CN106767835A - Localization method and device - Google Patents
Localization method and device Download PDFInfo
- Publication number
- CN106767835A CN106767835A CN201710068541.1A CN201710068541A CN106767835A CN 106767835 A CN106767835 A CN 106767835A CN 201710068541 A CN201710068541 A CN 201710068541A CN 106767835 A CN106767835 A CN 106767835A
- Authority
- CN
- China
- Prior art keywords
- information point
- geography information
- fix
- positioning time
- elements
- 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
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
This application discloses localization method and device.One specific embodiment of the method includes:Obtain the history visiting geography information point classification sequence of the location information and above-mentioned user including positioning time and the elements of a fix of user before above-mentioned positioning time;At least one geography information point of the distance less than predeterminable range threshold value of geography information point coordinates and the above-mentioned elements of a fix is obtained, wherein, geography information point includes geography information point coordinates and geography information point classification;To each geography information point in above-mentioned at least one geography information point, history visiting geography information point classification sequence based on above-mentioned location information and above-mentioned user before above-mentioned positioning time, determines the visiting probable value of the geographical entity that above-mentioned user visits indicated by the geography information point in above-mentioned positioning time;According to identified each visiting probable value, the geography information point corresponding to the geographical entity that above-mentioned user was visited in above-mentioned positioning time is determined.This embodiment improves the degree of accuracy of user's positioning.
Description
Technical field
The application is related to field of computer technology, and in particular to Internet technical field, more particularly to localization method and dress
Put.
Background technology
With continuing to develop for mobile Internet, intelligent movable equipment and terminal, terminal user generates substantial amounts of fixed
Data under the lines such as position, track.Data truly reflect user's behavioural characteristic aerial in physics under line, and data on line are formed
Good complement.Data are combined on data and line under line, it is possible to achieve more accurately user's portrait is portrayed.User's portrait can be with
It is widely used in the multiple concrete application such as online information push, precision marketing.Particularly, if it is possible to it is determined that or predicting
User has visited a geography information point (POI, Point Of Interest), is also called " information point " or " point of interest ", for example
Hotel, school, market, office building, subway station, airport etc., then can complete accurately to hit the information pushing of user's actual need.
However, typically predicting that user visits according to the current positioning coordinate and/or current time of user in the prior art
Geography information point, do not account for user history visiting geography information point, so as to cause prediction accuracy rate it is not high.
The content of the invention
The purpose of the application is to propose a kind of improved localization method and device to carry solving background section above
The technical problem for arriving.
In a first aspect, this application provides a kind of localization method, the method includes:Obtain user including positioning time and
The history visiting geography information point classification sequence of the location information of the elements of a fix and above-mentioned user before above-mentioned positioning time;Obtain
At least one geography information point of the distance less than predeterminable range threshold value of geography information point coordinates and the above-mentioned elements of a fix is taken, its
In, geography information point includes geography information point coordinates and geography information point classification;To every in above-mentioned at least one geography information point
Individual geography information point, the history visiting geography information based on above-mentioned location information and above-mentioned user before above-mentioned positioning time
Point classification sequence, determines that the visiting of the geographical entity that above-mentioned user visits indicated by the geography information point in above-mentioned positioning time is general
Rate value;According to identified each visiting probable value, the geographical entity institute that above-mentioned user is visited in above-mentioned positioning time is determined
Corresponding geography information point.
In certain embodiments, it is above-mentioned to each geography information point in above-mentioned at least one geography information point, based on above-mentioned
The history visiting geography information point classification sequence of location information and above-mentioned user before above-mentioned positioning time, determines above-mentioned user
Visited the visiting probable value of the geographical entity indicated by the geography information point in above-mentioned positioning time, including:Above-mentioned user is existed
History visiting geography information point classification sequence before above-mentioned positioning time imports the geography information point class prediction of training in advance
Model, obtains above-mentioned user each geography information point classification in above-mentioned positioning time visits at least one geography information point classification
The visiting class probability value of indicated geographical entity;To each geography information point, root in above-mentioned at least one geography information point
According to above-mentioned location information, determine that the above-mentioned elements of a fix belong to the geographical entity indicated by the geography information point in above-mentioned positioning time
Probable value;To each geography information point in above-mentioned at least one geography information point, according to the above-mentioned elements of a fix in above-mentioned positioning
Time belongs to the probable value of the geographical entity indicated by the geography information point and above-mentioned user visits the ground in above-mentioned positioning time
The visiting class probability value of the geographical entity indicated by the geography information point classification of information point is managed, determines above-mentioned user above-mentioned fixed
The position time visits the visiting probable value of the geographical entity indicated by the geography information point.
In certain embodiments, it is above-mentioned according to above-mentioned location information, determine that the above-mentioned elements of a fix belong in above-mentioned positioning time
In the probable value of the geographical entity indicated by the geography information point, including:According to the above-mentioned elements of a fix and the geography information point
Elements of a fix probability distribution, determines that the above-mentioned elements of a fix belong to the probable value of the geographical entity indicated by the geography information point;Root
According to above-mentioned positioning time and the positioning time probability distribution of the geography information point, determine that the geography indicated by the geography information point is real
The probable value that body is visited in above-mentioned positioning time, wherein, the positioning time probability distribution of the geography information point is according to the ground
The history positioning time for managing the history visiting user of information point carries out counting what is obtained;Belong to the geography according to the above-mentioned elements of a fix
Geographical entity indicated by the probable value of the geographical entity indicated by information point and the geography information point is in above-mentioned positioning time quilt
The probable value of visiting, determines that the above-mentioned elements of a fix belong to the geographical entity indicated by the geography information point in above-mentioned positioning time
Probable value.
In certain embodiments, the elements of a fix probability distribution of the above-mentioned geography information point is obtained by following operation
's:Obtain the history elements of a fix of the history visiting user of the geography information point;The acquired history elements of a fix are gathered
Class is obtaining at least one elements of a fix cluster centre of the geography information point;Geography information point according to the geography information point is sat
The distance between each elements of a fix cluster centre at least one elements of a fix cluster centre of mark and the geography information point, really
Each elements of a fix cluster centre of the fixed geography information point belongs to the probable value of the geographical entity indicated by the geography information point,
And using the probable value of the geographical entity indicated by identified each elements of a fix cluster centre belongs to the geography information point as
The elements of a fix probability distribution of the geography information point.
In certain embodiments, the step of above method also includes training geography information point class prediction model, above-mentioned instruction
The step of practicing geography information point class prediction model includes:Obtain at least one history visiting geography information of at least one user
Point classification sequence;Using above-mentioned at least one history visiting geography information point classification sequence as training data, recurrent neural is trained
Network is used as geography information point class prediction model.
Second aspect, this application provides a kind of positioner, the device includes:First acquisition unit, is configured to obtain
The history of the location information and above-mentioned user including positioning time and the elements of a fix at family before above-mentioned positioning time is taken to arrive
Visit geography information point classification sequence;Second acquisition unit, is configured to obtain geography information point coordinates and the above-mentioned elements of a fix
Distance less than predeterminable range threshold value 1 geography information point, wherein, geography information point include geography information point coordinates and
Geography information point classification;First determining unit, is configured to each geography information point in above-mentioned at least one geography information point,
History visiting geography information point classification sequence based on above-mentioned location information and above-mentioned user before above-mentioned positioning time, it is determined that
The visiting probable value of the geographical entity that above-mentioned user visits indicated by the geography information point in above-mentioned positioning time;Second determines list
Unit, is configured to each visiting probable value according to determined by, determines the geography that above-mentioned user is visited in above-mentioned positioning time
Geography information point corresponding to entity.
In certain embodiments, above-mentioned first determining unit includes:First determining module, is configured to exist above-mentioned user
History visiting geography information point classification sequence before above-mentioned positioning time imports the geography information point class prediction of training in advance
Model, obtains above-mentioned user each geography information point classification in above-mentioned positioning time visits at least one geography information point classification
The visiting class probability value of indicated geographical entity;Second determining module, is configured to above-mentioned at least one geography information
Each geography information point in point, according to above-mentioned location information, determines that the above-mentioned elements of a fix belong to the geography in above-mentioned positioning time
The probable value of the geographical entity indicated by information point;3rd determining module, is configured to above-mentioned at least one geography information point
In each geography information point, in above-mentioned positioning time belong to the geography information point according to the above-mentioned elements of a fix indicated by geography it is real
The probable value of body and above-mentioned user above-mentioned positioning time visit the geography information point geography information point classification indicated by ground
The visiting class probability value of entity is managed, the geography that above-mentioned user visits indicated by the geography information point in above-mentioned positioning time is determined
The visiting probable value of entity.
In certain embodiments, above-mentioned second determining module includes:First determination sub-module, is configured to according to above-mentioned fixed
The elements of a fix probability distribution of position coordinate and the geography information point, determines that the above-mentioned elements of a fix belong to indicated by the geography information point
Geographical entity probable value;Second determination sub-module, is configured to determining according to above-mentioned positioning time and the geography information point
Position time probability distribution, determines the probable value that the geographical entity indicated by the geography information point is visited in above-mentioned positioning time,
Wherein, the positioning time probability distribution of the geography information point is the history positioning according to the history of geography information point visiting user
Time carries out counting what is obtained;3rd determination sub-module, is configured to belong to the geography information point institute according to the above-mentioned elements of a fix
The probable value of the geographical entity of instruction and the geographical entity indicated by the geography information point above-mentioned positioning time visited it is general
Rate value, determines that the above-mentioned elements of a fix belong to the probable value of the geographical entity indicated by the geography information point in above-mentioned positioning time.
In certain embodiments, the elements of a fix probability distribution of the above-mentioned geography information point is obtained by following operation
's:Obtain the history elements of a fix of the history visiting user of the geography information point;The acquired history elements of a fix are gathered
Class is obtaining at least one elements of a fix cluster centre of the geography information point;Geography information point according to the geography information point is sat
The distance between each elements of a fix cluster centre at least one elements of a fix cluster centre of mark and the geography information point, really
Each elements of a fix cluster centre of the fixed geography information point belongs to the probable value of the geographical entity indicated by the geography information point,
And using the probable value of the geographical entity indicated by identified each elements of a fix cluster centre belongs to the geography information point as
The elements of a fix probability distribution of the geography information point.
In certain embodiments, said apparatus also include geography information point class prediction model training unit, above-mentioned geography
Information point class prediction model training unit is configured to:Obtain at least one history visiting geography information of at least one user
Point classification sequence;Using above-mentioned at least one history visiting geography information point classification sequence as training data, recurrent neural is trained
Network is used as geography information point class prediction model.
The third aspect, this application provides a kind of server, the server includes:One or more processors;Storage dress
Put, for storing one or more programs, when said one or multiple programs are by said one or multiple computing devices, make
Obtain the method for said one or multiple processor realizations as described in any implementation in first aspect.
Fourth aspect, this application provides a kind of computer-readable recording medium, is stored thereon with computer program, and it is special
Levy and be, the computer program is when executed by realizing the method as described in any implementation in first aspect.
The localization method and device that the application is provided, by the elements of a fix according to user and positioning time and above-mentioned use
History visiting geography information point classification sequence of the family before positioning time, determines that user visits and the elements of a fix in positioning time
Distance less than the geographical entity in 1 geography information point of predeterminable range threshold value indicated by each geography information point
Visiting probable value, and finally determine the geography information point corresponding to the geographical entity that user was visited in positioning time, so as to
The history visiting geography information point classification sequence of user is considered during being positioned to user, determination user is improve and is visited
Geographical entity corresponding to geography information point the degree of accuracy, can then improve to user portrait the degree of accuracy.
Brief description of the drawings
By the detailed description made to non-limiting example made with reference to the following drawings of reading, the application other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that the application can apply to exemplary system architecture figure therein;
Fig. 2 a are the flow charts of one embodiment of the localization method according to the application;
Fig. 2 b are the positioning time probability distribution schematic diagrames of geography information point in localization method according to the application;
Fig. 3 is the flow chart of another embodiment of the localization method according to the application;
Fig. 4 is the structural representation of one embodiment of the positioner according to the application;
Fig. 5 is adapted for the structural representation of the computer system of the server for realizing the embodiment of the present application.
Specific embodiment
The application 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 related invention, rather than the restriction to the invention.It also should be noted that, in order to
Be easy to description, be illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the exemplary system architecture of the embodiment of the localization method or positioner that can apply the application
100。
As shown in figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 is used to be provided between terminal device 101,102,103 and server 105 medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted by network 104 with using terminal equipment 101,102,103 with server 105, to receive or send out
Send message etc..Various client applications, such as map class application, positioning class can be installed on terminal device 101,102,103
It is soft using, web browser applications, the application of shopping class, searching class application, JICQ, mailbox client, social platform
Part etc..
Terminal device 101,102,103 can be the various electronic equipments for supporting positioning and/or WiFi function, including but not
It is limited to smart mobile phone, panel computer, pocket computer on knee etc..
Server 105 can be to provide the server of various services, and such as positioning to terminal device 101,102,103 takes
Business provides the background server supported.Background server such as can be analyzed at the treatment to data such as the location informations that receives.
It should be noted that the localization method that the embodiment of the present application is provided typically is performed by server 105, correspondingly,
Positioner is generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2 a, it illustrates the flow 200 of one embodiment of the localization method according to the application.The positioning
Method, comprises the following steps:
Step 201, obtain user location information including positioning time and the elements of a fix and above-mentioned user in positioning
Between before history visiting geography information point classification sequence.
In the present embodiment, localization method operation electronic equipment (such as the server shown in Fig. 1) thereon can be with head
First pass through the location information that wired connection mode or radio connection obtain user from the terminal of user.Here, user
Location information can include the elements of a fix and positioning time.Then, above-mentioned electronic equipment can obtain above-mentioned user in positioning
Between before history visiting geography information point classification sequence.
In the present embodiment, the location information of user can be the current location information of user, or going through for user
History location information.
In the present embodiment, geography information point is used to characterize geographical entity.Wherein, geographical entity can be the earth
Any specific entity on surface.For example, geographical entity can be specific building, road, geographic area, river, ocean,
Mountain peak etc..Geography information point classification is used to characterize the classification belonging to the geographical entity indicated by geography information point.As an example,
Geography information point classification can include:Primary school campus, Middle School, campus, subway station, bus stop, airport, government's machine
Pass, hotel, market, cinema, library, square, office building, park, amusement park, village, gas station, national highway, highway,
Urban road etc..For example, geographical entity " Overbridge In Haidian Park " and the geography information point class belonging to geographical entity " Purple Bamboo Court Park "
All it is not " park ".
In the present embodiment, the elements of a fix of user and geography information point coordinates can be the seats based on various coordinate systems
Mark.For example, the elements of a fix of user and geography information point coordinates can be three-dimensional coordinates (for example, the longitude and latitude under earth coordinates
Degree coordinate), or two-dimensional coordinate (for example, UTMGS (Universal Transverse Mercartor Grid
System, Universal Trans Meridian grid system) in abscissa and ordinate).
In the present embodiment, above-mentioned electronic equipment can obtain the location information of the terminal of user by various positioning methods
As the location information of user, wherein, various positioning methods include but is not limited to following positioning method:Based on GPS (Global
Positioning System, global positioning system) positioning, the positioning of the base station based on mobile operator, based on AGPS
The positioning of (Assisted GPS, auxiliary global satellite positioning system), based on the positioning of WiFi and other it is currently known or will
Come the terminal positioning mode developed.
In the present embodiment, the history visiting geography information point classification sequence of above-mentioned user can be arranged in chronological order
The geography information point classification of row.
In some optional implementations of the present embodiment, the history visiting geography information point classification sequence of above-mentioned user
Can be stored in advance in above-mentioned electronic equipment it is local or with other electronic equipments of above-mentioned electronic equipment network connection in, so
Above-mentioned electronic equipment can be obtained locally or remotely from other electronic equipments of above-mentioned electronic equipment network connection
State history visiting geography information point classification sequence of the user before positioning time.
In some optional implementations of the present embodiment, the history that above-mentioned electronic equipment can obtain above-mentioned user is arrived
Positioning time nearest the first predetermined number (such as 10) history for visiting distance users in geography information point classification sequence is arrived
Visit history visiting geography information point classification sequence of the geography information point classification sequence as above-mentioned user before positioning time.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can also obtain the history of above-mentioned user
In visiting geography information point classification sequence in the predetermined amount of time (such as 1 day or 1 week) nearest with the positioning time of user
History visiting geography information point classification of the history visiting geography information point classification sequence as above-mentioned user before positioning time
Sequence.
Step 202, obtains geography information point coordinates with the distance of the elements of a fix less than at least one of predeterminable range threshold value
Geography information point.
In the present embodiment, geography information point is used to characterize geographical entity.In physical world, geographical entity leads to
It is often the region of the material composition by certain building and nature, however in practice, it is convenient in order to represent, it is often ground
Manage geography information point coordinates of the entity set coordinate as the corresponding geography information point of the geographical entity.
In order to determine the geography information point corresponding to the geographical entity that above-mentioned user was visited in positioning time, it is necessary to each
1 geography information point is determined in individual geography information point, to reduce the scope.Therefore, above-mentioned electronic equipment can be obtained first
Each geography information point, then, chooses geography information point coordinates with the elements of a fix in each acquired geography information point
At least one geography information point of the distance less than predeterminable range threshold value (for example, 100 meters).Specifically, can be from location-based
The geography information point coordinates of each geography information point is obtained in service (LBS, Location Based Service).
Step 203, to each geography information point in 1 geography information point, based on location information and user in positioning
History visiting geography information point classification sequence before time, determines that user visits indicated by the geography information point in positioning time
Geographical entity visiting probable value.
In the present embodiment, based on the user obtained in step 201 location information and user are before positioning time
History visiting geography information point classification sequence, above-mentioned electronic equipment (such as the server shown in Fig. 1) can use various realizations
Mode, to each geography information point in the 1 geography information point that is obtained in step 202, determines that user arrives in positioning time
Visit the visiting probable value of the geographical entity indicated by the geography information point.
In some optional implementations of the present embodiment, step 203 can include following sub-step:
Sub-step 2031, the history visiting geography information point classification sequence by user before positioning time imports instruction in advance
Experienced geography information point class prediction model, obtain user positioning time visit at least one geography information point classification in each
The visiting class probability value of the geographical entity indicated by geography information point classification.
Wherein, it is each in history visiting geography information point classification sequence of at least one geography information point classification including user
The geography information point classification of each geography information point in individual history visiting geography information point classification and at least one geography information point.
In practice, at least one geography information point classification can be obtained from location Based service.Here, geography information point classification is pre-
Surveying model is used to characterize the corresponding relation of history visiting geography information point classification sequence and geography information point classification.
Alternatively, the step of above-mentioned localization method can also include following training geography information point class prediction model:It is first
First, at least one history visiting geography information point classification sequence of at least one user is obtained.Then, by acquired at least one
Individual history visiting geography information point classification sequence is used as training data, and training recurrent neural network is pre- as geography information point classification
Survey model.
Recurrent neural network is a class artificial neural network, and recurrent neural network possesses a kind of specific memory pattern, can
Pattern for recognizing the sequence datas such as text, genome, hand-written writing, voice, it can also be used to identification sensor, stock
The numeric type time series data that market, government organs produce.The input of recurrent neural network not only includes currently seen defeated
Enter sample, the information for also being perceived at a upper moment including network.Recurrent neural network is in (n-1)th judgement of time step
It can be influenceed in the judgement of subsequent n-th time step, wherein n is natural number.So recurrent neural network constantly will be with one
Carve output as input feedback cycle, thus, recurrent neural network can utilize sequence per se with order information complete before
The task that feedback neutral net cannot be completed, these order informations are stored in recurrent neural network hidden state, constantly to front layer
Layer transmission, across many time steps, influences the treatment of each new sample.Therefore train geographical using recurrent neural network
Information point class prediction model, can be by the history of user visiting geography information point classification sequence, exactly under prediction user
The one geography information point classification that may be visited.
Sub-step 2032, to each geography information point in 1 geography information point, user is visited in positioning time
The visiting class probability value of the geographical entity indicated by the geography information point classification of the geography information point is as user in positioning
Between the visiting probable value of geographical entity visited indicated by the geography information point.
In some optional implementations of the present embodiment, step 203 may be carried out as follows:
To each geography information point in 1 geography information point, according to the location information of user, the elements of a fix are determined
Belong to the probable value of the geographical entity indicated by the geography information point in positioning time, and by the identified elements of a fix in positioning
Time belongs to the probable value of the geographical entity indicated by the geography information point and is visited the geography information in positioning time as user
The visiting probable value of the indicated geographical entity of point.
Alternatively, wherein it is determined that the elements of a fix belong to the geographical entity indicated by the geography information point in positioning time
Probable value, can include following sub-step A to sub-step C:
Sub-step A, according to the elements of a fix and the elements of a fix probability distribution of the geography information point, determines that the elements of a fix belong to
The probable value of the geographical entity indicated by the geography information point.
Alternatively, the elements of a fix probability distribution of the geography information point can be by following sub-step A1 to sub-step A3
Obtain:
Sub-step A1, obtains the history elements of a fix of the history visiting user of the geography information point.
As an example, the data of WiFi can be connected by obtaining historic user, if this WiFi has determined that belongs to a certain
Geography information point, it may be determined that this historic user is the history visiting user of the geography information point, then obtain the historic user
The history elements of a fix can be obtained by the geography information point history visit user the history elements of a fix.
As an example, it is also possible to cross the geography information using navigation of electronic map class application searches by obtaining historic user
Point, and start navigation using the geography information point as destination, obtain what the historic user was used when navigation is terminated
The elements of a fix of terminal, if the distance between geography information point coordinates of the acquired elements of a fix and the geography information point is no
More than default positioning distance threshold (for example, 50 meters), then arrived the acquired elements of a fix as the history of the geography information point
Visit the history elements of a fix of user.
As an example, can also be by obtaining historic user (example when using the consumption voucher relevant with the geography information point
Such as, for the group buying voucher of the geography information point), the elements of a fix of the terminal that the historic user is used are obtained, if acquired
The distance between the geography information point coordinates of the elements of a fix and the geography information point be not more than default positioning distance threshold (example
Such as, 50 meters), then the history elements of a fix of the user that the acquired elements of a fix visited as the history of the geography information point.
The acquired history elements of a fix are clustered and determined with obtaining at least one of the geography information point by sub-step A2
Position coordinate cluster centre.
Wherein, clustering algorithm can be included but is not limited to:K-Means (K- averages) clustering algorithm, mixed Gauss model
(Gaussian Mixture Model) clustering algorithm, hierarchical clustering (Hierarchical Clustering) algorithm, SOM are (certainly
Organising map neutral net, Self-Organizing Maps) clustering algorithm, FCM (fuzzy C-mean algorithm, Fuzzy C-Means) gather
Class algorithm.It should be understood that above-mentioned clustering algorithm calculating process in itself is as well known to those skilled in the art, herein no longer
Repeat.
Sub-step A3, at least one positioning of geography information point coordinates and the geography information point according to the geography information point
The distance between each elements of a fix cluster centre in coordinate cluster centre, determines that each elements of a fix of the geography information point gather
Class center belongs in the probable value of the geographical entity indicated by the geography information point, and each elements of a fix cluster by determined by
The heart belongs to the probable value of the geographical entity indicated by the geography information point as the elements of a fix probability distribution of the geography information point.
As an example, a kind of geography information point coordinates according to the geography information point is given below with the geography information point
The distance between each elements of a fix cluster centre at least one elements of a fix cluster centre, determines each of the geography information point
Individual elements of a fix cluster centre belongs to the specific implementation of the probable value of the geographical entity indicated by the geography information point:
Wherein, geography information point poi has K elements of a fix cluster centre μi, K is the positive integer more than 1, i be 1 to K it
Between positive integer, elements of a fix cluster centre μiCan be two-dimensional coordinate (xi,yi), or three-dimensional coordinate (xi,yi,zi), P
(μi| poi) be calculate obtained by geography information point poi elements of a fix cluster centre μiBelong to indicated by geography information point poi
The probable value of geographical entity, D1It is the constant more than 0, l1iIt is elements of a fix cluster centre μiWith the geography of geography information point poi
The distance between information point coordinates, the elements of a fix of geography information point can be two-dimensional coordinate (xpoi,ypoi), or it is three-dimensional
Coordinate (xpoi,ypoi,zpoi).From above-mentioned formula as can be seen that in the elements of a fix cluster centre μ of geography information point poiiWith ground
The distance between the geography information point coordinates of reason information point poi l1iLess than or equal to D1In the case of, P (μi| poi) it is equal to 1.
l1iMore than D1In the case of, P (μi| poi) it is less than 1, and P (μi| poi) and l1iIt is negatively correlated.
It is given below according to the elements of a fix and the above-mentioned elements of a fix probability distribution of the geography information point, determines the elements of a fix
Belong to a kind of specific implementation of the probable value of geographical entity indicated by the geography information point:
Wherein, U is the elements of a fix of user, and U can be two-dimensional coordinate (xu,yu), or three-dimensional coordinate (xu,yu,
zu), poi is geography information point, P (U | poi) be calculate obtained by elements of a fix U belong to ground indicated by geography information point poi
Manage the probable value of entity, P (μi| poi) be geography information point poi obtained by above-mentioned calculating elements of a fix cluster centre μiBelong to
The probable value of the geographical entity indicated by geography information point poi, and P (U | μi) it is that elements of a fix U belongs to determining for geography information point poi
Position coordinate cluster centre μiProbable value, P (U | μi) and elements of a fix U and geography information point poi elements of a fix cluster centre μi
The distance between negative correlation, as an example, P (U | μi) can be calculated by equation below:
Wherein, D2It is greater than 0 constant, l2iIt is the geography information point coordinates cluster of elements of a fix U and geography information point poi
Center μiThe distance between.
Sub-step B, according to positioning time and the positioning time probability distribution of the geography information point, determines the geography information point
The probable value that indicated geographical entity is visited in positioning time.
Here, the positioning time probability distribution of the geography information point can be visited to use according to the history of the geography information point
The history positioning time at family carries out counting what is obtained.
As an example, the positioning time probability distribution according to positioning time t and geography information point poi is given below, it is determined that
A kind of implementation of the probable value that the geographical entity indicated by geography information point poi is visited in positioning time t:
P (t | poi)=P (hour | poi) P (week | poi) (formula 4)
Wherein, t represents positioning time, and poi represents geography information point, and P (hour | poi) represent geography information point poi with one
Hour be chronomere with 24 hours positioning time probability distribution for a cycle, i.e. P (hour | poi) represent in hour institute's generations
In the time period of a hour of table, the probable value that geography information point poi is visited, P (week | poi) represent geography information point poi
To be within 24 hours chronomere with one week positioning time probability distribution for a cycle, i.e. P (week | poi) expression is in week institutes
In the time of what day 24 hours for representing, the probable value that geography information point poi is visited.P (t | poi) it is obtained by calculating
The probable value that geography information point poi is visited in positioning time t.
As an example, P (hour | poi) can be obtained in the following manner:With in the order history time period (for example, nearly one
Individual month) pre-set user (for example, all registered users or searched for the registered user of geography information point poi) is representated by hour
Time period searching for geo information point poi number of times divided by the geographical letter of above-mentioned pre-set user search in the above-mentioned order history time period
Ratio obtained by the total degree of breath point poi, as geography information point poi within the time period of one hour representated by hour quilt
The probable value of visiting.The distribution map of geography information point poi P (hour | poi) in 24 hours is shown in Fig. 2 b.As can be seen that
Section between during the day, the searched number of times of the geography information point is more, thus corresponding P (hour | poi) it is also higher, at night
Time period, the searched number of times of the geography information point is less, thus corresponding P (hour | poi) it is relatively low.It is understood that
P (week | poi) can be obtained by similar fashion.
Sub-step C, the probable value and the geography of the geographical entity according to indicated by the elements of a fix belong to the geography information point
The probable value that geographical entity indicated by information point is visited in positioning time, determines that the elements of a fix belong to the ground in positioning time
The probable value of the geographical entity indicated by reason information point.
As an example, a kind of specific implementation is given below:
P (U, t | poi)=P (t | poi) P (U | poi) (formula 5)
Wherein, U is the elements of a fix of user, and U can be two-dimensional coordinate (xu,yu), or three-dimensional coordinate (xu,yu,
zu), t is positioning time, P (U | poi) be calculate in sub-step A obtained by elements of a fix U to belong to geography information point poi signified
The probable value of the geographical entity for showing, P (t | poi) be calculate in sub-step B obtained by geography information point poi indicated by geography it is real
The probable value that body is visited in positioning time t, P (U, t | poi) be calculate obtained by elements of a fix U belong to this in positioning time t
The probable value of the geographical entity indicated by geography information point poi.
By sub-step A to sub-step C, above-mentioned electronic equipment can determine that the elements of a fix belong to the geography in positioning time
The probable value of the geographical entity indicated by information point, then, above-mentioned electronic equipment can using the probable value of above-mentioned determination as with
The visiting probable value of the geographical entity that family is visited indicated by the geography information point in positioning time.
Step 204, according to identified each visiting probable value, determines the geographical entity that user is visited in positioning time
Corresponding geography information point.
In the present embodiment, based in step 203 it is identified each visiting probable value, above-mentioned electronic equipment can to
The geography information point corresponding to the geographical entity that user was visited in positioning time is determined in a few geography information point.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can be from 1 geography information point
The geographical entity institute that the maximum geography information point of visiting probable value determined by middle selection is visited as user in positioning time
Corresponding geography information point.
In some optional implementations of the present embodiment, above-mentioned electronic equipment can also be from least one geography information
Order in point according to identified visiting probable value from big to small chooses the second predetermined number (for example, 3) geography information
The geography information point corresponding to geographical entity that point is visited in positioning time as user.
The method that above-described embodiment of the application is provided is by the elements of a fix according to user and positioning time and above-mentioned
History visiting geography information point classification sequence of the user before positioning time, determines that user visits in positioning time and is sat with positioning
Target distance is less than the geographical entity indicated by each geography information point in 1 geography information point of predeterminable range threshold value
Visiting probable value, and finally determine the geography information point corresponding to the geographical entity that user was visited in positioning time so that
The history visiting geography information point classification of the elements of a fix and positioning time and user before positioning time is considered, is improve
Determine the degree of accuracy of the geography information point corresponding to the geographical entity that user is visited, can then improve the standard to user's portrait
Exactness.
With further reference to Fig. 3, it illustrates the flow 300 of another embodiment of the localization method according to the application.Should
The flow 300 of localization method, comprises the following steps:
Step 301, obtain user location information including positioning time and the elements of a fix and above-mentioned user in positioning
Between before history visiting geography information point classification sequence.
Step 302, obtains geography information point coordinates with the distance of the elements of a fix less than at least one of predeterminable range threshold value
Geography information point.
In the present embodiment, in the embodiment shown in the concrete operations of step 301 and step 302 and Fig. 2 a step 201 and
The operation of step 202 is essentially identical, will not be repeated here.
Step 303, the history visiting geography information point classification sequence by user before positioning time imports training in advance
Geography information point class prediction model, obtain user positioning time visit at least one geography information point classification in each ground
The visiting class probability value of the geographical entity indicated by reason information point classification.
Wherein, it is each in history visiting geography information point classification sequence of at least one geography information point classification including user
The geography information point classification of each geography information point in individual history visiting geography information point classification and at least one geography information point.
In practice, at least one geography information point classification can be obtained from location Based service.Here, geography information point classification is pre-
Surveying model is used to characterize the corresponding relation of geography information point classification sequence and geography information point classification.
Alternatively, the step of above-mentioned localization method can also include following training geography information point class prediction model:It is first
First, at least one history visiting geography information point classification sequence of at least one user is obtained.Then, by acquired at least one
Individual history visiting geography information point classification sequence is used as training data, and training recurrent neural network is pre- as geography information point classification
Survey model.
Step 304, to each geography information point in 1 geography information point, according to location information, it is determined that positioning is sat
It is marked on the probable value that positioning time belongs to the geographical entity indicated by the geography information point.
Alternatively, wherein it is determined that the elements of a fix belong to the geographical entity indicated by the geography information point in positioning time
Probable value, can be carried out as follows:
First, according to the elements of a fix and the elements of a fix probability distribution of the geography information point, determine that the elements of a fix belong to this
The probable value of the geographical entity indicated by geography information point.Specifically may be referred to the phase of sub-step A in the embodiment shown in Fig. 2 a
Speak on somebody's behalf bright, will not be repeated here.
Secondly, according to positioning time and the positioning time probability distribution of the geography information point, the geography information point institute is determined
The probable value that the geographical entity of instruction is visited in positioning time.Specifically may be referred to sub-step B in the embodiment shown in Fig. 2 a
Related description, will not be repeated here.
Finally, the probable value of the geographical entity according to indicated by the elements of a fix belong to the geography information point and the geography information
The probable value that the indicated geographical entity of point is visited in positioning time, determines that the elements of a fix belong to geography letter in positioning time
Cease the probable value of the geographical entity indicated by point.Specifically may be referred to mutually speaking on somebody's behalf for sub-step C in the embodiment shown in Fig. 2 a
It is bright, will not be repeated here.
Step 305, to each geography information point in 1 geography information point, belongs to according to the elements of a fix in positioning time
Visited the geography of the geography information point in positioning time in the probable value of the geographical entity indicated by the geography information point and user
The visiting class probability value of the geographical entity indicated by information point classification, determines that user visits the geography information point in positioning time
The visiting probable value of indicated geographical entity.
A kind of specific implementation is given below:
P(U,t,Scat| poi)=P (Scat|poicat) P (U, t | poi) (formula 6)
Wherein, U is the elements of a fix, and U can be two-dimensional coordinate (xu,yu), or three-dimensional coordinate (xu,yu,zu), t is
Positioning time, ScatIt is historical geography information point classification sequence of the user before positioning time t, P (Scat|poicat) it is step
By history visiting geography information point classification sequence S in 303catThe geography information point class prediction model for importing training in advance is obtained
User positioning time t visitings geography information point poi geography information point classification poicatProbable value, P (U, t | poi) is
Elements of a fix U obtained by being calculated in step 304 belongs to the geographical entity indicated by geography information point poi in positioning time t
Probable value.P(U,t,Scat| poi) be calculate obtained by user in the geography indicated by positioning time t visitings geography information point poi
The visiting probable value of entity.
Step 306, according to identified each visiting probable value, determines the geographical entity that user is visited in positioning time
Corresponding geography information point.
In the present embodiment, the basic phase of operation of the concrete operations of step 306 and step 204 in the embodiment shown in Fig. 2 a
Together, will not be repeated here.
From figure 3, it can be seen that compared with the corresponding embodiments of Fig. 2 a, the flow 300 of the localization method in the present embodiment
Highlight by the elements of a fix positioning time belong to the geographical entity indicated by the geography information point probable value and user fixed
The position time visit the geography information point geography information point classification indicated by the visiting class probability value of geographical entity melted
The step of conjunction, thus, the scheme of the present embodiment description can consider the elements of a fix and positioning time and user in positioning
History visiting geography information point classification before time, improves the geography information corresponding to the geographical entity that determination user is visited
The degree of accuracy of point, can then improve the degree of accuracy to user's portrait.
With further reference to Fig. 4, as the realization to method shown in above-mentioned each figure, this application provides a kind of positioner
One embodiment, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2 a, and the device specifically can apply to various
In electronic equipment.
As shown in figure 4, the positioner 400 of the present embodiment includes:First acquisition unit 401, second acquisition unit 402,
First determining unit 403 and the second determining unit 404.Wherein, first acquisition unit 401, are configured to obtain including for user
History visiting geography information point of the location information and above-mentioned user of positioning time and the elements of a fix before above-mentioned positioning time
Classification sequence;Second acquisition unit 402, is configured to obtain the distance of geography information point coordinates and the above-mentioned elements of a fix less than pre-
If 1 geography information point of distance threshold, wherein, geography information point includes geography information point coordinates and geography information point
Classification;First determining unit 403, is configured to each geography information point in above-mentioned at least one geography information point, based on upper
The history visiting geography information point classification sequence of location information and above-mentioned user before above-mentioned positioning time is stated, above-mentioned use is determined
The visiting probable value of the geographical entity that family is visited indicated by the geography information point in above-mentioned positioning time;Second determining unit 404,
Each visiting probable value according to determined by is configured to, the geographical entity that above-mentioned user is visited in above-mentioned positioning time is determined
Corresponding geography information point.
In the present embodiment, the first acquisition unit 401 of above-mentioned positioner 400, second acquisition unit 402, first are true
Order unit 403 can be corresponding real with reference to Fig. 2 a respectively with the specific treatment of the second determining unit 404 and its technique effect for being brought
The related description of step 201, step 202, step 203 and step 204 in example is applied, be will not be repeated here.
In some optional implementations of the present embodiment, above-mentioned first determining unit 403 can include:First determines
Module 4031, is configured to the history visiting geography information point classification sequence by above-mentioned user before above-mentioned positioning time and imports
The geography information point class prediction model of training in advance, obtains above-mentioned user in the geographical letter of visiting of above-mentioned positioning time at least one
The visiting class probability value of the geographical entity in breath point classification indicated by each geography information point classification, wherein, above-mentioned at least one
Individual geography information point classification is included in history visiting geography information point classification sequence of the above-mentioned user before above-mentioned positioning time
Each history visiting geography information point classification and above-mentioned at least one geography information point in each geography information point geographical letter
Breath point classification;Second determining module 4032, is configured to each geography information point, root in above-mentioned at least one geography information point
According to above-mentioned location information, determine that the above-mentioned elements of a fix belong to geographical real indicated by the geography information point in above-mentioned positioning time
The probable value of body;3rd determining module 4033, is configured to each geography information point in above-mentioned at least one geography information point,
The probable value of the geographical entity indicated by above-mentioned positioning time belonging to the geography information point according to the above-mentioned elements of a fix and above-mentioned
User above-mentioned positioning time visit the geography information point geography information point classification indicated by geographical entity visiting classification
Probable value, determines the visiting probability of the geographical entity that above-mentioned user visits indicated by the geography information point in above-mentioned positioning time
Value.First determining module 4031, the specific treatment of the second determining module 4032 and the 3rd determining module 4033 and its brought
Technique effect can respectively refer to the related description of step 303, step 304 and step 305 in Fig. 3 correspondence embodiments, herein no longer
Repeat.
In some optional implementations of the present embodiment, above-mentioned second determining module 4032 can include:First is true
Stator modules (not shown), is configured to according to the above-mentioned elements of a fix and the elements of a fix probability distribution of the geography information point, really
The fixed above-mentioned elements of a fix belong to the probable value of the geographical entity indicated by the geography information point;Second determination sub-module (is not shown
Go out), it is configured to, according to above-mentioned positioning time and the positioning time probability distribution of the geography information point, determine the geography information point
The probable value that indicated geographical entity is visited in above-mentioned positioning time, wherein, the positioning time probability of the geography information point
Distribution is to carry out counting what is obtained according to the history positioning time of the history of geography information point visiting user;3rd determines submodule
Block (not shown), the probable value of the geographical entity being configured to according to indicated by the above-mentioned elements of a fix belong to the geography information point and
The probable value that geographical entity indicated by the geography information point is visited in above-mentioned positioning time, determines the above-mentioned elements of a fix upper
State the probable value that positioning time belongs to the geographical entity indicated by the geography information point.First determination sub-module, second determine son
Module and the specific treatment of the 3rd determination sub-module and its technique effect for being brought can respectively with reference in the corresponding embodiments of Fig. 2 a
The related description of sub-step A, sub-step B and sub-step C, will not be repeated here.
In some optional implementations of the present embodiment, the elements of a fix probability distribution of the above-mentioned geography information point can
Obtained with by following operation:Obtain the history elements of a fix of the history visiting user of the geography information point;To acquired
The history elements of a fix clustered to obtain at least one elements of a fix cluster centre of the geography information point;According to the geography
The geography information point coordinates of information point and each elements of a fix at least one elements of a fix cluster centre of the geography information point
The distance between cluster centre, determines that each elements of a fix cluster centre of the geography information point belongs to geography information point meaning
The probable value of the geographical entity for showing, and identified each elements of a fix cluster centre is belonged to indicated by the geography information point
Geographical entity probable value as the geography information point elements of a fix probability distribution.Specifically refer to Fig. 2 a correspondence embodiments
The related description of middle sub-step A1, sub-step A2 and sub-step A3, will not be repeated here.
In the optional implementation of some of the present embodiment, above-mentioned positioner 400 can also include geography information point class
Other forecast model training unit (not shown), above-mentioned geography information point class prediction model training unit is configured to:Obtain extremely
At least one history visiting geography information point classification sequence of a few user;By above-mentioned at least one history visiting geography information
, used as training data, training recurrent neural network is used as geography information point class prediction model for point classification sequence.Geography information point
The specific treatment of class prediction model training unit and its technique effect for being brought refer to sub-step in Fig. 2 a correspondence embodiments
Rapid 2031 related description, will not be repeated here.
Below with reference to Fig. 5, it illustrates the computer system 500 for being suitable to the server for realizing the embodiment of the present application
Structural representation.Server shown in Fig. 5 is only an example, to the function of the embodiment of the present application and should not use range band
Carry out any limitation.
As shown in figure 5, computer system 500 includes CPU (CPU, Central Processing Unit)
501, it can be according to program of the storage in read-only storage (ROM, Read Only Memory) 502 or from storage part
506 programs being loaded into random access storage device (RAM, Random Access Memory) 503 and perform it is various appropriate
Action and treatment.In RAM 503, the system that is also stored with 500 operates required various programs and data.CPU 501、ROM
502 and RAM 503 is connected with each other by bus 504.Input/output (I/O, Input/Output) interface 505 is also connected to
Bus 504.
I/O interfaces 505 are connected to lower component:Storage part 506 including hard disk etc.;And including such as LAN (locals
Net, Local Area Network) card, modem etc. NIC communications portion 507.Communications portion 507 is passed through
Communication process is performed by the network of such as internet.Driver 508 is also according to needing to be connected to I/O interfaces 505.Detachable media
509, such as disk, CD, magneto-optic disk, semiconductor memory etc., as needed on driver 508, in order to from
The computer program for reading thereon is mounted into storage part 506 as needed.
Especially, in accordance with an embodiment of the present disclosure, the process above with reference to flow chart description may be implemented as computer
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being carried on computer-readable Jie
Computer program in matter, the computer program includes the program code for the method shown in execution flow chart.Such
In embodiment, the computer program can be downloaded and installed by communications portion 507 from network, and/or be situated between from detachable
Matter 509 is mounted.When the computer program is performed by CPU (CPU) 501, restriction in the present processes is performed
Above-mentioned functions.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Person's computer-readable recording medium or the two are combined.Computer-readable recording medium for example can be ---
But be not limited to --- the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or device, or it is any more than group
Close.The more specifically example of computer-readable recording medium can be included but is not limited to:Being electrically connected with one or more wires
Connect, portable computer diskette, hard disk, random access storage device (RAM), read-only storage (ROM), erasable type may be programmed it is read-only
Memory (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer-readable recording medium can be it is any comprising or storage
The tangible medium of program, the program can be commanded execution system, device or device and use or in connection.And
In the application, computer-readable signal media can include believing in a base band or as the data that a carrier wave part is propagated
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium beyond readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Included on computer-readable medium
Program code any appropriate medium can be used to transmit, including but not limited to:Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
The architectural framework in the cards of sequence product, function and operation.At this point, each square frame in flow chart or block diagram can generation
One part for module, program segment or code of table a, part for the module, program segment or code is used comprising one or more
In the executable instruction of the logic function for realizing regulation.It should also be noted that in some are as the realization replaced, being marked in square frame
The function of note can also occur with different from the order marked in accompanying drawing.For example, two square frames for succeedingly representing are actually
Can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also to note
Meaning, the combination of the square frame in each square frame and block diagram and/or flow chart in block diagram and/or flow chart can be with holding
The fixed function of professional etiquette or the special hardware based system of operation are realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in involved unit in the embodiment of the present application can be realized by way of software, it is also possible to by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as:A kind of processor bag
Include first acquisition unit, second acquisition unit, the first determining unit and the second determining unit.Wherein, the title of these units exists
The restriction to the unit in itself is not constituted in the case of certain, for example, second acquisition unit is also described as " obtaining at least
One unit of geography information point ".
Used as on the other hand, present invention also provides a kind of computer-readable medium, the computer-readable medium can be
Included in device described in above-described embodiment;Can also be individualism, and without in allocating the device into.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device:Obtain user location information including positioning time and the elements of a fix and above-mentioned user before above-mentioned positioning time
History visiting geography information point classification sequence;Obtain geography information point coordinates and be less than predeterminable range with the distance of the above-mentioned elements of a fix
1 geography information point of threshold value, wherein, geography information point includes geography information point coordinates and geography information point classification;It is right
Each geography information point in above-mentioned at least one geography information point, based on above-mentioned location information and above-mentioned user in above-mentioned positioning
Between before history visiting geography information point classification sequence, determine that above-mentioned user visits the geography information point in above-mentioned positioning time
The visiting probable value of indicated geographical entity;According to identified each visiting probable value, determine above-mentioned user above-mentioned fixed
The geography information point corresponding to geographical entity that the position time is visited.
Above description is only the preferred embodiment and the explanation to institute's application technology principle of the application.People in the art
Member is it should be appreciated that involved invention scope in the application, however it is not limited to the technology of the particular combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where foregoing invention design is not departed from, is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical schemes for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical scheme that the technical characteristic of energy is replaced mutually and formed.
Claims (12)
1. a kind of localization method, it is characterised in that methods described includes:
Obtain user location information including positioning time and the elements of a fix and the user before the positioning time
History visiting geography information point classification sequence;
Obtain at least one geography information of the distance less than predeterminable range threshold value of geography information point coordinates and the elements of a fix
Point, wherein, geography information point includes geography information point coordinates and geography information point classification;
To each geography information point at least one geography information point, based on the location information and the user described
History visiting geography information point classification sequence before positioning time, determines that the user visits the geography in the positioning time
The visiting probable value of the geographical entity indicated by information point;
According to identified each visiting probable value, determine that the geographical entity institute that the user is visited in the positioning time is right
The geography information point answered.
2. method according to claim 1, it is characterised in that described to each ground at least one geography information point
Reason information point, the history visiting geography information point classification based on the location information and the user before the positioning time
Sequence, determines the visiting probable value of the geographical entity that the user visits indicated by the geography information point in the positioning time,
Including:
History visiting geography information point classification sequence by the user before the positioning time imports the ground of training in advance
Reason information point class prediction model, obtains the user every in the positioning time visits at least one geography information point classification
The visiting class probability value of the geographical entity indicated by individual geography information point classification;
To each geography information point at least one geography information point, according to the location information, determine that the positioning is sat
It is marked on the probable value that the positioning time belongs to the geographical entity indicated by the geography information point;
To each geography information point at least one geography information point, belonged in the positioning time according to the elements of a fix
Visited the geography information in the positioning time in the probable value of the geographical entity indicated by the geography information point and the user
The visiting class probability value of the geographical entity indicated by the geography information point classification of point, determines the user in the positioning time
The visiting probable value of the geographical entity visited indicated by the geography information point.
3. method according to claim 2, it is characterised in that described according to the location information, determines that the positioning is sat
The probable value that the positioning time belongs to the geographical entity indicated by the geography information point is marked on, including:
According to the elements of a fix and the elements of a fix probability distribution of the geography information point, determine that the elements of a fix belong to the ground
The probable value of the geographical entity indicated by reason information point;
According to the positioning time and the positioning time probability distribution of the geography information point, determine indicated by the geography information point
The probable value that geographical entity is visited in the positioning time, wherein, the positioning time probability distribution of the geography information point is root
Carry out counting what is obtained according to the history positioning time of the history visiting user of the geography information point;
The probable value of the geographical entity according to indicated by the elements of a fix belong to the geography information point and the geography information point institute
The probable value that the geographical entity of instruction is visited in the positioning time, determines that the elements of a fix belong in the positioning time
The probable value of the geographical entity indicated by the geography information point.
4. method according to claim 3, it is characterised in that the elements of a fix probability distribution of the geography information point is
Obtained by following operation:
Obtain the history elements of a fix of the history visiting user of the geography information point;
The acquired history elements of a fix are clustered with least one elements of a fix cluster for obtaining the geography information point
The heart;
At least one elements of a fix cluster centre of geography information point coordinates and the geography information point according to the geography information point
In the distance between each elements of a fix cluster centre, determine that each elements of a fix cluster centre of the geography information point belongs to this
The probable value of the geographical entity indicated by geography information point, and identified each elements of a fix cluster centre is belonged into the geography
The probable value of the geographical entity indicated by information point as the geography information point elements of a fix probability distribution.
5. according to any described method in claim 2-4, it is characterised in that methods described also includes training geography information point
The step of the step of class prediction model, training geography information point class prediction model, includes:
Obtain at least one history visiting geography information point classification sequence of at least one user;
Using at least one history visiting geography information point classification sequence as training data, recurrent neural network conduct is trained
Geography information point class prediction model.
6. a kind of positioner, it is characterised in that described device includes:
First acquisition unit, is configured to obtain the location information including positioning time and the elements of a fix of user and the user
History visiting geography information point classification sequence before the positioning time;
Second acquisition unit, is configured to obtain the distance of geography information point coordinates and the elements of a fix less than predeterminable range threshold
1 geography information point of value, wherein, geography information point includes geography information point coordinates and geography information point classification;
First determining unit, is configured to each geography information point at least one geography information point, based on described fixed
The history visiting geography information point classification sequence of position information and the user before the positioning time, determines that the user exists
The positioning time visits the visiting probable value of the geographical entity indicated by the geography information point;
Second determining unit, is configured to each visiting probable value according to determined by, determines the user in the positioning
Between geography information point corresponding to the geographical entity visited.
7. device according to claim 6, it is characterised in that first determining unit includes:
First determining module, is configured to the history visiting geography information point classification before the positioning time by the user
Sequence imports the geography information point class prediction model of training in advance, obtains the user in positioning time visiting at least
The visiting class probability value of the geographical entity in individual geography information point classification indicated by each geography information point classification;
Second determining module, is configured to each geography information point at least one geography information point, according to described fixed
Position information, determines that the elements of a fix belong to the probability of the geographical entity indicated by the geography information point in the positioning time
Value;
3rd determining module, is configured to each geography information point at least one geography information point, according to described fixed
Position coordinate the positioning time belong to the geographical entity indicated by the geography information point probable value and the user described
Positioning time visit the geography information point geography information point classification indicated by geographical entity visiting class probability value, it is determined that
The visiting probable value of the geographical entity that the user visits indicated by the geography information point in the positioning time.
8. device according to claim 7, it is characterised in that second determining module includes:
First determination sub-module, is configured to according to the elements of a fix and the elements of a fix probability distribution of the geography information point,
Determine that the elements of a fix belong to the probable value of the geographical entity indicated by the geography information point;
Second determination sub-module, is configured to according to the positioning time and the positioning time probability distribution of the geography information point,
Determine the probable value that the geographical entity indicated by the geography information point is visited in the positioning time, wherein, the geography information
The positioning time probability distribution of point is according to the history positioning time of the history of geography information point visiting user count
Arrive;
3rd determination sub-module, the geographical entity being configured to according to indicated by the elements of a fix belong to the geography information point
The probable value that geographical entity indicated by probable value and the geography information point is visited in the positioning time, determines the positioning
Coordinate belongs to the probable value of the geographical entity indicated by the geography information point in the positioning time.
9. device according to claim 8, it is characterised in that the elements of a fix probability distribution of the geography information point is
Obtained by following operation:
Obtain the history elements of a fix of the history visiting user of the geography information point;
The acquired history elements of a fix are clustered with least one elements of a fix cluster for obtaining the geography information point
The heart;
At least one elements of a fix cluster centre of geography information point coordinates and the geography information point according to the geography information point
In the distance between each elements of a fix cluster centre, determine that each elements of a fix cluster centre of the geography information point belongs to this
The probable value of the geographical entity indicated by geography information point, and identified each elements of a fix cluster centre is belonged into the geography
The probable value of the geographical entity indicated by information point as the geography information point elements of a fix probability distribution.
10. according to any described device in claim 7-9, it is characterised in that described device also includes geography information point class
Other forecast model training unit, the geography information point class prediction model training unit is configured to:
Obtain at least one history visiting geography information point classification sequence of at least one user;
Using at least one history visiting geography information point classification sequence as training data, recurrent neural network conduct is trained
Geography information point class prediction model.
A kind of 11. servers, including:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processors
Realize the method as described in any in claim 1-5.
A kind of 12. computer-readable recording mediums, are stored thereon with computer program, it is characterised in that the program is by processor
The method as described in any in claim 1-5 is realized during execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710068541.1A CN106767835B (en) | 2017-02-08 | 2017-02-08 | Positioning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710068541.1A CN106767835B (en) | 2017-02-08 | 2017-02-08 | Positioning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106767835A true CN106767835A (en) | 2017-05-31 |
CN106767835B CN106767835B (en) | 2020-09-25 |
Family
ID=58956078
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710068541.1A Active CN106767835B (en) | 2017-02-08 | 2017-02-08 | Positioning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106767835B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108875007A (en) * | 2018-06-15 | 2018-11-23 | 腾讯科技(深圳)有限公司 | The determination method and apparatus of point of interest, storage medium, electronic device |
WO2019000468A1 (en) * | 2017-06-30 | 2019-01-03 | 广东欧珀移动通信有限公司 | User location identification method and apparatus, storage medium, and electronic device |
WO2019019786A1 (en) * | 2017-07-27 | 2019-01-31 | 杭州海康威视数字技术股份有限公司 | Vehicle positioning method, apparatus and device |
CN110677815A (en) * | 2019-08-07 | 2020-01-10 | 北京百度网讯科技有限公司 | Stay point identification method and device, computer equipment and storage medium |
CN110930187A (en) * | 2019-11-19 | 2020-03-27 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for mining shop visiting people |
CN111132029A (en) * | 2019-10-16 | 2020-05-08 | 张苏 | Positioning method and device based on terrain constraint |
CN111126736A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术(北京)有限公司 | Enterprise passenger flow determining method and device, server and storage medium |
US11379741B2 (en) | 2019-08-07 | 2022-07-05 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus and storage medium for stay point recognition and prediction model training |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101393035A (en) * | 2007-09-21 | 2009-03-25 | 株式会社电装 | Route length calculation apparatus and route length calculation method |
CN102298608A (en) * | 2010-06-16 | 2011-12-28 | 索尼公司 | Information processing apparatus, information processing method and program |
CN105138590A (en) * | 2015-07-31 | 2015-12-09 | 北京嘀嘀无限科技发展有限公司 | Trajectory prediction method and apparatus |
CN105183800A (en) * | 2015-08-25 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Information prediction method and apparatus |
CN105893537A (en) * | 2016-03-31 | 2016-08-24 | 百度在线网络技术(北京)有限公司 | Determination method and device for geographical information points |
-
2017
- 2017-02-08 CN CN201710068541.1A patent/CN106767835B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101393035A (en) * | 2007-09-21 | 2009-03-25 | 株式会社电装 | Route length calculation apparatus and route length calculation method |
CN102298608A (en) * | 2010-06-16 | 2011-12-28 | 索尼公司 | Information processing apparatus, information processing method and program |
CN105138590A (en) * | 2015-07-31 | 2015-12-09 | 北京嘀嘀无限科技发展有限公司 | Trajectory prediction method and apparatus |
CN105183800A (en) * | 2015-08-25 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Information prediction method and apparatus |
CN105893537A (en) * | 2016-03-31 | 2016-08-24 | 百度在线网络技术(北京)有限公司 | Determination method and device for geographical information points |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11082806B2 (en) | 2017-06-30 | 2021-08-03 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method of identifying user location, storage medium and electronic device |
WO2019000468A1 (en) * | 2017-06-30 | 2019-01-03 | 广东欧珀移动通信有限公司 | User location identification method and apparatus, storage medium, and electronic device |
CN109307512A (en) * | 2017-07-27 | 2019-02-05 | 杭州海康威视数字技术股份有限公司 | A kind of vehicle positioning method, device and equipment |
WO2019019786A1 (en) * | 2017-07-27 | 2019-01-31 | 杭州海康威视数字技术股份有限公司 | Vehicle positioning method, apparatus and device |
CN108875007A (en) * | 2018-06-15 | 2018-11-23 | 腾讯科技(深圳)有限公司 | The determination method and apparatus of point of interest, storage medium, electronic device |
CN108875007B (en) * | 2018-06-15 | 2019-12-17 | 腾讯科技(深圳)有限公司 | method and device for determining interest point, storage medium and electronic device |
CN111126736A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术(北京)有限公司 | Enterprise passenger flow determining method and device, server and storage medium |
CN111126736B (en) * | 2018-11-01 | 2023-09-01 | 百度在线网络技术(北京)有限公司 | Enterprise passenger flow volume determining method and device, server and storage medium |
CN110677815A (en) * | 2019-08-07 | 2020-01-10 | 北京百度网讯科技有限公司 | Stay point identification method and device, computer equipment and storage medium |
US11379741B2 (en) | 2019-08-07 | 2022-07-05 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus and storage medium for stay point recognition and prediction model training |
US11418918B2 (en) | 2019-08-07 | 2022-08-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus, computer device and storage medium for stay point recognition |
CN111132029A (en) * | 2019-10-16 | 2020-05-08 | 张苏 | Positioning method and device based on terrain constraint |
CN110930187A (en) * | 2019-11-19 | 2020-03-27 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for mining shop visiting people |
Also Published As
Publication number | Publication date |
---|---|
CN106767835B (en) | 2020-09-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106767835A (en) | Localization method and device | |
US11449908B2 (en) | Method and system for determining transport service fee | |
AU2016102423A4 (en) | System and method for determining vehicle load status | |
CN105893537B (en) | The determination method and apparatus of geography information point | |
AU2019236639A1 (en) | Methods and systems for providing information for an on-demand service | |
CN106912018A (en) | Map-matching method and system based on signaling track | |
CN107679189A (en) | A kind of point of interest update method, device, server and medium | |
CN108268573A (en) | For the method and apparatus of pushed information | |
CN105554704A (en) | Fake-locus-based location privacy protection method for use in recommendation system | |
CN105468580A (en) | Attention point information based method and apparatus for providing service | |
US20170045365A1 (en) | Travel planner platform for providing quality tourism information | |
CN110503485B (en) | Geographical region classification method and device, electronic equipment and storage medium | |
CN104636457B (en) | A kind of method and device of location finding cognition | |
CN105989024A (en) | Method and device for determining location area of user | |
CN107883974A (en) | Planing method, navigation server and the computer-readable medium of guidance path | |
CN109242043A (en) | Method and apparatus for generating information prediction model | |
CN106855878A (en) | History wheelpath display methods and device based on electronic map | |
CN110059849A (en) | Determining method of path and device | |
CN111104468B (en) | Method for deducing user activity based on semantic track | |
CN107659596A (en) | A kind of method and device, the terminal of dynamic navigation | |
CN106886911A (en) | A kind of travelling products method and device for planning based on user's telecommunications behavioural characteristic | |
CN108549649B (en) | Rural tourism recommendation method and system based on seasonal characteristics and position characteristics | |
CN109800903A (en) | A kind of profit route planning method based on taxi track data | |
Chaudhuri et al. | Application of web-based Geographical Information System (GIS) in tourism development | |
Chen et al. | Itinerary planning via deep reinforcement learning |
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 |