CN106534350B - A kind of method and device for prediction of meeting - Google Patents
A kind of method and device for prediction of meeting Download PDFInfo
- Publication number
- CN106534350B CN106534350B CN201611130290.7A CN201611130290A CN106534350B CN 106534350 B CN106534350 B CN 106534350B CN 201611130290 A CN201611130290 A CN 201611130290A CN 106534350 B CN106534350 B CN 106534350B
- Authority
- CN
- China
- Prior art keywords
- terminal
- matrix
- track
- data
- terminals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000011159 matrix material Substances 0.000 claims abstract description 171
- 230000005540 biological transmission Effects 0.000 claims abstract description 15
- 238000012512 characterization method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000009471 action Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention discloses a kind of method and device of prediction of meeting, and is related to field of communication technology, to solve the problems, such as that the method that the network server of the prior art is user's PUSH message is not smart enough.The described method includes: the tables of data of each terminal serviced is obtained, each serving BS ID of tables of data terminal including at least data flow initial time, data flow duration, Termination ID and in data flow duration；Determine the track data of each terminal respectively according to the tables of data of each terminal serviced；The track data of each terminal is converted into track matrix respectively；According to the track matrix of terminal, the collision probability of serviced every two terminal is calculated；The every two terminal transmission for being greater than first threshold to collision probability, which is met, predicts message, the estimated Encounter Time for predicting to carry two terminals in message, estimated meet place and collision probability of meeting.Scheme provided in an embodiment of the present invention is suitable for meeting using when predicting.
Description
Technical field
The present invention relates to field of communication technology more particularly to a kind of method and devices for prediction of meeting.
Background technique
With the arrival of big data era, user positioning technology is developed, in order to keep network server more intelligent
Ground is user's pushed information, needs to predict the behavior of meeting of user, for example, if predicting terminal 1 and terminal 2 on Monday
10:00 will meet in the market A, and network server can shift to an earlier date the market action message for recommending the market A to terminal 1 and terminal 2, this
Sample, network server can be according to predictions of meeting as a result, more intelligentized is user's PUSH message, and the prior art
In, the behavior of meeting of user can not be predicted, and cause the method that network server is user's PUSH message not smart enough.
Summary of the invention
The embodiment of the present invention provides a kind of method and device of prediction of meeting, to solve the network server of the prior art
For the method for user's PUSH message problem not smart enough.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that
A method of prediction of meeting, comprising:
The network server obtains the tables of data of each terminal serviced, and the tables of data rises including at least data flow
Begin the time, the data flow duration, Termination ID and in the data flow duration terminal each serving BS ID；
The network server determines the track data of each terminal according to the tables of data of each terminal serviced respectively；
The track data of each terminal is converted to track matrix, the member of the track matrix respectively by the network server
Element is the element in description terminal geographical location locating for different moments in the data flow duration；
The network server calculates the collision probability of serviced every two terminal according to the track matrix of terminal；
The network server meets to the every two terminal transmission that collision probability is greater than first threshold and predicts message, described
It meets and predicts to carry the estimated Encounter Time of two terminals in message, expects meet place and collision probability.
A kind of device for prediction of meeting, comprising:
Acquiring unit, for obtaining the tables of data for each terminal that the network server is serviced, the tables of data is extremely
Less include data flow initial time, the data flow duration, Termination ID and in the data flow duration terminal it is every
A serving BS ID；
Determination unit, the number for each terminal that the network server for being obtained according to the acquiring unit is serviced
Determine the track data of each terminal respectively according to table；
Converting unit is also used to that the track data for each terminal that the determination unit determines is converted to track square respectively
Battle array, the element of the track matrix are description terminal geographical location locating for different moments in the data flow duration
Element；
Computing unit, the track matrix of the terminal for being converted out according to the converting unit calculate the network service
The collision probability for the every two terminal that device is serviced；
Transmission unit, the every two terminal transmission for being greater than first threshold to collision probability, which is met, predicts message, described
It meets and predicts to carry the estimated Encounter Time of two terminals in message, expects meet place and collision probability.
The method and device of prediction provided in an embodiment of the present invention of meeting, and can not carry out prediction of meeting in the prior art,
And network server is caused to be compared to the method for user's PUSH message is not smart enough, each end that network server is obtained and handled
The tables of data at end obtains the track matrix for describing geographical location locating for each terminal different moments, thus according to track matrix meter
The collision probability of serviced every two terminal is calculated, when the collision probability of two terminals is higher, network server being capable of root
According to the estimated Encounter Time carried in the predictive information that meets, estimated meet place and collision probability, to Intelligent Terminal push away
Send message.For example, if network server predicts terminal 1 and terminal 2, on Monday 10:00 will meet in the market A, network service
Device can shift to an earlier date the market action message that the market A is pushed to terminal 1 and terminal 2, it is seen then that network server can be pre- according to meeting
Survey as a result, it is more intelligentized be user's PUSH message.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of logical construction schematic diagram of the system for prediction of meeting provided in an embodiment of the present invention；
Fig. 2 is a kind of flow chart of the method for prediction of meeting provided in an embodiment of the present invention；
Fig. 3 is the schematic diagram of the method provided in an embodiment of the present invention that track data is converted to track matrix；
Fig. 4 be another kind provided in an embodiment of the present invention meet prediction method flow chart；
Fig. 5 be another kind provided in an embodiment of the present invention meet prediction method flow chart；
Fig. 6 be another kind provided in an embodiment of the present invention meet prediction method flow chart；
Fig. 7 is a kind of logical construction schematic diagram of the device for prediction of meeting provided in an embodiment of the present invention；
Fig. 8 be another kind provided in an embodiment of the present invention meet prediction device logical construction schematic diagram；
Fig. 9 is a kind of logical construction schematic diagram of network server provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The method of prediction provided in an embodiment of the present invention of meeting, in the system applied to prediction of meeting, as shown in Figure 1, should
System includes: network server, and the terminal managed by network server and base station.It include at least two bases in the system
It stands, each base station can serve multiple terminals, three base stations illustratively be shown in Fig. 1, and serviced by each base station
Two terminals.
In the application scenarios, base station is used to carry out data interaction with the terminal that is managed, and records and each of managed
The tables of data of terminal, wherein if table 1 shows the tables of data for the terminal that a base station is managed, had recorded in tables of data
Under the terminal is serviced in the base station, the initial time of generated data flow, the data flow duration, the Termination ID of the terminal with
And the base station IDs of the base station, it is to be understood that when terminal movement is so that the serving BS of terminal changes, such as terminal
Base station B is switched to by base station A, then base station B will continue to record the tables of data of the terminal.
Table 1
It should be noted that network server can obtain the tables of data of each terminal from base station, and according to each end
The tables of data at end determines the track data of each terminal, and wherein track data is the company for describing the geographical location at terminal each moment
Continuous data.For example, terminal 1 switches to base station B by base station A, then network server needs are obtained from base station A and base station B respectively
The tables of data of terminal 1, the ID as from base station IDs recorded in the tables of data for the terminal 1 that base station A is obtained being base station A, from
The base station IDs that record are the ID of base station B in the tables of data for the terminal 1 that base station B is obtained, so can be with according to the tables of data of terminal 1
The motion track for determining terminal 1, as a kind of implementation, base station IDs can be inputted electronic map by network server, in turn
The longitude and latitude position of base station corresponding to base station IDs can be inquired, so that it is determined that terminal 1 is moved to base by the service range of base station A
Stand B service range motion track.
System as shown in connection with fig. 1, in order to make network server to Intelligent Terminal PUSH message, the embodiment of the present invention
A kind of method of prediction of meeting is provided, as shown in Fig. 2, this method comprises:
Step 201, network server obtain the tables of data of each terminal serviced.
Wherein, tables of data continues including at least data flow initial time, data flow duration, Termination ID and in data flow
Each serving BS ID of terminal in period.
Step 202, network server determine the track of each terminal according to the tables of data of each terminal serviced respectively
Data.
It should be noted that being continuous data by the track data that the tables of data of each terminal obtains, GC group connector is each
Geographical location locating for moment.
The track data of each terminal is converted to track matrix respectively by step 203, network server.
Wherein, the element of track matrix is description terminal geographical location locating for different moments in data flow duration
Element.
It should be noted that continuous track data is converted in the embodiment of the present invention in order to reduce data operation quantity
Discrete track matrix.In obtained track matrix, every row counterpart terminal of track matrix is in intraday track data, track
Track data of each column counterpart terminal of matrix within a daily period, for example, with 1 hour for the time since 0 point
Interval, takes 24 periods daily, and taking the location of last moment terminal of each period is the position element of matrix, i.e.,
1 point, 2 points ... 24 points, the location of integral point moment terminal is recorded in the matrix of track, obtains one day track matrix,
That is the daily track data of the terminal position element that is converted to 24 periods.
It is illustrated in figure 3 the schematic diagram that the track data of each terminal is converted to track matrix by network server.
It is general to calculate meeting for serviced every two terminal according to the track matrix of terminal for step 204, network server
Rate.
It should be noted that network server need to calculate the collision probability of every two terminal, for example, the network server management
Three terminals, respectively terminal 1, terminal 2 and terminal 3, then network server needs the collision probability of computing terminal 1 and terminal 2,
The collision probability and terminal 2 of terminal 1 and terminal 3 and the collision probability of terminal 3.
Step 205, network server meet to the every two terminal transmission that collision probability is greater than first threshold predicts message,
It meets and predicts to carry the estimated Encounter Time of two terminals in message, expects meet place and collision probability.
It should be noted that illustrating that taking network business device predicts when the collision probability of two terminals is greater than first threshold
The two terminals are likely to meet in following a certain position of certain time period, then at this point, network server can be to the two
Terminal transmission, which is met, predicts message.Wherein, this meet predict message include two terminals meet period, meet position,
The probability to meet.For example, first threshold is pre-set, example if the collision probability of terminal 1 and terminal 2 is greater than first threshold
It such as can be set to 80%, then network server needs to meet to terminal 1 and the transmission of terminal 2 and predict message, meets and predicts message
Time, the place that may be met and the probability to meet that middle carried terminal 1 and terminal 2 may meet.Equally, if terminal 2
With the collision probability of terminal 3 also greater than first threshold, then the network server prediction that also needs to meet to terminal 2 and the transmission of terminal 3 disappears
Breath.
As a kind of possible implementation, this, which meets, predicts that message can also include information relevant to meeting, for example,
The 10:00 that network server predicts 2 next Monday of terminal 1 and terminal is up to 90% in the probability that the market A is met, then network service
Device can send the action message in the market A respectively to terminal 1 and terminal 2.
The method of prediction provided in an embodiment of the present invention of meeting, and can not carry out prediction of meeting in the prior art, and cause
The method of network server to user's PUSH message is not smart enough to be compared, the number of each terminal that network server is obtained and handled
According to table, the track matrix for describing geographical location locating for each terminal different moments is obtained, to calculate institute according to track matrix
The collision probability of the every two terminal of service, when the collision probability of two terminals is higher, network server can be according to meeting
The estimated Encounter Time that is carried in predictive information, estimated meet place and collision probability, to Intelligent Terminal PUSH message.
For example, if network server predicts terminal 1 and terminal 2, on Monday 10:00 will meet in the market A, and network server can be with
The market action message in the market A is pushed to terminal 1 and terminal 2 in advance, it is seen then that network server can be according to the knot for prediction of meeting
Fruit, more intelligentized is user's PUSH message.
It should be noted that the phenomenon that there may be data flow overlappings in the tables of data for the terminal that network server obtains,
So also needing to be corrected the tables of data of terminal after the tables of data for obtaining terminal, it is based on this, is mentioned in the embodiment of the present invention
In another implementation supplied, as shown in figure 4, obtaining the data of each terminal serviced in step 201, network server
After table, also need to execute step 401.
Step 401, network server are corrected the tables of data of each terminal.
It should be noted that terminal is easy progress base station and cuts when terminal is in the edge of multiple base station institutes overlay area
It changes, so in section at the same time, terminal may be between multiple base stations there are data interaction, the number of terminal in the process
It can be recorded in multiple base stations according to table, so that the Termination ID of terminal just corresponds to multiple base station IDs in section at the same time, because
This, when being positioned to terminal, with regard to do not know to be positioned according to which base station IDs on earth.In order to determine that terminal 1 is corresponding
Base station IDs, terminal 1 need to be corrected in the data flow of same period, such as can choose the optimal base station of channel condition
As terminal in the period corresponding serving BS, the position of terminal 1 is determined with the base station IDs according to the serving BS.
The method of prediction provided in an embodiment of the present invention of meeting, network server can the tables of data to terminal carry out school
Just, data stream merging in multiple base stations will be recorded in the same period, i.e., only corresponds to one in the data flow of same period
A base station, and then network server can determine the position of terminal according to the position of the base station, allow network server more
Add and accurately determines terminal in the position of the period.
It should be noted that will appear in the track matrix of terminal when the tables of data of the terminal of base station record is imperfect
The phenomenon that position element lacks is based on this at this point, the position element of reply missing is filled, and provides in the embodiment of the present invention
Another implementation in, as shown in figure 5, the track data of each terminal is converted respectively in step 203, network server
After the matrix of track, also need to execute step 501.
Step 501 carries out the filling of position element to the track matrix of the terminal lacked there are position element, obtains each end
The complete track matrix at end.
It should be noted that base station and terminal can not when terminal is in shutdown or terminal is in the place of weak output signal
Realize that data interaction or data interaction are faint, it is likely that cause base station that can not record the tables of data of terminal, in turn result in track
The missing of position element in matrix.
In the embodiment of the present invention, complete track matrix in order to obtain, firstly, the self-similarity list of each column is calculated,
In, the self similarity tabular form of column is as follows:
{ bs_lable:rate }, wherein bs_lable characterizes geographical location, and rate characterizes the general of geographical location appearance
Rate.
For example, the track matrix of terminal 1 is
Then the self-similarity list of the first row of terminal 1 is { A:2/4, B:1/4, C:1/4 }, and the self-similarity of secondary series arranges
Table is { A:1/4, B:2/4, E:1/4 } ..., and so on.
After obtaining the self-similarity list of each column, each column in the matrix of track are successively scanned, if Current Scan
Rectangular array in and there is no position elements element, then continue to scan on next column, if there are position element in the rectangular array of Current Scan,
It then traverses each of column position, is lacked if there is position element, then it is random to generate according to the self-similarity list of the column
One position elements usually fills the position element of missing.For example, occur the position element of missing in terminal in the second row first row,
Then according to the self-similarity list of the column, the probability of the position element filling A of the missing is 2/4, and the probability for filling B is 1/4, filling
The probability of C is 1/4.Therefore, after column filling, the track matrix of terminal 1 may be?
May beBe also possible to for
After the filling arranged in the track matrix for terminating terminal, the track matrix is progressively scanned, if there is the position of missing
Element is set, then since the variation of terminal location in the same period should tend towards stability, then according to nearby principle, selects the track square
The position elements of the closest deletion sites element are usually filled in battle array.For example, it is assumed that through column filling in the embodiment of the present invention
Afterwards, the track matrix of terminal 1 isThen, when progressively scanning the track matrix, the first row the 4th is arranged
There is the position element that lacks, then according to nearby principle, position element of this missing be can be filled as C or D, probability everybody 50%,
And so on, the complete trajectory matrix for the terminal 1 assumed in the embodiment of the present invention is
It should be noted that the mode of filling track matrix used in the embodiment of the present invention is avoided due to being to fill at random
Interference caused by artificial designated position element.
The method of prediction provided in an embodiment of the present invention of meeting, network server can be to geographical locations locating for description terminal
Track matrix be filled, and then be capable of the collision probability of more accurate ground computing terminal using complete track matrix.
It is understood that network server can be according to track matrix after having obtained the track matrix of terminal
The collision probability of serviced every two terminal is calculated, this is based on, in another implementation provided in an embodiment of the present invention,
Such as Fig. 6, step 204, network server calculate the collision probability of serviced every two terminal according to the track matrix of terminal,
Include:
The similitude of the track matrix of two step 601, calculating terminals.
Wherein, the similitude of track matrix is that same position element number accounts for a track in the track matrix of two terminals
The probability of matrix element sum, same position element are that colleague's same column and characterization are in the track matrix of two terminals samely
Manage the element of position.
The calculation formula of the similitude of the track matrix of two terminals is as follows:
Wherein, NijIt is the number of same position element in the track matrix of terminal i and terminal j, m is the row of track matrix
Number, n is track matrix column number.
If the similitude of the track matrix of step 602, two terminals is more than or equal to second threshold, the rail of two terminals is calculated
The similitude of each rectangular array in mark matrix.
Wherein, the similitude of rectangular array is that the same position element number in the same row of the track matrix of two terminals accounts for
The probability of element sum in one rectangular array.
It should be noted that if the similitude of the track matrix of two terminals is less than second threshold, illustrate two terminals
Same position element number is less in the matrix of track, and network server terminates two terminals for being less than second threshold to similitude
Meet pre- flow gauge.
If the similar matrix column in the track matrix of step 603, two terminals there are similitude greater than 0, calculate in phase
The probability to meet like two terminals in the rectangular array corresponding period
Wherein, It is same position element in similar matrix column in terminal i
The probability occurred in similar matrix column,It is the same position element in similar matrix column in the similar matrix column of terminal j
The probability of appearance, locnFor the number of position element.
It should be noted that if the similitude of a certain column is equal to 0 in the track matrix of two terminals, then illustrate in this column
There is no same position element, so network server determines that two terminals will not meet within this column corresponding period, i.e.,
The probability that two terminals are met within this column corresponding periodIt is 0.
Above-described embodiment is illustrated below in conjunction with specific scene.
In conjunction with citing above, the complete trajectory matrix 1 of terminal 1 isTerminal 2 it is complete
Track matrix 2 isThe complete trajectory matrix 3 of terminal 3 is
It is computed, the track matrix 4 that same position element forms in the track matrix of terminal 1 and terminal 2 isTherefore, the similitude of the track matrix of terminal 1 and terminal 2For
76.6%.Based on same principle, the track matrix 5 that same position element forms in the track matrix of terminal 1 and terminal 3 isTherefore, the similitude of the track matrix of terminal 1 and terminal 3For
46.6%.
If second threshold is set as 68%, sim (1,3) less than 68%, in the track matrix for illustrating terminal 1 and terminal 3
Same position element number is less, then network server determines that terminal 1 and terminal 3 can not meet, and terminates to terminal 1 and terminal 3
Process flow.
Sim (1,2) is greater than 68%, illustrates that same position element number is more in the track matrix of terminal 1 and terminal 2, then
The similitude of each rectangular array in network server computing terminal 1 and the track matrix of terminal 2.
According to track matrix 4, network server obtain each column similitude 100%, 100%, 100%, 80%, 0,
80% }.Since same position element is not present in the 5th column, then terminal 1 and terminal 2 can not phases in the 5th column corresponding period
It meets, i.e.,It is 0.
For 1-4 column and the 6th column, first according to track matrix 4, network server obtains terminal 1 and terminal 2 each
Same position element in column is { the 1st column: ACB, the 2nd column: BAE, the 3rd column: CFD, the 4th column: CB, the 6th column ACB }.Then root
The probability that terminal 1 occurs within each column corresponding period in each geographical location is obtained according to track matrix 1, the period 1,
A:60%, C:20%, B:20% }, { period 2, B:60%, A:20%, E:20% }, period 3, C:60%, F:20%,
D:20% }, { period 4, C:60%, B:20% }, { period 6, A:40%, C:20%, B:20% }.Terminal 2 is in each column
The probability occurred in the corresponding period in each geographical location, { period 1, A:60%, C:20%, B:20% }, { period
2, B:60%, A:20%, E:20% }, { period 3, C:60%, F:20%, D:20% }, the period 4, C:60%, B:
40% }, { period 6, A:60%, C:20%, B:20% }.Then terminal 1 and terminal 2 are met within each column corresponding period
Probability be { period 1, A:60%*60%, C:20%*20%, B:20%*20% }, the period 2, B:60%*60%, A:
20%*20%, E:20%*20% }, { period 3, C:60%*60%, F:20%*20%, D:20%*20% }, { period
4, C:60%*60%, B:20%*40% }, { period 6, A:40%*60%, C:20%*20%, B:20%*20% }.
The method of prediction provided in an embodiment of the present invention of meeting calculates two terminals according to the track matrix of terminal first
The similitude of track matrix, then the similitude arranged in two terminal track matrixes is calculated, finally calculate two terminal track matrixes
It is middle to arrange the probability that two terminals are met in the corresponding period, and then the probability that two terminals are met in the same period is obtained,
When the collision probability of two terminals is higher, network server can be according to carrying it is expected that when meeting in the predictive information that meets
Between, estimated meet place and collision probability, to Intelligent Terminal PUSH message.For example, if network server predicts end
On Monday 10:00 will meet in the market A for end 1 and terminal 2, then network server, which can shift to an earlier date to terminal 1 and terminal 2, pushes A quotient
The market action message of field, it is seen then that network server can be according to prediction of meeting as a result, more intelligentized push for user
Message.
Corresponding to above-mentioned method flow, in order to solve that prediction of meeting can not be carried out in the prior art, and network is caused to take
It is engaged in the method problem not smart enough of from device to user's PUSH message, the embodiment of the invention provides a kind of device of prediction of meeting,
As shown in fig. 7, the device includes:
Acquiring unit 701, for obtaining the tables of data for each terminal that network server is serviced, tables of data is included at least
Data flow initial time, the data flow duration, Termination ID and in data flow duration terminal each serving BS
ID；
Determination unit 702, the data for each terminal that the network server for being obtained according to acquiring unit 701 is serviced
Table determines the track data of each terminal respectively；
Converting unit 703 is also used to that the track data for each terminal that determination unit 702 determines is converted to track respectively
Matrix, the element of track matrix are the element for describing terminal geographical location locating for different moments in data flow duration；
Computing unit 704, the track matrix of the terminal for being converted out according to converting unit 703 calculate network server
The collision probability of the every two terminal serviced；
Transmission unit 705, the every two terminal transmission for being greater than first threshold to collision probability, which is met, predicts message, phase
Meet the estimated Encounter Time that two terminals are carried in prediction message, estimated meet place and collision probability.
In another implementation provided in an embodiment of the present invention, as shown in figure 8, the device further include: correction unit
801, fills unit 802 and termination unit 803.
Unit 801 is corrected, the tables of data of each terminal for obtaining to acquiring unit 701 is corrected.
Fills unit 802 carries out the filling of position element for the track matrix to the terminal lacked there are position element, obtains
To the complete track matrix of each terminal.
Computing unit 704, is also used to calculate the similitude of the track matrix of two terminals, and the similitude of track matrix is two
Same position element number accounts for the probability of a track matrix element sum in the track matrix of a terminal, and same position element is
Element in the track matrix of two terminals in colleague's same column and the same geographical location of characterization；
Computing unit 704 calculates two if the similitude for being also used to the track matrix of two terminals is more than or equal to second threshold
The similitude of each rectangular array in the track matrix of a terminal, the similitude of rectangular array are the same of the track matrix of two terminals
Same position element number in column accounts for the probability of element sum in a rectangular array；
Computing unit 704, if being also used to the similar matrix column in the track matrix of two terminals there are similitude greater than 0,
It then calculates and arranges the probability that two terminals are met in the corresponding period in similar matrixWherein,It is describedIt is arranged for same position element in similar matrix column in the similar matrix of terminal i
The probability of middle appearance,Occur in the similar matrix column of terminal j for the same position element in similar matrix column general
Rate, locnFor the number of position element.
Unit 803 is terminated, if the similitude of the track matrix for two terminals is less than second threshold, is terminated to similitude
Less than the pre- flow gauge that meets of two terminals of second threshold.
The device of prediction provided in an embodiment of the present invention of meeting, and can not carry out prediction of meeting in the prior art, and cause
The method of network server to user's PUSH message is not smart enough to be compared, each terminal that acquiring unit is obtained and handled first
Tables of data obtains the track matrix for describing geographical location locating for each terminal different moments, to calculate according to track matrix
The collision probability for the every two terminal that network server is serviced, when the collision probability of two terminals is higher, transmission unit energy
Enough according to the estimated Encounter Time carried in the predictive information that meets, estimated meet place and collision probability, to Intelligent Terminal
Ground PUSH message.For example, if network server predicts terminal 1 and terminal 2, on Monday 10:00 will meet in the market A, network
Server can shift to an earlier date the market action message that the market A is pushed to terminal 1 and terminal 2, it is seen then that network server can be according to phase
Meet predicting as a result, more intelligentized is user's PUSH message.
The embodiment of the present invention also provides a kind of network server, as shown in figure 9, the device includes memory 901, processor
902, transceiver 903, bus 904.
Memory 901 can be ROM (Read Only Memory, read-only memory), static storage device, dynamic memory
Equipment or RAM (Random Access Memory, random access memory).Memory 901 can store an operating system and
Other applications.When by software or firmware to realize technical solution provided in an embodiment of the present invention, for realizing this
The program code for the technical solution that inventive embodiments provide is stored in memory 901, and is executed by processor 902.
Transceiver 903 is for device and other equipment or communication network (such as, but not limited to Ethernet, RAN Radio
Access Network, wireless access network), WLAN (Wireless Local Area Network, WLAN) etc.) it
Between communication.
Processor 902 can use general central processing unit (Central Processing Unit, CPU), micro process
Device, application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or one or
Multiple integrated circuits, for executing relative program, to realize technical solution provided by the embodiment of the present invention.
Bus 904 may include an access, in device all parts (such as memory 901, transceiver 903 and processor
902) information is transmitted between.
It should be noted that although hardware shown in Fig. 9 illustrate only memory 901, transceiver 903 and processor 902 and
Bus 904, but during specific implementation, it should be apparent to a person skilled in the art that the device also includes to realize normal fortune
Other devices necessary to row.Meanwhile according to specific needs, it should be apparent to a person skilled in the art that also may include realizing it
The hardware device of his function.
Specifically, when network server shown in Fig. 9 is for realizing device shown in Fig. 7 and Fig. 8 embodiment, in the device
Processor 902, for obtaining the tables of data for each terminal that network server is serviced, tables of data rises including at least data flow
Begin the time, the data flow duration, Termination ID and in data flow duration terminal each serving BS ID；
The tables of data of processor 902, each terminal for being also used to be serviced according to network server determines each end respectively
The track data at end；
Processor 902 is also used to that the track data of each terminal is converted to track matrix, the element of track matrix respectively
For the element for describing terminal geographical location locating for different moments in data flow duration；
Processor 902 is also used to the track matrix according to terminal, calculates the every two terminal that network server is serviced
Collision probability；
Transceiver 903, the every two terminal transmission for being greater than first threshold to collision probability, which is met, predicts message, meets
Estimated Encounter Time, estimated meet place and the collision probability of two terminals are carried in prediction message.
Processor 902 is also used to be corrected the tables of data of each terminal.
Processor 902 is also used to carry out the filling of position element to the track matrix of the terminal lacked there are position element, obtain
To the complete track matrix of each terminal.
Processor 902, is also used to calculate the similitude of the track matrix of two terminals, and the similitude of track matrix is two
Same position element number accounts for the probability of a track matrix element sum in the track matrix of terminal, and same position element is two
Element in the track matrix of a terminal in colleague's same column and the same geographical location of characterization；
Processor 902 calculates two if the similitude for being also used to the track matrix of two terminals is more than or equal to second threshold
The similitude of each rectangular array in the track matrix of terminal, the similitude of rectangular array are the same row of the track matrix of two terminals
In same position element number account for the probability of element sum in a rectangular array；
Processor 902, if being also used to the similar matrix column in the track matrix of two terminals there are similitude greater than 0,
It calculates and arranges the probability that two terminals are met in the corresponding period in similar matrixWherein,It is describedIt is arranged for same position element in similar matrix column in the similar matrix of terminal i
The probability of middle appearance,Occur in the similar matrix column of terminal j for the same position element in similar matrix column general
Rate, locnFor the number of position element.
Processor 902 terminates if the similitude for being also used to the track matrix of two terminals is less than second threshold to similitude
Less than the pre- flow gauge that meets of two terminals of second threshold.
Network server provided in an embodiment of the present invention, and can not carry out prediction of meeting in the prior art, and lead to network
The method of server to user's PUSH message is not smart enough to be compared, the data of each terminal that network server is obtained and handled
Table obtains the track matrix for describing geographical location locating for each terminal different moments, is taken to be calculated according to track matrix
The collision probability of the every two terminal of business, when the collision probability of two terminals is higher, network server can be pre- according to meeting
The estimated Encounter Time that is carried in measurement information, estimated meet place and collision probability, to Intelligent Terminal PUSH message.Example
Such as, if network server predicts terminal 1 and terminal 2, on Monday 10:00 will meet in the market A, and network server can mention
Forward direction terminal 1 and terminal 2 push the market action message in the market A, it is seen then that network server can be according to the knot for prediction of meeting
Fruit, more intelligentized is user's PUSH message.
Through the above description of the embodiments, it is apparent to those skilled in the art that the present invention can borrow
Help software that the mode of required common hardware is added to realize, naturally it is also possible to which the former is more preferably by hardware, but in many cases
Embodiment.Based on this understanding, the portion that technical solution of the present invention substantially in other words contributes to the prior art
Dividing can be embodied in the form of software products, which stores in a readable storage medium, such as count
The floppy disk of calculation machine, hard disk or CD etc., including some instructions are used so that computer equipment (it can be personal computer,
Server or the network equipment etc.) execute method described in each embodiment of the present invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is 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 (8)
1. a kind of method for prediction of meeting, which is characterized in that the method is wrapped in the system applied in forecasting system of meeting
Include network server, and the terminal managed by the network server and base station, which comprises
The network server obtains the tables of data of each terminal serviced, when the tables of data includes at least data flow starting
Between, the data flow duration, Termination ID and in the data flow duration terminal each serving BS ID；
The network server determines the track data of each terminal according to the tables of data of each terminal serviced respectively；
The track data of each terminal is converted to track matrix respectively by the network server, and the element of the track matrix is
The element in terminal geographical location locating for different moments in the data flow duration is described；
The network server calculates the collision probability of serviced every two terminal according to the track matrix of terminal；
The network server meets to the every two terminal transmission that collision probability is greater than first threshold and predicts message, described to meet
Estimated Encounter Time, estimated meet place and the collision probability of two terminals are carried in prediction message；
According to the track matrix of terminal, the collision probability for calculating serviced every two terminal includes: the network server
The similitude of the track matrix of two terminals is calculated, the similitude of the track matrix is in the track matrix of two terminals
Same position element number accounts for the probability of a track matrix element sum, and the same position element is the track of two terminals
Element in matrix in colleague's same column and the same geographical location of characterization；
If the similitude of the track matrix of two terminals is more than or equal to second threshold, calculate each in the track matrix of two terminals
The similitude of rectangular array, the similitude of the rectangular array are the same position element in the same row of the track matrix of two terminals
Number accounts for the probability of element sum in a rectangular array；
If the similar matrix column in the track matrix of two terminals there are similitude greater than 0, calculate and arrange in the similar matrix
The probability that two terminals are met in the corresponding periodWherein,
It is describedIt is described for the probability that same position element in similar matrix column occurs in the similar matrix column of terminal iFor the probability that the same position element in similar matrix column occurs in the similar matrix column of terminal j, locnFor position
Set the number of element.
2. the method for prediction according to claim 1 of meeting, which is characterized in that serviced in network server acquisition
Each terminal tables of data after, the method also includes:
The network server is corrected the tables of data of each terminal.
3. the method for prediction according to claim 2 of meeting, which is characterized in that in network server respectively by each terminal
Track data be converted to track matrix after, the method also includes:
Element filling in position is carried out to the track matrix of the terminal lacked there are position element, obtains the complete rail of each terminal
Mark matrix.
4. the method for prediction according to claim 1 of meeting, which is characterized in that calculating the track matrix of two terminals
After similitude, the method also includes:
If the similitude of the track matrix of two terminals is less than second threshold, two ends for being less than second threshold to similitude are terminated
The pre- flow gauge that meets at end.
5. a kind of device for prediction of meeting, which is characterized in that described device includes:
Acquiring unit, for obtaining the tables of data for each terminal that network server is serviced, the tables of data includes at least number
According to stream initial time, the data flow duration, Termination ID and in the data flow duration terminal each service base
Stand ID；
Determination unit, the tables of data for each terminal that the network server for being obtained according to the acquiring unit is serviced
The track data of each terminal is determined respectively；
Converting unit is also used to that the track data for each terminal that the determination unit determines is converted to track matrix respectively,
The element of the track matrix is the member for describing terminal geographical location locating for different moments in the data flow duration
Element；
Computing unit, the track matrix of the terminal for being converted out according to the converting unit calculate the network server institute
The collision probability of the every two terminal of service；
Transmission unit, the every two terminal transmission for being greater than first threshold to collision probability, which is met, predicts message, described to meet
Estimated Encounter Time, estimated meet place and the collision probability of two terminals are carried in prediction message；
The computing unit, is also used to calculate the similitude of the track matrix of two terminals, and the similitude of the track matrix is
Same position element number accounts for the probability of a track matrix element sum, the same position in the track matrix of two terminals
Element is the element in the track matrix of two terminals in colleague's same column and the same geographical location of characterization；
The computing unit calculates two if the similitude for being also used to the track matrix of two terminals is more than or equal to second threshold
The similitude of each rectangular array in the track matrix of terminal, the similitude of the rectangular array are the same of the track matrix of two terminals
Same position element number in one column accounts for the probability of element sum in a rectangular array；
The computing unit is counted if being also used to the similar matrix column in the track matrix of two terminals there are similitude greater than 0
It calculates and arranges the probability that two terminals are met in the corresponding period in the similar matrixWherein,It is describedIt is same position element in similar matrix column in terminal i
The probability occurred in similar matrix column, it is describedIt is the same position element in similar matrix column in the similar of terminal j
The probability occurred in rectangular array, locnFor the number of position element.
6. the device of prediction according to claim 5 of meeting, which is characterized in that described device further include:
Unit is corrected, the tables of data of each terminal for obtaining to the acquiring unit is corrected.
7. the device of prediction according to claim 6 of meeting, which is characterized in that described device further include:
Fills unit carries out the filling of position element for the track matrix to the terminal lacked there are position element, obtains each
The complete track matrix of terminal.
8. the device of prediction according to claim 5 of meeting, which is characterized in that described device further include:
Unit is terminated, if the similitude of the track matrix for two terminals is less than second threshold, is terminated to similitude less than the
The pre- flow gauge that meets of two terminals of two threshold values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611130290.7A CN106534350B (en) | 2016-12-09 | 2016-12-09 | A kind of method and device for prediction of meeting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611130290.7A CN106534350B (en) | 2016-12-09 | 2016-12-09 | A kind of method and device for prediction of meeting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106534350A CN106534350A (en) | 2017-03-22 |
| CN106534350B true CN106534350B (en) | 2019-08-02 |
Family
ID=58341546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611130290.7A Active CN106534350B (en) | 2016-12-09 | 2016-12-09 | A kind of method and device for prediction of meeting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106534350B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052518A (en) * | 2017-10-25 | 2018-05-18 | 小草数语（北京）科技有限公司 | The method for expressing and device of space-time track |
| CN108668265B (en) * | 2017-12-29 | 2020-01-07 | 西安电子科技大学 | Method for predicting meeting probability among mobile users based on cyclic neural network |
| CN109947793B (en) * | 2019-03-20 | 2022-05-31 | 深圳市北斗智能科技有限公司 | Method and device for analyzing accompanying relationship and storage medium |
| CN110290582B (en) * | 2019-05-22 | 2020-10-30 | 浙江工业大学 | Base station label track prediction method based on seq2seq frame |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574971A (en) * | 2015-02-03 | 2015-04-29 | 上海奕行信息科技有限公司 | Road condition analysis method and system of expressway |
| CN104867015A (en) * | 2015-04-27 | 2015-08-26 | 福州大学 | Article deliverer recommending method based on user mobility prediction |
| CN105005615A (en) * | 2015-07-17 | 2015-10-28 | 广东小天才科技有限公司 | Method, device and system for carrying out terminal recommendation on the basis of movement trajectory |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9407705B2 (en) * | 2014-01-02 | 2016-08-02 | Paypal, Inc. | Proxied push notifications based on user interaction |
-
2016
- 2016-12-09 CN CN201611130290.7A patent/CN106534350B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574971A (en) * | 2015-02-03 | 2015-04-29 | 上海奕行信息科技有限公司 | Road condition analysis method and system of expressway |
| CN104867015A (en) * | 2015-04-27 | 2015-08-26 | 福州大学 | Article deliverer recommending method based on user mobility prediction |
| CN105005615A (en) * | 2015-07-17 | 2015-10-28 | 广东小天才科技有限公司 | Method, device and system for carrying out terminal recommendation on the basis of movement trajectory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106534350A (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106534350B (en) | A kind of method and device for prediction of meeting | |
| US9092532B2 (en) | Method and server for searching for nearby user in social networking services | |
| US10341878B2 (en) | Connection technology-based wireless coverage verification | |
| US20170132264A1 (en) | Trajectory Data Query Method and Apparatus | |
| CN103647800A (en) | Method and system of recommending application resources | |
| CN102761606B (en) | A kind of method and apparatus determining targeted customer | |
| CN104680250A (en) | Position predicting system | |
| CN105045889A (en) | Information pushing method and apparatus | |
| CN111800447A (en) | Server scheduling method and device for cloud game and readable storage medium | |
| CN111488414A (en) | Road task matching method, device and equipment | |
| CN102664828B (en) | System and method for friend recommendation in social network service (SNS) network | |
| JP5986028B2 (en) | Apparatus, program, and method for estimating short-time stay location of user having portable terminal | |
| CN109831744A (en) | It is a kind of exception track recognizing method, device and storage equipment | |
| CN105991677A (en) | Method and device for providing information objects to users | |
| CN104852831B (en) | A kind of Forecasting Methodology of hierarchical network RTT | |
| CN105550334A (en) | Video recommendation method and device | |
| CN112287503B (en) | Dynamic space network construction method for traffic demand prediction | |
| CN104168174A (en) | Method and apparatus for information transmission | |
| CN103560974B (en) | Method and device for maintaining tokens | |
| CN105043377A (en) | Method and device for recording running routes, and electronic equipment | |
| CN108347355A (en) | A kind of detection method and its equipment of application state | |
| CN102521362B (en) | Web service recommendation method and device | |
| CN106611100B (en) | User behavior analysis method and device | |
| CN111967938B (en) | Cloud resource recommendation method and device, computer equipment and readable storage medium | |
| CN111711957B (en) | Traffic-based site capacity expansion prediction method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |