CN109299747A - Determination method, apparatus, computer equipment and the storage medium at one type cluster center - Google Patents
Determination method, apparatus, computer equipment and the storage medium at one type cluster center Download PDFInfo
- Publication number
- CN109299747A CN109299747A CN201811246206.7A CN201811246206A CN109299747A CN 109299747 A CN109299747 A CN 109299747A CN 201811246206 A CN201811246206 A CN 201811246206A CN 109299747 A CN109299747 A CN 109299747A
- Authority
- CN
- China
- Prior art keywords
- location information
- geographical location
- node
- tree
- value
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present disclosure discloses determination method, apparatus, computer equipment and the storage medium at a type cluster center, the described method includes: each two-dimensional geographical location information that geographical location information to be processed is concentrated is converted to one-dimensional position encoded information using geographical location coding techniques;Dictionary tree is generated according to each position encoded information, a tree node in dictionary tree corresponds to the geographic location area of a setting, and the corresponding geographic location area of a child node belongs within the scope of geographic location area corresponding with the father node of child node;According to the positional relationship between each tree node and each geographical location information in dictionary tree, and the quantitative value with the associated geographical location information of each tree node, density value corresponding with each geographical location information is calculated;According to density value, is concentrated in geographical location information and determine at least one class cluster center.The technical solution of the embodiment of the present disclosure can reduce the computation complexity at class cluster center in clustering algorithm.
Description
Technical field
The embodiment of the present disclosure be related to technical field of data processing more particularly to a type cluster center determination method, apparatus,
Computer equipment and storage medium.
Background technique
The target of density-based algorithms be find by density regions separate high-density region, it is popular for just
It is the point (high density) to flock together to be found out, and put seldom very sparse place (low-density) and be just used as cut zone.
The core concept of density-based algorithms is exactly that the higher point of density is first found according to the position data of acquisition,
Then similar high density point is gradually all joined together, and then generates various clusters, one class cluster center of each cluster Corresponding matching.
Inventor in implementing the present disclosure, it is found that existing density-based algorithms have following defects that
The position data being related in density-based algorithms is usually calculated with latitude and longitude information form, computation complexity compared with
It is high.
Summary of the invention
The embodiment of the present disclosure provides determination method, apparatus, computer equipment and the storage medium at a type cluster center, realizes
Reduce the computation complexity at class cluster center in clustering algorithm.
In a first aspect, the embodiment of the present disclosure provides the determination method at a type cluster center, comprising:
Using geographical location coding techniques, each two-dimensional geographical location information that geographical location information to be processed is concentrated
Be converted to one-dimensional position encoded information;
Dictionary tree is generated according to each position encoded information, a tree node in the dictionary tree corresponds to one and sets
Fixed geographic location area, and the corresponding geographic location area of a child node belong to it is corresponding with the father node of the child node
Within the scope of geographic location area;
According to the positional relationship between each tree node and each geographical location information in the dictionary tree, Yi Jiyu
The quantitative value of the associated geographical location information of each tree node calculates corresponding with each geographical location information
Density value;
According to the density value, is concentrated in the geographical location information and determine at least one class cluster center.
Optionally, it is closed according to the position between each tree node and each geographical location information in the dictionary tree
System, and the quantitative value with each associated geographical location information of tree node calculate and each geographical location information
Corresponding density value, comprising:
According to geographic location area corresponding with the tree node each in the dictionary tree, calculate and each tree node point
Not corresponding site error value and center geographical location information;
Calculate the difference in geographical location information and the dictionary tree between the center geographical location information of tree node and tree
Numerical relation between the site error value of node, and according to the numerical relation determine to the dictionary traversal of tree form with
And the update mode to the density value with the geographical location information, until traverse the dictionary tree, with obtain with it is each described
Manage the corresponding density value of location information.
Optionally, the difference in geographical location information and the dictionary tree between the center geographical location information of tree node is calculated
Numerical relation between value and the site error value of tree node, and determined according to the numerical relation to the dictionary traversal of tree
Form and update mode to the density value with the geographical location information, until traversing the dictionary tree, comprising:
A geographical location information of the geographical location information concentration is obtained as current location information, and described in setting
The initial density value of current location information;
According to top-down sequence, a untreated tree node is successively obtained in the dictionary tree as current ratio
To node, and calculates the current location information and currently compare the distance between center geographical location information of node with described
Value;
If the distance value is less than or equal to first threshold, the density value of the current location information is updated to and institute
State the cumulative of the current quantitative value for comparing the associated geographical location information of node and, and by the current comparison node and
With the corresponding whole child nodes of node that currently compare labeled as processed node;Wherein, the first threshold is that setting is close
Degree distance threshold and the difference currently compared between the site error value of node;
If the distance value is more than or equal to second threshold, keep the density value of the current location information constant, and
By the current comparison node and with the corresponding whole child nodes of node that currently compare labeled as processed node;Its
In, the second threshold be it is described setting density distance threshold and it is described currently compare between the site error value of node and
Value;
If the distance value is greater than the first threshold and is less than the second threshold, the present bit confidence is kept
The density value of breath is constant, and is processed node by the current comparison vertex ticks;
It returns and executes according to top-down sequence, a untreated tree node is successively obtained in the dictionary tree and is made
For the operation for currently comparing node, until complete the processing to tree nodes whole in the dictionary tree, with obtain with it is described current
The corresponding density value of location information;
It returns and executes a geographical location information for obtaining the geographical location information concentration as current location information
Operation, until completing the processing to whole geographical location information.
Optionally, according to geographic location area corresponding with the tree node each in the dictionary tree, calculate with it is each described
The corresponding site error value of tree node and center geographical location information, comprising:
According between geographic location area coboundary corresponding with the tree node each in the dictionary tree and lower boundary
Height value calculates the corresponding site error value of each tree node;
According to being averaged for the geographical location information of geographic location area corresponding with the tree node each in the dictionary tree
Value calculates the corresponding center geographical location information of each tree node;Wherein, the geographical location information includes longitude and latitude
Information.
Optionally, according to the density value, at least one class cluster center that determines, packet are concentrated in the geographical location information
It includes:
According to the corresponding density value of each geographical location information calculate the class cluster of each geographical location information away from
From;
Each geographical location letter is calculated according to the corresponding density value of each geographical location information and class cluster distance
The class cluster weight of breath;
It is concentrated according to the class cluster weight in described geographical location information and determines at least one class cluster center.
Optionally, each geographical location information is calculated according to the corresponding density value of each geographical location information
Class cluster distance, comprising:
Each geographical location information is ranked up according to setting rule according to the density value;
Each geographical location information is successively calculated according to ranking results between the forward geographical location information that sorts
Distance value as class cluster distance to be screened;
Class cluster of the class cluster distance to be screened of class cluster range estimation condition as the geographical location information will be met
Distance.
Optionally, the geographical location information to be processed integrates the track number as target user in setting time section
According to;
It is also being wrapped after the geographical location information is concentrated and determines at least one class cluster center according to the density value
It includes:
Using at least one described class cluster center as the resident point of the target user.
Second aspect, the embodiment of the present disclosure additionally provide the determining device at a type cluster center, comprising:
Info conversion module is concentrated geographical location information to be processed each for using geographical location coding techniques
Two-dimensional geographical location information is converted to one-dimensional position encoded information;
Dictionary tree generation module, for generating dictionary tree according to each position encoded information, one in the dictionary tree
A tree node correspond to one setting geographic location area, and the corresponding geographic location area of a child node belong to it is described
Within the scope of the corresponding geographic location area of the father node of child node;
Density value computing module, for according to and each tree node in the dictionary tree and each geographical location information it
Between positional relationship, and the quantitative value with each associated geographical location information of tree node, calculate with it is each described
Manage the corresponding density value of location information;
Class cluster center determining module, for being concentrated in the geographical location information and determining at least one according to the density value
A class cluster center.
Optionally, density value computing module includes: center geography positional information calculation unit, for basis and the dictionary
The corresponding geographic location area of each tree node in tree, calculate site error value corresponding with each tree node and
Center geographical location information;
Density value computing unit, for calculating the center geographical location of tree node in geographical location information and the dictionary tree
Difference between information and the numerical relation between the site error value of tree node, and determined according to the numerical relation to described
Dictionary traversal of tree form and update mode to the density value with the geographical location information, until traversing the dictionary
Tree, to obtain density value corresponding with each geographical location information.
Optionally, density value computing unit, the geographical location concentrated specifically for obtaining the geographical location information
The initial density value of the current location information is arranged as current location information in information;
According to top-down sequence, a untreated tree node is successively obtained in the dictionary tree as current ratio
To node, and calculates the current location information and currently compare the distance between center geographical location information of node with described
Value;
If the distance value is less than or equal to first threshold, the density value of the current location information is updated to and institute
State the cumulative of the current quantitative value for comparing the associated geographical location information of node and, and by the current comparison node and
With the corresponding whole child nodes of node that currently compare labeled as processed node;Wherein, the first threshold is that setting is close
Degree distance threshold and the difference currently compared between the site error value of node;
If the distance value is more than or equal to second threshold, keep the density value of the current location information constant, and
By the current comparison node and with the corresponding whole child nodes of node that currently compare labeled as processed node;Its
In, the second threshold be it is described setting density distance threshold and it is described currently compare between the site error value of node and
Value;
If the distance value is greater than the first threshold and is less than the second threshold, the present bit confidence is kept
The density value of breath is constant, and is processed node by the current comparison vertex ticks;
It returns and executes according to top-down sequence, a untreated tree node is successively obtained in the dictionary tree and is made
For the operation for currently comparing node, until complete the processing to tree nodes whole in the dictionary tree, with obtain with it is described current
The corresponding density value of location information;
It returns and executes a geographical location information for obtaining the geographical location information concentration as current location information
Operation, until completing the processing to whole geographical location information.
Optionally, center geography positional information calculation unit is specifically used for basis and the burl each in the dictionary tree
Height value between the corresponding geographic location area coboundary of point and lower boundary calculates the corresponding position of each tree node
Error amount;
According to being averaged for the geographical location information of geographic location area corresponding with the tree node each in the dictionary tree
Value calculates the corresponding center geographical location information of each tree node;Wherein, the geographical location information includes longitude and latitude
Information.
Optionally, class cluster center determining module includes: class cluster metrics calculation unit, for being believed according to each geographical location
Cease the class cluster distance that corresponding density value calculates each geographical location information;
Class cluster weight calculation unit, for according to the corresponding density value of each geographical location information and class cluster distance
Calculate the class cluster weight of each geographical location information;
Class cluster center determination unit determines at least for being concentrated according to the class cluster weight in described geographical location information
One class cluster center.
Optionally, class cluster metrics calculation unit, with specific reference to the density value by each geographical location information according to setting
Set pattern is then ranked up;
Each geographical location information is successively calculated according to ranking results between the forward geographical location information that sorts
Distance value as class cluster distance to be screened;
Class cluster of the class cluster distance to be screened of class cluster range estimation condition as the geographical location information will be met
Distance.
Optionally, the geographical location information to be processed integrates the track number as target user in setting time section
According to;Described device further include: resident point determining module, for using at least one described class cluster center as the target user's
Resident point.
The third aspect, the embodiment of the present disclosure additionally provide a kind of computer equipment, and the computer equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the determination method at class cluster center provided by disclosure any embodiment.
Fourth aspect, the embodiment of the present disclosure additionally provide a kind of computer storage medium, are stored thereon with computer program,
The determination method at class cluster center provided by disclosure any embodiment is realized when the program is executed by processor.
The embodiment of the present disclosure geographical location information to be processed is concentrated by using geographical location coding techniques each two
The geographical location information of dimension is converted to one-dimensional position encoded information to generate dictionary tree, according to each tree node in dictionary tree
With the positional relationship between each geographical location information, and the quantitative value with the associated geographical location information of each tree node, calculate
Density value corresponding with each geographical location information is finally concentrated in geographical location information according to density value and determines at least one
Class cluster center solves the problems, such as that computation complexity present in existing density-based algorithms is higher, and realizing reduces cluster
The computation complexity at class cluster center in algorithm.
Detailed description of the invention
Fig. 1 a is the flow chart of the determination method at the type cluster center that the embodiment of the present disclosure one provides;
Fig. 1 b is a kind of structural representation for dictionary tree generated according to position encoded information that the embodiment of the present invention one provides
Figure;
Fig. 2 a is the flow chart of the determination method at the type cluster center that the embodiment of the present disclosure two provides;
Fig. 2 b is a kind of calculating density value side corresponding with each geographical location information that the embodiment of the present disclosure two provides
The flow chart of method;
Fig. 3 is the schematic diagram of the determining device at the type cluster center that the embodiment of the present disclosure three provides;
Fig. 4 is a kind of hardware structural diagram for computer equipment that the embodiment of the present disclosure four provides.
Specific embodiment
The disclosure is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the disclosure, rather than the restriction to the disclosure.
It also should be noted that illustrate only part relevant to the disclosure for ease of description, in attached drawing rather than
Full content.It should be mentioned that some exemplary embodiments are described before exemplary embodiment is discussed in greater detail
At the processing or method described as flow chart.Although operations (or step) are described as the processing of sequence by flow chart,
It is that many of these operations can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operations can be by again
It arranges.The processing can be terminated when its operations are completed, it is also possible to have the additional step being not included in attached drawing.
The processing can correspond to method, function, regulation, subroutine, subprogram etc..
Embodiment one
Fig. 1 a is the flow chart of the determination method at the type cluster center that the embodiment of the present disclosure one provides, and the present embodiment can fit
The case where for quickly determining class cluster center, this method can be executed by the determining device at class cluster center, which can be by
The mode of software and/or hardware can be generally integrated in computer equipment to realize.Correspondingly, as shown in Figure 1a, this method
Including operating as follows:
S110, using geographical location coding techniques, each two-dimensional geographical position that geographical location information to be processed is concentrated
Confidence breath is converted to one-dimensional position encoded information.
Wherein, geographical location coding techniques can be the technology for carrying out coded treatment to geographic position data, for example,
Geographical location coding techniques can be using geographical hashing algorithm (Geo hash).Two-dimensional geographical location information can be in difference
The corresponding information of point data of geographical location acquisition.Position encoded information, which can be, to be formed after geographical location information is encoded
Information.
In the embodiments of the present disclosure, when calculating class cluster center using density-based algorithms, it is necessary first to obtain and use
In the geographical location information collection that algorithm calculates.Wherein, geographical location information concentration may include a variety of two-dimensional geographical location letters
Breath.Optionally, geographical location information can be latitude and longitude information.After obtaining geographical location information collection to be processed, it can use
Each two-dimensional geographical location information that geographical location coding techniques is included is converted to one-dimensional position encoded information.
Optionally, if geographical location coding techniques use Geo hash algorithm, the algorithm convert to be formed it is one-dimensional
Position encoded information can carry out approach coding to two-dimensional geographical location information, be converted into corresponding character string.
S120, dictionary tree is generated according to each position encoded information, a tree node in the dictionary tree corresponds to
The geographic location area of one setting, and the corresponding geographic location area of a child node belongs to the father node with the child node
Within the scope of corresponding geographic location area.
In the embodiments of the present disclosure, each two-dimensional geographical location information in geographical position information set is converted to one-dimensional
It, can be according to the position encoded information architecture dictionary tree after conversion after position encoded information.Dictionary tree can have multistage tree node
It constitutes, the obtained character string in the corresponding path of each tree node forms a position encoded information, each is position encoded
The geographic location area of the corresponding rectangle of information, each geographic location area may include one or more geographical location letters
Breath.Geographic location area corresponding to different levels tree node is of different sizes, and the corresponding geographic location area of a child node
Belong within the scope of geographic location area corresponding with the father node of child node.Wherein, the root node in dictionary tree is sky.
Fig. 1 b is a kind of structural representation for dictionary tree generated according to position encoded information that the embodiment of the present invention one provides
Figure.Illustratively, as shown in Figure 1 b, the two-level node of dictionary tree includes two nodes of A and C, and three-level node includes N, L, B and S
Four nodes.Assuming that the corresponding geographic location area of node A is the U.S., the corresponding geographic location area of node C is China, then saves
Child node N under point A can indicate New York, and child node L can indicate Los Angeles;Similarly, the child node B under node C can be with table
Show Beijing, child node S can indicate Shanghai.Wherein, may include in the corresponding geographic location area in Beijing 10 two-dimensionally
Location information is managed, such as 10 are located at the corresponding latitude and longitude information of point data in same city or different city acquisitions.
S130, basis and the positional relationship between each tree node and each geographical location information in the dictionary tree,
And the quantitative value with each associated geographical location information of tree node, it calculates and distinguishes with each geographical location information
Corresponding density value.
Wherein, the density value of geographical location information can react the geographical location information for including around the geographical location information
Intensive situation.
It in the embodiments of the present disclosure, can be according to each burl in dictionary tree when calculating geographical location information
Positional relationship between point and each geographical location information, and calculated with the quantitative value of the associated geographical location information of each tree node
The corresponding density value of each geographical location information.
S140, according to the density value, concentrated in the geographical location information and determine at least one class cluster center.
Correspondingly, can be that geographical location information concentration includes according to the corresponding density value of each geographical location information
All data determine at least one class cluster center.
The embodiment of the present disclosure geographical location information to be processed is concentrated by using geographical location coding techniques each two
The geographical location information of dimension is converted to one-dimensional position encoded information to generate dictionary tree, according to each tree node in dictionary tree
With the positional relationship between each geographical location information, and the quantitative value with the associated geographical location information of each tree node, calculate
Density value corresponding with each geographical location information is finally concentrated in geographical location information according to density value and determines at least one
Class cluster center solves the problems, such as that computation complexity present in existing density-based algorithms is higher, and realizing reduces cluster
The computation complexity at class cluster center in algorithm.
Embodiment two
Fig. 2 a is the flow chart of the determination method at the type cluster center that the embodiment of the present disclosure two provides, and Fig. 2 b is the disclosure
Embodiment two provide a kind of calculating density value method corresponding with each geographical location information flow chart, the present embodiment with
Embodied based on above-described embodiment, in the present embodiment, give according to in the dictionary tree each tree node with
Positional relationship between each geographical location information, and the number with each associated geographical location information of tree node
Magnitude calculates density value corresponding with each geographical location information, and the tool at class cluster center is determined according to density value
Body implementation.Correspondingly, as shown in Figure 2 a, the method for the present embodiment may include:
S210, using geographical location coding techniques, each two-dimensional geographical position that geographical location information to be processed is concentrated
Confidence breath is converted to one-dimensional position encoded information.
S220, dictionary tree is generated according to each position encoded information, a tree node in the dictionary tree corresponds to
The geographic location area of one setting, and the corresponding geographic location area of a child node belongs to the father node with the child node
Within the scope of corresponding geographic location area.
S230, according to geographic location area corresponding with the tree node each in the dictionary tree, calculate and each tree
The corresponding site error value of node and center geographical location information.
In the embodiments of the present disclosure, it in the corresponding density value of each geographical location information of calculating, can calculate first
The corresponding site error value of each tree node and center geographical location information are as intermediate quantity.
Optionally, in one embodiment, S230 may include operations described below:
S231, according to geographic location area coboundary corresponding with the tree node each in the dictionary tree and lower boundary it
Between height value, calculate the corresponding site error value of each tree node.
Specifically, the corresponding site error value of each tree node can be with the corresponding geographic location area of the tree node
Height value between coboundary and lower boundary is as corresponding site error value.It optionally, can be with geographic location area top
The difference of the corresponding latitude in boundary latitude numerical value corresponding with lower boundary is as height value.
S232, according to the geographical location information of geographic location area corresponding with the tree node each in the dictionary tree
Average value calculates the corresponding center geographical location information of each tree node.
Correspondingly, the corresponding center geographical location information of each tree node can be the corresponding geographic location area of each tree node
Longitude average value and latitude average value corresponding to geographical location information.
Difference in S240, calculating geographical location information and the dictionary tree between the center geographical location information of tree node
Numerical relation between the site error value of tree node, and determined according to the numerical relation to the dictionary traversal of tree shape
Formula and update mode to the density value with the geographical location information, until the dictionary tree is traversed, to obtain and each institute
State the corresponding density value of geographical location information.
In the embodiments of the present disclosure, the corresponding site error value of each tree node and center geographical location are being got
After information, the difference between the center geographical location information of each tree node in geographical location information and dictionary tree can be calculated separately
Value, then by the numerical relation between difference and the site error value of tree node in a manner of traversing each node in Dictionary of Computing tree
Density value contribution to geographical location information.The corresponding density value of each geographical location information is calculated by the Field Count of building
A large amount of unnecessary calculating can be effectively reduced, to reduce computation complexity.
Optionally, in one embodiment, as shown in Figure 2 b, S240 may include operations described below:
The geographical location information that S241, the acquisition geographical location information are concentrated is set as current location information
Set the initial density value of the current location information.
It in the embodiments of the present disclosure, can be to geographical location information when determining the class cluster center of geographical position information set
The each geographical location information concentrated calculates separately.When calculating, the initial density value of current location information can be set, it is optional
, the initial density value of current location information can be set to 0.
S242, according to top-down sequence, a untreated tree node conduct is successively obtained in the dictionary tree
It is current to compare node, and calculate the current location information and described currently compare between the center geographical location information of node
Distance value.
In the embodiments of the present disclosure, calculate geographical location information density value when, can by building dictionary tree into
Row calculates.Specifically, can successively obtain a untreated tree node conduct according to top-down sequence in dictionary tree
It is current to compare node, it then calculates current location information and currently compares the distance between center geographical location information of node
Value.
S243, judge whether distance value is less than or equal to first threshold, if so, executing S244;Otherwise, S245 is executed.
Wherein, first threshold is to set density distance threshold and the difference currently compared between the site error value of node
Value.
Wherein, first threshold can comprehensively consider the distribution character of geographical location information and actual demand is set.
Optionally, first threshold can be setting density distance threshold and currently compare the difference between the site error value of node.If
Determining density distance threshold can be the distance value of actual selection, such as 300m.
Correspondingly, obtaining current location information and currently comparing the distance between the center geographical location information of node value
Afterwards, the size relation between distance value and first threshold can be calculated to calculate the density value of current location information.
S244, the density value of the current location information is updated to currently to compare the associated geography of node with described
The quantitative value of location information cumulative and, and current compare the corresponding whole of node by current the comparisons node and with described
Child node is labeled as processed node.
Specifically, if distance value be less than or equal to first threshold, illustrate currently compare node under all nodes with currently
The distance of location information, which is respectively less than, sets density distance threshold, then can add on the basis of the density value of current location information
The upper current point quantity for comparing the geographical location information for including in the corresponding geographic location area of node, then will currently compare
To node and whole child nodes corresponding with node is currently compared are labeled as processed node, without calculating present bit confidence
The distance between each child node that breath is included with current comparison node.
S245, judge whether distance value is more than or equal to second threshold, if so, executing S246;Otherwise, S247 is executed.
Wherein, the second threshold is the setting density distance threshold and the site error value for currently comparing node
Between and value.
Correspondingly, in the embodiments of the present disclosure, can also be calculated according to the size relation between distance value and second threshold
The density value of current location information.
S246, keep the density value of the current location information constant, and by the current comparison node and with it is described
The current corresponding whole child nodes of node that compare are labeled as processed node.
Specifically, if distance value be more than or equal to second threshold, illustrate currently compare node under all nodes with currently
The distance of location information is all larger than setting density distance threshold, then can directly keep the density value of current location information constant i.e.
Can, current comparison node and whole child nodes corresponding with node is currently compared then are labeled as processed node, without
The distance between each child node that current location information and current comparison node are included must be calculated.
S247, distance value are greater than the first threshold and are less than the second threshold, keep the current location information
Density value is constant, and is processed node by the current comparison vertex ticks.
Correspondingly, needing to be traversed for current comparison node packet if distance value is greater than first threshold and is less than second threshold
The each child node included is to the density contribution of current location information, at this point it is possible to first keep the density value of current location information not
Become, and will currently compare vertex ticks is processed node, then successively traversal calculates the current every height for comparing node and including
Density contribution of the node to current location information.Its calculation is identical as the operation of S243-S245.
S248, judge whether to complete the processing to tree nodes whole in the dictionary tree, if so, executing S249;Otherwise,
It returns and executes S242.
Specifically, if distance value is greater than first threshold and is less than second threshold, successively using automatic downward sequence
Each child node that current comparison node includes is calculated to the density contribution of current location information, until completing to current comparison section
The processing for each child node that point includes.Then, execution is returned again to according to top-down on the basis of currently comparison node
Sequentially, a untreated tree node is successively obtained in dictionary tree as the current operation for comparing node, until completing to word
The processing of whole tree nodes in allusion quotation tree.
S249, judge whether to complete the processing to whole geographical location information, if so, end operation;Otherwise, return is held
Row S241.
Correspondingly, judging whether to complete to believe whole geographical locations after the density value calculating of current location information finishes
The processing of breath, if so, otherwise end operation returns to a geographical location for executing and obtaining the geographical location information concentration
Operation of the information as current location information, until completing the processing to whole geographical location information.
S250, according to the density value, concentrated in the geographical location information and determine at least one class cluster center.
Optionally, in one embodiment, as shown in Figure 2 a, S250 may include operations described below:
S251, the class that each geographical location information is calculated according to the corresponding density value of each geographical location information
Cluster distance.
Wherein, class cluster distance can be the distance between geographical location information and the biggish geographical location information of density value.
It in the embodiments of the present disclosure, can when determining class cluster center according to the corresponding density value of each geographical location information
The class cluster distance of each geographical location information is calculated according to the corresponding density value of each geographical location information first.
In an alternative embodiment of the disclosure, calculated according to the corresponding density value of each geographical location information
The class cluster distance of each geographical location information, may include: according to the density value by each geographical location information according to
Setting rule is ranked up;Each geographical location information is successively calculated according to ranking results and forward geographical location of sorting
The distance between information value is used as class cluster distance to be screened;The class cluster distance to be screened of class cluster range estimation condition will be met
Class cluster distance as the geographical location information.
Wherein, setting rule can be the sequence by numerical value from big to small.Class cluster range estimation condition can be to be screened
The value of class cluster distance is minimum.
Specifically, the class cluster for calculating each geographical location information apart from when, can be by each geographical location information according to correspondence
Density value be ranked up according to sequence from big to small.Then successively calculated according to ranking results each geographical location information with
Sort the distance between forward geographical location information value, the class by the smallest class cluster distance to be screened as geographical location information
Cluster distance.Meanwhile can will calculate class cluster apart from when corresponding geographical location information as father node.
Illustratively, it is assumed that it includes 5 geographical location information that geographical location information is concentrated altogether, from big to small according to density value
Sequence be ranked up after obtained geographical location information be respectively [5,4,3,2,1], wherein the digital number in set represents
The corresponding point data of one geographical location information.The class cluster for calculating digital 3 corresponding geographical location information apart from when, Ke Yiyi
It is secondary to calculate itself and the distance between number 5 and digital 4 corresponding geographical location information.Assuming that the corresponding geographical location letter of number 3
The distance between breath and digital 5 corresponding geographical location information are 200, between 4 corresponding geographical location information of number away from
From being 100, then by the 100 class cluster distance as digital 3 corresponding geographical location information, and the corresponding geographical location of number 4 is believed
The point data of breath can be used as the father node of the point data of digital 3 corresponding geographical location information.
S252, each geographical position is calculated according to the corresponding density value of each geographical location information and class cluster distance
The class cluster weight of confidence breath.
In the embodiments of the present disclosure, after the class cluster distance for obtaining each geographical location information, can be believed according to each geographical location
It ceases corresponding density value and class cluster distance calculates the class cluster weight of each geographical location information.It optionally, can be by geographical position
Confidence ceases class cluster weight of the product of corresponding density value and class cluster distance as geographical location information.That is, density value and class
Cluster distance is bigger, then corresponding class cluster weight is also bigger.
S253, at least one determining class cluster center is concentrated in described geographical location information according to the class cluster weight.
Finally, can determine at least one class cluster center according to the class cluster weight of each geographical location information.Specifically, can be with
According to class cluster weight by each geographical location information also according to sequence from big to small, and successively traverse each geographical location information
Density value and class cluster distance.When geographical location information density value be more than or equal to first setting numerical value and class cluster distance be more than or equal to
When the second setting numerical value, which can be determined as a class cluster center.Optionally, the first setting numerical value can be set
2 are set to, the second setting numerical value can be set to 500.
Correspondingly, can also determine that class cluster belongs to for each geographical location information after class cluster center determines.Specifically,
If geographical location information is class cluster center, class cluster is attributed to itself;Otherwise its class cluster belongs to its corresponding father node
It is identical.Influence in order to avoid discrete geographical location information to class cluster, can limit the corresponding class cluster of geographical location information away from
Density distance threshold is set from being less than.
In an alternative embodiment of the disclosure, the geographical location information to be processed integrates to be set as target user
Track data in time interval;According to the density value, is concentrated in the geographical location information and determine at least one class cluster
It can also include: using at least one described class cluster center as the resident point of the target user after center.
Wherein, setting time section can be set according to actual needs, such as one month or two months.Track data
It can be the latitude and longitude information data of user.
The determination method at class cluster center provided by the embodiment of the present disclosure can be applied to the excavation applications of the resident point of user.
When carrying out resident excavation of user, target user's user trajectory that (such as 60 days) report whithin a period of time is usually counted
Data are determined according to the position that each user often goes using the determination method at class cluster center provided by the embodiment of the present disclosure
Resident point of the class cluster center as target user.
By adopting the above technical scheme, by the one-dimensional position encoded information architecture dictionary tree of conversion, and according to dictionary tree
The corresponding density value of each geographical location information is calculated, at least one class cluster center is further determined according to density value, it can be with
A large amount of unnecessary calculation amounts are reduced, to reduce the computation complexity at class cluster center in clustering algorithm.
Embodiment three
Fig. 3 is the schematic diagram of the determining device at the type cluster center that the embodiment of the present disclosure three provides, as shown in figure 3, institute
Stating device includes: that info conversion module 310, dictionary tree generation module 320, density value computing module 330 and class cluster center are true
Cover half block 340, in which:
Info conversion module 310 concentrates geographical location information to be processed for using geographical location coding techniques
Each two-dimensional geographical location information is converted to one-dimensional position encoded information;
Dictionary tree generation module 320, for generating dictionary tree according to each position encoded information, in the dictionary tree
One tree node corresponds to the geographic location area of a setting, and the corresponding geographic location area of a child node belongs to and institute
It states within the scope of the corresponding geographic location area of father node of child node;
Density value computing module 330, for believing according to each tree node in the dictionary tree with each geographical location
Positional relationship between breath, and the quantitative value with each associated geographical location information of tree node calculate and each institute
State the corresponding density value of geographical location information;
Class cluster center determining module 340, for concentrating and being determined at least in the geographical location information according to the density value
One class cluster center.
The embodiment of the present disclosure geographical location information to be processed is concentrated by using geographical location coding techniques each two
The geographical location information of dimension is converted to one-dimensional position encoded information to generate dictionary tree, according to each tree node in dictionary tree
With the positional relationship between each geographical location information, and the quantitative value with the associated geographical location information of each tree node, calculate
Density value corresponding with each geographical location information is finally concentrated in geographical location information according to density value and determines at least one
Class cluster center solves the problems, such as that computation complexity present in existing density-based algorithms is higher, and realizing reduces cluster
The computation complexity at class cluster center in algorithm.
Optionally, density value computing module 330 includes: center geography positional information calculation unit, for according to it is described
The corresponding geographic location area of each tree node in dictionary tree calculates site error value corresponding with each tree node
And center geographical location information;
Density value computing unit, for calculating the center geographical location of tree node in geographical location information and the dictionary tree
Difference between information and the numerical relation between the site error value of tree node, and determined according to the numerical relation to described
Dictionary traversal of tree form and update mode to the density value with the geographical location information, until traversing the dictionary
Tree, to obtain density value corresponding with each geographical location information.
Optionally, density value computing unit, the geographical location concentrated specifically for obtaining the geographical location information
The initial density value of the current location information is arranged as current location information in information;
According to top-down sequence, a untreated tree node is successively obtained in the dictionary tree as current ratio
To node, and calculates the current location information and currently compare the distance between center geographical location information of node with described
Value;
If the distance value is less than or equal to first threshold, the density value of the current location information is updated to and institute
State the cumulative of the current quantitative value for comparing the associated geographical location information of node and, and by the current comparison node and
With the corresponding whole child nodes of node that currently compare labeled as processed node;Wherein, the first threshold is that setting is close
Degree distance threshold and the difference currently compared between the site error value of node;
If the distance value is more than or equal to second threshold, keep the density value of the current location information constant, and
By the current comparison node and with the corresponding whole child nodes of node that currently compare labeled as processed node;Its
In, the second threshold be it is described setting density distance threshold and it is described currently compare between the site error value of node and
Value;
If the distance value is greater than the first threshold and is less than the second threshold, the present bit confidence is kept
The density value of breath is constant, and is processed node by the current comparison vertex ticks;
It returns and executes according to top-down sequence, a untreated tree node is successively obtained in the dictionary tree and is made
For the operation for currently comparing node, until complete the processing to tree nodes whole in the dictionary tree, with obtain with it is described current
The corresponding density value of location information;
It returns and executes a geographical location information for obtaining the geographical location information concentration as current location information
Operation, until completing the processing to whole geographical location information.
Optionally, center geography positional information calculation unit is specifically used for basis and the burl each in the dictionary tree
Height value between the corresponding geographic location area coboundary of point and lower boundary calculates the corresponding position of each tree node
Error amount;
According to being averaged for the geographical location information of geographic location area corresponding with the tree node each in the dictionary tree
Value calculates the corresponding center geographical location information of each tree node;Wherein, the geographical location information includes longitude and latitude
Information.
Optionally, class cluster center determining module 340 includes: class cluster metrics calculation unit, for according to each geographical position
Confidence ceases the class cluster distance that corresponding density value calculates each geographical location information;
Class cluster weight calculation unit, for according to the corresponding density value of each geographical location information and class cluster distance
Calculate the class cluster weight of each geographical location information;
Class cluster center determination unit determines at least for being concentrated according to the class cluster weight in described geographical location information
One class cluster center.
Optionally, class cluster metrics calculation unit, specifically for being pressed each geographical location information according to the density value
It is ranked up according to setting rule;
Each geographical location information is successively calculated according to ranking results between the forward geographical location information that sorts
Distance value as class cluster distance to be screened;
Class cluster of the class cluster distance to be screened of class cluster range estimation condition as the geographical location information will be met
Distance.
Optionally, the geographical location information to be processed integrates the track number as target user in setting time section
According to;Described device further include: resident point determining module, for using at least one described class cluster center as the target user's
Resident point.
The determination side at class cluster center provided by disclosure any embodiment can be performed in the determining device at above-mentioned class cluster center
Method has the corresponding functional module of execution method and beneficial effect.The not technical detail of detailed description in the present embodiment, can join
See the determination method at the class cluster center that disclosure any embodiment provides.
Example IV
Fig. 4 is the hardware structural diagram for illustrating the computer equipment according to the embodiment of the present disclosure four.Computer equipment can
To implement in a variety of manners, computer equipment in the disclosure can include but is not limited to such as mobile phone, smart phone,
Laptop, digit broadcasting receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia broadcasting
Put device), navigation device, vehicle-mounted terminal equipment, vehicle-mounted display terminal, vehicle electronics rearview mirror etc. mobile computer device with
And the fixed computer equipment of such as number TV, desktop computer etc..
As shown in figure 4, computer equipment 0 may include wireless communication unit 41, A/V (audio/video) input unit 42,
User input unit 43, sensing unit 44, output unit 45, memory 46, interface unit 47, processor 48 and power supply unit 49
Etc..Fig. 4 shows the computer equipment 0 with various assemblies, it should be understood that being not required for implementing all show
Component.More or fewer components can alternatively be implemented.
Wherein, wireless communication unit 41 allows the radio between computer equipment 0 and wireless communication system or network logical
Letter.A/V input unit 42 is for receiving audio or video signal.The order that user input unit 43 can be inputted according to user is raw
The various operations of computer equipment 0 are controlled at key input data.The current state of the detection computer equipment 0 of sensing unit 44,
The position of computer equipment 0, user for the presence or absence of touch input of computer equipment 0, computer equipment 0 orientation, calculate
The acceleration or deceleration movement of machine equipment 0 and direction etc., and generate order or the letter for controlling the operation of computer equipment 0
Number.Interface unit 47 be used as at least one external device (ED) connect with computer equipment 0 can by interface.45 quilt of output unit
It is configured to provide output signal with vision, audio and/or tactile manner.Memory 46, which can store, to be executed by processor 48
The software program etc. of reason and control operation, or can temporarily store oneself data through exporting or will export.Memory
46 may include the storage medium of at least one type.Moreover, computer equipment 0 can execute memory with by network connection
The network storage device of 46 store function cooperates.The overall operation of the usually control computer equipment 0 of processor 48.In addition, place
Reason device 48 may include for reproducing or the multi-media module of multimedia playback data.Processor 48 can be with execution pattern identification at
The handwriting input executed on the touchscreen or picture are drawn input and are identified as character or image by reason.Power supply unit 49 exists
Electricity appropriate needed for receiving external power or internal power under the control of processor 48 and each element of operation and component being provided
Power.
The program that processor 48 is stored in memory 46 by operation, at various function application and data
Reason, such as realize the determination method at a type cluster center provided by the embodiment of the present disclosure, comprising: skill is encoded using geographical location
Each two-dimensional geographical location information that geographical location information to be processed is concentrated is converted to one-dimensional position encoded information by art;
Dictionary tree is generated according to each position encoded information, a tree node in the dictionary tree corresponds to the geography of a setting
The band of position, and the corresponding geographic location area of a child node belongs to geographical location corresponding with the father node of the child node
In regional scope;According to the positional relationship between each tree node and each geographical location information in the dictionary tree, with
And the quantitative value with each associated geographical location information of tree node, it is right respectively with each geographical location information to calculate
The density value answered;According to the density value, is concentrated in the geographical location information and determine at least one class cluster center.
Embodiment five
The embodiment of the present disclosure five also provides a kind of computer storage medium for storing computer program, the computer program
When being executed by computer processor for executing any data processing method of disclosure above-described embodiment: acquisition and source
The data modification information of code file association, wherein the sound code file is binary file;According to the data modification information
Data change type generates and the matched data processor of data modification information;Call the data processor pair
The sound code file is handled, and is formed and the matched new sound code file of the data modification information.
The computer storage medium of the embodiment of the present disclosure, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(Read Only Memory, ROM), erasable programmable read only memory ((Erasable Programmable Read
Only Memory, EPROM) or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic
Memory device or above-mentioned any appropriate combination.In this document, computer readable storage medium, which can be, any includes
Or the tangible medium of storage program, which can be commanded execution system, device or device use or in connection make
With.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, radio frequency (Radio Frequency, RF) etc. or above-mentioned any appropriate combination.
Can with one or more programming languages or combinations thereof come write for execute the disclosure operation computer
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language --- such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Note that above are only the preferred embodiment and institute's application technology principle of the disclosure.It will be appreciated by those skilled in the art that
The present disclosure is not limited to specific embodiments described here, be able to carry out for a person skilled in the art it is various it is apparent variation,
The protection scope readjusted and substituted without departing from the disclosure.Therefore, although being carried out by above embodiments to the disclosure
It is described in further detail, but the disclosure is not limited only to above embodiments, in the case where not departing from disclosure design, also
It may include more other equivalent embodiments, and the scope of the present disclosure is determined by the scope of the appended claims.
Claims (10)
1. the determination method at a type cluster center characterized by comprising
Using geographical location coding techniques, each two-dimensional geographical location information that geographical location information to be processed is concentrated is converted
For one-dimensional position encoded information;
Dictionary tree is generated according to each position encoded information, a tree node in the dictionary tree corresponds to a setting
Geographic location area, and the corresponding geographic location area of a child node belongs to geography corresponding with the father node of the child node
Within the scope of the band of position;
According to the positional relationship between each tree node and each geographical location information in the dictionary tree, and with it is described
The quantitative value of each associated geographical location information of tree node calculates density corresponding with each geographical location information
Value;
According to the density value, is concentrated in the geographical location information and determine at least one class cluster center.
2. the method according to claim 1, wherein according to in the dictionary tree each tree node with it is each described
Positional relationship between geographical location information, and the quantitative value with each associated geographical location information of tree node,
Calculate density value corresponding with each geographical location information, comprising:
According to geographic location area corresponding with the tree node each in the dictionary tree, it is right respectively with each tree node to calculate
The site error value and center geographical location information answered;
Calculate the difference and tree node in geographical location information and the dictionary tree between the center geographical location information of tree node
Site error value between numerical relation, and determined according to the numerical relation to the dictionary traversal of tree form and right
With the update mode of the density value of the geographical location information, until traverse the dictionary tree, to obtain and each geographical position
Confidence ceases corresponding density value.
3. according to the method described in claim 2, it is characterized in that, calculating tree node in geographical location information and the dictionary tree
Center geographical location information between difference and tree node site error value between numerical relation, and according to the numerical value
Relationship is determining to the dictionary traversal of tree form and to the update mode of the density value with the geographical location information, until
Traverse the dictionary tree, comprising:
A geographical location information of the geographical location information concentration is obtained as current location information, and is arranged described current
The initial density value of location information;
According to top-down sequence, a untreated tree node is successively obtained in the dictionary tree as current and compares section
Point, and calculate the current location information and currently compare the distance between the center geographical location information of node value with described;
If the distance value is less than or equal to first threshold, the density value of the current location information is updated to work as with described
The preceding quantitative value for comparing the associated geographical location information of node cumulative and, and by the current comparison node and with institute
The current corresponding whole child nodes of node that compare are stated labeled as processed node;Wherein, the first threshold be setting density away from
From threshold value and the difference currently compared between the site error value of node;
If the distance value is more than or equal to second threshold, keep the density value of the current location information constant, and by institute
State it is current compare node and with the corresponding whole child nodes of node that currently compare labeled as processed node;Wherein, institute
State second threshold be it is described setting density distance threshold and it is described currently compare between the site error value of node and value;
If the distance value is greater than the first threshold and is less than the second threshold, the current location information is kept
Density value is constant, and is processed node by the current comparison vertex ticks;
It returns and executes according to top-down sequence, a untreated tree node is successively obtained in the dictionary tree and is used as and is worked as
The preceding operation for comparing node, until the processing to tree nodes whole in the dictionary tree is completed, to obtain and the current location
The corresponding density value of information;
The operation for executing a geographical location information for obtaining the geographical location information concentration as current location information is returned,
Until completing the processing to whole geographical location information.
4. according to the method described in claim 2, it is characterized in that, according to corresponding with the tree node each in the dictionary tree
Geographic location area calculates site error value corresponding with each tree node and center geographical location information, comprising:
According to the height between geographic location area coboundary corresponding with the tree node each in the dictionary tree and lower boundary
Value calculates the corresponding site error value of each tree node;
According to the average value of the geographical location information of geographic location area corresponding with the tree node each in the dictionary tree, meter
Calculate the corresponding center geographical location information of each tree node;Wherein, the geographical location information includes latitude and longitude information.
5. the method according to claim 1, wherein according to the density value, in the geographical location information collection
At least one class cluster center of middle determination, comprising:
The class cluster distance of each geographical location information is calculated according to the corresponding density value of each geographical location information;
Each geographical location information is calculated according to the corresponding density value of each geographical location information and class cluster distance
Class cluster weight;
It is concentrated according to the class cluster weight in described geographical location information and determines at least one class cluster center.
6. according to the method described in claim 5, it is characterized in that, according to the corresponding density of each geographical location information
Value calculates the class cluster distance of each geographical location information, comprising:
Each geographical location information is ranked up according to setting rule according to the density value;
Successively calculated according to ranking results between each geographical location information and the forward geographical location information of sorting away from
From value as with a distance from class cluster to be screened;
Class cluster distance of the class cluster distance to be screened of class cluster range estimation condition as the geographical location information will be met.
7. method according to claim 1-6, which is characterized in that the geographical location information collection to be processed is
Track data of the target user in setting time section;
According to the density value, after the geographical location information is concentrated and determines at least one class cluster center, further includes:
Using at least one described class cluster center as the resident point of the target user.
8. the determining device at a type cluster center characterized by comprising
Info conversion module, for using geographical location coding techniques, by each two dimension of geographical location information concentration to be processed
Geographical location information be converted to one-dimensional position encoded information;
Dictionary tree generation module, for generating dictionary tree according to each position encoded information, a tree in the dictionary tree
Node corresponds to the geographic location area of a setting, and the corresponding geographic location area of a child node belongs to and the sub- section
Within the scope of the corresponding geographic location area of father node of point;
Density value computing module, for according to between each tree node and each geographical location information in the dictionary tree
Positional relationship, and the quantitative value with each associated geographical location information of tree node calculate and each geographical position
Confidence ceases corresponding density value;
Class cluster center determining module, for being concentrated in the geographical location information and determining at least one class according to the density value
Cluster center.
9. a kind of computer equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now determination method at the class cluster center as described in any in claim 1-7.
10. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the program is executed by processor
The determination method at class cluster center of the Shi Shixian as described in any in claim 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811246206.7A CN109299747B (en) | 2018-10-24 | 2018-10-24 | Method and device for determining cluster center, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811246206.7A CN109299747B (en) | 2018-10-24 | 2018-10-24 | Method and device for determining cluster center, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109299747A true CN109299747A (en) | 2019-02-01 |
CN109299747B CN109299747B (en) | 2020-12-15 |
Family
ID=65157705
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811246206.7A Active CN109299747B (en) | 2018-10-24 | 2018-10-24 | Method and device for determining cluster center, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299747B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110287426A (en) * | 2019-05-23 | 2019-09-27 | 北京百度网讯科技有限公司 | Method for building up, device, storage medium and the processor of point of interest set membership |
CN112330332A (en) * | 2021-01-05 | 2021-02-05 | 南京智闪萤科技有限公司 | Methods, computing devices, and media for identifying fraud risk with respect to node tasks |
CN117828382A (en) * | 2024-02-26 | 2024-04-05 | 闪捷信息科技有限公司 | Network interface clustering method and device based on URL |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103744861A (en) * | 2013-12-12 | 2014-04-23 | 深圳先进技术研究院 | Lookup method and device for frequency sub-trajectories in trajectory data |
CN104199860A (en) * | 2014-08-15 | 2014-12-10 | 浙江大学 | Dataset fragmentation method based on two-dimensional geographic position information |
US20150046473A1 (en) * | 2013-08-08 | 2015-02-12 | Academia Sinica | Social activity planning system and method |
US20150261786A1 (en) * | 2014-03-14 | 2015-09-17 | Twitter, Inc. | Density-based dynamic geohash |
CN107273471A (en) * | 2017-06-07 | 2017-10-20 | 国网上海市电力公司 | A kind of binary electric power time series data index structuring method based on Geohash |
CN107330466A (en) * | 2017-06-30 | 2017-11-07 | 上海连尚网络科技有限公司 | Very fast geographical GeoHash clustering methods |
CN107547633A (en) * | 2017-07-27 | 2018-01-05 | 腾讯科技(深圳)有限公司 | Processing method, device and the storage medium of a kind of resident point of user |
CN107911293A (en) * | 2017-10-31 | 2018-04-13 | 天津大学 | A kind of flow route tree constructing method based on geographical location |
CN108011987A (en) * | 2017-10-11 | 2018-05-08 | 北京三快在线科技有限公司 | IP address localization method and device, electronic equipment and storage medium |
CN108304502A (en) * | 2018-01-17 | 2018-07-20 | 中国科学院自动化研究所 | Quick hot spot detecting method and system based on magnanimity news data |
CN108536695A (en) * | 2017-03-02 | 2018-09-14 | 北京嘀嘀无限科技发展有限公司 | A kind of polymerization and device of geographical location information point |
-
2018
- 2018-10-24 CN CN201811246206.7A patent/CN109299747B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150046473A1 (en) * | 2013-08-08 | 2015-02-12 | Academia Sinica | Social activity planning system and method |
CN103744861A (en) * | 2013-12-12 | 2014-04-23 | 深圳先进技术研究院 | Lookup method and device for frequency sub-trajectories in trajectory data |
US20150261786A1 (en) * | 2014-03-14 | 2015-09-17 | Twitter, Inc. | Density-based dynamic geohash |
CN104199860A (en) * | 2014-08-15 | 2014-12-10 | 浙江大学 | Dataset fragmentation method based on two-dimensional geographic position information |
CN108536695A (en) * | 2017-03-02 | 2018-09-14 | 北京嘀嘀无限科技发展有限公司 | A kind of polymerization and device of geographical location information point |
CN107273471A (en) * | 2017-06-07 | 2017-10-20 | 国网上海市电力公司 | A kind of binary electric power time series data index structuring method based on Geohash |
CN107330466A (en) * | 2017-06-30 | 2017-11-07 | 上海连尚网络科技有限公司 | Very fast geographical GeoHash clustering methods |
CN107547633A (en) * | 2017-07-27 | 2018-01-05 | 腾讯科技(深圳)有限公司 | Processing method, device and the storage medium of a kind of resident point of user |
CN108011987A (en) * | 2017-10-11 | 2018-05-08 | 北京三快在线科技有限公司 | IP address localization method and device, electronic equipment and storage medium |
CN107911293A (en) * | 2017-10-31 | 2018-04-13 | 天津大学 | A kind of flow route tree constructing method based on geographical location |
CN108304502A (en) * | 2018-01-17 | 2018-07-20 | 中国科学院自动化研究所 | Quick hot spot detecting method and system based on magnanimity news data |
Non-Patent Citations (2)
Title |
---|
向隆刚等: "大规模轨迹数据的Geohash编码组织及高效范围查询", 《武汉大学学报(信息科学版)》 * |
赵鹏祥: "基于轨迹聚类的城市热点区域提取与分析方法研究", 《中国博士学位论文全文数据库_基础科学辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110287426A (en) * | 2019-05-23 | 2019-09-27 | 北京百度网讯科技有限公司 | Method for building up, device, storage medium and the processor of point of interest set membership |
CN110287426B (en) * | 2019-05-23 | 2021-12-31 | 北京百度网讯科技有限公司 | Method and device for establishing parent-child relationship of interest points, storage medium and processor |
CN112330332A (en) * | 2021-01-05 | 2021-02-05 | 南京智闪萤科技有限公司 | Methods, computing devices, and media for identifying fraud risk with respect to node tasks |
CN117828382A (en) * | 2024-02-26 | 2024-04-05 | 闪捷信息科技有限公司 | Network interface clustering method and device based on URL |
CN117828382B (en) * | 2024-02-26 | 2024-05-10 | 闪捷信息科技有限公司 | Network interface clustering method and device based on URL |
Also Published As
Publication number | Publication date |
---|---|
CN109299747B (en) | 2020-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111695697B (en) | Multiparty joint decision tree construction method, equipment and readable storage medium | |
Rawassizadeh et al. | Scalable daily human behavioral pattern mining from multivariate temporal data | |
TW201935273A (en) | A statement user intention identification method and device | |
CN111382174B (en) | Multi-party data joint query method, device, server and storage medium | |
Sturm et al. | On cones of nonnegative quadratic functions | |
CN109299747A (en) | Determination method, apparatus, computer equipment and the storage medium at one type cluster center | |
CN110225368B (en) | Video positioning method and device and electronic equipment | |
US10346737B1 (en) | Distributed multisensor system to record spatially diverse events | |
Zhang et al. | Modeling and computing probabilistic skyline on incomplete data | |
Li et al. | Using granule to search privacy preserving voice in home IoT systems | |
CN111062431A (en) | Image clustering method, image clustering device, electronic device, and storage medium | |
CN110825863B (en) | Text pair fusion method and device | |
CN116894085A (en) | Dialog generation method and device, electronic equipment and storage medium | |
Karim et al. | Spatiotemporal Aspects of Big Data. | |
KR102157175B1 (en) | Multimedia contents recommendation method considering mood tags and synonyms in social networks | |
Toader et al. | A new modelling framework over temporal graphs for collaborative mobility recommendation systems | |
CN116112282A (en) | User information sharing management method, system and storage medium based on big data | |
Luo et al. | Timestamps as Prompts for Geography-Aware Location Recommendation | |
CN113808582B (en) | Speech recognition method, device, equipment and storage medium | |
US9202472B1 (en) | Magnitude ratio descriptors for pitch-resistant audio matching | |
CN113010769A (en) | Knowledge graph-based article recommendation method and device, electronic equipment and medium | |
CN111382233A (en) | Similar text detection method and device, electronic equipment and storage medium | |
CN108984666A (en) | Data processing method, data processing equipment and server | |
CN116561735B (en) | Mutual trust authentication method and system based on multiple authentication sources and electronic equipment | |
CN116910372B (en) | Information push model processing method and device, information push method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |