CN106101222A

CN106101222A - The method for pushing of information and device

Info

Publication number: CN106101222A
Application number: CN201610409217.7A
Authority: CN
Inventors: 刘志斌
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2016-06-08
Filing date: 2016-06-08
Publication date: 2016-11-09

Abstract

The invention discloses method for pushing and the device of a kind of information.Wherein, the method includes: obtaining the geographic position data sequence of the first account, wherein, geographic position data sequence includes the first account in the geographical position residing for different time；Geographical position cluster in geographic position data sequence is obtained objective；Obtain the information at least mated with objective；Give the first account by information pushing.The present invention solves existing information-pushing method cannot the technical problem of information requirement of accurate match user.

Description

The method for pushing of information and device

Technical field

The present invention relates to internet arena, in particular to method for pushing and the device of a kind of information.

Background technology

In the mobile Internet epoch, various application emerge in an endless stream.The application program being arranged in terminal would generally push away to user Deliver letters breath, such as news, advertisement, commodity information etc..It is clear that the information pushing of these application programs current is typically to user History of looking at is analyzed, and goes out user's information interested according to browse history analysis, and pushes.

But, browse a kind of form of expression that history is only user preferences, can not accurately embody user needs to know Information, also just cannot the information requirement of accurate match user.

For above-mentioned problem, effective solution is not yet proposed at present.

Content of the invention

Embodiments provide method for pushing and the device of a kind of information, at least to solve existing information pushing side Method cannot the technical problem of information requirement of accurate match user.

An aspect according to embodiments of the present invention, provides the method for pushing of a kind of information, comprising: obtain the first account Geographic position data sequence, wherein, described geographic position data sequence includes described first account residing for different time Geographical position；Geographical position cluster in described geographic position data sequence is obtained objective；Obtain at least with described mesh The information of mark ground Point matching；Give described first account by described information pushing.

Another aspect according to embodiments of the present invention, additionally provides the pusher of a kind of information, comprising: first obtains list Unit, for obtaining the geographic position data sequence of the first account, wherein, described geographic position data sequence includes described first account Number in the geographical position residing for different time；Cluster cell, for gathering the geographical position in described geographic position data sequence Class obtains objective；Second acquisition unit, for obtaining the information at least mated with described objective；Push unit, uses In by described information pushing give described first account.

In embodiments of the present invention, the geographic position data sequence of acquisition the first account, wherein, geographic position data are used Sequence includes the first account in the geographical position residing for different time；Geographical position in geographic position data sequence is clustered To objective；Obtain the information at least mated with objective；Information pushing is given the mode of the first account, according to clustering out Objective obtain coupling information, the information of coupling more conforms to the information requirement of the first account, thus solves existing Information-pushing method cannot the technical problem of information requirement of accurate match user.

Brief description

Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this Bright schematic description and description is used for explaining the present invention, is not intended that inappropriate limitation of the present invention.In the accompanying drawings:

Fig. 1 is the Organization Chart of hardware system according to embodiments of the present invention；

Fig. 2 is the flow chart of information-pushing method according to embodiments of the present invention；

Fig. 3 is the schematic diagram that isomery sequence characteristics according to embodiments of the present invention disassembles packet aggregation module；

Fig. 4 is the schematic diagram of isomorphism vector space sequential density additive fusion module according to embodiments of the present invention；

Fig. 5 is the schematic diagram of the elastic partition-merge module of isomery vector space matrix according to embodiments of the present invention；

Fig. 6 is the schematic diagram of interpolation alignment padding sequence according to embodiments of the present invention；

Fig. 7 is the schematic diagram of alternative splicing sequence according to embodiments of the present invention；

Fig. 8 is the schematic flow sheet extracting static geographical attribute according to embodiments of the present invention；

Fig. 9 is the schematic flow sheet of extraction Dynamic Geographic attribute according to embodiments of the present invention；

Figure 10 is the schematic diagram of information push-delivery apparatus according to embodiments of the present invention；

Figure 11 is the structure chart of server according to embodiments of the present invention.

Detailed description of the invention

In order to make those skilled in the art be more fully understood that the present invention program, below in conjunction with in the embodiment of the present invention Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people The every other embodiment that member is obtained under the premise of not making creative work, all should belong to the model of present invention protection Enclose.

It should be noted that term " first " in description and claims of this specification and above-mentioned accompanying drawing, " Two " it is etc. for distinguishing similar object, without being used for describing specific order or precedence.Should be appreciated that so use Data can exchange in the appropriate case, in order to embodiments of the invention described herein can with except here diagram or Order beyond those describing is implemented.Additionally, term " includes " and " having " and their any deformation, it is intended that cover Covering non-exclusive comprising, for example, the process, method, system, product or the equipment that contain series of steps or unit are not necessarily limited to Those steps clearly listed or unit, but can include clearly not listing or for these processes, method, product Or intrinsic other steps of equipment or unit.

Before the present invention is further elaborated, the noun and term relating in the embodiment of the present invention is said Bright, the noun relating in the embodiment of the present invention and term are applicable to following explanation.

1) geographical position, user's location when using based on location-based service, longitude and latitude etc. can be used arbitrarily may be used Characterize in the way of calibration position.

2) objective, obtains after the cluster of geographical position, and place can be a geographical position, it is also possible to Shi Yige district Territory.

3) geographic position data sequence, is the sequence that basic element is constituted with " time geographical position ", and geographical position refers to User uses based on location during location-based service, the time refer to user's time in this position (can be a certain moment, Also can be one is the time period).Exemplarily, " geographical location marker time " such form recording geographical position is used And the time.

4) geographical attribute, comprising:

Static geographical attribute: the category attribute corresponding to several places that user often haunts.

Dynamic Geographic attribute: motion track pattern (such as A place, place B place C) between multiple places for the user, or Space-time migration model (for example, " every morning 6 adheres to outdoor exercises ", " about 8 drivings of coming off duty every night are gone home " etc.)；In advance In the classification system of the different mode first set up, same pattern (motion track pattern and space-time migration model) is carried out multiple The division (description) of dimension simultaneously gives respective labels, obtains motion track pattern or the multidimensional of space-time migration model describes.

5) account attribute: for representing for being in the spy that the semanteme expressed by certain geographical position shows in certain field Levying, such as, geographical position is at the congestion status represented by suburb, area wealth etc..

6) apply (App): be often referred to the application software on equipment (such as smart mobile phone) in the narrow sense, also refer to all and calculate All application software outside the upper division operation system of machine equipment (containing PC, mobile terminal, cloud computing sever platform etc.) and son thereof are soft Part (such as plug-in unit).

According to embodiments of the present invention, a kind of embodiment of the method that can be performed is provided by the application device embodiment, It should be noted that can be in the department of computer science of such as one group of computer executable instructions in the step shown in the flow chart of accompanying drawing System performs, and, although show logical order in flow charts, but in some cases, can be to be different from herein Order perform shown or described step.

According to embodiments of the present invention, the method for pushing of a kind of information is provided.

Alternatively, in the present embodiment, the method for pushing of above-mentioned information can apply to terminal 102 He as shown in Figure 1 In the hardware environment that server 104 is constituted.As it is shown in figure 1, terminal 102 is attached with server 104 by network, above-mentioned Network includes but is not limited to: mobile communications network, wide area network, Metropolitan Area Network (MAN) or LAN, and terminal 102 can be mobile phone terminal, also Can be PC terminal, notebook terminal or panel computer terminal.

The main operational principle of the hardware environment system shown in Fig. 1 is:

Terminal 102 can gather the geographic position data of user, or receives the geographic position data that smart machine gathers. The geographic position data of acquisition is sent to server 104 by terminal 102, forms geographic position data sequence.Server 104 is to this A little geographic position data sequences are processed, and analyze the semanteme expressed by geographical position and geographic position data sequence, thus Push the information meeting semanteme for user.The terminal receiving pushed information can be with the terminal of the geographic position data gathering user Identical or different.For example, the geographic position data display user of collection is currently at job site, then recommend position for user Information；If active user is in lunch place, then recommend dining room for user；Move to place of abode from job site if user is in Move, then traffic route not blocked up to user's recommendation etc..

The equipment of gathering geographic position data may is that mobile phone, panel computer, Wearable (intelligent watch, Brilliant Eyes Mirror) and car-mounted terminal etc., the said equipment has locating module, and is provided with the authority to terminal positioning such that it is able to collect phase Answer geographical position and the time of user.Or, at terminal operating based on location-based service (the lookup nearby friends such as social networking application Navigation feature etc. in function, map application).

Fig. 2 is the flow chart of the method for pushing of information according to embodiments of the present invention, implements the present invention below in conjunction with Fig. 2 The method for pushing of the information that example is provided does concrete introduction, as in figure 2 it is shown, the method for pushing of this information mainly includes walking as follows Rapid:

Step S202, obtains the geographic position data sequence of the first account, and wherein, geographic position data sequence includes first Account is in the geographical position residing for different time.

Geographical position cluster in geographic position data sequence is obtained objective by step S204.

Step S206, obtains the information at least mated with objective.

Information pushing is given the first account by step S208.

Obtain the geographic position data sequence that one or more data collection station gathers, and to geographic position data sequence Row carry out cluster analysis, obtain objective.The determination of objective can be determined according to dimension to be analyzed.Determining After objective, push corresponding information to the first account.

In certain embodiments, when pushing corresponding financing information to analyze the economic situation of user, user is obtained The amusement and recreation place often coming in and going out and job site, thus judge the economic situation of user, and push according to economic situation Corresponding financing information.

In certain embodiments, in order to push traffic related information to user, job site and the residence of user are analyzed Path between point, and combine user and provide the user the optimal path in commuter time section the common commuter time.

Geographic position data sequence according to the first account determines the behavioural characteristic of the first account, and true according to objective Fixed matched information, and give the first account by information pushing so that the information of propelling movement is more accurate, solves prior art It is accustomed to carrying out pushing the inaccurate technical problem being caused according only to browsing when pushed information.

Above example is all based on obtaining objective, and the method just obtaining objective below illustrates.

The first: process is carried out to the geographic position data sequence from different pieces of information source and obtains objective.Geographical position Put data sequence as shown in table 1.

Table 1

As shown in table 1, can be described in three dimensions for same place 1, these three dimension is respectively divides Class dimension A, classification dimension B and classification dimension C, i.e. each place one or more dimension corresponding, each dimension has one Or multiple dimensional characteristics.In Table 1, the dimensional characteristics that " residence " " place of working " and " amusement and leisure ground " is classification dimension A. Visible, a geographical position can be expressed by multiple dimensions, and each dimension includes that multiple dimensional characteristics information is retouched State.

When obtaining objective, the multiple geographical position in a dimension can be clustered, or, to multiple dimensions Degree clusters.

1) when some dimension being clustered, the geographical position with identical dimensional characteristics information is classified as a class or Person one group.For example, by geographic position data sequence representing, the geographical position of residence is classified as one group, by geographic position data sequence Row representing, the geographical position of job site is classified as one group.

2), when clustering multiple dimensions, the cluster result according to each dimension carries out across dimension cluster.For example, it is possible to Classification dimension A, classification dimension B and classification dimension C etc. are reconfigured the static geographical attributive character (example obtaining a multidimensional As place 1 is residence, is in the suburbs), or (for example, the amusement in place 3 is stopped to be mapped to high level abstract semantics classification Public land is advanced entertainment place), or calculate based on the relevance between classification dimension A, classification dimension B and classification dimension C etc. Joint probability density function the result to each dimension are modified, optimize, to improve the accuracy rate of result.

Above-mentioned handling process is as shown in Figure 3.

Data source 1 to data source n is separately input to model of dividing and ruling, and obtains intermediate object program (geographical attribute sequence), including many The static geographical sequence of attributes of dimension and Dynamic and Multi dimensional geographical attribute sequence.

Geographical attribute sequence inputting to heterogeneous characteristic is disassembled in module, is used for extracting certain geographical position in certain dimension Under dimensional characteristics information.For example, in table 1, place 1 is residence under dimension A, is the suburbs under dimension B.

It is grouped by tagsort grouping module, the geographical position with identical dimensional characteristics information is divided into one Group.And by homogenous characteristics Fusion Module, of a sort dimensional characteristics information is merged.Each class dimensional characteristics information is adopted Merge with a kind of fusion device.

Each class dimensional characteristics information so and after be input to across category feature Fusion Module, carry out across class fusion, it is thus achieved that multidimensional Static geographical attributive character, be mapped to high level abstract semantics classification and probability density etc., and input results.

Modules shown in Fig. 3 and fusion device can use different algorithms to perform, and improve the flexibility of fusion, adopt Make result more accurate with the algorithm being more suitable for certain dimensional characteristics information.

The second: isomorphism vector space sequential density additive fusion.To the geographic position data sequence from different pieces of information source Row are mapped in isomorphism vector space expression so that the data of homology do not have than your implication sum gage degree.

Data for different pieces of information source can use different isomorphism vector space conversion models to map.For example, Data shown in table 1 are mapped to dimension A.For example, the geographic position data sequence from a data source is according to hour For unit arrangement, the geographic position data sequence of another one data source is that unit arranges by minute, can be by The unit of this two groups of geographic position data sequences is unified to carrying out arranging or arranging in units of minute in units of hour Row.

After the mapping completing isomorphism vector, by the data investigation from different pieces of information source to time shaft.Different numbers According to source according on respective weighted superposition to time shaft, weight can be according to the respective accuracy of each data source and reliability etc. Give.In order to avoid determining that user believes from the geographical position sequence pair of corrupt data source (or accuracy not high data source) The negative effect of the degree of accuracy, when multiple geographical position sequence is overlapped, in the integrated data sequence of geographical position be The geographical position distribution weight in corresponding different pieces of information source, weight is the reliability according to each data source data, accuracy and sampling At least one density determines so that based on the pushed information shadow of the geographical position sequence pair acquisition of more reliable data source output Ring bigger, it is ensured that the accuracy of pushed information.

For example, dense motion trace data and the user's hand that user's intelligent shoe gathers is collected at night at 20 o'clock to 21 o'clock The discrete geographic position data that machine gathers.The data investigation gathering intelligent shoe and mobile phone, can be by dense to before time shaft Motion trace data and the time map corresponding to discrete geographic position data express to identical time and space.Then will The data of identical time add up, and thus there will be the data that the existing intelligent shoe of certain time point on time shaft gathers, Have again the data that mobile phone gathers so that on time shaft, the packing density in the geographical position of same time increases.

The time shaft completing after mapping is extracted and has the feature of differentiation power, and use linear and complex nonlinear classification and return Reduction method, obtains the semantic classes (account attribute) in one or more place, thus pushes and account attribute and objective The second information to coupling.Wherein, the feature having differentiation power can select for the result going for.

In certain embodiments, in order to judge the economic situation of user, from time shaft, extract whether user has room, if High consumption place, the trip mode of coming in and going out be what etc. feature.And these features are input in classification or regression model, with defeated Go out the economic situation of user.Thus obtain, according to situation, the information that will push.

Illustrate as a example by Fig. 4.

Data source 1 to data source n is respectively adopted an isomorphism vector space conversion model and carries out spatial alternation, for difference Data source can use different isomorphism vector space conversion models, the data of multiple data sources are transformed to identical isomorphism In vector space.

The data completing vector space conversion are overlapped by sequential density laminating module, and by defeated for the result after superposition Enter to isomorphic space characteristic extracting module, to extract the feature of differentiation power, for classification or analysis of regression model.

Modules shown in Fig. 4 and fusion device can use different algorithms to perform, and improve the flexibility of fusion, adopt Make result more accurate with the algorithm being more suitable for certain dimensional characteristics information.

The third: the elastic partition-merge of isomery vector space matrix.

The data sequence collecting at least two data source (is generally of different physical significance, sampling density and quantity Yardstick etc.) carry out stretching on unified time shaft, interpolation and alignment, form multi-dimensional time sequence vector matrix (being called for short HDLM).

Extract positioning data block (LDB, Location Data Block) and multidimensional positioning data block from multidimensional data matrix (MDB, Multiple Dimensional Location Data Block), in positioning data block and multidimensional positioning data block Geographical position sequence carry out dissection process and obtain geographical attribute sequence (sequence of attributes as static geographical in multidimensional, Dynamic and Multi dimensional The forms such as reason sequence of attributes) as the intermediate object program for obtaining account attribute.

In conjunction with Fig. 5 explanation.Data source 1 to data source n is input to sequential homogeneous conversion module, processes it, then inputs To isomery vector matrix recombination module, enter row matrix restructuring, then be input to the elastic division module of matrix, obtain length and differ, count According to the different matrix block of sparse degree, in Block Characteristic extraction module, corresponding feature is extracted to each matrix block, and It is calculated the fusion feature of last output through Block Characteristic Fusion Module.

One example as shown in Figure 6, by multiple data sources output geographical position sequence, according to each geographical position (with reality Line square frame identifies) the sequential sequencing of time (namely each geographical position corresponding) alignment, if a data source output Geographical position sequence in corresponding geographical position sometime lack (this is because data source does not collect use in this time The geographical position at family), then utilize the value (such as zero, with dashed rectangle mark) of acquiescence or the calculated value of interpolation algorithm to fill For the geographical position of disappearance, each geographical position sequence after processing alignment and filling builds multidimensional data square as row vector Battle array.

The corresponding geographic position data sequence from a data source of every a line of multidimensional data matrix shown in Fig. 7 (through the alignment of sequential, the disappearance filling in geographical position and interpolation processing), the first geographical position sequence to multiple data sources Arrange into the elastic partition-merge process of row matrix, obtain building the row vector (also referred to as primary features sequence) of multidimensional data matrix, It is then based on multidimensional data matrix to extract the geographical attribute in each place (obtaining geographical position cluster) and (include static geographical genus Property and Dynamic Geographic attribute) to build geographical attribute sequence (also can be considered secondary features sequence), intermediate object program.Intermediate object program can To be used for obtaining objective and account attribute, provide foundation for pushed information.

Again multiple geographical position sequence is entered by the place that the elastic partition-merge of row matrix obtains primary features sequence to above-mentioned Reason illustrates.

Usually, in multiple data sources, only one of which data source can collect geographical position sometime, accordingly Ground, in multidimensional data matrix there is Effective Numerical in each row (vectorial) generally only certain one-dimensional geographical position, this column vector (can fill default value) that the data in the geographical position of other dimensions are missing from, exists a large amount of only one in multidimensional data matrix Individual dimension has the column vector of value, and such column vector exists the feature of continuous distributed, thus forms several big blocks also It is exactly to position data block (LDB).

In addition, in multidimensional data matrix in addition to there is big block, there is also block of cells i.e. multidimensional positioning data Block (MDB), block of cells is made up of the continuous print column vector of the Effective Numerical that all there is geographical position in multiple dimensions.For example, If there are 10 data sources to collect the position of user in continuous three moment, 10 dimension (each dimensions in this moment simultaneously A corresponding data source) geographical position constitute one of multidimensional data matrix column vector, each column vector includes 10 dimensions The geographical position of degree, in multidimensional data matrix, corresponding column vector of continuous three times forms a multidimensional positioning data block.

In certain embodiments, as it is shown in fig. 7, the positioning data being identified by such a way in multidimensional data matrix Block and multidimensional positioning data block: scan by column identification multidimensional data matrix column vector, identify in poly-dimensional block data and only have The continuation column vector of effective geographic position data of one dimension is positioning data block；Identify in poly-dimensional block data and have at least The continuation column vector of effective geographic position data of two dimensions positions data block for multidimensional.Whole multidimensional data matrix is divided Position the sequence (primary features sequence) of data block alternative splicing for the positioning data block of staggered splicing and multidimensional, wherein position number Position the inconsistent (collection in each column vector corresponding data source of quantity of the column vector included by data block according to block, multidimensional Time), therefore the length of the time that positioning data block and multidimensional positioning data block are covered is inconsistent.

In order to improve the accuracy of pushed information, weight, weight and positioning can be distributed for different positioning data blocks At least one the reliability in data block corresponding data source and accuracy determine, exemplarily, positioning data block weight with corresponding The reliability of data source and accuracy positive correlation, the reliability of data source is higher with accuracy, then position the power of data block accordingly Heavily higher, so that based on the geographical position sequence pair objective of more reliable data source output and account attribute really Determining result affects japonica rice, it is ensured that the accuracy of account attribute.

In certain embodiments, for the multidimensional positioning data block identifying from multidimensional data matrix, due to multidimensional positioning Data block is that not only this time is corresponding owing to multiple data sources are formed in the geographical position that the same time collects user simultaneously The packing density in geographical position is higher than the packing density in geographical position in positioning data block, but also illustrates that user is now in certain A little special scenes or implement some specific behavior.

For example, the vehicle mounted guidance App of user collects geographical position, and the mobile phone of user is commented on App masses and also adopted simultaneously Collection arrives geographical position, illustrates that user is possible to drive and search where have a meal.If now certain good friend of this user Mobile phone also collect geographic position data, and the geographical position of good friend synchronizes with the position of this user very much, then be likely to It is that user drives to carry good friend and goes together to have a meal somewhere.

To construction in the present embodiment, static geographical attribute and Dynamic Geographic attribute illustrate individually below.

Static geographical attribute:

In one embodiment, the geographical position in the sequence of geographical position is carried out clustering (such as gathering based on distribution density Class or the cluster based on Euclidean distance) it is place, place can be a geographical position, it is also possible to be by multiple geographical position structure The region (region for example being formed by multiple geographical position) becoming.

The mark using the place after cluster replaces the mark in corresponding geographical position in geographical position sequence, when obtaining place Between sequence (sequence that the binary combination of place and time is constituted), as geographical position sequence: the geographical position 1-time is the 1st, Reason the 3rd, the geographical position 4-time 4 the 2nd, geographical position 3-time position 2-time, if geographical position 1 and geographical position 2 cluster are ground Point 1, geographical position 3 and geographical position 4 cluster are place 2, then replace geographical position 1 and geographical position 2 with place 1, utilize ground Point 2 replacement geographical position 3 and geographical position 4, the ground point sequence of formation is: during the 1st, place 1-time place 1-time the 2nd, place 2- Between the 3rd, place 2-time 4.

After forming place time series, to each place in the time series of place and corresponding time from least one Individual dimension carries out semantic classes classification, obtains the static geographical attribute of at least one dimension corresponding of each place in the time series of place (then forming multidimensional static geographical attribute during multiple dimension), based on static geographical attribute, the place corresponding time shape in each place Become static geographical sequence of attributes, such as the 1st, static geographical attribute 2-time 2 such form of static geographical attribute 1-time.

Form an example of static geographical sequence of attributes as it is shown in fig. 7, for the geographical position of random length (being designated as n) Sequence, clustering algorithm (the such as K-means by density-based algorithms (such as DBSCAN etc.) or based on Euclidean distance Deng), (being designated as m, usual m is much smaller than the list in n) place (or region) to obtain several.Based on m dimension place to n dimension geography position The mark putting geographical position in sequence is replaced, and obtains n dimension place time series.

The mode using semantic classes classification carries out semantics recognition to the place in the time series of n dimension place, it is thus achieved that static Geographical attribute sequence: m ties up " place-classification " list.Every a line in m dimension " place-classification " list has 2 data item, and first Individual data item is place ID, and second data item is classification obtained by semantics recognition for the place, such as residence, work The classifications such as ground, amusement and leisure ground.

When it is pointed out that carry out semantics recognition classifies to the various places point in the time series of place, it is possible to use one (semantics recognition grader is for each place in the time series of place for semantic classes grader or multiple semantics recognition grader Carry out the Mathematical Modeling of semantics recognition classification).Utilize multiple semantic classes grader (namely from multiple dimensions) to each ground When point carries out semantics recognition classification, correspondingly, m dimension " place-classification " list has also just been extended to many column vectors namely matrix Form, the classification being had under certain taxonomic hierarchies for each column vector each place corresponding, example such as table 1 institute Show.

As it can be seen from table 1 same place has the label of different classifications, and some under different taxonomic hierarchieses The label of the classification under dimension can lack (as in table 1/NA represents disappearance.Such as, because data source does not collect accordingly Geographical position or because type excessively obscure and cannot definitely classify).

Can directly obtain related pushed information according to static geographical attribute, such as the room rate information pushing of residence, stop The dining information propelling movement on not busy amusement ground etc..After these basic geographical attributes are analyzed, can also obtain for example: income water Flat, the level of consumption (consumption place top restaurant, common little shop), occupation type are (such as high-tech company, colleges and universities and institutional settings Deng) and the information such as quality of life, thus recommend to meet the information of user identity.For example, the colony of high income is pushed The level of consumption and the higher leisure place of quality, submit to the colony that income level is relatively low that cost performance is high but the stopping of level of consumption ground Public land point.

It is to say, the static geographical attributive character that the present embodiment can give some dimension carries out information pushing, also The static geographical attributive character that can give multiple dimension carries out information pushing.

Dynamic Geographic attribute:

Dynamic Geographic attribute uses the space-time migration model of user and the type of motion track pattern to describe, to two kinds of moulds The classification of the extraction of formula and determination pattern illustrates.

Input data shown in Fig. 8 and intermediate object program are used for being formed Dynamic Geographic attribute, input data and intermediate object program Including aforesaid n dimension geographical position sequence, n dimension place time series and m dimension " place-classification " list (or matrix).

Motion track pattern

See Fig. 9, determine that motion track pattern depends on n dimension geographical position sequence, in one embodiment, can pass through Such mode determines motion track pattern, by the geographical position in the sequence of geographical position based at least one partition of the scale (example As in time scale and space scale) it is multiple segmentations, a moving rail of the corresponding user in the geographical position in each segmentation Mark, motion track pattern on different scale for the user that the motion track on different scale is corresponding.For example in residential quarters On yardstick, user may take a walk in cell, or travels to and fro between the supermarket shopping in cell, or it is alive to carry out various entertainment in cell Move, according to different application demands, pre-establish the motion track mode type table on a series of different scale, by building Grader stamps the classification mark of at least one dimension in motion track mode type table to the motion track pattern on different scale Sign.As shown in table 2 below:

Table 2

In geographical attribute sequence, the corresponding geographical attribute in each place and time carry out mapping process, exemplarily, based on The static geographical attribute in each place and user are in the time in all kinds of place, by the Nonlinear Classifier that builds in advance and recurrence Model, credit feature that determine at least one dimension, that directly or indirectly reflect user's loan repayment capacity and refund wish, exemplary Ground, comprising: the income level of user, the level of consumption, job specification (such as day shift, night shift or in shifts), occupation type are (for example High-tech enterprise, school, institutional settings etc.), quality of life and life health degree (add for example whether often stay up late for a long time Class, life or operating pressure are big).

Based on the feature that obtains of mapping, then by compressive classification and regression model, mapping is carried out to credit feature and obtain finally Credit scoring result.

The process of the above-mentioned map user credit based on static geographical attribute is if provided as credit mapping block, except can To be used alone and outside export credit appraisal result, multiple dimension spy of user's loan repayment capacity and refund wish can also be reflected Levy as intermediate object program output, for the follow-up Dynamic Geographic attribute intermediate object program determining each place, for combining the quiet of each place State geographical attribute and the credit scoring of Dynamic Geographic attribute map user, obtain credit more comprehensive, accurate, reliable and comment Estimate.

Space-time migration model

N dimension locations and regions time series and m dimension " place-classification " list are combined, extracts user different The different subsequence (such as B-place, place A-place C) migrating between place, extracts frequently to the subsequence extracting The subsequence of pattern, namely the frequency of occurrences meets that pre-conditioned (as the frequency of occurrences is higher than frequency threshold, or the frequency of occurrences is High predetermined quantity) subsequence, as user at the space-time migration model of place rank.

In addition, the space-time migration model (such as residence-hospital-residence, or CBD between different types of place Region-high-tech park--CBD region, the suburbs etc.) in, there is also some and be under multiple category division systems frequently simultaneously Migration between the time of staying in these space-time migration models and each place, place is lasted, migrates by the subsequence of pattern Initial complete the moment etc. with migration and combine, just constitute " multidimensional space-time migration series ".By structural classification device, by these Multidimensional space-time migration series is mapped in " the space-time migration semantic classes " pre-establishing, and is formed to user's habits and customs or life The quantitative expression of pattern, for example, " often work then go to bar street to entertain 2:00 AM at 9 in evening then go home sleep ", Or " working in morning often late and on the way Dou Shi smooth traffic district " etc., above-mentioned quantitative expression can represent the happiness of user Good, habits and customs feature, and push according to the information of these feature minings user needs of user.

After the information getting coupling, can push after getting the information of coupling, can arrive user Reach pushed information after objective, it is also possible in the region reaching objective place, carry out information pushing, can also be spy Fix time pushed information etc. after arrival objective.

Based on motion track pattern derived above and space-time migration model, by the Nonlinear Classifier that builds in advance and return Return model, carry out mapping process based on motion track pattern and space-time migration model, can obtain multiple dimension, directly or Connect the associated credit feature of reflection user's loan repayment capacity and refund wish.

Exemplarily, comprising: (such as every day adheres to outdoor fortune for the habits and customs of user, work habit, sports health custom Dynamic, indoor timing body-building etc. weekly), quality of life and health status (whether having serious disease etc. for example recently), philosophy of life (for example Strict punctual, work drive foot, life are careless and sloppy freely etc.), (for example " working day lives in CBD district to income level with quality of the life Territory and the villa that goes back to the suburbs weekend is lived and leisure ", or " during work, often domestic and international aircraft is gone on business and is often gone to the beach weekend And sea " etc.), the level of consumption etc..

Based on the credit feature mapping the user obtaining, then pass through compressive classification and the credit feature to user for the regression model Carry out mapping and process the final credit scoring result obtaining user.Credit scoring may be used for many finance debt-credit fields, example The loan limit height that can obtain such as a people, or cash pledge can be exempted from for the high user of credit grade when moving in hotel Deng.

The above-mentioned credit mapping model based on Dynamic Geographic attribute is if provided as credit mapping block, except can be independent Use and export credit appraisal result outside, can also using reflection user's loan repayment capacity and refund wish multiple dimensional characteristics as Intermediate object program exports, for the follow-up Dynamic Geographic attribute intermediate object program determining each place, for the static geography combining each place Attribute and the credit scoring of Dynamic Geographic attribute map user, obtain credit evaluation more comprehensive, accurate, reliable.

It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore it is all expressed as a series of Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement because According to the present invention, some step can use other orders or carry out simultaneously.Secondly, those skilled in the art also should know Knowing, embodiment described in this description belongs to preferred embodiment, involved action and the module not necessarily present invention Necessary.

Through the above description of the embodiments, those skilled in the art is it can be understood that arrive according to above-mentioned enforcement The method of example can add the mode of required general hardware platform by software and realize, naturally it is also possible to by hardware, but a lot In the case of the former is more preferably embodiment.Based on such understanding, technical scheme is substantially in other words to existing The part that technology contributes can embody with the form of software product, and this computer software product is stored in a storage In medium (such as ROM/RAM, magnetic disc, CD), including some instructions are with so that a station terminal equipment (can be mobile phone, calculate Machine, server, or the network equipment etc.) perform the method described in each embodiment of the present invention.

According to embodiments of the present invention, the propelling movement dress of the information of a kind of method for pushing for implementing above-mentioned information is additionally provided Putting, the pusher of this information is mainly used in performing the method for pushing of the information that embodiment of the present invention foregoing is provided, with Under the pusher of information that the embodiment of the present invention is provided do concrete introduction:

Figure 10 is the schematic diagram of the pusher of information according to embodiments of the present invention, as shown in Figure 10, and pushing away of this information Device is sent to specifically include that the first acquiring unit the 10th, cluster cell the 20th, second acquisition unit 30 and push unit 40.

First acquiring unit 10 is for obtaining the geographic position data sequence of the first account, wherein, geographic position data sequence Row include the first account in the geographical position residing for different time.

Cluster cell 20 is for obtaining objective by the geographical position cluster in geographic position data sequence.

Second acquisition unit 30 is for obtaining the information at least mated with objective.

Push unit 40 is for giving the first account by information pushing.

Alternatively, second acquisition unit includes one below for obtaining the information at least mated with objective: obtain The second information mated with objective and temporal information corresponding with objective；Obtain and the target indicated by objective 3rd information of resource characteristic information matches.

Alternatively, push unit includes: the first pushing module, for obtaining and objective and corresponding with objective Temporal information coupling the second information in the case of, indicated by temporal information time reach and/or the first account detected When number being positioned at objective, give the first account by the second information pushing.

Alternatively, second acquisition unit includes: the first acquisition module, for obtain the target area at objective place with And with target area corresponding target resource characteristic information, wherein, zones of different including target area is corresponding different Resource characteristic information, resource characteristic information is for indicating the money that the account in region corresponding with resource characteristic information is had Source grade；Second acquisition module, for obtaining the 3rd information mated with target resource characteristic information.Resource characteristic information ratio As economic situation, hierarchical resource includes high-income group, common income groups.

The first: isomery sequence characteristics disassembles packet aggregation.Geographic position data sequence from different pieces of information source is carried out Process obtains objective.Geographic position data sequence is as shown in table 1.

Alternatively, cluster cell includes: the first acquisition module, for obtaining the dimensional characteristics information in geographical position, wherein, The corresponding one or more dimensions in each geographical position, each dimension has one or more dimensional characteristics information；Cluster module, uses According to the dimensional characteristics information under at least one target dimension in one or more dimensions, by geographic position data sequence Geographical position cluster obtain objective and the first account account attribute under at least one target dimension；Second obtains Unit is additionally operable to obtain the first information with objective and account attributes match.

Alternatively, cluster cell includes: the first mapping block, for by geographic position data sequence mapping to isomorphism vector In space；Second mapping block, for the power according to each data source in the geographic position data sequence of at least two data source Heavily by geographic position data sequence mapping to the time shaft of isomorphism vector space；Extraction module, meets target for extraction and belongs to The geographical position of property is as objective, and the account attribute of the first account objective；Second acquisition unit is additionally operable to obtain Take the second information with objective and account attributes match.

Alternatively, the second mapping block includes: cumulative submodule, identical for carrying out each data source on a timeline The data accumulation in geographical position.

The third: the elastic partition-merge of isomery vector space matrix.

Alternatively, cluster cell includes identification module, for identifying each column vector in multidimensional data matrix；Split mould Block, for including the dimension in effective geographical position, by the positioning that multidimensional data matrix-split is alternative splicing according to each column vector Data block and multidimensional positioning data block, wherein, multidimensional data matrix includes at least two geographic position data sequence, positions data Block includes the continuation column vector with effective geographical position of a dimension, and multidimensional positioning data block includes having at least two dimension The continuation column vector in effective geographical position of degree.

One example as it is shown in figure 5, by multiple data sources output geographical position sequence, according to each geographical position (with reality Line square frame identifies) the sequential sequencing of time (namely each geographical position corresponding) alignment, if a data source output Geographical position sequence in corresponding geographical position sometime lack (this is because data source does not collect use in this time The geographical position at family), then utilize the value (such as zero, with dashed rectangle mark) of acquiescence or the calculated value of interpolation algorithm to fill For the geographical position of disappearance, each geographical position sequence after processing alignment and filling builds multidimensional data square as row vector Battle array.

Static geographical attribute:

Alternatively, device also includes: time attribute unit, for gathering the geographical position in geographic position data sequence After class, time attribute is added to the geographic position data sequence after cluster, obtains geographical position time series；Taxon, Enter lang for the time corresponding to the geographical position in the time series of geographical position and geographical position from least one dimension Justice category classification, obtains the static geographical attribute of at least one dimension corresponding of each geographical position in the time series of geographical position.

Dynamic Geographic attribute:

Alternatively, device also includes: migration series unit, for gathering the geographical position in geographic position data sequence After class, from the time series of geographical position, extract the migration subsequence of the first account movement between diverse geographic location；Paint Unit processed, for according to the mobile geographical track migrating subsequence drafting the first account.

Alternatively, device also includes: construction unit, for the geographical position in geographic position data sequence is being clustered it After, meet pre-conditioned migration subsequence by the frequency of occurrences and build space-time migration series, and using space-time migration series as the The Dynamic Geographic attribute of one account.

According to embodiments of the present invention, the server of a kind of method for pushing for implementing above-mentioned information is additionally provided, such as figure Shown in 11, this server mainly includes processor the 401st, data-interface the 403rd, memory 405 and network interface 407, wherein:

The data-interface 403 then main geographic position data sequence by way of data are transmitted, third party's instrument being collected Processor 401 is defeated by by biographies.

Memory 405 is mainly used in the geographic position data sequence that storage gathers.

Network interface 407 is mainly used in carrying out network service with terminal device, is terminal device pushed information.

Processor 401 is mainly used in performing to operate as follows:

Obtaining the geographic position data sequence of the first account, wherein, described geographic position data sequence includes described first Account is in the geographical position residing for different time；Geographical position cluster in described geographic position data sequence is obtained target ground Point；Obtain the information at least mated with described objective；Give described first account by described information pushing.

Processor 401 is additionally operable to perform to operate as follows: the geographical position cluster in geographic position data sequence is obtained mesh Mark place includes: obtain the dimensional characteristics information in geographical position, wherein, the corresponding one or more dimensions in each geographical position, often Individual dimension has one or more dimensional characteristics information；According to the dimension under at least one target dimension in one or more dimensions Geographical position cluster in geographic position data sequence is obtained objective and the first account at least one by degree characteristic information Account attribute under individual target dimension；Obtain the information at least mated with objective to include: obtain and objective and account The first information of attributes match.

Processor 401 is additionally operable to perform to operate as follows: the geographical position cluster in geographic position data sequence is obtained mesh Mark place includes: by geographic position data sequence mapping to isomorphism vector space；Geographical position according at least two data source Put the weight of each data source in data sequence by geographic position data sequence mapping to the time shaft of isomorphism vector space；Carry Take the geographical position meeting objective attribute target attribute as objective, and the account attribute of the first account objective；Obtain at least The information mated with objective includes: obtain the second information with objective and account attributes match.

Processor 401 is additionally operable to perform to operate as follows: according to every in the geographic position data sequence of at least two data source Geographic position data sequence mapping is included on the time shaft of isomorphism vector space by the weight of individual data source: to each data source Carry out the data accumulation of same geographic location on a timeline.

Processor 401 is additionally operable to perform to operate as follows: the geographical position cluster in geographic position data sequence is obtained mesh Mark place includes: identify each column vector in multidimensional data matrix；Include the dimension in effective geographical position according to each column vector, will Multidimensional data matrix-split is positioning data block and the multidimensional positioning data block of alternative splicing, and wherein, multidimensional data matrix includes At least two geographic position data sequence, positioning data block include having the continuation column in effective geographical position of a dimension to Amount, multidimensional positioning data block includes the continuation column vector with effective geographical position of at least two dimension.

Embodiments of the invention additionally provide a kind of storage medium.Alternatively, in the present embodiment, above-mentioned storage medium can For storing the program code of the method for pushing of the information of the embodiment of the present invention.

Alternatively, in the present embodiment, above-mentioned storage medium may be located at mobile communications network, wide area network, Metropolitan Area Network (MAN) or At least one network equipment in multiple network equipments in the network of LAN.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps:

S1, obtains the geographic position data sequence of the first account, and wherein, geographic position data sequence includes that the first account exists Geographical position residing for different time；

Geographical position cluster in geographic position data sequence is obtained objective by S2.

S3, obtains the information at least mated with objective.

Information pushing is given the first account by S4.

Alternatively, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk, read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), portable hard drive, magnetic disc or The various medium that can store program code such as CD.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: will Geographical position cluster in geographic position data sequence obtains objective and includes: obtain the dimensional characteristics information in geographical position, Wherein, the corresponding one or more dimensions in each geographical position, each dimension has one or more dimensional characteristics information；According to one The dimensional characteristics information under at least one target dimension in individual or multiple dimension, by the geographical position in geographic position data sequence Put cluster and obtain objective and the first account account attribute under at least one target dimension；Obtain at least with target ground The information of Point matching includes: obtain the first information with objective and account attributes match.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: will Geographical position cluster in geographic position data sequence obtains objective and includes: by geographic position data sequence mapping to isomorphism In vector space；According to the weight of each data source in the geographic position data sequence of at least two data source by geographical position number According on sequence mapping to the time shaft of isomorphism vector space；Extract and meet the geographical position of objective attribute target attribute as objective, with And the first account attribute of account objective；Obtain the information at least mated with objective to include: obtain and objective The second information with account attributes match.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: press Geographic position data sequence mapping is arrived by the weight according to each data source in the geographic position data sequence of at least two data source Include on the time shaft of isomorphism vector space: carry out the data accumulation of same geographic location on a timeline to each data source.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: will Geographical position cluster in geographic position data sequence obtains objective and includes: identify each row in multidimensional data matrix to Amount；Include the dimension in effective geographical position according to each column vector, by the positioning data that multidimensional data matrix-split is alternative splicing Block and multidimensional positioning data block, wherein, multidimensional data matrix includes at least two geographic position data sequence, positions data block bag Including the continuation column vector in effective geographical position with a dimension, multidimensional positioning data block includes having at least two dimension The continuation column vector in effective geographical position.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: After the geographical position cluster in geographic position data sequence, method also includes: to the geographic position data sequence after cluster Add time attribute, obtain geographical position time series；To the geographical position in the time series of geographical position and geographical position The corresponding time carries out semantic classes classification from least one dimension, obtains each geographical position pair in the time series of geographical position Answer the static geographical attribute of at least one dimension.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: After the geographical position cluster in geographic position data sequence, method also includes: extract the from the time series of geographical position The migration subsequence of one account movement between diverse geographic location；According to the mobile geography migrating subsequence drafting the first account Track.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: After the geographical position cluster in geographic position data sequence, method also includes: meet pre-conditioned moving by the frequency of occurrences Move subsequence and build space-time migration series, and using space-time migration series as the Dynamic Geographic attribute of the first account.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: obtain Take the information at least mated with objective and include one below: obtain with objective and with objective letter of corresponding time Second information of breath coupling；Obtain the 3rd information mated with the target resource characteristic information indicated by objective.

Alternatively, in the present embodiment, storage medium is arranged to storage for performing the program code of following steps: In the case of obtaining the second information mated with objective and temporal information corresponding with objective, by information pushing to the One account includes: reach and/or when detecting that the first account is positioned at objective in the time indicated by temporal information, by the Two information pushings give the first account.

The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.

If the integrated unit in above-described embodiment realizes and as independent product using the form of SFU software functional unit When selling or use, can be stored in the storage medium that above computer can read.Based on such understanding, the skill of the present invention Part that prior art is contributed by art scheme substantially in other words or this technical scheme completely or partially can be with soft The form of part product embodies, and this computer software product is stored in storage medium, including some instructions are with so that one Platform or multiple stage computer equipment (can be personal computer, server or the network equipment etc.) perform each embodiment institute of the present invention State all or part of step of method.

In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not has in certain embodiment The part describing in detail, may refer to the associated description of other embodiments.

In several embodiments provided herein, it should be understood that disclosed client, can be by other side Formula realizes.Wherein, device embodiment described above is only schematically, the division of for example described unit, and only one Kind of logic function divides, actual can have when realizing other dividing mode, for example multiple unit or assembly can in conjunction with or It is desirably integrated into another system, or some features can be ignored, or do not perform.Another point, shown or discussed mutual it Between coupling direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING of unit or module or communication link Connect, can be electrical or other form.

The described unit illustrating as separating component can be or may not be physically separate, shows as unit The parts showing can be or may not be physical location, i.e. may be located at a place, or also can be distributed to multiple On NE.Some or all of unit therein can be selected according to the actual needs to realize the mesh of the present embodiment scheme 's.

In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it is also possible to It is that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.Above-mentioned integrated list Unit both can use the form of hardware to realize, it would however also be possible to employ the form of SFU software functional unit realizes.

The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For Yuan, under the premise without departing from the principles of the invention, can also make some improvements and modifications, these improvements and modifications also should It is considered as protection scope of the present invention.

Claims

1. the method for pushing of an information, it is characterised in that include:

Obtaining the geographic position data sequence of the first account, wherein, described geographic position data sequence includes described first account In the geographical position residing for different time；

Geographical position cluster in described geographic position data sequence is obtained objective；

Obtain the information at least mated with described objective；

Give described first account by described information pushing.

2. method according to claim 1, it is characterised in that

The described geographical position cluster by described geographic position data sequence obtains objective and includes: obtain described geographical position The dimensional characteristics information put, wherein, the corresponding one or more dimensions in each described geographical position, each dimension has one or many Individual dimensional characteristics information；According to the dimensional characteristics information under at least one target dimension in the one or more dimension, will In described geographic position data sequence geographical position cluster obtain described objective and described first account described extremely Account attribute under a few target dimension；

Obtain the information at least mated with described objective to include: obtain and described objective and described account attributes match The first information.

3. method according to claim 1, it is characterised in that

The described geographical position cluster by described geographic position data sequence obtains objective and includes: by described geographical position Data sequence is mapped in isomorphism vector space；According to number every in the described geographic position data sequence of at least two data source According to the weight in source by described geographic position data sequence mapping to the time shaft of described isomorphism vector space；Extraction meets target The geographical position of attribute is as described objective, and the account attribute of objective described in described first account；

Obtain the information at least mated with described objective to include: obtain and described objective and described account attributes match The second information.

4. method according to claim 3, it is characterised in that according to the described geographic position data of at least two data source In sequence, the weight of each data source is by described geographic position data sequence mapping to the time shaft of described isomorphism vector space Including:

Carry out the data accumulation of same geographic location to each data source on the time axis.

5. method according to claim 1, it is characterised in that described by the geographical position in described geographic position data sequence Put cluster to obtain objective and include:

Identify each column vector in multidimensional data matrix；

Include the dimension in effective geographical position according to each described column vector, be alternative splicing by described multidimensional data matrix-split Positioning data block and multidimensional positioning data block, wherein, described multidimensional data matrix includes geographic position data described at least two Sequence, described positioning data block includes the continuation column vector with effective geographical position of a dimension, and described multidimensional positions number Include the continuation column vector with effective geographical position of at least two dimension according to block.

6. method according to claim 1, it is characterised in that by the geographical position in described geographic position data sequence After cluster, described method also includes:

Time attribute is added to the geographic position data sequence after cluster, obtains geographical position time series；

Geographical position in the time series of described geographical position and geographical position corresponding time are entered from least one dimension Lang justice category classification, obtains at least one dimension corresponding of each geographical position in the time series of described geographical position statically Reason attribute.

7. method according to claim 6, it is characterised in that by the geographical position in described geographic position data sequence After cluster, described method also includes:

Described first account sub-sequence of the migration of movement between diverse geographic location is extracted from the time series of described geographical position Row；

Draw the mobile geographical track of described first account according to described migration subsequence.

8. method according to claim 7, it is characterised in that by the geographical position in described geographic position data sequence After cluster, described method also includes:

Meet pre-conditioned described migration subsequence by the frequency of occurrences and build space-time migration series, and described space-time is migrated sequence Row are as the Dynamic Geographic attribute of described first account.

9. method according to claim 1, it is characterised in that obtain the information at least mated with described objective and include One below:

Obtain the second information mated with described objective and temporal information corresponding with described objective；

Obtain the 3rd information mated with the target resource characteristic information indicated by described objective.

10. method according to claim 9, it is characterised in that obtain with described objective and with described target ground In the case of second information of point corresponding temporal information coupling, described include described information pushing to described first account:

When the time indicated by described temporal information reaches and/or detects that described first account is positioned at described objective, Give described first account by described second information pushing.

11. methods according to claim 9, it is characterised in that obtain and the target resource indicated by described objective 3rd information of characteristic information coupling includes:

Obtain described objective place target area and with described target area corresponding target resource characteristic information, its In, the corresponding different resource characteristic information of the zones of different including described target area, described resource characteristic information is used for The hierarchical resource that account in region corresponding with described resource characteristic information for the instruction is had；

Obtain described 3rd information mated with described target resource characteristic information.

12. methods according to claim 11, it is characterised in that obtaining and the target money indicated by described objective In the case of second information of source characteristic information coupling, described described information pushing is given described first account include following it One:

After getting described 3rd information, give described first account by described 3rd information pushing；

When the target area that described first account is positioned at described objective place being detected, described 3rd information pushing is given Described first account.

The pusher of 13. 1 kinds of information, it is characterised in that include:

First acquiring unit, for obtaining the geographic position data sequence of the first account, wherein, described geographic position data sequence Including described first account is in the geographical position residing for different time；

Cluster cell, for obtaining objective by the geographical position cluster in described geographic position data sequence；

Second acquisition unit, for obtaining the information at least mated with described objective；

Push unit, for giving described first account by described information pushing.

14. devices according to claim 13, it is characterised in that

Described cluster cell includes: the first acquisition module, for obtaining the dimensional characteristics information in described geographical position, wherein, often The corresponding one or more dimensions in individual described geographical position, each dimension has one or more dimensional characteristics information；Cluster module, For according to the dimensional characteristics information under at least one target dimension in the one or more dimension, by described geographical position Geographical position cluster in data sequence obtains described objective and described first account is tieed up at least one target described Account attribute under Du；

Described second acquisition unit is additionally operable to obtain the first information with described objective and described account attributes match.

15. devices according to claim 13, it is characterised in that

Described cluster cell includes: the first mapping block, for by described geographic position data sequence mapping to isomorphism vector sky In between；Second mapping block, for according to each data source in the described geographic position data sequence of at least two data source Weight is by described geographic position data sequence mapping to the time shaft of described isomorphism vector space；Extraction module, is used for extracting Meet the geographical position of objective attribute target attribute as described objective, and the account of objective described in described first account belongs to Property；

Described second acquisition unit is additionally operable to obtain the second information with described objective and described account attributes match.

16. devices according to claim 15, it is characterised in that described second mapping block includes:

Cumulative submodule, for carrying out the data accumulation of same geographic location on the time axis to each data source.

17. devices according to claim 13, it is characterised in that described cluster cell includes

Identification module, for identifying each column vector in multidimensional data matrix；

Split module, for including the dimension in effective geographical position according to each described column vector, described multidimensional data matrix is torn open Being divided into positioning data block and the multidimensional positioning data block of alternative splicing, wherein, described multidimensional data matrix includes at least two institute Stating geographic position data sequence, described positioning data block includes the continuation column vector with effective geographical position of a dimension, Described multidimensional positioning data block includes the continuation column vector with effective geographical position of at least two dimension.

18. devices according to claim 13, it is characterised in that described device also includes:

Time attribute unit, for after by the geographical position cluster in described geographic position data sequence, after cluster Geographic position data sequence adds time attribute, obtains geographical position time series；

Taxon, for the geographical position in the time series of described geographical position and geographical position corresponding time from At least one dimension carries out semantic classes classification, obtains each geographical position correspondence at least one in the time series of described geographical position The static geographical attribute of individual dimension.

19. devices according to claim 18, it is characterised in that described device also includes:

Migration series unit, for after by the geographical position cluster in described geographic position data sequence, from described geography Position time series is extracted the migration subsequence of described first account movement between diverse geographic location；

Drawing unit, for drawing the mobile geographical track of described first account according to described migration subsequence.

20. devices according to claim 19, it is characterised in that described device also includes:

Construction unit is for after by the geographical position cluster in described geographic position data sequence, full by the frequency of occurrences The pre-conditioned described migration subsequence of foot builds space-time migration series, and using described space-time migration series as described first account Dynamic Geographic attribute.

21. devices according to claim 13, it is characterised in that described second acquisition unit for obtain at least with described The information of objective coupling includes one below:

22. devices according to claim 21, it is characterised in that described push unit includes:

First pushing module, for mate with described objective and temporal information corresponding with described objective in acquisition In the case of second information, reach in the time indicated by described temporal information and/or detect that described first account is positioned at institute When stating objective, give described first account by described second information pushing.

23. devices according to claim 21, it is characterised in that described second acquisition unit includes:

First acquisition module, for obtain described objective place target area and with described target area corresponding mesh Mark resource characteristic information, wherein, the corresponding different resource characteristic information of zones of different including described target area, described Resource characteristic information is for indicating the hierarchical resource that the account in region corresponding with described resource characteristic information is had；

Second acquisition module, for obtaining described 3rd information mated with described target resource characteristic information.