WO2017084221A1 - 交通状态的获取方法及装置 - Google Patents

交通状态的获取方法及装置 Download PDF

Info

Publication number
WO2017084221A1
WO2017084221A1 PCT/CN2016/075255 CN2016075255W WO2017084221A1 WO 2017084221 A1 WO2017084221 A1 WO 2017084221A1 CN 2016075255 W CN2016075255 W CN 2016075255W WO 2017084221 A1 WO2017084221 A1 WO 2017084221A1
Authority
WO
WIPO (PCT)
Prior art keywords
mobile station
base station
monitored
log
road
Prior art date
Application number
PCT/CN2016/075255
Other languages
English (en)
French (fr)
Inventor
王利学
刘君亮
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
Publication of WO2017084221A1 publication Critical patent/WO2017084221A1/zh

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
    • 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
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
    • 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
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • 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
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed

Definitions

  • the present invention relates to the field of traffic and mobile communications, and in particular to a method and apparatus for acquiring traffic conditions.
  • Traffic is one of the important components of the city. With the continuous development of society and the rapid increase of vehicle ownership, although the urban road network is also undergoing rapid construction, the construction of the road is still far behind the actual demand, resulting in traffic. Congestion becomes a worldwide urban disease. The impact of traffic problems on the city is all-round, including traffic management, road network planning, and public resource allocation planning, as well as travel planning, energy conservation and emission reduction. In short, traffic problems have become a constraint to urban health, efficiency, and sustainability. The core issue of development.
  • a core basis for solving traffic problems is the quantitative depiction of traffic conditions within the city. Only when we have quantitative information on regional, all-weather, real-time, and high-density traffic conditions can we make scientific and reasonable urban operations. Long-term planning, and accurate and efficient real-time intervention, and even promote the full and effective application of traffic information to various fields, and thus bring about a wider range of social effects.
  • Fixed traffic information collection refers to the collection of vehicle information (GB2436909, CN201510162656) through magnetic frequency, wave frequency and video sensors arranged at intersections and bayonet, including the number of passes, time, speed, direction, video images, etc., and then calculate each Traffic flow on the road.
  • This method is essentially a point measurement method, although the vehicle with each measurement point can obtain relatively rich and high-precision measurement information, and then push the measurement of the traffic state at the measurement point, but there is coverage.
  • the low disadvantages can only be monitored at limited intersections and bayonet, so there are a large number of monitoring blind spots. Due to the variety of sensors involved in the solution, the technical complexity required for data integration and subsequent analysis is high. In addition, the number of sensors required for the solution is large, and some earthwork is required for deployment, and the deployment cost is high.
  • Mobile traffic data collection generally refers to the acquisition of traffic data by floating vehicles (US7783296, CN200910254490) equipped with GPS and other positioning equipment, and then combined with map matching technology to solve the calculation of road traffic status.
  • the solution solves the shortcomings of a large number of blind spots in the fixed acquisition scheme, and the GPS receiver can collect various vehicle operating parameters with high precision, including time, position, speed and acceleration. , direction, etc.
  • the technology relied on by the solution is still relatively complicated, and it is necessary to deploy a GPS receiver on a floating car, and due to some characteristics of the GPS positioning system itself (easy to interfere, the positioning accuracy is lower than the meter level), the subsequent processing procedure for the vehicle result is made.
  • the embodiment of the invention provides a method and a device for acquiring a traffic state, so as to at least solve the problem of complicated operation and high cost when acquiring traffic data in the related art.
  • a method for acquiring a traffic state including: obtaining, from a log of a network operator, a trajectory of a mobile station that communicates with a base station of the network operator on a bus to be monitored a sequence, wherein the trajectory sequence includes: a plurality of sets of time stamps having corresponding relationships, a vehicle-mounted mobile station ID, and a base station ID; and acquiring, according to the trajectory sequence, road section operation information of each road section on the travel route of the bus to be monitored
  • the road segment operation information includes a plurality of sets of time stamps and link IDs having corresponding relationships; and the travel speed of the bus to be monitored on the respective road segments is obtained according to the road segment operation information.
  • the obtaining, according to the road segment operation information, the traveling speed of the bus to be monitored on the respective road segments comprises: acquiring the bus to be monitored according to multiple time stamps corresponding to the same segment ID
  • the method before acquiring the trajectory sequence of the vehicular mobile station that communicates with the base station of the network operator on the bus to be monitored from the log of the network operator, the method includes: determining, from the log, the non-handheld mobile station a sequence, wherein the non-handheld mobile station sequence includes a plurality of sets of time stamps having a corresponding relationship, a mobile station ID, and a base station ID; acquiring, according to the non-handheld mobile station sequence, the network operator recorded in the log The trajectory of the non-handheld mobile station communicated by the base station; the non-handheld mobile station having the coincidence degree between the trajectory and the predetermined bus running line being greater than a predetermined threshold is determined as the in-vehicle mobile station.
  • the method before acquiring the trajectory sequence of the in-vehicle mobile station that communicates with the base station of the network operator on the bus to be monitored from the log of the network operator, the method includes: according to the road information and the driving route in the area to be monitored The information, the base station distribution information is used to establish a traffic route map, and the roads in the area to be monitored are divided into one or more road segments; the mapping of each road segment in the to-be-monitored area to the base station is established, that is, the to-be-established
  • the probability model of each road segment in the monitoring area to the base station includes: establishing a transition probability model of each road segment, establishing an observation probability model of the base station to the respective road segments; and acquiring the network operator in the to-be-monitored area Log.
  • the establishing a traffic route map according to the road information, the travel route information, and the base station distribution information in the area to be monitored, and dividing the road in the to-be-monitored area into one or more road segments includes: acquiring to be monitored The latitude and longitude information of the base station, the travel route, and the road in the area; the travel route and the road are distribution lines, and the radiation range of the base station is a distribution circle to establish a traffic line distribution map; The intersection with the distribution line and the intersection of the travel route divides the distribution line into a plurality of road segments as division points.
  • the establishing the mapping of each road segment in the to-be-monitored area to the base station includes: determining, from the traffic line profile, a base station ID that radiates the each road segment; establishing a trajectory according to the driving line on each road segment Mapping of multiple base stations connected separately.
  • the mapping of establishing a plurality of base stations respectively connected to the respective road sections according to the trajectory of the driving line comprises: establishing the vehicle-mounted mobile station ID and the plurality of base stations respectively connected to the respective road sections according to the uplink trajectory of the driving line The first correspondence between the base station IDs, and/or the second correspondence between the in-vehicle mobile station ID and the base station IDs of the plurality of base stations respectively connected to the respective segments according to the downlink trajectory of the travel route.
  • the determining, by the log, the non-handheld mobile station sequence comprises: determining that the mobile station recorded in the log and communicating with the base station of the network operator averages in a first predetermined time period of each day Whether the number of connected base stations is greater than a first preset threshold, and/or determining that the mobile station recorded in the log communicating with the base station of the network operator averages the base station in a second predetermined time period of each day Whether the number of times is greater than a second preset threshold; when the determination result is yes, determining that the mobile station is a non-handheld mobile station, and acquiring a non-handheld mobile station sequence of the non-handheld mobile station from the log.
  • the determining, by the log, the non-handheld mobile station sequence comprises: determining that the mobile station recorded in the log and communicating with the base station of the network operator is parking in a third predetermined time period of each day Whether the average time of camping in the field is greater than a third preset threshold, and/or determining that the mobile station recorded in the log communicating with the base station of the network operator is in the parking lot during the fourth predetermined time period of each day Whether the average number of times of camping is greater than a fourth preset threshold, and/or determining whether the time point of the mobile station that is recorded in the log to communicate with the base station of the network operator is in the parking lot is And within five predetermined time periods; when the determination result is yes, determining that the mobile station is a non-handheld mobile station, and acquiring the non-handheld mobile station sequence of the non-handheld mobile station from the log.
  • a device for acquiring a traffic state including: a first acquiring module, configured to acquire, from a log of a network operator, a bus to be monitored and a network operator a trajectory sequence of the vehicular mobile station communicated by the base station, wherein the trajectory sequence includes: a plurality of sets of time stamps having a corresponding relationship, a vehicle mobile station ID, and a base station ID; and a second acquisition module configured to acquire the trajectory sequence according to the trajectory sequence
  • the apparatus further includes: a first determining module, configured to: before acquiring, from a log of the network operator, a trajectory sequence of the in-vehicle mobile station that communicates with the base station of the network operator on the bus to be monitored, Determining a non-handheld mobile station sequence from the log, wherein the non-handheld mobile station sequence includes a plurality of sets of time stamps having a corresponding relationship, a mobile station ID, and a base station ID; and a fourth obtaining module, configured to The handheld mobile station sequence acquires a running track of the non-handheld mobile station recorded in the log and communicates with the base station of the network operator; and the second determining module is configured to set the running track with a predetermined bus running line The non-handheld mobile station having a degree of coincidence greater than a predetermined threshold is determined to be an in-vehicle mobile station.
  • a first determining module configured to: before acquiring, from a log of the network operator, a trajectory sequence of the in-vehicle mobile
  • the apparatus further includes: a first establishing module, configured to: before acquiring, from a log of the network operator, a trajectory sequence of the in-vehicle mobile station that communicates with the base station of the network operator on the bus to be monitored, Establishing a traffic route map according to road information, driving route information, and base station distribution information in the area to be monitored, and dividing the road in the to-be-monitored area into one or more road segments; and establishing a second establishing module to establish the Establishing a mapping of each road segment in the to-be-monitored area to the base station, that is, establishing a probability model of each road segment in the to-be-monitored area to the base station, including: establishing a transition probability model of each road segment, and establishing the base station to each of the road segments
  • the observation probability model is configured to acquire a log of the network operator in the to-be-monitored area.
  • the first establishing module includes: a second acquiring unit, configured to acquire latitude and longitude information of a base station, a driving line, and a road in the area to be monitored; and a first establishing unit, configured to use the base station as a distribution point,
  • the driving line and the road are distribution lines, the radiation range of the base station is a distribution circle to establish a traffic line distribution map; the dividing unit is set to be an intersection of the distribution circle and the distribution line and an intersection of the driving line
  • the distribution line is divided into a plurality of road segments for the division point.
  • the second establishing module includes: a first determining unit, configured to determine, according to the traffic line profile, to radiate the base station IDs of the respective road sections; and the second establishing unit is configured to establish a track according to the trajectory of the driving line Mapping of multiple base stations connected to each other on the road segment.
  • the second establishing unit further includes: a first establishing subunit, configured to establish that the in-vehicle mobile station ID is between the base station IDs of the plurality of base stations respectively connected to the respective sections according to the uplink trajectory of the driving line And a second establishing subunit, configured to establish a second between the in-vehicle mobile station ID and the base station ID of the plurality of base stations respectively connected to the respective segments according to the downlink trajectory of the travel route Correspondence relationship.
  • the first determining module includes: a first determining unit, configured to determine that the mobile station recorded in the log that communicates with the base station of the network operator is averagely connected in a first predetermined time period of each day. Whether the number of base stations is greater than a first preset threshold; and/or, the second determining unit is configured to determine that the mobile station recorded in the log communicates with the base station of the network operator is at a second predetermined time of day Whether the number of times the average base station is switched in the segment is greater than a second preset threshold; the second determining unit is configured to: when the determination result is yes, determine that the mobile station is a non-handheld mobile station, and obtain the non-handling from the log Handheld mobile station non-handheld mobile station sequence.
  • the first determining module includes: a third determining unit, configured to determine that the mobile station that is recorded in the log and communicates with the base station of the network operator is in the parking lot in a third predetermined time period of each day Whether the average time of the internal camping is greater than a third preset threshold, and/or the fourth determining unit is configured to determine that the mobile station recorded in the log communicates with the base station of the network operator is in the fourth day of each day Whether the average number of times of staying in the parking lot within the predetermined time period is greater than a fourth preset threshold, and/or the fifth determining unit is configured to determine the movement recorded in the log to communicate with the base station of the network operator Whether the time point of the station staying in the parking lot is within the fifth predetermined time period; the third determining unit is configured to determine, when the determination result is yes, that the mobile station is a non-handheld mobile station, and from the log Obtaining a sequence of non-handheld mobile stations of the non-handheld mobile station.
  • a trajectory sequence of the vehicular mobile station that communicates with the base station of the network operator on the bus to be monitored is obtained from the log of the network operator, where the trajectory sequence includes: multiple groups have corresponding Relationship time a section, an in-vehicle mobile station ID, and a base station ID; acquiring, according to the trajectory sequence, road section operation information of each road section on the travel route of the bus to be monitored, wherein the road section operation information includes multiple groups having corresponding relationships a time stamp and a road segment ID; obtaining, according to the road segment operation information, a travel speed of the bus to be monitored on the respective road segments, and directly obtaining the traffic data by using existing base station data and bus route data, and solving the correlation
  • the technology has complicated and high-cost problems in obtaining traffic data, thereby achieving cost-saving effects.
  • FIG. 1 is a flow chart of a method of acquiring a traffic state according to an embodiment of the present invention
  • FIG. 2 is a structural block diagram of an apparatus for acquiring a traffic state according to an embodiment of the present invention
  • FIG. 3 is a block diagram 1 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention
  • FIG. 4 is a block diagram 2 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention
  • FIG. 5 is a block diagram 3 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention
  • FIG. 6 is a block diagram 4 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention
  • FIG. 7 is a block diagram 5 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention.
  • FIG. 8 is a block diagram 6 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention.
  • FIG. 9 is a block diagram 7 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention.
  • 11 is a flow chart of trajectory recognition and model solving in accordance with an alternate embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for acquiring a traffic state according to an embodiment of the present invention. As shown in FIG. 1, the process includes the following steps:
  • Step S102 Obtain, from a log of the network operator, a trajectory sequence of the vehicular mobile station that communicates with the base station of the network operator on the bus to be monitored, where the trajectory sequence includes: multiple sets of time stamps with corresponding relationships, and the mobile station ID and Base station ID;
  • Step S104 Obtain, according to the trajectory sequence, the road segment operation information of each road segment on the travel route of the bus to be monitored, where the road segment operation information includes multiple sets of time stamps and link IDs having corresponding relationships;
  • Step S106 obtaining the traveling speed of the bus to be monitored on each road segment according to the road segment running information.
  • the trajectory sequence of the vehicular mobile station that communicates with the base station of the network operator on the bus to be monitored is obtained from the log of the network operator, where the trajectory sequence includes: multiple sets of time stamps having corresponding relationships, The vehicle mobile station ID and the base station ID; the road segment operation information of each road segment on the travel route of the bus to be monitored is obtained according to the trajectory sequence, wherein the road segment operation information includes multiple sets of time stamps and link IDs having corresponding correspondences;
  • the information obtains the traveling speed of the bus to be monitored on each road section, and directly obtains the traffic data by directly using the existing base station data and the bus line data, and solves the problem that the related technology has complicated operation and high cost when acquiring the traffic data, In turn, the cost-saving effect is achieved.
  • acquiring the travel speed of the bus to be monitored on each road segment according to the road segment operation information includes:
  • S11 Obtain a retention time T of the to-be-monitored bus on the road segment indicated by the link ID according to multiple timestamps corresponding to the same road segment ID;
  • the communication in the base station may also be Logging identifies and identifies vehicle-mounted mobile stations, including:
  • the non-handheld mobile station whose coincidence degree between the running track and the predetermined bus running line is greater than a predetermined threshold is determined as the in-vehicle mobile station.
  • each road segment may be established to the base station.
  • the mapping relationship, the probability model of the road segment is established, and specifically includes:
  • the mapping of each road segment to the base station includes: establishing a transition probability model of each road segment, and establishing an observation probability model of the base station to the respective road segments.
  • the traffic route map is established according to the road information, the travel route information, and the base station distribution information in the area to be monitored, and the road in the to-be-monitored area is divided into one or more road segments, including:
  • the intersection of the driving route includes: a traffic intersection such as a cross traffic intersection and a T-shaped traffic intersection.
  • mapping of each road segment to the base station in the area to be monitored includes:
  • the mapping is established according to the uplink trajectory and the downlink trajectory of the bus, including: establishing the vehicle mobile station ID and following the driving
  • the first correspondence between the base station IDs of the plurality of base stations connected to each of the uplink segments of the line is established, and the base station ID of the plurality of base stations connected to each of the road segments according to the downlink trajectory of the travel line is established. The second correspondence between them.
  • determining the sequence of the non-handheld mobile station from the log includes two alternative manners, wherein
  • the method 1 includes: determining whether the number of base stations that the mobile station that communicates with the base station of the network operator recorded in the log communicates with each other in the first predetermined time period of each day is greater than a first preset threshold, and determines the recorded in the log. Whether the number of times that the mobile station communicating by the base station of the network operator averages the base station to switch is greater than the second preset threshold in the second predetermined time period of each day, and determines whether the base station of the network operator that communicates with the mobile station recorded in the log belongs to the first A preset set, when the determination result is yes, determining that the mobile station is a non-handheld mobile station, and acquiring a non-handheld mobile station sequence of the non-handheld mobile station from the log.
  • the second method includes: determining whether the average time that the mobile station that communicates with the base station of the network operator recorded in the log resides in the parking lot in the third predetermined time period of each day is greater than a third preset threshold, and records the record in the log.
  • the average number of times that the mobile station communicating with the base station of the network operator resides in the parking lot during the fourth predetermined time period of each day is greater than a fourth preset threshold, and determining the communication recorded in the log with the base station of the network operator Time when the mobile station is parked in the parking lot Whether the point is within the fifth predetermined time period; when the determination result is YES, it is determined that the mobile station is a non-handheld mobile station, and the non-handheld mobile station sequence of the non-handheld mobile station is acquired from the log.
  • the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present invention which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a cell phone, a computer, a server, or a network device, etc.) to perform the methods of various embodiments of the present invention.
  • a device for acquiring a traffic state is provided, and the device is used to implement the foregoing embodiments and preferred embodiments, and details are not described herein.
  • the term "module” may implement a combination of software and/or hardware of a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware, is also possible and contemplated.
  • FIG. 2 is a structural block diagram of a device for acquiring a traffic state according to an embodiment of the present invention. As shown in FIG. 2, the device includes: a first acquiring module 20, a second acquiring module 22, and a third acquiring module 24, where
  • the first obtaining module 20 is configured to obtain, from a log of the network operator, a trajectory sequence of the vehicular mobile station that communicates with the base station of the network operator on the bus to be monitored, where the trajectory sequence includes: multiple groups of time having corresponding relationships Stamp, vehicle mobile station ID and base station ID;
  • the second obtaining module 22 is configured to obtain, according to the trajectory sequence, the road segment running information of each road segment on the driving route of the bus to be monitored, wherein the road segment running information includes multiple sets of time stamps and link IDs having corresponding relationships;
  • the third obtaining module 24 is configured to acquire the traveling speed of the bus to be monitored on each road segment according to the road segment running information.
  • FIG. 3 is a block diagram of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention.
  • the third acquiring module 24 includes:
  • the first obtaining unit 30 is configured to acquire, according to the multiple time stamps corresponding to the same road segment ID, the residence time T of the bus to be monitored on the road segment indicated by the link ID;
  • FIG. 4 is a block diagram of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention. As shown in FIG. 4, the device further includes: a first determining module 40, in addition to all the modules shown in FIG. a fourth obtaining module 42 and a second determining module 44, wherein
  • the first determining module 40 is configured to determine a sequence of the non-handheld mobile station from the log before acquiring the trajectory sequence of the in-vehicle mobile station that communicates with the base station of the network operator on the bus to be monitored from the log of the network operator.
  • the non-handheld mobile station sequence includes multiple sets of timestamps, mobile station IDs, and base station IDs having corresponding relationships;
  • the fourth obtaining module 42 is configured to acquire, according to the non-handheld mobile station sequence, the running track of the non-handheld mobile station that communicates with the base station of the network operator recorded in the log;
  • the second determining module 44 is configured to determine the non-handheld mobile station whose coincidence degree between the running track and the predetermined bus running line is greater than a predetermined threshold as the in-vehicle mobile station.
  • FIG. 5 is a block diagram 3 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention.
  • the device further includes: a first establishing module 50, in addition to all the modules shown in FIG. a second establishing module 52, a fifth obtaining module 54, wherein
  • the first establishing module 50 is configured to: before acquiring the trajectory sequence of the in-vehicle mobile station that communicates with the base station of the network operator on the bus to be monitored from the log of the network operator, according to the road information and the driving route in the area to be monitored Information, base station distribution information establishes a traffic route map, and divides the road in the area to be monitored into one or more road segments;
  • the second establishing module 52 is configured to establish a mapping of each road segment in the to-be-monitored area to the base station;
  • the fifth obtaining module 54 is configured to obtain a log of the network operator in the area to be monitored.
  • FIG. 6 is a block diagram of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention. As shown in FIG. 6, the device includes, in addition to all the modules shown in FIG. Unit 60, first establishing unit 62, and dividing unit 64, wherein
  • the second obtaining unit 60 is configured to acquire latitude and longitude information of the base station, the driving line, and the road in the area to be monitored;
  • the first establishing unit 62 is configured to use the base station as a distribution point, the driving line and the road as a distribution line, and the radiation of the base station is a distribution circle to establish a traffic line distribution map;
  • the dividing unit 64 is configured to divide the distribution line into a plurality of sections by using the intersection of the distribution circle and the distribution line and the intersection of the traveling line as division points.
  • FIG. 7 is a block diagram 5 of an optional structure of a traffic state acquiring apparatus according to an embodiment of the present invention.
  • the second establishing module 52 includes: first determining, in addition to all the modules shown in FIG. Unit 70, a second establishing unit 72, wherein
  • the first determining unit 70 is configured to determine, from the traffic line profile, a base station ID that radiates each road segment;
  • the second establishing unit 72 is arranged to establish a mapping of a plurality of base stations respectively connected to the respective road sections according to the trajectory of the traveling line, wherein the base stations that perform communication connections on the adjacent road sections are different.
  • the second establishing unit 72 further includes: a first establishing subunit, configured to establish a first between the in-vehicle mobile station ID and the base station IDs of the plurality of base stations respectively connected to the respective segments according to the uplink trajectory of the driving line Corresponding relationship; the second establishing subunit is configured to establish a second correspondence between the in-vehicle mobile station ID and the base station IDs of the plurality of base stations respectively connected to the respective segments according to the downlink trajectory of the driving line.
  • FIG. 8 is a block diagram 6 of an optional structure of a device for acquiring a traffic state according to an embodiment of the present invention. As shown in FIG. 8, the device includes: first, all of the modules shown in FIG. Unit 80, second judgment unit 82. The second determining unit 84, where
  • the first determining unit 80 is configured to determine whether the number of base stations that the mobile station that communicates with the base station of the network operator recorded in the log is connected to each other within a first predetermined time period of each day is greater than a first preset threshold;
  • the second determining unit 82 is configured to determine whether the number of times that the mobile station that communicates with the base station of the network operator recorded in the log communicates the base station on average in a second predetermined time period of each day is greater than a second preset threshold;
  • the second determining unit 84 is configured to determine that the mobile station is a non-handheld mobile station when the determination result is YES, and acquire a non-handheld mobile station sequence of the non-handheld mobile station from the log.
  • the mobile station is determined to be a non-handheld mobile station when the determination result of the first determining unit 80 and the second determining unit 82 is negative at the same time, or when one of them is no.
  • FIG. 9 is a block diagram showing an optional structure of an apparatus for acquiring a traffic state according to an embodiment of the present invention.
  • the first determining module 40 includes: third determining, in addition to all the modules shown in FIG. The unit 90, the fourth determining unit 92, the fifth determining unit 94, and the third determining unit 96, wherein
  • the third determining unit 90 is configured to determine whether the average time that the mobile station that is recorded in the log and communicates with the base station of the network operator resides in the parking lot in the third predetermined time period of each day is greater than a third preset threshold;
  • the fourth determining unit 92 is configured to determine whether the average number of times that the mobile station that is recorded in the log and communicates with the base station of the network operator resides in the parking lot in the fourth predetermined time period of each day is greater than a fourth preset threshold;
  • the fifth determining unit 94 is configured to determine whether a time point of the mobile station that is recorded in the log and communicates with the base station of the network operator in the parking lot is within a fifth predetermined time period;
  • the third determining unit 96 is configured to determine that the mobile station is a non-handheld mobile station when the determination result is yes, and acquire a non-handheld mobile station sequence of the non-handheld mobile station from the log.
  • the mobile station is determined to be a non-handheld mobile station.
  • the optional embodiment integrates the knowledge of the latitude and longitude position of the bus line and the base station, and the sequence change data of the bus in the base station space observed in a given time window, so as to improve the accuracy of the base station positioning and estimate the bus at The road segment where the corresponding time period is located, and further calculate the traffic speed of the vehicle at the corresponding road segment.
  • Stage 1 bus identification and modeling stage: This stage is an offline processing stage, which runs regularly and mainly completes three aspects of work: 1. Maintaining predicted information such as bus lines and base station locations; 2. Establishing probability for implicit state estimation Model; 3. Identify bus-mobile stations/groups.
  • Phase 2 trajectory identification and model solving phase: This phase is an online processing phase that identifies the current bus line and uplink and downlink status of each bus in real time, and uses the probability model established in the modeling phase to observe the data sequence basis. The reasoning is to estimate the section of the vehicle at each time interval, and further calculate the traffic speed of each section by combining the time and the length of the section.
  • Phase 1 bus identification and modeling includes:
  • the first step base station latitude and longitude, bus line, road information input.
  • the third step the road segments are separated. Separate all the points intersecting the circle drawn by the base station and the line representing the bus line in step one (the separation point also includes various intersections), divide the road into sections, calculate the length of each section and make each section Assign the link ID.
  • Step 4 Establish a two-layer probability model.
  • a probability model is constructed for the uplink and downlink lines of each bus line, mainly to determine the hidden state, the transfer matrix and the observation matrix.
  • the road segment separated by the third step of the model is in a hidden state, and the base station connected to the bus-mounted mobile station is in an observation state.
  • the probability of model observation is proportional to the distance between the road segment and the base station, and normalized to ensure that the probability sum of each observation state observed in the hidden state is 1.
  • the transition probability is related to the length of the road segment and the relationship between the uplink and the downlink.
  • the possible target transition state B of the hidden state A can only be in the forward direction of the current driving direction (upward and downward), and the hidden state A is in the backward state or the far ahead state.
  • the transition probability is 0; the transition probability of the hidden state A to the adjacent state is not zero, and the implicit state A is related to the length of the link corresponding to A, and the implicit state transition probability needs to be normalized to ensure The sum is 1.
  • a corresponding probability model needs to be established for each uplink and downlink corresponding to all lines.
  • Step 5 Identify bus-mobile stations/groups. Extract mobile station behavior and mobility data from logs of mobile operators' CDRs, Internet access, cell handover, location update, etc., according to Humanity behavior attributes and average duration of daily mobile status, daily average number of base station handovers, daily Mobility indicators such as trajectory repeatability, trajectory and bus line repeatability factor filter out mobile stations on the bus. Based on the principle of high repetition of time and space, it is identified from the mobile stations on the bus that the mobile stations are deployed on the same bus, that is, the mobile station group.
  • trajectory identification and model solving of phase 2 includes:
  • the first step extract the upper and lower trajectories of the bus.
  • the trajectory sequence of the same bus-mounted mobile station is extracted from the mobile operator log, and the trajectory is separated according to the base station set near the originating station and the terminal station and the vehicle moving state, and the uplink and downlink states are identified according to the running direction.
  • the bus's uplink and downlink trajectory separation and uplink and downlink state identification it is possible to extract a sequence of motion trajectories for each vehicle in service state, including line ID, uplink and downlink states, and trajectory sequences.
  • Step 2 Estimate the hidden state sequence.
  • the model of the corresponding uplink and downlink state of the corresponding line is taken out from the model set established in the “modeling phase” stage, and the observation sequence is input into the model to estimate the road segment where the vehicle is located at different times.
  • the third step calculate the speed of each section. For each vehicle's trajectory sequence, according to the length of each road segment and the time interval in the road segment, the traffic speed of the road segment can be directly calculated, and smoothing filtering is used between adjacent road segments to improve the estimation accuracy.
  • the area coverage of the related technology is insufficient, the technology is complicated, and the deployment cost is high. It is difficult to obtain the problems and defects of the road traffic state in the region in real time, reduce the deployment difficulty, save the deployment cost, improve the regional coverage rate, and achieve the effect of real-time detection.
  • a cell, a base station, and a base station antenna refer to a base station antenna.
  • FIG. 10 is a flowchart of a bus identification and modeling according to an alternative embodiment of the present invention. As shown in FIG. 10, the method includes:
  • Base stations, bus stops, and road junctions are in a point manner, bus lines and roads are in a line manner, and the base station influence range is drawn in a plane in a circle (radius R).
  • the transition probability matrix is a matrix composed of the transition probabilities of the source state (hidden state) to the target state (hidden state), and the ordinate represents the original state, the abscissa represents the target state, and the state follows the relationship between the top and bottom, from top to bottom, from the top to bottom. Left to right.
  • the transition matrix diagonal elements and one element above the diagonal are non-zero, and all other matrix elements are zero, which is a typical sparse matrix.
  • the matrix element (i, j) represents the probability p(i, j) of the next observation when the vehicle observes the corresponding segment of the hidden state i, and the next observation shifts to the corresponding segment of the hidden state j.
  • the observation probability matrix is a matrix composed of the probability p o (i, j) of the base station corresponding to the observation state j when the vehicle is in the section corresponding to the hidden state i, and the ordinate definition is the same as the definition of the ordinate of the transfer matrix, and the abscissa For each observation state (base station).
  • d ij be the average distance from the segment i to the base station j.
  • p o (i, j) is as follows:
  • an improved model construction manner may be used to combine the actual road test data of the floating vehicle with the theoretical calculation value to construct a transition probability matrix and an observation probability matrix, including the following two examples:
  • Example 1 Combine the actual road test data of the floating car with the theoretical calculation value.
  • the transition probability matrix calculated by the above theoretical calculation method does not take into account the different busyness and time differences of the various sections. Based on the law of large numbers, it is a good choice to calibrate theoretical calculations using a large number of floating vehicle drive test data.
  • the specific method is to randomly sample, randomly select a floating car record in the moving state, calculate the current road segment i according to the latitude and longitude, and use the current speed and the interval (see S301 below) to extrapolate the next step. Section j.
  • the transfer probability matrix with the drive test statistics performs some weighting operation on an element-by-element basis, such as averaging, and then normalizes the obtained matrix by row, that is, the corrected observation probability matrix is obtained.
  • Example 2 Combine the actual road test data of the floating car with the theoretical calculation value. Affected by various factors such as terrain and buildings, the actual coverage of the base station is relatively complicated, and it is difficult to accurately estimate the probability of observing the corresponding base station in each road segment. Based on the law of large numbers, it is a good choice to calibrate the theoretical calculations with a large number of floating vehicle road test data over a long period of time.
  • the specific method can be used to count the number of times of each base station in each section of the floating car road test data, construct the observation quantity matrix of the hidden state to the observation state, and then normalize the observed quantity matrix to obtain the statistical observation probability matrix.
  • the theoretically calculated observation probability matrix and the observation probability matrix of the drive test statistics perform some weighting operation on an element-by-element basis, such as averaging, and then normalize the obtained matrix by row, that is, the corrected observation probability matrix is obtained.
  • N-day N>30
  • the call-on call duration is not less than 10 seconds
  • record all valid callers is greater than 1 Mobile station IDs, and these mobile stations are referred to as handheld mobile stations.
  • the M-day (M>30) mobile operator accesses the Internet, the cell handover, the location update, and the like, records the log of the mobile station location data, and combines the multiple logs according to the timestamp sequence, and merges them into one ⁇ timestamp.
  • the observation sequence record composed of the mobile station ID and the base station ID>triple can only retain the observation sequence record between 10:00 and 17:00 every day.
  • the above observation sequence records are extracted, and all records with the same mobile station ID are extracted into an independent recording set to constitute an observation record of the mobile station.
  • only the observation records of the non-handheld mobile station are retained for subsequent analysis, and the observation records of all the handheld mobile stations are cleared.
  • a trajectory separation is performed on the observation records of each mobile station, and a list of moving trajectory observation sequences in which each mobile station is in a moving state is extracted.
  • the duration of each mobile station in motion is counted, and the mobile station trajectory observation sequence (list) in which the duration is within the maximum 10% interval is retained, and the moving trajectory observation sequence (list) of all other mobile stations is cleared.
  • the trajectory similarity between each moving trajectory observation sequence in the moving trajectory observation sequence list and each bus line is calculated in turn, and the number of times the recorded trajectory observation sequence and the bus line similarity is greater than 90% is recorded as the effective trajectory number.
  • the mobile station trajectory observation sequence (list) of not less than 2 is retained while the ratio of the effective trajectory to the M (effective trajectory/M) is kept, and the moving trajectory observation sequence (list) of all other mobile stations is cleared.
  • the remaining mobile station is the bus-mounted mobile station.
  • the ⁇ line ID, origination time, terminal station time, mobile station ID> quaternion list is extracted, and all records with the same line ID are extracted to an independent ⁇ originating time, terminal time, mobile station ID>
  • the triple record list the ⁇ starting time, terminal time, mobile station ID> triplet record list corresponding to each line is sorted according to the originating time and the ending time, and then the last column of the sorting result is extracted (moving Station ID) performs frequent pattern mining, and finds frequently frequent sets, which are mobile stations/groups on the same vehicle.
  • an improved bus mobile station identification method may be adopted, that is, the location information of the bus parking lot is adopted, thereby improving the recognition accuracy of the bus mobile station. details as follows:
  • the bus parking lot is found by using the location data in the on-board mobile station to register the signaling log, and then the discovered parking lot location is used to assist the provision of the bus mobile station identification accuracy.
  • the vehicle mobile station is turned off.
  • the vehicle mobile station is powered on, and the cellular network communication protocol is installed.
  • the mobile station needs to complete the registration process in the cellular network.
  • the specific method is to extract all mobile station registration records identified by the above process from the M-day (M>30) mobile station registration log, take out the corresponding base station ID, and query the base station latitude and longitude position (Lat, Lon).
  • Kmeans clustering is performed on these two-dimensional data (the clustering maximum radius is R, where each latitude and longitude data pair is called a sample), and the clustering result is taken out from the clustering result, and the class of the clusters is larger than 4M and the base stations belonging to the class Together, they form a set of base stations and become a set of base stations for parking services.
  • Use the parking lot service base station set to compare with all mobile stations identified by the above process, and extract all network registration signaling records after each mobile station parking interval is greater than 2 hours, if more than 20% of the base stations in the record do not belong to the parking lot
  • the serving base station set removes the mobile station from the bus-mounted mobile station set.
  • FIG. 11 is a flowchart of a trajectory recognition and model solution according to an alternative embodiment of the present invention, as shown in FIG.
  • the above observation sequence records are extracted, and all records with the same mobile station ID are extracted into an independent recording set to constitute an observation record of the mobile station. Only the observation sequence corresponding to the bus-mounted mobile station is reserved here.
  • the in-vehicle mobile station group is queried, and the mobile station records belonging to the vehicle are merged according to the time stamp sequence, and merged into an observation sequence record composed of a ⁇ time stamp, mobile station ID, base station ID> triplet.
  • the trajectory separation is performed for the observation sequence composed of the ⁇ time stamp, mobile station ID, base station ID> triplet of each bus, and the moving trajectory observation sequence list in which the vehicle is in the moving state is extracted.
  • the bus route and the uplink and downlink states of the current vehicle service can be directly determined according to the originating location information.
  • the sequence is sampled, sampled and sorted in chronological order , fixed interval ⁇ timestamp, ⁇ base station ID1, base station ID2, base station IDn>> observation sequence.
  • the model corresponding to the uplink and downlink states of the corresponding route is selected from the model set.
  • the initial state of the hidden state is initialized according to the line and the uplink and downlink states, and the observation sequence is input by the Viterbi algorithm for reasoning, and the corresponding hidden state sequence ⁇ timestamp, link ID> is obtained.
  • the 300 sets of the base station ID1, base station ID2, and base station ID3 observation sequences sorted in chronological order in the above example are compared with the corresponding model to estimate the hidden state by the Viterbi algorithm, and a sequence consisting of 300 link IDs is output. It should be understood that the position of the vehicle corresponding to each sampling moment can be arranged in chronological order.
  • the length of stay of the vehicle in each road segment is counted, and the traffic speed of the road segment is the length of the link segment/the length of the road segment staying.
  • the road section passing speed calculated directly by this method is different because the actual road section staying time is different from the calculated staying time length, so the calculation result is inaccurate and the variation between adjacent road sections is severe.
  • the original estimation result can be further processed by the smoothing method.
  • the widely installed conditions of various mobile APPs can be used.
  • Many APPs, such as social applications frequently communicate with the server side through the mobile network in the background, thus generating a large number of letters in the operator's mobile Internet log. Order records. Therefore, a better way to improve the accuracy of speed estimation is to integrate the mobile phone of the car and the passengers of the bus.
  • the generated signaling data is subjected to implicit state estimation.
  • the key to integrating the mobile phone signaling data of the passengers of the bus is to associate the mobile phone with the passengers. Once the connection between the passenger and the vehicle is completed, the subsequent trajectory extraction and implicit state estimation will be carried out using the existing methods. This is achieved in the following ways:
  • M-day M>30
  • mobile operator cell handover and location update log combine multiple logs in timestamp order, and merge them into one ⁇ timestamp, mobile station ID, base station ID> triplet Observation sequence recording (only observation sequence records between 10:00 and 17:00 daily).
  • the above observation sequence records are extracted, and all records with the same mobile station ID are extracted into an independent recording set to constitute an observation record of the mobile station. Only the observation records of the handheld mobile station are retained here, and the observation records of all non-handheld mobile stations are cleared.
  • Each of the remaining handheld mobile station observation records is filtered using the parking service base station set, leaving only the records in the mobile station observation record that the base station ID belongs to the parking service base station set. Perform trajectory separation on the filtered handheld mobile station observation records, calculate the number of times each handheld mobile station stays near the parking lot service base station, and retain the observation records of the handheld mobile stations with the number of stays greater than 2M, and clear all other mobile station observations. recording.
  • the trajectory similarity between each moving trajectory observation sequence in the moving trajectory observation sequence list and each bus line is calculated in turn, and the number of times the recorded trajectory observation sequence and the bus line similarity is greater than 90% is recorded as the effective trajectory number.
  • the mobile station trajectory observation sequence (list) of not less than 2 is retained while the ratio of the effective trajectory to the M (effective trajectory/M) is kept, and the moving trajectory observation sequence (list) of all other mobile stations is cleared.
  • the remaining mobile station is the mobile phone of the bus driver.
  • each of the above modules may be implemented by software or hardware.
  • the foregoing may be implemented by, but not limited to, the foregoing modules are all located in the same processor; or, the modules are located in multiple In the processor.
  • Embodiments of the present invention also provide a storage medium.
  • the foregoing storage medium may be configured to store program code for performing the following steps:
  • the log of the network operator obtains a trajectory sequence of the vehicular mobile station that communicates with the base station of the network operator on the bus to be monitored, wherein the trajectory sequence includes: multiple sets of time stamps having corresponding relationships, vehicle mobile station IDs, and Base station ID;
  • the road segment operation information of each road segment on the travel route of the bus to be monitored is obtained according to the trajectory sequence, wherein the road segment operation information includes multiple sets of time stamps and link IDs having corresponding relationships;
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a Read-Only Memory (ROM), a Random Access Memory (RAM), a mobile hard disk, and a magnetic memory.
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • a mobile hard disk e.g., a hard disk
  • magnetic memory e.g., a hard disk
  • modules or steps of the present invention described above can be implemented by a general-purpose computing device that can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they may be implemented by program code executable by the computing device such that they may be stored in the storage device by the computing device and, in some cases, may be different from the order herein.
  • the steps shown or described are performed, or they are separately fabricated into individual integrated circuit modules, or a plurality of modules or steps thereof are fabricated as a single integrated circuit module.
  • the invention is not limited to any specific combination of hardware and software.
  • a trajectory sequence of the vehicular mobile station that communicates with the base station of the network operator on the bus to be monitored is obtained from the log of the network operator, where the trajectory sequence includes: multiple groups have corresponding a time stamp of the relationship, the in-vehicle mobile station ID, and the base station ID; the road segment operation information of each road segment on the travel route of the bus to be monitored is obtained according to the trajectory sequence, wherein the road segment operation information includes multiple groups having corresponding The time stamp of the relationship and the link ID; obtaining the travel speed of the bus to be monitored on the respective road sections according to the road segment operation information, and obtaining the traffic data by directly using the existing base station data and the bus line data, and solving
  • the operation is complicated and the cost is high when the traffic data is acquired, thereby achieving the cost-saving effect.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种交通状态的获取方法及装置，其中，该方法包括：从网络运营商的日志中获取待监测的公交车上与该网络运营商的基站通信的车载移动台的轨迹序列，其中，该轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID（S102）；根据该轨迹序列获取该待监测的公交车的行驶路线上各个路段的路段运行信息，其中，该路段运行信息中包括多组具有对应关系的时间戳和路段ID（S104）；根据该路段运行信息获取该待监测的公交车在该各个路段上的行驶速度（S106）。该技术方案解决了相关技术中在获取交通数据时操作复杂且成本高的问题，进而达到了节省成本的效果。

Description

交通状态的获取方法及装置 技术领域
本发明涉及交通与移动通信领域，具体而言，涉及一种交通状态的获取方法及装置。
背景技术
交通是城市的重要构成要素之一，随着社会的持续发展和机动车保有量的快速上升，虽然城市路网也在日新月异的建设中，但道路的建设仍然远远落后于实际需求，导致交通拥堵成为一种世界范围内的城市病。而交通问题对城市的影响是全方面的，既包括交通管理、路网规划，又包括公共资源配置规划，还包括出行规划、节能减排，总之交通问题已经成为制约城市健康、高效、可持续发展的核心问题。
解决交通问题的一个核心基础是对城市范围内交通状态的定量刻画，只有在掌握区域性、全天候、实时、高密度的交通状态的定量信息的基础上，才能够为城市运营制定科学、合理的长期规划，并进行准确、高效的实时干预，甚至推动交通信息更充分、有效的应用到各个领域，进而带来更广泛的社会效应。
当前对交通信息的采集和分析有两条主要的技术路线，其一是基于固定型的路侧采集设备进行交通数据采集及相应的分析方法；其二是基于移动型交通数据采集及相应的分析方法。
固定型交通信息采集指通过布置在路口和卡口的磁频、波频和视频传感器采集过车信息(GB2436909、CN201510162656)，包括过车数量、时间、速度、方向、视频图像等，然后计算各路段的车流量。这种方法本质上是一种点测量的方法，虽然对于每个途经量测点的车辆可以获得比较丰富且高精度的量测信息，进而推测量测点处的交通状态，但却存在覆盖率低的缺点，只能在有限的路口和卡口进行监控，因此存在大量的监控盲区。由于该方案涉及的传感器种类多，数据集成与后续分析所需的技术复杂度高；另外，该方案需要的传感器数量多，并且部署时需要一定的土方工程，部署成本很高。
移动型交通数据采集一般指通过装备了GPS等定位设备的浮动车(US7783296、CN200910254490)获取交通数据，再结合地图匹配技术解决对道路通行状态的计算。因为采用了移动式的数据采集设备，该方案解决了固定型采集方案存在大量盲区的缺点，且通过GPS接收机能够以较高的精度采集多种车辆运行参数，包括时间、位置、速度、加速度、方向等。但该方案所依赖的技术仍然比较复杂，需要在浮动车上部署GPS接收机，且由于GPS定位系统自身的一些特点(易干扰、定位精度低于米级)，使得对车辆结果的后续处理流程也比较复杂，需要做异常检测、轨迹补齐、地图匹配等处理。使用该方案，为获取城市范围内高覆盖率、实时的交通数据，需要部署大量的浮动车，而其成本是非常高且依赖性强。
针对相关技术在获取实时交通数据时，操作繁杂，部署成本高的问题，目前尚未发现有效的解决方法。
发明内容
本发明实施例提供了一种交通状态的获取方法及装置，以至少解决相关技术中在获取交通数据时操作复杂且成本高的问题。
根据本发明实施例的一个方面，提供了一种交通状态的获取方法，包括：从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列，其中，所述轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；根据所述轨迹序列获取所述待监测的公交车的行驶路线上各个路段的路段运行信息，其中，所述路段运行信息中包括多组具有对应关系的时间戳和路段ID；根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度。
可选地，根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度包括：根据相同的所述路段ID对应的多个时间戳获取所述待监测的公交车在所述路段ID所指示的路段上的滞留时间T；通过以下公式计算得到所述待监测的公交车在所述路段ID所指示的路段上的行驶速度V：V＝D/T，其中，D为预先获取到的所述路段ID所指示的路段的长度。
可选地，在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，包括：从所述日志中确定出非手持移动台序列，其中，所述非手持移动台序列包括多组具有对应关系的时间戳、移动台ID和基站ID；根据所述非手持移动台序列获取所述日志中所记录的与所述网络运营商的基站通信的非手持移动台的运行轨迹；将所述运行轨迹与预定的公交车运行线路之间的重合度大于预定阈值的非手持移动台确定为车载移动台。
可选地，在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，包括：根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将所述待监控区域内的道路分割成一个或多个路段；建立所述待监控区域内各个路段到所述基站的映射，即建立所述待监控区域内各个路段到所述基站的概率模型，包括：建立各个路段的转移概率模型、建立所述基站到所述各个路段的观测概率模型；获取所述待监控区域内所述网络运营商的日志。
可选地，所述根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将所述待监控区域内的道路分割成一个或多个路段包括：获取待监控区域内的基站、行驶线路、道路的经纬度信息；以所述基站为分布点，所述行驶线路、道路为分布线，所述基站的辐射范围为分布圆建立交通线路分布图；所述分布圆与所述分布线的交点和所述行驶线路的交叉路口为分割点将所述分布线分割成多个路段。
可选地，所述建立所述待监控区域内各个路段到所述基站的映射包括：从所述交通线路分布图确定辐射所述各个路段的基站ID；建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射。
可选地，所述建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射包括：建立所述车载移动台ID与按照行驶线路的上行轨迹在各个路段上分别连接的多个基站的基站ID之间的第一对应关系，和/或，建立所述车载移动台ID与按照行驶线路的下行轨迹在各个路段上分别连接的多个基站的基站ID之间的第二对应关系。
可选地，所述从所述日志中确定出非手持移动台序列包括：判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第一预定时间段内平均连接的基站的数量是否大于第一预设阈值，和/或，判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第二预定时间段内平均切换基站的次数是否大于第二预设阈值；在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
可选地，所述从所述日志中确定出非手持移动台序列包括：判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第三预定时间段内在停车场内驻留的平均时间是否大于第三预设阈值，和/或，判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第四预定时间段内在停车场内驻留的平均次数是否大于第四预设阈值，和/或，判断所述日志中所记录的与所述网络运营商的基站通信的移动台在停车场内驻留的时间点是否在第五预定时间段内；在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
根据本发明实施例的另一方面，提供了一种交通状态的获取装置，包括：第一获取模块，设置为从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列，其中，所述轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；第二获取模块，设置为根据所述轨迹序列获取所述待监测的公交车的行驶路线上各个路段的路段运行信息，其中，所述路段运行信息中包括多组具有对应关系的时间戳和路段ID；第三获取模块，设置为根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度。
可选地，所述第三获取模块包括：第一获取单元，设置为根据相同的所述路段ID对应的多个时间戳获取所述待监测的公交车在所述路段ID所指示的路段上的滞留时间T；计算单元，设置为通过以下公式计算得到所述待监测的公交车在所述路段ID所指示的路段上的行驶速度V：V＝D/T，其中，D为预先获取到的所述路段ID所指示的路段的长度。
可选地，所述装置还包括：第一确定模块，设置为在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，从所述日志中确定出非手持移动台序列，其中，所述非手持移动台序列包括多组具有对应关系的时间戳、移动台ID和基站ID；第四获取模块，设置为根据所述非手持移动台序列获取所述日志中所记录的与所述网络运营商的基站通信的非手持移动台的运行轨迹；第二确定模块，设置为将所述运行轨迹与预定的公交车运行线路之间的重合度大于预定阈值的非手持移动台确定为车载移动台。
可选地，所述装置还包括：第一建立模块，设置为在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将所述待监控区域内的道路分割成一个或多个路段；第二建立模块，设置为建立所述待监控区域内各个路段到所述基站的映射，即建立所述待监控区域内各个路段到所述基站的概率模型，包括：建立各个路段的转移概率模型、建立所述基站到所述各个路段的观测概率模型；第五获取模块，设置为获取所述待监控区域内所述网络运营商的日志。
可选地，所述第一建立模块包括：第二获取单元，设置为获取待监控区域内的基站、行驶线路、道路的经纬度信息；第一建立单元，设置为以所述基站为分布点，所述行驶线路、道路为分布线，所述基站的辐射范围为分布圆建立交通线路分布图；分割单元，设置为以所述分布圆与所述分布线的交点和所述行驶线路的交叉路口为分割点将所述分布线分割成多个路段。
可选地，所述第二建立模块包括：第一确定单元，设置为从所述交通线路分布图确定辐射所述各个路段基站ID；第二建立单元，设置为建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射。
可选地，所述第二建立单元还包括：第一建立子单元，设置为建立所述车载移动台ID与按照行驶线路的上行轨迹在各个路段上分别连接的多个基站的基站ID之间的第一对应关系；和/或，第二建立子单元，设置为建立所述车载移动台ID与按照行驶线路的下行轨迹在各个路段上分别连接的多个基站的基站ID之间的第二对应关系。
可选地，所述第一确定模块包括：第一判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第一预定时间段内平均连接的基站的数量是否大于第一预设阈值；和/或，第二判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第二预定时间段内平均切换基站的次数是否大于第二预设阈值；第二确定单元，设置为在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
可选地，所述第一确定模块包括：第三判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第三预定时间段内在停车场内驻留的平均时间是否大于第三预设阈值，和/或，第四判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第四预定时间段内在停车场内驻留的平均次数是否大于第四预设阈值，和/或，第五判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在停车场内驻留的时间点是否在第五预定时间段内；第三确定单元，设置为在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
通过本发明实施例，采用从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列，其中，所述轨迹序列包括：多组具有对应关系的时 间戳、车载移动台ID和基站ID；根据所述轨迹序列获取所述待监测的公交车的行驶路线上各个路段的路段运行信息，其中，所述路段运行信息中包括多组具有对应关系的时间戳和路段ID；根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度，通过直接利用已有的基站数据和公交线路数据来得到交通数据，解决了相关技术中在获取交通数据时操作复杂且成本高的问题，进而达到了节省成本的效果。
附图说明
此处所说明的附图用来提供对本发明的进一步理解，构成本申请的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1是根据本发明实施例的交通状态的获取方法的流程图；
图2是根据本发明实施例的交通状态的获取装置的结构框图；
图3是根据本发明实施例的交通状态的获取装置的可选结构框图一；
图4是根据本发明实施例的交通状态的获取装置的可选结构框图二；
图5是根据本发明实施例的交通状态的获取装置的可选结构框图三；
图6是根据本发明实施例的交通状态的获取装置的可选结构框图四；
图7是根据本发明实施例的交通状态的获取装置的可选结构框图五；
图8是根据本发明实施例的交通状态的获取装置的可选结构框图六；
图9是根据本发明实施例的交通状态的获取装置的可选结构框图七；
图10是根据本发明可选实施例的公交车识别与建模流程图；
图11是根据本发明可选实施例的轨迹识别与模型求解流程图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本发明。需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。
需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
在本实施例中提供了一种交通状态的获取方法，图1是根据本发明实施例的交通状态的获取方法的流程图，如图1所示，该流程包括如下步骤：
步骤S102，从网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列，其中，轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和 基站ID；
步骤S104，根据轨迹序列获取待监测的公交车的行驶路线上各个路段的路段运行信息，其中，路段运行信息中包括多组具有对应关系的时间戳和路段ID；
步骤S106，根据路段运行信息获取待监测的公交车在各个路段上的行驶速度。
通过本实施例，采用从网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列，其中，轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；根据轨迹序列获取待监测的公交车的行驶路线上各个路段的路段运行信息，其中，路段运行信息中包括多组具有对应关系的时间戳和路段ID；根据路段运行信息获取待监测的公交车在各个路段上的行驶速度，通过直接利用已有的基站数据和公交线路数据来得到交通数据，解决了相关技术中在获取交通数据时操作复杂且成本高的问题，进而达到了节省成本的效果。
在根据本实施例的可选实施方式中，根据路段运行信息获取待监测的公交车在各个路段上的行驶速度包括：
S11，根据相同的路段ID对应的多个时间戳获取待监测的公交车在路段ID所指示的路段上的滞留时间T；
S12，通过以下公式计算得到待监测的公交车在路段ID所指示的路段上的行驶速度V：V＝D/T，其中，D为预先获取到的路段ID所指示的路段的长度。
在根据本实施例的可选实施方式中，在从网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列之前，还可以通过基站内的通信日志记录识别和确定车载移动台，具体包括：
S21，从日志中确定出非手持移动台序列，其中，非手持移动台序列包括多组具有对应关系的时间戳、移动台ID和基站ID；
S22，根据非手持移动台序列获取日志中所记录的与网络运营商的基站通信的非手持移动台的运行轨迹；
S23，将运行轨迹与预定的公交车运行线路之间的重合度大于预定阈值的非手持移动台确定为车载移动台。
在根据本实施例的可选实施方式中，在从网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列之前，还可以建立各个路段到基站的映射关系，建立路段的概率模型，具体包括：
S31，根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将待监控区域内的道路分割成一个或多个路段；
S32，建立待监控区域内各个路段到基站的映射；可选的，在本实施例中建立待监控区域 内各个路段到基站的映射，即建立所述待监控区域内各个路段到所述基站的概率模型，包括：建立各个路段的转移概率模型、建立所述基站到所述各个路段的观测概率模型。
S33，获取待监控区域内网络运营商的日志。
可选的，根据上述实施方式，根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将待监控区域内的道路分割成一个或多个路段包括：
S41，获取待监控区域内的基站、行驶线路、道路的经纬度信息；
S42，以基站为分布点，行驶线路、道路为分布线，基站的辐射为分布圆建立交通线路分布图；
S43，以分布圆与分布线的交点和行驶线路的交叉路口为分割点将分布线分割成多个路段。
在本实施例中，行驶线路的交叉路口包括：十字交通路口、丁字交通路口等交通路口。
可选的，建立待监控区域内各个路段到基站的映射包括：
S51，从交通线路分布图确定辐射各个路段的基站ID；
S52，建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射，其中，在相邻路段上进行通信连接的基站不同。
可选的，在具体实现建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射时，按照公交车的上行轨迹和下行轨迹分别建立映射，包括：建立车载移动台ID与按照行驶线路的上行轨迹在各个路段上分别连接的多个基站的基站ID之间的第一对应关系，建立车载移动台ID与按照行驶线路的下行轨迹在各个路段上分别连接的多个基站的基站ID之间的第二对应关系。
在根据本实施例的可选实施方式中，从日志中确定出非手持移动台序列包括两种可选的方式，其中，
方式一包括：判断日志中所记录的与网络运营商的基站通信的移动台在每天的第一预定时间段内平均连接的基站的数量是否大于第一预设阈值，判断日志中所记录的与网络运营商的基站通信的移动台在每天的第二预定时间段内平均切换基站的次数是否大于第二预设阈值，判断日志中所记录的与移动台通信的网络运营商的基站是否属于第一预设集合，在判断结果为是时，确定移动台为非手持移动台，并从日志中获取非手持移动台的非手持移动台序列。
方式二包括：判断日志中所记录的与网络运营商的基站通信的移动台在每天的第三预定时间段内在停车场内驻留的平均时间是否大于第三预设阈值，判断日志中所记录的与网络运营商的基站通信的移动台在每天的第四预定时间段内在停车场内驻留的平均次数是否大于第四预设阈值，判断日志中所记录的与网络运营商的基站通信的移动台在停车场内驻留的时间 点是否在第五预定时间段内；在判断结果为是时，确定移动台为非手持移动台，并从日志中获取非手持移动台的非手持移动台序列。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本发明各个实施例的方法。
在本实施例中还提供了一种交通状态的获取装置，该装置用于实现上述实施例及优选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图2是根据本发明实施例的交通状态的获取装置的结构框图，如图2所示，该装置包括：第一获取模块20、第二获取模块22、第三获取模块24，其中，
第一获取模块20，设置为从网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列，其中，轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；
第二获取模块22，设置为根据轨迹序列获取待监测的公交车的行驶路线上各个路段的路段运行信息，其中，路段运行信息中包括多组具有对应关系的时间戳和路段ID；
第三获取模块24，设置为根据路段运行信息获取待监测的公交车在各个路段上的行驶速度。
图3是根据本发明实施例的交通状态的获取装置的可选结构框图一，如图3所示，该装置除包括图2所示的所有模块外，第三获取模块24还包括：
第一获取单元30，设置为根据相同的路段ID对应的多个时间戳获取待监测的公交车在路段ID所指示的路段上的滞留时间T；
计算单元32，设置为通过以下公式计算得到待监测的公交车在路段ID所指示的路段上的行驶速度V：V＝D/T，其中，D为预先获取到的路段ID所指示的路段的长度。
图4是根据本发明实施例的交通状态的获取装置的可选结构框图二，如图4所示，该装置除包括图2所示的所有模块外，装置还包括：第一确定模块40、第四获取模块42、第二确定模块44，其中，
第一确定模块40，设置为在从网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列之前，从日志中确定出非手持移动台序列，其中，非手持移动台序列包括多组具有对应关系的时间戳、移动台ID和基站ID；
第四获取模块42，设置为根据非手持移动台序列获取日志中所记录的与网络运营商的基站通信的非手持移动台的运行轨迹；
第二确定模块44，设置为将运行轨迹与预定的公交车运行线路之间的重合度大于预定阈值的非手持移动台确定为车载移动台。
图5是根据本发明实施例的交通状态的获取装置的可选结构框图三，如图5所示，该装置除包括图2所示的所有模块外，装置还包括：第一建立模块50、第二建立模块52、第五获取模块54，其中，
第一建立模块50，设置为在从网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列之前，根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将待监控区域内的道路分割成一个或多个路段；
第二建立模块52，设置为建立待监控区域内各个路段到基站的映射；
第五获取模块54，设置为获取待监控区域内网络运营商的日志。
图6是根据本发明实施例的交通状态的获取装置的可选结构框图四，如图6所示，该装置除包括图5所示的所有模块外，第一建立模块50包括：第二获取单元60、第一建立单元62、分割单元64，其中，
第二获取单元60，设置为获取待监控区域内的基站、行驶线路、道路的经纬度信息；
第一建立单元62，设置为以基站为分布点，行驶线路、道路为分布线，基站的辐射为分布圆建立交通线路分布图；
分割单元64，设置为以分布圆与分布线的交点和行驶线路的交叉路口为分割点将分布线分割成多个路段。
图7是根据本发明实施例的交通状态的获取装置的可选结构框图五，如图7所示，该装置除包括图5所示的所有模块外，第二建立模块52包括：第一确定单元70、第二建立单元72，其中，
第一确定单元70，设置为从交通线路分布图确定辐射各个路段的基站ID；
第二建立单元72，设置为建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射，其中，在相邻路段上进行通信连接的基站不同。
可选的，第二建立单元72还包括：第一建立子单元，设置为建立车载移动台ID与按照行驶线路的上行轨迹在各个路段上分别连接的多个基站的基站ID之间的第一对应关系；第二建立子单元，设置为建立车载移动台ID与按照行驶线路的下行轨迹在各个路段上分别连接的多个基站的基站ID之间的第二对应关系。
图8是根据本发明实施例的交通状态的获取装置的可选结构框图六，如图8所示，该装置除包括图4所示的所有模块外，第一确定模块40包括：第一判断单元80、第二判断单元 82、第二确定单元84，其中，
第一判断单元80，设置为判断日志中所记录的与网络运营商的基站通信的移动台在每天的第一预定时间段内平均连接的基站的数量是否大于第一预设阈值；
第二判断单元82，设置为判断日志中所记录的与网络运营商的基站通信的移动台在每天的第二预定时间段内平均切换基站的次数是否大于第二预设阈值；
第二确定单元84，设置为在判断结果为是时，确定移动台为非手持移动台，并从日志中获取非手持移动台的非手持移动台序列。可选的，可以在第一判断单元80和第二判断单元82的判断结果同时为否，或者其中之一为否时，确定移动台为非手持移动台。
图9是根据本发明实施例的交通状态的获取装置的可选结构框图七，如图9所示，该装置除包括图4所示的所有模块外，第一确定模块40包括：第三判断单元90、第四判断单元92、第五判断单元94、第三确定单元96，其中，
第三判断单元90，设置为判断日志中所记录的与网络运营商的基站通信的移动台在每天的第三预定时间段内在停车场内驻留的平均时间是否大于第三预设阈值；
第四判断单元92，设置为判断日志中所记录的与网络运营商的基站通信的移动台在每天的第四预定时间段内在停车场内驻留的平均次数是否大于第四预设阈值；
第五判断单元94，设置为判断日志中所记录的与网络运营商的基站通信的移动台在停车场内驻留的时间点是否在第五预定时间段内；
第三确定单元96，设置为在判断结果为是时，确定移动台为非手持移动台，并从日志中获取非手持移动台的非手持移动台序列。可选的，可以在第三判断单元90、第四判断单元92、第五判断单元94其中至少之一或者全部的判断结果为是时，确定移动台为非手持移动台。
下面结合根据本发明的可选实施例对本发明进行详细具体的说明：
本可选实施例将预知的公交线路和基站经纬度位置知识，和给定时间窗口中观测到的公交车在基站空间的位置变化序列数据进行信息融合，以提高基站定位的精度进而估计公交车在相应时间段所处的路段，并进一步计算车辆在相应路段的通行速度。
本可选实施例的方法包括如下两个阶段：
阶段1，公交车识别与建模阶段：本阶段是一个离线处理阶段，定期运行，主要完成三方面工作：1.维护公交线路、基站位置等预知信息；2.建立用于隐状态估计的概率模型；3.识别公交车载移动台/组。
阶段2，轨迹识别与模型求解阶段：本阶段是一个在线处理阶段，实时的识别出每辆公交车当前运行的公交线路与上下行状态，并使用建模阶段建立的概率模型在观测数据序列基础上推理，估计车辆各时段所在的路段，并进一步结合时间和路段长度计算各路段的通行速度。
可选的，阶段1的公交车识别与建模包括：
第一步：基站经纬度、公交线路、道路信息录入。
第二步：建立基站经纬度、公交线路、道路分布关系图。将道路、公交线路以线的方式，基站以点的方式绘制在同一个二维空间中，同时以每个基站为圆心，以R(假设基站控制器中配置的基站覆盖半径为r，则此处R＝2*r)为半径在该二维空间中绘制基站的影响范围图。在实际使用中，基站控制器配置的覆盖半径为r都会小于基站的实际覆盖范围，实际覆盖的半径R为配置半径的两倍，R＝2*r。
第三步：路段分隔。以步骤一中围绕基站所绘圆与代表公交线路的线相交的所有点为分隔点(此外分隔点还包括各种路口)，将道路分隔成一个个的路段，计算各路段长度并为各路段分配路段ID。
第四步：建立两层概率模型。对每条公交线路的上下行线路构建概率模型，主要是确定隐状态、转移矩阵和观测矩阵。模型以步骤三分隔出来的路段为隐状态，公交车载移动台连接的基站为观测状态。模型观测概率与路段与基站距离成正比，并进行归一化处理，保证隐状态观测到各观测状态的概率和为1。转移概率与路段的长度与上下行关系有关，隐状态A的可能的目标转移状态B只能在当前行驶方向(上行、下行)的临近的前方，隐状态A向其后方状态或前方远处状态的转移概率为0；隐状态A向其前方临近状态的转移概率不为零，隐状态A向其自身的转移状态与A对应的路段长度有关，隐状态转移概率需进行归一化处理，保证其和为1。本阶段需要为所有线路对应的上行线路和下行线路分别建立相应的概率模型。
第五步：识别公交车载移动台/组。从移动运营商话单、上网、小区切换、位置更新等日志中抽取各移动台行为和移动性数据，按照Humanity行为属性和每日处于移动状态的平均时长、每日平均基站切换数量、每日的轨迹重复度、轨迹与公交线路重复度因子等移动性指标，过滤出公交车载的移动台。并以时空重复度高为原则，从这批公交车载的移动台中识别出哪些移动台是部署在同一台公交车上的，即移动台组。
可选的，阶段2的轨迹识别与模型求解包括：
第一步：提取公交车上下行轨迹。从移动运营商日志中提取同一辆公交车载移动台的轨迹序列，根据始发站和终点站附近的基站集合和车辆移动状态对轨迹进行分隔，根据运行方向识别上下行状态。经过公交车上下行轨迹分隔和上下行状态识别，能够提取到每辆车处于服务状态的运动轨迹序列，包括线路ID、上下行状态和轨迹序列。
第二步：估计隐状态序列。根据步骤一上下行线路轨迹提取结果，从“建模阶段”阶段建立的模型集合中取出相应线路相应上下行状态的模型，将观测序列输入模型，估计不同时刻车辆所在路段。
第三步：计算各路段通行速度。对于每个车辆的轨迹序列，根据各路段长度和处于该路段中的时间间隔，可以直接计算该路段通行速度，同时在相邻路段间使用平滑滤波提高估计精度。
通过本可选实施例，克服了相关技术中存在的区域覆盖面不足、技术复杂、部署成本高， 难于实时获取区域范围内道路交通状态的问题和缺陷，降低了部署难度，节省了部署成本，提高了区域覆盖率，能够达到实时检测的效果。
需要说明的是，本实施例如不特别说明，小区、基站、基站天线均指基站天线。
下面结合附图对实施例的实施作进一步的详细描述，图10是根据本发明可选实施例的公交车识别与建模流程图，如图10所示，包括：
S201、基站经纬度、公交线路、道路信息录入
需要将基站经纬度、基站覆盖半径、公交线及其各站点经纬度、城市道路经纬度信息录入系统。
S202、建立城市道路、公交线路与基站分布图
将基站、公交站点、道路路口以点的方式，公交线、道路以线的方式，基站影响范围以圆(半径为R)的方式绘制在一个平面中。
S203、路段分隔
提取步骤二中所有的圆与公交线的交点，以及所有的道路路口点，共同构成分割点集合，以这些点对公交线进行分隔，得到一系列直线型的分隔段--路段，并对每个线路中的每个路段顺序(按照上行方向)进行编号，分配唯一的路段ID，获得<线路ID，List(路段ID)>两元组集合。同时计算每个路段的路段长度。
S204、建立两层概率模型
对于每条公交线路需要构建两个模型：上行模型和下行模型。
本实施例仅以构建一个上行线路的概率模型为例说明模型构建的方式，下行线路模型的构建原理相同，在此不再赘述。
转移概率矩阵为源状态(隐状态)到目标状态(隐状态)的转移概率构成的矩阵，以纵坐标代表原状态横坐标代表目标状态，状态按照上下行的前后历经关系从上到下、从左到右。转移矩阵对角线元素和对角线上面一个元素非零，其他所有矩阵元素都为零，是一个典型的稀疏矩阵。矩阵元素(i,j)代表车辆上一次观测在隐状态i对应路段时，下一次观测转移到隐状态j对应路段上的概率p(i,j)。设路段i的长度为li，该线路平均运行速度V和观测采样间隔为T，p(i,j)取值如下：
Figure PCTCN2016075255-appb-000001
观测概率矩阵为车辆处于隐状态i对应的路段情况下，能够观测到观测状态j相应的基站的概率po(i,j)构成的矩阵，其纵坐标定义同转移矩阵纵坐标定义，横坐标为各观测状态(基站)。设dij为路段i到基站j的平均距离，po(i,j)取值如下：
Figure PCTCN2016075255-appb-000002
其中∝代表正比关系，需要对观测矩阵的每行元素做归一化。
可选的，还可以使用改进的模型构造方式，将浮动车实际路测数据与理论计算值相结合，构造转移概率矩阵和观测概率矩阵，包括如下两个示例：
示例一、将浮动车实际路测数据与理论计算值相结合。采用上述理论计算方法计算得的转移概率矩阵没有考虑到各个路段不同的繁忙程度和时间差异。基于大数定律，使用大量的浮动车路测数据对理论计算值进行校准成为一种较好的选择。具体做法是进行随机抽样，随机的选择一条处于移动状态的浮动车记录，计算根据经纬度计算当前所处路段i，并使用当前速度和采用间隔(详见下述S301部分)外推下一步所处路段j。重复进行大量的这种抽样，统计路段i转移到路段j的次数，构造隐状态转移数量矩阵，然后对转移数量矩阵按行归一化得到统计到的转移概率矩阵，将理论计算的转移概率矩阵与路测统计的转移概率矩阵逐个元素的进行某种加权运算，如求平均值，然后将所得矩阵再按行归一化，即得到校正后的观测概率矩阵。
示例二、将浮动车实际路测数据与理论计算值相结合。受地形、建筑物等各种因素的影响，基站的实际覆盖范围比较复杂，各路段观测到相应基站的概率难于进行准确的进行理论估算。而基于大数定律，采用较长一段时间内大量的浮动车路测数据对理论计算值进行校准成为一种较好的选择。具体做法可以从海量浮动车路测数据统计各路段观测到各个基站的次数，构造隐状态对观测状态的观测数量矩阵，然后对观测数量矩阵按行归一化得到统计到的观测概率矩阵，将理论计算的观测概率矩阵与路测统计的观测概率矩阵逐个元素的进行某种加权运算，如求平均值，然后将所得矩阵再按行归一化，即得到校正后的观测概率矩阵。
S205、识别公交车载移动台/组
可选的，取N天(N>30)的话单日志，统计各移动台作为主叫方进行语音呼叫，且呼叫接通通话时长不低于10秒的次数，记录所有有效主叫次数大于1的移动台ID，且将这些移动台称为手持移动台。
可选的，取M天(M>30)的移动运营商上网、小区切换、位置更新等记录移动台位置数据的日志，将多个日志按照时间戳先后顺序进行融合，合并成一个<时间戳、移动台ID、基站ID>三元组构成的观测序列记录，可以只保留每天10:00～17:00之间的观测序列记录。
对上述观测序列记录进行抽取，将所有移动台ID相同的记录抽取到一个独立的记录集中，构成该移动台的观测记录。在此仅保留非手持移动台的观测记录进行后续分析，而清除所有手持移动台的观测记录。
对每个移动台的观测记录进行轨迹分隔，提取各移动台处于移动状态下的移动轨迹观测序列列表。
统计各移动台处于运动状态下的时长，保留时长处于最多的10％区间内的移动台移动轨迹观测序列(列表)，而清除所有其他移动台的移动轨迹观测序列(列表)。
对于每个移动台，依次计算其移动轨迹观测序列列表中每段移动轨迹观测序列与各公交线路的轨迹相似度，记录轨迹观测序列与公交线路相似度大于90％的次数记为有效轨迹次数。保留有效轨迹次数与M之比(有效轨迹次数/M)不小于2的移动台移动轨迹观测序列(列表)，而清除所有其他移动台的移动轨迹观测序列(列表)。
经上述几步过滤，保留下来的移动台即为公交车载移动台。
对每个车载移动台的每个移动轨迹观测序列，提取其对应公交线路，以及从始发站发车和到达终点站的时间构成<线路ID、始发时间、终点站时间、移动台ID>四元组，将所有车载移动台的所有移动轨迹观测序列提取结果合并到同一个列表中。将该<线路ID、始发时间、终点站时间、移动台ID>四元组列表进行抽取，将所有线路ID相同的记录抽取到一个独立的<始发时间、终点站时间、移动台ID>三元组记录列表中，并分别对各线路对应的<始发时间、终点站时间、移动台ID>三元组记录列表按照始发时间、终点时间排序，然后抽取排序结果的最后一列(移动台ID)进行频繁模式挖掘，从中发现经常出现的频繁集，即为同一台车辆上的移动台/组。
可选的，还可以采用改进的公交车移动台识别方法，即采用公交车停车场的位置信息，以此提高公交车移动台识别准确率。具体如下：
使用车载移动台开机注册信令日志中的位置数据发现公交车停车场，并进而再利用发现的停车场位置辅助公交车移动台识别精度的提供。公交车辆进场停车后车载设备掉电导致车载移动台关机，当第二天启动车辆时车载移动台上电，安装蜂窝网络通信协议，移动台需完成在蜂窝网络的注册流程。利用该特点，具体做法是从M天(M>30)移动台注册日志中抽取由上述流程识别出的所有移动台注册记录，取出相应的基站ID，并查询基站经纬度位置(Lat，Lon)。对这些二维数据进行Kmeans聚类(聚类最大半径为R，在此每个经纬度数据对称为一个样本)，从聚类结果中取出聚类中样本数大于4M的类以及属于该类的基站，共同构成一个基站集合，成为停车场服务基站集。使用停车场服务基站集与上述流程识别出的所有移动台进行对比，提取每个移动台停车间隔大于2小时后的所有网络注册信令记录，如果记录中有超过20％的基站不属于停车场服务基站集，则将该移动台从公交车载移动台集合中删除。
图11是根据本发明可选实施例的轨迹识别与模型求解流程图，如图11所示，包括：
S301、提取公交车上下行轨迹
取移动运营商上网、小区切换、位置更新等记录移动台位置数据的日志，将多个日志按照记录按时间戳先后顺序进行融合，合并成一个<时间戳、移动台ID、基站ID>三元组构成的观测序列记录。
对上述观测序列记录进行抽取，将所有移动台ID相同的记录抽取到一个独立的记录集中，构成该移动台的观测记录。在此仅保留公交车载移动台对应的观测序列。
对于每辆公交车，查询其车载移动台组，将属于车辆的移动台记录按照时间戳顺序进行融合，合并成一个<时间戳、移动台ID、基站ID>三元组构成的观测序列记录。
针对每辆公交车的<时间戳、移动台ID、基站ID>三元组构成的观测序列进行轨迹分隔，提取车辆处于移动状态下的移动轨迹观测序列列表。对于移动轨迹观测序列列表中的每个移动轨迹观测序列，根据其始发地点信息就可以直接判断当前车辆服务的公交线路以及上下行状态。以固定采样间隔(5秒，平均路段长度/(10*平均行驶速度)<采样间隔<平均路段长度/(2*平均行驶速度))，对该序列进行采样获得采样后按时间先后顺序排序的、固定间隔的<时间戳、<基站ID1，基站ID2，基站IDn>>观测序列。
例如对于一台携带3个移动台的公交车，经过上述分析能够判断在10:15～10:40之间跑了一趟公交101路的上行线路，且在这25分钟的运营中共采样到25*(60/5)＝300组观测数据，每组观测数据由3个基站ID构成，如(基站ID1，基站ID2，基站ID3)。
S302、估计隐状态序列
对于上述S301步骤中经固定间隔采样到的观测序列，从模型集中选择相应路线相应上下行状态的模型。
按照线路和上下行状态初始化隐状态初始值，使用Viterbi算法输入观测序列进行推理，获得相应的隐状态序列<时间戳、路段ID>。
如将上例的300组按时间先后顺序排序的<基站ID1，基站ID2，基站ID3>观测序列和相应模型一起进行Viterbi算法估计隐状态，会输出一个由300个路段ID构成的序列，该序列应该理解成各采样时刻对应的车辆位置，可以按照时间先后顺序进行排列。
S303、计算各路段通行速度
在得到各条移动轨迹观测序列对应的隐状态序列<时间戳、路段ID>的基础上，统计车辆在各路段的滞留时长，该路段的通行速度＝路段长度/路段滞留时长。
使用该方法直接计算得的路段通行速度因为实际路段滞留时长与计算使用的滞留时长存在差异，因此计算结果不准确，且相邻路段间变化剧烈。为进一步提高路段估计误差，可以采用平滑方法对原始估计结果进一步处理。
可选的，可以使用当前各种手机APP的广泛安装的条件，很多APP，如社交类应用，后台会频繁的通过移动网络与服务器侧通信，因而会在运营商移动上网日志中产生大量的信令记录。因此，一种更优的提升速度估计精度的方法是融合车载移动台和公交车司乘人员手机 产生的信令数据进行隐状态估计。融合公交车司乘人员手机信令数据的关键，是将司乘人员手机与公交车进行关联，一旦完成人车的关联，后续的轨迹提取、隐状态估计都将使用现有方式进行。具体通过以下方式实现：
取N天(N>30)的话单日志，统计各移动台作为主叫方进行语音呼叫，且呼叫接通通话时长不低于10秒的次数，记录所有有效主叫次数大于1的移动台ID，且将这些移动台称为手持移动台。
取M天(M>30)的移动运营商小区切换、位置更新日志，将多个日志按照时间戳先后顺序进行融合，合并成一个<时间戳、移动台ID、基站ID>三元组构成的观测序列记录(只保留每天10:00～17:00之间的观测序列记录)。
对上述观测序列记录进行抽取，将所有移动台ID相同的记录抽取到一个独立的记录集中，构成该移动台的观测记录。在此仅保留手持移动台的观测记录，而清除所有非手持移动台的观测记录。
统计各手持移动台观测记录中记录数量，保留记录数最多的Top K(K为2倍的该市公交车数量)移动台移动轨迹观测序列(列表)，而清除所有其他移动台的移动轨迹观测序列(列表)。
使用停车场服务基站集对保留下来的每个手持移动台观测记录进行过滤，仅保留每个移动台观测记录中基站ID属于停车场服务基站集的记录。对过滤后的手持移动台观测记录进行轨迹分隔，计算每个手持移动台在停车场服务基站附近逗留的次数，保留逗留次数大于2M的手持移动台的观测记录，而清除所有其他移动台的观测记录。
对于每个移动台，依次计算其移动轨迹观测序列列表中每段移动轨迹观测序列与各公交线路的轨迹相似度，记录轨迹观测序列与公交线路相似度大于90％的次数记为有效轨迹次数。保留有效轨迹次数与M之比(有效轨迹次数/M)不小于2的移动台移动轨迹观测序列(列表)，而清除所有其他移动台的移动轨迹观测序列(列表)。
经上述几步过滤，保留下来的移动台即为公交车司乘人员手机。
需要说明的是，上述各个模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：上述模块均位于同一处理器中；或者，上述模块分别位于多个处理器中。
本发明的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以被设置为存储用于执行以下步骤的程序代码：
S1，网络运营商的日志中获取待监测的公交车上与网络运营商的基站通信的车载移动台的轨迹序列，其中，轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；
S2，根据轨迹序列获取待监测的公交车的行驶路线上各个路段的路段运行信息，其中，路段运行信息中包括多组具有对应关系的时间戳和路段ID；
S3，根据路段运行信息获取待监测的公交车在各个路段上的行驶速度。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
可选地，本实施例中的具体示例可以参考上述实施例及可选实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本发明的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本发明不限制于任何特定的硬件和软件结合。
以上所述仅为本发明的优选实施例而已，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
通过本发明实施例，采用从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列，其中，所述轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；根据所述轨迹序列获取所述待监测的公交车的行驶路线上各个路段的路段运行信息，其中，所述路段运行信息中包括多组具有对应关系的时间戳和路段ID；根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度，通过直接利用已有的基站数据和公交线路数据来得到交通数据，解决了相关技术中在获取交通数据时操作复杂且成本高的问题，进而达到了节省成本的效果。

Claims (18)

  1. 一种交通状态的获取方法，包括：
    从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列，其中，所述轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；
    根据所述轨迹序列获取所述待监测的公交车的行驶路线上各个路段的路段运行信息，其中，所述路段运行信息中包括多组具有对应关系的时间戳和路段ID；
    根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度。
  2. 根据权利要求1所述的方法，其中，根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度包括：
    根据相同的所述路段ID对应的多个时间戳获取所述待监测的公交车在所述路段ID所指示的路段上的滞留时间T；
    通过以下公式计算得到所述待监测的公交车在所述路段ID所指示的路段上的行驶速度V：V＝D/T，其中，D为预先获取到的所述路段ID所指示的路段的长度。
  3. 根据权利要求1所述的方法，其中，在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，包括：
    从所述日志中确定出非手持移动台序列，其中，所述非手持移动台序列包括多组具有对应关系的时间戳、移动台ID和基站ID；
    根据所述非手持移动台序列获取所述日志中所记录的与所述网络运营商的基站通信的非手持移动台的运行轨迹；
    将所述运行轨迹与预定的公交车运行线路之间的重合度大于预定阈值的非手持移动台确定为车载移动台。
  4. 根据权利要求1所述的方法，其中，在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，包括：
    根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将所述待监控区域内的道路分割成一个或多个路段；
    建立所述待监控区域内各个路段到所述基站的映射；
    获取所述待监控区域内所述网络运营商的日志。
  5. 根据权利要求4所述的方法，其中，所述根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将所述待监控区域内的道路分割成一个或多个路段包括：
    获取待监控区域内的基站、行驶线路、道路的经纬度信息；
    以所述基站为分布点，所述行驶线路、道路为分布线，所述基站的辐射范围为分布圆建立交通线路分布图；
    以所述分布圆与所述分布线的交点和所述行驶线路的交叉路口为分割点将所述分布线分割成多个路段。
  6. 根据权利要求4所述的方法，其中，所述建立所述待监控区域内各个路段到所述基站的映射包括：
    从所述交通线路分布图确定辐射所述各个路段的基站的基站ID；
    建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射。
  7. 根据权利要求6所述的方法，其中，所述建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射包括：
    建立所述车载移动台ID与按照行驶线路的上行轨迹在各个路段上分别连接的多个基站的基站ID之间的第一对应关系，和/或，建立所述车载移动台ID与按照行驶线路的下行轨迹在各个路段上分别连接的多个基站的基站ID之间的第二对应关系。
  8. 根据权利要求3所述的方法，其中，所述从所述日志中确定出非手持移动台序列包括：
    判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第一预定时间段内平均连接的基站的数量是否大于第一预设阈值，和/或，判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第二预定时间段内平均切换基站的次数是否大于第二预设阈值；
    在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
  9. 根据权利要求3所述的方法，其中，所述从所述日志中确定出非手持移动台序列包括：
    判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第三预定时间段内在停车场内驻留的平均时间是否大于第三预设阈值，和/或，判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第四预定时间段内在停车场内驻留的平均次数是否大于第四预设阈值，和/或，判断所述日志中所记录的与所述网络运营商的基站通信的移动台在停车场内驻留的时间点是否在第五预定时间段内；
    在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
  10. 一种交通状态的获取装置，包括：
    第一获取模块，设置为从网络运营商的日志中获取待监测的公交车上与所述网络运 营商的基站通信的车载移动台的轨迹序列，其中，所述轨迹序列包括：多组具有对应关系的时间戳、车载移动台ID和基站ID；
    第二获取模块，设置为根据所述轨迹序列获取所述待监测的公交车的行驶路线上各个路段的路段运行信息，其中，所述路段运行信息中包括多组具有对应关系的时间戳和路段ID；
    第三获取模块，设置为根据所述路段运行信息获取所述待监测的公交车在所述各个路段上的行驶速度。
  11. 根据权利要求10所述的装置，其中，所述第三获取模块包括：
    第一获取单元，设置为根据相同的所述路段ID对应的多个时间戳获取所述待监测的公交车在所述路段ID所指示的路段上的滞留时间T；
    计算单元，设置为通过以下公式计算得到所述待监测的公交车在所述路段ID所指示的路段上的行驶速度V：V＝D/T，其中，D为预先获取到的所述路段ID所指示的路段的长度。
  12. 根据权利要求10所述的装置，其中，所述装置还包括：
    第一确定模块，设置为在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，从所述日志中确定出非手持移动台序列，其中，所述非手持移动台序列包括多组具有对应关系的时间戳、移动台ID和基站ID；
    第四获取模块，设置为根据所述非手持移动台序列获取所述日志中所记录的与所述网络运营商的基站通信的非手持移动台的运行轨迹；
    第二确定模块，设置为将所述运行轨迹与预定的公交车运行线路之间的重合度大于预定阈值的非手持移动台确定为车载移动台。
  13. 根据权利要求10所述的装置，其中，所述装置还包括：
    第一建立模块，设置为在从网络运营商的日志中获取待监测的公交车上与所述网络运营商的基站通信的车载移动台的轨迹序列之前，根据待监控区域内的道路信息、行驶线路信息、基站分布信息建立交通线路分布图，并将所述待监控区域内的道路分割成一个或多个路段；
    第二建立模块，设置为建立所述待监控区域内各个路段到所述基站的映射；
    第五获取模块，设置为获取所述待监控区域内所述网络运营商的日志。
  14. 根据权利要求13所述的装置，其中，所述第一建立模块包括：
    第二获取单元，设置为获取待监控区域内的基站、行驶线路、道路的经纬度信息；
    第一建立单元，设置为以所述基站为分布点，所述行驶线路、道路为分布线，所述 基站的辐射范围为分布圆建立交通线路分布图；
    分割单元，设置为以所述分布圆与所述分布线的交点和所述行驶线路的交叉路口为分割点将所述分布线分割成多个路段。
  15. 根据权利要求13所述的装置，其中，所述第二建立模块包括：
    第一确定单元，设置为从所述交通线路分布图确定辐射所述各个路段的基站ID；
    第二建立单元，设置为建立按照行驶线路的轨迹在各个路段上分别连接的多个基站的映射。
  16. 根据权利要求15所述的装置，其中，所述第二建立单元还包括：
    第一建立子单元，设置为建立所述车载移动台ID与按照行驶线路的上行轨迹在各个路段上分别连接的多个基站的基站ID之间的第一对应关系；和/或
    第二建立子单元，设置为建立所述车载移动台ID与按照行驶线路的下行轨迹在各个路段上分别连接的多个基站的基站ID之间的第二对应关系。
  17. 根据权利要求12所述的装置，其中，所述第一确定模块包括：
    第一判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第一预定时间段内平均连接的基站的数量是否大于第一预设阈值；和/或，第二判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第二预定时间段内平均切换基站的次数是否大于第二预设阈值；
    第二确定单元，设置为在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
  18. 根据权利要求12所述的装置，其中，所述第一确定模块包括：
    第三判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第三预定时间段内在停车场内驻留的平均时间是否大于第三预设阈值，和/或，第四判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在每天的第四预定时间段内在停车场内驻留的平均次数是否大于第四预设阈值，和/或，第五判断单元，设置为判断所述日志中所记录的与所述网络运营商的基站通信的移动台在停车场内驻留的时间点是否在第五预定时间段内；
    第三确定单元，设置为在判断结果为是时，确定所述移动台为非手持移动台，并从所述日志中获取所述非手持移动台的非手持移动台序列。
PCT/CN2016/075255 2015-11-16 2016-03-01 交通状态的获取方法及装置 WO2017084221A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510790751.2A CN106710208A (zh) 2015-11-16 2015-11-16 交通状态的获取方法及装置
CN201510790751.2 2015-11-16

Publications (1)

Publication Number Publication Date
WO2017084221A1 true WO2017084221A1 (zh) 2017-05-26

Family

ID=58718062

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/075255 WO2017084221A1 (zh) 2015-11-16 2016-03-01 交通状态的获取方法及装置

Country Status (2)

Country Link
CN (1) CN106710208A (zh)
WO (1) WO2017084221A1 (zh)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110298531A (zh) * 2019-04-15 2019-10-01 同济大学 一种基于多元数据的电动车调度方法
CN111125552A (zh) * 2019-11-11 2020-05-08 北京金山安全软件有限公司 一种移动轨迹绘制方法、装置、电子设备及存储介质
CN111126807A (zh) * 2019-12-12 2020-05-08 浙江大华技术股份有限公司 行程切分方法和装置、存储介质及电子装置
CN112216387A (zh) * 2020-09-02 2021-01-12 成都大汇智联科技有限公司 基于云数据平台的复工复产管理方法及系统
CN112530166A (zh) * 2020-12-01 2021-03-19 江苏欣网视讯软件技术有限公司 基于信令数据与大数据分析识别公交出行上下车站点的方法与系统
CN113163361A (zh) * 2021-01-08 2021-07-23 中国联合网络通信集团有限公司 车辆信息处理方法、装置及服务器
CN113766430A (zh) * 2021-09-14 2021-12-07 广州瀚信通信科技股份有限公司 基于5g网络的城市轨道拥堵分析方法及装置
CN114724407A (zh) * 2022-03-25 2022-07-08 中电达通数据技术股份有限公司 一种道路拟合中基于多数据源的正确车道识别方法

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109309956B (zh) * 2017-07-28 2020-11-24 中国移动通信集团山西有限公司 位置定位方法、装置、设备和计算机可读存储介质
CN108320586A (zh) * 2018-04-04 2018-07-24 飞行家族（北京）科技有限公司 一种低空空域障碍物信息获取系统及方法
CN109660989B (zh) * 2019-01-04 2021-11-30 中国联合网络通信集团有限公司 定位方法、终端设备、位置业务平台及定位系统
CN110047277B (zh) * 2019-03-28 2021-05-18 华中科技大学 基于信令数据的城市道路交通拥堵排名方法及系统
CN110891293B (zh) * 2019-11-11 2022-09-16 南京邮电大学 一种基于车辆轨迹预测的多属性网络选择方法
CN111914955B (zh) * 2020-10-13 2021-01-15 上海世脉信息科技有限公司 一种基于gps轨迹数据的公共交通线路识别方法
CN113469109B (zh) * 2021-07-16 2022-09-13 阿波罗智联(北京)科技有限公司 交通灯识别结果处理方法、装置、路侧设备及云控平台
CN113920722B (zh) * 2021-09-23 2023-04-14 摩拜(北京)信息技术有限公司 路口通行状态获取方法、装置、电子设备及存储介质
CN114944058B (zh) * 2022-05-11 2023-06-23 福勤智能科技（昆山）有限公司 拥堵区域距离确定方法、装置、预警设备和存储介质
CN115762055B (zh) * 2023-01-05 2023-04-14 广东汇通信息科技股份有限公司 一种基于计算机视觉的公共场所踩踏预警方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012019246A1 (en) * 2010-08-13 2012-02-16 Seeker Wireless Pty Limited Systems, methods, and processor readable media for traffic flow measurement
CN102521984A (zh) * 2011-12-31 2012-06-27 北京世纪高通科技有限公司 获取道路实时交通信息的方法和装置
CN103778784A (zh) * 2013-12-31 2014-05-07 上海云砥信息科技有限公司 基于手机数据实时获取高速公路路段交通状态信息的方法
CN104978858A (zh) * 2015-06-15 2015-10-14 北京拓明科技有限公司 一种基于手机信令的高速公路实时路况监测方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6341255B1 (en) * 1999-09-27 2002-01-22 Decell, Inc. Apparatus and methods for providing route guidance to vehicles
CN101645202A (zh) * 2009-08-25 2010-02-10 任佳 基于移动定位技术的高速路网内车辆轨迹识别系统及方法
CN101794516B (zh) * 2009-12-25 2011-11-23 北京工业大学 基于手机信息的路段速度计算方法
CN102496280B (zh) * 2011-12-13 2014-04-23 北京航空航天大学 一种路况信息实时获取方法
CN103177562B (zh) * 2011-12-26 2015-07-29 中国移动通信集团公司 一种获取交通状态预测所需信息的方法及装置
CN103037507A (zh) * 2012-12-17 2013-04-10 浙江鸿程计算机系统有限公司 一种基于Cell-ID定位技术的地图匹配方法
CN103810851B (zh) * 2014-01-23 2015-10-21 广州地理研究所 一种基于手机定位的交通出行模式识别方法
CN104318765A (zh) * 2014-10-22 2015-01-28 浙江工业大学 基于智能手机的实时交通拥堵自动检测方法
CN104778836B (zh) * 2015-04-03 2017-03-29 中设设计集团股份有限公司 基于手机信令数据质量感知的高速公路交通状态识别方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012019246A1 (en) * 2010-08-13 2012-02-16 Seeker Wireless Pty Limited Systems, methods, and processor readable media for traffic flow measurement
CN102521984A (zh) * 2011-12-31 2012-06-27 北京世纪高通科技有限公司 获取道路实时交通信息的方法和装置
CN103778784A (zh) * 2013-12-31 2014-05-07 上海云砥信息科技有限公司 基于手机数据实时获取高速公路路段交通状态信息的方法
CN104978858A (zh) * 2015-06-15 2015-10-14 北京拓明科技有限公司 一种基于手机信令的高速公路实时路况监测方法

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110298531A (zh) * 2019-04-15 2019-10-01 同济大学 一种基于多元数据的电动车调度方法
CN111125552A (zh) * 2019-11-11 2020-05-08 北京金山安全软件有限公司 一种移动轨迹绘制方法、装置、电子设备及存储介质
CN111125552B (zh) * 2019-11-11 2024-02-13 北京金山安全软件有限公司 一种移动轨迹绘制方法、装置、电子设备及存储介质
CN111126807B (zh) * 2019-12-12 2023-10-10 浙江大华技术股份有限公司 行程切分方法和装置、存储介质及电子装置
CN111126807A (zh) * 2019-12-12 2020-05-08 浙江大华技术股份有限公司 行程切分方法和装置、存储介质及电子装置
CN112216387A (zh) * 2020-09-02 2021-01-12 成都大汇智联科技有限公司 基于云数据平台的复工复产管理方法及系统
CN112216387B (zh) * 2020-09-02 2024-04-09 成都大汇智联科技有限公司 基于云数据平台的复工复产管理方法及系统
CN112530166B (zh) * 2020-12-01 2021-11-05 江苏欣网视讯软件技术有限公司 基于信令数据与大数据分析识别公交出行上下车站点的方法与系统
CN112530166A (zh) * 2020-12-01 2021-03-19 江苏欣网视讯软件技术有限公司 基于信令数据与大数据分析识别公交出行上下车站点的方法与系统
CN113163361A (zh) * 2021-01-08 2021-07-23 中国联合网络通信集团有限公司 车辆信息处理方法、装置及服务器
CN113766430A (zh) * 2021-09-14 2021-12-07 广州瀚信通信科技股份有限公司 基于5g网络的城市轨道拥堵分析方法及装置
CN113766430B (zh) * 2021-09-14 2023-11-10 广州瀚信通信科技股份有限公司 基于5g网络的城市轨道拥堵分析方法及装置
CN114724407A (zh) * 2022-03-25 2022-07-08 中电达通数据技术股份有限公司 一种道路拟合中基于多数据源的正确车道识别方法
CN114724407B (zh) * 2022-03-25 2023-05-30 中电达通数据技术股份有限公司 一种道路拟合中基于多数据源的正确车道识别方法

Also Published As

Publication number Publication date
CN106710208A (zh) 2017-05-24

Similar Documents

Publication Publication Date Title
WO2017084221A1 (zh) 交通状态的获取方法及装置
CN106197458B (zh) 一种基于手机信令数据和导航路线数据的手机用户出行方式识别方法
CN104751631B (zh) 基于gps定位和模糊理论判断出行链交通方式的方法
US9564048B2 (en) Origin destination estimation based on vehicle trajectory data
CN108959466B (zh) 基于bcs-dbscan的出租车载客热点可视化方法及系统
CN108154698B (zh) 一种基于gps轨迹大数据的公交到离站精确时间计算方法
CN108415975B (zh) 基于bdch-dbscan的出租车载客热点识别方法
Autey et al. Safety evaluation of right-turn smart channels using automated traffic conflict analysis
CN105608505B (zh) 一种基于手机信令数据的居民轨道交通出行方式识别方法
WO2019007111A1 (zh) 一种公路异常事件的判断方法
CN106651027B (zh) 一种基于社交网络的互联网班车线路优化方法
CN105809962A (zh) 一种基于手机数据的交通出行方式划分的方法
CN111091720A (zh) 基于信令数据和浮动车数据的拥堵路段识别方法及装置
CN103325245A (zh) 一种黑名单车辆的时空行驶轨迹预测方法
CN113724489B (zh) 基于多源数据的交通拥堵溯源方法
CN108848460A (zh) 基于rfid和gps数据的人车关联方法
CN114363842B (zh) 基于手机信令数据的公交乘客下车站点预测方法及装置
CN107085944A (zh) 一种交通数据处理系统及方法
CN112036757A (zh) 基于手机信令和浮动车数据的停车换乘停车场的选址方法
CN109489679A (zh) 一种导航路径中的到达时间计算方法
CN115795332A (zh) 一种用户出行模式识别的方法
CN109166336B (zh) 一种基于区块链技术的实时路况信息采集推送方法
CN108269421A (zh) 基于视频感知的路内停车泊位实时检测方法、装置及系统
CN104978859A (zh) 一种计算城市任意区域公交线网密度的方法
TW201327458A (zh) 一種應用車輛探測資料之交通路網生成方法

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: 16865404

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16865404

Country of ref document: EP

Kind code of ref document: A1