smart city bus route planning, and particularly relates to a method for public transportation planning by using mobile communication data mining.
  • the forecast of passenger flow and passenger flow distribution in public transport planning is the basis of the planning plan, and whether the forecast result is scientifically reasonable will ultimately affect the benefit evaluation of the plan.
  • Passenger flow OD survey (0 is from English ORIGIN, indicating the starting point of the trip, "D" is from English DESTINATION, indicating the destination of the trip.) That is, the traffic start and end point survey is also called OD traffic survey, OD traffic refers to The amount of traffic travel between the starting and ending points.
  • urban passenger flow OD needs to be obtained through resident travel surveys. The usual practice is to conduct a survey of residents. Questionnaires can only be sampled data and cannot reflect the travel needs of most citizens. Or one inspector is required for each door of each bus.
  • the investigator records the arrival time, number of passengers and number of passengers from each vehicle from morning till night.
  • Long-term passenger flow OD observation is quite complicated, it requires a lot of manpower, material resources and financial resources, and the accuracy is difficult to guarantee.
  • the investigation cycle is also long, and the data information is relatively lagging.
  • the technical problem to be solved by the embodiments of the present invention is to provide a method for public transportation planning by using mobile communication data mining, obtaining the life trajectory analysis of the residents in the selected area, and counting the flow of people, the direction of the flow of people, the gathering point of the passengers, and the residence time.
  • An embodiment of the present invention provides a method for performing bus planning, where the method uses mobile communication data for public transportation planning, including:
  • the bus planning is carried out.
  • the crowd data information includes: a population resident point set and a crowd travel feature; the step of obtaining the crowd data information according to the time and space data sets of the multiple users includes: extracting, according to the time and space data set of the user a set of berth points for each user;
  • the step of extracting the mooring point set of the user includes:
  • the spatio-temporal data set of the user includes: a dwell time of the location point and the location point; and extracting a dwell time of the location point of the user according to the spatio-temporal data set of the user, if the location point of the user If the dwell time exceeds the preset mooring point threshold, the location point of the user is marked as a berth point, and the berth point set of the user is established, and a plurality of berth points of the user are collectively established.
  • the step of extracting the repeated berth point set of the user includes:
  • the crowd trip features include: a flow of people, a direction of a person flow, and a feature of the crowd; and the step of performing bus planning according to the data of the crowd includes:
  • a device for performing bus planning wherein the device performs communication planning using mobile communication data, including: an information collection module, an information conversion module, an information conversion module, and a planning module, where
  • the information collection module is configured to: receive mobile signaling data of the mobile terminal in a preset statistical period in a preset statistical area acquired from the operator server, and obtain the mobile terminal according to the mobile signaling data of the mobile terminal. Location update information;
  • the information conversion module is configured to: receive location update information of each mobile terminal, and obtain a spatiotemporal data set of the user corresponding to the mobile terminal;
  • the data mining module is configured to: receive a plurality of time and space data sets of the user, and obtain crowd data information;
  • the planning module is configured to: receive the crowd data information, and perform bus planning according to the crowd data information.
  • the population data information includes: a population resident point set and a crowd travel feature; and the data mining module includes:
  • a berth sub-module configured to receive the spatio-temporal data set of the user, and extract a mooring re-spot sub-module of the user, configured to receive the berth point set of the user, and extract the re-pod-point set of the user;
  • a crowd resident point sub-module configured to receive a plurality of repeated berth points of the user, and aggregate the group of the resident dwell points;
  • the crowd travel feature sub-module is configured to receive a plurality of repeated berth points of the user, obtain a travel trajectory of the working hours of the plurality of the users, and a travel trajectory of the off-hours, and summarize the travel characteristics of the crowd.
  • the time-space data set of the user includes: a location point and a dwell time of the location point; the berth sub-module is configured to receive the spatio-temporal data set of the user by extracting the vacancy set of the user:
  • a set of berths of the user is established, and a set of berths of the plurality of users is summarized.
  • the repeated berth sub-module is configured to receive the set of vacant points of the user by extracting the set of repeated berths of the user:
  • the degree of repetition of the berth point of the berth point set of the user is greater than a preset repetition degree threshold, marking the repeated berth point of the user, establishing a set of repeated berth points of the user, and summarizing and establishing the plurality of The user's repeated set of berths.
  • the crowd travel characteristics include: a flow of people, a flow of people, and a characteristic of the crowd; the planning module is configured to receive the crowd data information by: performing public transportation planning according to the crowd data information:
  • the present invention has the following beneficial effects:
  • the embodiment of the invention is based on the method of using the mobile communication data mining for public transportation planning, obtains the mobile communication signaling data of the residents in the selected area, and analyzes the living trajectory analysis of the residents in the selected area, and calculates the resident point and the human flow.
  • the flow direction of the people and the characteristics of the crowd can be used as the basic data for the planning and evaluation of the urban comprehensive transportation system.
  • the input of human and material resources for the urban passenger flow OD survey is reduced, and the cost is low and the accuracy is high.
  • FIG. 1 is a flow chart showing a method for public transportation planning using mobile communication data mining in an embodiment of the present invention
  • Figure 2 shows a typical trajectory of a user working from home
  • Figure 3 shows a schematic diagram of the population resident point
  • FIG. 4 is a block diagram showing an apparatus for performing bus planning using mobile communication data mining in an embodiment of the present invention. Preferred embodiment of the invention
  • the guest OD survey content of the embodiment of the present invention mainly includes the start and end point distribution, the travel destination, the travel mode, the travel time, the travel distance, and the travel time. Big data mining of mobile communication signaling data can easily obtain the above information and provide basic data for urban integrated transportation system planning. For the key technical points in the present invention, only the following non-limiting examples are described in conjunction with the accompanying drawings.
  • FIG. 1 is a schematic diagram of a method for performing bus planning according to an embodiment of the present invention, where the method uses mobile communication data for public transportation planning, including:
  • the collected mobile signaling data sources include, but are not limited to, mobile signaling data, mobile phone GPS positioning information, and the like.
  • the location update information includes, but is not limited to, a user's mobile phone number, a location update time, a location cell identity, and the like.
  • Step 102 Obtain a spatio-temporal data set of the user corresponding to each mobile terminal according to the location update information of the mobile terminal.
  • 103 Obtaining crowd data information according to a time and space data set of a plurality of users, where the population data information includes: a population resident point set and a crowd travel feature;
  • the steps of obtaining the population resident point set and the crowd travel feature according to each user's spatio-temporal data set may include:
  • Step 1031 Extract a set of berth points for each user according to a spatio-temporal data set of each user; the spatio-temporal data set of the user includes, but is not limited to: a dwell time of the location point and the location point; and extracting according to the spatio-temporal data set of the user If the dwell time of the user's location point exceeds the preset mooring threshold, the location of the user is marked as a berth, and the user's berth point set is established. Establish a set of berth points for multiple users.
  • Step 1032 Extract a set of repeated berth points for each user according to a set of berth points of the plurality of users. If the degree of repetition of the berth point of the user's berth point set is greater than a preset repetition degree threshold, the mark is the repeated parking of the user. Point, establish the user's repeated berth point set, and summarize the repeated berth points of multiple users. Step 1033: According to the repeated berth point set of multiple users, the crowd resident point set is summarized. Step 1034: According to the repeated parking point set of the plurality of users, the travel trajectory of each user's working hours and the travel trajectory of the off-hours are obtained, and the group travel characteristics are summarized.
  • the crowd data information includes: a population resident point set and a crowd trip feature.
  • Crowd travel characteristics including: human flow, direction of people flow, characteristics of the crowd;
  • the steps for public transportation planning based on crowd data information include:
  • Embodiment 1 City bus route planning.
  • the daily life trajectory of the user is depicted (see Figure 2).
  • Characteristic analysis (repetition rate, dispersion) of all user life trajectories in the target area (such as cities, districts, counties, etc.), and the population-intensive areas of the time-segment, and the direction of human traffic.
  • Plan bus lines based on the distribution of people's traffic, and set up bus stops at dense traffic points. The corresponding implementation steps are as follows:
  • 201 Obtain mobile signaling data of the mobile terminal in the statistical period in the statistical area from the operator server, and obtain location update information of the mobile terminal according to the mobile signaling data of the mobile terminal;
  • the collected mobile signaling data sources include, but are not limited to, mobile signaling data, mobile phone GPS positioning information, and the like.
  • the mobile signaling update data of the first half of the year (the statistical period can be set) from the operator, and obtain the user location update information in the period, including: user mobile phone number, location update time, location Cell identification.
  • the following basic information is obtained from the operator: User registration information: including mobile phone number, gender, age, social attribute, etc.
  • the base station cell information includes: a cell identifier, a cell latitude and longitude, a cell radius, a cell administrative address, and the like.
  • the step of obtaining the crowd resident point set and the crowd travel feature according to the user's spatio-temporal data set may include:
  • Step 2031 Extract a user's berth point set according to the user's spatiotemporal data set.
  • the user's spatiotemporal data set includes: a location point, a dwell time of the location point; According to the user's spatio-temporal data set, the dwell time of the user's location point is extracted. If the dwell time of the user's location point exceeds the preset mooring threshold, the location of the user is marked as a mooring point, and the location is established.
  • the user's berth point set summarizes the set of berth points for multiple users.
  • the step of extracting the user berth point set includes: performing state judgment on each point in the user space-time data set A, determining whether it is a mobile state or a resident state, and the dwell time (t2-tl) exceeds 1 hour (the berth point threshold can be The judgment of the adjustment is the resident state, and the position point is added to the user mooring point set B, and if it is less than one hour (the mooring point threshold is adjustable), it is judged to be the moving state.
  • Step 2032 Extract a set of repeated mooring points of each user according to a set of berth points of each user;
  • the step of extracting the berth point set includes: establishing a repeated berth point set C by using a berth point with a repetition degree greater than 0.7 (a threshold value adjustable) as a normal berth point of the user.
  • the berth repetition calculation includes but is not limited to the following methods: the first day of the berth is the B1 set, and the second day of the berth is B2, so the repetition of the two days is the number of B1 B2 points / B1 and The number of points in B2 can be extended to one week or one month. It is also possible to calculate day, night, office hours, weekends, etc. separately.
  • Step 2033 According to the repeated berth point set of multiple users, the crowd resident point set is summarized; the step of extracting the population resident point set includes: summarizing the repeated berth points of all users in the area to obtain the crowd berth point set D , can get the change of the number of people in each MAP grid in 24 hours a day, the data accuracy is 1 hour (data precision can be adjusted). A grid with a number of people exceeding 6 (the judgment threshold can be adjusted as needed) is marked as a dwell point, and a crowd resident point set E is established.
  • the dwell point information includes: location point, number of people, dwell time, and the like.
  • Step 2034 According to the repeated berth point set of the plurality of users, obtain the travel trajectory of the working hours of the plurality of users and the travel trajectory of the off-hours, and summarize the travel characteristics of the crowd.
  • the step of judging the feature of the berth point includes: the residence time of the repeated berth point set C is 20: 00 to the next day, the user's home address is 6: 00, and the resident time of the repeated berth point set C is 9 hours of the working day. : 30 to 11:30 noon or 14:00 pm to 16:30 pm for the user's office, the above judgment conditions can be adjusted according to local time, there can be multiple home addresses and work addresses.
  • the steps of user travel characteristics analysis include: travel trajectory during work hours, starting from home to the unit, the starting point is the home address, the ending point is the office location; the trajectory of the off-hours travel time, from the unit to the home, the starting point is the office location, and the destination is the home address.
  • the steps of extracting the characteristics of the crowd trip include: summarizing the travel characteristics of all users in the area, and obtaining the travel characteristics of the people in the area, that is, the original passenger flow OD data (the travel-arrival information of the crowd in a certain period of time).
  • the crowd data information includes: a population resident point set and a crowd travel feature.
  • Crowd travel characteristics including: human flow, direction of people flow, characteristics of the crowd;
  • the steps of public transportation planning include:
  • Plan bus routes based on crowd travel characteristics (passenger OD data).
  • the flow of people can be expanded based on the number of mobile phones per capita in the city.
  • Embodiment 2 Optimization of bus lines.
  • Bus companies should add routes and increase the number of flights in densely populated areas.
  • the addition of lines allows passengers to sit on the same bus at different locations, which is convenient for passengers and brings more passengers to the bus.
  • the corresponding implementation steps are as follows:
  • 301 Obtain mobile signaling data of the mobile terminal in a preset statistical period in the preset statistical area from the operator server, and obtain location update information of the mobile terminal according to the mobile signaling data of the mobile terminal;
  • the collected mobile signaling data sources include, but are not limited to, mobile signaling data, mobile phone GPS positioning information, and the like.
  • the signaling is updated to obtain the user location update information in the time period, including: the user mobile phone number, the location update time, and the location cell identifier.
  • the following basic information is obtained from the operator: User registration information: including mobile phone number, gender, age, social attribute, etc.
  • the base station cell information includes: a cell identifier, a cell latitude and longitude, a cell radius, a cell administrative address, and the like.
  • 303 Obtaining crowd data information according to a time and space data set of the user, where the crowd data information includes: a population resident point set and a crowd travel feature;
  • the step of obtaining the crowd data information according to the spatio-temporal data set of each user may include: Step 3031: Extract a mooring point set of each user according to the spatio-temporal data set of each user;
  • the user's spatiotemporal data set includes: location point and dwell time of the location point;
  • the dwell time of the location point of the user is extracted. If the dwell time of the user's location point exceeds the pour point threshold, the location point of the user is marked as a mooring point, and the user's location is established.
  • a set of berth points which summarizes the set of berth points for multiple users.
  • the step of extracting the user berth point set includes: performing state judgment on each point in the user space-time data set A, determining whether it is a mobile state or a resident state, and the dwell time (t2-tl) exceeds 1 hour (the berth point threshold can be The judgment of the adjustment is the resident state, and the position point is added to the user mooring point set B, and if it is less than one hour (the mooring point threshold is adjustable), it is judged to be the moving state.
  • Step 3032 Extract a set of repeated parking points of the user according to a set of berth points of multiple users
  • the steps of the mooring point set extraction include: using a mooring point greater than 0.7 (thickness adjustable) The household berth point, establish a set of repeated berth points c.
  • the berth repetition calculation includes but is not limited to the following methods: the first day of the berth is the B1 set, and the second day of the berth is B2, so the repetition of the two days is the number of B1 B2 points / B1 and The number of points in B2 can be extended to one week or one month. It is also possible to calculate day, night, office hours, weekends, etc. separately.
  • Step 3033 According to the repeated berth point set of each user, the crowd resident point set is summarized; the step of extracting the crowd resident point set includes: summarizing the repeated berth points of all users in the area to obtain the group berth point set D, The change in the number of people in each MAP grid for 24 hours a day, the data accuracy is 1 hour (data accuracy can be adjusted). A grid with a number of people exceeding 6 (the judgment threshold can be adjusted as needed) is marked as a dwell point, and a crowd resident point set E is established.
  • the dwell point information includes: location point, number of people, dwell time, and the like.
  • Step 3034 According to the repeated parking point set of the plurality of users, obtain the travel trajectory of the working hours of the plurality of users and the travel trajectory of the off-hours, and summarize the travel characteristics of the crowd.
  • the step of judging the feature of the berth point includes: the residence time of the repeated berth point set C is 20: 00 to the next day, the user's home address is 6: 00, and the resident time of the repeated berth point set C is 9 hours of the working day. : 30 to 11:30 noon or 14:00 pm to 16:30 pm for the user's office, the above judgment conditions can be adjusted according to local time, there can be multiple home addresses and work addresses.
  • the steps of user travel characteristics analysis include: travel trajectory during work hours, starting from home to the unit, the starting point is the home address, the ending point is the office location; the travel trajectory during the off-hours, from the unit to the home, the exit point is the office location, and the destination is the home address.
  • the steps of extracting the characteristics of the crowd trip include: summarizing the travel characteristics of all users in the area, and obtaining the travel characteristics of the people in the area, that is, the original passenger flow OD data (the travel-arrival information of the crowd in a certain period of time)
  • the crowd data information includes: a population resident point set and a crowd travel feature.
  • the characteristics of crowd travel include: human flow, direction of people flow, characteristics of the crowd; According to the crowd data information, the steps of public transportation planning include:
  • the overlapping lines are combined and optimized according to the flow direction of the people's travel characteristics.
  • Embodiment 3 Optimization of bus scheduling.
  • the passenger's dwell time at the site is counted as the waiting time. For sites with large traffic and long dwell time, additional bus shifts are required. Increasing the number of shifts can greatly shorten the waiting time for passengers, saving time for passengers and improving the competitiveness of buses.
  • the starting model can also be adjusted according to the characteristics of the user group. The corresponding implementation steps are as follows:
  • 401 Obtain mobile signaling data of the mobile terminal in a preset statistical period in the preset statistical area from the operator server, and obtain location update information of the mobile terminal according to the mobile signaling data of the mobile terminal;
  • the collected mobile signaling data sources include, but are not limited to, mobile signaling data, mobile phone GPS positioning information, and the like.
  • the mobile signaling update data of the first half of the year (the statistical period can be set) from the operator, and obtain the user location update information in the period, including: user mobile phone number, location update time, location Cell identification.
  • the following basic information is obtained from the operator: User registration information: including mobile phone number, gender, age, social attribute, etc.
  • the base station cell information includes: a cell identifier, a cell latitude and longitude, a cell radius, a cell administrative address, and the like.
  • the crowd data information includes: a population resident point set and a crowd travel feature
  • the step of obtaining the crowd data information according to the time and space data sets of each user may include: Step 4031: Extract a parking point set of each user according to a time and space data set of each user.
  • the user's spatiotemporal data set includes: location point and dwell time of the location point;
  • the dwell time of the user's location point is extracted. If the dwell time of the user's location point exceeds the preset mooring threshold, the location of the user is marked as a mooring point, and the location is established.
  • the user's berth point set summarizes the set of berth points for multiple users.
  • the step of extracting the user berth point set includes: performing state judgment on each point in the user space-time data set A, determining whether it is a mobile state or a resident state, and the dwell time (t2-tl) exceeds 1 hour (the berth point threshold can be The judgment of the adjustment is the resident state, and the position point is added to the user mooring point set B, and if it is less than one hour (the mooring point threshold is adjustable), it is judged to be the moving state.
  • Step 4032 extracting a set of repeated berth points of multiple users according to a set of berth points of multiple users; if the degree of repetition of the berth points of the berth point set of the user is greater than a preset repetition width, the user is marked as Repeating the mooring point, establishing the repeated mooring point set of the user, and summarizing the steps of establishing the repeated mooring point repetitive mooring point set of the plurality of users, including: setting the repetitive degree greater than 0.7 (thickness adjustable) mooring point as the user's regular mooring point , establish a set of repeated berth points C.
  • the berth repetition calculation includes but is not limited to the following methods: the first day of the berth is the B1 set, and the second day of the berth is B2, so the repetition of the two days is the number of B1 B2 points / B1 and The number of points in B2 can be extended to one week or one month. It is also possible to calculate day, night, office hours, weekends, etc. separately.
  • Step 4033 According to the repeated berth point set of multiple users, the crowd resident point set is summarized; the step of extracting the crowd resident point set includes: summarizing the repeated berth points of all users in the area to obtain the crowd berth point set D , can get the change of the number of people in each MAP grid in 24 hours a day, the data accuracy is 1 hour (data accuracy can be adjusted). A grid with a number of people exceeding 6 (the judgment threshold can be adjusted as needed) is marked as a dwell point, and a crowd resident point set E is established.
  • the dwell point information includes: a position point, a number of people, a dwell time, and the like.
  • Step 4034 According to the repeated parking point set of the plurality of users, obtain the travel trajectory of the working hours of the plurality of users and the travel trajectory of the off-hours, and summarize the travel characteristics of the crowd.
  • the step of judging the feature of the berth point includes: the residence time of the repeated berth point set C is 20: 00 in the evening to 6: 00 in the morning of the next day, and the resident time of the repeated parking point set C is the working day morning. From 9:30 to 11:30, or from 14:00 to 16:30 in the afternoon, the user's office location can be adjusted according to local time. There can be multiple home addresses and work addresses.
  • the steps of user travel characteristics analysis include: travel trajectory during work hours, starting from home to the unit, the starting point is the home address, the ending point is the office location; the travel trajectory during the off-hours, from the unit to the home, the exit point is the office location, and the destination is the home address.
  • User travel characteristics analysis also includes user feature analysis.
  • User characteristics analysis age (old, middle, young, young), gender (male, female), social attributes (office workers, school, shopping).
  • the steps of extracting the characteristics of the crowd trip include: summarizing the travel characteristics of all users in the area, and obtaining the travel characteristics of the people in the area, that is, the original passenger flow OD data (the travel-arrival information of the crowd in a certain period of time), including: Traffic (number of people), direction of people flow (departure location, arrival location), travel time and demographic characteristics (number of people counted by age, gender, social attributes, etc.).
  • the crowd data information includes: a population resident point set and a crowd travel characteristic.
  • the characteristics of crowd travel include: human flow, direction of people flow, characteristics of the crowd;
  • the steps of public transportation planning include:
  • Plan bus scheduling including departure interval and departure model.
  • the time interval between the delivery and the bus will be shortened, and large-capacity vehicles will be arranged.
  • Vehicle arrangements are scheduled based on the characteristics of the crowd's travel characteristics. For older passengers, arrange a multi-seat, low-pedal model.
  • an embodiment of the present invention further provides an apparatus for performing bus planning by using mobile communication data mining, including: an information collection module 41, an information conversion module 42, a data mining module 43, and a planning module 44, wherein ,
  • the information collection module 41 is configured to: receive mobile signaling data of the mobile terminal in a preset statistical period in a preset statistical area acquired from the operator server, and obtain a location of the mobile terminal according to the mobile signaling data of the mobile terminal. Update information;
  • the information conversion module 42 is configured to: receive location update information of the mobile terminal, and obtain a spatiotemporal data set of the user corresponding to the mobile terminal;
  • the data mining module 43 is configured to: receive a spatio-temporal data set of a plurality of users, and obtain crowd data information;
  • the planning module 44 is configured to: receive the crowd data information, and perform bus planning according to the crowd data information.
  • the data of the crowd data includes: a population resident point set and a crowd travel feature; and the data mining module 43 includes:
  • a berth sub-module 431 configured to receive the spatio-temporal data set of the user, and extract a set of berth points of the user;
  • Repeating the berth sub-module 432 configured to receive the set of berths of the user, and extract a set of repeated berths of the user;
  • a crowd resident point sub-module 433, configured to receive a plurality of repeated berth points of the user, and obtain a set of crowd resident points;
  • the crowd travel feature sub-module 434 is configured to receive a plurality of repeated berth points of the user, obtain a travel trajectory of the plurality of the working hours of the user, and a travel trajectory of the off-hours, and summarize the travel characteristics of the crowd.
  • the technical solution of the present invention obtains the mobile communication signaling data of the residents in the selected area when using the mobile communication data mining for public transportation planning, and analyzes the living trajectory analysis of the residents in the selected area, and statistics.
  • the dwelling point, the flow of people, the direction of people flow, and the characteristics of the crowd can be used as the basic data for the planning and evaluation of the urban comprehensive transportation system.
  • the input of human and material resources for the urban passenger flow OD survey is reduced, and the cost is low and the accuracy is high.
  • all or a portion of the above steps may be performed by a program to instruct the associated hardware, such as a read only memory, a magnetic disk, or an optical disk.
  • each module/unit in the foregoing embodiment may be implemented in the form of hardware, or may use software functions.
  • the form of the module is implemented.
  • the invention is not limited to any specific form of combination of hardware and software.
  • the embodiment of the present invention is based on a method for public transportation planning using mobile communication data mining, obtains mobile communication signaling data of residents in a selected area, and statistically analyzes living trajectories of residents in a selected area, and statistically resides points.
  • the flow of people, the direction of people flow, and the characteristics of the crowd can be used as the basic data for the planning and evaluation of the urban comprehensive transportation system.
  • the input of human and material resources for the urban passenger flow OD survey is reduced, and the cost is low and the accuracy is high. Therefore, it has industrial applicability.

Abstract

一种利用移动通信数据挖掘进行公交规划的方法,包括从运营商服务器获取统计区域内统计时段内用户终端的移动信令数据,根据所述用户终端的移动信令数据获得用户终端的位置更新信息;根据各所述用户终端的所述位置更新信息,分别得到各用户终端对应的用户的时空数据集;根据所述各用户的时空数据集得到人群驻留点集和人群出行特征;根据所述人群驻留点集和人群出行特征,进行公交规划。以及一种实现上述方法的装置。

Description

一种利用移动通信数据挖掘进行公交规划的方法
技术领域
本发明涉及移动通讯领域的大数据挖掘在智慧城市公交线路规划中的应 用, 尤其涉及一种利用移动通信数据挖掘进行公交规划的方法。
背景技术
公交规划中客流量及客流分布的预测是规划方案的基础, 而预测结果是 否科学合理将最终影响方案的效益评价。 客流 OD 调查 ("0"来源于英文 ORIGIN,指出行的出发地点, "D"来源于英文 DESTINATION, 指出行的目的 地。 )即交通起止点调查又称 OD交通量调查, OD交通量就是指起终点间的 交通出行量。 目前城市客流 OD需要通过居民出行调查获取, 常规做法是进 行居民问卷调查。 问卷调查只能是抽样数据, 无法反应大部分市民的出行需 求。 或每辆公交车的每个门配备一名调查员, 调查员从早到晚要记录每辆车 的到站时间、 上车人数和下车人数。 长期进行客流 OD观测是相当复杂的, 需花费大量的人力物力财力, 且精准度难以保证, 调查周期也较长, 数据信 息也相对滞后。
目前移动电话普及率大大提高, 在大多数省市都达到 80部 /百人以上, 预计到 2015年, 中国移动电话普及率将达到并超过 100部 /百人, 目前并没 有针对利用移动信令数据的大数据挖掘技术的进行公交规划的相关方法。
发明内容
本发明实施例要解决的技术问题是提供一种利用移动通信数据挖掘进行 公交规划的方法, 获得选定区域内的居民生活轨迹分析, 统计出人流量、 人 流方向、 聚客点、 驻留时间, 用于城市公交线路的规划、 站点设置、 调度运 营。
为了解决上述问题, 釆用以下技术方案: 本发明实施例提供了一种进行公交规划的方法, 所述方法利用移动通信 数据进行公交规划, 包括:
从运营商服务器获取预设的统计区域内的预设统计时段内移动终端的移 动信令数据, 根据所述移动终端的移动信令数据获得所述移动终端的位置更 新信息;
根据所述移动终端的位置更新信息, 得到所述移动终端对应的用户的时 空数据集;
根据多个所述用户的时空数据集, 得到人群数据信息; 以及
根据所述人群数据信息, 进行公交规划。
可选地, 所述人群数据信息包括: 人群驻留点集和人群出行特征; 所述根据多个用户的时空数据集得到人群数据信息的步骤包括: 根据所述用户的时空数据集, 提取所述各用户的泊点集;
根据所述用户的泊点集, 提取所述各用户的重复泊点集;
根据多个所述用户的重复泊点集, 汇总得到所述人群驻留点集; 以及 根据多个所述用户的重复泊点集, 得到多个所述用户的上班时段出行轨 迹和下班时段出行轨迹, 汇总得到所述人群出行特征。
可选地, 根据所述用户的时空数据集, 提取所述用户的泊点集的步骤包 括:
所述用户的时空数据集包括: 位置点和位置点的驻留时间; 以及 根据所述用户的时空数据集, 提取出所述用户的位置点的驻留时间, 如 果所述用户的位置点的驻留时间超过预设的泊点阔值, 则标记所述用户的位 置点为泊点, 建立所述用户的泊点集, 汇总建立多个所述用户的泊点集。
可选地, 根据所述用户的泊点集, 提取所述用户的重复泊点集的步骤包 括:
如果所述用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记 为所述用户的重复泊点, 建立所述用户的重复泊点集, 汇总建立多个所述用 户的重复泊点集。 可选地, 人群出行特征包括: 人流量、 人流方向, 以及人群特征; 所述根据所述人群数据信息, 进行公交规划的步骤包括:
根据人群驻留点集, 规划公交站点位置;
根据人流量, 规划公交调度;
根据人流方向, 对重叠线路进行合并优化; 以及
根据人群特征, 调度车辆安排。
可选地, 一种进行公交规划的装置, 所述装置利用移动通信数据进行公 交规划, 包括: 信息釆集模块、 信息转化模块、 信息转化模块, 以及规划模 块, 其中,
所述信息釆集模块设置成: 接收从运营商服务器获取的预设的统计区域 内的预设统计时段内移动终端的移动信令数据, 根据移动终端的移动信令数 据获得所述移动终端的位置更新信息;
所述信息转化模块设置成: 接收各移动终端的位置更新信息, 得到所述 移动终端对应的用户的时空数据集;
所述数据挖掘模块设置成: 接收多个所述用户的时空数据集, 获得人群 数据信息; 以及
所述规划模块设置成: 接收所述人群数据信息, 根据所述人群数据信息 进行公交规划。
可选地, 所述人群数据信息包括: 人群驻留点集和人群出行特征; 所述 数据挖掘模块包括:
泊点子模块, 其设置成接收所述用户的时空数据集, 提取所述用户的泊 重复泊点子模块, 其设置成接收所述用户的泊点集, 提取所述用户的重 复泊点集;
人群驻留点子模块, 其设置成接收多个所述用户的重复泊点集, 汇总得 到所述人群驻留点集; 以及 人群出行特征子模块, 其设置成接收多个所述用户的重复泊点集, 得到 多个所述用户的上班时段出行轨迹和下班时段出行轨迹, 汇总得到所述人群 出行特征。 可选地, 所述用户的时空数据集包括: 位置点和位置点的驻留时间; 泊点子模块设置成通过如下方式接收所述用户的时空数据集, 提取所述 用户的泊点集:
根据所述用户的时空数据集, 提取出所述用户的位置点的驻留时间, 如 果所述用户的位置点的驻留时间超过预设的泊点阔值, 则标记所述用户的位 置点为泊点, 建立所述用户的泊点集, 汇总建立多个所述用户的泊点集。
可选地, 重复泊点子模块设置成通过如下方式接收所述用户的泊点集, 提取所述用户的重复泊点集:
如果所述用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记 为所述用户的重复泊点, 建立所述用户的重复泊点集, 汇总建立多个所述用 户的重复泊点集。
可选地, 人群出行特征, 包括: 人流量、 人流方向, 以及人群特征; 规划模块设置成通过如下方式接收人群数据信息, 根据所述人群数据信 息进行公交规划:
根据人群驻留点集, 规划公交站点位置;
根据人流量, 规划公交调度;
根据人流方向, 对重叠线路进行合并优化; 以及
根据人群特征, 调度车辆安排。
综上, 本发明具有如下有益效果:
本发明实施例基于利用移动通信数据挖掘进行公交规划的方法, 获得选 定区域内的居民的移动通讯信令数据, 统计出选定区域内的居民生活轨迹分 析, 统计出驻留点、 人流量、 人流方向、 人群特征, 可作为城市综合交通体 系规划与评价的基础数据, 减少城市客流 OD调查的人力物力的投入, 耗费 少, 准确度高。 附图概述
图 1所示为本发明实施方式中利用移动通信数据挖掘进行公交规划的方 法的流程图;
图 2所示为一个用户从家上班的典型轨迹;
图 3所示为人群驻留点示意图;
图 4所示为本发明实施方式中利用移动通信数据挖掘进行公交规划的装 置的架构图。 本发明的较佳实施方式
本发明实施例的客流 OD调查内容主要有起止点分布、 出行目的、 出行 方式、 出行时间、 出行距离、 出行次数等。 对移动通讯信令数据的大数据挖 掘可以方便地获取以上信息, 为城市综合交通体系规划提供基础数据。 对于 本发明中的关键技术点仅列举如下非限制示例结合附图进行描述。
下面结合附图和具体实施方式对本发明作可选说明。
图 1为本发明实施例提供一种进行公交规划的方法, 所述方法利用移动 通信数据进行公交规划, 包括:
101 :从运营商服务器获取预设的统计区域内的预设统计时段内移动终端 的移动信令数据, 根据移动终端的移动信令数据获得移动终端的位置更新信 息;
釆集的移动信令数据来源包括但不限于移动信令数据、 手机 GPS定位信 息等。
位置更新信息包括, 但不限于: 用户手机号、 位置更新时间、 位置小区 标识等。
102: 根据移动终端的位置更新信息, 得到各移动终端对应的用户的时空 数据集。 103: 根据多个用户的时空数据集得到人群数据信息, 其中, 所述人群数 据信息包括: 人群驻留点集和人群出行特征;
本步骤中, 根据各用户的时空数据集得到人群驻留点集和人群出行特征 的步骤可以包括:
步骤 1031 : 根据各用户的时空数据集, 提取各用户的泊点集; 用户的时空数据集包括, 但不限于: 位置点和位置点的驻留时间; 根据所述用户的时空数据集, 提取出该用户的位置点的驻留时间, 如果 该用户的位置点的驻留时间超过预设的泊点阔值, 则标记该用户的位置点为 泊点, 建立该用户的泊点集, 汇总建立多个用户的泊点集。
步骤 1032: 根据多个用户的泊点集, 提取各用户的重复泊点集; 如果用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记为该 用户的重复泊点, 建立该用户的重复泊点集, 汇总建立多个用户的重复泊点 步骤 1033: 才艮据多个用户的重复泊点集, 汇总得到人群驻留点集。 步骤 1034: 根据多个用户的重复泊点集, 得到各用户的上班时段出行轨 迹和下班时段出行轨迹, 汇总得到人群出行特征。
104: 根据人群数据信息, 进行公交规划, 其中, 人群数据信息包括: 人 群驻留点集和人群出行特征。
运用 GIS地图技术将人群驻留点集和人群出行特征的分析结果与交通路 线、 社区分布、 商圈分布等信息联系起来, 有助于直观化的进行公交路线规 划。
人群出行特征, 包括: 人流量、 人流方向、 人群特征;
根据人群数据信息进行公交规划的步骤包括:
根据人群驻留点集, 规划公交站点位置;
根据人流量, 规划公交调度;
根据人流方向, 对重叠线路进行合并优化;
根据人群特征, 调度车辆安排。 实施例一、 城市公交路线规划。
根据用户的每日泊点分析(不同时间段停留在不同位置区) , 刻画出用 户每天的生活轨迹(见图 2 ) 。 对目标区域内 (如城市、 区县等)所有用户 生活轨迹进行特征分析(重复率、 离散度), 得出分时间段的人流量密集区, 及人流量方向。 (见图 3 )根据人流量分布规划公交线路, 人流量密集点设 置公交站点。 相应实施步骤如下所述:
201 :从运营商服务器获取统计区域内统计时段内移动终端的移动信令数 据, 根据移动终端的移动信令数据获得移动终端的位置更新信息;
釆集的移动信令数据来源包括但不限于移动信令数据、 手机 GPS定位信 息等。
从运营商获取本市 (统计区域可设定)上半年(统计时段可设定) 的移 动信令更新数据, 获得该时段内的用户位置更新信息, 含: 用户手机号、 位 置更新时间、 位置小区标识。 从运营商获取如下基本信息: 用户注册登记信 息: 含手机号、 性别、 年龄、 社会属性等, 可选地, 基站小区信息包括: 含 小区标识、 小区经纬度、 小区半径、 小区行政地址等。
202: 根据移动终端的位置更新信息, 得到移动终端对应的用户的时空数 据集;
结合上述步骤的数据源, 分析出用户每天 24小时的实时移动轨迹, 见图 2,记录用户位置随时间的动态变化,建立用户的时空数据集 A, 包含信息有: 位置点 p (按照城市无线小区覆盖情况对 Map进行栅格化, 一个小区对应一 个栅格, 对小区的栅格位置进行编码记为 P ) 、 进入该位置点时间 tl、 离开 该位置点时间 t2。
203: 根据用户的时空数据集得到人群驻留点集和人群出行特征; 本步骤中, 根据用户的时空数据集得到人群驻留点集和人群出行特征的 步骤可以包括:
步骤 2031 : 根据用户的时空数据集, 提取用户的泊点集;
用户的时空数据集包括: 位置点, 位置点的驻留时间; 根据用户的时空数据集, 提取出该用户的位置点的驻留时间, 如果该用 户的位置点的驻留时间超过预设的泊点阔值,则标记该用户的位置点为泊点, 建立该用户的泊点集, 汇总建立多个用户的泊点集。
用户泊点集提取的步骤包括: 对用户时空数据集 A中的每个点进行状态 判断, 判断是移动状态还是驻留状态, 驻留时长 (t2-tl)超过 1小时 (泊点阔值 可调整) 的判断为驻留状态, 将该位置点加入用户泊点集 B, 未超过 1小时 (泊点阔值可调整) 的则判断是移动状态。
步骤 2032: 根据各用户的泊点集, 提取各用户的重复泊点集;
如果用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记为该 用户的重复泊点, 建立该用户的重复泊点集, 汇总建立多个用户的重复泊点 重复泊点集提取的步骤包括: 将重复度大于 0.7(阔值可调整)泊点作为用 户常规泊点, 建立重复泊点集 C。 泊点重复度计算包括但不限于如下方法: 第一天的泊点是 B1集合, 第二天的泊点集是 B2, 于是这两天的重复度就是 B1交 B2的点的数量 / B1并 B2的点的数量, 可以按此扩展到一周或一个月。 也可以分别计算白天的、 晚上的、 上班时间的、 周末的等。
步骤 2033: 才艮据多个用户的重复泊点集, 汇总得到人群驻留点集; 人群驻留点集提取的步骤包括: 对区域内所有用户的重复泊点进行汇总 得到人群泊点集 D, 可得出一天中 24小时人员数量在每个 MAP栅格内的变 化情况, 数据精度是 1 小时(数据精度可调整) 。 人员数量超过 6 (判断阔 值可根据需要调整) 的栅格标记为驻留点, 建立人群驻留点集合 E, 驻留点 信息包括: 位置点、 人员数量、 驻留时段等。
步骤 2034: 根据多个用户的重复泊点集, 得到多个用户的上班时段出行 轨迹和下班时段出行轨迹, 汇总得到人群出行特征。
泊点特征判断的步骤包括: 重复泊点集 C中驻留时间为晚上 20: 00到第 二天早上 6: 00的为用户家庭住址, 重复泊点集 C中驻留时间为工作日上午 9: 30到中午 11 : 30或下午 14: 00到下午 16: 30时段的为用户办公地点, 以上判断条件可根据当地时间调整, 家庭地址及工作地址可以有多个。 用户出行特征分析的步骤包括: 上班时段出行轨迹, 从家出发到单位, 出发点为家庭住址, 终点为办公地点; 下班时段出行轨迹, 从单位回家, 出 发点为办公地点, 终点为家庭住址。
人群出行特征提取的步骤包括:对区域内所有用户的出行特征进行汇总, 可得出区域内人群的出行特征, 即原始的客流 OD数据 (某时段人群的出行- 到达信息) 。
204: 根据人群数据信息,进行公交规划,其中, 所述人群数据信息包括: 人群驻留点集和人群出行特征。
运用 GIS地图技术将人群驻留点集和人群出行特征的分析结果与交通路 线、 社区分布、 商圈分布等信息联系起来, 有助于直观化的进行公交路线规 划。
人群出行特征, 包括: 人流量、 人流方向、 人群特征;
根据人群数据信息, 进行公交规划的步骤包括:
根据人群出行特征(客流 OD数据) , 规划公交线路。 人流量可根据该 城市的人均手机拥有量进行人员数量扩充。
根据人群驻留点集, 规划公交站点位置。
实施例二、 公交线路优化。
公交公司应该在人口稠密的地区增设线路, 增加班次。 增设线路, 可以 让乘客在同一站点, 就能坐上开往不同地点的公车, 既方便了乘客, 又能为 公车带来更多的客源。 相应实施步骤如下所述:
301 :从运营商服务器获取预设的统计区域内的预设统计时段内移动终端 的移动信令数据, 根据移动终端的移动信令数据获得移动终端的位置更新信 息;
釆集的移动信令数据来源包括但不限于移动信令数据、 手机 GPS定位信 息等。
从运营商获取本市 (统计区域可设定)上半年(统计时段可设定) 的移 动信令更新数据, 获得该时段内的用户位置更新信息, 含: 用户手机号、 位 置更新时间、 位置小区标识。 从运营商获取如下基本信息: 用户注册登记信 息: 含手机号、 性别、 年龄、 社会属性等, 可选地, 基站小区信息包括: 含 小区标识、 小区经纬度、 小区半径、 小区行政地址等。
302: 根据移动终端的位置更新信息, 得到各移动终端对应的用户的时空 数据集;
结合上述步骤的数据源, 分析出用户每天 24小时的实时移动轨迹, 见图 2,记录用户位置随时间的动态变化,建立用户的时空数据集 A, 包含信息有: 位置点 p (按照城市无线小区覆盖情况对 Map进行栅格化, 一个小区对应一 个栅格, 对小区的栅格位置进行编码记为 P ) 、 进入该位置点时间 tl、 离开 该位置点时间 t2。
303:根据用户的时空数据集得到人群数据信息,所述人群数据信息包括: 人群驻留点集和人群出行特征;
本步骤中,根据各用户的时空数据集得到人群数据信息的步骤可以包括: 步骤 3031 : 根据各用户的时空数据集, 提取各用户的泊点集;
用户的时空数据集包括: 位置点和位置点的驻留时间;
根据用户的时空数据集, 提取出该用户的位置点的驻留时间, 如果该用 户的位置点的驻留时间超过泊点阔值, 则标记该用户的位置点为泊点, 建立 该用户的泊点集, 汇总建立多个用户的泊点集。
用户泊点集提取的步骤包括: 对用户时空数据集 A中的每个点进行状态 判断, 判断是移动状态还是驻留状态, 驻留时长 (t2-tl)超过 1小时(泊点阔值 可调整) 的判断为驻留状态, 将该位置点加入用户泊点集 B, 未超过 1小时 (泊点阔值可调整) 的则判断是移动状态。
步骤 3032: 才艮据多个用户的泊点集, 提取用户的重复泊点集;
如果用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记为该 用户的重复泊点, 建立该用户的重复泊点集, 汇总建立多个用户的重复泊点 重复泊点集提取的步骤包括: 将重复度大于 0.7(阔值可调整)泊点作为用 户常规泊点, 建立重复泊点集 c。 泊点重复度计算包括但不限于如下方法: 第一天的泊点是 B1集合, 第二天的泊点集是 B2, 于是这两天的重复度就是 B1交 B2的点的数量 / B1并 B2的点的数量, 可以按此扩展到一周或一个月。 也可以分别计算白天的、 晚上的、 上班时间的、 周末的等。
步骤 3033: 根据各用户的重复泊点集, 汇总得到人群驻留点集; 人群驻留点集提取的步骤包括: 对区域内所有用户的重复泊点进行汇总 得到人群泊点集 D, 可得出一天中 24小时人员数量在每个 MAP栅格内的变 化情况, 数据精度是 1 小时(数据精度可调整) 。 人员数量超过 6 (判断阔 值可根据需要调整) 的栅格标记为驻留点, 建立人群驻留点集合 E, 驻留点 信息包括: 位置点、 人员数量、 驻留时段等。
步骤 3034: 根据多个用户的重复泊点集, 得到多个用户的上班时段出行 轨迹和下班时段出行轨迹, 汇总得到人群出行特征。
泊点特征判断的步骤包括: 重复泊点集 C中驻留时间为晚上 20: 00到第 二天早上 6: 00的为用户家庭住址, 重复泊点集 C中驻留时间为工作日上午 9: 30到中午 11 : 30或下午 14: 00到下午 16: 30时段的为用户办公地点, 以上判断条件可根据当地时间调整, 家庭地址及工作地址可以有多个。
用户出行特征分析的步骤包括: 上班时段出行轨迹, 从家出发到单位, 出发点为家庭住址, 终点为办公地点; 下班时段出行轨迹, 从单位回家, 出 发点为办公地点, 终点为家庭住址。
人群出行特征提取的步骤包括:对区域内所有用户的出行特征进行汇总, 可得出区域内人群的出行特征, 即原始的客流 OD数据 (某时段人群的出行- 到达信息)
304: 根据人群数据信息,进行公交规划,其中, 所述人群数据信息包括: 人群驻留点集和人群出行特征。
运用 GIS地图技术将人群驻留点集和人群出行特征的分析结果与交通路 线、 社区分布、 商圈分布等信息联系起来, 有助于直观化的进行公交路线规 划。
人群出行特征包括: 人流量、 人流方向、 人群特征; 根据人群数据信息, 进行公交规划的步骤包括:
根据人群出行特征的人流方向对重叠线路进行合并优化。
实施例三、 公交调度优化。
统计乘客在站点的驻留时间即等车时间, 对于人流量大且驻留时间长的 站点, 需要增加公交班次。 增加班次, 可以大大缩短乘客的候车时间, 既能 为乘客节约时间, 又能提高公交车的竟争能力。 也可根据用户群特点调整发 车车型。 相应实施步骤如下所述:
401 :从运营商服务器获取预设的统计区域内的预设统计时段内移动终端 的移动信令数据, 根据移动终端的移动信令数据获得移动终端的位置更新信 息;
釆集的移动信令数据来源包括但不限于移动信令数据、 手机 GPS定位信 息等。
从运营商获取本市 (统计区域可设定)上半年(统计时段可设定) 的移 动信令更新数据, 获得该时段内的用户位置更新信息, 含: 用户手机号、 位 置更新时间、 位置小区标识。 从运营商获取如下基本信息: 用户注册登记信 息: 含手机号、 性别、 年龄、 社会属性等, 可选地, 基站小区信息包括: 含 小区标识、 小区经纬度、 小区半径、 小区行政地址等。
402: 根据移动终端的位置更新信息, 得到移动终端对应的用户的时空数 据集;
结合上述步骤的数据源, 分析出用户每天 24小时的实时移动轨迹, 见图 2,记录用户位置随时间的动态变化,建立用户的时空数据集 A, 包含信息有: 位置点 p (按照城市无线小区覆盖情况对 Map进行栅格化, 一个小区对应一 个栅格, 对小区的栅格位置进行编码记为 P ) 、 进入该位置点时间 tl、 离开 该位置点时间 t2。
403: 根据用户的时空数据集得到人群数据信息, 其中, 所述人群数据信 息包括: 人群驻留点集和人群出行特征;
本步骤中,根据各用户的时空数据集得到人群数据信息的步骤可以包括: 步骤 4031 : 根据各用户的时空数据集, 提取各用户的泊点集;
用户的时空数据集包括: 位置点和位置点的驻留时间;
根据用户的时空数据集, 提取出该用户的位置点的驻留时间, 如果该用 户的位置点的驻留时间超过预设的泊点阔值,则标记该用户的位置点为泊点, 建立该用户的泊点集, 汇总建立多个用户的泊点集。
用户泊点集提取的步骤包括: 对用户时空数据集 A中的每个点进行状态 判断, 判断是移动状态还是驻留状态, 驻留时长 (t2-tl)超过 1小时(泊点阔值 可调整) 的判断为驻留状态, 将该位置点加入用户泊点集 B, 未超过 1小时 (泊点阔值可调整) 的则判断是移动状态。
步骤 4032: 才艮据多个用户的泊点集, 提取多个用户的重复泊点集; 如果用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记为该 用户的重复泊点, 建立该用户的重复泊点集, 汇总建立多个用户的重复泊点 重复泊点集提取的步骤包括: 将重复度大于 0.7(阔值可调整)泊点作为用 户常规泊点, 建立重复泊点集 C。 泊点重复度计算包括但不限于如下方法: 第一天的泊点是 B1集合, 第二天的泊点集是 B2, 于是这两天的重复度就是 B1交 B2的点的数量 / B1并 B2的点的数量, 可以按此扩展到一周或一个月。 也可以分别计算白天的、 晚上的、 上班时间的、 周末的等。
步骤 4033: 才艮据多个用户的重复泊点集, 汇总得到人群驻留点集; 人群驻留点集提取的步骤包括: 对区域内所有用户的重复泊点进行汇总 得到人群泊点集 D, 可得出一天中 24小时人员数量在每个 MAP栅格内的变 化情况, 数据精度是 1小时 (数据精度可调整)。 人员数量超过 6 (判断阔值可 根据需要调整) 的栅格标记为驻留点, 建立人群驻留点集合 E, 驻留点信息 包括: 位置点、 人员数量、 驻留时段等。
步骤 4034: 根据多个用户的重复泊点集, 得到多个用户的上班时段出行 轨迹和下班时段出行轨迹, 汇总得到人群出行特征。
泊点特征判断的步骤包括: 重复泊点集 C中驻留时间为晚上 20: 00到第 二天早上 6: 00的为用户家庭住址, 重复泊点集 C中驻留时间为工作日上午 9: 30到中午 11 : 30或下午 14: 00到下午 16: 30时段的为用户办公地点, 以上判断条件可根据当地时间调整, 家庭地址及工作地址可以有多个。
用户出行特征分析的步骤包括: 上班时段出行轨迹, 从家出发到单位, 出发点为家庭住址, 终点为办公地点; 下班时段出行轨迹, 从单位回家, 出 发点为办公地点, 终点为家庭住址。
用户出行特征分析还包括, 用户特征分析。 用户特征分析: 年龄(老、 中、 青、 幼) 、 性别 (男、 女) 、 社会属性(上班族、 上学族、 购物族)等。
人群出行特征提取的步骤包括:对区域内所有用户的出行特征进行汇总, 可得出区域内人群的出行特征, 即原始的客流 OD数据 (某时段人群的出行- 到达信息) , 内容包括: 人流量(人员数量) 、 人流方向 (出发地点、 到达 地点) 、 出行时间和人群特征(按年龄、 性别、 社会属性等分组统计的人员 数量)等。
404: 根据人群数据信息, , 进行公交规划, 其中, 人群数据信息包括: 人群驻留点集和人群出行特征。
运用 GIS地图技术将人群驻留点集和人群出行特征的分析结果与交通路 线、 社区分布、 商圈分布等信息联系起来, 有助于直观化的进行公交路线规 划。
人群出行特征包括: 人流量、 人流方向、 人群特征;
根据人群数据信息, 进行公交规划的步骤包括:
根据人群出行特征的人流量(根据该城市的人均手机拥有量进行人扩充) 规划公交调度, 包括发车间隔及发车车型。 人流量大的时段, 则缩短发车间 隔增加公交班次, 安排大容量车型。
根据人群出行特征的人群特征调度车辆安排。 对老年乘客, 安排座位多 的、 低踏板的车型。
如图 4所示, 本发明实施例还提供了一种利用移动通信数据挖掘进行公 交规划的装置, 包括: 信息釆集模块 41、 信息转化模块 42、 数据挖掘模块 43 , 以及规划模块 44, 其中, 所述信息釆集模块 41设置成:接收从运营商服务器获取的预设的统计区 域内的预设统计时段内移动终端的移动信令数据, 根据移动终端的移动信令 数据获得移动终端的位置更新信息;
所述信息转化模块 42设置成: 接收移动终端的位置更新信息, 得到移动 终端对应的用户的时空数据集;
所述数据挖掘模块 43设置成: 接收多个用户的时空数据集, 获得人群数 据信息;
所述规划模块 44设置成: 接收所述人群数据信息, 根据人群数据信息进 行公交规划。
其中, 所述人群数据信息包括: 人群驻留点集和人群出行特征; 所述数据挖掘模块 43包括:
泊点子模块 431 , 其设置成接收所述所述用户的时空数据集, 提取所述 用户的泊点集;
重复泊点子模块 432 , 其设置成接收所述用户的泊点集, 提取所述用户 的重复泊点集;
人群驻留点子模块 433 , 其设置成接收多个所述用户的重复泊点集, 汇 总得到人群驻留点集; 以及
人群出行特征子模块 434 , 其设置成接收多个所述用户的重复泊点集, 得到多个所述用户的上班时段出行轨迹和下班时段出行轨迹, 汇总得到所述 人群出行特征。
该装置的其他功能请参考方法内容的描述。
从上述实施例可以看出, 本发明技术方案在利用移动通信数据挖掘进行 公交规划时, 获得选定区域内的居民的移动通讯信令数据, 统计出选定区域 内的居民生活轨迹分析, 统计出驻留点、 人流量、 人流方向、 人群特征, 可 作为城市综合交通体系规划与评价的基础数据, 减少城市客流 OD调查的人 力物力的投入, 耗费少, 准确度高。 本领域普通技术人员可以理解上述方法中的全部或部分步骤可通过程序 来指令相关硬件完成, 所述程序可以存储于计算机可读存储介质中, 如只读 存储器、 磁盘或光盘等。 可选地, 上述实施例的全部或部分步骤也可以使用 一个或多个集成电路来实现, 相应地, 上述实施例中的各模块 /单元可以釆用 硬件的形式实现, 也可以釆用软件功能模块的形式实现。 本发明不限制于任 何特定形式的硬件和软件的结合。
以上所述仅为本发明的较佳实施例而已, 并不用于限制本发明, 对于本 领域的技术人员来说, 本发明可以有各种更改和变化。 凡在本发明的精神和 原则之内, 所作的任何修改、 等同替换、 改进等, 均应包含在本发明的保护 范围之内。
工业实用性 本发明实施例基于利用移动通信数据挖掘进行公交规划的方法, 获得选 定区域内的居民的移动通讯信令数据, 统计出选定区域内的居民生活轨迹分 析, 统计出驻留点、 人流量、 人流方向、 人群特征, 可作为城市综合交通体 系规划与评价的基础数据, 减少城市客流 OD调查的人力物力的投入, 耗费 少, 准确度高。 因此具有^ 虽的工业实用性。

Claims

权 利 要 求 书
1、一种进行公交规划的方法,所述方法利用移动通信数据进行公交规划, 包括:
从运营商服务器获取预设的统计区域内的预设统计时段内移动终端的移 动信令数据, 根据所述移动终端的移动信令数据获得所述移动终端的位置更 新信息;
根据所述移动终端的位置更新信息, 得到所述移动终端对应的用户的时 空数据集;
根据多个所述用户的时空数据集得到人群数据信息; 以及
根据所述人群数据信息, 进行公交规划。
2、 如权利要求 1所述的进行公交规划的方法, 其中,
所述人群数据信息包括: 人群驻留点集和人群出行特征;
所述根据多个所述用户的时空数据集得到人群数据信息的步骤包括: 根据所述用户的时空数据集, 提取所述用户的泊点集;
才艮据所述用户的泊点集, 提取所述用户的重复泊点集;
根据多个所述用户的重复泊点集, 汇总得到所述人群驻留点集; 以及 根据多个所述用户的重复泊点集, 得到多个所述用户的上班时段出行轨 迹和下班时段出行轨迹, 汇总得到所述人群出行特征。
3、 如权利要求 2所述的进行公交规划的方法, 其中, 所述根据所述用户 的时空数据集, 提取所述用户的泊点集的步骤包括:
所述用户的时空数据集包括: 位置点和位置点的驻留时间;
根据所述用户的时空数据集, 提取出所述用户的位置点的驻留时间, 如 果所述用户的位置点的驻留时间超过预设的泊点阔值, 则标记所述用户的位 置点为泊点, 建立所述用户的泊点集, 汇总建立多个所述用户的泊点集。
4、 如权利要求 2所述的进行公交规划的方法, 其中, 所述根据所述用户 的泊点集, 提取所述用户的重复泊点集的步骤包括: 如果所述用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记 为所述用户的重复泊点, 建立所述用户的重复泊点集, 汇总建立多个所述用 户的重复泊点集。
5、 如权利要求 2所述的进行公交规划的方法, 其中:
所述人群出行特征包括: 人流量、 人流方向, 以及人群特征;
所述根据所述人群数据信息, 进行公交规划的步骤包括:
根据所述人群驻留点集, 规划公交站点位置;
根据所述人流量, 规划公交调度;
根据所述人流方向, 对重叠线路进行合并优化; 以及
根据所述人群特征, 调度车辆安排。
6、一种进行公交规划的装置,所述装置利用移动通信数据进行公交规划, 包括: 信息釆集模块、 信息转化模块、 数据挖掘模块, 以及规划模块, 其中, 所述信息釆集模块设置成: 接收从运营商服务器获取的预设的统计区域 内的预设统计时段内移动终端的移动信令数据, 根据所述移动终端的移动信 令数据获得所述移动终端的位置更新信息;
所述信息转化模块设置成: 接收所述移动终端的所述位置更新信息, 得 到所述移动终端对应的用户的时空数据集;
所述数据挖掘模块设置成: 接收多个所述用户的时空数据集, 获得人群 数据信息; 以及
所述规划模块设置成: 接收所述人群数据信息, 根据所述人群数据信息 进行公交规划。
7、 如权利要求 6所述的进行公交规划的装置, 其中,
所述人群数据信息包括: 人群驻留点集和人群出行特征;
所述数据挖掘模块包括:
泊点子模块, 其设置成接收所述用户的时空数据集, 提取所述用户的泊 重复泊点子模块, 其设置成接收所述用户的泊点集, 提取所述用户的重 复泊点集;
人群驻留点子模块, 其设置成接收多个所述用户的重复泊点集, 汇总得 到所述人群驻留点集; 以及
人群出行特征子模块, 其设置成接收多个所述用户的重复泊点集, 得到 多个所述用户的上班时段出行轨迹和下班时段出行轨迹, 汇总得到所述人群 出行特征。
8、 如权利要求 7所述的进行公交规划的装置, 其中, 所述用户的时空数 据集包括: 位置点和位置点的驻留时间;
泊点子模块设置成通过如下方式接收所述用户的时空数据集, 提取所述 用户的泊点集:
根据所述用户的时空数据集, 提取出所述用户的位置点的驻留时间, 如 果所述用户的位置点的驻留时间超过预设的泊点阔值, 则标记所述用户的位 置点为泊点, 建立所述用户的泊点集, 汇总建立多个所述用户的泊点集。
9、 如权利要求 7所述的进行公交规划的装置, 其中, 重复泊点子模块设 置成通过如下方式接收所述用户的泊点集, 提取所述用户的重复泊点集: 如果所述用户的泊点集的泊点的重复度大于预设的重复度阔值, 则标记 为所述用户的重复泊点, 建立所述用户的重复泊点集, 汇总建立多个所述用 户的重复泊点集。
10、 如权利要求 7所述的进行公交规划的装置, 其中, 所述人群出行特 征, 包括: 人流量、 人流方向, 以及人群特征;
所述规划模块设置成通过如下方式接收所述人群数据信息, 根据所述人 群数据信息进行公交规划:
根据所述人群驻留点集, 规划公交站点位置;
根据所述人流量, 规划公交调度;
根据所述人流方向, 对重叠线路进行合并优化; 以及
根据所述人群特征, 调度车辆安排。
PCT/CN2014/079385 2013-12-24 2014-06-06 一种利用移动通信数据挖掘进行公交规划的方法 WO2015096400A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/107,438 US20170032291A1 (en) 2013-12-24 2014-06-06 Bus Planning Method Using Mobile Communication Data Mining

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310723597.8A CN104732756A (zh) 2013-12-24 2013-12-24 一种利用移动通信数据挖掘进行公交规划的方法
CN201310723597.8 2013-12-24

Publications (1)

Publication Number Publication Date
WO2015096400A1 true WO2015096400A1 (zh) 2015-07-02

Family

ID=53456617

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/079385 WO2015096400A1 (zh) 2013-12-24 2014-06-06 一种利用移动通信数据挖掘进行公交规划的方法

Country Status (3)

Country Link
US (1) US20170032291A1 (zh)
CN (1) CN104732756A (zh)
WO (1) WO2015096400A1 (zh)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105303854A (zh) * 2015-09-11 2016-02-03 百度在线网络技术(北京)有限公司 一种出行路线数据的处理方法和装置
CN105469624A (zh) * 2016-01-11 2016-04-06 深圳市蓝泰源信息技术股份有限公司 一种基于调度的运营全过程自动监控方法
CN107025788A (zh) * 2017-05-17 2017-08-08 青岛海信网络科技股份有限公司 一种旅行时间预测方法及装置
CN111339159A (zh) * 2020-02-24 2020-06-26 交通运输部科学研究院 一种一票制公交数据的分析挖掘方法
CN111476494A (zh) * 2020-04-11 2020-07-31 重庆交通开投科技发展有限公司 基于多源数据精准分析公交人口地理分布的方法
CN112732778A (zh) * 2020-12-28 2021-04-30 江苏欣网视讯软件技术有限公司 基于手机信令的交通枢纽客流流向识别方法、计算机系统、服务器与存储介质
CN114693495A (zh) * 2022-05-24 2022-07-01 成都秦川物联网科技股份有限公司 智慧城市公共交通管理方法、物联网系统、装置及介质
CN116153088A (zh) * 2023-04-23 2023-05-23 北京大学 交通需求预测方法、装置和电子设备

Families Citing this family (50)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106294381A (zh) * 2015-05-18 2017-01-04 中兴通讯股份有限公司 大数据计算的方法及系统
CN105184728A (zh) * 2015-09-15 2015-12-23 广州地理研究所 定制客运班车出行需求热力图构建方法
CN105205553A (zh) * 2015-09-15 2015-12-30 广州地理研究所 定制包车出行需求热力图构建方法
CN105184410A (zh) * 2015-09-15 2015-12-23 广州地理研究所 定制货运需求热力图构建方法
CN105184409A (zh) * 2015-09-15 2015-12-23 广州地理研究所 定制公交规划线路出行需求热力图构建方法
CN106549993A (zh) * 2015-09-21 2017-03-29 阿里巴巴集团控股有限公司 一种站点规划方法和装置
CN105788341A (zh) * 2016-01-04 2016-07-20 北京百度网讯科技有限公司 车辆站点位置确定方法和装置
CN105657666B (zh) * 2016-03-31 2019-04-30 东南大学 一种基于手机定位数据的商务就业人群居住地识别方法
AU2017255282B2 (en) * 2016-04-27 2020-02-27 Beijing Didi Infinity Technology And Development Co., Ltd. System and method for determining routes of transportation service
CN106157601B (zh) * 2016-07-21 2018-05-18 宁波大学 一种基于移动通信数据的公交客流需求的调查方法
CN106297273B (zh) * 2016-09-29 2019-11-26 百度在线网络技术(北京)有限公司 班车路线的处理方法及装置
CN108122424B (zh) * 2016-11-28 2020-04-14 高德信息技术有限公司 车辆在站点停靠时间的确定方法和装置
US10945096B2 (en) * 2017-02-17 2021-03-09 DataSpark, PTE. LTD. Mobility gene for visit data
CN108629469A (zh) * 2017-03-17 2018-10-09 上海苍烨智能科技有限公司 一种公共交通运营管理调度方法及系统
CN107392357A (zh) * 2017-06-30 2017-11-24 安徽四创电子股份有限公司 一种基于大数据平台的公共交通精准出行服务系统及方法
CN107748953A (zh) * 2017-10-16 2018-03-02 深圳正品创想科技有限公司 一种厕所投放的提示方法及装置
CN108320501B (zh) * 2017-12-21 2021-01-12 江苏欣网视讯软件技术有限公司 基于用户手机信令的公交线路识别方法
CN108151757A (zh) * 2017-12-28 2018-06-12 安徽科硕智谷信息科技有限公司 一种基于智慧城市公交线路构建系统及构建方法
CN108449711B (zh) * 2018-01-08 2021-04-27 上海元卓信息科技有限公司 一种基于手机信令数据和安检数据的大型场馆客流计算方法
CN108959448B (zh) * 2018-06-14 2021-10-22 上海百林通信网络科技服务股份有限公司 结合移动大数据形成危险地图的方法
CN110956188A (zh) * 2018-09-26 2020-04-03 北京融信数联科技有限公司 基于移动通信信令数据的人口行为轨迹数字化编码方法
CN109409731B (zh) * 2018-10-22 2022-04-12 北京航空航天大学 一种融合断面检测交通数据及众包数据的公路节假日出行特征识别方法
CN109447882B (zh) * 2018-10-29 2021-06-11 东南大学 一种基于信令数据的人口交换量估计方法
CN109711438A (zh) * 2018-12-10 2019-05-03 中国联合网络通信集团有限公司 大巴交通线路获取方法、装置及设备
CN109614948B (zh) * 2018-12-19 2020-11-03 北京锐安科技有限公司 异常行为的检测方法、装置、设备和存储介质
CN109840872A (zh) * 2019-01-08 2019-06-04 福建福诺移动通信技术有限公司 一种基于运营商信令数据计算城市通勤模型的方法
CN109872047B (zh) * 2019-01-21 2021-07-09 河海大学 一种考虑出行者拥挤度感知的公交出行方案推荐方法
US20200273345A1 (en) * 2019-02-26 2020-08-27 Aptiv Technologies Limited Transportation system and method
CN110021164B (zh) * 2019-03-02 2020-09-04 合肥学院 基于行驶时间数据的网约车路网占有率分析方法
CN110021163B (zh) * 2019-03-02 2020-10-13 合肥学院 基于行驶里程数据的网约车路网占有率分析方法
CN110020980B (zh) * 2019-04-08 2023-08-18 江苏号百科技有限公司 基于手机信令数据的机场到发旅客识别与客情分析方法
CN110415397B (zh) * 2019-06-28 2021-09-10 苏州浪潮智能科技有限公司 一种基于云计算的智能卡数据信息采集方法、设备和介质
CN110910293A (zh) * 2019-11-01 2020-03-24 广州丰石科技有限公司 一种基于基站位置的地铁人群行为标签识别方法
CN111209261B (zh) * 2020-01-02 2020-11-03 邑客得(上海)信息技术有限公司 基于信令大数据的用户出行轨迹提取方法和系统
CN111382334B (zh) * 2020-03-11 2022-05-13 腾讯科技(深圳)有限公司 一种数据处理方法、装置、计算机以及可读存储介质
CN111556434A (zh) * 2020-04-28 2020-08-18 中国联合网络通信集团有限公司 一种游客画像方法及装置
CN111653099B (zh) * 2020-06-10 2022-06-17 南京瑞栖智能交通技术产业研究院有限公司 基于手机信令数据的公交客流od获取方法
CN111667121A (zh) * 2020-06-15 2020-09-15 常州市规划设计院 基于手机信令数据的轨道交通线路初期客流预测方法
CN112070463A (zh) * 2020-08-25 2020-12-11 深圳前海微众银行股份有限公司 数据处理方法、装置、设备及存储介质
CN112165686B (zh) * 2020-08-27 2021-09-03 同济大学 基于手机信令数据的城市访客识别方法、装置、存储介质
CN112288131B (zh) * 2020-09-24 2021-06-11 和智信(山东)大数据科技有限公司 公交站点优化方法、电子设备及计算机可读存储介质
CN112298293B (zh) * 2020-10-30 2022-07-01 上海市信产通信服务有限公司 基于5g获取车站乘客行为轨迹参数的系统及方法
CN112183904A (zh) * 2020-11-19 2021-01-05 北京清研宏达信息科技有限公司 一种基于居民出行od的公交线路优化方法
CN112801514A (zh) * 2021-01-30 2021-05-14 崔向棠 一种厕所规划推荐方法及系统
CN113610307B (zh) * 2021-08-12 2023-06-20 中国民用航空飞行学院 一种航班计划管理系统
CN113722565B (zh) * 2021-11-02 2022-03-15 北京融信数联科技有限公司 一种基于大数据的人口特征分析方法、系统和存储介质
CN114418533A (zh) * 2022-01-13 2022-04-29 北京声智科技有限公司 问卷处理方法、装置、设备、存储介质和计算机程序产品
CN114936724B (zh) * 2022-07-25 2022-09-20 四川语璐科技有限公司 一种基于大数据的路线预测推荐方法和系统
CN115731734A (zh) * 2022-11-09 2023-03-03 支付宝(杭州)信息技术有限公司 基于交通出行量数据处理进行出行线路规划的方法及系统
CN117634788A (zh) * 2023-11-22 2024-03-01 艾迪普科技股份有限公司 一种数字城市的电气资源和交通监测管理方法、系统和介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101694706A (zh) * 2009-09-28 2010-04-14 深圳先进技术研究院 基于多源数据融合的人口时空动态出行特征建模方法
CN101908275A (zh) * 2010-07-27 2010-12-08 南京信息工程大学 基于多网络的公共交通优化出行方法
CN102013163A (zh) * 2010-11-25 2011-04-13 广州通易科技有限公司 使用手机基站数据与营运车辆gps数据进行公交od调查的方法
US20120249340A1 (en) * 2011-03-29 2012-10-04 Samsung Electronics Co., Ltd. Method and apparatus for providing public transportation service in a communication system
CN103177575A (zh) * 2013-03-07 2013-06-26 上海交通大学 城区出租车动态在线调度优化系统及其方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102281498A (zh) * 2011-07-28 2011-12-14 北京大学 手机通话数据中用户通勤od的挖掘方法
CN103052022B (zh) * 2011-10-17 2015-08-19 中国移动通信集团公司 基于移动行为的用户稳定点发现方法和系统
US8924503B2 (en) * 2011-12-07 2014-12-30 International Business Machines Corporation Data services using location patterns and intelligent caching
CN102607553B (zh) * 2012-03-06 2014-08-13 北京建筑工程学院 一种基于出行轨迹数据的行程识别方法
CN102595323B (zh) * 2012-03-20 2014-05-07 北京交通发展研究中心 基于手机定位数据的居民出行特征参数的获取方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101694706A (zh) * 2009-09-28 2010-04-14 深圳先进技术研究院 基于多源数据融合的人口时空动态出行特征建模方法
CN101908275A (zh) * 2010-07-27 2010-12-08 南京信息工程大学 基于多网络的公共交通优化出行方法
CN102013163A (zh) * 2010-11-25 2011-04-13 广州通易科技有限公司 使用手机基站数据与营运车辆gps数据进行公交od调查的方法
US20120249340A1 (en) * 2011-03-29 2012-10-04 Samsung Electronics Co., Ltd. Method and apparatus for providing public transportation service in a communication system
CN103177575A (zh) * 2013-03-07 2013-06-26 上海交通大学 城区出租车动态在线调度优化系统及其方法

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105303854A (zh) * 2015-09-11 2016-02-03 百度在线网络技术(北京)有限公司 一种出行路线数据的处理方法和装置
CN105469624A (zh) * 2016-01-11 2016-04-06 深圳市蓝泰源信息技术股份有限公司 一种基于调度的运营全过程自动监控方法
CN107025788A (zh) * 2017-05-17 2017-08-08 青岛海信网络科技股份有限公司 一种旅行时间预测方法及装置
CN111339159A (zh) * 2020-02-24 2020-06-26 交通运输部科学研究院 一种一票制公交数据的分析挖掘方法
CN111339159B (zh) * 2020-02-24 2023-08-18 交通运输部科学研究院 一种一票制公交数据的分析挖掘方法
CN111476494A (zh) * 2020-04-11 2020-07-31 重庆交通开投科技发展有限公司 基于多源数据精准分析公交人口地理分布的方法
CN111476494B (zh) * 2020-04-11 2023-05-23 重庆交通开投科技发展有限公司 基于多源数据精准分析公交人口地理分布的方法
CN112732778A (zh) * 2020-12-28 2021-04-30 江苏欣网视讯软件技术有限公司 基于手机信令的交通枢纽客流流向识别方法、计算机系统、服务器与存储介质
CN114693495A (zh) * 2022-05-24 2022-07-01 成都秦川物联网科技股份有限公司 智慧城市公共交通管理方法、物联网系统、装置及介质
US11741565B1 (en) 2022-05-24 2023-08-29 Chengdu Qinchuan Iot Technology Co., Ltd. Method, internet of things system and storage medium of public transport management in a smart urban
CN116153088A (zh) * 2023-04-23 2023-05-23 北京大学 交通需求预测方法、装置和电子设备
CN116153088B (zh) * 2023-04-23 2023-09-01 北京大学 交通需求预测方法、装置和电子设备

Also Published As

Publication number Publication date
CN104732756A (zh) 2015-06-24
US20170032291A1 (en) 2017-02-02

Similar Documents

Publication Publication Date Title
WO2015096400A1 (zh) 一种利用移动通信数据挖掘进行公交规划的方法
Gurumurthy et al. Analyzing the dynamic ride-sharing potential for shared autonomous vehicle fleets using cellphone data from Orlando, Florida
CN103700174B (zh) 一种基于wifi身份识别的公交客流数据采集及od分析方法
WO2015096379A1 (zh) 一种公交站点优化评估方法和系统
CN107316098B (zh) 一种基于用户行为分析的汽车租赁点选址方法
Kostakos et al. Wireless detection of end-to-end passenger trips on public transport buses
CN111932925A (zh) 一种公共交通站点的出行客流的确定方法、装置及系统
CN108549976A (zh) 智慧旅游大数据分析方法
US10489431B2 (en) Digital location-based data methods and product
CN109637134A (zh) 一种公交设备匹配方法
CN105336155A (zh) 公交班次加派方法及系统
CN110910293A (zh) 一种基于基站位置的地铁人群行为标签识别方法
CN112118548A (zh) 一种大数据识别常住人口与流动人口的方法和存储设备
Ndibatya et al. Mapping the informal public transport network in Kampala with smartphones: Making sense of an organically evolved chaotic system in an emerging city in sub-Saharan Africa
CN109493601B (zh) 一种公交支线设置方法
Misharin et al. On Processing of Correspondence Matrices in Transport Systems
Jang et al. Pedestrian mode identification, classification and characterization by tracking mobile data
Raghothama et al. Analytics on public transport delays with spatial big data
CN113160542A (zh) 基于信息反馈的乘车方法及装置
Cui et al. Usage demand forecast and quantity recommendation for urban shared bicycles
CN108256101B (zh) 基于公共自行车刷卡数据和poi识别通勤od的方法
Li et al. Travel patterns analysis of urban residents using automated fare collection system
Zeng et al. Development of Application for Estimating Daily Boarding and Alighting Counts on New York City Buses: Implementation of Daily Production System
Yang et al. Taxicab availability: empirical study of Kunshan, China
CN107545761B (zh) 一种用于采集公交车留站客流的方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14873575

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15107438

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14873575

Country of ref document: EP

Kind code of ref document: A1