CN105610929A

CN105610929A - Personalized data pushing method and device

Info

Publication number: CN105610929A
Application number: CN201510993024.6A
Authority: CN
Inventors: 周楠; 常富洋; 李强
Original assignee: Beijing Qihoo Technology Co Ltd; Qizhi Software Beijing Co Ltd
Current assignee: Beijing Qihoo Technology Co Ltd; Qizhi Software Beijing Co Ltd
Priority date: 2015-12-24
Filing date: 2015-12-24
Publication date: 2016-05-25

Abstract

The embodiment of the invention provides a personalized data pushing method and a personalized data pushing device. The method comprises the steps of receiving user data sent by a client; adopting the user data to generate the personalized feature information of the user; and pushing data to the client according to the personalized feature information of the user. According to the personalized data pushing method and device provided by the embodiment of the invention, the data pushing efficiency is improved, the user experience is optimized, and the more intelligent automated interaction process is achieved.

Description

A kind of data push method of personalization and device

Technical field

The present invention relates to technical field of computer information processing, particularly relate to a kind of number of personalizationAccording to the data-pushing device of method for pushing and a kind of personalization.

Background technology

Information is carried out to intelligent processing method, is an important topic of current computer technology. At presentThe most representatively be applied in various mobile terminals and embodied with the service technology field of being combined, high in the clouds,High in the clouds utilizes large data to realize data mining, and mobile terminal can be realized the number of these large dataAccording to the profound level application of data after gathering and excavating.

Typically apply about the one of intelligent processing method technology, be the personalisation process to information,Can go out the customized information for Internet user based on large data mining in the industry, formulate for thisUser's Personalized Ways, thereby, the intelligent degree of raising information process-.

Specific to mobile terminal application, mobile terminal is generally held by a user, makesUser is by downloading the application program corresponding with cloud server next with its user account loginSet up and contact with cloud server, cloud server just can come by its corresponding application program realNow be associated with the information gathering of such user account, thereby utilize this data of magnanimity to realize numberAccording to excavation, the final customized information forming corresponding to each user account.

For example, but mostly current multiple similar techniques, be to carry out for user's networking activity,In the time of connecting Internet, directly for user pushes default information, and user is on mobile terminalActivity is obviously not limited to above-mentioned scope, and not necessarily available free time browsing information of user, thereby,Can find out, the intelligent processing method technology providing for mobile terminal in prior art has limitation,The effect of the effective personalized recommendation of more difficult realization.

Further, consider for the angle of the information security of broad sense, user expects to obtain one sometimesThe information a little and self-demand is more proper, information in addition all can be considered harassing and wrecking, should giveWith interception, obviously, meeting of this demand, also needs to depend on accurate and intelligent personalization placeReason technology.

In view of the problem of above-mentioned existence, can find out, this area correlation technique still has the space of lifting.

Summary of the invention

In view of the above problems, the present invention has been proposed to provide one to overcome the problems referred to above or at leastThe personalized data push method partly addressing the above problem and corresponding personalized data push awaySend device.

According to one aspect of the present invention, a kind of data push method of personalization is provided, comprising:

Receive the user data that client sends;

Adopt described user data to generate user individual characteristic information;

Be described client push data according to described user individual characteristic information.

Alternatively, described user data has corresponding ID, and described employing user data is rawBecome the step of user individual characteristic information to comprise:

Obtain at the appointed time the user data in section; Described user data comprise user click shouldWith the time;

Adopt described user to click Applicative time counting user and click the highest click time of applying frequencySection;

Using described click time period and described ID as user individual characteristic information.

Alternatively, the step of described employing user data generation user individual characteristic information comprises:

Obtain at the appointed time the user data in section; Described user data comprise user click shouldWith place;

The place counting user that adopts described user to click application is clicked the click ground that applying frequency is the highestDistrict;

Using described click area and described ID as user individual characteristic information.

Obtain at the appointed time the user data in section; Described user data comprise user click shouldWith label;

The label counting user that adopts described user to click application is clicked the highest label of applying frequency;

Using described label and described ID as user individual characteristic information.

According to described ID, obtain at the appointed time the user data in section;

Adopt described user data counting user to click the total amount of data of application; It is right that described application hasThe label of answering;

Adopt described user data counting user to click the data volume for the application of same label;

Adopt described data volume and described total amount of data to calculate for the described application for same labelFirst user is clicked probable value;

Adopting described first user to click probable value calculates for the of the described application for same labelThe one historical probable value of clicking;

Descending the described first historical click probable value sequence determined to click probability is the highestLabel;

Using label the highest described click probability as user individual characteristic information.

According to described ID, obtain at the appointed time the user data in section; Described number of usersAccording to comprising that user clicks the place of application, described application has corresponding label;

The place statistics user in default area who adopts described user to click application clicks as identical markThe data volume of the application of signing;

The place statistics user in described default area who adopts described user to click application clicks applicationTotal amount of data;

The second user who adopts described data volume and described total amount of data to calculate in default area clicksProbable value;

Adopting described the second user to click probable value calculates for the of the described application for same labelThe two historical probable values of clicking;

The descending acquisition of sorting of the described second historical click probable value is clicked to probability the highestClick area;

Using click area the highest described click probability as user individual characteristic information.

Alternatively, described is the step of described client push data according to user individual characteristic informationSuddenly comprise:

Receive the propelling movement inquiry request that described client is submitted to; Described propelling movement inquiry request comprises userRespective user mark, current time and/or current place;

Search the user individual characteristic information mating with described ID;

Adopt described current time and/or current place, and described user individual characteristic information is trueWhether fixed is described client push data;

If be defined as to described client push data, be that described client push is preset to be recommendedData.

Alternatively, described employing current time and/or current place, and described user individual spyThe step that reference breath is described client push data comprises:

Determine the whether click time period in described user individual characteristic information of described current timeIn;

If so, be defined as to described client push data;

And/or,

Determine the whether click area in described user individual characteristic information, described current placeIn;

If so, be defined as to described client push data.

Alternatively, described preset data to be recommended have corresponding label, and described is client pushThe step of preset data to be recommended comprises:

Determine whether label corresponding to described preset data to be recommended is believed with described user individual featureLabel in breath is consistent;

If so, to preset data to be recommended described in described client push.

Receive the propelling movement inquiry request that described client is submitted to;

Judge label corresponding to described data to be recommended, whether in described user individual characteristic informationClick the label that probability is the highest consistent;

If so, to described client push data to be recommended.

Receive the propelling movement inquiry request that described client is submitted to; Described propelling movement inquiry request comprises currentPlace;

Judge that whether described current place is the highest at the click probability of described user individual characteristic informationClick area;

If so, to described client push data to be recommended.

Alternatively, described be described client push data according to user individual characteristic informationBefore step, also comprise:

Obtain the recommendation record of data to be recommended;

Adopt the recommendation record of described data to be recommended to determine whether to need according to described user individualCharacteristic information is described client push data.

According to a further aspect in the invention, provide a kind of data-pushing device of personalization, having comprised:

User data receiver module, is suitable for receiving the user data that client sends;

User individual characteristic information generation module, is suitable for adopting described user data to generate userProperty characteristic information;

Client data pushing module, being suitable for according to described user individual characteristic information is described visitorFamily end propelling data.

Alternatively, described user data has corresponding ID, described user individual featureInformation generating module comprises:

First user data acquisition submodule, is suitable for obtaining at the appointed time the user data in section;Described user data comprises that user clicks Applicative time;

Click the highest time period of probability and determine submodule, be suitable for adopting described user to click Applicative timeCounting user is clicked the highest click time period of applying frequency;

First user individualized feature information is preserved submodule, is suitable for described click time period and instituteState ID as user individual characteristic information.

Alternatively, described user individual characteristic information generation module comprises:

The second user data obtains submodule, is suitable for obtaining at the appointed time the user data in section;Described user data comprises that user clicks the place of application;

Click probability and superlatively determine submodule in district, be suitable for adopting described user to click the place of applicationCounting user is clicked the highest click area of applying frequency;

The second user individual characteristic information is preserved submodule, be suitable for by described clicks area with described inID is as user individual characteristic information.

The 3rd user data obtains submodule, is suitable for obtaining at the appointed time the user data in section;Described user data comprises that user clicks the label of application;

First clicks probability the highest label determines submodule, is suitable for adopting described user to click applicationLabel counting user is clicked the highest label of applying frequency;

The 3rd user individual characteristic information is preserved submodule, is suitable for described label and described userMark is as user individual characteristic information.

Four-function user data is obtained submodule, is suitable for according to described ID, obtains in the time specifyingBetween section in user data;

User clicks the total amount of data statistics submodule of application, is suitable for adopting described user data statisticsUser clicks the total amount of data of application; Described application has corresponding label;

The data volume statistics submodule of the application of same label, is suitable for adopting described user data statisticsUser clicks the data volume for the application of same label;

First user is clicked probable value calculating sub module, is suitable for adopting described data volume and described sumCalculate for the first user of the described application that is same label and click probable value according to amount;

The first historical probable value calculating sub module of clicking, is suitable for adopting described first user to click probabilityValue is calculated the first historical probable value of clicking for the described application that is same label;

Second clicks the highest label of probability determines submodule, is suitable for the described first historical click generallyThe descending sequence of rate value determined the highest label of click probability;

Four-function family individualized feature information is preserved submodule, is suitable for the highest described click probabilityLabel is as user individual characteristic information.

The 5th user data obtains submodule, is suitable for according to described ID, obtains in the time specifyingBetween section in user data; Described user data comprises that user clicks the place of application, described applicationThere is corresponding label;

The total amount of data statistics submodule of clicking application in area, being suitable for adopting described user to click shouldWith the user's click in default area of place statistics be the data volume of the application of same label;

In area, user clicks the total amount of data statistics submodule of application, is suitable for adopting described user's pointThe place statistics user in described default area who hits application clicks the total amount of data of application;

The second user clicks probable value calculating sub module, is suitable for adopting described data volume and described sumThe second user who calculates in default area according to amount clicks probable value;

The second historical probable value calculating sub module of clicking, is suitable for adopting described the second user to click probabilityValue is calculated the second historical probable value of clicking for the described application that is same label;

Click the click area that probability is the highest and determine submodule, be suitable for general the described second historical clickThe descending sequence of rate value obtains the click the highest click area of probability;

The 5th user individual characteristic information is preserved submodule, is suitable for the highest described click probabilityClick area as user individual characteristic information.

Alternatively, described client data pushing module comprises:

First pushes inquiry request receiving submodule, is suitable for receiving the propelling movement inquiry that described client is submitted toAsk request; Described propelling movement inquiry request comprises user's respective user mark, current time and/or currentPlace;

First user individualized feature information searching submodule, is suitable for searching and described IDThe user individual characteristic information of joining;

Client push data judging submodule, is suitable for adopting described current time and/or current place,And described user individual characteristic information determines whether as described client push data;

Preset data-pushing submodule to be recommended, is defined as if be suitable for to described client push data,Be the preset data to be recommended of described client push.

Alternatively, described client push data judging submodule comprises:

Click determining unit in the time period, be suitable for determining that whether described current time is described userIn the click time period in property characteristic information; If so, call the first client push data sheetUnit;

The first client push data cell, is suitable for being defined as to described client push data;

And/or,

Click determining unit in area, be suitable for determining that whether described current place is at described user personalityChange in the click area in characteristic information; If so, call the second client push data cell;

The second client push data cell, is suitable for being defined as to described client push data.

Alternatively, described preset data to be recommended have corresponding label, described preset number to be recommendedComprise according to pushing submodule:

Label uniformity determining unit, is suitable for determining that label corresponding to described preset data to be recommended isLabel in no and described user individual characteristic information is consistent; If so, call preset to be recommendedData-pushing unit;

Preset data-pushing to be recommended unit, is suitable for to preset to be recommended described in described client pushData.

Alternatively, described client data pushing module comprises:

Second pushes inquiry request receiving submodule, is suitable for receiving the propelling movement inquiry that described client is submitted toAsk request;

Click the highest label uniformity of probability and judge submodule, be suitable for judging described data to be recommendedWhether corresponding label, click the label that probability is the highest in described user individual characteristic information consistent;If so, call the first data-pushing submodule to be recommended;

The first data-pushing submodule to be recommended, is suitable for to described client push data to be recommended.

Alternatively, described client data pushing module comprises:

The 3rd pushes inquiry request receiving submodule, is suitable for receiving the propelling movement inquiry that described client is submitted toAsk request; Described propelling movement inquiry request comprises current place;

Click the highest regional uniformity of probability and judge submodule, be suitable for judging that described current place isNo in the highest click area of the click probability of described user individual characteristic information; If so, adjustWith the second data-pushing submodule to be recommended;

The second data-pushing submodule to be recommended, is suitable for to described client push data to be recommended.

Alternatively, also comprise:

Recommendation record acquisition module, is suitable for obtaining the recommendation record of data to be recommended;

Propelling data determination module, is suitable for adopting the recommendation record of described data to be recommended to determine whetherNeeding according to described user individual characteristic information is described client push data.

According to the data push method of a kind of personalization of the present invention and device, the embodiment of the present invention is logicalCross in the client using user and to gather the number of users that can reflect and embody user's use habitAccording to, and obtain user individual characteristic information for user data analysis, with thinking that user pushes awayRecommend data. Preferably, the embodiment of the present invention can be the behavior for user's individuality, can be alsoFor colony's user behavior, can obtain user individual characteristic information for certain user, alsoCan obtain user individual characteristic information for the user of colony, then in the time being user's recommending data,Can first adopt and carry out data for certain user's user individual characteristic information for user and push awaySend, carry out data for user and push away when not obtaining user individual characteristic information for certain userWhile sending, can also further adopt user individual characteristic information for the user of colony for userCarry out data-pushing, improved the pushing efficiency of data, optimizing user is experienced, and realizes more intelligentAutomation interaction.

Above-mentioned explanation is only the general introduction of technical solution of the present invention, in order to better understand the present inventionTechnological means, and can be implemented according to the content of description, and for allow of the present invention onState with other objects, features and advantages and can become apparent, below especially exemplified by concrete reality of the present inventionExecute mode.

Brief description of the drawings

By reading below detailed description of the preferred embodiment, various other advantage and benefit forIt is cheer and bright that those of ordinary skill in the art will become. Accompanying drawing is only for illustrating preferred embodimentObject, and do not think limitation of the present invention. And in whole accompanying drawing, by identical ginsengExamine symbol and represent identical parts. In the accompanying drawings:

Fig. 1 shows a kind of individual character of one embodiment of the invention according to an embodiment of the inventionThe flow chart of steps of the data push method embodiment mono-changing;

Fig. 2 shows a kind of individual character of one embodiment of the invention according to an embodiment of the inventionThe flow chart of steps of the data push method embodiment bis-changing; And

Fig. 3 shows a kind of individual character of one embodiment of the invention according to an embodiment of the inventionThe structured flowchart of the data-pushing device embodiment changing.

Detailed description of the invention

Exemplary embodiment of the present disclosure is described below with reference to accompanying drawings in more detail. Although in accompanying drawingShow exemplary embodiment of the present disclosure, but should be appreciated that and can realize this with various formsEmbodiment open and that should do not set forth here limits. On the contrary, provide these embodiment be forCan more thoroughly understand the disclosure, and can be by the ability that conveys to complete the scope of the present disclosureThe technical staff in territory.

With reference to Fig. 1, show a kind of data-pushing side of personalization according to an embodiment of the inventionThe flow chart of steps of method embodiment mono-, specifically can comprise the steps:

Step 101, receives the user data that client sends;

In embodiments of the present invention, the client of mobile terminal includes multiple personal information, whereinComparatively frequently producing, and can reflect personal characteristic information, is user carrying out in social processThe data that produce. User, by the click for the various application on mobile terminal, has represented conventionallyCertain demand of user or certain wish, thereby, be enough to embody user such as free time,Or idle place, and the personal characteristic information such as data of liking because this several typesPeople's characteristic information, in theory, in other words to a certain extent, is the mark of user's character trait,By acting in user's behavioural habits, be finally reflected in these user data.

In the embodiment of the present invention, user data gather approach, be by user at mobile terminalThe third party application of upper installation carries out Analysis deterrmination. For example,, in the installation of mobile terminalSuch as mobile phone assistant, mobile phone bodyguard etc. By the third party application of installing on mobile terminal,Can collect user on mobile terminal, for the click information of application, can be also user's numberAccording to propelling movement.

Because mobile terminal is generally thin-client type, about the life of user individual characteristic informationOne-tenth technology is server realization beyond the clouds conventionally, thereby, in the embodiment of the present invention, can be by long-rangeInterface is submitted user data to cloud server, and follow-up described cloud server just can be given birth to according to thisBecome user individual characteristic information.

Step 102, adopts described user data to generate user individual characteristic information;

Preferably, the embodiment of the present invention can be a user personality for the behavior of user's individualityChange characteristic information and generate, particularly, raw for the user individual characteristic information of the behavior with individualOne-tenth process can comprise several as follows, can be respectively for time, place, and for user,Wherein, can adopt ID to carry out unique identification user.

In a preferred embodiment of the present invention, described user data has corresponding ID,Described step 102 can comprise following sub-step:

Sub-step S11, obtains at the appointed time the user data in section; Described user data comprisesUser clicks Applicative time;

Sub-step S12, adopts described user to click Applicative time counting user click applying frequency the highestThe click time period;

Sub-step S13, using described click time period and described ID as user individual featureInformation.

In a preferred embodiment of the present invention, described step 102 can comprise following sub-step:

Sub-step S21, obtains at the appointed time the user data in section; Described user data comprisesUser clicks the place of application;

Sub-step S22, the place counting user that adopts described user to click application is clicked applying frequencyHigh click area;

Sub-step S23, believes described click area and described ID as user individual featureBreath.

In embodiments of the present invention, server end is analyzed the user data that client is submitted to, according to useMost possible time and/or the area of checking PUSH message clicked of user data counting user.

Specifically, statistics is section at the appointed time, such as the user data in every day, calculatesIt is the highest which time period user of a day clicks applying frequency, and, at which area, Yong HudianHit applying frequency the highest, can be defined as to user these time periods and expect to its propelling dataExpected time, and, expect place.

Preferably, can also calculate in the last week in the embodiment of the present invention, user is point when and whereThe number of times that hits PUSH message is maximum, this time this ground be the phase that message is checked by user in clientPrestige time and expectation place.

By and this user is clicked to the area that applying frequency is the highest, and user clicks applying frequencyThe highest time period, also has ID as one of user individual characteristic information.

Sub-step S31, obtains at the appointed time the user data in section; Described user data comprisesUser clicks the label of application;

Sub-step S32, the label counting user that adopts described user to click application is clicked applying frequencyHigh label;

Sub-step S33, using described label and described ID as user individual characteristic information.

In specific implementation, the application on each mobile terminal has corresponding label (Tag),As: physical culture, news, call a taxi, take out etc., first capture the Tag of each application, to what captureTag arranges, classifies; Obtain the application message of installing on mobile terminal, according to application institute is installedThe Tag type statistics recurrence user's who belongs to Tag. Wherein, for making user's Tag more accurate, also canFrequency of usage in conjunction with application is simplified user's Tag, as: frequency of usage is 1 timeSoftware, its Tag can be not as user's Tag, without being not counted in statistics.

In a kind of preferred exemplary of the present invention, can add up some day user click applying frequencyThe highest label, and using this label and ID as one of user individual characteristic information.

Step 103 is described client push data according to described user individual characteristic information.

In a preferred embodiment of the present invention, described step 103 can comprise following sub-step:

Sub-step S41, receives the propelling movement inquiry request that described client is submitted to; Described propelling movement inquiry pleaseAsk and comprise user's respective user mark, current time and/or current place;

Sub-step S42, searches the user individual characteristic information mating with described ID;

Sub-step S43, adopts described current time and/or current place, and described user personalityChanging characteristic information determines whether as described client push data;

Sub-step S44, if be defined as to described client push data, is described client pushPreset data to be recommended.

In embodiments of the present invention, on mobile terminal, can be provided with push application, when needs toWhen user's propelling data, can be via pushing application to user's propelling data. Wherein, push applicationCan be mobile phone assistant or mobile phone bodyguard.

In a preferred embodiment of the present invention, described sub-step S43 can comprise following sub-stepRapid:

Sub-step S43-1, determines that described current time is whether in described user individual characteristic informationThe click time period in; If so, carry out sub-step S43-2;

Sub-step S43-2, is defined as to described client push data;

And/or,

Sub-step S43-3, determines that described current place is whether in described user individual characteristic informationClick area in; If so, carry out sub-step S43-4;

Sub-step S43-4, is defined as to described client push data.

In user individual characteristic information in embodiments of the present invention, collect and have user to expect to itThe expected time of propelling data and/or expectation place, please if receive client transmission propelling movement inquiryCurrent time in asking and/or current place all meet, or part meets user individual spyExpected time in reference breath and/or expectation place, just can be defined as user and push preset to be recommendedData.

In a preferred embodiment of the present invention, described sub-step S44 can comprise following sub-stepRapid:

Sub-step S44-1, determine label corresponding to described preset data to be recommended whether with described userLabel in individualized feature information is consistent; If so, carry out sub-step S44-2;

Sub-step S44-2, to preset data to be recommended described in described client push.

In a kind of preferred exemplary of the present invention, in the time being defined as user and pushing data to be recommended, alsoCan further determine the corresponding label of data to be recommended, whether with user individual characteristic informationIn label consistent, if so, specifier share the demand at family, can push in advance to this userPut data to be recommended, otherwise, do not push preset data to be recommended to this user.

With reference to Fig. 2, show a kind of data-pushing side of personalization according to an embodiment of the inventionThe flow chart of steps of method embodiment bis-, specifically can comprise the steps:

Step 201, receives the user data that client sends;

Step 202, adopts described user data to generate user individual characteristic information;

In a preferred embodiment of the present invention, described step 202 can comprise following sub-step:

Sub-step S51, according to described ID, obtains at the appointed time the user data in section;

Sub-step S52, adopts described user data counting user to click the total amount of data of application; DescribedApplication has corresponding label;

Sub-step S53, adopts described user data counting user to click the number for the application of same labelAccording to amount;

Sub-step S54, adopt described data volume and described total amount of data calculate for described be identical markThe first user of the application of signing is clicked probable value;

Sub-step S55, adopt described first user click probable value calculate for described be same labelThe first historical probable value of clicking of application;

Sub-step S56, determines click by descending sequence of the described first historical click probable valueThe label that probability is the highest;

Sub-step S57, using label the highest described click probability as user individual characteristic information.

In embodiments of the present invention, click frequency value specifically can be by calculating point in Preset Time sectionHit the number of users of label same application and result that total number of users amount is divided by and obtain, existed by serverIn Preset Time section, click the user of same label application according to the user data statistics of client uploadQuantity, and by the number of users of this click same label application of statistics and the total number of users amount of statisticsBe divided by, to obtain the click frequency value of user in Preset Time. Wherein, described Preset Time is passableBe set as 10 days or other times value, the embodiment of the present invention is not limited this.

Server end receives the user data that client sends, with the information based in this user data,Statistics is clicked the number of users of same label application. Wherein, the information in user data can compriseApply Names, No. ID, version number, application icon, user account information. Can based on Apply NamesThe application of clicking with unique definite user is for No. ID the identity mark that server end distributes for application in advanceKnow symbol, the application that can click for unique definite user. The version number of application is should in order to distinguishWith the clicking rate of different editions, determine with Apply Names or ID combination the application that user clicks.Application icon also can be used for the application that unique definite user clicks, and user account is for which is added upA little users have carried out clicking operation to application, if comprise new user, upgrade the total of user simultaneouslyQuantity.

The user data of server end based on receiving, real-time update is used for adding up described same labelThe history of application is clicked the relevant data value of probability data value, and wherein, described relevant data value comprisesIn Preset Time section, click number of users, the total number of users amount of same label application.

For example, the frequency of the click same label application to user in Preset Time section is repeatedly unitedMeter, wherein, described Preset Time section is identical, is 10 days or other times value of setting, as,Add up 20 within 10 day time user click the frequency values of same label application, obtain thus manyIndividual user clicks the click frequency value of same label application.

Calculate the mean value that the above-mentioned multiple users that obtain click the frequency values of same label application, shouldMean value is the described historical probable value of clicking. Those historical probable values of clicking are sorted, toolBody sorts with order from big to small. Wherein, history can be clicked to probability data value the highestLabel as one of user individual characteristic information.

In a preferred embodiment of the present invention, described user data has corresponding ID,Described step 202 can comprise following sub-step:

Sub-step S61, according to described ID, obtains at the appointed time the user data in section;Described user data comprises that user clicks the place of application, and described application has corresponding label;

Sub-step S62, adopts described user to click place statistics user's point in default area of applicationHit the data volume for the application of same label;

Sub-step S63, the place statistics that adopts described user to click application is used in described default areaThe total amount of data of application is clicked at family;

Sub-step S64, adopt described data volume and described total amount of data calculate in default area theTwo users click probable value;

Sub-step S65, adopts described the second user to click probable value and calculates for described as same labelThe second historical probable value of clicking of application;

Sub-step S66, obtains click by descending sequence of the described second historical click probable valueThe click area that probability is the highest;

Sub-step S67, believes click area the highest described click probability as user individual featureBreath.

In embodiments of the present invention, the area that statistical history click probable value is the highest is as user personalityChange one of characteristic information process, click label that probable value is the highest as user personality with statistical historyChange one of characteristic information similar process, just seldom repeated.

Step 203, obtains the recommendation record of data to be recommended;

Step 204, adopts the recommendation record of described data to be recommended to determine whether to need according to described useFamily individualized feature information is described client push data;

In embodiments of the present invention, be the data that user pushes, can comprise application recommendation interestedApplication is installed, commercial advertisement, red packet information, prize information, peripheral information etc. Use for improvingFamily is experienced, and can be optimized for the process of these user's propelling datas. Taking peripheral information as example,Definite peripheral information is sorted, be specially according to the feature of peripheral information and sort. SoAfter according to these order carry out the propelling movement of data for user.

Wherein, peripheral information can comprise recommended information, and further, peripheral information can also compriseAction message. Recommended information is the introduction to businessman, and action message is the prize drawing, excellent that businessman releasesThe activities such as favour certificate.

In the embodiment of the present invention, can be according to the feature of peripheral information further for it to user'sRecommendation process is optimized. Wherein, the feature of peripheral information comprises: peripheral information publisher's is excellentFirst level and peripheral information publisher, apart from the distance of mobile terminal, further, also can comprise action messageTemperature, manual intervention etc. Peripheral information publisher is sent out by peripheral information apart from the distance of mobile terminalCloth person's coordinate information and the coordinate information of mobile terminal calculate and obtain, and the temperature of action message is with excellentFavour certificate is example, comprises the granting degree of reward voucher and user's conversion ratio. Sortord comprises two kinds:Give corresponding weight to every in peripheral information feature, by calculating the comprehensive of each peripheral informationScoring is sorted; Taking businessman as example, server end also stores coordinate information and the phase of each businessmanThe peripheral information of answering. Peripheral information comprises recommended information, and further, peripheral information also can comprise workMoving information. Recommended information is the introduction to businessman, and action message is the prize drawing, preferential that businessman releasesThe activities such as certificate. Businessman described herein is the publisher of peripheral information.

In embodiments of the present invention, can be at server end construction strategy model, if number to be recommendedAccording to according to its recommendation record formerly determine do not need to push, can reduce for pushComputational process, avoids recommending useless information to user.

For the propelling movement of prize drawing information is example, server end is built with prize drawing Policy model, for screeningThe prize information that can push, comprises time period Policy model, region Policy model and prize-winning number of times planSlightly model. Wherein, the screening process of prize information is specially: when server end receives prize informationObtain after request, first time period Policy model judges that whether this request meets the prize drawing time, isNo within the prize drawing time period, if, region Policy model is according to the region in user personalized informationInformation judges the prize that this region can push, and the number of times Policy model of then getting the winning number in a bond is to pushing away of judgingSend prize further to screen, this screening comprises two kinds of situations, and one is can only for one dayIn prize once, if in prize drawing record, record today in mistake, do not push this prize information,Another kind is for the prize that only allows preset times in user, if record this prize in prize drawing record, cross preset times, do not push this prize information.

Step 205 is described client push data according to described user individual characteristic information.

In a preferred embodiment of the present invention, described step 205 can comprise following sub-step:

Sub-step S71, receives the propelling movement inquiry request that described client is submitted to;

Whether sub-step S72, judges label corresponding to described data to be recommended, described user individualIn characteristic information, click the label that probability is the highest consistent; If so, carry out sub-step S73;

Sub-step S73, to described client push data to be recommended.

Sub-step S81, receives the propelling movement inquiry request that described client is submitted to; Described propelling movement inquiry pleaseAsk and comprise current place;

Sub-step S82, judges that described current place is whether at the point of described user individual characteristic informationHit the click area that probability is the highest; If so, carry out sub-step S83;

Sub-step S83, to described client push data to be recommended.

In a kind of preferred exemplary of the present invention, for the process of user individual propelling data, canWith successively according to the step of following A, B:

If the focus time in the user individual characteristic information of A server end and/or focus groundPoint, mates with user's current time and/or current place, recommends preset data to be recommended to user;

If the focus time in the user individual characteristic information of B server end and/or focus groundPoint, does not mate with user's current time and/or current place, can be further according to current timeAnd/or carry out in popular time of user in current place and user individual characteristic information and/or placeCoupling, if there is occurrence, can be to user's recommending data.

In embodiments of the present invention, by gathering and can reflect also in the client using userEmbody the user data of user's use habit, and obtain user personality for user data analysisChange characteristic information, with thinking user's recommending data.

Preferably, the embodiment of the present invention can be the behavior for user's individuality, can be also forColony's user behavior, can obtain user individual characteristic information for certain user, also canObtain user individual characteristic information for the user of colony, then in the time being user's recommending data, canCarry out data for certain user's user individual characteristic information for user and push away first to adoptSend, carry out data for user and push away when not obtaining user individual characteristic information for certain userWhile sending, can also further adopt user individual characteristic information for the user of colony for userCarry out data-pushing, improved the pushing efficiency of data, optimizing user is experienced, and realizes more intelligentAutomation interaction.

For embodiment of the method, for simple description, therefore it is all expressed as to a series of action groupClose, but those skilled in the art should know, the embodiment of the present invention is not subject to described actionOrder restriction because according to the embodiment of the present invention, some step can adopt other order orCarry out simultaneously. Secondly, those skilled in the art also should know, the enforcement described in descriptionExample all belongs to preferred embodiment, and related action might not be that the embodiment of the present invention is necessary.

With reference to Fig. 3, show the data-pushing dress of a kind of personalization according to an embodiment of the inventionPut the structured flowchart of embodiment, specifically can comprise as lower module:

User data receiver module 301, is suitable for receiving the user data that client sends;

User individual characteristic information generation module 302, is suitable for adopting described user data to generate userIndividualized feature information;

Client data pushing module 303, is suitable for according to described in described user individual characteristic information isClient push data.

In a preferred embodiment of the present invention, described user data has corresponding ID,Described user individual characteristic information generation module comprises:

In a preferred embodiment of the present invention, described user individual characteristic information generation moduleComprise:

In a preferred embodiment of the present invention, described client data pushing module comprises:

In a preferred embodiment of the present invention, described client push data judging submodule bagDraw together:

And/or,

In a preferred embodiment of the present invention, described preset data to be recommended have corresponding markSign, described preset data-pushing submodule to be recommended comprises:

In a preferred embodiment of the present invention, also comprise:

For device embodiment, because it is substantially similar to embodiment of the method, so describeFairly simple, relevant part is referring to the part explanation of embodiment of the method.

The algorithm providing at this and not showing is established with any certain computer, virtual system or otherStandby intrinsic relevant. Various general-purpose systems also can with based on using together with this teaching. According to upperThe description of face, it is apparent constructing the desired structure of this type systematic. In addition, the present invention alsoNot for any certain programmed language. It should be understood that and can utilize various programming languages to realize at thisThe content of the present invention of describing, and the description of above language-specific being done is in order to disclose thisBright preferred forms.

In the description that provided herein, a large amount of details are described. But, can understand,Embodiments of the invention can be put into practice in the situation that there is no these details. In some instances,Be not shown specifically known method, structure and technology, so that not fuzzy understanding of this description.

Similarly, should be appreciated that in order to simplify the disclosure and to help and understand in each inventive aspectOne or more, in the above in the description of exemplary embodiment of the present invention, of the present invention eachFeature is grouped together into single embodiment, figure or sometimes in its description. But, andThe method of the disclosure should be construed to the following intention of reflection: i.e. the present invention for required protection requirementThan the more feature of feature of clearly recording in each claim. Or rather, as followsIt is such that claims of face reflect, inventive aspect is to be less than disclosed single enforcement aboveAll features of example. Therefore claims of, following detailed description of the invention are incorporated to thus clearlyThis detailed description of the invention, wherein each claim itself is as independent embodiment of the present invention.

Those skilled in the art are appreciated that and can enter the module in the equipment in embodimentRow adaptively changes and they is arranged on to the one or more equipment different from this embodimentIn. Module in embodiment or unit or assembly can be combined into a module or unit or assembly,And can put them in addition multiple submodules or subelement or sub-component. Except such spyLevy and/or process or unit at least some be, outside mutually repelling, can adopt any combinationTo disclosed all features in this description (comprising claim, summary and the accompanying drawing followed) withAnd all processes or the unit of disclosed any method like this or equipment combine. Unless in additionClearly statement, disclosed every in this description (comprising claim, summary and the accompanying drawing followed)Individual feature can be by providing identical, be equal to or the alternative features of similar object replaces.

In addition, although those skilled in the art will appreciate that embodiment bags more described hereinDraw together some feature instead of further feature included in other embodiment, but different embodimentThe combination of feature means within scope of the present invention and forms different embodiment. For example,In the following claims, the one of any of embodiment required for protection can be with arbitrarilyCombination use.

All parts embodiment of the present invention can realize with hardware, or with at one or moreThe software module of moving on processor realizes, or realizes with their combination. The technology of this areaPersonnel should be appreciated that and can use in practice microprocessor or digital signal processor (DSP)Realize according to the some or all portions in the personalized data push service of the embodiment of the present inventionThe some or all functions of part. The present invention can also be embodied as for carrying out side as described hereinThe equipment of part or all of method or device program (for example, computer program and computerProgram product). Realizing program of the present invention and can be stored on computer-readable medium like this, orPerson can have the form of one or more signal. Such signal can be from internet websiteDownload obtains, or provides on carrier signal, or provides with any other form.

It should be noted above-described embodiment the present invention will be described instead of the present invention is limitSystem, and those skilled in the art can design in the case of not departing from the scope of claimsGo out alternative embodiment. In the claims, should be by any reference symbol structure between bracketCause limitations on claims. Word " comprises " not to be got rid of existence and is not listed as in the claimsElement or step. Be positioned at word " " before element or " one " do not get rid of exist multiple thisThe element of sample. The present invention can be by means of including the hardware of some different elements and by means of suitableWhen the computer of programming is realized. In the unit claim of having enumerated some devices, these dressesSeveral in putting can be to carry out imbody by same hardware branch. Word first, second,And the use of C grade does not represent any order. Can be title by these word explanations.

The data push method that the embodiment of the invention discloses A1, a kind of personalization, comprising:

Receive the user data that client sends;

A2, method as described in claim A1, is characterized in that, it is right that described user data hasThe ID of answering, the step that described employing user data generates user individual characteristic information comprises:

A3, method as described in claim A1 or A2, is characterized in that described employing userThe step that data generate user individual characteristic information comprises:

A4, method as described in claim A1 or A2, is characterized in that described employing userThe step that data generate user individual characteristic information comprises:

A5, method as described in claim A1, is characterized in that, it is right that described user data hasThe ID of answering, the step that described employing user data generates user individual characteristic information comprises:

A6, method as described in claim A1 or A5, is characterized in that described user dataHave corresponding ID, described employing user data generates the step of user individual characteristic informationSuddenly comprise:

A7, method as described in claim A1 or A2 or A3, is characterized in that described complying withThe step that is described client push data according to user individual characteristic information comprises:

Search the user individual characteristic information mating with described ID;

A8, method as described in claim A1 or A2 or A3, is characterized in that, described in adoptWith current time and/or current place, and described user individual characteristic information is described clientThe step of propelling data comprises:

If so, be defined as to described client push data;

And/or,

If so, be defined as to described client push data.

A9, method as described in claim A7, is characterized in that described preset data to be recommendedHave corresponding label, the described step for the preset data to be recommended of client push comprises:

If so, to preset data to be recommended described in described client push.

A10, method as described in claim A1 or A5, is characterized in that, described according to usingFamily individualized feature information is that the step of described client push data comprises:

If so, to described client push data to be recommended.

A11, method as described in claim A1 or A6 or A10, is characterized in that, described inThe step that is described client push data according to user individual characteristic information comprises:

If so, to described client push data to be recommended.

A12, method as described in claim A1, is characterized in that, described according to userProperty characteristic information is before the step of described client push data, also comprises:

Obtain the recommendation record of data to be recommended;

The data-pushing device that the embodiment of the invention also discloses B13, a kind of personalization, comprising:

B14, device as described in claim B13, is characterized in that, described user data hasCorresponding ID, described user individual characteristic information generation module comprises:

B15, device as described in claim B13 or B14, is characterized in that described userIndividualized feature information generating module comprises:

B16, device as described in claim B13 or B14, is characterized in that described userIndividualized feature information generating module comprises:

B17, device as described in claim B13, is characterized in that, described user data hasCorresponding ID, described user individual characteristic information generation module comprises:

B18, device as described in claim B13 or B17, is characterized in that described userData have corresponding ID, and described user individual characteristic information generation module comprises:

B19, device as described in claim B13 or B14 or B15, is characterized in that instituteStating client data pushing module comprises:

B20, device as described in claim B13 or B14 or B15, is characterized in that instituteStating client push data judging submodule comprises:

And/or,

B21, device as described in claim B19, is characterized in that described preset number to be recommendedAccording to having corresponding label, described preset data-pushing submodule to be recommended comprises:

B22, device as described in claim B13 or B17, is characterized in that described clientEnd data pushing module comprises:

B23, device as described in claim B13 or B18 or B22, is characterized in that instituteStating client data pushing module comprises:

B24, device as described in claim B13, is characterized in that, also comprises:

Claims

1. a personalized data push method, comprising:

Receive the user data that client sends;

2. the method for claim 1, is characterized in that, described user data has correspondenceID, the step that described employing user data generates user individual characteristic information comprises:

3. method as claimed in claim 1 or 2, is characterized in that, described employing user dataThe step that generates user individual characteristic information comprises:

4. method as claimed in claim 1 or 2, is characterized in that, described employing user dataThe step that generates user individual characteristic information comprises:

5. the method for claim 1, is characterized in that, described user data has correspondenceID, the step that described employing user data generates user individual characteristic information comprises:

6. the method as described in claim 1 or 5, is characterized in that, described user data hasCorresponding ID, described employing user data generates the step bag of user individual characteristic informationDraw together:

7. the method as described in claim 1 or 2 or 3, is characterized in that, described according to userIndividualized feature information is that the step of described client push data comprises:

Search the user individual characteristic information mating with described ID;

8. the method as described in claim 1 or 2 or 3, is characterized in that, described employing is currentTime and/or current place, and described user individual characteristic information is described client push numberAccording to step comprise:

If so, be defined as to described client push data;

And/or,

If so, be defined as to described client push data.

9. method as claimed in claim 7, is characterized in that, described preset data tool to be recommendedHave corresponding label, the described step for the preset data to be recommended of client push comprises:

If so, to preset data to be recommended described in described client push.

10. a personalized data-pushing device, comprising: