CN102073717A - Home page recommending method for orienting vertical e-commerce website - Google Patents
Home page recommending method for orienting vertical e-commerce website Download PDFInfo
- Publication number
- CN102073717A CN102073717A CN2011100021362A CN201110002136A CN102073717A CN 102073717 A CN102073717 A CN 102073717A CN 2011100021362 A CN2011100021362 A CN 2011100021362A CN 201110002136 A CN201110002136 A CN 201110002136A CN 102073717 A CN102073717 A CN 102073717A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- visit
- brought
- product
- 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.)
- Pending
Links
Images
Abstract
The invention relates to a home page recommending method for orienting a vertical e-commerce website, comprising the following steps: collecting the access drag-in information and ordering product information of a user through a script (such as a JavaScript); computing the correlation degree of each dimension of the access drag-in information and each dimension of the ordering product information as a recommending foundation according to history data; and computing the correlation degree of the user and all products according to the access drag-in information of the user and the correlation degree matrix obtained by the history data when a new user accesses the website home page, and recommending N products with the highest correlation degree. The method can be suitable for the requirement of special scene that the new user of the vertical e-commerce website has no history behavior information data (such as history score, browsing and purchasing behaviors) and also no vital statistics information data in a majority condition. The products in the vertical e-commerce website are the same type of goods, and the ratio of the new user in the user of the vertical e-commerce is very high. The method is beneficial.
Description
Technical field
The invention belongs to the personalized recommendation field, the new user of vertical electronics website is carried out homepage recommend.The method of recommending is by JavaScript script collection user " information is brought in visit into ", calculates the degree of correlation of this user and every product in conjunction with " information is brought in visit into---product information places an order " correlation matrix again, recommends the highest N spare product of the degree of correlation.
Background technology
Along with the continuous development of ecommerce, type of merchandize and number increase fast, and often the user need take a long time to find the commodity of oneself liking.In order to improve user's satisfaction, reduce the customer loss problem in browsing search procedure, personalized recommendation method arises at the historic moment.
The method that present personalized recommendation system mainly adopts is information filtering and collaborative filtering recommending.Information filtering is by gathering the browsing information before the user, and purchase information is recommended the product of the similar content of user.Collaborative filtering is by gathering or calculate user's score information, is divided into based on user's collaborative filtering with based on two kinds of the collaborative filterings of product.Collaborative filtering based on the user calculates similar users according to score information, the product of recommending similar users to buy.Collaborative filtering based on product is given the user according to score information calculating with the similar Products Show of product that the user bought.But all there are new customer problem in information filtering and collaborative filtering, and the new user without any historical data is difficult to effectively recommend.
New user recommends to insert the personal information (age when requiring the user to register, sex, occupation, hobby etc.) or the user is carried out survey obtain related data and recommend again, but these two kinds of methods are owing to need extra user's operation, user experience is relatively poor, usually causes user's loss.
Summary of the invention
Technical matters to be solved by this invention is: propose the homepage recommend method towards the new user of vertical e-commerce website, commodity under the vertical e-commerce website all are the commodity of same type, new user's ratio is very high among the user of vertical ecommerce, and a lot of new users just register login when placing an order purchase.The new user of a vertical e-commerce website had not both had historical behavior information data (behaviors such as purchase are browsed in historical scoring), most of situation does not have the population statistical information data (age yet, sex, occupation), so traditional recommend method is difficult to satisfy the needs of this special screne.
Technical scheme of the present invention is: a kind of homepage recommend method at vertical e-commerce website.Gather user " information is brought in visit into " and " product information places an order " by the JavaScript script.Calculate the degree of correlation of " information is brought in visit into " each dimension and " product information places an order " each dimension according to historical data.When a new user capture website homepage, obtain the degree of correlation of this user and all products according to this user " information is brought in visit into " with by the relatedness computation that historical data obtains, recommend the highest N spare product of the degree of correlation.
A kind of homepage recommend method towards the new user of vertical e-commerce website is characterized in that concrete steps are as follows:
1) gathers user's " information is brought in visit into " and " product information places an order " by the JavaScript script, set up historical data base; (" information is brought in visit into " comprises user's ground domain information, access time information, browser information, operation system information, system language information, access mode information and presumable search keyword information etc.; " product information places an order " comprises product colour, style, and price, material, brand etc. :)
2) " information is brought in visit into " and " product information places an order " carried out pre-service; Each user " information " being treated to the set of a set of keyword, " product information that places an order is brought in visit into, and " be treated to the set of another set of keyword, this two set of keyword is common to constitute a record, deposits into historical data base;
3) according to all record calculating " information is brought in visit into " each dimensions in the historical data base and the degree of correlation of " product information places an order " each dimension, obtain " information is brought in visit into---and product information places an order " correlation matrix; Each dimension of " information is brought in visit into " and " product information places an order " is represented a key word, and correlation matrix is the two-dimensional matrix of a m * n, the number of dimensions of m representative " information is brought in visit into ", the number of dimensions of n representative " product information places an order ";
4) when a new user capture website homepage, obtain this user " information is brought in visit into " by the JavaScript script, and be treated to the set of a set of keyword;
5) if comprise the keyword of search in this user " information is brought in visit into ", according to historical data base, do coupling with the keyword of search and the feature key word of product information, the purpose of coupling is the set that the product collection is kept to approximately the product that meets this user search keyword by all over products; If do not comprise the key word of search, then directly enter step (6);
6) calculate the degree of correlation that this user and product are concentrated every product according to this user " information is brought in visit into " with by the correlation matrix that historical data base obtains, all products by the descending ordering of the degree of correlation, are thought that this user recommends the highest preceding N spare product of the degree of correlation.
The invention has the beneficial effects as follows: the present invention can be applicable to that the new user of vertical e-commerce website had not both had historical behavior information data (behaviors such as purchase are browsed in historical scoring), and most of situation does not have the needs of different scenes such as population statistical information data yet.Commodity under the vertical e-commerce website all are the commodity of same type, and new user's ratio is very high among the user of vertical ecommerce, and the inventive method is useful.
Description of drawings
Fig. 1 is the process flow diagram at the homepage recommend method of vertical e-commerce website.
Embodiment
Consult Fig. 1, the present invention solves the problem of new user without any data by " information is brought in visit into " of gathering new user, and calculate the degree of correlation that new user and product are concentrated product in conjunction with the correlation matrix of " information is brought in visit into---product information places an order " that obtain by historical data training, recommend the highest N spare product of the degree of correlation.Its concrete steps are as follows:
1) gathers user's " information is brought in visit into " and " product information places an order " by the JavaScript script, set up historical data base." information is brought in visit into " comprises user's ground domain information (as: China-Jiangsu-Nanjing), access time information (as: 2010-12-1 08:00), browser information (as: IE 6.0), operation system information (as: Win32), system language information (as: English), access mode information (as: by Google search visit) and presumable search keyword information etc." product information places an order " comprises product colour, style, price, material, brand etc.;
" information is brought in visit into " can collect by following JavaScript script:
var?x?=?navigator;
Var Name=x.appName; // browser
Var Version=parseFloat (x.appVersion); // browser version
Var Platform=x.platform; // operating system
Var SystemLanguage=x.systemLanguage x.systemLanguage:x.language; // system language
Var Refer=encodeURIComponent (encodeURIComponent (document.referrer)); // access mode
var?Str=new?Date();
Var Date=Str.getTime (); // the time
Var country=geoip_country_name (); // country
Var region=geoip_region_name (); // area
Var city=geoip_city (); // city
" product information places an order " can obtain by the product information table in the Query Database.
2) " information is brought in visit into " and " product information places an order " carried out pre-service; Each user " information " being treated to the set of a set of keyword, " product information that places an order is brought in visit into, and " be treated to the set of another set of keyword, this two set of keyword is common to constitute a record, deposits into historical data base;
Be recorded as such as one in the historical data base after the pre-service:
Information is brought in visit into: (Jiangsu, Nanjing, Dec, the morning, IE, Win32, English, Google, glasses)
Product information places an order: (black, sunglasses, 100-150 unit, plastics, precious appearance)
3) degree of correlation of calculating " information is brought in visit into " each dimension and " product information places an order " each dimension, obtain " information is brought in visit into---and product information places an order " correlation matrix; Each dimension of " information is brought in visit into " and " product information places an order " is represented a key word, and correlation matrix is the two-dimensional matrix of a m * n, the number of dimensions of m representative " information is brought in visit into ", the number of dimensions of n representative " product information places an order ";
The computing method of correlation matrix are as follows:
Suppose that " information is brought in visit into " has m dimension, " product information places an order " has n dimension, correlation matrix be A (m, n).A
I, jThe degree of correlation of representative " information is brought in visit into " i dimension and " product information places an order " j dimension.Total N bar record in the historical data base, every record is made up of " information is brought in visit into " and " product information places an order ".A
I, jComputing method be:
4) when a new user capture website homepage, obtain this user's " information is brought in visit into " and be treated to the set of a set of keyword by the JavaScript script;
The same step of acquisition method (1).
5) if comprise the key word of search in this user " information is brought in visit into ", do coupling with the key word and the product information of search, the product collection is kept to approximately the set of the product that meets this user search key word by all over products; If do not comprise search key, then directly enter step (6).As: scene is a notebook online sales website, user search be " association's notebook ", by search key and product information are done coupling, the product collection is kept to approximately the notebook of all association's brands by whole notebooks.
6) calculate the degree of correlation that this user and product are concentrated every product according to this user " information is brought in visit into " with by the correlation matrix that historical data base obtains, all products by the descending ordering of the degree of correlation, are thought that this user recommends the highest preceding N spare product of the degree of correlation.
The relatedness computation method is as follows:
Suppose that " information is brought in visit into---product information places an order " correlation matrix is
A(m, n), active user's " information is brought in visit into " is the vector of m with length
UExpression.If active user " information is brought in visit into " comprises i the dimension of " information is brought in visit into ",
U i=1; Otherwise
U i=0.Certain part product length that product is concentrated is the vector of n
VExpression.If " product information " of this product comprises i the dimension of " product information places an order ",
V i=1; Otherwise
V i=0.Then the relatedness computation method of active user and this product is:
The degree of correlation=
U * A * V T
Claims (3)
1. the homepage recommend method towards vertical e-commerce website is characterized in that " information is brought in visit into " and " product information places an order " by script (as JavaScript) collection user; The degree of correlation of calculating " information is brought in visit into " each dimension and " product information places an order " each dimension according to historical data is as recommending the basis; When a new user capture website homepage, calculate the degree of correlation of this user and all products according to this user " information is brought in visit into " with by the correlation matrix that historical data obtains, recommend the highest N spare product of the degree of correlation.
2. a kind of homepage recommend method towards the new user of vertical e-commerce website according to claim 1 is characterized in that concrete steps are as follows:
1) gathers user's " information is brought in visit into " and " product information places an order " by the JavaScript script, set up historical data base; " information is brought in visit into " comprises user's ground domain information, access time information, browser information, operation system information, system language information, access mode information and presumable search keyword information etc.; " product information places an order " comprises product colour, style, and price, material, brand etc.:
2) " information is brought in visit into " and " product information places an order " carried out pre-service; Each user " information " being treated to the set of a set of keyword, " product information that places an order is brought in visit into, and " be treated to the set of another set of keyword, this two set of keyword is common to constitute a record, deposits into historical data base;
3) according to all record calculating " information is brought in visit into " each dimensions in the historical data base and the degree of correlation of " product information places an order " each dimension, obtain " information is brought in visit into---and product information places an order " correlation matrix; Each dimension of " information is brought in visit into " and " product information places an order " is represented a key word, and correlation matrix is the two-dimensional matrix of a m * n, the number of dimensions of m representative " information is brought in visit into ", the number of dimensions of n representative " product information places an order ";
4) when a new user capture website homepage, obtain this user " information is brought in visit into " by the JavaScript script, and be treated to the set of a set of keyword;
5) if comprise the keyword of search in this user " information is brought in visit into ", according to historical data base, do coupling with the keyword of search and the feature key word of product information, the purpose of coupling is the set that the product collection is kept to approximately the product that meets this user search keyword by all over products; If do not comprise the key word of search, then directly enter step (6);
6) calculate the degree of correlation that this user and product are concentrated every product according to this user " information is brought in visit into " with by the correlation matrix that historical data base obtains, all products by the descending ordering of the degree of correlation, are thought that this user recommends the highest preceding N spare product of the degree of correlation.
3. the homepage recommend method towards vertical e-commerce website according to claim 2, the computing method that it is characterized in that calculating correlation matrix are as follows:
Suppose that " information is brought in visit into " has m dimension, " product information places an order " has n dimension, correlation matrix be A (m, n); A
I, jThe degree of correlation of representative " information is brought in visit into " i dimension and " product information places an order " j dimension; Total N bar record in the historical data base, every record is made up of " information is brought in visit into " and " product information places an order "; A
I, jComputing method be:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100021362A CN102073717A (en) | 2011-01-07 | 2011-01-07 | Home page recommending method for orienting vertical e-commerce website |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100021362A CN102073717A (en) | 2011-01-07 | 2011-01-07 | Home page recommending method for orienting vertical e-commerce website |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102073717A true CN102073717A (en) | 2011-05-25 |
Family
ID=44032256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100021362A Pending CN102073717A (en) | 2011-01-07 | 2011-01-07 | Home page recommending method for orienting vertical e-commerce website |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102073717A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289509A (en) * | 2011-08-31 | 2011-12-21 | 南京大学 | Method for obtaining, migrating and using website data |
| CN102426686A (en) * | 2011-09-29 | 2012-04-25 | 南京大学 | Internet information product recommending method based on matrix decomposition |
| CN102508870A (en) * | 2011-10-10 | 2012-06-20 | 南京大学 | Individualized recommending method in combination of rating data and label data |
| CN102629257A (en) * | 2012-02-29 | 2012-08-08 | 南京大学 | Commodity recommending method of e-commerce website based on keywords |
| CN102663626A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Collaborative filtering recommended method based on provincial characteristics |
| CN102866992A (en) * | 2011-07-04 | 2013-01-09 | 阿里巴巴集团控股有限公司 | Method and device for displaying product information in webpage |
| CN102999493A (en) * | 2011-09-08 | 2013-03-27 | 百度在线网络技术（北京）有限公司 | Method and device for achieving video resource recommendation |
| CN103020855A (en) * | 2012-12-11 | 2013-04-03 | 北京京东世纪贸易有限公司 | Bad commodity distinguishing method and system based on user purchasing behavior |
| CN103034640A (en) * | 2011-09-30 | 2013-04-10 | 腾讯科技（深圳）有限公司 | Analysis method and system of page information |
| CN103093369A (en) * | 2011-11-03 | 2013-05-08 | 阿里巴巴集团控股有限公司 | Method and device for offering matched product based on correlation degree between products |
| CN103198080A (en) * | 2012-01-10 | 2013-07-10 | 纽海信息技术（上海）有限公司 | Homepage display system and method |
| CN103559623A (en) * | 2013-09-24 | 2014-02-05 | 浙江大学 | Personalized product recommendation method based on combined non-negative matrix decomposition |
| CN103885987A (en) * | 2012-12-21 | 2014-06-25 | 中国移动通信集团公司 | Music recommendation method and system |
| CN104050174A (en) * | 2013-03-12 | 2014-09-17 | 腾讯科技（深圳）有限公司 | Personalized page generating method and device |
| CN105975472A (en) * | 2015-12-09 | 2016-09-28 | 乐视网信息技术（北京）股份有限公司 | Method and device for recommendation |
| CN103093369B (en) * | 2011-11-03 | 2016-12-14 | 阿里巴巴集团控股有限公司 | A kind of method and device that collocation product is provided based on the degree of association between product |
| WO2017012406A1 (en) * | 2015-07-22 | 2017-01-26 | 中兴通讯股份有限公司 | Commodity recommending method and system |
| CN106462615A (en) * | 2014-06-03 | 2017-02-22 | 索尼公司 | Information processing device, information presentation method, program, and system |
| CN106777962A (en) * | 2016-12-13 | 2017-05-31 | 天津迈沃医药技术股份有限公司 | A kind of medical information platform information analysis Application way and system |
| CN106850750A (en) * | 2016-12-26 | 2017-06-13 | 北京五八信息技术有限公司 | A kind of method and apparatus of real time propelling movement information |
| CN107609902A (en) * | 2017-08-28 | 2018-01-19 | 口碑(上海)信息技术有限公司 | The methods of exhibiting and device of a kind of targeted ads |
| CN107851115A (en) * | 2015-10-08 | 2018-03-27 | 谷歌有限责任公司 | By content mix into content stream |
| CN109324955A (en) * | 2018-09-14 | 2019-02-12 | 科大国创软件股份有限公司 | A kind of IT operational system interface creating method with intelligent recommendation function |
-
2011
- 2011-01-07 CN CN2011100021362A patent/CN102073717A/en active Pending
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102866992B (en) * | 2011-07-04 | 2015-12-02 | 阿里巴巴集团控股有限公司 | A kind of method and device showing product information in webpage |
| CN102866992A (en) * | 2011-07-04 | 2013-01-09 | 阿里巴巴集团控股有限公司 | Method and device for displaying product information in webpage |
| CN102289509A (en) * | 2011-08-31 | 2011-12-21 | 南京大学 | Method for obtaining, migrating and using website data |
| CN102999493A (en) * | 2011-09-08 | 2013-03-27 | 百度在线网络技术（北京）有限公司 | Method and device for achieving video resource recommendation |
| CN102999493B (en) * | 2011-09-08 | 2018-07-03 | 北京小度互娱科技有限公司 | A kind of method and apparatus for being used to implement video resource recommendation |
| CN102426686A (en) * | 2011-09-29 | 2012-04-25 | 南京大学 | Internet information product recommending method based on matrix decomposition |
| CN103034640A (en) * | 2011-09-30 | 2013-04-10 | 腾讯科技（深圳）有限公司 | Analysis method and system of page information |
| CN102508870B (en) * | 2011-10-10 | 2013-09-11 | 南京大学 | Individualized recommending method in combination of rating data and label data |
| CN102508870A (en) * | 2011-10-10 | 2012-06-20 | 南京大学 | Individualized recommending method in combination of rating data and label data |
| CN103093369A (en) * | 2011-11-03 | 2013-05-08 | 阿里巴巴集团控股有限公司 | Method and device for offering matched product based on correlation degree between products |
| CN103093369B (en) * | 2011-11-03 | 2016-12-14 | 阿里巴巴集团控股有限公司 | A kind of method and device that collocation product is provided based on the degree of association between product |
| CN103198080A (en) * | 2012-01-10 | 2013-07-10 | 纽海信息技术（上海）有限公司 | Homepage display system and method |
| CN103198080B (en) * | 2012-01-10 | 2017-11-24 | 北京京东尚科信息技术有限公司 | Homepage display system and method |
| CN102629257A (en) * | 2012-02-29 | 2012-08-08 | 南京大学 | Commodity recommending method of e-commerce website based on keywords |
| CN102663626A (en) * | 2012-04-26 | 2012-09-12 | 焦点科技股份有限公司 | Collaborative filtering recommended method based on provincial characteristics |
| CN102663626B (en) * | 2012-04-26 | 2015-10-28 | 焦点科技股份有限公司 | Based on the collaborative filtering recommending method of provincial characteristics |
| CN103020855A (en) * | 2012-12-11 | 2013-04-03 | 北京京东世纪贸易有限公司 | Bad commodity distinguishing method and system based on user purchasing behavior |
| WO2014089944A1 (en) * | 2012-12-11 | 2014-06-19 | 北京京东世纪贸易有限公司 | Method and system for identifying defective goods based on user purchasing behaviour |
| CN103020855B (en) * | 2012-12-11 | 2016-02-10 | 北京京东世纪贸易有限公司 | The method and system of bad commodity is identified based on user's buying behavior |
| CN103885987A (en) * | 2012-12-21 | 2014-06-25 | 中国移动通信集团公司 | Music recommendation method and system |
| WO2014139436A1 (en) * | 2013-03-12 | 2014-09-18 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for generating personalized page |
| CN104050174A (en) * | 2013-03-12 | 2014-09-17 | 腾讯科技（深圳）有限公司 | Personalized page generating method and device |
| CN104050174B (en) * | 2013-03-12 | 2018-10-02 | 腾讯科技（深圳）有限公司 | A kind of personal page generation method and device |
| CN103559623A (en) * | 2013-09-24 | 2014-02-05 | 浙江大学 | Personalized product recommendation method based on combined non-negative matrix decomposition |
| CN106462615A (en) * | 2014-06-03 | 2017-02-22 | 索尼公司 | Information processing device, information presentation method, program, and system |
| WO2017012406A1 (en) * | 2015-07-22 | 2017-01-26 | 中兴通讯股份有限公司 | Commodity recommending method and system |
| CN106709741A (en) * | 2015-07-22 | 2017-05-24 | 中兴通讯股份有限公司 | Commodity recommendation method and system |
| CN107851115A (en) * | 2015-10-08 | 2018-03-27 | 谷歌有限责任公司 | By content mix into content stream |
| WO2017096877A1 (en) * | 2015-12-09 | 2017-06-15 | 乐视控股（北京）有限公司 | Recommendation method and device |
| CN105975472A (en) * | 2015-12-09 | 2016-09-28 | 乐视网信息技术（北京）股份有限公司 | Method and device for recommendation |
| CN106777962A (en) * | 2016-12-13 | 2017-05-31 | 天津迈沃医药技术股份有限公司 | A kind of medical information platform information analysis Application way and system |
| CN106850750A (en) * | 2016-12-26 | 2017-06-13 | 北京五八信息技术有限公司 | A kind of method and apparatus of real time propelling movement information |
| CN106850750B (en) * | 2016-12-26 | 2020-11-10 | 北京五八信息技术有限公司 | Method and device for pushing information in real time |
| CN107609902A (en) * | 2017-08-28 | 2018-01-19 | 口碑(上海)信息技术有限公司 | The methods of exhibiting and device of a kind of targeted ads |
| CN109324955A (en) * | 2018-09-14 | 2019-02-12 | 科大国创软件股份有限公司 | A kind of IT operational system interface creating method with intelligent recommendation function |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102073717A (en) | Home page recommending method for orienting vertical e-commerce website | |
| Zhao et al. | Connecting social media to e-commerce: Cold-start product recommendation using microblogging information | |
| Wu et al. | Turning clicks into purchases: Revenue optimization for product search in e-commerce | |
| US9734258B2 (en) | Method and system of displaying cross-website information | |
| CN102629257B (en) | Commodity recommending method of e-commerce website based on keywords | |
| US9489688B2 (en) | Method and system for recommending search phrases | |
| US8301514B1 (en) | System, method, and computer readable medium for providing recommendations based on purchase phrases | |
| US9342791B2 (en) | Systems and methods for trend aware self-correcting entity relationship extraction | |
| CN103246980B (en) | Information output method and server | |
| CN107784066A (en) | Information recommendation method, device, server and storage medium | |
| CN103198118B (en) | A kind of commodity webpage retrogressive method and system | |
| CN105426528A (en) | Retrieving and ordering method and system for commodity data | |
| Siddiqui et al. | Web mining techniques in e-commerce applications | |
| CN106062743A (en) | Systems and methods for keyword suggestion | |
| CN106447463A (en) | Commodity recommendation method based on Markov decision-making process model | |
| Hasan et al. | Query suggestion for e-commerce sites | |
| JP6976207B2 (en) | Information processing equipment, information processing methods, and programs | |
| CN103325047A (en) | Device and method for guiding online shopping | |
| CN102542046A (en) | Book recommendation method based on book contents | |
| CN103744904B (en) | A kind of method and device that information is provided | |
| CN109299426A (en) | A kind of recommended method and device of accurate top information | |
| Kaminskas et al. | Product-seeded and basket-seeded recommendations for small-scale retailers | |
| US20160196579A1 (en) | Dynamic deep links based on user activity of a particular user | |
| TWI629652B (en) | Intelligent network marketing analysis and judgment method | |
| Lin et al. | A consumer review-driven recommender service for web e-commerce |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110525 |