CN106681996A - Method and device for determining interest areas and interest points within geographical scope - Google Patents
Method and device for determining interest areas and interest points within geographical scope Download PDFInfo
- Publication number
- CN106681996A CN106681996A CN201510746851.5A CN201510746851A CN106681996A CN 106681996 A CN106681996 A CN 106681996A CN 201510746851 A CN201510746851 A CN 201510746851A CN 106681996 A CN106681996 A CN 106681996A
- Authority
- CN
- China
- Prior art keywords
- information point
- information
- point
- value
- threshold 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and device for determining interest areas and interest points within a geographical scope. The method for determining interest areas within a geographical scope comprises following steps: obtaining all information points within the geographical area; selecting a plurality of information points containing the same keywords and the number is larger than a first preset threshold value; determining an information point a at a central position and determining an information point b which is the farthest away from the center position through calculating the distance among the plurality of information points; segmenting the distance value between the information point a and the information point b and screening information points whose numbers are larger than a second threshold value within each segment; calculating the number of information points containing the same keywords enclosed by the above screened information points and keeping the information points whose numbers are larger than a third threshold value; determining interest areas from the kept information points.
Description
Technical field
The present invention relates to the data processing field of electronic chart, and in particular to it is determined that emerging in geographical scope
Interesting region, the method and apparatus of point of interest.
Background technology
Geographic range would generally be marked in electronic map data, user can identify according to electronic chart
The geographic ranges such as province, city, district, but existing geographic range is larger, leads in geographic range
Often also include multiple more specifically regions, such as Xicheng District of Beijing, the scope of Xicheng District
Data can be identified according to the map, but also include Xidan area etc. more specifically in Xicheng District
Region, user cannot determine the scope in such region.
At present interest region partitioning method is with some object (such as one road in map datum
Road, an information point) based on, to the objects perimeter a certain distance is spread as interest region,
Or according to preset range (such as specific trellis) by map partitioning be multiple regions, each preset
Region may each be interest region, above two mode be suitably applied the less area of information point or
Remote districts, area that arrangement situation complicated more for information points such as cities, existing region of interest
Domain classification method accuracy is poor.
Also, above- mentioned information point screening technique lacks Regional Analysis, typically in geographic range,
Directly screened according to the temperature of information point, this can cause the information point in non-hot spot areas to lack,
Screening efficiency is relatively low.
The content of the invention
In consideration of it, the present invention provides a kind of method for determining interest region in geographical scope, the method bag
Include：Obtain the information point in geographic range；Choose from above- mentioned information point comprising same keyword and number
Multiple information points of the amount more than the first predetermined threshold value；Distance between the plurality of information point is calculated, really
An information point for being located at center is made, a is designated as, and the result calculated by the distance is determined
Information point b maximum with the distance value between information point a；To the distance between information point a and information point b
Value is segmented, and filters out information point c of the quantity more than the second predetermined threshold value in each section；Calculate above-mentioned
The quantity of the information point comprising the same keyword around each information point c for filtering out, and encumbrance
Information point c of the amount more than or equal to the 3rd predetermined threshold value；It is pre- more than or equal to the 3rd according to the quantity of above-mentioned reservation
If information point c of threshold value determines interest region.
Correspondingly, the present invention provides a kind of device for determining interest region in geographical scope, including：Obtain
Unit is taken, for obtaining the information point in geographic range；Unit is chosen, for from above- mentioned information point
Choose comprising same keyword and quantity is more than multiple information points of the first predetermined threshold value；Information point determines
Unit, for calculating the distance between the plurality of information point, determines that is located at a center
Information point, is designated as a, and the result calculated by the distance is determined and the distance value between information point a
Maximum information point b；First screening unit, for entering to the distance value between information point a and information point b
Row segmentation, filters out information point c of the quantity more than the second predetermined threshold value in each section；Second screening unit,
For calculating the number of the information point comprising the same keyword around above-mentioned each information point c for filtering out
Amount, and retain information point c of the quantity more than or equal to the 3rd predetermined threshold value；Area determination unit, for root
Determine interest region more than or equal to information point c of the 3rd predetermined threshold value according to the quantity of above-mentioned reservation.
In addition, the present invention provides a kind of point of interest screening technique, the method includes：Using above-mentioned determination
The method in interest region determines interest region in geographic range；According to information in the interest region
The included information sifting of point goes out at least one information point, and at least one information point that this is filtered out is emerging
Interesting point.
Correspondingly, the present invention also provides a kind of point of interest screening plant, including：Interest region determines single
Unit, for determining interest region using the method in interest region in above-mentioned determination geography scope；Screening is single
Unit, for going out at least one information according to the information sifting that information point is included in the interest region
Point, at least one information point that this is filtered out is point of interest.
It is provided in an embodiment of the present invention to determine interest region, the method and apparatus of point of interest in geographical scope
Map datum can be divided into multiple semi-cylindrical hills, feature phase is then filtered out in interest region
The information point of a relatively high to obvious, popularity, the information point can be used as the terrestrial reference in interest region
Property building, the information point for filtering out can apply to several scenes, for example can should in some service classes
With, as standard information point, or being highlighted in map datum in program, user is allow
More easily search information point.
Description of the drawings
In order to be illustrated more clearly that the specific embodiment of the invention or technical scheme of the prior art, under
Face will be briefly described to the accompanying drawing to be used needed for specific embodiment or description of the prior art,
It should be evident that drawings in the following description are some embodiments of the present invention, it is general for this area
For logical technical staff, on the premise of not paying creative work, can be being obtained according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is the stream of the method in interest region in the determination geographic range for providing according to embodiments of the present invention
Cheng Tu；
Fig. 2 is the arrangement situation schematic diagram of the multiple information points chosen；
Fig. 3 is the schematic diagram processed information point shown in Fig. 2；
Fig. 4 is the schematic diagram being further processed to result shown in Fig. 3；
Fig. 5 be information point shown in Fig. 4 is processed after determine interest area schematic；
Fig. 6 is the flow chart of the point of interest screening technique for providing according to embodiments of the present invention；
Fig. 7 is the knot of the device in interest region in the determination geographic range for providing according to embodiments of the present invention
Composition；
Fig. 8 is the structure chart of the point of interest screening plant for providing according to embodiments of the present invention.
Specific embodiment
Technical scheme is clearly and completely described below in conjunction with accompanying drawing, it is clear that
Described embodiment is a part of embodiment of the invention, rather than the embodiment of whole.Based on this
Embodiment in bright, those of ordinary skill in the art are obtained under the premise of creative work is not made
Every other embodiment, belong to the scope of protection of the invention.
In order to succinct and directly perceived on describing, hereafter by describing some representational embodiments come to this
The scheme of invention is illustrated.Substantial amounts of details is only used for help and understands the solution of the present invention in embodiment.
However, it will be apparent that technical scheme can be not limited to these details when realizing.In order to avoid
The solution of the present invention is unnecessarily obscured, some embodiments are not meticulously described, but
Only give framework.Hereinafter, " including " refer to " including but not limited to ", " according to ... "
Refer to " according at least to ..., but be not limited to according only to ... ".Hereinafter it is not specifically stated one
During the quantity of composition, it is meant that it can also be multiple that the composition can be one, or can be regarded as at least
One.
The method in interest region, information point screening technique in determination geographic range in the embodiment of the present invention
Can be set by the calculating of the various methods and software systems that can realize the embodiment of the present invention with device
It is standby to realize.The computing device can be that by method provided in an embodiment of the present invention and software systems
Computing device.The computing device can be PC or portable equipment, such as notebook computer,
Panel computer, mobile phone or smart mobile phone etc..The computing device to can also be and pass through network with the said equipment
Connected server.
The computing device can have different performance and feature.Various possible implementations all exist
In the protection domain of this paper.For example, computing device can include key zone/keyboard, can also include one
Individual display, such as liquid crystal display (LCRD), or the display with Premium Features, for example, touch
Touch sensing 2RD or 3RD displays.In one example, a computing device with web functions can
To include one or more physical keyboards or dummy keyboard, and mass storage device.
Computing device can also include or allow various operating systems, including or run various application programs,
Such as coding/decoding application.Application program can be encrypted with miscellaneous equipment by network and be communicated.
Additionally, computing device can also include that the readable non-volatile memories of one or more processors are situated between
Matter and the processor that one or more communicate with storage medium.For example, readable non-volatile of processor
Storage medium can be RAM, flash memory, ROM, EPROM, EEPROM, register, hard disk, mobile hard
Disk, CRD-ROM, or other various forms of non-volatile memory mediums.Storage medium can store one
Series of instructions or unit and/or module comprising instruction, for completing the behaviour of various embodiments of the invention
Make.Processor can perform above-mentioned instruction, complete the operation in various embodiments.
The embodiment of the present invention provides a kind of method for determining interest region in geographical scope, as shown in figure 1,
The method comprises the steps：
S1, obtains the information point in geographic range.Geographic range can be administrative division, such as Beijing
The region of the known boundaries such as city Chaoyang District, Haidian District, or state, town.Information point data is existing
Data have and opening, each information point data at least includes title, classification, longitude latitude
The information (reference information) such as degree, neighbouring other information point, some information points also have rich information, example
Such as hotel information point, including the class information (such as 0-5 stars) in hotel, and for example for
Residential quarter information point, it includes the information such as resident family's quantity, flat price.
S2, chooses comprising same keyword from above- mentioned information point and quantity is more than the first predetermined threshold value
Multiple information points.Vocabulary technology of identification can be specifically utilized, in title, address respectively from information point
Keyword is identified, it is then determined which information point includes same keyword.Keyword can not deposited
" east in " Xidan ", Dongcheng District in the title of the region on concrete border, such as Xicheng District of Beijing
It is single " etc..Multipacket message point would generally be filtered out for some geographic range, each group information point is equal
Including same keyword, but the information point quantity in some groups may be less, and this situation represents the group
The cognition degree of the keyword that information point includes is not high enough, therefore should choose a fairly large number of information click-through
Row subsequent treatment.By taking geographic range-Beijing " Xicheng District " as an example, it is assumed that comprising keyword " Xidan "
Information point quantity be more than predetermined threshold value, according to comprising keyword " Xidan " information point in map
In arrangement situation understand some information point Relatively centralizeds, some information points may relative distributions.Assume
After the process of step S2, multiple information points as shown in Figure 2 are have chosen, intuitively according to Fig. 2
In information point arrange situation it is found that information point P1 and information point P2 are the scattered information of comparison
Point.
Scattered information point of arranging will affect final region division result, it is therefore desirable to from above-mentioned many
The scattered information point in position is found out and removed in individual information point.It will be understood by those skilled in the art that really
Each other whether centralised or decentralised method has various to fixed multiple points, for example can be according to each two point
The distance between, get rid of the larger point of distance value.Removal is discussed in detail with reference to Fig. 3 and Fig. 4
The process of dispersed information point.
S3, calculates the distance between the plurality of information point, determines a letter for being located at center
Breath point, is designated as a, and the result calculated by the distance determine and the distance value between information point a most
Big information point b, information point a is the middle site of all information points.Those skilled in the art can manage
Solution, the method in site has various in finding in multiple points that position is fixed, by calculating between each point
Distance value can find out middle site.For situation shown in Fig. 3, information point P0 is located at center
The information point of position, is designated as a；Information point P1 range information point P0 is farthest, therefore information point
The information point of the distance value maximum between P1 and information point a, is designated as b.,
S4, is segmented to the distance value between information point a and information point b, filters out number in each section
Information point c of the amount more than the second predetermined threshold value.As shown in figure 3, the present embodiment is by information point a and information
The distance value of point b is 5 sections in Rmax minute, and 5 distance value intervals are determined after segmentation, is then then counted
Calculate the information point quantity in each interval and judged, retain if quantity is more than the second preset value,
Otherwise remove.Assume that the second predetermined threshold value is 2, then may determine that in the interval that information point b is located only
There is its 1 information point, the information point quantity in other intervals is all higher than or equal to 2, thereby determines that information
Point b is removed, that is, remove Fig. 3 in P1, other information point P0, P2, P3, P4, P5, P6,
P7, P8, P9, P10 temporarily retain, and the information point of reservation is designated as into c.
S5, calculates the information point comprising the same keyword around above-mentioned each information point c for filtering out
Quantity, if negligible amounts, then it represents that around the information point equally comprising the keyword information point
Less, information point arrangement then represents that information point arrangement is concentrated than relatively decentralized, thus, can
With and retain quantity more than or equal to the 3rd predetermined threshold value information point c.Above-mentioned " surrounding " is a scope
Value, for example, can be radius, a value range can be set when actually used, then within the range
Judge the quantity comprising above-mentioned keyword.It is assumed that value range take N*Rd, the 3rd preset
Threshold value value is 1, then the information point quantity only around information point P2 is 0, so further removing
Information point P2, retain other qualified information points P0, P3, P4, P5, P6, P7, P8, P9,
P10。
S6, interest is determined according to the quantity of above-mentioned reservation more than or equal to information point c of the 3rd predetermined threshold value
Region.By above-mentioned steps S2-S5, information point P1 and information point P2 are removed, then for example may be used
To utilize information point P0, P3, P4, P5, P6, P7, P8, P9, P10 for retaining according to algorithm of convex hull
Minimum external chimb row region is constructed, Fig. 5 shows the interest region determined according to this method, and this is emerging
There are the intensive multiple information points of arrangement in interesting region.
The method in interest region in the determination geographic range for providing according to embodiments of the present invention, by obtaining
All information points and the multiple information points comprising same keyword are filtered out in geographic range, it may be determined that
Go out the multiple information points containing same keyword, the information point of predetermined threshold value then whether is more than to quantity
Processed, removed the wherein scattered information point in position, finally determined according to the multiple information points for retaining
Interest region, can further determine that out more specifically interest region, interest region in geographic range
The information point including same keyword is inside, it is possible thereby to improve the accuracy of ground interest regional extent.
Used as a kind of preferred embodiment, above-mentioned steps S3 can include following sub-step：
S31, calculates respectively each information point (excellent apart from sum with all information points in addition to itself
Air line distance is elected as but it is also possible to be the route distance in map, hereafter by taking air line distance as an example),
And determine apart from minimum information point a of sum.
S32, calculates respectively the distance of the information point in addition to information point a and information point a, and determines have
Information point b of maximum range value；As shown in figure 3, ultimate range is Rmax (information point P0 and information
The distance between point P1).
The distance of all information points of the above-mentioned preferred version by each information point of calculating and in addition to itself
Sum, site in more accurately can finding in multiple information points, and it is farthest to find site in distance
Information point.
Used as a kind of preferred embodiment, above-mentioned steps S4 can include following sub-step：
S41, is segmented to ultimate range Rmax, it is preferred to use the method for decile, determines segments
Amount N, it is N sections that Rmax is divided, Ri=i/N Rmax, it will be understood by those skilled in the art that using it
His segmentation method, such as golden section are all feasible.
S42, calculates respectively the quantity of the information point in each section, i.e. calculating distance is between [0, R1]
Information between quantity x2 of the information point between quantity x1 of information point, [R1, R2], [R2, R3]
Quantity x3 of point, until quantity xn of the information point between [Rn, Rmax] is calculated, above-mentioned each interval
Can be expressed as [Rmax/N* (n-1), Rmax/N* (n)], wherein n is positive integer, span is
[1, n] and n≤N, N are the positive integer more than 1, such as above-mentioned N values are 5, you can obtain [0,
Rmax/5] quantity X1 of information point, quantity X2 of the information point of [Rmax/5, Rmax/5*2],
The letter of quantity X2 of the information point of [Rmax/5*2, Rmax/5*3], [Rmax/5*3, Rmax/5*4]
Quantity X3, quantity X4 of the information point of [Rmax/5*4, Rmax] of breath point；
S43, filters out quantity more than the information point in the section of the second predetermined threshold value.For example judge respectively
Whether X1-X4 is more than predetermined threshold value, it is assumed that the second predetermined threshold value value is 2, then can according to result of determination
To determine that information point P1 is removed, other information point is retained, that is, it is [0, Rmax/5*4] to retain distance
Between information point, remove distance for [Rmax/5*4, Rmax] information point.
Above-mentioned preferred version is segmented to maximum range value, and judges the information in each segmentation successively
The quantity of point, and retain information point of the quantity more than predetermined threshold value, it is possible thereby to it is relative to get rid of distribution
Scattered information point.
Used as a kind of preferred embodiment, above-mentioned steps S5 can include following sub-step：
S51, the average distance Rd between the information point that calculating sifting goes out；
S52, includes the same keyword in the range of N*Rd around the information point that respectively calculating sifting goes out
Information point quantity, if number is less, then it represents that around the information point equally include the keyword
Information point it is less, information point arrangement then represents that information point arrangement is concentrated than relatively decentralized；
S53, the quantity for removing the information point comprising the same keyword in the range of surrounding N*Rd is less than
The information point of the 3rd predetermined threshold value, as shown in figure 4, such as predetermined threshold value value is 1, then only information
Information point quantity around point P2 in the range of N*Rd is 0, so removing information point P2, retains other
Qualified information point.
Above-mentioned preferred version calculates first the average distance Rd between information point, then with average distance
Rd and coefficient N be according to come judge in the range of each information point N*Rd whether there is enough information
Point, it is possible thereby to further get rid of the scattered information point of arrangement, arranges the information point for finally retaining
Cloth density is sufficiently high.
Another embodiment of the present invention provides a kind of point of interest screening technique, the method bag as shown in Figure 6
Include following steps：
S ' 1, using the method in interest region in the determination geographic range in previous embodiment interest is determined
, generally there is more information point in interest region in region；
S ' 2, at least one letter is gone out in the interest region according to the information sifting that information point is included
Breath point, at least one information point that this is filtered out is point of interest (Point of Interest, POI),
The point of interest compares the other information point in interest region, with higher popularity or more obviously special
Levy.It will be understood by those skilled in the art that the method for filter information point has various, for example can basis
The temperature (by user's inquiry, the number of times for selecting, submitting in various application systems) of information point is carried out
Sequence, the information point for selecting temperature higher.
The point of interest screening technique for providing according to embodiments of the present invention, can be divided into map datum many
Individual area-of-interest, then filters out feature obvious, popularity relatively of a relatively high in interest region
Information point, the information point for filtering out can be as the landmark in interest region or referred to as emerging
Interesting, the information point for filtering out can apply to several scenes, for example can be in some service class applications
As standard information point in program, or highlighted in map datum, allow user more
It is convenient to search information point.
As one preferred embodiment, ' 2 of step S in the present embodiment specifically can include：
S ' 21, determines the characteristic value of all information points in the interest region, those skilled in the art
It is appreciated that determining the method for the characteristic value of information point has various, for example can receiving according to information point
Determining, existing feature value calculating method is all feasible to the factors such as attention degree；
S ' 22, using support vector cassification model, the characteristic value with described information point is as input value pair
Information point is screened.SVMs (SVM, Support Vector Machine) be to it is related
The relevant supervised learning model of learning algorithm, can with analyze data, recognition mode, for classification and
Regression analysis.Supporting vector machine model can be trained by the sample data for giving and be obtained, this
Sample data in bright can be classified as two classes, and a class is qualified target sample, and another kind of is not to be inconsistent
The non-targeted samples of conjunction condition.May determine that using the supporting vector machine model obtained through training
Whether given information point is target information point.
The present embodiment preferably uses multiple characteristic values and information point is screened, i.e. the characteristic value of information point
Including the First Eigenvalue, Second Eigenvalue and third feature value, the wherein computational methods of the First Eigenvalue
Including：
Type and the number of times that information point is cited is calculated according to the address information of information point, is each species
Type gives weight, and the First Eigenvalue of information point is then calculated according to reference type weight and reference number of times.
Preferably, above-mentioned reference type at least includes three classes：
The first kind is cited in another information point differed by geographical position.For example there are two information points：
Information point 1- Hai Dianqiao, information point 2- China's technology business mansion, the address information of information point 2 includes
" Haidian Qiao Dong China's technology businesses mansion ", then information point 1- Haidian bridge is by information point 2- China technology
Transaction mansion is quoted once, and the reference is properly termed as external reference；
Equations of The Second Kind is cited in public transport category information point.Such as information point 1- Hai Dianqiao, information point 2- sea
Dian Qiaodong bus stations, then information point 1- Haidian bridge by information point 2- Haidian Qiao Dong bus stations quote once,
The reference is properly termed as public transport reference；
3rd class is cited in another information point of geographical position identical.For example there are two information points：
Information point 1- China's technology business mansion, information point 2- beta coffee shop, the address information of information point 2
Including " Chinese technology business mansion B1 floor beta coffees ", information point 1- China's technology business mansion quilt
Information point 2- beta coffee shop quotes once, and the reference is properly termed as internal reference.
The type and number of times that each information point is cited may be differed, and some information points may
Belong to many class references simultaneously, therefore the First Eigenvalue can be calculated using following equation：
Y1=information points AX1+BX2+CX3,
Wherein Y1 is the First Eigenvalue, and information point A, B, C are the weight of three kinds of reference types, X1,
X2, X3 are the reference number of times of corresponding reference type, and information point A, B, C can take arbitrary value, the power
The importance for embodying reference type is reused in, for example, can be information point A>B>C or information point
A=B=C.It will be understood by those skilled in the art that above-mentioned formula is simply to illustrate that the thing of the First Eigenvalue
The specific embodiment managed implication and enumerate, during practical application, can also be by more simply or more
Complicated algorithm calculates the fisrt feature of information point using reference type weight and number of times the two information
Value.
The computational methods of above-mentioned Second Eigenvalue include：
The numerical information included according to information point and maximum preset numerical value and minimum default value are calculated
The Second Eigenvalue of information point, it will be understood by those skilled in the art that in information point, except name information,
Beyond address information, reference information, also with rich information, the rich information of various information point is differed,
Such as there are corresponding class information in hotel's class, hospital's class, scenic spot class, government bodies, and house class has
The information such as inhabitation amount, price, food and drink class has the information such as comment quantity or point score value, above-mentioned rich letter
Breath is numerical information, can be with the numerical information in Extracting Information point, then according to letter during practical application
The type of breath point, determines the maximum and minimum of a value of the numerical information of such information point.For example for wine
For the category information point of shop, its maximum can take 5, and minimum of a value can take 0, then can be according to the wine
The actual grade information of shop information point and maximum, the ratio of minimum of a value are determining Second Eigenvalue.It is right
Also can be calculated in this manner in other kinds of information point.It will be understood by those skilled in the art that
The calculation of above-mentioned Second Eigenvalue simply to illustrate that the physical meaning of Second Eigenvalue and enumerate
One specific embodiment, can also be counted during practical application using simpler or more complicated mode
Calculate.
The computational methods of above-mentioned third feature value include：
Selected operation of the different application to information point is used according to user, determines what user was used
Application program and accordingly selected number of times, are that each application program gives weights, then according to weights
With the third feature value that selected number of times calculates information point.For example for some information point, user uses
Application program 1 selectes information point X1 time, and user selectes information point X2 using application program 2
Secondary ... user selectes information point Xn time using application program n, and thus, third feature value can be by
Calculated according to following formula：
Y3=information point AX1+BX2+ ...+NXn,
Wherein Y3 is third feature value, and information point A, B ... N is the weight of n kind application programs, on
Stating weight can any value, it is possible to give higher weight etc. for specific application program.Ability
Field technique personnel be appreciated that above-mentioned formula simply to illustrate that the physical meaning of third feature value and lift
The specific embodiment for going out, during practical application, can also pass through simpler or more complicated algorithm
The third feature value of information point is calculated using Application Type weight and number of times the two information.
The rich letter of situation, user's submission situation and information point that above-mentioned preferred version is cited with information point
Breath is foundation, and information point is screened using machine learning model, it is possible thereby to make screening mode
It is more targeted, and improve screening efficiency.
It will be understood by those skilled in the art that support vector cassification model is using substantial amounts of sample number
According to obtained from constantly training.In order to improve the classification performance of support vector cassification model, as institute
State the target information point training sample of support vector cassification model characteristic value (the First Eigenvalue,
Two characteristic values and third feature value) default characteristic threshold value is all higher than, the default characteristic threshold value includes that this is emerging
Same category letter in the average characteristics threshold value of all information points in interesting region and/or the interest region
The average characteristics threshold value of breath point.
Due to potentially including the higher information point of many popularity, such as Xidan area in an interest region
There are many market category information points in domain, many markets all may be determined when using above-mentioned model discrimination
For target information point, but this does not meet direct feel of the user to popularity.In certain region, use
Family is typically only capable to remember top to the information point of some classification, so certain classification in regional area
Target information point be excessively irrational, in order to further screen to target information point, we
Method can also comprise the steps：
S ' 3, chooses the multiple information points of type identical；
S ' 4, according to the sequence that features described above value carries out from high to low to the multiple information points of type identical,
Then the same type of target information point of top n is retained, it is possible thereby to make the knowledge of information point for filtering out
Bie Dugenggao, improves the experience of user.
An alternative embodiment of the invention also provides a kind of device for determining interest region in geographical scope,
As shown in fig. 7, the device includes：
Acquiring unit 71, for obtaining the information point in geographic range；
Unit 72 is chosen, for choosing from above- mentioned information point comprising same keyword and quantity more than the
Multiple information points of one predetermined threshold value；
Information point determining unit 73, for calculating the distance between the plurality of information point, determines one
The individual information point positioned at center, is designated as a, and the result calculated by the distance is determined and the letter
Information point b of the distance value maximum between breath point a；
First screening unit 74, for being segmented to the distance value between information point a and information point b,
Filter out information point c of the quantity more than the second predetermined threshold value in each section；
Second screening unit 75, for calculating around above-mentioned each information point c for filtering out comprising described same
The quantity of the information point of one keyword, and retain information point c of the quantity more than or equal to the 3rd predetermined threshold value；
Area determination unit 76, for being more than or equal to the 3rd predetermined threshold value according to the quantity of above-mentioned reservation
Information point c determines interest region.
Said apparatus are by all information points in acquisition geographic range and filter out comprising same keyword
Multiple information points, it may be determined that go out the multiple information points containing same keyword, then to quantity whether
Processed more than the information point of predetermined threshold value, removed the wherein scattered information point in position, final basis
The multiple information points for retaining determine interest region, can further determine that out in geographic range more specific
Interest region, the information point including same keyword is in interest region, it is possible thereby to improve ground
The accuracy of interest regional extent.
Preferably, described information point determining unit 73 includes：
Middle site determining unit, for calculating each information point respectively with all information in addition to itself
Between point apart from sum, and determine apart from minimum information point a of sum；
Solstics determining unit, for calculating the information point in addition to information point a and information point a respectively
Between distance, and determine with maximum range value information point b.
The distance of all information points of the above-mentioned preferred version by each information point of calculating and in addition to itself
Sum, site in more accurately can finding in multiple information points, and it is farthest to find site in distance
Information point.
Preferably, first screening unit 74 includes：
Segmenting unit, for being segmented to the maximum range value；
First amount calculation unit, for calculating the quantity of the information point in each section respectively；
Sub- screening unit, for filtering out the information point in section of the quantity more than the second predetermined threshold value, note
For information point c.
Preferably, the segmenting unit includes：
Number of fragments determining unit, for determining number of fragments；
Deng subdivision, for carrying out decile to the maximum range value according to the number of fragments.
Above-mentioned preferred version is segmented to maximum range value, and judges the information in each segmentation successively
The quantity of point, and retain information point of the quantity more than predetermined threshold value, it is possible thereby to it is relative to get rid of distribution
Scattered information point.
Preferably, second screening unit 75 includes：
Average distance computing unit, the average distance Rd between information point c gone out for calculating sifting；
Second amount calculation unit, around each information point gone out for calculating sifting respectively in the range of N*Rd
The quantity of the information point comprising the same keyword；
Removal unit, for the information point comprising the same keyword in the range of N*Rd around removing
Information point c of the quantity less than the 3rd predetermined threshold value.
Above-mentioned preferred version calculates first the average distance Rd between information point, then with average distance
Rd and coefficient N be according to come judge in the range of each information point N*Rd whether there is enough information
Point, it is possible thereby to further get rid of the scattered information point of arrangement, arranges the information point for finally retaining
Cloth density is sufficiently high.
An alternative embodiment of the invention also provides a kind of point of interest screening plant, as shown in figure 8, should
Device includes：
Interest area determination unit 81, for the determination geography model provided using above-mentioned one embodiment
The method for enclosing interior interest region determines interest region；
Screening unit 82, for being gone out according to the information sifting that information point is included in the interest region
At least one information point, at least one information point that this is filtered out is point of interest.
Map datum can be divided into multiple semi-cylindrical hills, Ran Hou by above-mentioned point of interest screening plant
The feature of a relatively high information point of obvious, popularity relatively is filtered out in interest region, the information point can
So that used as the landmark in interest region, the information point for filtering out can apply to several scenes,
For example in some service class application programs as standard information point, or can enter in map datum
Row is highlighted, and allows user more easily to search information point.
Preferably, above-mentioned screening unit 82 can include：
Characteristic value determination subelement, for determining the characteristic value of all information points in the interest region；
Classification subelement, for using support vector cassification model, the characteristic value with described information point is
Input value is screened to information point.
Preferably, the characteristic value includes fisrt feature, second feature and third feature value, wherein
The First Eigenvalue is the corresponding reference weights of type and reference time being cited according to information point
Number is calculated；
The characteristic value also includes Second Eigenvalue, and the Second Eigenvalue is included according to information point
Numerical information and maximum preset numerical value and minimum default value it is calculated；
The third feature value is to submit to the application program that described information point is used corresponding according to user
Carry out using weights and submission number of times calculated.
Preferably, the type being cited includes that another information point differed by geographical position is drawn
With, cited in public transport category information point, cited in another information point of geographical position identical.
Situation, rich information, the user of information point that above-mentioned preferred version is cited with information point is in difference
The situation of selected information point is foundation in scene, and information point is screened using machine learning model,
It is possible thereby to make screening mode more targeted, and improve screening efficiency.
Preferably, the information point of the training sample for meeting screening conditions of support vector cassification model
Characteristic value is all higher than default characteristic threshold value, presets characteristic threshold value including all to be screened in interest region
Information point same category of to be screened in the average characteristics threshold value of information point and/or interest region it is flat
Equal characteristic threshold value.Above-mentioned training sample can improve the classification performance of support vector cassification model.
Preferably, above- mentioned information point screening plant can also include：
Unit 83 is chosen, for choosing the multiple information points of type identical；
Removal unit 84, for being carried out from high to low to the multiple information points of type identical according to characteristic value
Sequence, then retain forward at least one information point of sequence.Above-mentioned preferred version can make screening
The resolution of the information point for going out is higher, improves the experience of user.
Obviously, above-described embodiment is only intended to clearly illustrate example, and not to embodiment party
The restriction of formula.For those of ordinary skill in the field, may be used also on the basis of the above description
To make other changes in different forms.There is no need to give all of embodiment
With exhaustion.And the obvious change thus extended out or change guarantor still in the invention
Among shield scope.
Claims (22)
1. a kind of method for determining interest region in geographical scope, it is characterised in that include：
Obtain the information point in geographic range；
Choose from above- mentioned information point comprising same keyword and quantity is multiple more than the first predetermined threshold value
Information point；
Distance between the plurality of information point is calculated, an information point for being located at center is determined,
It is designated as a, and the letter that the result calculated by the distance is determined and the distance value between information point a is maximum
Breath point b；
Distance value between information point a and information point b is segmented, quantity in each section is filtered out big
In information point c of the second predetermined threshold value；
Calculate the number of the information point comprising the same keyword around above-mentioned each information point c for filtering out
Amount, and retain information point c of the quantity more than or equal to the 3rd predetermined threshold value；
Interest region is determined more than or equal to information point c of the 3rd predetermined threshold value according to the quantity of above-mentioned reservation.
2. method according to claim 1, it is characterised in that described to the plurality of information point
Between distance calculate, determine an information point for being located at center, be designated as a, and by it is described away from
Information point b of the distance value maximum between the result determination and information point a for calculating, including：
Calculate respectively between each information point and all information points in addition to itself apart from sum, and really
Minimum information point a of set a distance sum；
The information point in addition to information point a and the distance between information point a are calculated respectively, and determine have
Information point b of maximum range value.
3. method according to claim 2, it is characterised in that described to information point a and information
Distance value between point b is segmented, and filters out information of the quantity more than the second predetermined threshold value in each section
Point c, including：
The maximum range value is segmented；
The quantity of the information point in each section is calculated respectively；
Quantity is filtered out more than the information point in the section of the second predetermined threshold value, information point c is designated as.
4. method according to claim 3, it is characterised in that described to the maximum range value
Carrying out segmentation includes：
Determine number of fragments；
Decile is carried out to the maximum range value according to the number of fragments.
5. method according to claim 1, it is characterised in that the calculating is above-mentioned to be filtered out
Around each information point c comprising the same keyword information point quantity, and retain quantity more than etc.
In information point c of the 3rd predetermined threshold value, including：
Average distance Rd between information point c that calculating sifting goes out；
Letter comprising the same keyword in the range of N*Rd around each information point that respectively calculating sifting goes out
The quantity of breath point；
The quantity of the information point comprising the same keyword is pre- less than the 3rd in the range of N*Rd around removing
If information point c of threshold value.
6. a kind of point of interest screening technique, it is characterised in that include：
Method using interest region in the determination geographic range any one of claim 1-5 is true
Make interest region；
At least one information point is gone out according to the information sifting that information point is included in the interest region,
At least one information point that this is filtered out is point of interest.
7. point of interest screening technique according to claim 6, it is characterised in that described described
Going out at least one information point according to the information sifting that information point is included in interest region includes：
Determine the characteristic value of all information points in the interest region；
Using support vector cassification model, the characteristic value with described information point is input value to information point
Screened.
8. point of interest screening technique according to claim 7, it is characterised in that the characteristic value
Including the First Eigenvalue, Second Eigenvalue and third feature value,
Wherein, the First Eigenvalue be the type being cited according to information point it is corresponding quote weights and
Quote number of times calculated；
The Second Eigenvalue be the numerical information that included according to information point and maximum preset numerical value and
Minimum default value is calculated；
The third feature value is to submit to the application program that described information point is used corresponding according to user
Carry out using weights and submission number of times calculated.
9. point of interest screening technique according to claim 8, it is characterised in that described to be cited
Type include drawing cited in another information point differed by geographical position, by public transport category information point
With, cited in another information point of geographical position identical.
10. the point of interest screening technique according to any one of claim 7-9, it is characterised in that
The characteristic value of the sample data of the support vector cassification model is all higher than default characteristic threshold value, described
Default characteristic threshold value include the interest region in information point all to be screened average characteristics threshold value and
/ or the interest region in information point same category of to be screened average characteristics threshold value.
The 11. point of interest screening techniques according to any one of claim 7-9, it is characterised in that
After the information sifting included according to information point in the interest region goes out at least one information point, also
Including：
Choose the multiple information points of type identical；
According to the sequence that the characteristic value carries out from high to low to the multiple information points of type identical, then
Retain at least one forward information point of sequence.
12. a kind of devices for determining interest region in geographical scope, it is characterised in that include：
Acquiring unit, for obtaining the information point in geographic range；
Unit is chosen, for the selection from above- mentioned information point to be comprising same keyword and quantity is more than first
Multiple information points of predetermined threshold value；
Information point determining unit, for calculating the distance between the plurality of information point, determines one
Positioned at the information point of center, a is designated as, and the result calculated by the distance is determined and the information
Information point b of the distance value maximum between point a；
First screening unit, for being segmented to the distance value between information point a and information point b, sieve
Select information point c of the quantity more than the second predetermined threshold value in each section；
Second screening unit, for calculating around above-mentioned each information point c for filtering out comprising described same
The quantity of the information point of keyword, and retain information point c of the quantity more than or equal to the 3rd predetermined threshold value；
Area determination unit, for being more than or equal to the letter of the 3rd predetermined threshold value according to the quantity of above-mentioned reservation
Breath point c determines interest region.
13. devices according to claim 12, it is characterised in that described information point determining unit
Including：
Middle site determining unit, for calculating each information point respectively with all information in addition to itself
Between point apart from sum, and determine apart from minimum information point a of sum；
Solstics determining unit, for calculating the information point in addition to information point a and information point a respectively
Between distance, and determine with maximum range value information point b.
14. devices according to claim 13, it is characterised in that the first screening unit bag
Include：
Segmenting unit, for being segmented to the maximum range value；
First amount calculation unit, for calculating the quantity of the information point in each section respectively；
Sub- screening unit, for filtering out the information point in section of the quantity more than the second predetermined threshold value, note
For information point c.
15. devices according to claim 14, it is characterised in that the segmenting unit includes：
Number of fragments determining unit, for determining number of fragments；
Deng subdivision, for carrying out decile to the maximum range value according to the number of fragments.
16. devices according to claim 12, it is characterised in that the second screening unit bag
Include：
Average distance computing unit, the average distance Rd between information point c gone out for calculating sifting；
Second amount calculation unit, around each information point gone out for calculating sifting respectively in the range of N*Rd
The quantity of the information point comprising the same keyword；
Removal unit, for the information point comprising the same keyword in the range of N*Rd around removing
Information point c of the quantity less than the 3rd predetermined threshold value.
17. a kind of point of interest screening plants, it is characterised in that include：
Interest area determination unit, for using the determination geography model any one of claim 1-5
The method for enclosing interior interest region determines interest region；
Screening unit, in the interest region according to the information sifting that information point is included go out to
A few information point, at least one information point that this is filtered out is point of interest.
18. devices according to claim 17, it is characterised in that the screening unit includes：
Characteristic value determination subelement, for determining the characteristic value of all information points in the interest region；
Classification subelement, for using support vector cassification model, the characteristic value with described information point is
Input value is screened to information point.
19. devices according to claim 18, it is characterised in that the characteristic value includes first
Feature, second feature and third feature value, wherein
The First Eigenvalue is the corresponding reference weights of type and reference time being cited according to information point
Number is calculated；
The characteristic value also includes Second Eigenvalue, and the Second Eigenvalue is included according to information point
Numerical information and maximum preset numerical value and minimum default value it is calculated；
The third feature value is to submit to the application program that described information point is used corresponding according to user
Carry out using weights and submission number of times calculated.
20. devices according to claim 19, it is characterised in that the type bag being cited
Include cited in another information point differed by geographical position, cited in public transport category information point, by ground
Cited in another information point of reason position identical.
21. devices according to any one of claim 18-20, it is characterised in that described
The characteristic value for holding the sample data of vector machine disaggregated model is all higher than default characteristic threshold value, the default spy
Levy average characteristics threshold value and/or institute of the threshold value including the information point all to be screened in the interest region
State the average characteristics threshold value of the information point same category of to be screened in interest region.
22. devices according to any one of claim 18-20, it is characterised in that also include：
Unit is chosen, for choosing the multiple information points of type identical；
Removal unit, for according to the characteristic value the multiple information points of type identical are carried out from height to
Low sequence, then retains at least one forward information point of sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746851.5A CN106681996B (en) | 2015-11-05 | 2015-11-05 | The method and apparatus for determining interest region in geographic range, point of interest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510746851.5A CN106681996B (en) | 2015-11-05 | 2015-11-05 | The method and apparatus for determining interest region in geographic range, point of interest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106681996A true CN106681996A (en) | 2017-05-17 |
| CN106681996B CN106681996B (en) | 2019-03-26 |
Family
ID=58857525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510746851.5A Active CN106681996B (en) | 2015-11-05 | 2015-11-05 | The method and apparatus for determining interest region in geographic range, point of interest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106681996B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520070A (en) * | 2018-04-13 | 2018-09-11 | 百度在线网络技术（北京）有限公司 | The method and apparatus of screening point of interest for electronic map |
| CN108875013A (en) * | 2018-06-19 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Handle the method and device of map datum |
| CN108875032A (en) * | 2018-06-25 | 2018-11-23 | 讯飞智元信息科技有限公司 | Area type determines method and device |
| CN109710709A (en) * | 2018-12-13 | 2019-05-03 | 北京百度网讯科技有限公司 | Interest point data processing method, device, electronic equipment and storage medium |
| CN109960778A (en) * | 2017-12-26 | 2019-07-02 | 北京金风慧能技术有限公司 | The method and apparatus for calculating wind power plant theoretical power (horse-power) |
| CN110348525A (en) * | 2019-07-15 | 2019-10-18 | 北京百度网讯科技有限公司 | Map point of interest acquisition methods, device, equipment and storage medium |
| CN110889048A (en) * | 2018-08-20 | 2020-03-17 | 高德信息技术有限公司 | Map data query method, system, terminal and server |
| CN111523061A (en) * | 2020-04-23 | 2020-08-11 | 北京百度网讯科技有限公司 | Method and apparatus for generating interest plane |
| CN111552750A (en) * | 2020-04-13 | 2020-08-18 | 深圳震有科技股份有限公司 | Dynamic tracking display method, terminal and storage medium |
| CN111797183A (en) * | 2020-05-29 | 2020-10-20 | 汉海信息技术(上海)有限公司 | Method and device for mining road attribute of information point and electronic equipment |
| CN112132460A (en) * | 2020-09-22 | 2020-12-25 | 京东城市(北京)数字科技有限公司 | Method, device and system for identifying potential danger area and storage medium |
| CN112711719A (en) * | 2019-10-25 | 2021-04-27 | 北京搜狗科技发展有限公司 | Interest point searching method and device and readable storage medium |
| CN113626729A (en) * | 2021-07-30 | 2021-11-09 | 高德软件有限公司 | Method and device for determining point of interest information |
| CN114077979A (en) * | 2020-08-18 | 2022-02-22 | 北京三快在线科技有限公司 | Method and device for determining distribution service range |
| CN114363796A (en) * | 2020-09-30 | 2022-04-15 | 中移(成都)信息通信科技有限公司 | Livestock outlier judgment method and device, electronic equipment and computer storage medium |
| CN112711719B (en) * | 2019-10-25 | 2024-06-04 | 北京搜狗科技发展有限公司 | Point-of-interest searching method and device and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010040400A1 (en) * | 2008-10-08 | 2010-04-15 | Tomtom International B.V. | Navigation apparatus and method of providing points of interest |
| CN102176206A (en) * | 2011-01-18 | 2011-09-07 | 宇龙计算机通信科技(深圳)有限公司 | Periphery searching method and device of points of interest |
| CN103167404A (en) * | 2011-12-14 | 2013-06-19 | 北京千橡网景科技发展有限公司 | Method and device used for confirming interest points |
| CN103533501A (en) * | 2013-10-15 | 2014-01-22 | 厦门雅迅网络股份有限公司 | Geofence generating method |
| US20140071170A1 (en) * | 2011-05-11 | 2014-03-13 | Nokia Corporation | Non-uniformly scaling a map for emphasizing areas of interest |
| CN104102637A (en) * | 2013-04-02 | 2014-10-15 | 高德软件有限公司 | Method and device for generating hot spot region |
-
2015
- 2015-11-05 CN CN201510746851.5A patent/CN106681996B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010040400A1 (en) * | 2008-10-08 | 2010-04-15 | Tomtom International B.V. | Navigation apparatus and method of providing points of interest |
| CN102176206A (en) * | 2011-01-18 | 2011-09-07 | 宇龙计算机通信科技(深圳)有限公司 | Periphery searching method and device of points of interest |
| US20140071170A1 (en) * | 2011-05-11 | 2014-03-13 | Nokia Corporation | Non-uniformly scaling a map for emphasizing areas of interest |
| CN103167404A (en) * | 2011-12-14 | 2013-06-19 | 北京千橡网景科技发展有限公司 | Method and device used for confirming interest points |
| CN104102637A (en) * | 2013-04-02 | 2014-10-15 | 高德软件有限公司 | Method and device for generating hot spot region |
| CN103533501A (en) * | 2013-10-15 | 2014-01-22 | 厦门雅迅网络股份有限公司 | Geofence generating method |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109960778A (en) * | 2017-12-26 | 2019-07-02 | 北京金风慧能技术有限公司 | The method and apparatus for calculating wind power plant theoretical power (horse-power) |
| CN108520070A (en) * | 2018-04-13 | 2018-09-11 | 百度在线网络技术（北京）有限公司 | The method and apparatus of screening point of interest for electronic map |
| CN108875013A (en) * | 2018-06-19 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Handle the method and device of map datum |
| CN108875032B (en) * | 2018-06-25 | 2022-02-25 | 讯飞智元信息科技有限公司 | Region type determination method and device |
| CN108875032A (en) * | 2018-06-25 | 2018-11-23 | 讯飞智元信息科技有限公司 | Area type determines method and device |
| CN110889048A (en) * | 2018-08-20 | 2020-03-17 | 高德信息技术有限公司 | Map data query method, system, terminal and server |
| CN109710709A (en) * | 2018-12-13 | 2019-05-03 | 北京百度网讯科技有限公司 | Interest point data processing method, device, electronic equipment and storage medium |
| CN110348525A (en) * | 2019-07-15 | 2019-10-18 | 北京百度网讯科技有限公司 | Map point of interest acquisition methods, device, equipment and storage medium |
| CN110348525B (en) * | 2019-07-15 | 2022-02-22 | 北京百度网讯科技有限公司 | Map interest point acquisition method, device, equipment and storage medium |
| CN112711719A (en) * | 2019-10-25 | 2021-04-27 | 北京搜狗科技发展有限公司 | Interest point searching method and device and readable storage medium |
| CN112711719B (en) * | 2019-10-25 | 2024-06-04 | 北京搜狗科技发展有限公司 | Point-of-interest searching method and device and readable storage medium |
| CN111552750A (en) * | 2020-04-13 | 2020-08-18 | 深圳震有科技股份有限公司 | Dynamic tracking display method, terminal and storage medium |
| CN111523061A (en) * | 2020-04-23 | 2020-08-11 | 北京百度网讯科技有限公司 | Method and apparatus for generating interest plane |
| CN111523061B (en) * | 2020-04-23 | 2023-03-21 | 北京百度网讯科技有限公司 | Method and apparatus for generating interest plane |
| CN111797183A (en) * | 2020-05-29 | 2020-10-20 | 汉海信息技术(上海)有限公司 | Method and device for mining road attribute of information point and electronic equipment |
| CN114077979A (en) * | 2020-08-18 | 2022-02-22 | 北京三快在线科技有限公司 | Method and device for determining distribution service range |
| CN114077979B (en) * | 2020-08-18 | 2024-05-28 | 北京三快在线科技有限公司 | Method and device for determining distribution service range |
| CN112132460A (en) * | 2020-09-22 | 2020-12-25 | 京东城市(北京)数字科技有限公司 | Method, device and system for identifying potential danger area and storage medium |
| CN114363796A (en) * | 2020-09-30 | 2022-04-15 | 中移(成都)信息通信科技有限公司 | Livestock outlier judgment method and device, electronic equipment and computer storage medium |
| CN113626729A (en) * | 2021-07-30 | 2021-11-09 | 高德软件有限公司 | Method and device for determining point of interest information |
| CN113626729B (en) * | 2021-07-30 | 2024-04-16 | 高德软件有限公司 | Method and equipment for determining interest point information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106681996B (en) | 2019-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106681996A (en) | Method and device for determining interest areas and interest points within geographical scope | |
| CN110726418B (en) | Method, device and equipment for determining interest point region and storage medium | |
| O'sullivan et al. | Geographic information analysis | |
| CN108876032A (en) | A kind of data processing method, device, equipment and the system of object addressing | |
| CA2746910C (en) | Method and system for displaying points of interest | |
| CN109478184B (en) | Identifying, processing, and displaying clusters of data points | |
| CN107291888B (en) | Machine learning statistical model-based living recommendation system method near living hotel | |
| EP3267390A1 (en) | Information processing device, information processing method, and program | |
| TW201633241A (en) | Target address determining method and device | |
| CN104881472B (en) | A kind of travelling route sight spot combined recommendation method based on network data collection | |
| CN111091417B (en) | Site selection method and device | |
| CN112861972B (en) | Site selection method and device for exhibition area, computer equipment and medium | |
| CN107220308B (en) | Method, device and equipment for detecting rationality of POI (Point of interest) and readable medium | |
| CN102163214A (en) | Numerical map generation device and method thereof | |
| CN109740049B (en) | Article generation method and device | |
| JP2022504597A (en) | Area division method and equipment, electronic equipment and programs | |
| Zhao et al. | A network distance and graph-partitioning-based clustering method for improving the accuracy of urban hotspot detection | |
| CN104516980B (en) | The output method and server system of search result | |
| Shi et al. | The visual analysis of flow pattern for public bicycle system | |
| Hu et al. | Construction of a refined population analysis unit based on urban forms and population aggregation patterns | |
| CN114219350A (en) | Intelligent site selection method and device for natural resource construction project | |
| Eckman et al. | Methods of geo-spatial sampling | |
| CN111369284B (en) | Target object type determining method and device | |
| Chung et al. | Investigating the effects of POI-based land use on traffic accidents in Suzhou Industrial Park, China | |
| CN112257970A (en) | Automatic city functional area dividing method based on interest point big data |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210930 Address after: 518057 Tencent Building, No. 1 High-tech Zone, Nanshan District, Shenzhen City, Guangdong Province, 35 floors Patentee after: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. Patentee after: TENCENT CLOUD COMPUTING (BEIJING) Co.,Ltd. Address before: 518000 Room 403, East Building 2, SEG Science Park, Zhenxing Road, Shenzhen, Guangdong Patentee before: TENCENT TECHNOLOGY (SHENZHEN) Co.,Ltd. |
|
| TR01 | Transfer of patent right |