CN106851586A - A kind of track traffic user identification method, apparatus and system - Google Patents
A kind of track traffic user identification method, apparatus and system Download PDFInfo
- Publication number
- CN106851586A CN106851586A CN201710044664.1A CN201710044664A CN106851586A CN 106851586 A CN106851586 A CN 106851586A CN 201710044664 A CN201710044664 A CN 201710044664A CN 106851586 A CN106851586 A CN 106851586A
- Authority
- CN
- China
- Prior art keywords
- record
- user
- event
- logout
- mobile type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a kind of track traffic user identification method, device and system, it is related to communication technical field, with more preferable implementation and wider array of applicability.Methods described includes：Obtain the mobile communication network side signaling plane full dose data of the user of target area；Using the record of whole mobile type events of the full dose data genaration user；The record of the motion class event in the record of whole mobile type events is extracted, and generates motion class logout group；The cluster feature of every record in the motion class logout group determines whether user is track traffic user.During track traffic user's identification.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of track traffic user identification method, apparatus and system.
Background technology
With the fast development of China's transportation industry, track traffic (including high ferro, subway, subway etc.) has become people
One of major way of trip.Because track traffic communication scenes become increasingly popular and become more and more important, therefore track is handed over
General family is identified having important value for the network optimization and customer analysis.
By taking the high-speed railway (hereinafter referred to as high ferro) in track traffic as an example, high ferro is covered by building a chain at present
The passenger of the communication network of circuit, i.e. high ferro private network (abbreviation private network) to ensure in high ferro has preferable communication experiences.And cover
Network outside high ferro region is referred to as public network.Current identification high ferro user mainly has following several method：The first, by user's end
The residence time in private network cell is held to judge whether user is high ferro user.Second, by user terminal when default
Interior location updating number of times determines whether user is high ferro user.The third, high-speed rail cell A mouthfuls and Abis mouthfuls of collection covering
Full dose signaling data；According to resident user storehouse along pre-building, matched from the full dose signaling data along the line often
In user；According to the actual drive test data of high-speed railway, the high ferro user in the user along described outside resident user is isolated
Low speed user along the line.
Present inventor has found that the analysis means that the above method one and two is used are analyzed for private network in actual applications
Means, and when high ferro user resides in public network, be difficult to determine whether the user is high ferro user by the analysis means of private network；
And in the second approach, for high ferro and the scene of high-speed parallel, high speed car user will move with high ferro users to share
Network, if their speed is similar, the message event type that it occurs is identical, and effective reality will be difficult to using location updating number of times
Existing high ferro user and the differentiation of periphery highspeed user；And for high ferro user's identification that the third is matched using measured data
Method to every circuit, it is necessary to survey, and actual measurement is often limited by quantities in advance, it is difficult to be tested comprehensively, and logical
Often test can only gather a small amount of sample, and more recessive problems cannot expose, and consumption human cost is larger.
The content of the invention
The embodiment of the present invention provides a kind of track traffic user identification method, apparatus and system, with more preferable implementation
With wider array of applicability --- suitable for various network environments, while high ferro user can be not only recognized, in rails such as subway/subways
It is equally applicable in the identification of road traffic user.
To reach above-mentioned purpose, embodiments of the invention are adopted the following technical scheme that：
A kind of track traffic user identification method, including：
Obtain the mobile communication network side signaling plane full dose data of the user of target area；
Using the record of whole mobile type events of the full dose data genaration user；
The record of the motion class event in the record of whole mobile type events is extracted, and generates motion class event note
Record group；
The cluster feature of every record in the motion class logout group determines whether user is track traffic
User.
A kind of track traffic customer identification device, including：
Acquiring unit, the acquiring unit is used for the mobile communication network side signaling plane full dose of the user for obtaining target area
Data；
Generation unit, the generation unit is used for the whole of the full dose data genaration user obtained using the acquiring unit
The record of mobile type event；
Extraction unit, the extraction unit is used for the record of the whole mobile type events for extracting the generation unit generation
In motion class event record, and generate motion class logout group；
Determining unit, the determining unit is used for every in the motion class logout group generated according to the extraction unit
The cluster feature of bar record determines whether user is track traffic user.
A kind of track traffic user's identification system, including track traffic customer identification device as described above.
Track traffic user identification method, apparatus and system that the present invention is provided, obtain the movement of the user of target area
Communication network side signaling plane full dose data；Using the record of whole mobile type events of the full dose data genaration user；Carry
The record of the motion class event in the record of whole mobile type events is taken, and generates motion class logout group；According to
The cluster feature of every record in the motion class logout group determines whether user is track traffic user.This utilization
Cluster feature determine user whether be track traffic user mode, when track traffic user's identification is carried out, do not rely on rail
Private network/public network mark of the road traffic work parameter in, also not dependent on the speed threshold of track traffic, and need not be in advance right
Every rail line is surveyed, therefore with more preferable implementation；Various track traffic users can be recognized simultaneously, because
This also has wider array of applicability.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to that will use needed for embodiment description
Accompanying drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those of ordinary skill in the art, on the premise of not paying creative work, other can also be obtained according to these accompanying drawings
Accompanying drawing.
Fig. 1 is the flow chart of the kind track traffic user identification method of the embodiment of the present invention one；
Fig. 2 is another flow chart of the kind track traffic user identification method of the embodiment of the present invention one；
Fig. 3 is the another flow chart of the kind track traffic user identification method of the embodiment of the present invention one；
Fig. 4 is the another flow chart of the kind track traffic user identification method of the embodiment of the present invention one；
Fig. 5 is the another flow chart of the kind track traffic user identification method of the embodiment of the present invention one；
Fig. 6 is the flow chart of the kind track traffic user identification method of the embodiment of the present invention two；
Fig. 7 is the high ferro trip user for having cluster feature determined using track traffic user identification method of the invention
Temporal characteristics；
Fig. 8 is the trip user of the non-high ferro without cluster feature determined using track traffic user identification method of the invention
Temporal characteristics；
Fig. 9 is the structure chart of the kind track traffic customer identification device of the embodiment of the present invention three.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Embodiment one
As shown in figure 1, the embodiment of the present invention one provides a kind of track traffic user identification method, including：
S11, the mobile communication network side signaling plane full dose data of the user of acquisition target area.
Wherein, the target area can be rail line a certain section of region, such as in Beijing-Shanghai express railway circuit from
Beijing to this section of Nanjing region." the full dose data " are whole signaling plane numbers of gathered mobile communication network side interface
According to, including user and mobile communications network whole interaction messages.
The mobile communication network side signaling plane full dose data of user for example can be under 2G networks in the step A interfaces,
Gb Interface, C/D interfaces, Iu-CS (Circuit Switched Domain, the circuit commutative field) interface under 3G network, Iu-PS
(Packet Switched Domain, packet-switched domain) interface, C/D interfaces, gn interface, Gr interface, the S1- under 4G networks
MME (Mobility Management Entity, mobile management entity) interface, S6a interface etc. is obtained.
S12, using the full dose data genaration user whole mobile type events record.
Wherein, the full dose data include the interaction message of user and mobile communications network.
As shown in Fig. 2 in actual applications, this step may include：
Step S121, using the full dose data, interacting user and mobile communications network is associated by interface message
Message is associated, and generates the record of various types of events.
In a particular application, using the record of the interface message of the prior art association various types of events of generation.
For example, generating a record for event using about 10~40 interaction messages.
Step S122, from the record of various types of events extract user whole mobile type events note
Record.
Wherein, the mobile type event at least includes location updating class event, switching class event, may also include tracking area
Update event, Routing Area Update event, TMSI (transmission measuring set input, transmission measuring set input)
Distribution event, P-TMSI distribution event, relocation event etc..
ID USER-ID, event type EVENTTYPE comprising user in the record of the mobile type event
Old Location Area Identification LAI-OLD, thing before (comprising general position updating type, switching type etc.), event triggering where user
The time TIME that new position area mark LAI-NEW and event after part triggering where user occur.
The record of the motion class event in step S13, the record of extraction whole mobile type events, and generate motion
Class logout group.
As shown in figure 3, in actual applications, this step is specifically included：
Step S131, the time occurred according to event to the mobile type event under same user according to the ID
It is ranked up, generates mobile type sequence of events.
Wherein, in the mobile type sequence of events of generation each mobile type event is allocated a sequence number
SHIFT EVENT-ID。
Step S132, judge whether the record of each event in the mobile type sequence of events belongs to motion class one by one
Logout.
That is, this step needs to determine motion class event from mobile type event.And the motion in the application
Class event can determine according to following steps S132 specific steps.
Wherein, step S132 is specially：
Judge whether every record of each event meets first condition and second condition.
If the record of nth bar mobile type event meets first condition and second condition simultaneously, nth bar movement class is judged
Type event is recorded as one group of intermediate record of motion class logout.
If the record of nth bar mobile type event meets the first condition, the second condition is unsatisfactory for, then judges
The one group of termination of motion class logout that is recorded as of n bar mobile type events is recorded.
If the record of nth bar mobile type event meets the second condition, the first condition is unsatisfactory for, then judges
N bar mobile type events are recorded as one group of home record of motion class logout.
If the record of nth bar mobile type event had both been unsatisfactory for the first condition, the second condition is also unsatisfactory for, then
Judge that the record of nth bar mobile type event is not belonging to move class logout.
Wherein, the first condition is：For the record of nth bar mobile type event, in the first scheduled time T1 internal memory
It is not equal in the old Location Area Identification of (n-1)th record of mobile type event, and (n-1)th article of record of mobile type event
The new position area mark of the record of n bar mobile type events；The second condition is：For the note of nth bar mobile type event
, there is (n+1)th record of mobile type event, and (n+1)th mobile type event within first scheduled time T1 in record
Record new position area mark be not equal to nth bar mobile type event record old Location Area Identification.
In a particular application, the size that T1 can be planned according to Location Area Identification determine, for example, 20 minutes.
Wherein, above-mentioned home record, intermediate record and termination record belong to the record of motion class event, that is to say, that
In this application, it is referred to as moving class event with home record, intermediate record and the event for terminating recording.
Step S133, the record rejecting that will not belong to move class event, fortune is generated using the record for belonging to motion class event
Dynamic class logout group.
That is the record that being not belonging in the record of whole mobile type events moves class event is rejected, will be remaining
The record packet for belonging to motion class event, each group of record of motion class event all include above-described home record, in
Between record and terminate record.
S14, every cluster feature for recording in the motion class logout group determine whether user is track
Traffic user.
As shown in figure 4, in actual applications, this step may include：
S141, the every associated user of record determined in each group of motion class logout, and count the related use
The quantity at family.
Specifically, for every record in each group of motion class logout, statistics is pre- in every record front and rear second
Fix time in T2 and this record identical record, registration records the ID that identical records owning user with this, with
Determine the associated user of this record, and generate associated user's group.Afterwards, count associated user's in associated user's group
Quantity.
Wherein, the second scheduled time T2 can be set according to the speed of track vehicle and position area scope, example
Such as it is 3 minutes.
Wherein, if after old Location Area Identification, event before two event types of record, event triggerings where user are triggered
New position area mark where user, event success or not are all identical, then this two are recorded as identical record.That is,
The user with identical recordings is referred to as " associated user " in the application, each associated user has for identifying correlation use
The relevent users' identities M-USER-X at family, associated user's sequence number M-USER-ID, associated user cluster mark M-USER-TAG, and
And each associated user's composition associated user's group of record.
S142, the N articles quantity of the associated user of record in M groups move class logout are less than predetermined number
When, it is unusual record by the N articles recording mark；The N articles number of the associated user of record in M groups motion class logout
It is nonsingular record by the N articles recording mark when amount is more than or equal to the predetermined number.
Wherein, the predetermined number can be set as needed, for example, institute in one group of motion class logout of user
Have the 20% of associated user's average of record.
Wherein, the unusual record is, for example, that, when the radio-frequency module of user terminal breaks down, original this switches
When do not occur so that the interaction time with network is postponed；Or due to network interface congestion, the event time of record
Inconsistent with the event that should occur in logic, the record in the case of these is unusual record.
S143, the cluster record determined in all of nonsingular record.
As shown in figure 5, in actual applications, this step may include：
S1431, it is all of it is nonsingular record, determine every in every group of motion class logout all phases of record
User is closed, and counts the frequency that each associated user occurs in all records.
Wherein, in the application, the frequency that each associated user occurs in all nonsingular records refers to every record
In the ratio that occurs in all nonsingular records of each associated user.
S1432, when the frequency that associated user m occurs in all nonsingular records be more than or equal to preset value when, by phase
Close user m and be labeled as cluster user.Now,<M-USER-TAG>Put 1.
Wherein, the preset value can be set according to actual conditions, and such as 80%.
If for example, the preset value is set into 80%, and 10 nonsingular records are had, for the 5th article of nonsingular record
In associated user M-USER-1 (being equal to the m in step S432), if occurring in 9 in this 10 nonsingular records
Associated user M-USER-1, the then frequency 90% (9/10) that associated user M-USER-1 occurs in all nonsingular records is more than
Preset value 80%, now, cluster user is labeled as by associated user M-USER-1.
S1433, every ratio of the cluster user recorded of statistics.
Because every record has its associated user's group, therefore, the ratio of every cluster user recorded is referred to often
Cluster user in associated user's group that bar is recorded accounts for the ratio of all users in associated user's group.
If for example, having 10 associated users in the 3rd article of associated user's group of record, wherein cluster user has 8, then the
The ratio of 3 cluster users recorded is 80% (8/10).
If the ratio of the cluster user under S1434, record K is more than or equal to the first default ratio, by record K labeled as poly-
Class is recorded.
Wherein, the described first default ratio can be set according to actual conditions, and such as 70%.
Continue by taking the example in step S1433 as an example, now, the K in step S1434 is 3, due to its cluster user
Ratio is 80%, if default than being set to 70% by first, the 3rd article of record can be recorded labeled as cluster.
The quantity of S144, the unusual record in the motion class logout group under each user and cluster record is true
Determine whether user is track traffic user.
In actual applications, this step specifically may include：
When the unusual record in a motion class logout group of user accounts for the summary journal of the motion class logout group
Ratio ratio default less than second, and cluster record in the motion class logout group account for nonsingular record ratio be more than or
It is default equal to the 3rd than when, determine that user is track traffic user.
Wherein, the described second default ratio, the 3rd default ratio can be set as the case may be, and the such as second default ratio can
7% is set to, the 3rd default ratio can be set to 80%.
Further, so that track traffic is as high ferro as an example, (e.g. capital when it is determined which section high ferro user user is specifically
Shanghai high ferro user or Beijing-Harbin high ferro user), if the riding information according to user determines that a certain user is on November 21
The Beijing-Shanghai express railway user that noon gets on the bus, and user is determined for high ferro user (taking high ferro) according to the scheme of the application,
And the motion class event type and the restrictive condition such as position area and time of the user are consistent with the riding information of user, then can confirm
The user is the Beijing-Shanghai express railway user that morning November 21 gets on the bus, rather than Beijing-Harbin high ferro user.
Therefore, the track traffic user identification method of the embodiment of the present invention one determines that user is using cluster feature
No is track traffic user, when track traffic user's identification is carried out, does not rely on private network/public affairs of the track traffic work parameter in
Network mark is known, and also not dependent on the speed threshold of track traffic, and every rail line need not be surveyed in advance,
Therefore there is more preferable implementation；Various track traffic users can be recognized simultaneously, therefore also there is wider array of applicability.
Embodiment two
Below by taking the high ferro in track traffic as an example, by embodiment two to the track traffic user identification method of the application
It is described in detail.
As shown in fig. 6, the track traffic user identification method of the embodiment of the present invention two includes：
S21, the signaling plane full dose data for gathering user from network side according to the network coverage mode in target high ferro region.
Wherein, the full dose data include the interaction message of user and mobile communications network.
With WCDMA (Wideband Code Division Multiple Access, broad band CDMA mobile communication system
System) as a example by 3G network coverage mode, Iu-CS interface message can be gathered by network side equipment end or interface end, the interface disappear
Comprising the full dose signaling data needed for the application in breath.Depending on acquisition time is according to analysis demand.
It should be noted that the present invention is in addition to for 3G network, it may also be used for 2G networks, LTE (Long Term
Evolution, Long Term Evolution) in/EPC (Evolved Packet Core, evolution block core net) network.
S22, by interface message associate by user associated with the interaction message of mobile communications network generate it is various types of
Event, and therefrom extract the event of mobile type.The event of the mobile type includes location updating class event, switching class thing
Part, tracking go to update class event, relocation event etc..
S23, relevant field is extracted from the interaction message of user and mobile communications network, generate database file table.
Wherein, the relevant field structure is as shown in table 1.
Table 1
S24, with user be index in chronological order to the record ordering of all of mobile type event of user, and fill extremely
<SHIFT EVENT-ID>。
S25, determine every record<MOVEMENT-TAG>With<MOVEMENT-ID>.
Wherein,<MOVEMENT-TAG>With<MOVEMENT-ID>For characterizing whether a record is motion class event note
Record.
It may be noted that " the motion class logout group " under each motion class event has one group of home record, centre
Record and terminate record, and same group of home record, intermediate record and terminate record<MOVEMENT-ID>All it is identical,
Every record for belonging to same record group has identical<MOVEMENT-ID>.Wherein, home record, intermediate record and end
The judgement for only recording can refer to the description in the step S132 of embodiment one, will not be repeated here.
In actual applications, when it is determined that one be recorded as one group of intermediate record of motion class logout, terminate record or
Home record, or when determining that the record is not belonging to motion class logout, can be by the record identification of the motion class event in table 1
<MOVEMENT-TAG>It is set to corresponding value.
For example, for nth bar record, if nth bar is recorded as one group of intermediate record of motion class logout, its motion
The record identification of class event<MOVEMENT-TAG>=1；If nth bar is recorded as one group of termination record of motion class logout,
The record identification that then it moves class event<MOVEMENT-TAG>=2；If nth bar is recorded as rising for one group of motion class logout
Begin record, then the record identification of its motion class event<MOVEMENT-TAG>=3；If nth bar record is not belonging to move class event
Record, the then record identification that it moves class event<MOVEMENT-TAG>=0.
It is determined that every record<MOVEMENT-TAG>Afterwards, can be according to it<MOVEMENT-TAG>Determine that this records
's<MOVEMENT-ID>.
Specifically, can be according to<SHIFT EVENT-ID>Order traveled through, for example, connect example, if initially<
MOVEMENT-ID>=0, when<MOVEMENT-TAG>When=3, show that this is recorded as one group of starting of motion class logout
Record, then this records<MOVEMENT-ID>For upper one be not 0<MOVEMENT-ID>Value Jia 1；When<MOVEMENT-
TAG>When=1, show that this is recorded as one group of intermediate record of motion class logout, then this records<MOVEMENT-ID
>It is the record of previous bar<MOVEMENT-ID>Value；When<MOVEMENT-TAG>When=2, show that this is recorded as one group of motion
The termination of class logout is recorded, then this records<MOVEMENT-ID>It is the record of previous bar<MOVEMENT-ID>
Value；When<MOVEMENT-TAG>When=0, show that this record is not belonging to move class logout, then this records<
MOVEMENT-ID>=0.
Wherein, if same<MOVEMENT-ID>Under record number be less than N1, then this is recorded all of<
MOVEMENT-ID>Set to 0, remove short record.
N1 can be set according to the length of target area, for example, be set to 5.
If for example, user have a motion recording group include 5 record, if N1=6, then show the movement locus of user
Less, then this group of motion recording does not possess reference value, therefore using this motion recording group as short record treatment, by under it
The MOVEMENT-ID of all records>Set to 0.
S26, judge every record<MOVEMENT-TAG>With<MOVEMENT-ID>Whether it is not 0.
Recorded when one<MOVEMENT-ID>With<MOVEMENT-TAG>When being not 0, it is determined that this is recorded as moving class
Logout, the event with the record is motion class event.Now, step S27 is performed, the record is otherwise rejected.
S27, determine each motion class logout group in every record whether be unusual record.
This step can refer to the description in the step S141 of embodiment one, will not be repeated here.
When unusual record is recorded as one, it is unusual event that surface has the event of the record, now will<ODD-
EVENT>Put 1；Otherwise this is recorded as nonsingular record, now will<ODD-EVENT>Set to 0, and perform step S28.
S28, determine it is all it is nonsingular record clusters record.
When it is determined that one be recorded as cluster record when, that is, determine with this record event be cluster event, now will<
GT-EVENT>Put 1.
S29, according to all records under a certain motion class logout group of user<ODD-EVENT>With<GT-EVENT>Mark
Note situation judges whether the motion recording is high ferro record.
Wherein, the specific implementation of step S27-S29 can refer to the description in embodiment one, will not be repeated here.
When it is determined that a certain user is high ferro user, can be by<GT-TAG>Put 1.
Fig. 7 and Fig. 8 are shown respectively the temporal characteristics of the high ferro trip user of cluster feature and without the non-of cluster feature
The temporal characteristics of high ferro trip user.
Therefore, the track traffic user identification method that the embodiment of the present invention two is provided determines user using cluster feature
Whether be track traffic user, when track traffic user's identification is carried out, do not rely on track traffic work parameter according in private network/
Public network is identified, and also not dependent on the speed threshold of track traffic, and need not carry out reality to every rail line in advance
Survey, therefore with more preferable implementation.Simultaneously, although example of the embodiment two with high ferro as track traffic is illustrated, but,
Various other track traffic users can also be recognized using track traffic user identification method of the invention, therefore is also had more
Wide applicability.
Embodiment three
As shown in figure 9, the embodiment of the present invention three provides a kind of track traffic customer identification device 30, including：Obtain single
Unit 31, the acquiring unit 31 is used for the mobile communication network side signaling plane full dose data of the user for obtaining target area；Generation
Unit 32, the generation unit 32 is used for the mobile class of whole of the full dose data genaration user obtained using the acquiring unit 31
The record of type event；Extraction unit 33, the extraction unit 33 is used to extract the mobile class of whole of the generation of the generation unit 32
The record of the motion associated class event in the record of type event, and generate motion class logout group；Determining unit 34, it is described true
Order unit determines for every cluster feature of record in the motion class logout group according to the generation of the extraction unit 33
Whether user is track traffic user.
Wherein, the full dose data that the acquiring unit 31 is obtained include the interaction message of user and mobile communications network, institute
Stating generation unit 32 includes：First generation subelement, the first generation subelement is used to utilize the full dose data, by connecing
With the interaction message of mobile communications network be associated user by mouth message relating, generates the record of various types of events；Carry
Subelement is taken, the extraction subelement is used to be carried from the record of various types of events of the described first generation subelement generation
The record of whole mobile type events at family is taken, the mobile type event at least includes location updating class event, switching class
Event.
Wherein, ID, event comprising user in the record of the mobile type event of the generation of the generation unit 32
New position area mark and thing after old Location Area Identification, event triggering before type, event triggering where user where user
The time that part occurs.The extraction unit 33 includes：Second generation subelement, the second generation subelement is used for according to described
ID is ranked up to the mobile type event under same user according to the time that event occurs, and generates mobile type event
Sequence；Judgment sub-unit, the judgment sub-unit is used to judge one by one the mobile type thing of the second generation subelement generation
Whether every record of each event in part sequence belongs to motion class logout；3rd generation subelement, the three lives
It is used to reject the record for being not belonging to move class event that the judgment sub-unit determines into subelement, class thing is moved using belonging to
The record generation motion class logout group of part.
In actual applications, the judgment sub-unit specifically for：Judge whether every of each event record meets the
One condition and second condition；If the record of nth bar mobile type event meets first condition and second condition simultaneously, is judged
N bar mobile type events are recorded as one group of intermediate record of motion class logout；If the record of nth bar mobile type event
Meet the first condition, be unsatisfactory for the second condition, then judge nth bar mobile type event is recorded as one group of motion class
The termination record of logout；If the record of nth bar mobile type event meets the second condition, described first is unsatisfactory for
Part, then judge nth bar mobile type event is recorded as one group of home record of motion class logout；If nth bar moves class
The record of type event had both been unsatisfactory for the first condition, was also unsatisfactory for the second condition, then judge nth bar mobile type event
Record be not belonging to move class logout.Wherein, the first condition is：For the record of nth bar mobile type event,
There is (n-1)th record of mobile type event, and (n-1)th old position of the record of mobile type event in first scheduled time
Put the new position area mark that area's mark is not equal to the record of nth bar mobile type event；The second condition is：For nth bar
, there is (n+1)th record of mobile type event, and (n+1)th within first scheduled time in the record of mobile type event
The new position area mark of the record of bar mobile type event is not equal to the old position area mark of the record of nth bar mobile type event
Know.
Wherein, the determining unit 34 includes：It is determined that and statistics subelement, the determination and statistics subelement be used for determine
Every associated user of record in each group of motion class logout, and count the quantity of the associated user；Mark is single
Unit, the N articles quantity of the associated user of record that the mark subelement is used in M groups motion class logout is less than pre-
If being unusual record by the N articles recording mark during quantity；The related of the N articles record in M groups motion class logout is used
It is nonsingular record by the N articles recording mark when the quantity at family is more than or equal to the predetermined number；First determination subelement,
The cluster record that first determination subelement is used to determine in all of nonsingular record；Second determination subelement, described
Unusual record and the number of cluster record that two determination subelements are used in the motion class logout group under each user
Amount determines whether user is track traffic user.
In actual applications, it is described determination and statistics subelement specifically for：For in each group of motion class logout
Every record, statistics before and after every record in second scheduled time with this record identical record, registration and this note
Record identical records the ID of owning user, to determine the associated user that this records, and generates associated user's group；Statistics
The quantity of the associated user in associated user's group.Wherein, if before two event types of record, event triggerings where user
Old Location Area Identification, event triggering after new position area mark where user, event success or not it is all identical, then this two notes
Record as identical is recorded.
In actual applications, first determination subelement specifically for：It is all of it is nonsingular record, determine every group
Every all associated users of record in motion class logout, and count each associated user in all nonsingular records
The frequency of appearance；When the frequency that associated user m occurs in all nonsingular records is more than or equal to preset value, correlation is used
Family m is labeled as cluster user；Every ratio of the cluster user recorded of statistics；If the ratio of the cluster user under record K is big
In or equal to the first default ratio, then record K is recorded labeled as cluster.
In actual applications, second determination subelement specifically for：When in a motion class logout group of user
The unusual record summary journal that accounts for the motion class logout group ratio ratio default less than second, and the motion class event remembers
Cluster record in record group account for the ratio of nonsingular record it is default more than or equal to the 3rd than when, determine that user is that track traffic is used
Family.
The operation principle of said apparatus 30 can refer to the description in preceding method embodiment one and two, will not be repeated here.
Therefore, the track traffic customer identification device of the embodiment of the present invention two determines that user is using cluster feature
No is track traffic user, when track traffic user's identification is carried out, does not rely on private network/public affairs of the track traffic work parameter in
Network mark is known, and also not dependent on the speed threshold of track traffic, and every rail line need not be surveyed in advance,
Therefore there is more preferable implementation；Various track traffic users can be recognized simultaneously, therefore also there is wider array of applicability.
Additionally, the embodiment of the present invention additionally provides a kind of track traffic user's identification system, the system includes as described above
Track traffic customer identification device 30.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the part with other embodiment.Especially for device embodiment
For, because it is substantially similar to embodiment of the method, so describe fairly simple, referring to the portion of embodiment of the method in place of correlation
Defend oneself bright.
It should be noted that, device embodiment described above is only schematical, wherein being illustrated as separating component
Unit can be or may not be physically separate, the part shown as unit can be or may not be
Physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can be according to the actual needs
Some or all of module therein is selected to realize the purpose of this embodiment scheme.In addition, the device that the present invention is provided is implemented
In example accompanying drawing, the annexation between module represents between them there is communication connection, specifically can be implemented as one or more
Communication bus or holding wire.Those of ordinary skill in the art are without creative efforts, you can simultaneously real to understand
Apply.
The above, specific embodiment only of the invention, but protection scope of the present invention is not limited thereto, and it is any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all contain
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (17)
1. a kind of track traffic user identification method, it is characterised in that including：
Obtain the mobile communication network side signaling plane full dose data of the user of target area；
Using the record of whole mobile type events of the full dose data genaration user；
The record of the motion class event in the record of whole mobile type events is extracted, and generates motion class logout
Group；
The cluster feature of every record in the motion class logout group determines whether user is track traffic user.
2. track traffic user identification method according to claim 1, it is characterised in that the full dose data include user
With the interaction message of mobile communications network, the record of the whole mobile type events using the full dose data genaration user
Including：
Using the full dose data, associated by interface message and user be associated with the interaction message of mobile communications network,
Generate the record of various types of events；
The record of whole mobile type events of user, the mobile type are extracted from the record of various types of events
Event at least includes location updating class event, switching class event.
3. track traffic user identification method according to claim 1 and 2, it is characterised in that the mobile type event
Record in comprising old Location Area Identification, the event triggering where user before the ID of user, event type, event triggering
The time that the new position area mark and event where user occur afterwards, the fortune in extraction whole mobile type events
The record of dynamic class event, generation motion class logout group includes：
The mobile type event under same user is ranked up according to the time that event occurs according to the ID, is generated
Mobile type sequence of events；
Judge whether the record of each event in the mobile type sequence of events belongs to motion class logout one by one；
The record that will not belong to move class event is rejected, using the record generation motion class logout for belonging to motion class event
Group.
4. track traffic user identification method according to claim 3, it is characterised in that described to judge the movement one by one
Whether the record of each event in types of events sequence belongs to motion class logout is specially：
Judge whether every record of each event meets first condition and second condition；
If the record of nth bar mobile type event meets first condition and second condition simultaneously, nth bar mobile type thing is judged
Part is recorded as one group of intermediate record of motion class logout；
If the record of nth bar mobile type event meets the first condition, the second condition is unsatisfactory for, then judges nth bar
The one group of termination of motion class logout that is recorded as of mobile type event is recorded；
If the record of nth bar mobile type event meets the second condition, the first condition is unsatisfactory for, then judges nth bar
Mobile type event is recorded as one group of home record of motion class logout；
If the record of nth bar mobile type event had both been unsatisfactory for the first condition, the second condition is also unsatisfactory for, then judged
The record of nth bar mobile type event is not belonging to move class logout；
Wherein, the first condition is：For the record of nth bar mobile type event, there is (n-1)th within first scheduled time
The record of bar mobile type event, and the old Location Area Identification of (n-1)th record of mobile type event is not equal to nth bar movement
The new position area mark of the record of types of events；The second condition is：For the record of nth bar mobile type event, in institute
State in first scheduled time and there is (n+1)th record of mobile type event, and (n+1)th record of mobile type event is new
Location Area Identification is not equal to the old Location Area Identification of the record of nth bar mobile type event.
5. track traffic user identification method according to claim 1 and 2, it is characterised in that described according to the motion
The cluster feature of every record in class logout group determines whether user is that track traffic user includes：
Determine every associated user of record in each group of motion class logout, and count the quantity of the associated user；
When the N articles quantity of the associated user of record in M groups motion class logout is less than predetermined number, by the N articles
Recording mark is unusual record；When the N articles quantity of the associated user of record in M groups motion class logout is more than or waits
It is nonsingular record by the N articles recording mark when the predetermined number；
Determine the cluster record in all of nonsingular record；
The quantity of unusual record and cluster record in the motion class logout group under each user determines that user is
No is track traffic user.
6. track traffic user identification method according to claim 5, it is characterised in that each group of motion class of the determination
Every in the logout associated user of record, and count the quantity of the associated user and be specially：
Recorded for every in each group of motion class logout, statistics is within second scheduled time before and after every record and is somebody's turn to do
Bar record identical record, registration records the ID of owning user with this record identical, to determine what this recorded
Associated user, and generate associated user's group；
Count the quantity of the associated user in associated user's group；
Wherein, if user after old Location Area Identification, event triggering before two event types of record, events triggerings where users
The new position area mark at place, event success or not are all identical, then this two are recorded as identical record.
7. track traffic user identification method according to claim 5, it is characterised in that the determination is all of nonsingular
Cluster record in record includes：
It is all of it is nonsingular record, determine every in every group of motion class logout all associated users of record, and
Count the frequency that each associated user occurs in all nonsingular records；
When the frequency that associated user m occurs in all nonsingular records is more than or equal to preset value, by associated user m marks
It is cluster user；
Every ratio of the cluster user recorded of statistics；
If the ratio of the cluster user under record K ratio default more than or equal to first, record K is recorded labeled as cluster.
8. track traffic user identification method according to claim 5, it is characterised in that described according under each user
Each motion class logout group in unusual record and cluster record quantity determine whether user is track traffic user
Specifically include：
When the unusual record in a motion class logout group of user accounts for the ratio of the summary journal of the motion class logout group
Ratio default less than second, and cluster record in the motion class logout group accounts for the ratio of nonsingular record and is more than or equal to
3rd it is default than when, determine that user is track traffic user.
9. a kind of track traffic customer identification device, it is characterised in that including：
Acquiring unit, the acquiring unit is used for the mobile communication network side signaling plane full dose number of the user for obtaining target area
According to；
Generation unit, the whole that the generation unit is used for the full dose data genaration user obtained using the acquiring unit is mobile
The record of types of events；
Extraction unit, the extraction unit is used in the record of the whole mobile type events for extracting the generation unit generation
The record of class event is moved, and generates motion class logout group；
Determining unit, every note that the determining unit is used in the motion class logout group generated according to the extraction unit
The cluster feature of record determines whether user is track traffic user.
10. track traffic customer identification device according to claim 9, it is characterised in that what the acquiring unit was obtained
Full dose data include the interaction message of user and mobile communications network, and the generation unit includes：
First generation subelement, the first generation subelement is used to utilize the full dose data, and being associated by interface message will
User is associated with the interaction message of mobile communications network, generates the record of various types of events；
Subelement is extracted, the extraction subelement is used for the note of the various types of events from the described first generation subelement generation
In record extract user whole mobile type events record, the mobile type event at least include location updating class event,
Switching class event.
The 11. track traffic customer identification device according to claim 9 or 10, it is characterised in that the generation unit life
Into mobile type event record in comprising the old position where user before the ID of user, event type, event triggering
The time that new position area mark and event after area's mark, event are triggered where user occur is put, the extraction unit includes：
Second generation subelement, it is described second generation subelement be used for according to the ID to same user under mobile class
Type event is ranked up according to the time that event occurs, and generates mobile type sequence of events；
Judgment sub-unit, the judgment sub-unit is used to judge one by one the mobile type event of the second generation subelement generation
Whether every record of each event in sequence belongs to motion class logout；
3rd generation subelement, the 3rd generation subelement is used to be not belonging to motion class thing by what the judgment sub-unit determined
The record of part is rejected, using the record generation motion class logout group for belonging to motion class event.
12. track traffic customer identification devices according to claim 11, it is characterised in that the judgment sub-unit is specific
For：
Judge whether every record of each event meets first condition and second condition；
If the record of nth bar mobile type event meets first condition and second condition simultaneously, nth bar mobile type thing is judged
Part is recorded as one group of intermediate record of motion class logout；
If the record of nth bar mobile type event meets the first condition, the second condition is unsatisfactory for, then judges nth bar
The one group of termination of motion class logout that is recorded as of mobile type event is recorded；
If the record of nth bar mobile type event meets the second condition, the first condition is unsatisfactory for, then judges nth bar
Mobile type event is recorded as one group of home record of motion class logout；
If the record of nth bar mobile type event had both been unsatisfactory for the first condition, the second condition is also unsatisfactory for, then judged
The record of nth bar mobile type event is not belonging to move class logout；
Wherein, the first condition is：For the record of nth bar mobile type event, there is (n-1)th within first scheduled time
The record of bar mobile type event, and the old Location Area Identification of (n-1)th record of mobile type event is not equal to nth bar movement
The new position area mark of the record of types of events；The second condition is：For the record of nth bar mobile type event, in institute
State in first scheduled time and there is (n+1)th record of mobile type event, and (n+1)th record of mobile type event is new
Location Area Identification is not equal to the old Location Area Identification of the record of nth bar mobile type event.
The 13. track traffic customer identification device according to claim 9 or 10, it is characterised in that the determining unit bag
Include：
It is determined that and statistics subelement, the determination and statistics subelement are used for determine in each group of motion class logout every
The associated user of record, and count the quantity of the associated user；
Mark subelement, the N articles associated user of record that the mark subelement is used in M groups motion class logout
Quantity be less than predetermined number when, by the N articles recording mark be unusual record；The N articles in M groups motion class logout
It is nonsingular record by the N articles recording mark when the quantity of the associated user of record is more than or equal to the predetermined number；
First determination subelement, the cluster record that first determination subelement is used to determine in all of nonsingular record；
Second determination subelement, second determination subelement is used for according in the motion class logout group under each user
Unusual record and cluster record quantity determine whether user is track traffic user.
14. track traffic customer identification devices according to claim 13, it is characterised in that the determination and statistics are single
Unit specifically for：
Recorded for every in each group of motion class logout, statistics is within second scheduled time before and after every record and is somebody's turn to do
Bar record identical record, registration records the ID of owning user with this record identical, to determine what this recorded
Associated user, and generate associated user's group；
Count the quantity of the associated user in associated user's group；
Wherein, if user after old Location Area Identification, event triggering before two event types of record, events triggerings where users
The new position area mark at place, event success or not are all identical, then this two are recorded as identical record.
15. track traffic customer identification devices according to claim 13, it is characterised in that first determination subelement
Specifically for：
It is all of it is nonsingular record, determine every in every group of motion class logout all associated users of record, and
Count the frequency that each associated user occurs in all nonsingular records；
When the frequency that associated user m occurs in all nonsingular records is more than or equal to preset value, by associated user m marks
It is cluster user；
Every ratio of the cluster user recorded of statistics；
If the ratio of the cluster user under record K ratio default more than or equal to first, record K is recorded labeled as cluster.
16. track traffic customer identification devices according to claim 13, it is characterised in that second determination subelement
Specifically for：
When the unusual record in a motion class logout group of user accounts for the ratio of the summary journal of the motion class logout group
Ratio default less than second, and cluster record in the motion class logout group accounts for the ratio of nonsingular record and is more than or equal to
3rd it is default than when, determine that user is track traffic user.
17. a kind of track traffic user's identification systems, it is characterised in that the system includes that claim 9-16 is any described
Track traffic customer identification device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710044664.1A CN106851586B (en) | 2017-01-19 | 2017-01-19 | A kind of rail traffic user identification method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710044664.1A CN106851586B (en) | 2017-01-19 | 2017-01-19 | A kind of rail traffic user identification method, apparatus and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106851586A true CN106851586A (en) | 2017-06-13 |
| CN106851586B CN106851586B (en) | 2019-08-09 |
Family
ID=59119439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710044664.1A Active CN106851586B (en) | 2017-01-19 | 2017-01-19 | A kind of rail traffic user identification method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106851586B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510203A (en) * | 2018-04-09 | 2018-09-07 | 智慧足迹数据科技有限公司 | Track vehicle user determines method, system and electronic equipment |
| CN108769951A (en) * | 2018-04-18 | 2018-11-06 | 西安汇龙科技股份有限公司 | Identify the method and system of non-high ferro user in 4G high ferro private networks |
| CN109246590A (en) * | 2017-06-15 | 2019-01-18 | 上海大唐移动通信设备有限公司 | A kind of rail traffic user identification method and device |
| CN109996299A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团河北有限公司 | High-speed rail user identification method, device, equipment and medium |
| WO2020119428A1 (en) * | 2018-12-12 | 2020-06-18 | 中兴通讯股份有限公司 | User identification method and apparatus, device and computer readable storage medium |
| CN115022810A (en) * | 2021-03-05 | 2022-09-06 | 中国移动通信集团江苏有限公司 | Method and device for identifying travel mode based on mobile phone signaling data and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102869037A (en) * | 2012-08-16 | 2013-01-09 | 北京拓明科技有限公司 | High-speed railway user separation method based on signaling data of A interface and Abis interface |
| CN102932864A (en) * | 2011-08-09 | 2013-02-13 | 鼎桥通信技术有限公司 | Method for determining running direction of high-speed train and network-side equipment |
| CN103841585A (en) * | 2014-03-27 | 2014-06-04 | 中国联合网络通信集团有限公司 | Method and device for distinguishing high speed railway users |
| CN103841576A (en) * | 2012-11-20 | 2014-06-04 | 中国移动通信集团浙江有限公司 | High speed railway user separation method and system and signaling data processing method and system |
| CN105636104A (en) * | 2014-10-27 | 2016-06-01 | 北京市天元网络技术股份有限公司 | Method and system of high-speed mobile user conversation identification in mobile communication network |
| CN106131865A (en) * | 2016-07-19 | 2016-11-16 | 浪潮软件集团有限公司 | Network quality analysis method based on high-speed rail line |
-
2017
- 2017-01-19 CN CN201710044664.1A patent/CN106851586B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102932864A (en) * | 2011-08-09 | 2013-02-13 | 鼎桥通信技术有限公司 | Method for determining running direction of high-speed train and network-side equipment |
| CN102869037A (en) * | 2012-08-16 | 2013-01-09 | 北京拓明科技有限公司 | High-speed railway user separation method based on signaling data of A interface and Abis interface |
| CN103841576A (en) * | 2012-11-20 | 2014-06-04 | 中国移动通信集团浙江有限公司 | High speed railway user separation method and system and signaling data processing method and system |
| CN103841585A (en) * | 2014-03-27 | 2014-06-04 | 中国联合网络通信集团有限公司 | Method and device for distinguishing high speed railway users |
| CN105636104A (en) * | 2014-10-27 | 2016-06-01 | 北京市天元网络技术股份有限公司 | Method and system of high-speed mobile user conversation identification in mobile communication network |
| CN106131865A (en) * | 2016-07-19 | 2016-11-16 | 浪潮软件集团有限公司 | Network quality analysis method based on high-speed rail line |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109246590A (en) * | 2017-06-15 | 2019-01-18 | 上海大唐移动通信设备有限公司 | A kind of rail traffic user identification method and device |
| CN109246590B (en) * | 2017-06-15 | 2020-12-04 | 上海大唐移动通信设备有限公司 | Rail transit user identification method and device |
| CN109996299A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团河北有限公司 | High-speed rail user identification method, device, equipment and medium |
| CN109996299B (en) * | 2017-12-30 | 2021-08-24 | 中国移动通信集团河北有限公司 | High-speed rail user identification method, device, equipment and medium |
| CN108510203A (en) * | 2018-04-09 | 2018-09-07 | 智慧足迹数据科技有限公司 | Track vehicle user determines method, system and electronic equipment |
| CN108769951A (en) * | 2018-04-18 | 2018-11-06 | 西安汇龙科技股份有限公司 | Identify the method and system of non-high ferro user in 4G high ferro private networks |
| WO2020119428A1 (en) * | 2018-12-12 | 2020-06-18 | 中兴通讯股份有限公司 | User identification method and apparatus, device and computer readable storage medium |
| CN111314947A (en) * | 2018-12-12 | 2020-06-19 | 中兴通讯股份有限公司 | User identification method, device, equipment and computer readable storage medium |
| CN111314947B (en) * | 2018-12-12 | 2022-12-09 | 中兴通讯股份有限公司 | User identification method, device, equipment and computer readable storage medium |
| CN115022810A (en) * | 2021-03-05 | 2022-09-06 | 中国移动通信集团江苏有限公司 | Method and device for identifying travel mode based on mobile phone signaling data and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106851586B (en) | 2019-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106851586A (en) | A kind of track traffic user identification method, apparatus and system | |
| CN102869037B (en) | High-speed railway user separation method based on signaling data of A interface and Abis interface | |
| CN110113718A (en) | A kind of railway traffic hinge type of population recognition methods based on mobile phone signaling data | |
| CN108156626A (en) | Rail traffic quality of wireless network appraisal procedure, device and medium | |
| DE60017474T2 (en) | TRAFFIC MONITORING | |
| CN106354797B (en) | Data recommendation method and device | |
| CN106878946A (en) | High ferro user identification method based on movement locus | |
| CN103619036A (en) | Data acquisition and evaluation method and equipment | |
| CN103414608B (en) | Rapid web flow collection statistical system and method | |
| CN106921982B (en) | Method and device for evaluating communication abnormity | |
| CN105335795B (en) | A kind of subway Public Transport Transfer problem automatic diagnosis method based on IC card data | |
| CN105897811B (en) | A kind of method of data synchronization and device | |
| CN109714712A (en) | A kind of method and device of the data drop point based on attributes match to grid | |
| CN104768169A (en) | Optimization analysis method for high-speed railway mobile user perception and high-speed railway mobile user perception system | |
| CN109978746B (en) | Population exchange amount estimation method for judging travel effectiveness based on signaling data and combined with dynamic threshold | |
| CN104573874A (en) | Bus line planning method and device | |
| Holleczek et al. | Traffic measurement and route recommendation system for mass rapid transit (mrt) | |
| CN109768886A (en) | Network planning evaluation method and device | |
| CN113282575A (en) | Railway station passenger flow characteristic extraction method based on mobile phone signaling | |
| CN108646261A (en) | A kind of data processing method and device of vehicle GPS data set | |
| CN205792730U (en) | Metro passenger flow intelligence score-clearing system | |
| CN105848230B (en) | A kind of method and system judging the racing of motor vehicle road surface | |
| CN106776902A (en) | The analysis method and device of path locus | |
| CN116933958B (en) | Subway transfer station transfer passenger flow estimation method based on card swiping data | |
| CN103944862B (en) | Advertisement supervision method and advertisement supervision device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |