CN105409306A - Method and apparatus for predicting location of mobile terminal - Google Patents
Method and apparatus for predicting location of mobile terminal Download PDFInfo
- Publication number
- CN105409306A CN105409306A CN201480009660.4A CN201480009660A CN105409306A CN 105409306 A CN105409306 A CN 105409306A CN 201480009660 A CN201480009660 A CN 201480009660A CN 105409306 A CN105409306 A CN 105409306A
- Authority
- CN
- China
- Prior art keywords
- information
- trajectory
- forecasting
- mobile terminal
- historical track
- 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
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method and apparatus for predicting a location of a mobile terminal, so as to predict a next location of a target mobile terminal according to history trajectory information of multiple mobile terminals. First, clustering of history trajectory segments of multiple users is acquired to obtain trajectory segment groups, wherein history trajectory segments of a user are obtained by dividing entire history trajectory information of the user. Next, a target trajectory segment group similar to a current trajectory segment of a target user is acquired from the trajectory segment groups. Finally, a next location of the target user is predicted according to trajectory segments in the target trajectory segment group. A history trajectory is divided into multiple history trajectory segments, and each period of time has an independent trajectory segment. Therefore, if a trajectory of a mobile terminal changes at a moment, the change of the trajectory can be rapidly captured, thereby improving the accuracy of a prediction result.
Description
Mobile terminal locations Forecasting Methodology and device
The present invention relates to the Forecasting Methodology and device of communication technical field, more particularly to mobile terminal locations for technical field.Background technology base station can determine the mobile terminal in its coverage（User）Current geographic position, the geographical position of base station record user obtains the historical track information of user.Next position of user can be predicted by the historical track information of user.
Due to having certain relevance between some user's factum and the behavior of the user friend, therefore, a kind of existing customer location Forecasting Methodology, the position of user is predicted using the trace information of the similar users with similar behavior, specifically, analyzed the whole historical track of user as an entirety, excavate the part of user behavior rule, set up suitable personal behavior model.And at the following a certain moment for needing to predict customer location, matched using the historical track information before personal behavior model, and a certain moment, obtain positional information of the user at a certain moment.
Because user trajectory is being continually changing, current similar user may also be no longer similar in future, causes the position prediction result accuracy rate of user low.In addition, using the whole historical track of user as an entirety, the change to user behavior is insensitive, i.e. the nearest Behavioral change of user influences little in the probability distribution of whole behavior pattern, it is difficult to embody, the accuracy rate reduction that predicts the outcome of customer location is further resulted in.
A kind of mobile terminal locations Forecasting Methodology and device are provided in the content of the invention embodiment of the present invention, to solve the problem of position prediction result accuracy rate of the prior art is low.
In order to solve the above-mentioned technical problem, the embodiment of the invention discloses following technical scheme：
In a first aspect, the present invention provides a kind of mobile terminal locations Forecasting Methodology, including：
The track fragment group after the historical track section cluster to multiple mobile terminals is obtained, the historical track section is divided according to the historical track information of mobile terminal to be obtained；From the track fragment group, the target trajectory fragment group similar to the current track segment of destination mobile terminal is obtained；According to the target trajectory fragment group, next position of the destination mobile terminal after the current track segment is determined.
With reference in a first aspect, in the first possible implementation of first aspect, methods described also includes：According to the similarity between historical track section, historical track section is clustered using clustering algorithm, track fragment group is obtained.
With reference to the first possible implementation of first aspect, in second of possible implementation of first aspect, according to the similarity between historical track section, historical track section is clustered using clustering algorithm, including:The trajectory model of each historical track section is obtained respectively；The similarity between the trajectory model is calculated, the similarity between historical track section corresponding with the trajectory model is obtained；According to the similarity between historical track section, similarity is met to mono- track fragment group of historical track Duan Juwei of predetermined threshold value.
With reference to second of possible implementation of first aspect, in the third possible implementation of first aspect, the trajectory model of each historical track section is obtained respectively, including：Extracted sequentially in time from each historical track section and obtain multiple sub-trajectories；Select support to be not less than the sub-trajectory of minimum support threshold value from the multiple sub-trajectory, obtain the trajectory model of the historical track section.
With reference to second of possible implementation of first aspect, in the 4th kind of possible implementation of first aspect, the similarity between the trajectory model is calculated, including：Determine the longest common subsequence between two trajectory models；With reference to the position continuity parameter of trajectory model, longest common subsequence ratio shared in two trajectory models respectively is calculated；Calculate the longest common subsequence respectively in described two trajectory models proportion average value, obtain the similarity between described two trajectory models.
With reference to first aspect or the first any one into the 4th kind of possible implementation, in the 5th kind of possible implementation of first aspect, according to the target trajectory fragment group, next position of the destination mobile terminal after the current track segment is determined, including：
According to the corresponding historical track section of destination mobile terminal in the target trajectory fragment group, destination mobile terminal is predicted in next position of the current track segment, the first information of forecasting is obtained, first information of forecasting includes predicted position and corresponding first probable value；
According to the corresponding historical track section of other mobile terminals in the target trajectory fragment group, next position of the destination mobile terminal after current track segment is predicted, the second information of forecasting is obtained, second information of forecasting includes predicted position and corresponding second probable value；
Merge first information of forecasting and the second information of forecasting, determine next position that the maximum predicted position of probable value is destination mobile terminal.
With reference to the 5th kind of possible implementation of first aspect, in the 6th kind of possible implementation of first aspect, merge first information of forecasting and the second information of forecasting, determine next position that the maximum corresponding predicted position of probable value is destination mobile terminal, including：
Obtain corresponding first weight of first information of forecasting, and corresponding second weight of second information of forecasting；
By the first probable value in first information of forecasting and first multiplied by weight, the first Weight prediction information is obtained；
By the second probable value in second information of forecasting and second multiplied by weight, the second Weight prediction information is obtained；
The corresponding probable value of corresponding predicted position in the first Weight prediction information and the second Weight prediction information is overlapped merging, obtains merging information of forecasting；
It regard the maximum predicted position of probable value in the merging information of forecasting as next position of destination mobile terminal.
Second aspect, the present invention implements also to provide a kind of mobile terminal locations prediction meanss, including：
Receiving unit, for receiving the track fragment group after the historical track section cluster to multiple mobile terminals, the historical track section is divided according to the historical track information of mobile terminal to be obtained；
Processing unit, for from the track fragment group, obtaining the target trajectory fragment group similar to the current track segment of destination mobile terminal；And, according to the target trajectory fragment group, determine next position of the destination mobile terminal after the current track segment.
With reference to second aspect, in the first possible implementation of second aspect, the processing unit, it is additionally operable to obtain the trajectory model of each historical track section respectively, the similarity between the trajectory model is calculated, the similarity between historical track section corresponding with the trajectory model is obtained；According to the similarity between historical track section, similarity is met to mono- track fragment group of historical track Duan Juwei of predetermined threshold value.
With reference to the first possible implementation of second aspect, in second of possible implementation of second aspect, the processing unit, specifically for determining the longest common subsequence between two trajectory models, with reference to the position continuity parameter of trajectory model, calculate longest common subsequence ratio shared in two trajectory models respectively, calculate the longest common subsequence respectively in described two trajectory models proportion average value, obtain the similarity between described two trajectory models.
With reference to the first any one into second of possible implementation of second aspect or second aspect, in the third possible implementation of second aspect, the processing unit specifically for：
According to the corresponding historical track section of destination mobile terminal in the target trajectory fragment group, destination mobile terminal is predicted in next position of the current track segment, the first information of forecasting is obtained, first information of forecasting includes predicted position and corresponding first probable value；
According to the corresponding historical track section of other mobile terminals in the target trajectory fragment group, destination mobile terminal is existed
Next position after current track segment is predicted, and obtains the second information of forecasting, and second information of forecasting includes predicted position and corresponding second probable value；
Merge first information of forecasting and the second information of forecasting, determine next position that the maximum predicted position of probable value is destination mobile terminal.
With reference to the third possible implementation of second aspect, in the 4th kind of possible implementation of second aspect, the processing unit specifically for：
Obtain corresponding first weight of first information of forecasting, and corresponding second weight of second information of forecasting；
By the first probable value in first information of forecasting and first multiplied by weight, the first Weight prediction information is obtained；
By the second probable value in second information of forecasting and second multiplied by weight, the second Weight prediction information is obtained；
The corresponding probable value of corresponding predicted position in the first Weight prediction information and the second Weight prediction information is overlapped merging, obtains merging information of forecasting；
It regard the maximum predicted position of probable value in the merging information of forecasting as next position of destination mobile terminal.
From above technical scheme, mobile terminal locations Forecasting Methodology provided in an embodiment of the present invention and device, obtain first and track fragment group is obtained to the historical track end cluster of multiple users, wherein, the historical track section of user is divided from the whole historical track information of user to be obtained.Then, the target trajectory fragment group similar to the current track segment of targeted customer is obtained from the fragment group of track, finally, the orbit segment in target trajectory fragment group is predicted to next position of targeted customer.
Historical track is divided into multiple historical track sections by methods described, each historical track section is a part for historical track information, therefore, if sometime the track of mobile terminal is changed, the situation of change of track can be captured quickly, so as to improve the accuracy rate predicted the outcome.Moreover, methods described is by traditional similar users（Mobile terminal）Similar track section is converted into, i.e., does not compare the corresponding historical track information of mobile terminal as an overall historical track information with other mobile terminals, judges the similitude between mobile terminal.But, the corresponding historical track information of mobile terminal is divided into multiple historical track sections, the similitude between orbit segment is judged, so, it is capable of the similitude of trickleer, more accurately capture mobile terminal historical track, can further improves the accuracy rate predicted the outcome.The Figure of description that brief description of the drawings constitutes the part of the application is used for providing a further understanding of the present invention, and schematic description and description of the invention is used to explain the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 shows a kind of schematic flow sheet of mobile terminal locations Forecasting Methodology of the embodiment of the present invention；
Fig. 2 shows the method flow schematic diagram of the step S120 in embodiment illustrated in fig. 1；
Fig. 3 shows the method flow schematic diagram of the step S140 in embodiment illustrated in fig. 1；
Fig. 4 shows a kind of sub-trajectory schematic diagram of the embodiment of the present invention；
Fig. 5 shows the method flow schematic diagram of the step S130 in embodiment illustrated in fig. 1；
Fig. 6 shows the method flow schematic diagram of the step S133 in embodiment illustrated in fig. 5；
Fig. 7 shows a kind of block diagram of mobile terminal locations prediction meanss of the embodiment of the present invention.
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, the required accompanying drawing used in embodiment or description of the prior art will be briefly described below, apparently, for those of ordinary skills, without having to pay creative labor, other accompanying drawings can also be obtained according to these accompanying drawings.
Embodiment is to realize the purpose of the present invention; the invention provides mobile terminal locations Forecasting Methodology and device; the whole historical track of mobile terminal is divided into multiple historical track sections, and historical track section clustered, similar mono- track fragment group of historical track Duan Juwei；From the track fragment group, the target trajectory fragment group similar to the moment to be predicted affiliated orbit segment of destination mobile terminal is obtained, according to target trajectory fragment group, predicted position of the destination mobile terminal at the moment to be predicted is determined.Historical track is divided into multiple historical track sections according to time response, each period has independent orbit segment, therefore, if sometime the track of mobile terminal is changed, the situation of change of track can be captured quickly, so as to improve the accuracy rate predicted the outcome.
Above is the core concept of the present invention, in order that those skilled in the art more fully understand the present invention program, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is purged, is fully described by, obviously, the embodiment of the description is only a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art are obtained under the premise of creative work is not made belongs to the scope of protection of the invention.
Fig. 1 is referred to, a kind of schematic flow sheet of mobile terminal locations Forecasting Methodology of the embodiment of the present invention is shown, this method is applied in wireless network.As shown in figure 1, methods described may comprise steps of：
Step S110, obtains the track fragment group after the historical track section cluster to multiple mobile terminals, and the historical track section is divided according to the historical track information of mobile terminal to be obtained.
The historical track information of multiple mobile terminals is divided and obtains historical track section.It is assumed that mobile terminal（That is, user）In moving process, active wireless network is accessed at the ^ moment, wherein, it is 1=1 to access position, 2,3 ..., n, and in tnMoment have left active wireless network, then define ^ ^O:^, /2, ...,/„>It is the one of the user
Individual historical track section, historical track information is made up of some orderly position sequences.The process that user moves in a network can produce multiple historical tracks section, all these historical tracks constitute the historical track information D of the mobile terminal=, ^2..., S extract each orbit segment therein from the whole historical track of user, the historical track section of the user is obtained.
After the historical track section for obtaining user, historical track section can be clustered in advance using clustering algorithm, similarity is met to mono- track fragment group of historical track Duan Juwei of default similarity, i.e., by similar mono- track fragment group of historical track Duan Juwei.If weighing the similitude between historical track section using cosine similarity, when the cosine similarity between historical track section is more than predetermined threshold value, shows that the similitude between corresponding historical track section is very big, can be divided into a group.
Customer location prediction need not be carried out every time to the process that historical track section is clustered to be carried out, and existing historical track section in database can be clustered in advance, then, the position of user is predicted using cluster result.
Step S120, from the track fragment group, obtains the target trajectory fragment group similar to the current track segment of destination mobile terminal.
In one embodiment of the invention, as shown in Fig. 2 step S120 can include step S121 S125:Step S121, obtains the current track segment of destination mobile terminal；The current track segment is destination mobile terminal in the orbit segment residing for current time.
Step S122, judges whether the similarity between the current track segment and track fragment group meets predetermined threshold value.If meeting predetermined threshold value（For example, the similarity between current track segment and track fragment group is more than predetermined threshold value）, in step S123, it is target trajectory fragment group to determine the track fragment group.Then, then step S124 is performed.
If being unsatisfactory for predetermined threshold value, in step S124, judge whether that whole track fragment groups have all judged.
If whole tracks fragment group has all judged, in step S125, target trajectory fragment group is determined.The track fragment group that similarity between current track segment is met into predetermined threshold value is defined as target trajectory fragment group.
If also there is the track fragment group not judged, return and perform step S122, continuation judges whether next track fragment group is target trajectory fragment group.
Step S130, according to the target trajectory fragment group, determines next position of the destination mobile terminal after current track segment.
To prediction destination mobile terminal（That is targeted customer）Next position after current track segment, next position is predicted respectively using the historical track section of the targeted customer in target trajectory fragment group itself and the historical track section of other users, obtain comprising predicted position and correspond to predicting the outcome for probability, by the obtained merging that predicts the outcome, wherein, it regard the maximum position of probable value as next position of targeted customer.
Customer location prediction of the invention signified only need to predict next position of user current location, without in view of up to
At the time of next position.Time is only used for doing the sequence of historical position and time window is divided and is used, that is, ensures that user's history trace information is ordered into sequence, and historical track section can be effectively divided according to the time.
The mobile terminal locations Forecasting Methodology that the present embodiment is provided, next position of targeted customer is predicted according to the historical track information of multiple users, obtain first and track fragment group is obtained to the historical track end cluster of multiple users, wherein, the historical track section of user is divided from the whole historical track information of user obtains.Then, the target trajectory fragment group similar to the current track segment of targeted customer is obtained from the fragment group of track, finally, the orbit segment in target trajectory fragment group is predicted to next position of targeted customer.
Historical track information is divided into multiple historical track sections by methods described, each historical track section is a part for historical track information, therefore, if sometime the track of user is changed, the situation of change of track can be captured quickly from historical track section, so as to improve the accuracy rate predicted the outcome.And, traditional similar users are converted into similar track section by methods described, it is not overall to be compared the corresponding historical track information of user as one with the historical track information of other users, judge the similitude between user, but the corresponding historical track information of user is divided into multiple historical track sections, judge the similitude between orbit segment.In such manner, it is possible to which the similitude between trickleer, more accurately capture user historical track, can further improve the accuracy rate of position prediction result.
Alternatively, the embodiment shown in Fig. 1 can also comprise the following steps before step S110：
Step S140, according to the similarity between historical track section, cluster obtaining track fragment group using clustering algorithm to historical track section.
For example, when the cosine similarity between historical track section A and historical track section B is more than predetermined threshold value, then by A and B clusters to a track fragment group.
Classical clustering algorithm can be utilized（For example, K-means algorithms）, multiple users corresponding historical track section is clustered according to the similitude between historical track section, track fragment group is obtained.Historical track section in the fragment group of each track is similar, and each user corresponding historical track section in different time sections may be assigned in different track fragment groups, and the historical track of different user section may be assigned in same track fragment group.
Alternatively, when increasing new historical track section in database, newly-increased historical track section and existing track fragment group can be clustered using incremental clustering algorithm, obtains new cluster result.Refer to Fig. 3, show the method flow schematic diagram of step S140 in Fig. 1, in the present embodiment, before the similarity between obtaining historical track section, trajectory model, then, the similarity based on trajectory model are extracted for each historical track section, different historical track sections is clustered, the similar track fragment group of trajectory model is obtained.
As shown in figure 3, methods described can include step：
Step S141, obtains the trajectory model of each historical track section respectively.
In one embodiment of the invention, step S141 may comprise steps of 11) -12)：
Step 11), extracted from each historical track section obtain multiple sub-trajectories sequentially in time.
If there is a track《, its position sequence included, the whole position sequences that there is track in another track, i.e.,《The subset for being, such a situation claims track《For the sub-trajectory of track.
For example, length is m track ^^^, ^, ^ ..., ^^^ and the track sets that length is n
..,βη>If, exist integer 1≤<A:2<...<Am≤ n so that α1 =βί1,α2=βί2,...απι=βίιη, then track " be called track ^ sub-trajectory, i.e. ^, be ^ subset.
Alternatively, the whole historical track information of user is divided into the user's history track that a period of time is included in several time windows, each time window, i.e., each time window to should historical track section a sub-trajectory.It is assumed that time window length is Τ, then, moved forward by Δ Τ of step-length, the corresponding sub-trajectory of time window 1 is： tl: a、 b、 c、 d、 e、 f;The corresponding sub-trajectory of time window 2 is： t2: e、 f、 g、 h、 i;The corresponding sub-trajectory of time window 3 is： t3: h、 i、 j、 k、 1.
Step 12), select support to be not less than the sub-trajectory of minimum support threshold value from the multiple sub-trajectory, obtain the trajectory model of the historical track section.
First, support and the concept of trajectory model are introduced.
(1) support：Track《Support be to include《Sub-trajectory percentage shared in historical track section.
(2) trajectory model：If support of some sub-trajectory in historical track section exceedes minimum support threshold value, the sub-trajectory is referred to as a trajectory model of the historical track section.
For example, table 1 is historical track section《Five sub-trajectories, if minimum support threshold value be 0.4.
Wherein, included in sub-trajectory 1,2,4<6, therefore, sub-trajectory<E, support sup e, f>) =3/5=0.6>0.4, therefore,<E, is a trajectory model of historical track section.Similarly, included in sub-trajectory 3,4,5<1) >, sub-trajectory<b,c >Support sup (<b,c>) =3/5=0.6>0.4, therefore,< b,c>Iii is historical track section《A trajectory model.I.e. the historical track section《Trajectory model be< e,f >With< b,c>.
Table 1
Numbering sub-trajectory
1 <a, c, e, f, g>
2 <e,
3 <b, c>
4 <e, b, c, b, d, ΐ>
Step S 142, calculates the similarity between the trajectory model, obtains the similarity between historical track section corresponding with the trajectory model.
The similarity between trajectory model is calculated in one embodiment of the invention, the longest common subsequence between two trajectory models is determined first, then, longest common subsequence ratio shared in two trajectory models respectively is calculated, then calculates two being averaged for ratio and is worth to the similarity of two trajectory models.
In another embodiment of the present invention, step S 142 can include step 21) -23)：
Step 21), determine the longest common subsequence of two trajectory models；
Step 22), with reference to the position continuity parameter of trajectory model, calculate longest common subsequence ratio shared in two trajectory models respectively.
The continuity of position in two tracks is different, then may represent two kinds of entirely different behaviors.For example, a track is " office one>Nursery one>Dining room " a, it may be possible to family party；And if track is " office one>Dining room ", then be probably that one action is had a dinner party.As can be seen here, the continuity between two positions is critically important factor, therefore, considers that position continuity parameter is necessary completely in the process for calculating the similarity of trajectory model.
Give two trajectory models《And ^, it is assumed that《Longest common subsequence with ^ is θ, then Θ is in trajectory model《Middle proportion R (a, Θ) is as shown in Equation 1：
R(a, 6>)=(formula 1)
Wherein, | α | represent trajectory model《The quantity of middle position, | θ | represent the quantity of position in longest common subsequence Θ, h}Represent the continuity parameter of two positions.Μ ^, θ in formula 1；) as shown in Equation 2：
In formula 1/z ,=eδ】The continuity between two positions is represented, as shown in Equation 3:
(formula 3)> 1, 6>.—！^ and ^, ^ matching
U, v in formula 3 represent a respectivelyu, position in trajectory model, | u-v | represent the interval between two positions.For example, trajectory model is：<A, b, c, d>If, auFor b, it is（1, then u=2, v=4, then | u-v |=2, represent the interval between position b and d.For example, trajectory model： a— >b— >c— >d— >E, trajectory model： a— >c— >e— >f— >The longest common subsequence Θ of g a sums for a->c—>e}.
According to formula 1- formula 3, calculating obtains Θ and existed《Middle proportion R (a, ^)=(1+e- 1+1/5- 1) / 5；Calculating obtains Θ in middle proportion R (A ^> = (l + l + i;)/5, it can be seen that, ^, and ^ ^) numerical value differ.
From《Knowable to position sequence with, for《For, before a place of arrival c of place, centre also have passed through place b, and then be that, from the direct place of arrival c of place a, centre is without by other places for.
Step 23), calculate the longest common subsequence respectively in described two trajectory models proportion average value, obtain the similarity between described two trajectory models.
According to ratio R (a, Θ) shared in the trajectory model longest common subsequence Θ and(β, Θ), calculate two trajectory models between similarity sim a, β), sim (a, be 0 " and middle proportion average value, as shown in Equation 4：
sim(a^i ± m i. (formulas4 )Step S143, according to the similarity between historical track section, similarity is met mono- track fragment group of historical track Duan Juwei of predetermined threshold value.
The similarity between the trajectory model of two historical track sections is calculated according to above-mentioned similarity calculating method, it is used as the similarity between two historical track sections, according to the similarity between historical track section, whole historical track sections is clustered using clustering algorithm, mono- track fragment group of historical track Duan Juwei with similar trajectory model.Historical track section in the fragment group of each track is similar, and each user may be divided into different track fragment groups in historical track section not in the same time, and the historical track of different user section may be divided into same track fragment group.
The Similarity Measure mode for the historical track section that the present embodiment is provided, trajectory model is extracted from the historical track section of mobile terminal, the similarity of trajectory model is calculated as the similarity between corresponding historical track section, the data volume of the trajectory model extracted is far smaller than the data volume of historical track section, therefore, calculating data volume can be greatly reduced by calculating the similarity between trajectory model, and the resource saved inside the processing unit taken can be reduced to processing unit performance
Requirement.And, the present embodiment is in the similarity between calculating trajectory model, it is considered to the continuity of position in trajectory model, that is, considers the behavior of user, the similarity for so calculating obtained trajectory model is more accurate, and the user behavior similitude of similar historical track section is bigger.
Fig. 5 is referred to, is shown in the method flow diagram of step S130 shown in Fig. 1, the target trajectory fragment group comprising the corresponding historical track section of destination mobile terminal, and the corresponding historical track section of other mobile terminals.
As shown in figure 5, step S130 may comprise steps of：
S131, according to the corresponding historical track section of destination mobile terminal in the target trajectory fragment group, is predicted to next position of the destination mobile terminal after current track segment, obtains the first information of forecasting.First information of forecasting includes predicted position and corresponding first probable value.
S132, according to the corresponding historical track section of other mobile terminals in the target trajectory fragment group, is predicted to next position of destination mobile terminal, obtains the second information of forecasting.Second information of forecasting includes predicted position and corresponding second probable value.
S133, merges first information of forecasting and the second information of forecasting, determines next position that the maximum predicted position of probable value is destination mobile terminal.
In one embodiment of the invention, the first information of forecasting and the second information of forecasting are merged, can be in the following way：The corresponding probable value of identical predicted position in first information of forecasting and the second information of forecasting is added up, total probable value of the predicted position is obtained.
For example, the first information of forecasting is< ( )、 ( L'2, P >, the second information of forecasting is< ( ,Ρ )、 ( LJ 2, P2 J )
>, wherein, L with！^ is same position, then the information of forecasting after merging is《 L + P )、 ( L'2, P^ )、 ( LJ 2, P2 J) >, found out from the information of forecasting maximum probable value it is corresponding predict the outcome, be used as next position of destination mobile terminal.
In another embodiment of the present invention, using corresponding first weight of first information of forecasting and the second weight of the second information of forecasting, first information of forecasting and second information of forecasting are merged.As shown in Fig. 6, step S133 may comprise steps of：
Step S1331, obtains corresponding first weight of first information of forecasting, and corresponding second weight of second information of forecasting.
First weight of the first information of forecasting is ξ, and the second weight of the second information of forecasting is（1_ ξ), wherein, ξ is more than 0 and less than 1, is predicted the outcome in order that the historical track section of the more partial destination mobile terminal itself that predicts the outcome after merging is corresponding, therefore, it can setting 0. 5< ξ < 1.
Step S1332, by the first probable value of first information of forecasting and first multiplied by weight, obtains the first Weight prediction information.
It is assumed that the first information of forecasting that the historical track section of the destination mobile terminal in target trajectory fragment group is obtained is ＜ (), (υ2,ρ >, then the first Weight prediction information is ＜ (, ξ-ρ), (υ2,ξ-ρ >。
Step S1333, by the second probable value of second information of forecasting and second multiplied by weight, obtains the second Weight prediction information.
It is assumed that the historical track section of other mobile terminals in target trajectory fragment group obtains the second information of forecasting<
( ,P )、 (LJ 2,P2 J) >, then the second Weight prediction information be<
(¾,(1-ξ)·Ρ2" >。
Wherein, step S1332 and step S1333 execution sequence can be exchanged, for example, step S1333 can be first carried out, then perform step S1332, the present invention is not intended to limit to this.
Step S1334, merging is overlapped by the corresponding probable value of identical predicted position in the first Weight prediction information and the second Weight prediction information, obtains merging information of forecasting.
Assuming that in L and the second information of forecasting in the first information of forecasting for same position, i.e. L=I^, then the first Weight prediction information and the second Weight prediction information merge into ＜（L,
(υ2,ξ-ρ ,
(¾,(1-ξ)·Ρ2" >
Step S1335, regard the maximum predicted position of probable value in the merging information of forecasting as next position of destination mobile terminal.
Compare the size for merging the probable value in information of forecasting, the maximum predicted position of probable value predicting the outcome for the next position of destination mobile terminal.
The method of next position of the prediction mobile terminal that the present embodiment is provided after current track segment, one group of information of forecasting is obtained according to the historical track of destination mobile terminal in target trajectory fragment group, and, the historical track section of other terminals in target trajectory fragment group obtains another group of information of forecasting, the corresponding probability of predicted position in two groups of information of forecastings is merged with reference to the weight of information of forecasting, then probable value is compared, the maximum predicted position of probable value is predicting the outcome for next position of destination mobile terminal.With reference to weight, the information of forecasting of destination mobile terminal and the information of forecasting of other mobile terminals can be made to merge according to a certain percentage, weight be set according to the importance of information of forecasting, so as to improve the accuracy rate predicted the outcome.
Corresponding to above-mentioned embodiment of the method, present invention also provides device embodiment.
Fig. 7 is referred to, a kind of block diagram of mobile terminal locations prediction meanss of the embodiment of the present disclosure is shown, the device is applied in wireless network, as shown in fig. 7, described device can include：Receiving unit 110 and processing unit 120.
Receiving unit 110 is configured as receiving the track fragment group after the historical track section cluster to multiple mobile terminals, and the historical track section is divided according to the historical track information of mobile terminal to be obtained.
The receiving unit 110 can be the structure that network element etc. has certain transfer function.
Processing unit 120 is configured as from the track fragment group, obtains the current track segment with destination mobile terminal
Similar target trajectory fragment group；And, according to the target trajectory fragment group, determine next position of the destination mobile terminal after the current track segment.
In one embodiment of the invention, when processing unit 120 obtains the target trajectory fragment group similar to the current track segment of destination mobile terminal from the fragment group of track, specifically it is configurable to：The current track segment of destination mobile terminal is obtained, whether within a preset range similarity between the current track segment and track fragment group is judged, if within a preset range, it is target trajectory fragment group to determine the track fragment group.
In another embodiment of the present invention, processing unit 120 according to the target trajectory fragment group, is determining that the destination mobile terminal, at next position after the current track segment, is specifically configurable to：
According to the corresponding historical track section of destination mobile terminal in the target trajectory fragment group, destination mobile terminal is predicted in next position of the current track segment, the first information of forecasting is obtained, first information of forecasting includes predicted position and corresponding first probable value；
According to the corresponding historical track section of other mobile terminals in the target trajectory fragment group, next position of the destination mobile terminal after current track segment is predicted, the second information of forecasting is obtained, second information of forecasting includes predicted position and corresponding second probable value；
Merge first information of forecasting and the second information of forecasting, determine next position that the maximum predicted position of probable value is destination mobile terminal.
The processing unit 120 is merging first information of forecasting and the second information of forecasting, when the predicted position for determining probable value maximum is next position of destination mobile terminal, is specifically configurable to：
Obtain corresponding first weight of first information of forecasting, and corresponding second weight of second information of forecasting；
By the first probable value in first information of forecasting and first multiplied by weight, the first Weight prediction information is obtained；
By the second probable value in second information of forecasting and second multiplied by weight, the second Weight prediction information is obtained；
The corresponding probable value of corresponding predicted position in the first Weight prediction information and the second Weight prediction information is overlapped merging, obtains merging information of forecasting；
It regard the maximum predicted position of probable value in the merging information of forecasting as next position of destination mobile terminal.
The processing unit 120 can be general processor（CPU), digital signal processor（DSP), application specific integrated circuit（ASIC), ready-made programmable gate array（) or other PLDs, discrete gate or transistor logic, discrete hardware components FPGA.It can realize or perform the disclosed each side in the embodiment of the present invention
Method, step and logic diagram.General processor can be microprocessor or any conventional processor etc..
The mobile terminal locations prediction meanss that the present embodiment is provided, are received by receiving unit and the historical track section of multiple users are carried out clustering obtained track fragment group, wherein, the historical track section of user is divided from the whole historical track information of user to be obtained.Then, the target trajectory fragment group similar to the current track segment of targeted customer is obtained from the fragment group of track, finally, the orbit segment in target trajectory fragment group is predicted to next position of targeted customer.Historical track information is divided into multiple historical track sections, each historical track section is a part for historical track information, therefore, if sometime the track of user is changed, the situation of change of track can be captured quickly from historical track section, so as to improve the accuracy rate predicted the outcome.And, the corresponding historical track information of user is divided into multiple historical track sections, judge the similitude between orbit segment, so can trickleer, more accurately capture the similitude between the historical track of user, can further improve the accuracy rate of position prediction result.
In another embodiment of the present invention, processing unit 120 is additionally configured to, according to the similarity between historical track section, cluster historical track section using clustering algorithm, obtaining track fragment group, there is provided to the receiving unit 110.
In one embodiment of the invention, processing unit 120 is specifically configurable to when being clustered using clustering algorithm to historical track section：The trajectory model of each historical track section is obtained respectively；The similarity between the trajectory model is calculated, the similarity between historical track section corresponding with the trajectory model is obtained；According to the similarity between historical track section, similarity is met to mono- track fragment group of historical track Duan Juwei of predetermined threshold value.Historical track section in the fragment group of each track is similar, and each user corresponding historical track section in different time sections may be assigned in different track fragment groups, and the historical track of different user section may be assigned in same track fragment group.
In one embodiment of the invention, processing unit 120 is specifically configurable to when obtaining the trajectory model of each historical track section respectively：Extracted sequentially in time from each historical track section and obtain multiple sub-trajectories, select support to be not less than the sub-trajectory of minimum support threshold value from the multiple sub-trajectory, obtain the trajectory model of the historical track section.
In one embodiment of the invention, processing unit 120 is specifically configurable in the similarity between calculating the corresponding trajectory model of two historical track sections：Determine the longest common subsequence between two trajectory models, with reference to the position continuity parameter of trajectory model, calculate longest common subsequence ratio shared in two trajectory models respectively, calculate again the longest common subsequence respectively in described two trajectory models proportion average value, the similarity between described two trajectory models is obtained, the similarity between trajectory model is regard as the similarity between corresponding historical track section.
The predicted position device for the mobile terminal that the present embodiment is provided, track is extracted from the historical track section of mobile terminal
Pattern, the similarity of trajectory model is calculated as the similarity between corresponding historical track section, the data volume of the trajectory model extracted is far smaller than the data volume of historical track section, therefore, the similarity calculated between trajectory model can greatly reduce calculating data volume, the resource saved inside the processing unit taken, can reduce the requirement to processing unit performance.And, the present embodiment is in the similarity between calculating historical track section, it is considered to the continuity of position in trajectory model, that is, considers the behavior of user, the similarity for so calculating obtained trajectory model is more accurate, and the user behavior similitude of similar historical track section is bigger.
Each embodiment in this specification is described by the way of progressive, and identical similar part is mutually referring to what each embodiment was stressed is the difference with other embodiment between each embodiment.For device or system embodiment, because it is substantially similar to embodiment of the method, so describing fairly simple, the relevent part can refer to the partial explaination of embodiments of method.Apparatus and system embodiment described above is only schematical, the wherein described unit illustrated as separating component can be or may not be physically separate, the part shown as unit can be or may not be physical location, a place can be located at, or can also be distributed on multiple NEs.Some or all of module therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.Those of ordinary skill in the art are without creative efforts, you can to understand and implement.
The present invention can be described in the general context of computer executable instructions, such as program module.Usually, program module includes execution particular task or the routine for realizing particular abstract data type, program, object, component, data structure etc..The present invention can also be put into practice in a distributed computing environment, and in these DCEs, task is performed by the remote processing devices connected by communication network.In a distributed computing environment, program module can be located at including in the local and remote computer-readable storage medium including storage device.
It should be noted that, herein, the relational terms of such as " first " and " second " or the like are used merely to make a distinction an entity or operation with another entity or operation, and not necessarily require or imply between these entities or operation there is any this actual relation or order.And, term " including ", " including " or any other variant thereof is intended to cover non-exclusive inclusion, so that process, method, article or equipment including a series of key elements not only include those key elements, but also other key elements including being not expressly set out, or also include for this process, method, article or the intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence " including one ... ", it is not excluded that also there is other identical element in the process including the key element, method, article or equipment.
Described above is only the embodiment of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; some improvements and modifications can also be made, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (16)
- Claim1st, a kind of mobile terminal locations Forecasting Methodology, it is characterised in that including：The track fragment group after the historical track section cluster to multiple mobile terminals is obtained, the historical track section is divided according to the historical track information of mobile terminal to be obtained；From the track fragment group, the target trajectory fragment group similar to the current track segment of destination mobile terminal is obtained；According to the target trajectory fragment group, next position of the destination mobile terminal after the current track segment is determined.2nd, according to the method described in claim 1, it is characterised in that methods described also includes：According to the similarity between historical track section, historical track section is clustered using clustering algorithm, track fragment group is obtained.3rd, method according to claim 2, it is characterised in that according to the similarity between historical track section, clustered using clustering algorithm to historical track section, including：The trajectory model of each historical track section is obtained respectively；The similarity between the trajectory model is calculated, the similarity between historical track section corresponding with the trajectory model is obtained；According to the similarity between historical track section, similarity is met to mono- track fragment group of historical track Duan Juwei of predetermined threshold value.4th, method according to claim 3, it is characterised in that obtain the trajectory model of each historical track section respectively, including：Extracted sequentially in time from each historical track section and obtain multiple sub-trajectories；Select support to be not less than the sub-trajectory of minimum support threshold value from the multiple sub-trajectory, obtain the trajectory model of the historical track section.5th, method according to claim 3, it is characterised in that calculate the similarity between the trajectory model, including：Determine the longest common subsequence between two trajectory models；With reference to the position continuity parameter of trajectory model, longest common subsequence ratio shared in two trajectory models respectively is calculated；Calculate the longest common subsequence respectively in described two trajectory models proportion average value, obtain the similarity between described two trajectory models.6th, the method according to claim any one of 1-5, it is characterised in that from the track fragment group, obtains the target trajectory fragment group similar to the current track segment of destination mobile terminal, including： Obtain the current track segment of destination mobile terminal；Whether within a preset range similarity between the current track segment and track fragment group is judged, if within a preset range, it is target trajectory fragment group to determine the track fragment group.7th, the method according to claim any one of 1-6, it is characterised in that according to the target trajectory fragment group, determines next position of the destination mobile terminal after the current track segment, including：According to the corresponding historical track section of destination mobile terminal in the target trajectory fragment group, destination mobile terminal is predicted in next position of the current track segment, the first information of forecasting is obtained, first information of forecasting includes predicted position and corresponding first probable value；According to the corresponding historical track section of other mobile terminals in the target trajectory fragment group, next position of the destination mobile terminal after current track segment is predicted, the second information of forecasting is obtained, second information of forecasting includes predicted position and corresponding second probable value；Merge first information of forecasting and the second information of forecasting, determine next position that the maximum predicted position of probable value is destination mobile terminal.8th, method according to claim 7, it is characterised in that merge first information of forecasting and the second information of forecasting, determines next position that the maximum corresponding predicted position of probable value is destination mobile terminal, including：Obtain corresponding first weight of first information of forecasting, and corresponding second weight of second information of forecasting；By the first probable value in first information of forecasting and first multiplied by weight, the first Weight prediction information is obtained；By the second probable value in second information of forecasting and second multiplied by weight, the second Weight prediction information is obtained；The corresponding probable value of corresponding predicted position in the first Weight prediction information and the second Weight prediction information is overlapped merging, obtains merging information of forecasting；It regard the maximum predicted position of probable value in the merging information of forecasting as next position of destination mobile terminal.9th, a kind of mobile terminal locations prediction meanss, it is characterised in that including：Receiving unit, for receiving the track fragment group after the historical track section cluster to multiple mobile terminals, the historical track section is divided according to the historical track information of mobile terminal to be obtained；Processing unit, for from the track fragment group, obtaining the target trajectory fragment group similar to the current track segment of destination mobile terminal；And, according to the target trajectory fragment group, determine next position of the destination mobile terminal after the current track segment.10th, device according to claim 9, it is characterised in that： The processing unit is additionally operable to, and according to the similarity between historical track section, historical track section is clustered using clustering algorithm, track fragment group is obtained.11st, device according to claim 10, it is characterised in that：The processing unit, the trajectory model specifically for obtaining each historical track section respectively, calculates the similarity between the trajectory model, obtains the similarity between historical track section corresponding with the trajectory model；According to the similarity between historical track section, similarity is met to mono- track fragment group of historical track Duan Juwei of predetermined threshold value.12nd, device according to claim 11, it is characterised in that：The processing unit, multiple sub-trajectories are obtained specifically for being extracted sequentially in time from each historical track section, select support to be not less than the sub-trajectory of minimum support threshold value from the multiple sub-trajectory, obtain the trajectory model of the historical track section.13rd, device according to claim 11, it is characterised in that：The processing unit, specifically for determining the longest common subsequence between two trajectory models, with reference to the position continuity parameter of trajectory model, calculate longest common subsequence ratio shared in two trajectory models respectively, calculate the longest common subsequence respectively in described two trajectory models proportion average value, obtain the similarity between described two trajectory models.14th, the device according to claim any one of 9-13, it is characterised in that：The processing unit, current track segment specifically for obtaining destination mobile terminal, whether within a preset range similarity between the current track segment and track fragment group is judged, if within a preset range, it is target trajectory fragment group to determine the track fragment group.15th, the device according to claim any one of 9-14, it is characterised in that the processing unit specifically for：According to the corresponding historical track section of destination mobile terminal in the target trajectory fragment group, destination mobile terminal is predicted in next position of the current track segment, the first information of forecasting is obtained, first information of forecasting includes predicted position and corresponding first probable value；According to the corresponding historical track section of other mobile terminals in the target trajectory fragment group, next position of the destination mobile terminal after current track segment is predicted, the second information of forecasting is obtained, second information of forecasting includes predicted position and corresponding second probable value；Merge first information of forecasting and the second information of forecasting, determine next position that the maximum predicted position of probable value is destination mobile terminal.16th, device according to claim 15, it is characterised in that the processing unit specifically for：Obtain corresponding first weight of first information of forecasting, and corresponding second weight of second information of forecasting； By the first probable value in first information of forecasting and first multiplied by weight, the first Weight prediction information is obtained；By the second probable value in second information of forecasting and second multiplied by weight, the second Weight prediction information is obtained；The corresponding probable value of corresponding predicted position in the first Weight prediction information and the second Weight prediction information is overlapped merging, obtains merging information of forecasting；It regard the maximum predicted position of probable value in the merging information of forecasting as next position of destination mobile terminal.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2014/079655 WO2015188324A1 (en) | 2014-06-11 | 2014-06-11 | Method and apparatus for predicting location of mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105409306A true CN105409306A (en) | 2016-03-16 |
| CN105409306B CN105409306B (en) | 2019-01-18 |
Family
ID=54832704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201480009660.4A Active CN105409306B (en) | 2014-06-11 | 2014-06-11 | Mobile terminal locations prediction technique and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105409306B (en) |
| WO (1) | WO2015188324A1 (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107655490A (en) * | 2017-08-29 | 2018-02-02 | 重庆邮电大学 | Hotspot path based on mobile subscriber track segmentation and most hot search finds method |
| CN108289279A (en) * | 2018-01-30 | 2018-07-17 | 浙江省公众信息产业有限公司 | Processing method, device and the computer readable storage medium of location information |
| CN109041218A (en) * | 2018-09-25 | 2018-12-18 | 广东小天才科技有限公司 | A kind of method and Intelligent hardware for predicting user location |
| CN109041217A (en) * | 2018-09-21 | 2018-12-18 | 北京邮电大学 | A kind of classification mobility prediction technique in heterogeneous network |
| CN109388757A (en) * | 2018-10-10 | 2019-02-26 | 广州力挚网络科技有限公司 | A kind of hot topic track extraction method and device |
| CN110209560A (en) * | 2019-05-09 | 2019-09-06 | 北京百度网讯科技有限公司 | Data exception detection method and detection device |
| CN110825833A (en) * | 2019-11-11 | 2020-02-21 | 杭州数澜科技有限公司 | Method for predicting user moving track point |
| CN110928914A (en) * | 2018-08-30 | 2020-03-27 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN111339449A (en) * | 2020-03-24 | 2020-06-26 | 青岛大学 | User motion trajectory prediction method, device, equipment and storage medium |
| CN111723123A (en) * | 2019-03-20 | 2020-09-29 | 杭州海康威视数字技术股份有限公司 | Trajectory prediction method and apparatus, electronic device, and storage medium |
| CN111929715A (en) * | 2020-06-28 | 2020-11-13 | 杭州云起智慧校园科技有限公司 | Positioning method, device and equipment for school badge and storage medium |
| CN112116805A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视系统技术有限公司 | Method and device for determining specified driving route |
| CN112215429A (en) * | 2020-10-20 | 2021-01-12 | 清华大学 | Historical trajectory-based trajectory prediction method and device |
| CN112613673A (en) * | 2020-12-29 | 2021-04-06 | 北京梧桐车联科技有限责任公司 | Travel track determination method and device and computer readable storage medium |
| CN112667763A (en) * | 2020-12-29 | 2021-04-16 | 电子科技大学 | Trajectory prediction method based on self-adaptive timestamp and multi-scale feature extraction |
| CN112714398A (en) * | 2021-01-26 | 2021-04-27 | 上海明略人工智能(集团)有限公司 | Method, device and equipment for correcting positioning coordinate drift of indoor positioning system |
| CN113784362A (en) * | 2021-07-29 | 2021-12-10 | 三维通信股份有限公司 | Aerial base station deployment method, aerial base station deployment device, electronic device and storage medium |
| CN114584657A (en) * | 2022-02-28 | 2022-06-03 | 天翼安全科技有限公司 | Telephone number identification method, device, equipment and medium for abnormal communication |
| CN114756367A (en) * | 2022-04-15 | 2022-07-15 | 中国电信股份有限公司 | Service migration method, device, medium and electronic equipment |
| CN116558513A (en) * | 2023-07-06 | 2023-08-08 | 中国电信股份有限公司 | Indoor terminal positioning method, device, equipment and medium |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109768869B (en) * | 2017-11-06 | 2022-05-31 | 中国移动通信有限公司研究院 | Service prediction method, system and computer storage medium |
| CN109727141B (en) * | 2018-03-02 | 2021-06-04 | 中国平安人寿保险股份有限公司 | Information processing method, device and equipment based on vehicle moving card |
| FR3079309B1 (en) | 2018-03-21 | 2020-07-17 | Sigfox | METHOD AND SYSTEM FOR GEOLOCATION OF TERMINALS EVOLVING IN A GROUP |
| CN108566618B (en) * | 2018-04-04 | 2020-07-28 | 广州杰赛科技股份有限公司 | Method, device, equipment and storage medium for acquiring user residence law |
| CN111753214A (en) * | 2020-06-24 | 2020-10-09 | 平安科技（深圳）有限公司 | Data pushing method and system based on behavior track and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175253A (en) * | 2010-12-28 | 2011-09-07 | 清华大学 | Multi-hypothesis map matching method based on vehicle state transition |
| WO2011150971A1 (en) * | 2010-06-03 | 2011-12-08 | Sony Ericsson Mobile Communications Ab | Method and apparatus for location prediction |
| CN102984799A (en) * | 2012-11-27 | 2013-03-20 | 中国人民解放军信息工程大学 | Method and system for judging user positions |
| CN103747523A (en) * | 2014-01-14 | 2014-04-23 | 上海河广信息科技有限公司 | User position predicating system and method based on wireless network |
-
2014
- 2014-06-11 CN CN201480009660.4A patent/CN105409306B/en active Active
- 2014-06-11 WO PCT/CN2014/079655 patent/WO2015188324A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011150971A1 (en) * | 2010-06-03 | 2011-12-08 | Sony Ericsson Mobile Communications Ab | Method and apparatus for location prediction |
| CN102175253A (en) * | 2010-12-28 | 2011-09-07 | 清华大学 | Multi-hypothesis map matching method based on vehicle state transition |
| CN102984799A (en) * | 2012-11-27 | 2013-03-20 | 中国人民解放军信息工程大学 | Method and system for judging user positions |
| CN103747523A (en) * | 2014-01-14 | 2014-04-23 | 上海河广信息科技有限公司 | User position predicating system and method based on wireless network |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107655490A (en) * | 2017-08-29 | 2018-02-02 | 重庆邮电大学 | Hotspot path based on mobile subscriber track segmentation and most hot search finds method |
| CN107655490B (en) * | 2017-08-29 | 2020-03-17 | 重庆邮电大学 | Hot spot path discovery method based on mobile user track segmentation and hottest search |
| CN108289279A (en) * | 2018-01-30 | 2018-07-17 | 浙江省公众信息产业有限公司 | Processing method, device and the computer readable storage medium of location information |
| CN110928914A (en) * | 2018-08-30 | 2020-03-27 | 百度在线网络技术（北京）有限公司 | Method and apparatus for outputting information |
| CN109041217A (en) * | 2018-09-21 | 2018-12-18 | 北京邮电大学 | A kind of classification mobility prediction technique in heterogeneous network |
| CN109041217B (en) * | 2018-09-21 | 2020-01-10 | 北京邮电大学 | Hierarchical mobility prediction method in heterogeneous network |
| CN109041218A (en) * | 2018-09-25 | 2018-12-18 | 广东小天才科技有限公司 | A kind of method and Intelligent hardware for predicting user location |
| CN109041218B (en) * | 2018-09-25 | 2020-08-11 | 广东小天才科技有限公司 | Method for predicting user position and intelligent hardware |
| CN109388757A (en) * | 2018-10-10 | 2019-02-26 | 广州力挚网络科技有限公司 | A kind of hot topic track extraction method and device |
| CN109388757B (en) * | 2018-10-10 | 2021-11-02 | 广州力挚网络科技有限公司 | Hot track extraction method and device |
| CN111723123A (en) * | 2019-03-20 | 2020-09-29 | 杭州海康威视数字技术股份有限公司 | Trajectory prediction method and apparatus, electronic device, and storage medium |
| CN110209560A (en) * | 2019-05-09 | 2019-09-06 | 北京百度网讯科技有限公司 | Data exception detection method and detection device |
| CN110209560B (en) * | 2019-05-09 | 2023-05-12 | 北京百度网讯科技有限公司 | Data anomaly detection method and detection device |
| CN112116805A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视系统技术有限公司 | Method and device for determining specified driving route |
| CN110825833A (en) * | 2019-11-11 | 2020-02-21 | 杭州数澜科技有限公司 | Method for predicting user moving track point |
| CN110825833B (en) * | 2019-11-11 | 2022-05-17 | 杭州数澜科技有限公司 | Method for predicting user moving track point |
| CN111339449A (en) * | 2020-03-24 | 2020-06-26 | 青岛大学 | User motion trajectory prediction method, device, equipment and storage medium |
| CN111929715A (en) * | 2020-06-28 | 2020-11-13 | 杭州云起智慧校园科技有限公司 | Positioning method, device and equipment for school badge and storage medium |
| CN112215429A (en) * | 2020-10-20 | 2021-01-12 | 清华大学 | Historical trajectory-based trajectory prediction method and device |
| CN112613673A (en) * | 2020-12-29 | 2021-04-06 | 北京梧桐车联科技有限责任公司 | Travel track determination method and device and computer readable storage medium |
| CN112667763A (en) * | 2020-12-29 | 2021-04-16 | 电子科技大学 | Trajectory prediction method based on self-adaptive timestamp and multi-scale feature extraction |
| CN112613673B (en) * | 2020-12-29 | 2024-05-14 | 北京梧桐车联科技有限责任公司 | Travel track determining method and device and computer readable storage medium |
| CN112714398B (en) * | 2021-01-26 | 2024-03-29 | 上海明略人工智能(集团)有限公司 | Method, device and equipment for correcting positioning coordinate drift of indoor positioning system |
| CN112714398A (en) * | 2021-01-26 | 2021-04-27 | 上海明略人工智能(集团)有限公司 | Method, device and equipment for correcting positioning coordinate drift of indoor positioning system |
| CN113784362A (en) * | 2021-07-29 | 2021-12-10 | 三维通信股份有限公司 | Aerial base station deployment method, aerial base station deployment device, electronic device and storage medium |
| CN114584657A (en) * | 2022-02-28 | 2022-06-03 | 天翼安全科技有限公司 | Telephone number identification method, device, equipment and medium for abnormal communication |
| CN114756367A (en) * | 2022-04-15 | 2022-07-15 | 中国电信股份有限公司 | Service migration method, device, medium and electronic equipment |
| CN114756367B (en) * | 2022-04-15 | 2024-02-23 | 中国电信股份有限公司 | Service migration method, device, medium and electronic equipment |
| CN116558513B (en) * | 2023-07-06 | 2023-10-03 | 中国电信股份有限公司 | Indoor terminal positioning method, device, equipment and medium |
| CN116558513A (en) * | 2023-07-06 | 2023-08-08 | 中国电信股份有限公司 | Indoor terminal positioning method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2015188324A1 (en) | 2015-12-17 |
| CN105409306B (en) | 2019-01-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105409306A (en) | Method and apparatus for predicting location of mobile terminal | |
| CN108875007B (en) | method and device for determining interest point, storage medium and electronic device | |
| US9519684B2 (en) | User recommendation method and a user recommendation system using the same | |
| JP6225257B2 (en) | Interest point clustering method and related apparatus | |
| CN104102719B (en) | The method for pushing and device of a kind of trace information | |
| CN103795613B (en) | Method for predicting friend relationships in online social network | |
| US20140258281A1 (en) | Method And Server For Searching For Nearby User In Social Networking Services | |
| CN104680250B (en) | A kind of position prediction system | |
| CN108574933B (en) | User track recovery method and device | |
| US11663282B2 (en) | Taxonomy-based system for discovering and annotating geofences from geo-referenced data | |
| KR20150031309A (en) | Dynamic language model | |
| CN108834077B (en) | Tracking area division method and device based on user movement characteristics and electronic equipment | |
| CN108259546A (en) | Information push method, equipment and programmable device | |
| US20160275533A1 (en) | Segment Membership Determination for Content Provisioning | |
| US20180165708A1 (en) | Notification Control based on Location, Activity, and Temporal Prediction | |
| CN110267206A (en) | User location prediction technique and device | |
| JPWO2018186235A1 (en) | Location popularity estimation system | |
| CN111988168B (en) | Edge service deployment method and device and electronic equipment | |
| JP2015170338A (en) | Residence point extraction method, residence point extraction device and residence point extraction program | |
| US10444062B2 (en) | Measuring and diagnosing noise in an urban environment | |
| US20150169794A1 (en) | Updating location relevant user behavior statistics from classification errors | |
| CN106161553B (en) | Community application information pushing method and system | |
| CN112214677B (en) | Point of interest recommendation method and device, electronic equipment and storage medium | |
| CN110795519A (en) | Markov model and probability statistics-based position prediction method and readable storage medium | |
| CN110958565B (en) | Method and device for calculating signal distance, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |