CN106294485B - Determine the method and device in significant place - Google Patents
Determine the method and device in significant place Download PDFInfo
- Publication number
- CN106294485B CN106294485B CN201510307160.5A CN201510307160A CN106294485B CN 106294485 B CN106294485 B CN 106294485B CN 201510307160 A CN201510307160 A CN 201510307160A CN 106294485 B CN106294485 B CN 106294485B
- Authority
- CN
- China
- Prior art keywords
- attribute
- significant place
- place
- potential
- conditional
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides the method and devices in the significant place of determination, are related to mobile internet technical field.It is invented to solve the problems, such as in the prior art lower to the accuracy of identification in significant place.The method comprising the steps of one: determining that significant place determines attribute and step 2 according to sample position track: determining that attribute determines the significant place in location track to be processed according to significant place.Wherein, step 1 specifically includes: determining the potential significant place on sample position track；The value for obtaining corresponding first attribute set in each potential significant place, obtains attribute information table；According to attribute information table, significant place is chosen from the first attribute set using default Feature Selection algorithm and determines attribute；Obtain the threshold range that significant place determines attribute.Step 2 specifically includes: determining at least one potential significant place in location track to be processed；Significant place is determined that potential significant place of the value of attribute in threshold range is determined as significant place.
Description
Technical field
The present invention relates to mobile internet technical fields, more particularly to determine the method and device in significant place.
Background technique
Prevailing with mobile Internet, the behavioural analysis of mobile terminal user has become the focus of research.Wherein, with
In the behavioural analysis of family, the position analysis tool of user has very important significance, and can be used based on the position acquisition of mobile terminal user
The more position of family access times namely significant place are to provide more intelligent clothes for user when user is in significant place
Business.
A kind of determination method in significant place is provided in the prior art, during the realization of this method, first to obtaining
The location track got is pre-processed, and rejecting is clearly not the point in significant place, then uses clustering algorithm to remaining point
Handled each point the point labeled as noise spot and significant place, labeled as significant place be determine significantly
Point.There may be judge non-significant place by accident in the identification process in significant place for the method in the existing significant place of this determination
The problem of for significant place, thus the prior art is lower to the accuracy of identification in significant place.
Summary of the invention
The present invention provides a kind of method and device for determining significant place, in the prior art to significant place to solve
The lower problem of resolution.
In order to achieve the above objectives, the present invention adopts the following technical scheme:
In a first aspect, the present invention provides a kind of methods for determining significant place, which comprises according to sample position
Track determines that significant place determines attribute and determines according to the significant place decision attribute significant in location track to be processed
Place；
Wherein, described to determine that significant place determines attribute according to sample position track, it specifically includes:
At least one potential significant place on the sample position track is obtained by default clustering algorithm；
The value for obtaining corresponding first attribute set in each potential significant place, obtains attribute information table, and described
One attribute set includes the conditional attribute and a decision attribute of predetermined number；
According to the attribute information table, chosen significantly from first attribute set using default Feature Selection algorithm
Point determines attribute；
Obtain the threshold range that the significant place determines attribute；
It is described to determine that attribute determines the significant place in location track to be processed according to the significant place, it specifically includes:
At least one potential significant place in the location track to be processed is obtained by the default clustering algorithm；
The significant place is determined that potential significant place of the value of attribute in the threshold range is determined as significantly
Point.
With reference to first aspect, described according to the attribute information table in the first implementation of first aspect, it uses
Default Feature Selection algorithm chooses significant place from first attribute set and determines attribute, specifically includes:
There is fault tolerance using what default Feature Selection algorithm calculated each conditional attribute in first attribute set
P norm value；
The corresponding conditional attribute of maximum value in all values of P norm described in being calculated with fault tolerance is true
It is set to significant place and determines attribute.
The first implementation with reference to first aspect, it is described using pre- in second of implementation of first aspect
If Feature Selection algorithm calculates the value of the P norm with fault tolerance of each conditional attribute in first attribute set, tool
Body includes:
Using the first condition attribute in first attribute set as attribute to be assessed, remaining conditional attribute is constituted
Set is determined as the second attribute set, and the first condition attribute is any conditional attribute；
Game playing algorithm is selected using the user property based on fuzzy entropy, successively judges the attribute to be assessed described second
Whether the sharing in game for each destination subset in attribute set wins, and obtains judgement knot corresponding with each destination subset
Fruit, the destination subset include at least two conditional attributes；
According to all judging results, the value of the P norm with fault tolerance of the attribute to be assessed is calculated.
With reference to first aspect, in the third implementation of first aspect, the default clustering algorithm includes apart from threshold
Value, points three parameters of threshold value and time threshold；
It is described to be obtained in the sample position track or the location track to be processed at least by default clustering algorithm
One potential significant place, specifically includes:
Place not labeled in the location track is used as to starting point, the label include be labeled as it is potential significantly
Point or noise spot；
Search the target point for being less than or equal to the distance threshold at a distance from the starting point；
If the quantity of the target point found is more than or equal to the points threshold value, and each target point and institute
The time interval for stating starting point is all larger than the time threshold, then the starting point and all target points is determined as one
Cluster, and the starting point is labeled as potential significant place；
After all the points in the cluster are marked, the place that successively marks other not to be labeled.
With reference to first aspect or the first implementation of first aspect, second of implementation, the third realization side
Any one implementation in formula includes speed in first attribute set in the 4th kind of implementation of first aspect
Record number in the sample position track of degree, acceleration, potential significant place, the potential significant place are in the sample
The time period of stay and Orientation differences standard deviation of the number of days, the potential significant place that occur in this location track.
Second aspect, the present invention also provides a kind of device for determining significant place, described device includes:
Processing module, for by preset clustering algorithm obtain on the sample position track at least one is potential significant
Place；
Module is obtained, for obtaining the value of corresponding first attribute set in each potential significant place, obtains attribute
Information table, first attribute set include the conditional attribute and a decision attribute of predetermined number；
The processing module, is also used to according to the attribute information table, using default Feature Selection algorithm from described first
Significant place is chosen in attribute set determines attribute；
The acquisition module is also used to obtain the threshold range that the significant place determines attribute；
The processing module is also used to obtain in the location track to be processed at least by the default clustering algorithm
One potential significant place；
The processing module is also used to determining the significant place into that the value of attribute is potential aobvious in the threshold range
Touchdown point is determined as significant place.
In conjunction with second aspect, in the first implementation of second aspect, the acquisition module is specifically used for using pre-
If Feature Selection algorithm calculates the value of the P norm with fault tolerance of each conditional attribute in first attribute set；
The corresponding conditional attribute of maximum value in all values of P norm described in being calculated with fault tolerance is true
It is set to significant place and determines attribute.
In conjunction with the first implementation of second aspect, in second of implementation of second aspect, the acquisition mould
Block, also particularly useful for:
Using the first condition attribute in first attribute set as attribute to be assessed, remaining conditional attribute is constituted
Set is determined as the second attribute set, and the first condition attribute is any conditional attribute；
Game playing algorithm is selected using the user property based on fuzzy entropy, successively judges the attribute to be assessed described second
Whether the sharing in game for each destination subset in attribute set wins, and obtains judgement knot corresponding with each destination subset
Fruit, the destination subset include at least two conditional attributes；
According to all judging results, the value of the P norm with fault tolerance of the attribute to be assessed is calculated.
In conjunction with second aspect, in the third implementation of second aspect, the default clustering algorithm includes apart from threshold
Value, points three parameters of threshold value and time threshold；
The processing module, is specifically used for:
Place not labeled in the location track is used as to starting point, the label include be labeled as it is potential significantly
Point or noise spot；
Search the target point for being less than or equal to the distance threshold at a distance from the starting point；
If the quantity of the target point found is more than or equal to the points threshold value, and each target point and institute
The time interval for stating starting point is all larger than the time threshold, then the starting point and all target points is determined as one
Cluster, and the starting point is labeled as potential significant place；
After all the points in the cluster are marked, the place that successively marks other not to be labeled.
In conjunction with the first of second aspect or second aspect implementation, second implementation, the third realization side
Any one implementation in formula, in the 4th kind of implementation of second aspect, described for obtaining module and obtaining
It include record number in the sample position track of speed, acceleration, potential significant place in one attribute set, described latent
The time period of stay and orientation of the number of days, the potential significant place that occur in the sample position track in significant place
Change standard deviation.
The method and device in the significant place of determination provided in an embodiment of the present invention, passes through clustering algorithm for sample position track
It obtains potential significant place, then goes out the decision attribute and its threshold range in significant place by Feature Selection algorithm picks, so
Location track to be processed is handled again afterwards, by the decision in significant place in the potential significant place in location track to be processed
The potential significant place that the value of attribute meets threshold range is determined as significant place, and will be selected in the prior art by clustering algorithm
The point selected out is compared directly as significant place, and the present invention after clustering algorithm due to using Feature Selection algorithm, thus energy
The False Rate in significant place is enough reduced, and then can be improved the accuracy for determining significant place.
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 flow diagram for the method for determining significant place provided in an embodiment of the present invention；
Fig. 2 be it is provided in an embodiment of the present invention it is a kind of by preset clustering algorithm determine in location track it is potential significantly
The flow diagram of the method for point；
Fig. 3 is aobvious using default Feature Selection algorithm picks to be provided in an embodiment of the present invention a kind of according to attribute information table
Touchdown point determines the flow diagram of the method for attribute；
Fig. 4 is a kind of value for the P norm with fault tolerance for calculating each conditional attribute provided in an embodiment of the present invention
Method flow diagram；
Fig. 5 is a kind of structural schematic diagram for the device for determining significant place provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of another device for determining significant place provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the present embodiment, the technical solution in the present embodiment is clearly and completely described,
Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based in the present invention
Embodiment, every other embodiment obtained by those of ordinary skill in the art without making creative efforts, all
Belong to the scope of protection of the invention.
The embodiment of the invention provides a kind of methods for determining significant place, which comprises according to sample position rail
Mark determines that significant place determines attribute and to determine that attribute determines according to the significant place significant in location track to be processed
Point.
Wherein, the sample position track is to have had determined which place is the location track in significant place.It is described to
Handling location track is to have not determined the location track in significant place.The sample position track and the location track to be processed
The location information in a period of time where various time points mobile terminal is contained as a kind of location track to be passed through in other words
The route crossed.In general, having GPS sensor on existing mobile terminal, the mobile terminal of user is can receive and recorded
Continuous GPS latitude and longitude coordinates point is to form location track signified in GPS track i.e. the embodiment of the present invention.
" the determining that significant place determines attribute according to sample position track " specifically includes following step 101 to step
104；" the determining that attribute determines the significant place in location track to be processed according to the significant place " specifically includes following
Step 105 and 106.
As shown in Figure 1, the method in the significant place of determination provided in an embodiment of the present invention specifically includes:
101: at least one potential significant place on the sample position track is obtained by default clustering algorithm.
Wherein, the basic object of clustering algorithm is that will meet point one class of formation of specified conditions, common clustering algorithm
Including density-based spatial clustering algorithm (Density-Based Spatial Clustering of Applications
With Noise, abbreviation DBSCAN) algorithm etc..
Point in location track can be divided into noise spot and potential significant according to its probability for being likely to become significant place
Point, signified potential significant place are the biggish point of probability as significant place.
102: obtaining the value of corresponding first attribute set in each potential significant place, obtain attribute information table, institute
State the conditional attribute and a decision attribute that the first attribute set includes predetermined number.
Wherein, the value of each conditional attribute in the first attribute set and decision attribute can be by analyzing sample position track
It directly reads or is obtained after certain operation.Such as: when the record number in track is set as item in the potential place in place
When part attribute, it can potentially put appearance number by directly searching and obtain.For another example: when speed is a conditional attribute, In
It, can be by obtaining the pole including the potential significant place for some potential significant place after potential significant place has been determined
Segment path and the path corresponding time, the speed of the mobile terminal of this short time is obtained simultaneously by speed calculation formula
Using the speed as the speed in the potential significant place.
As an optional implementation, may include in first attribute set speed, acceleration, it is potential significantly
The day that point occurs in the sample position track in the record number in the sample position track, the potential significant place
The time period of stay and Orientation differences standard deviation in several, the described potential significant place totally 6 conditional attributes.Signified decision attribute
Refer to whether the potential significant place is significant place.
It include above-mentioned 6 items in the first attribute set table altogether to include 10 potential significant places in sample position track
For part attribute and 1 decision attribute, following table table one gives the corresponding attribute information table in potential significant place.
Table one: attribute information table
Wherein, if in significant place column, " 1 " represents the potential significant place as significant place, and " 0 " represents should
Potential significant place is not significant place.
Above-mentioned table one simply shows the way of realization of attribute information table, wherein the value of each conditional attribute can be according to reality
Situation obtains after obtaining.
103: according to the attribute information table, being chosen from first attribute set using default Feature Selection algorithm aobvious
Touchdown point determines attribute.
Wherein, signified default Feature Selection algorithm can be the P norm with fault tolerance.
104: obtaining the threshold range that the significant place determines attribute.
In a kind of specific implementation of this step, by obtain multiple places (both included non-significant place and also including
Significant place) the corresponding significant place determines the value of attribute；If significant place determines some section packet of the value of attribute
The number in the significant place contained is most, then the section is determined as the threshold range that significant place determines attribute.With by speed this
For one conditional attribute determines attribute as significant place, the determination process specifically:
Obtain the velocity amplitude in multiple places on sample position track；
Section comprising the largest number of velocity amplitudes in significant place is determined as to the threshold range of this conditional attribute of speed.
105: by the default clustering algorithm obtain in the location track to be processed at least one is potential significantly
Point.
106: the significant place is determined that potential significant place of the value of attribute in the threshold range is determined as showing
Touchdown point.
The method in the significant place of determination provided in an embodiment of the present invention is obtained by clustering algorithm sample position track latent
In significant place, then go out by Feature Selection algorithm picks the decision attribute and its threshold range in significant place, it is then right again
Location track to be processed is handled, by the decision attribute in significant place in the potential significant place in location track to be processed
The potential significant place that value meets threshold range is determined as significant place, and will be selected in the prior art by clustering algorithm
Point is compared directly as significant place, and the present invention after clustering algorithm due to using Feature Selection algorithm, it is thus possible to reduce
The False Rate in significant place, and then can be improved the accuracy for determining significant place.
It should be noted that determining attribute and the threshold of the decision attribute to improve the significant place of the embodiment of the present invention
It is worth the accuracy of the selection of range, it can be by obtaining multiple sample position tracks and using step 101 identical to step 104
Method obtains one corresponding with each sample position track threshold range for determining attribute and the decision attribute, then carries out
Final significant place, which is obtained, after analysis processing determines attribute and its threshold range.
A kind of implementation as the potential significant place in acquisition location track described in step 101 and step 105:
Signified default clustering algorithm is the variant of DBSCAN algorithm, the default clustering algorithm include distance threshold, points threshold value and when
Between three parameters of threshold value.
It is described to be obtained in the sample position track or the location track to be processed at least by default clustering algorithm
One potential significant place, as shown in Fig. 2, specifically including:
201: using the place not being labeled in the location track as starting point.
Wherein, the label includes being labeled as potential significant place or noise spot.
202: searching the target point for being less than or equal to the distance threshold at a distance from the starting point.
It illustrates as one, the value of the distance threshold can be 100m.
203: if the quantity of the target point found is more than or equal to the points threshold value, and each target point
It is all larger than the time threshold with the time interval of the starting point, then is determined as the starting point and all target points
One cluster, and the starting point is labeled as potential significant place.
It illustrates as one, which can be 5；The time threshold can be 10 minutes.
If being unsatisfactory for above-mentioned condition, the starting point is labeled as noise spot.
204: after all the points in the cluster are marked, the place that successively marks other not to be labeled.
Step 201 is repeated to step 203, successively all the points in cluster are handled, when all the points are marked in cluster
After having remembered (can be described as the cluster sufficiently to be extended), processing is marked to other unlabelled points.
This clustering algorithm used in the embodiment of the present invention is the variant of DBSCAN algorithm, it not only consider track midpoint and
The distance between point, and the distance between putting point is distance on track rather than the direct range of two points, so more
Close to real-life truth.And replace Minimum Area number to determine cluster using minimum time in cluster process, then
User equipment can be prevented simply because a certain cause specific, it has to stop short time herein, and significant place is caused to judge by accident.
As step 103 " according to the attribute information table, using default Feature Selection algorithm from first attribute set
A kind of specific implementation of the middle significant place decision attribute of selection ", as shown in figure 3, the process specifically includes:
301: there is tolerance using what default Feature Selection algorithm calculated each conditional attribute in first attribute set
The value of the P norm of ability.
302: the corresponding condition category of maximum value in all values of the P norm described in being calculated with fault tolerance
Property be determined as significant place and determine attribute.
Wherein, as shown in figure 4, in above-mentioned steps 301, the P norm with fault tolerance of each conditional attribute is calculated
The detailed process of value are as follows:
401: using the first condition attribute in first attribute set as attribute to be assessed, by remaining conditional attribute structure
At set be determined as the second attribute set, the first condition attribute is any conditional attribute.
402: selecting game playing algorithm using the user property based on fuzzy entropy, successively judge the attribute to be assessed described
Whether the sharing in game for each destination subset in the second attribute set wins, and obtains judgement corresponding with each destination subset
As a result, the destination subset includes at least two conditional attributes.
The basic principle of the realization process of this step is to be calculated using the user property selection game method based on fuzzy entropy
Conditional mutual information, judges whether attribute to be assessed wins in sharing in game for attribute set.
403: according to all judging results, calculating the value of the P norm with fault tolerance of the attribute to be assessed.
401 are repeated the above steps to step 403, the corresponding P norm with fault tolerance of each conditional attribute can be obtained
Value.
Assuming that sharing N-1 conditional attribute Ni and 1 decision attribute D in the first attribute set, potential location information is selected
Either condition attribute Ni in table is assessed as attribute to be assessed, then remaining N-2 conditional attribute constitutes the second attribute
Set.Second attribute set is corresponding with multiple subsets, any one for selecting in second attribute set contains at least two
The attribute set Si of conditional attribute, to assess in the situation known to conditional attribute Ni, attribute set Si and final decision attribute
Extent of information sharing.Its calculation formula is as follows:
MI(Si；D | Ni)=E (Si | Ni)-E (Si | D, Ni) (1)
Wherein, conditional entropy E (Si | Ni) is referred to as when known to Ni, the entropy of attribute set Si, E (Si | D, Ni) indicate to
When evaluation condition attribute Ni and decision attribute D are existed simultaneously, the entropy of attribute set Si.
If in formula (1), MI (Si；D | Ni) value be greater than 0, then explanation increases in the presence of the attribute Ni to be assessed
The information sharing of attribute set Si and decision attribute D claim Ni to win in sharing in game for attribute set Si.
According to the calculation method of formula (1), it is corresponding in each objective attribute target attribute subset can successively to obtain attribute Ni to be assessed
Whether sharing in game for Si wins.
In addition, conditional entropy E (Si | Ni) calculation method are as follows:
E (Si | Ni)=- (∑ log2(|[xi]|/n))/n (2)
Wherein, | [xi] |=∑ rij, rijFor any two conditional attribute value x in Si setiWith xjSimilarity relation, n is
The number of Si conditional attribute.rijFor example following formula (3) of calculation formula shown in:
Wherein, in formula (3), | | xi-xj| | it is the P norm with fault tolerance.
According to attribute to be assessed sharing whether to win in game and calculate attribute to be assessed in each objective attribute target attribute subset
The value of P norm (Banzhaf) with fault tolerance.
In formula (1), as MI (Si；D | Ni) be greater than 0, i.e. conditional attribute Ni wins in sharing in game for attribute set Si
When, count Δi(Si)=1, otherwise Δi(Si)=0.
Then the Banzhaf value calculating method of conditional attribute Ni is as follows:
The corresponding Banzhaf value of each conditional attribute is finally obtained, Banzhaf value is higher, illustrates it to attribute set
Contribution it is bigger.Select the corresponding conditional attribute of Banzhaf value peak as determine the most important attribute in significant place namely
Significant place determines attribute.
Since potential significant place is obtained by clustering algorithm, it is understood that there may be the sparse situation of sample, and this feature
With the P norm of fault tolerance used in extracting, the situation that more to cope with sample than traditional P norm sparse is kept away simultaneously
Equivalence relation sample discretization bring information loss is exempted from.
In addition, before step 101 and step 105, due to having drift when the location track got according to GPS sensor understands
It moves, thus the shift point for needing for these to be evident as noise spot is rejected, for example moment has floated to Shanghai from Beijing, this is clearly
Mistake, this GPS latitude and longitude coordinates point just needs to weed out.
As the realization of the above method, the embodiment of the invention also provides a kind of devices for determining significant place, such as Fig. 5 institute
Show, which includes:
Processing module 501, for by preset clustering algorithm obtain on the sample position track at least one is potential
Significant place；
Module 502 is obtained, for obtaining the value of corresponding first attribute set in each potential significant place, is belonged to
Property information table, first attribute set includes the conditional attribute and a decision attribute of predetermined number；
The processing module 501, is also used to according to the attribute information table, using default Feature Selection algorithm from described
Significant place is chosen in one attribute set determines attribute；
The acquisition module 502 is also used to obtain the threshold range that the significant place determines attribute；
The processing module 501 is also used to obtain in the location track to be processed by the default clustering algorithm
At least one potential significant place；
The processing module 501 is also used to the significant place determining that the value of attribute is latent in the threshold range
It is determined as significant place in significant place.
Further, the acquisition module 502 is specifically used for calculating first attribute using default Feature Selection algorithm
The value of the P norm with fault tolerance of each conditional attribute in set；
The corresponding conditional attribute of maximum value in all values of P norm described in being calculated with fault tolerance is true
It is set to significant place and determines attribute.
Further, the acquisition module 502, also particularly useful for:
Using the first condition attribute in first attribute set as attribute to be assessed, remaining conditional attribute is constituted
Set is determined as the second attribute set, and the first condition attribute is any conditional attribute；
Game playing algorithm is selected using the user property based on fuzzy entropy, successively judges the attribute to be assessed described second
Whether the sharing in game for each destination subset in attribute set wins, and obtains judgement knot corresponding with each destination subset
Fruit, the destination subset include at least two conditional attributes；
According to all judging results, the value of the P norm with fault tolerance of the attribute to be assessed is calculated.
Further, the default clustering algorithm includes distance threshold, points three parameters of threshold value and time threshold；Then institute
Processing module 501 is stated, is specifically used for:
Place not labeled in the location track is used as to starting point, the label include be labeled as it is potential significantly
Point or noise spot；
Search the target point for being less than or equal to the distance threshold at a distance from the starting point；
If the quantity of the target point found is more than or equal to the points threshold value, and each target point and institute
The time interval for stating starting point is all larger than the time threshold, then the starting point and all target points is determined as one
Cluster, and the starting point is labeled as potential significant place；
After all the points in the cluster are marked, the place that successively marks other not to be labeled.
It further, include speed, acceleration in first attribute set for obtaining the acquisition of module 502, potential
Significant place goes out in the sample position track in the record number in the sample position track, the potential significant place
The time period of stay and Orientation differences standard deviation of existing number of days, the potential significant place.
The device in the significant place of determination provided in an embodiment of the present invention is obtained by clustering algorithm sample position track latent
In significant place, then go out by Feature Selection algorithm picks the decision attribute and its threshold range in significant place, it is then right again
Location track to be processed is handled, by the decision attribute in significant place in the potential significant place in location track to be processed
The potential significant place that value meets threshold range is determined as significant place, and will be selected in the prior art by clustering algorithm
Point is compared directly as significant place, and the present invention after clustering algorithm due to using Feature Selection algorithm, it is thus possible to reduce
The False Rate in significant place, and then can be improved the accuracy for determining significant place.
As the realization of the above method, the embodiment of the invention also provides a kind of devices for determining significant place, such as Fig. 6 institute
Show, which includes processor 601, memory 602 and bus 603, and processor 601 and memory 602 are connected by bus 603
It connects.Wherein:
Processor 601, for by preset clustering algorithm obtain on the sample position track at least one is potential aobvious
Touchdown point；
The value for obtaining corresponding first attribute set in each potential significant place, obtains attribute information table, and described
One attribute set includes the conditional attribute and a decision attribute of predetermined number；
According to the attribute information table, chosen significantly from first attribute set using default Feature Selection algorithm
Point determines attribute；
Obtain the threshold range that the significant place determines attribute；
At least one potential significant place in the location track to be processed is obtained by the default clustering algorithm；
The significant place is determined that potential significant place of the value of attribute in the threshold range is determined as significantly
Point.
Further, the processor 601 is specifically used for calculating first property set using default Feature Selection algorithm
The value of the P norm with fault tolerance of each conditional attribute in conjunction；
The corresponding conditional attribute of maximum value in all values of P norm described in being calculated with fault tolerance is true
It is set to significant place and determines attribute.
Further, the processor 601, also particularly useful for:
Using the first condition attribute in first attribute set as attribute to be assessed, remaining conditional attribute is constituted
Set is determined as the second attribute set, and the first condition attribute is any conditional attribute；
Game playing algorithm is selected using the user property based on fuzzy entropy, successively judges the attribute to be assessed described second
Whether the sharing in game for each destination subset in attribute set wins, and obtains judgement knot corresponding with each destination subset
Fruit, the destination subset include at least two conditional attributes；
According to all judging results, the value of the P norm with fault tolerance of the attribute to be assessed is calculated.
Further, the processor 601, is specifically used for:
Place not labeled in the location track is used as to starting point, the label include be labeled as it is potential significantly
Point or noise spot；
Search the target point for being less than or equal to the distance threshold at a distance from the starting point；
If the quantity of the target point found is more than or equal to the points threshold value, and each target point and institute
The time interval for stating starting point is all larger than the time threshold, then the starting point and all target points is determined as one
Cluster, and the starting point is labeled as potential significant place；
After all the points in the cluster are marked, the place that successively marks other not to be labeled.
It further, include speed, acceleration in first attribute set that the processor 601 obtains, potential aobvious
Touchdown point occurs in the sample position track in the record number in the sample position track, the potential significant place
Number of days, the potential significant place time period of stay and Orientation differences standard deviation.
Memory 602 is for program used in 601 implementation procedure of storage processor.
The device in the significant place of determination provided in an embodiment of the present invention is obtained by clustering algorithm sample position track latent
In significant place, then go out by Feature Selection algorithm picks the decision attribute and its threshold range in significant place, it is then right again
Location track to be processed is handled, by the decision attribute in significant place in the potential significant place in location track to be processed
The potential significant place that value meets threshold range is determined as significant place, and will be selected in the prior art by clustering algorithm
Point is compared directly as significant place, and the present invention after clustering algorithm due to using Feature Selection algorithm, it is thus possible to reduce
The False Rate in significant place, and then can be improved the accuracy for determining significant place.
It should be noted that processor 601 described in the embodiment of the present invention can be a processor, it is also possible to multiple
The general designation of processing element.For example, the processor 601 can be central processing unit (Central Processing Unit, abbreviation
CPU), it is also possible to specific integrated circuit (Application Specific Integrated Circuit, abbreviation ASIC),
Or be arranged to implement one or more integrated circuits of the embodiment of the present invention, such as: one or more microprocessors
(digital signal processor, abbreviation DSP), or, one or more field programmable gate array (Field
Programmable Gate Array, abbreviation FPGA).
Memory 602 can be a storage device, be also possible to the general designation of multiple memory elements, and for storing and can hold
Line program code etc..And memory 602 may include random access memory (RAM), also may include nonvolatile memory (non-
Volatile memory), for example, magnetic disk storage, flash memory (Flash) etc..
It is total that bus 603 can be industry standard architecture (Industry Standard Architecture, ISA)
Line, external equipment interconnection (Peripheral Component, PCI) bus or extended industry-standard architecture (Extended
Industry Standard Architecture, EISA) bus etc..It is total that the bus 603 can be divided into address bus, data
Line, control bus etc..Only to be indicated with a thick line in Fig. 6, it is not intended that an only bus or a type convenient for indicating
The bus of type.
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.
Claims (6)
1. a kind of method for determining significant place, which is characterized in that the described method includes: being determined according to sample position track significant
Place determines attribute and determines that attribute determines the significant place in location track to be processed according to the significant place；
Wherein, described to determine that significant place determines attribute according to sample position track, it specifically includes:
At least one potential significant place on the sample position track is obtained by default clustering algorithm；
The value for obtaining corresponding first attribute set in each potential significant place, obtains attribute information table, described first belongs to
Property set includes the conditional attribute and a decision attribute of predetermined number；Wherein, the conditional attribute include speed, acceleration,
Record number of the potential significant place in the sample position track, the potential significant place are in the sample position track
The number of days of middle appearance, the potential significant place time period of stay and Orientation differences standard deviation；The decision attribute refers to
Whether the potential significant place is significant place；
According to the attribute information table, significant place is chosen from first attribute set using default Feature Selection algorithm and is determined
Determine attribute；It specifically includes: calculating having for each conditional attribute in first attribute set using default Feature Selection algorithm
The value of the P norm of fault tolerance；Maximum value in all values of P norm described in being calculated with fault tolerance is corresponding
Conditional attribute be determined as significant place and determine attribute；
Obtain the threshold range that the significant place determines attribute；
It is described to determine that attribute determines the significant place in location track to be processed according to the significant place, it specifically includes:
At least one potential significant place in the location track to be processed is obtained by the default clustering algorithm；
Significant place is determined that potential significant place of the value of attribute in the threshold range is determined as significant place.
2. the method according to claim 1, wherein described calculate described first using default Feature Selection algorithm
The value of the P norm with fault tolerance of each conditional attribute in attribute set, specifically includes:
Using the first condition attribute in first attribute set as attribute to be assessed, the set that remaining conditional attribute is constituted
It is determined as the second attribute set, the first condition attribute is any conditional attribute；
Game playing algorithm is selected using the user property based on fuzzy entropy, successively judges the attribute to be assessed in second attribute
Whether the sharing in game for each destination subset in set wins, and obtains judging result corresponding with each destination subset, institute
Stating destination subset includes at least two conditional attributes；
According to all judging results, the value of the P norm with fault tolerance of the attribute to be assessed is calculated.
3. the method according to claim 1, wherein the default clustering algorithm includes distance threshold, points threshold
Value and three parameters of time threshold；
It is described that at least one on the sample position track or the location track to be processed is obtained by default clustering algorithm
Potential significant place, specifically includes:
Place not labeled in the location track is used as to starting point, the label include be labeled as potential significant place or
Noise spot；
Search the target point for being less than or equal to the distance threshold at a distance from the starting point；
If the quantity of the target point found is more than or equal to the points threshold value, and each target point and described
The time interval of initial point is all larger than the time threshold, then the starting point and all target points is determined as a cluster,
And the starting point is labeled as potential significant place；
After all the points in the cluster are marked, the place that successively marks other not to be labeled.
4. a kind of device for determining significant place, which is characterized in that described device includes:
Processing module, for obtaining at least one potential significant place on sample position track by default clustering algorithm；
Module is obtained, for obtaining the value of corresponding first attribute set in each potential significant place, obtains attribute information
Table, first attribute set include the conditional attribute and a decision attribute of predetermined number；Wherein, the conditional attribute includes
Record number in the sample position track of speed, acceleration, potential significant place, the potential significant place are described
The time period of stay and Orientation differences standard deviation of the number of days, the potential significant place that occur in sample position track；It is described
Decision attribute refers to whether the potential significant place is significant place；
The processing module, is also used to according to the attribute information table, using default Feature Selection algorithm from first attribute
Significant place is chosen in set determines attribute；
The acquisition module is specifically used for calculating each condition category in first attribute set using default Feature Selection algorithm
The value of the P norm with fault tolerance of property；In all values of P norm described in being calculated with fault tolerance most
It is worth corresponding conditional attribute greatly and is determined as significant place decision attribute；
The acquisition module is also used to obtain the threshold range that the significant place determines attribute；
The processing module, at least one for being also used to obtain in location track to be processed by the default clustering algorithm are potential
Significant place；
The processing module, be also used to determine in the significant place value of attribute in the threshold range it is potential significantly
Point is determined as significant place.
5. device according to claim 4, which is characterized in that the acquisition module, also particularly useful for:
Using the first condition attribute in first attribute set as attribute to be assessed, the set that remaining conditional attribute is constituted
It is determined as the second attribute set, the first condition attribute is any conditional attribute；
Game playing algorithm is selected using the user property based on fuzzy entropy, successively judges the attribute to be assessed in second attribute
Whether the sharing in game for each destination subset in set wins, and obtains judging result corresponding with each destination subset, institute
Stating destination subset includes at least two conditional attributes；
According to all judging results, the value of the P norm with fault tolerance of the attribute to be assessed is calculated.
6. device according to claim 4, which is characterized in that the default clustering algorithm includes distance threshold, points threshold
Value and three parameters of time threshold；
The processing module, is specifically used for:
Place not labeled in the location track is used as to starting point, the label include be labeled as potential significant place or
Noise spot；
Search the target point for being less than or equal to the distance threshold at a distance from the starting point；
If the quantity of the target point found is more than or equal to the points threshold value, and each target point and described
The time interval of initial point is all larger than the time threshold, then the starting point and all target points is determined as a cluster,
And the starting point is labeled as potential significant place；
After all the points in the cluster are marked, the place that successively marks other not to be labeled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510307160.5A CN106294485B (en) | 2015-06-05 | 2015-06-05 | Determine the method and device in significant place |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510307160.5A CN106294485B (en) | 2015-06-05 | 2015-06-05 | Determine the method and device in significant place |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106294485A CN106294485A (en) | 2017-01-04 |
| CN106294485B true CN106294485B (en) | 2019-11-01 |
Family
ID=57659648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510307160.5A Active CN106294485B (en) | 2015-06-05 | 2015-06-05 | Determine the method and device in significant place |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106294485B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491895A (en) * | 2017-08-30 | 2017-12-19 | 国信优易数据有限公司 | A kind of shared bicycle parks determination method and device a little |
| CN112230253B (en) * | 2020-10-13 | 2021-07-09 | 电子科技大学 | Track characteristic anomaly detection method based on public slice subsequence |
| CN113254570B (en) * | 2021-07-15 | 2021-10-01 | 浙江网商银行股份有限公司 | Data identification method and device |
| CN114995628B (en) * | 2021-10-13 | 2023-08-11 | 荣耀终端有限公司 | Space gesture recognition method and related equipment thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218442A (en) * | 2013-04-22 | 2013-07-24 | 中山大学 | Method and system for life mode analysis based on mobile device sensor data |
| CN103577547A (en) * | 2013-10-12 | 2014-02-12 | 优视科技有限公司 | Webpage type identification method and device |
| CN104252527A (en) * | 2014-09-02 | 2014-12-31 | 百度在线网络技术（北京）有限公司 | Method and device for determining resident point information of mobile subscriber |
| CN104636354A (en) * | 2013-11-07 | 2015-05-20 | 华为技术有限公司 | Position point of interest clustering method and related device |
-
2015
- 2015-06-05 CN CN201510307160.5A patent/CN106294485B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218442A (en) * | 2013-04-22 | 2013-07-24 | 中山大学 | Method and system for life mode analysis based on mobile device sensor data |
| CN103577547A (en) * | 2013-10-12 | 2014-02-12 | 优视科技有限公司 | Webpage type identification method and device |
| CN104636354A (en) * | 2013-11-07 | 2015-05-20 | 华为技术有限公司 | Position point of interest clustering method and related device |
| CN104252527A (en) * | 2014-09-02 | 2014-12-31 | 百度在线网络技术（北京）有限公司 | Method and device for determining resident point information of mobile subscriber |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106294485A (en) | 2017-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102205096B1 (en) | Transaction risk detection method and apparatus | |
| TWI706273B (en) | Uniform resource locator (URL) attack detection method, device and electronic equipment | |
| CN109816397B (en) | Fraud discrimination method, device and storage medium | |
| CN106294485B (en) | Determine the method and device in significant place | |
| CN106649331A (en) | Business district recognition method and equipment | |
| CN105910612A (en) | Personalized navigation method and system | |
| CN109299981A (en) | A kind of advertisement recommended method and device | |
| CN110688589A (en) | Store arrival identification method and device, electronic equipment and readable storage medium | |
| CN108846097A (en) | The interest tags representation method of user, article recommended method and device, equipment | |
| CN107148553A (en) | Method and system for improving Inertial Measurement Unit sensor signal | |
| CN108834077A (en) | Tracking limited region dividing method, device and electronic equipment based on user's mobility | |
| CN113328994B (en) | Malicious domain name processing method, device, equipment and machine readable storage medium | |
| CN105990170A (en) | Wafer yield analysis method and device | |
| CN103324949B (en) | The method and apparatus identifying object from image | |
| JP2022126678A (en) | Method, apparatus and system for retrieving image, electronic device, computer-readable storage medium, and computer program | |
| CN109344176B (en) | False comment detection method based on double-cycle graph | |
| CN114117261A (en) | Track detection method and device, electronic equipment and storage medium | |
| CN111121803B (en) | Method and device for acquiring common stop points of road | |
| Galba et al. | Public transportation bigdata clustering | |
| CN116011504A (en) | Fraud recognition method and device based on sensor data, electronic equipment and medium | |
| CN102779120A (en) | Method, system and device for determining field information of station and judging correlation | |
| CN105354597B (en) | A kind of classification method and device of game articles | |
| EP3590025A2 (en) | Smart context subsampling on-device system | |
| CN108074301A (en) | A kind of system of real name method and device of transportation card | |
| CN108460057A (en) | A kind of user's stroke method for digging and device based on unsupervised learning |
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 |