CN103618774B - A kind of resource recommendation method based on network behavior and device, system - Google Patents

A kind of resource recommendation method based on network behavior and device, system Download PDF

Info

Publication number
CN103618774B
CN103618774B CN201310586089.XA CN201310586089A CN103618774B CN 103618774 B CN103618774 B CN 103618774B CN 201310586089 A CN201310586089 A CN 201310586089A CN 103618774 B CN103618774 B CN 103618774B
Authority
CN
China
Prior art keywords
recommendation
internet resources
network
network resource
resource
Prior art date
Application number
CN201310586089.XA
Other languages
Chinese (zh)
Other versions
CN103618774A (en
Inventor
李恒
胡聪
彭蔚
田野
韩三普
Original Assignee
北京奇虎科技有限公司
奇智软件(北京)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京奇虎科技有限公司, 奇智软件(北京)有限公司 filed Critical 北京奇虎科技有限公司
Priority to CN201310586089.XA priority Critical patent/CN103618774B/en
Publication of CN103618774A publication Critical patent/CN103618774A/en
Application granted granted Critical
Publication of CN103618774B publication Critical patent/CN103618774B/en

Links

Abstract

The present invention provides a kind of resource recommendation method based on network behavior and device, system, and the method includes: the network behavior that record client is carried out according to recommendation network resource;It is iterated according to the dependency between described recommendation network resource and the described Internet resources having carried out described network behavior, obtains potential recommendation network resource and the conversion ratio of described potential recommendation network resource;The conversion ratio of the conversion ratio according to described recommendation network resource, having carried out the Internet resources of described network behavior, potential recommendation network resource and described potential recommendation network resource generates the new recommendation list of described recommendation network resource and is sent to described client.Using client to the behaviour in service of Internet resources as feedback, obtain new recommendation list, provide a user with the most network resource recommended.

Description

A kind of resource recommendation method based on network behavior and device, system

Technical field

The present invention relates to network technology, particularly to a kind of resource recommendation method based on network behavior and dress Put, system.

Background technology

Along with the development of network technology, people have browsed the most in a network or have downloaded money Source.Internet resources are the hugest, and user actively scans for finding needs or the Internet resources interested are User obtains the major way of Internet resources, but the time that this mode is spent is a lot, is searching user The ability aspect of rope also requires that the highest, sometimes can take a lot of time and the result searched for is the most undesirable.For Provide a user with experience of surfing the Net the most easily, occur in that network resource recommended technology, according to various nets The conventional property of network resource or versatility generate recommendation list for user.And network resource recommended technology is relatively The network behavior utilizing user less feeds back.

Summary of the invention

In view of the above problems, it is proposed that the present invention is to provide a kind of resource recommendation method based on network behavior And device, system, can carry out network resource recommended the most accurately.

The present invention provides a kind of resource recommendation method based on network behavior, and the method includes:

The network behavior that record client is carried out according to recommendation network resource, obtains data record;

Extract described data record, by the mark of recommendation network resource, the network that carried out described network behavior The conversion ratio of the mark of resource and the Internet resources that carried out described network behavior generates extraction record;

According to the phase between described recommendation network resource with the described Internet resources having carried out described network behavior Pass property is iterated, and obtains potential recommendation network resource and the conversion of described potential recommendation network resource Rate;

According to described recommendation network resource, carry out the conversion ratio of the Internet resources of described network behavior, potential Recommendation network resource and described potential recommendation network resource conversion ratio generate described recommendation network money The new recommendation list in source is also sent to described client.

Wherein, the network behavior that described record client is carried out according to Internet resources, obtain data record and include:

Described client downloads and/or the daily record browsed is obtained by result collection system Scribe;

And/or, user installation record and/or the user of record client browse record.

Wherein, the conversion ratio of the Internet resources having carried out described network behavior described in is to be downloaded Internet resources Download time is divided by showing number of times;And/or, described in carried out the conversion of Internet resources of described network behavior Rate is divided by showing number of times by the number of visits of browse network resource.

Wherein, when described recommendation network resource is first network resource, the network of described network behavior has been carried out When resource is the second Internet resources, carry out described network behavior according to described recommendation network resource with described Dependency between Internet resources is iterated, and obtains potential recommendation network resource and described potential pushing away The conversion ratio recommending Internet resources includes:

Described first network resource is directly related with described second Internet resources;Obtain described through an iteration Potential recommendation network resource is described second Internet resources, the conversion ratio of described potential recommendation network resource For described second Internet resources conversion ratio divided by specify numerical value.

Wherein, when described recommendation network resource is first network resource, the network of described network behavior has been carried out Resource is the second Internet resources;And when described recommendation network resource is the second Internet resources, carried out described net When the Internet resources of network behavior are three Internet resources, carry out institute according to described recommendation network resource with described The dependency stated between the Internet resources of network behavior is iterated, obtain potential recommendation network resource and The conversion ratio of described potential recommendation network resource includes:

Described first network resource and described 3rd Internet resources indirect correlation;Obtain described through second iteration Potential recommendation network resource is described 3rd Internet resources, the conversion ratio of described potential recommendation network resource Conversion ratio for described 3rd Internet resources specifies numerical value divided by two times.

The present invention also provides for the device of a kind of resource recommendation based on network behavior, and this device includes:

Data center, for recording the network behavior that client is carried out according to recommendation network resource, obtains data Record;

Recommended engine, is used for extracting described data record, by the mark of recommendation network resource, carried out described The conversion ratio of the mark of the Internet resources of network behavior and the Internet resources that carried out described network behavior generates Extraction record;According between described recommendation network resource and the described Internet resources having carried out described network behavior Dependency be iterated, obtain potential recommendation network resource and described potential recommendation network resource Conversion ratio;The conversion ratio that according to described recommendation network resource, carried out the Internet resources of described network behavior, The conversion ratio of potential recommendation network resource and described potential recommendation network resource generates described recommendation net The new recommendation list of network resource;

Recommending data interface, is sent to described client by described new recommendation list.

Wherein, described data center includes:

Recommending data storehouse, for obtaining described client downloads and/or clear by result collection system Scribe The daily record look at;

And/or,

Customer data base, browses record for the user installation record and/or user recording client.

The present invention also provides for a kind of resource recommendation system device based on network behavior, and this system includes:

Recommendation server, described server includes any of the above-described described device;

Client, is used for showing recommendation list and new recommendation list.

What the present invention brought has the beneficial effect that:

It is iterated according to the dependency between recommendation network resource and the Internet resources having carried out network behavior, Obtain potential recommendation network resource and the conversion ratio of potential recommendation network resource, thus by client pair The behaviour in service of Internet resources, as feedback, obtains new recommendation list, provides a user with net the most accurately Network resource recommendation.

Described above is only the general introduction of technical solution of the present invention, in order to better understand the technology of the present invention Means, and can being practiced according to the content of description, and in order to allow above and other objects of the present invention, Feature and advantage can become apparent, below especially exemplified by the detailed description of the invention of the present invention.

Accompanying drawing explanation

By reading the detailed description of hereafter preferred implementation, various other advantage and benefit for ability Territory those of ordinary skill will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and also It is not considered as limitation of the present invention.And in whole accompanying drawing, it is denoted by the same reference numerals identical Parts.In the accompanying drawings:

Fig. 1 is the flow process signal of a kind of resource recommendation method based on network behavior in the embodiment of the present invention one Figure;

Fig. 2 is the flow process signal of a kind of resource recommendation method based on network behavior in the embodiment of the present invention two Figure;

Fig. 3 is the application scenarios one of a kind of resource recommendation method based on network behavior in the embodiment of the present invention two Schematic diagram;

Fig. 4 is the application scenarios two of a kind of resource recommendation method based on network behavior in the embodiment of the present invention two Schematic diagram;

Fig. 5 is the application scenarios three of a kind of resource recommendation method based on network behavior in the embodiment of the present invention two Schematic diagram;

Fig. 6 is the structural representation of the device of a kind of resource recommendation based on network behavior in the embodiment of the present invention three Figure.

Detailed description of the invention

It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although accompanying drawing shows The exemplary embodiment of the disclosure, it being understood, however, that may be realized in various forms the disclosure and should be by Embodiments set forth here is limited.On the contrary, it is provided that these embodiments are able to be best understood from this Open, and complete for the scope of the present disclosure can be conveyed to those skilled in the art.

The present invention is further detailed explanation with detailed description of the invention below in conjunction with the accompanying drawings.

In embodiments of the present invention, calculating equipment includes but not limited to that client, server etc. are to have operation The smart machine of system, such as desktop computer, notebook computer etc..Calculating equipment can connect net in a wired fashion Network, it is also possible to wireless mode connects network, and the network connected can be the Internet, it is also possible to be LAN. Wirelessly connect network can be by calculate the built-in wireless network card of equipment or pass through USB without Gauze card.Described wireless network card is set to share the hotspot of the network that described calculating equipment is connected After, access the mobile terminals such as the mobile phone of this hotspot, PAD and just can access this meter by this wireless network card The network that calculation equipment is connected, uses the bandwidth of this calculating equipment connected network, extra without spending Flow rate.The concrete process that wireless network card is set to hotspot refers to follow-up Fig. 2 and phase Close and describe.

Referring to Fig. 1, embodiment one, a kind of resource recommendation method based on network behavior, the method includes:

The network behavior that S110 record client is carried out according to recommendation network resource, obtains data record.

In the present embodiment, network behavior includes but not limited to download and/or browse.

In the present embodiment, the daily record that data include but not limited to client downloads, the daily record browsed, client The user installation record of end, user browse record and/or obtain the attribute data of Internet resources.Wherein, institute The attribute data stating Internet resources includes: label (TAG), developer, classification and/or the owner.

Such as, the service end for application shop can store user's history when user uses Mobile solution shop Daily record, text formatting storage user's history log;User's history log includes that user is in Mobile solution shop The data of the Mobile solution accessed, the Mobile solution that user accessed includes the movement that user checks or downloads Application;Wherein, the data of the Mobile solution that user accessed in Mobile solution shop include ID (UID), Mobile solution mark (packageID) and access the time.

In the present embodiment, the mode obtaining data record can include but not limited to:

Described client downloads and/or the daily record browsed is obtained by result collection system Scribe;

And/or, user installation record and/or the user of record client browse record.

And/or, the attribute data of the Internet resources in the service end data base at DUMP Internet resources place.

In an embodiment, client includes but not limited to PC and/or mobile terminal.

In an embodiment, Internet resources at least include APP, music, game, novel, video and picture it One.

In order to improve the safety of data, in the present embodiment, described data record is passed through irreversible encryption Algorithm is encrypted.

S120 extracts described data record, by the mark of recommendation network resource, has carried out described network behavior The conversion ratio of the mark of Internet resources and the Internet resources that carried out described network behavior generates extraction record.

In the present embodiment, conversion ratio is that the download time being downloaded Internet resources is divided by showing number of times;With/ Or, by the number of visits of browse network resource divided by showing number of times.

For ease of consulting, extracting record in the present embodiment can be with behavior unit, and every behavior three arranges, first row For the mark of recommendation network resource, second is classified as the mark of the Internet resources having carried out described network behavior, the Three conversion ratios being classified as the Internet resources having carried out described network behavior.

S130 is according between described recommendation network resource and the described Internet resources having carried out described network behavior Dependency be iterated, obtain potential recommendation network resource and described potential recommendation network resource Conversion ratio.

In the present embodiment, optionally, when described recommendation network resource is first network resource, institute has been carried out State the Internet resources of network behavior when being the second Internet resources, carry out with described according to described recommendation network resource Dependency between the Internet resources of described network behavior is iterated, and obtains potential recommendation network resource And the conversion ratio of described potential recommendation network resource includes:

Described first network resource is directly related with described second Internet resources;Obtain described through an iteration Potential recommendation network resource is described second Internet resources, the conversion ratio of described potential recommendation network resource For described second Internet resources conversion ratio divided by specify numerical value.Optionally, in the present embodiment, it is intended that number Value is 2.

Such as, first network resource is APP1, and the second Internet resources are APP2, are browsed by APP1 APP2, through an iteration, obtaining browsing APP1 by APP2 is potential browsing, and APP2 turns Rate is the number of visits displaying number of times divided by APP2 of APP2, then the potential conversion ratio that browses is Conversion ratio/2 of APP2.

The most such as, first network resource is APP1, and the second Internet resources are APP2, are browsed by APP1 APP2, through an iteration, obtaining downloading APP1 by APP2 is potential download, APP2's Conversion ratio is the number of visits displaying number of times divided by APP2 of APP2, then the conversion ratio of potential download is Conversion ratio/2 of APP2.

In the present embodiment, optionally, when described recommendation network resource is first network resource, institute has been carried out The Internet resources stating network behavior are the second Internet resources;And when described recommendation network resource is the second network money Source, has carried out the Internet resources of described network behavior when being three Internet resources, has provided according to described recommendation network Dependency between source and the described Internet resources having carried out described network behavior is iterated, and obtains potential The conversion ratio of recommendation network resource and described potential recommendation network resource includes:

Described first network resource and described 3rd Internet resources indirect correlation;Obtain described through second iteration Potential recommendation network resource is described 3rd Internet resources, the conversion ratio of described potential recommendation network resource Conversion ratio for described 3rd Internet resources specifies numerical value divided by two times.

Such as, first network resource is APP1, and the second Internet resources are APP2, and the 3rd Internet resources are APP3, has downloaded APP2 by APP1, has downloaded APP3 by APP2, then, APP1 and APP3 For indirect correlation, through second iteration, obtaining downloading APP3 by APP1 is potential download, APP3 The number of visits that conversion ratio is APP3 divided by the displaying number of times of APP3, then the conversion ratio of potential download Conversion ratio/4 for APP3.

The most such as, first network resource is APP1, and the second Internet resources are APP2, and the 3rd Internet resources are APP3, has downloaded APP2 by APP1, has browsed APP3 by APP2, then, APP1 and APP3 For indirect correlation, through second iteration, obtaining downloading/browse APP3 by APP1 is potential download, The conversion ratio of APP3 is the number of visits displaying number of times divided by APP3 of APP3, then potential download/clear The conversion ratio look at is conversion ratio/4 of APP3.

Conversion ratio that S140 according to described recommendation network resource, has carried out the Internet resources of described network behavior, The conversion ratio of potential recommendation network resource and described potential recommendation network resource generates described recommendation net The new recommendation list of network resource is also sent to described client.

In the present embodiment, according to described recommendation network resource, the Internet resources that carried out described network behavior The conversion ratio of conversion ratio, potential recommendation network resource and described potential recommendation network resource generates described The new recommendation list of recommendation network resource includes:

By conversion ratio and the described potential recommendation network of the described Internet resources having carried out described network behavior The conversion ratio of resource sorts from big to small, generates the new recommendation list of described recommendation network resource.

After iteration, the length of new recommendation list likely can be less than the length of recommendation list, now, and will The recommendation network resource obtained by other algorithms is supplemented until the length of described new recommendation list is equal to described The length of recommendation list.

In a particular application, different algorithms can be used, can include but not limited to based on article collaborative Filter algorithm (ITEM-BASED CF) and/or collaborative filtering based on user (USER-BASED CF) Deng, the ranking of the conversion ratio obtained after applying according to various algorithms, regular or irregular employing ranking exists Front algorithm, is iterated recommendation network resource, and the result obtained is supplemented in new recommendation list.

The concrete application of technique scheme, may include steps of:

A) first 10 days of server timing extraction every day get daily record ready, this gets daily record ready is to pass through commending system The download behavior brought.The daily record of getting ready extracted arranges with behavior unit, every behavior three, and first is classified as and pushes away The appid recommended, second is classified as the appid of recommended download, and the 3rd is classified as conversion ratio, i.e. download time divided by Show number of times.

B) daily record of getting ready by extracting is iterated, to produce the most possible download, iteration Method has two kinds:

1. downloaded the user of app2 by app1, it is also possible to download app1 by app2;

2. downloaded app2 by app1, downloaded app3 by app2, then also being had by app1 can App3 can be downloaded.Often carrying out an iteration, conversion ratio, divided by a fixing numerical value, is 2.0 at present.

C) by the iteration of B process, more many potential download behaviors can be produced.Potential download behavior Can serve as metadata plus the download having had and carry out downloading based on user the recommendation of behavior.

D) metadata produced by C process, can be utilized the app of first row recommending when, push away Recommend the app of secondary series, it is recommended that order arrange in reverse order with the size of conversion ratio.This algorithm may cause pushing away Recommend list length inadequate, now can use other proposed algorithms according to the length required for recommendation list Result selects to supplement from front to back, to meet the length required for recommendation list shows.

Due to the feedback according to user, adding potential recommendation, the download conversion ratio of the Internet resources being obtains To promoting.

Embodiment two, a kind of resource recommendation method based on network behavior, in the present embodiment, client bag Including PC end and mobile terminal, the mobile terminal in the present embodiment is mobile phone, the applied environment of the technical program The recommendation details page of web browser, my mobile phone display page of PC end and/or pushing away of mobile phone for PC end Recommend details page.

The technical scheme of the present embodiment comprises the steps:

S210 collects the data of the network behavior that user is carried out, this enforcement according to recommendation network resource from client Example is applied in following several prods: the recommendation details page of the web browser of PC end, my hands of PC end The machine display page and the recommendation details page of mobile phone.

The data that S220 collects are stored in data Layer, can classify and be saved in customer data base, recommending data storehouse With in APP data base.Wherein, user data library storage includes but not limited to the user installation record of client Record is browsed with user.APP data base stores the attribute data of APP.Recommending data library storage include but The daily record being not limited to client downloads and the daily record browsed;Recommending data storehouse can also include but not limited to multiple The title of Mobile solution and the download link etc. of multiple Mobile solution.Specifically, for the title of Mobile solution Service provider can also revise it and describe information, describes information so that the user of use Mobile solution can Clearly to identify the main contents of each Mobile solution in Mobile solution set, under facilitating user to carry out Carry, install and uninstall etc. operates.

The data of S230 recommended engine extracted data layer storage, by the mark of recommendation network resource, have carried out institute The conversion ratio of the mark stating the Internet resources of network behavior and the Internet resources having carried out described network behavior is raw Become extraction record, and according to described recommendation network resource and the described network money having carried out described network behavior Dependency between source is iterated, and obtains potential recommendation network resource and described potential recommendation network The conversion ratio of resource;Afterwards, according to described recommendation network resource, carried out described network behavior network money The conversion ratio of the conversion ratio in source, potential recommendation network resource and described potential recommendation network resource generates The new recommendation list of described recommendation network resource.

On implementing, the real-time computing engines of recommendation and/or recommendation calculated off line engine two set can be used Recommended engine processes, thus the speed and the efficiency that process data are taken into account.

The new recommendation list obtained is pushed by S240 by recommending data interface, in order to improve propelling movement effect Rate, can use different interfaces, in the present embodiment, interface according to the receiving terminal difference of new recommendation list The receiving terminal of 1 correspondence is the recommendation details page of the web browser of PC end, and the receiving terminal of interface 2 correspondence is My mobile phone display page of PC end, the recommendation details page that receiving terminal is mobile phone of interface 3 correspondence.

New recommendation list is pushed to the product of correspondence by S250 respectively by different service end front end interfaces, In the present embodiment, the recommendation of the web browser new recommendation list being pushed to PC end by intf interface is detailed Feelings page, by third assistant's interface new recommendation list is pushed to my mobile phone display page of PC end with And by mobile phone terminal interface, new recommendation list is pushed to the recommendation details page of mobile phone.

When pushing product by service end front end, pc or mobile phone can obtain described from corresponding server Web page contents currently displaying on calculating equipment.

In order to meet the demand of user, save data traffic, can selected in webpage in advance be transmitted Target, such as, selected a few moneys game, or certain wallpaper etc., can mark for selected target Note, thus when currently displaying web page contents is resolved, can detect in this webpage whether there is choosing Fixed target (target of tape label), if there is selected target, then obtains this selected content.If inspection Measure and webpage is not selected any target, now it is believed that the content in whole webpage is all selected mesh Mark, thus transmit the content in whole webpage.

The embodiment of the present invention can obtain the one in information described below or many according to selected target Kind, wherein, described description information include but not limited to the title of described target, the storage address of described target, The size of data of described target and the thumbnail of described target.Wherein, described title is the name of selected target Claim, such as game name, web page title etc..Described storage address is the storage of the related data of selected target Address, if selected target is game, described storage address can be the download address of single-play game, or net The reference address etc. of network game.Described size of data is the data volume of the related data of selected target, such as choosing Fixed target is single-play game, and the most described size of data can be the data of the installation procedure of this single-play game Amount, such as 2M;And for example selected target is wallpaper, and the most described size of data is exactly the size of this wallpaper. Described thumbnail is the picture of the content that can show selected target, when being webpage such as selected target, Described thumbnail can be the Logo of this website, webpage place, and and for example, selected target is game, then institute State the poster picture etc. that thumbnail can be this game.

Transmitting procedure data acquisition is configurable to Json form with preset form, and the data of the most preset form are permissible Character string for Json form.

Also include concrete application, such as " Dungeon is with brave ... ", " lamb general mobilization " and " forgetting celestial being " etc.. Wherein, the full name of " Dungeon is with brave ... " is " DNF official is legal ", due to the position in webpage It is equipped with limit, therefore illustrate only division name.

It is assumed that now selected target is " DNF official is legal ", then calculating equipment can obtain The character string describing information structure Json form of " DNF official is legal ".Wherein, Json A kind of exemplary forms of the character string of form is as follows:

[{"attach":[{"Market_name":"","apkid":"com.Nexon.DunfightENGF360","file The formal version of dispname ": " DNF official 1.01 ", " filename ": " DNF official is just Formula version 1.01.apk ", " filesize ": " 28899475 ", " filethumb ": "http://p3.qhimg.com/t01 617c9165b3dae3eb.png","filetype":"app","fileurl":"http://shouji.360safe.com/360sj/ adm/apk/20121215/com.Nexon.DunfightENGF360_2_194130.apk","format":"apk", "mid":"12fcd727fc624ed180de17e94ff72c67ca1089050c376ba8a499618bea589322 ", " msgsource ": " mobile phone assistant

The character string of above-mentioned Json form identifies the description information of " DNF official is legal ", As stored address (fileurl), and for example size of data (filesize), also include " DNF official Legal " type (filetype) etc..

Currently displaying web page contents is sent to server by calculating equipment.

The character string of upper described Json form can be sent to server by calculating equipment.

Described currently displaying web page contents is stored by server, and generates file acquisition message.

Server stores and generates file acquisition message, wherein, file to the character string of this Json form Obtain the storage address comprising the character string of this Json form in server in message.

Server sends described file acquisition message to mobile device.

Mobile device obtains web page contents currently displaying on described calculating equipment from server.

The storage address of the character string of this Json form in server can be conducted interviews by mobile device, thus Obtain the character string of this Json form.

Currently displaying web page contents on described calculating equipment is resolved and shows by mobile device.

The character string of Json form is resolved by mobile device, and displays it to the screen of mobile device On.

As got the character string of Json form in mobile device after, it is resolved, is converted into display During data, described chained address can be shown, thus described selected mesh can be obtained by this chained address Target related data.When described chained address is associated with the description information such as thumbnail or title, Ke Yitong Cross click thumbnail or title, trigger described chained address, obtain the related data of described selected target.

Refer to Fig. 3, for the recommendation details page of the web browser of application scenarios in the present embodiment one PC end Schematic diagram, wherein, guesses that you like a hurdle to be the recommendation list for 360 mobile phone bodyguards.

Refer to Fig. 4, for the signal of my mobile phone display page of application scenarios in the present embodiment two PC end Figure, wherein, guesses that you may also like a hurdle to be the recommendation list for 360 address lists.

Refer to Fig. 5, for the schematic diagram of the recommendation details page of application scenarios in the present embodiment three mobile phone, wherein, Guess that you like a hurdle to be the recommendation list for Sina's microblogging cell-phone customer terminal.

Embodiment three, refers to Fig. 6, the device of a kind of resource recommendation based on network behavior, this device bag Include:

Data center 610, for recording the network behavior that client is carried out according to recommendation network resource, obtains Data record;

Recommended engine 620, is used for extracting described data record, by the mark of recommendation network resource, carries out The mark of the Internet resources of described network behavior and carried out the conversion ratio of Internet resources of described network behavior Generate extraction record;According to described recommendation network resource and the described Internet resources having carried out described network behavior Between dependency be iterated, obtain potential recommendation network resource and described potential recommendation network money The conversion ratio in source;According to described recommendation network resource, the conversion that carried out the Internet resources of described network behavior The conversion ratio of rate, potential recommendation network resource and described potential recommendation network resource generates described recommendation The new recommendation list of Internet resources;

Recommending data interface 630, is sent to described client by described new recommendation list.

Wherein, described data center includes:

Recommending data storehouse, for obtaining described client downloads and/or clear by result collection system Scribe The daily record look at;

And/or,

Customer data base, browses record for the user installation record and/or user recording client.

Wherein, described data center also includes:

APP data base, for obtaining corresponding attribute data from the service end of described APP.

The present invention also provides for a kind of resource recommendation system device based on network behavior, and this system includes:

Recommendation server, described server includes any of the above-described described device;

Client, is used for showing recommendation list and new recommendation list.

Those skilled in the art are it should be appreciated that embodiments herein can be provided as method, system or meter Calculation machine program product.Therefore, the application can use complete hardware embodiment, complete software implementation or knot The form of the embodiment in terms of conjunction software and hardware.And, the application can use and wherein wrap one or more Computer-usable storage medium containing computer usable program code (include but not limited to disk memory, CD-ROM, optical memory etc.) form of the upper computer program implemented.

The application is with reference to method, equipment (system) and the computer program product according to the embodiment of the present application The flow chart of product and/or block diagram describe.It should be understood that can by computer program instructions flowchart and / or block diagram in each flow process and/or flow process in square frame and flow chart and/or block diagram and/ Or the combination of square frame.These computer program instructions can be provided to general purpose computer, special-purpose computer, embedding The processor of formula datatron or other programmable data processing device is to produce a machine so that by calculating The instruction that the processor of machine or other programmable data processing device performs produces for realizing at flow chart one The device of the function specified in individual flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.

These computer program instructions may be alternatively stored in and computer or the process of other programmable datas can be guided to set In the standby computer-readable memory worked in a specific way so that be stored in this computer-readable memory Instruction produce and include the manufacture of command device, this command device realizes in one flow process or multiple of flow chart The function specified in flow process and/or one square frame of block diagram or multiple square frame.

These computer program instructions also can be loaded in computer or other programmable data processing device, makes Sequence of operations step must be performed to produce computer implemented place on computer or other programmable devices Reason, thus the instruction performed on computer or other programmable devices provides for realizing flow chart one The step of the function specified in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.

Although having been described for the preferred embodiment of the application, but those skilled in the art once knowing base This creativeness concept, then can make other change and amendment to these embodiments.So, appended right is wanted Ask and be intended to be construed to include preferred embodiment and fall into all changes and the amendment of the application scope.

Obviously, those skilled in the art can carry out various change and modification without deviating from this Shen to the application Spirit and scope please.So, if the application these amendment and modification belong to the application claim and Within the scope of its equivalent technologies, then the application is also intended to comprise these change and modification.

Claims (16)

1. a resource recommendation method based on network behavior, it is characterised in that the method includes:
The network behavior that record client is carried out according to recommendation network resource, obtains data record;
Extract described data record, by the mark of recommendation network resource, the network that carried out described network behavior The conversion ratio of the mark of resource and the Internet resources that carried out described network behavior generates extraction record;
According to the phase between described recommendation network resource with the described Internet resources having carried out described network behavior Pass property is iterated, and obtains potential recommendation network resource and the conversion of described potential recommendation network resource Rate;
According to described recommendation network resource, carry out the conversion ratio of the Internet resources of described network behavior, potential Recommendation network resource and described potential recommendation network resource conversion ratio generate described recommendation network money The new recommendation list in source is also sent to described client;
Wherein, when the length of described new recommendation list is less than the length of described recommendation list, supplement until institute State the length length equal to described recommendation list of new recommendation list.
Method the most according to claim 1, it is characterised in that: described network behavior include download and/ Or browse.
Method the most according to claim 2, it is characterised in that described record client is according to network The network behavior that resource is carried out, obtains data record and includes:
Described client downloads and/or the daily record browsed is obtained by result collection system Scribe;
And/or, user installation record and/or the user of record client browse record.
Method the most according to claim 3, it is characterised in that described record client is according to network The network behavior that resource is carried out, obtains data record and also includes: obtain the attribute data of Internet resources.
Method the most according to claim 4, it is characterised in that the attribute data of described Internet resources Including: label, developer, classification and/or the owner.
Method the most according to claim 2, it is characterised in that carried out described network behavior described in: The conversion ratio of Internet resources be that the download time being downloaded Internet resources is divided by showing number of times;And/or, institute The conversion ratio stating the Internet resources having carried out described network behavior is to be removed by the number of visits of browse network resource To show number of times.
Method the most according to claim 1, it is characterised in that when described recommendation network resource is One Internet resources, have carried out the Internet resources of described network behavior when being the second Internet resources, have pushed away according to described The dependency recommended between Internet resources and the described Internet resources having carried out described network behavior is iterated, Conversion ratio to potential recommendation network resource and described potential recommendation network resource includes:
Described first network resource is directly related with described second Internet resources;Obtain described through an iteration Potential recommendation network resource is described second Internet resources, the conversion ratio of described potential recommendation network resource For described second Internet resources conversion ratio divided by specify numerical value.
Method the most according to claim 1, it is characterised in that when described recommendation network resource is One Internet resources, the Internet resources having carried out described network behavior are the second Internet resources;And when described recommendation Internet resources are the second Internet resources, and the Internet resources having carried out described network behavior are the 3rd Internet resources Time, relevant according between described recommendation network resource to the described Internet resources having carried out described network behavior Property is iterated, and obtains potential recommendation network resource and the conversion ratio of described potential recommendation network resource Including:
Described first network resource and described 3rd Internet resources indirect correlation;Obtain described through second iteration Potential recommendation network resource is described 3rd Internet resources, the conversion ratio of described potential recommendation network resource Conversion ratio for described 3rd Internet resources specifies numerical value divided by two times.
9. according to the method described in claim 7 or 8, it is characterised in that described appointment numerical value is 2.
Method the most according to claim 1, it is characterised in that according to described recommendation network resource, The conversion ratio of the Internet resources of described network behavior, potential recommendation network resource and described potential are carried out Recommendation network resource conversion ratio generate described recommendation network resource new recommendation list include:
By conversion ratio and the described potential recommendation network of the described Internet resources having carried out described network behavior The conversion ratio of resource sorts from big to small, generates the new recommendation list of described recommendation network resource.
11. methods according to claim 1, it is characterised in that: described client include PC and/or Mobile terminal.
12. methods according to claim 1, it is characterised in that: described Internet resources at least include APP, One of music, game, novel, video and picture.
The device of 13. 1 kinds of resource recommendations based on network behavior, it is characterised in that this device includes:
Data center, for recording the network behavior that client is carried out according to recommendation network resource, obtains data Record;
Recommended engine, is used for extracting described data record, by the mark of recommendation network resource, carried out described The conversion ratio of the mark of the Internet resources of network behavior and the Internet resources that carried out described network behavior generates Extraction record;According between described recommendation network resource and the described Internet resources having carried out described network behavior Dependency be iterated, obtain potential recommendation network resource and described potential recommendation network resource Conversion ratio;The conversion ratio that according to described recommendation network resource, carried out the Internet resources of described network behavior, The conversion ratio of potential recommendation network resource and described potential recommendation network resource generates described recommendation net The new recommendation list of network resource, is wherein less than the length of described recommendation list when the length of described new recommendation list Time, supplement until the length of described new recommendation list is equal to the length of described recommendation list;
Recommending data interface, is sent to described client by described new recommendation list.
14. devices according to claim 13, it is characterised in that described data center includes:
Recommending data storehouse, for obtaining described client downloads and/or clear by result collection system Scribe The daily record look at;
And/or,
Customer data base, browses record for the user installation record and/or user recording client.
15. devices according to claim 13, it is characterised in that described data center also includes:
APP data base, for obtaining corresponding attribute data from the service end of described APP.
16. 1 kinds of resource recommendation system devices based on network behavior, it is characterised in that this system includes:
Recommendation server, described server includes the arbitrary described device of claim 13 to 15;
Client, is used for showing recommendation list and new recommendation list.
CN201310586089.XA 2013-11-19 2013-11-19 A kind of resource recommendation method based on network behavior and device, system CN103618774B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310586089.XA CN103618774B (en) 2013-11-19 2013-11-19 A kind of resource recommendation method based on network behavior and device, system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310586089.XA CN103618774B (en) 2013-11-19 2013-11-19 A kind of resource recommendation method based on network behavior and device, system

Publications (2)

Publication Number Publication Date
CN103618774A CN103618774A (en) 2014-03-05
CN103618774B true CN103618774B (en) 2016-11-23

Family

ID=50169478

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310586089.XA CN103618774B (en) 2013-11-19 2013-11-19 A kind of resource recommendation method based on network behavior and device, system

Country Status (1)

Country Link
CN (1) CN103618774B (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104065981A (en) * 2014-06-20 2014-09-24 海信集团有限公司 Method and device for recommending videos
CN104537104A (en) * 2015-01-13 2015-04-22 百度在线网络技术(北京)有限公司 Software ranking method and system
CN105868208B (en) * 2015-01-21 2019-04-26 方正宽带网络服务有限公司 A kind of Internet resources analysis method and device
CN104811783B (en) * 2015-03-17 2018-02-06 四川长虹电器股份有限公司 Intelligent television home court scape design method as content display platform
CN105183882A (en) * 2015-09-23 2015-12-23 百度在线网络技术(北京)有限公司 Application software recommending method and device
CN106156351B (en) * 2016-07-26 2019-07-23 合一网络技术(北京)有限公司 Multimedia resource recommendation information generation method and device
CN108280102B (en) * 2017-02-08 2020-12-08 阿里巴巴(中国)有限公司 Internet surfing behavior recording method and device and user terminal
CN108737479B (en) * 2017-04-24 2021-01-15 北京小熊博望科技有限公司 Method and device for pushing information
CN108510313A (en) * 2018-03-07 2018-09-07 阿里巴巴集团控股有限公司 A kind of prediction of information transferring rate, information recommendation method and device
CN109299350B (en) * 2018-09-13 2019-08-20 掌阅科技股份有限公司 The sort method of e-book calculates equipment and computer storage medium
CN109902245A (en) * 2019-02-01 2019-06-18 天津字节跳动科技有限公司 Interactive information providing method and device
CN110503478B (en) * 2019-08-26 2020-08-18 北京深演智能科技股份有限公司 APP pushing method and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102054003A (en) * 2009-11-04 2011-05-11 北京搜狗科技发展有限公司 Methods and systems for recommending network information and creating network resource index
CN102999589A (en) * 2012-11-15 2013-03-27 Tcl集团股份有限公司 Method and system for recommending order

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102054003A (en) * 2009-11-04 2011-05-11 北京搜狗科技发展有限公司 Methods and systems for recommending network information and creating network resource index
CN102999589A (en) * 2012-11-15 2013-03-27 Tcl集团股份有限公司 Method and system for recommending order

Also Published As

Publication number Publication date
CN103618774A (en) 2014-03-05

Similar Documents

Publication Publication Date Title
CN109145078B (en) The application page of the machine application is indexed
US10146887B2 (en) Providing separate views for items
US10789626B2 (en) Deep-linking system, method and computer program product for online advertisement and e-commerce
KR102005054B1 (en) Launching applications from webpages
US10592515B2 (en) Surfacing applications based on browsing activity
CN102722563B (en) Method and device for displaying page
US9013426B2 (en) Providing a sense of touch in a mobile device using vibration
US10055762B2 (en) Deep application crawling
US10776501B2 (en) Automatic augmentation of content through augmentation services
US10007933B2 (en) Systems and methods for integrating dynamic content into electronic media
US20150058821A1 (en) Mobile design patterns
EP2633487B1 (en) Method and system to recommend applications from an application market place to a new device
US9483388B2 (en) Discovery of application states
CN103488781B (en) Method, the search engine server of information search are provided
JP2016520913A (en) Entity bid
CN104641363B (en) The system and method for assessment application compatibility
CN107203894B (en) Information pushing method and device
CN102819555B (en) A kind of method and apparatus carrying out recommendation information loading in the reading model of webpage
US9262057B2 (en) Providing item specific functionality via service-assisted applications
WO2015175384A1 (en) Query categorizer
US20160283592A1 (en) Method for performing network search at a browser side and a browser
US20130326333A1 (en) Mobile Content Management System
WO2016069956A1 (en) Classifying user intent based on location information electronically communicated from a mobile device
JP6814298B2 (en) Methods and equipment for warning
CN102076115B (en) A kind of control method of issuing advertisement information in mobile terminal and device

Legal Events

Date Code Title Description
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant