CN103019550B - The real-time exhibiting method of content association and system - Google Patents

The real-time exhibiting method of content association and system Download PDF

Info

Publication number
CN103019550B
CN103019550B CN201210524614.0A CN201210524614A CN103019550B CN 103019550 B CN103019550 B CN 103019550B CN 201210524614 A CN201210524614 A CN 201210524614A CN 103019550 B CN103019550 B CN 103019550B
Authority
CN
China
Prior art keywords
content
screen display
user terminal
focus
display page
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201210524614.0A
Other languages
Chinese (zh)
Other versions
CN103019550A (en
Inventor
邹存璐
蒋理成
韩宇
赵博
王菊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Neusoft Corp
Original Assignee
Neusoft Corp
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 Neusoft Corp filed Critical Neusoft Corp
Priority to CN201210524614.0A priority Critical patent/CN103019550B/en
Publication of CN103019550A publication Critical patent/CN103019550A/en
Application granted granted Critical
Publication of CN103019550B publication Critical patent/CN103019550B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention provides the real-time exhibiting method of a kind of content association and system, its method comprises: change screen action, the content of the current screen display page of user in real terminal according to user terminal; Then the focus content of the screen display page is determined; And then judge whether and the cache information that the focus content of the screen display page is associated; If had, obtain cache information and be shown to user terminal as the content association recommended to user terminal; Otherwise, other customer groups of the focus content of the screen display page and other customer groups similar to the behavior of user terminal were paid close attention to by calculating in real time to obtain, determine the common focus of other customer groups, and be shown to user terminal using described common focus as the content association recommended to described user terminal.The present invention can be different according to the focus of the current stop of user and concern, the content that real-time change display and user relevant to this focus may like, thus the raising experience of user and the conversion ratio of website.

Description

The real-time exhibiting method of content association and system
Technical field
The present invention relates to web browsing technology field, more specifically, relate to a kind of real-time exhibiting method of content association and system of recommendation network information.
Background technology
Along with the progress of society and the development of technology, people utilize network to carry out obtaining information more and more.In this case, by the browsing of user, search for, click and the behavior such as comment, for user recommends to be associated most with them one of focus content that the content that maybe may like pays close attention to the most with regard to the companies such as Cheng Liao portal website, online shopping mall or enterprise.
Commending system is applied on the website of Amazon, according to the buying behavior of user in the past, recommends out other products that certain product of purchase may be bought simultaneously.Commending system is successfully utilized to improve conversion ratio (visit capacity/total visit capacity of the action that website is expected of its electronic bookstore from Amazon, this index is used for weighing the attraction degree of web site contents to visitor and the effect of publicity of website) after, current personalized recommendation system is obtained for and applies widely in internet product, ecommerce and social network sites.In general, proposed algorithm needs (to browse the behavior in certain product use procedure in website according to a large number of users, click, comment etc.), in conjunction with relevant proposed algorithm (such as collaborative filtering), find and represent the content of be associated most with it (may like) to user.
In recent years, proposed algorithm obtains continuous retrofit, such as collaborative filtering, this algorithm finds that co-browse crosses certain page or the user group similar to this user behavior, and from similar users colony, find its joint act and recommend this user, thus can more effectively to user recommend may interested in perhaps good friend.The crawl of legacy user's behavioral data is divided into recessive data and Dominant Data, and Dominant Data mainly comprises evaluation, buys the operation of so direct performance user preferences; The action that recessive data mainly comprise the navigation patterns of user, clickthrough directly can not express user preferences like this.The superiority that recessive data have it certain: the certain operations process that first recessive data do not need user extra, better user experience; Recessive data can effectively avoid data fabrication brush to grade deceptive practices because it is larger in addition.
Fig. 1 shows and utilizes the crawl of traditional hidden customer behavioral data to recommend the flow process of content association for user.As shown in Figure 1, when user browses a URL webpage, namely add this navigation patterns to user browsing behavior database, user browsing behavior database root obtains the information of two aspects according to this navigation patterns: 1. obtain other user behavior information browsing this webpage; 2. obtain with other similar user behavior information of this user behavior, then carry out down sequence according to the URL of number of users to involved webpage of co-browse; Display rank top n URL content information recommends user, and user can check the URL content information of recommendation by clicking.
Process flow diagram according to Fig. 1, can find, the grasping means of current traditional hidden customer behavioral data just obtains user and clicks the content browsing a page, but because a present page often contains contents different in a large number, user has often just browsed or has paid close attention to wherein very little a part of content in the process browsed.
And due to the difference that website UI designs, the focal position that different web pages user pays close attention to all there are differences.And due to the restriction of the mobile device such as mobile phone, panel computer screen size, the content of screen display is very limited, user is needed to check contents (such as popular at present social network sites, microblogging website etc. widely, contain the different content that a lot of user produces in mobile phone application in a page) different in a webpage by the mode of rolling roller bearing or slip.So it can the subject of knowledge and the object of knowledge content (the roll/slide page stop page address portions) browsing and pay close attention to be greatly different that the different user browsing the same URL page has, and said method this situation cannot be distinguished.Therefore, this crawl clicking the content of pages browsed only by user is the mode according to determining content recommendation, inevitably can cause the reduction of recommendation results accuracy.
In addition, the result that current commending system calculates often all fixedly is presented at a position of the page, user is when rolling view page diverse location, the position of recommendation results and content all can not produce according to the change of user's focus the change be associated in real time, cause user or the content (content recommendation roll out screen display scope) of recommendation cannot be seen, or the content of recommending has nothing to do with the focus of current concern.
Summary of the invention
In view of the above problems, the object of this invention is to provide a kind of can user in real focus recommend the real-time exhibiting method of content association and the system of the content of association according to the different real-time change of focus, to improve the conversion ratio of Consumer's Experience and website.
According to an aspect of the present invention, provide the real-time exhibiting method of a kind of content association, comprising:
Screen action is changed, the content of the current screen display page of user in real terminal according to user terminal; The focus content of the described screen display page is determined according to the content of the obtained user terminal current screen display page; Judge whether and the cache information that the focus content of the described screen display page is associated according to the focus content of the described screen display page; If had, obtain described cache information and be shown to described user terminal as the content association recommended to described user terminal; Otherwise, other customer groups of the focus content of the described screen display page and other customer groups similar to the behavior of described user terminal were paid close attention to by calculating in real time to obtain, determine the common focus of other customer groups, and be shown to described user terminal using described common focus as the content association recommended to described user terminal.
Wherein, the screen action of changing of user terminal comprises rolling or the sliding action that user changes screen display content of pages, described according to user's rolling and sliding action, and the content of acquisition user current display page, specifically refers to the content that the current display screen of user can show.Due to the difference of screen resolution size, the content that each user screen page can demonstrate is not quite similar, and need according to ticker position here, screen resolution calculates the content gone out shown by active user's screen.
On the other hand, the present invention also provides a kind of content association to represent system in real time, comprising:
Screen display contents acquiring unit, for changing screen action, the content of the current screen display page of user in real terminal according to user terminal;
Focus content determining unit, the content for the user terminal current screen display page obtained according to described screen display contents acquiring unit determines the focus content of the described screen display page;
Related information buffer unit, for associatedly storing the focus content of the described screen display page and the user click on content at the described screen display page;
Whether cache information administrative unit, have for judging according to the focus content of the described screen display page cache information be associated with the focus content of the described screen display page in described related information buffer unit; If had, obtain described cache information also as the content association recommended to described user terminal; Otherwise, other customer groups of the focus content of the described screen display page and other customer groups similar to the behavior of described user terminal were paid close attention to by calculating in real time to obtain, determine the common focus of other customer groups, and using described common focus as the content association recommended to described user terminal;
Content association represents unit, for the content association recommended to described user terminal being shown to described user terminal.
In order to realize above-mentioned and relevant object, will describe in detail and the feature particularly pointed out in the claims after one or more aspect of the present invention comprises.Explanation below and accompanying drawing describe some illustrative aspects of the present invention in detail.But what these aspects indicated is only some modes that can use in the various modes of principle of the present invention.In addition, the present invention is intended to comprise all these aspects and their equivalent.
Accompanying drawing explanation
By reference to the content below in conjunction with the description of the drawings and claims, and understand more comprehensively along with to of the present invention, other object of the present invention and result will be understood and easy to understand more.In the accompanying drawings:
Fig. 1 utilizes the crawl of traditional hidden customer behavioral data to recommend the schematic flow sheet of content association for user;
Fig. 2 is the schematic flow sheet according to the real-time exhibiting method of the content association of the embodiment of the present invention;
Fig. 3 is rolling or carrying out the schematic flow sheet that content association represents in real time under slide according to the embodiment of the present invention;
Fig. 4 is the specific implementation process schematic of the related information cache module according to the embodiment of the present invention;
Fig. 5 is the logical organization schematic diagram representing system according to the content association of the embodiment of the present invention in real time.
Label identical in all of the figs indicates similar or corresponding feature or function.
Embodiment
Wherein, the screen action of changing of user terminal comprises rolling or the sliding action that user changes screen display content of pages, can be realized by the input media such as mouse or touch-screen.Such as, user's utilize mouse roller or mouse to pull when using PC browser the operation that diverse location content in a webpage checked by roller bearing, user uses the equipment slip pages such as touch-screen to check the content etc. of diverse location in mobile device such as use mobile phone, panel computer etc.
Wherein, calculate in real time to obtain and paid close attention to other customer groups of this focus content and other customer groups similar to this user behavior, thus obtain the common focus of other customer groups; Its specific implementation mainly comprises and obtains nearest-neighbors (comprising the customer group of paying close attention to this focus content and the similar customer group of behavior) and from the joint act nearest-neighbors, find that user may interested content.Wherein, utilize the customer group of focus content to obtain the maximally related content of follow focus content, and the customer group utilizing behavior similar obtain with the maximally related content of this user.
Particularly, exemplarily, Fig. 3 shows and is rolling or carrying out the schematic flow sheet that content association represents in real time under slide.As shown in Figure 3, user according to after browsing and needing to open a URL page (step S310), first obtain the content of user terminal current display page, specifically the finger user current display screen content (S320) that can show.Due to the screen resolution of each user terminal and the difference of screen size, the lower content that can demonstrate of each user screen page is not quite similar, and can calculate the content gone out shown by active user's screen according to ticker position, screen resolution.
Then, in step S330, pay close attention to according to obtained current page displaying contents acquisition user
Focus content, specifically refers to the position that user most possibly focuses under a page.Due to the uncertainty of the focus that diversity and the user of the content of the page pay close attention to, the focus that user pays close attention in a page is not what be evenly distributed, but becomes log-Normal distribution.The sight line distribution that user browses a webpage can carry out matching by the click action of user, user's click location is identical with the focus that user pays close attention to, so utilize clickstream data and the click location information of user, effectively can simulate user to distribute in different page sight line, thus utilize probability theory to find the focus that user most possibly pays close attention to.
Along with the correcting of webpage design changes, the focus distribution that user pays close attention to likely can change, and utilizes the approximating method of real-time clickstream data, can obtain focus distribution the most accurately in real time.Its circular is, supposes that the focus probability that user pays close attention to can utilize following log-Normal to distribute, needs here to utilize Multivariate Log-Normal to distribute:
F ( X , D , μ ) = ( 2 Π ) - P 2 * | D | - 1 2 * [ x 1 , x 2 , . . . x P ] - 1 * Exp ( - ( ln X - μ ) ′ D - 1 ( ln X - μ ) 2 )
Wherein, P is the dimension (within display screen, the coordinate of dimension to be 2, X the be screen point wherein lower left corner is initial point (0,0)) of X, D and μ is the parameter of X probability distribution equation respectively, ln X=[ln x 1, ln x 2... ln x p].So the log-normal on screen (2 dimension space) is distributed as:
F ( x , y ) = ( 2 Π ) - 1 * | D | - 1 2 * [ x , y ] - 1 * Exp ( - ( [ ln x , ln y ] - μ ) ′ D - 1 ( [ ln x , ln y ] - μ ) 2 )
Can find from above-mentioned formula, the probability distribution graph of log-normal depends on two parameter D and μ, so the Function Fitting of log-normal, and according to existing user's click location, estimate the parameter in above-mentioned formula, obtain with maximum likelihood evaluation method herein:
If existing subscriber n click coordinate collection is [(x 1, y 1), (x 2, y 2) ... (x n, y n)], calculate mean value and the variance of this set respectively,
x ‾ = Σ i x i n , y ‾ = Σ i y i n
s xx = var ( x ) = Σ i ( x i - x ‾ ) 2 / n , s yy = var ( y ) = Σ i ( y i - y ‾ ) 2 / n
s xy = s yx = var ( x , y ) = Σ i ( x i - x ‾ ) ( y i - y ‾ ) / n
Then parameter D can utilize formula estimation with μ and obtain:
μ = [ μ x , μ y ] = [ exp ( x ‾ + s xx 2 2 ) , exp ( y ‾ + s yy 2 2 ) ]
D = D xx D xy D xy D yy = exp ( 2 x ‾ + s xx 2 2 ( exp ( s xx 2 ) - 1 ) exp [ ( x ‾ + y ‾ ) + ( s xx 2 + s yy 2 ) ] 2 ( exp ( s xy 2 ) - 1 ) exp [ ( x ‾ + y ‾ ) + ( s xx 2 + s yy 2 ) 2 ( exp ( s xy 2 ) - 1 ) exp ( 2 y ‾ + s yy 2 2 ( exp ( s yy 2 ) - 1 )
Utilize the log-Nomal function of above-mentioned matching, just can obtain the focus probability distribution that user's screen may be paid close attention to, the position of maximum probability is exactly the position that user's most probable is paid close attention to.
After the focus content obtaining user's concern, judge whether there is the cache information (step S340) be associated with this focus content further in focus information association buffer memory; If had, then from focus information association buffer memory, obtain cache information (step S351); If no, calculate in real time to obtain and paid close attention to other customer groups (S352) of this focus content and other customer groups (S353) similar to this user behavior, thus obtain the common focus of other customer groups.
Wherein, in focus information association buffer memory, judge whether the cache information be associated with this focus content, its Main Function is the acquisition speed in order to improve content recommendation.Due to roll or slip correlation recommendation very high for real-time requirement, if the content association recommended can not push in time be presented to user, screen display content is probably rolled or is slided into other positions of the page by user, cause the content of recommending and the content of current display to exist content that time delay or user cannot view recommendation, in order to solve this problem, related information cache module is adopted to improve the acquisition speed of recommendation information.
S360: inquire about according to above-described storage organization, inquires according to focus information the content association that history clicked, and carries out down sequence according to number of clicks;
S370: the recommendation index according to the content association of comparison method discovery carries out sequencing display, the content association that display is recommended, its particular content is carry out sequencing display (the higher sequence of recommendation index is more forward) according to the recommendation index of the content association of comparison method discovery, the content association simultaneously shown can not produce change in location along with the rolling slide of user, and its content can be presented at the current page of user all the time;
S380: the focus related content that it estimates according to system recommendation, user finds oneself interested content recommendation and clickthrough checks its detail;
S390: judge that user's slides/rolls operates, specifically comprising user's utilize mouse roller or mouse to pull when using PC browser the operation that diverse location content in a webpage checked by roller bearing, also comprising user and using the equipment slip pages such as touch-screen to check the content of diverse location in mobile device such as use mobile phone, panel computer etc.If detect that slides/rolls operates, repeat above step, otherwise continue to carry out active user slides/rolls operation detection.
Related information cache module is used to store the focus content of user's concern and judge whether focus content has the related information of buffer memory; If had, obtain cache information; If no, calculate in real time to obtain and paid close attention to other customer groups of this focus content and other customer groups similar to this user behavior, thus obtain the common focus of other customer groups.Adopt related information cache module to improve the acquisition speed of recommendation information in the present invention, the specific implementation step of this module is mainly divided into cache information to write and cache information inquiry.Fig. 4 shows the specific implementation step of the related information cache module according to the embodiment of the present invention.
As shown in Figure 4, as follows according to the process of the related information buffer memory of the related information cache module of the embodiment of the present invention and related information inquiry:
Step S411-S412: cache information is write, mainly according to user, behavior is clicked for the history of content recommendation, its concrete steps can be described as, when user's rolling view page, the focus that system may be paid close attention to according to the user estimated recommends out related content, user finds that oneself interested content recommendation can check its detail by clickthrough, at this moment (one record comprises focus content as Key to follow the focus content of the current concern of user to carry out association store the content clicked, click on content is as Value), add up the history number of clicks (comprising the number of clicks of other users) of this click on content simultaneously, after number of clicks exceedes certain threshold values (such as more than 10 times), just using this association store content, (focus content is as Key, click on content and its number of clicks are as Value) put in buffer memory and obtain in order to the fast query of content recommendation, simultaneously in order to ensure that cache size can not unrestrictedly expand, after buffer memory capacity exceedes certain threshold values, the record that number of clicks is minimum can remove from buffer memory,
Step S420: cache information is inquired about, and mainly inquires about according to above-described storage organization, inquires according to focus information the content association that history clicked, and carries out down sorting according to number of clicks.

Claims (8)

1. the real-time exhibiting method of content association, comprising:
Screen action is changed, the content of the current screen display page of user in real terminal according to user terminal; Wherein, the screen action of changing of user terminal comprises rolling or the sliding action that user changes screen display content of pages;
The focus content of the described screen display page is determined according to the content of the obtained user terminal current screen display page;
Judge whether and the cache information that the focus content of the described screen display page is associated according to the focus content of the described screen display page; If had, obtain described cache information and be shown to described user terminal as the content association recommended to described user terminal; Otherwise,
Other customer groups of the focus content of the described screen display page and other customer groups similar to the behavior of described user terminal were paid close attention to by calculating in real time to obtain, determine the common focus of other customer groups, and be shown to described user terminal using described common focus as the content association recommended to described user terminal.
2. the real-time exhibiting method of content association as claimed in claim 1, wherein, the process according to the rolling of user terminal or the content of sliding action acquisition user current display page comprises:
The content of the current screen display page of described user terminal is determined according to the screen resolution of ticker position and described user terminal in the described screen display page.
3. the real-time exhibiting method of content association as claimed in claim 1, wherein, the described content according to the obtained user terminal current screen display page determines that the process of the focus content of the described screen display page comprises:
Utilize clickstream data and the click location information of user terminal, go out user according to the log-Normal Function Fitting of matching and distribute in the sight line of the current screen display page;
Utilize probability theory using the focus content of position maximum for sight line distribution probability as the determined described screen display page.
4. the real-time exhibiting method of content association as claimed in claim 1, wherein, after determining the focus content of the described screen display page according to the content of the obtained user terminal current screen display page, also comprises:
By the focus content of the described screen display page and user in the click on content of the described screen display page associatedly stored in buffer memory.
5. the real-time exhibiting method of content association as claimed in claim 4, wherein, obtains described cache information and comprises as the process that the content association recommended to described user terminal is shown to described user terminal:
Obtain described cache information, described cache information comprises the focus content of the screen display page of association store and the user click on content at the described screen display page;
Sort according to the number of clicks of described focus content to the content association that the history inquired was clicked;
In described sequence, the focus content of the predetermined number that number of clicks is the highest is shown to described user terminal as the content association recommended to described user terminal.
6. the real-time exhibiting method of content association as claimed in claim 1, wherein, real-time calculating obtains and paid close attention to other customer groups of the focus content of the described screen display page and other customer groups similar to the behavior of described user terminal, determines that the process of the common focus of other customer groups comprises:
Obtain nearest-neighbors and find the interested content of user from the joint act nearest-neighbors, described nearest-neighbors comprises the customer group of paying close attention to described focus content and the similar customer group of behavior;
According to the user terminal quantity of co-browse, described focus content is sorted; In described sequence, the focus content of the predetermined number that the user terminal quantity of co-browse is the highest is as described common focus; Wherein,
Utilize the customer group of focus content to obtain and the maximally related content of described focus content, the customer group utilizing behavior similar obtains with the maximally related content of this user.
7. the real-time exhibiting method of content association as claimed in claim 1, wherein, described in be shown to the recommendation of described user terminal content association be presented at all the time on the current screen display page of user terminal.
8. content association represents a system in real time, comprising:
Screen display contents acquiring unit, for changing screen action, the content of the current screen display page of user in real terminal according to user terminal; Wherein, the screen action of changing of user terminal comprises rolling or the sliding action that user changes screen display content of pages;
Focus content determining unit, the content for the user terminal current screen display page obtained according to described screen display contents acquiring unit determines the focus content of the described screen display page;
Related information buffer unit, for associatedly storing the focus content of the described screen display page and the user click on content at the described screen display page;
Whether cache information administrative unit, have for judging according to the focus content of the described screen display page cache information be associated with the focus content of the described screen display page in described related information buffer unit; If had, obtain described cache information also as the content association recommended to described user terminal; Otherwise, other customer groups of the focus content of the described screen display page and other customer groups similar to the behavior of described user terminal were paid close attention to by calculating in real time to obtain, determine the common focus of other customer groups, and using described common focus as the content association recommended to described user terminal;
Content association represents unit, for the content association recommended to described user terminal being shown to described user terminal.
CN201210524614.0A 2012-12-07 2012-12-07 The real-time exhibiting method of content association and system Active CN103019550B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210524614.0A CN103019550B (en) 2012-12-07 2012-12-07 The real-time exhibiting method of content association and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210524614.0A CN103019550B (en) 2012-12-07 2012-12-07 The real-time exhibiting method of content association and system

Publications (2)

Publication Number Publication Date
CN103019550A CN103019550A (en) 2013-04-03
CN103019550B true CN103019550B (en) 2015-08-26

Family

ID=47968208

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210524614.0A Active CN103019550B (en) 2012-12-07 2012-12-07 The real-time exhibiting method of content association and system

Country Status (1)

Country Link
CN (1) CN103019550B (en)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104519321A (en) * 2014-12-22 2015-04-15 深圳市科漫达智能管理科技有限公司 Method and device for checking monitoring video
CN105989045A (en) * 2015-02-04 2016-10-05 华为技术有限公司 Method, device and system for recommending persuasion content
CN106294489B (en) * 2015-06-08 2022-09-30 北京三星通信技术研究有限公司 Content recommendation method, device and system
CN104899306B (en) * 2015-06-12 2019-06-28 百度在线网络技术(北京)有限公司 Information processing method, information display method and device
US10275716B2 (en) * 2015-07-30 2019-04-30 Microsoft Technology Licensing, Llc Feeds by modelling scrolling behavior
CN106469153A (en) * 2015-08-14 2017-03-01 阿里巴巴集团控股有限公司 The method and apparatus carrying out information pushing in the page
CN106204060B (en) * 2016-06-28 2018-04-13 腾讯科技(深圳)有限公司 The method and device that user is divided to cluster realized by computer system
CN106202446B (en) * 2016-07-14 2020-02-07 刘志军 Webpage information display method and system
CN106850951B (en) * 2016-12-19 2020-04-28 北京五八信息技术有限公司 User interest module display method and device
CN106886594B (en) * 2017-02-21 2020-06-02 北京百度网讯科技有限公司 Method and device for displaying information
CN109388737B (en) * 2017-08-03 2023-03-31 腾讯科技(北京)有限公司 Method and device for sending exposure data of content item and storage medium
CN108196926B (en) * 2017-12-29 2021-03-26 努比亚技术有限公司 Platform content identification method, terminal and computer readable storage medium
CN108932091B (en) * 2018-06-06 2022-07-22 北京搜狗科技发展有限公司 Data processing method and device and data processing device
CN109039869B (en) * 2018-08-16 2020-05-05 北京达佳互联信息技术有限公司 Social communication method and device, electronic equipment and storage medium
CN109710146B (en) * 2018-12-07 2022-03-11 北京小米移动软件有限公司 Document display method and device
CN110472154B (en) * 2019-08-26 2022-03-29 秒针信息技术有限公司 Resource pushing method and device, electronic equipment and readable storage medium
CN111400628B (en) * 2020-03-12 2023-04-07 腾讯科技(深圳)有限公司 Information propagation method, device, equipment and medium
CN113676531B (en) * 2021-08-16 2023-10-31 北京百度网讯科技有限公司 E-commerce flow peak clipping method and device, electronic equipment and readable storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6654735B1 (en) * 1999-01-08 2003-11-25 International Business Machines Corporation Outbound information analysis for generating user interest profiles and improving user productivity
CN101079824A (en) * 2006-06-15 2007-11-28 腾讯科技(深圳)有限公司 A generation system and method for user interest preference vector
CN101504671A (en) * 2009-03-05 2009-08-12 阿里巴巴集团控股有限公司 Visible processing method, apparatus and system for web page access behavior of users
CN101650634A (en) * 2008-08-11 2010-02-17 索尼株式会社 Display apparatus, display method, and program
CN101930475A (en) * 2010-09-14 2010-12-29 中兴通讯股份有限公司 Web page display method and browser
CN102063456A (en) * 2010-09-17 2011-05-18 百度在线网络技术(北京)有限公司 Method for positioning to optic center of webpage automatically and device
CN102087582A (en) * 2011-01-27 2011-06-08 广东威创视讯科技股份有限公司 Automatic scrolling method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7536417B2 (en) * 2006-05-24 2009-05-19 Microsoft Corporation Real-time analysis of web browsing behavior

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6654735B1 (en) * 1999-01-08 2003-11-25 International Business Machines Corporation Outbound information analysis for generating user interest profiles and improving user productivity
CN101079824A (en) * 2006-06-15 2007-11-28 腾讯科技(深圳)有限公司 A generation system and method for user interest preference vector
CN101650634A (en) * 2008-08-11 2010-02-17 索尼株式会社 Display apparatus, display method, and program
CN101504671A (en) * 2009-03-05 2009-08-12 阿里巴巴集团控股有限公司 Visible processing method, apparatus and system for web page access behavior of users
CN101930475A (en) * 2010-09-14 2010-12-29 中兴通讯股份有限公司 Web page display method and browser
CN102063456A (en) * 2010-09-17 2011-05-18 百度在线网络技术(北京)有限公司 Method for positioning to optic center of webpage automatically and device
CN102087582A (en) * 2011-01-27 2011-06-08 广东威创视讯科技股份有限公司 Automatic scrolling method and device

Also Published As

Publication number Publication date
CN103019550A (en) 2013-04-03

Similar Documents

Publication Publication Date Title
CN103019550B (en) The real-time exhibiting method of content association and system
US11354584B2 (en) Systems and methods for trend aware self-correcting entity relationship extraction
CN103886074B (en) Commercial product recommending system based on social media
CN110222272A (en) A kind of potential customers excavate and recommended method
CN103309967B (en) Collaborative filtering method based on similarity transmission and system
Yu The dynamic competitive recommendation algorithm in social network services
CN103617540A (en) E-commerce recommendation method of tracking user interest changes
CN105894332A (en) Commodity recommendation method, device and system based on user behavior analysis
CN102542490A (en) Commodity recommendation method based on model matching
CN109325179A (en) A kind of method and device that content is promoted
CN102479366A (en) Commodity recommending method and system
CN102760124A (en) Pushing method and system for recommended data
CN103914484A (en) Method and device for generating page contents
CN101968802A (en) Method and equipment for recommending content of Internet based on user browse behavior
CN105976229A (en) Collaborative filtering algorithm based on user and project mixing
CN108198045A (en) The design method of mixing commending system based on e-commerce website data mining
CN103186565A (en) Method and device for judging user preference according to web browsing behavior of user
WO2014209758A1 (en) Selecting content based on performance of a content slot
CN104616178A (en) Recommendation method of E-commerce goods based on big-data multi-label classification method
CN105677867A (en) User label generation method and device
CN104992352A (en) Individualized resource retrieval method
JP5738785B2 (en) Recommendation program, apparatus and method for recommending critics that meet user preferences
CN103365876A (en) Method and device for generating network operation auxiliary information based on relation maps
WO2019184204A1 (en) Resource information recommendation method and resource information recommendation system
CN116703485B (en) Advertisement accurate marketing method and system based on big data

Legal Events

Date Code Title Description
C06 Publication
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