CN104317945A - E-commerce website commodity recommending method on basis of search behaviors - Google Patents
E-commerce website commodity recommending method on basis of search behaviors Download PDFInfo
- Publication number
- CN104317945A CN104317945A CN201410606971.0A CN201410606971A CN104317945A CN 104317945 A CN104317945 A CN 104317945A CN 201410606971 A CN201410606971 A CN 201410606971A CN 104317945 A CN104317945 A CN 104317945A
- Authority
- CN
- China
- Prior art keywords
- commodity
- sum
- degree
- search
- relation
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Disclosed is an E-commerce website commodity recommending method on the basis of search behaviors. The E-commerce website commodity recommending method includes steps of computing correlation between user search keywords and purchased commodities as well as between user browse commodities and the purchased commodities through the correlation rule algorithm, computing current hot-sell commodity sequence of an E-commerce website and recommending users individually via the correlation and the sequence. On the basis of search behaviors of the users, the first N commodities most suitable for the users can be recommended. For different user searches, the recommended commodities are different, and individuation is realized.
Description
Technical field
The invention belongs to field of computer technology, relate to personalized recommendation technology, for a kind of based on electric business's web site commodity recommend method of search behavior.
Background technology
Electricity business web site commodity Search Results is various, and user wants to find interested commodity, needs to click repeatedly Search Results, both consuming time, also requires great effort, user's purchase experiences extreme difference; If in the Search Results of user, electricity business website can list the commodity of appropriate personalization automatically according to individual Man's Demands, avoid blindly finding in numerous Search Results, spend minimum time and efforts to find applicable commodity, this is by the purchase experiences of significant increase user.
2 implementations be similar to the present invention:
1), such as, by different sort key words can be selected to reset Search Results, sales volume, price, popularity etc. to Search Results.
2), by calculating the hot item of electric business website, commercial articles searching results page is placed in, for reference.
Above-mentioned two schemes have following shortcoming:
1) after, commercial articles searching result being reset according to optional sort key word, the quantity of Search Results does not change, and under the sort key word of various combination, representing of commodity is very inflexible, user still needs continuous differentiation to judge, finds the same time and effort consuming of suitable commercial product.
2), by commercial articles searching result, add hot item, although judge whether that the user buying commodity is very useful for part with sales volume, but, different users, searching plain result what see from commodity is all identical hot item, and unavoidable thousand times are without exception, be applied to individual, also do not there is personalization.
Summary of the invention
The problem to be solved in the present invention is: for the shortcoming of prior art, a kind of new recommend method is provided to help user's commodity that quick position is suitable from numerous commercial articles searching result, satisfied 1) based on the search behavior of user, the top n commodity of the most applicable user are recommended; 2) for different user searchs, the commodity of recommendation are also different, have personalization.
Technical scheme of the present invention is: a kind of electric business's web site commodity accurate recommendation method based on search behavior, comprises the following steps:
Step one, according to association rule algorithm, the incidence relation in calculated off-line historical data between user search keyword and purchase commodity, as relation data one;
Step 2, according to association rule algorithm, the incidence relation that in calculated off-line historical data, user browses commodity and buys between commodity, as relation data two;
Step 3, calculated off-line goes out the current hot item sequence in electric business website, as relation data three;
Step 4, recommend to active user: according to the search keyword A of active user's input, finding the same with searching for keyword A from relation data one, according to the incidence relation of relation data one, buying commodity as Recommendations for front i that selects the wherein degree of association large; Recommendations, if met, are returned to search results pages by the number whether calculated recommendation commodity satisfy the demands, and recommending to terminate, if do not met, then carrying out step 5;
Step 5, according to 1-5 commodity browsed recently before user search, find with to browse commodity the same from relation data two, the purchase commodity of the front j selecting the wherein degree of association large supply commodity as step 4 recommendation results, and then the number whether calculated recommendation commodity satisfy the demands, if met, Recommendations are returned to search results pages, terminate to recommend; If do not met, then carry out step 6;
Step 6, sort from big to small according to the sales volume of hot item in current electric business website, i.e. relation data three, obtain large front k the commodity of sales volume and supply commodity as step 5 recommendation results, then, then the number whether calculated recommendation commodity satisfy the demands, if met, Recommendations are returned to search results pages, terminates to recommend; If do not met, also terminate to recommend.
Step one is specially:
11) obtain the commodity data of user's search word all at no distant date and purchase, sample data buys product after comprising user ID, search keyword and search;
12) according to the needs of association rule algorithm, calculate the degree of confidence of every rule, support, the molecule of lifting degree and denominator, i.e. things sum, total, the consequent total Sum fanction sum of preceding paragraph, according to step 11) sample data, things refers to user ID, and things adds up to 4; Preceding paragraph is search keyword, and preceding paragraph sum refers to the number of times that each search keyword occurs; Consequent for buying product after search, the consequent purchase number of times ading up to search rear purchase product, rule is search keyword and searches for the rear corresponding relation bought between product, and rule adds up to the number of times that described corresponding relation occurs;
13) according to association rule algorithm formula, calculate: degree of confidence=regular sum/preceding paragraph sum, support=regular sum/things sum, lifting degree=degree of confidence/natural degree of confidence, wherein natural degree of confidence=consequent sum/things sum, degree of confidence represents the credibility of certain relation in correlation rule; Support represents the probability that in correlation rule, certain relation occurs; Lifting degree represents in correlation rule, whether certain relation can be used, the incidence relation that can obtain search word and buy between commodity.
Step 2 is specially:
21) obtain user's commodity data browsed and buy all at no distant date, sample data comprises user ID, browses commodity and buys product after searching for;
22) according to the needs of association rule algorithm, calculate degree of confidence, support, the molecule of lifting degree and denominator, i.e. things sum, total, the consequent total Sum fanction sum of preceding paragraph, according to step 21) sample data, things refers to user ID, and things adds up to 4; Preceding paragraph is for browsing commodity, and preceding paragraph sum refers to that each browses the number of times of commodity appearance; Consequent for buying product after search, consequent ading up to searches for the rear purchase number of times buying product, and rule is for browsing the corresponding relation between commodity and search rear purchase product, and rule adds up to the number of times that described corresponding relation occurs;
23) according to association rule algorithm formula, calculate: degree of confidence=regular sum/preceding paragraph sum, support=regular sum/things sum, lifting degree=degree of confidence/natural degree of confidence, wherein natural degree of confidence=consequent sum/things sum, degree of confidence represents the credibility of certain relation in correlation rule; Support represents the probability that in correlation rule, certain relation occurs; Lifting degree represents in correlation rule, whether certain relation can be used, and can obtain the incidence relation browsed commodity and buy between commodity.
The present invention is based on the search behavior of user, the top n commodity of the most applicable user can be recommended.Can for different user searchs, the commodity of recommendation are also different, have personalization.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention.
Fig. 2 is the process flow diagram of step one of the present invention.
Fig. 3 is the process flow diagram of step 2 of the present invention.
Embodiment
It is various that the present invention mainly solves electric business's web site commodity Search Results, and user finds and admires commodity time and effort consuming; Meanwhile, stand in fast-selling recommended technology do not have a problem of personalization.For individual subscriber hobby, recommend limited the commodity be applicable to user, to realize precisely recommending user, concrete performing step divides six to walk greatly, as Fig. 1
Step one, according to association rule algorithm, the incidence relation in calculated off-line historical data between user search keyword and purchase commodity, as relation data one.
Step 2, according to association rule algorithm, the incidence relation that in calculated off-line historical data, user browses commodity and buys between commodity, as relation data two.
Step 3, calculated off-line goes out the current hot item sequence in electric business website, as relation data three.
Step 4, recommend to active user: according to the search keyword A of active user's input, finding the same with searching for keyword A from relation data one, according to the incidence relation of relation data one, buying commodity as Recommendations for front i that selects the wherein degree of association large; Recommendations, if met, are returned to search results pages by the number whether calculated recommendation commodity satisfy the demands, and recommending to terminate, if do not met, then carrying out step 5.
Step 5, according to 1-5 commodity browsed recently before user search, find with to browse commodity the same from relation data two, the purchase commodity of the front j selecting the wherein degree of association large supply commodity as step 4 recommendation results, and then the number whether calculated recommendation commodity satisfy the demands, if met, Recommendations are returned to search results pages, terminate to recommend; If do not met, then carry out step 6.
Step 6, sort from big to small according to the sales volume of hot item in current electric business website, i.e. relation data three, obtain large front k the commodity of sales volume and supply commodity as step 5 recommendation results, then, then the number whether calculated recommendation commodity satisfy the demands, if met, Recommendations are returned to search results pages, terminates to recommend; If do not met, also terminate to recommend.
Relation between the calculated off-line search word of step one and purchase commodity, concrete computation process can in three steps, as Fig. 2, be specially again:
11) obtain the commodity data of user's search word all at no distant date and purchase, sample data buys product after comprising user ID, search keyword and search;
12) according to the needs of association rule algorithm, calculate the degree of confidence of every rule, support, the molecule of lifting degree and denominator, i.e. things sum, total, the consequent total Sum fanction sum of preceding paragraph, according to step 11) sample data, things refers to user ID, and things adds up to 4; Preceding paragraph is search keyword, has 3, S1, S2, S3, and preceding paragraph sum refers to the number of times that each search keyword occurs, number of times is 1,2 respectively, 3; Consequent have 2, G1, G4 for buying product after search, the consequent purchase number of times ading up to search rear purchase product, and number of times is 3,1 respectively; Rule is for buying the corresponding relation between product after search keyword and search, 4, S2-->G1, S3-->G1, S1-->G4, S3-->G4, rule adds up to the number of times that described corresponding relation occurs, number of times is 2,2 respectively, 1,1;
13) according to association rule algorithm formula, calculate: degree of confidence=regular sum/preceding paragraph sum, support=regular sum/things sum, lifting degree=degree of confidence/natural degree of confidence, wherein natural degree of confidence=consequent sum/things sum, degree of confidence represents the credibility (must be greater than during use and specify threshold value) of certain relation in correlation rule; Support represents the probability (must be greater than during use and specify threshold value) that in correlation rule, certain relation occurs; Lifting degree represents in correlation rule, whether certain relation with (must be greater than 1 during use), can obtain the incidence relation between search word and purchase commodity.According to step 12) result can to calculate the relation value of four rules as follows:
| Rule | Support | Degree of confidence | Nature degree of confidence | Lifting degree |
| S2-->G1 | 2/4＝0.5 | 2/2＝1 | 3/4＝0.75 | 1/0.75＝1.33 |
| S3-->G1 | 2/4＝0.5 | 2/3＝0.67 | 3/4＝0.75 | 0.67/0.75＝0.89 |
| S1-->G4 | 1/4＝0.25 | 1/1＝1 | 1/4＝0.25 | 1/0.25＝4 |
| S3-->G4 | 1/4＝0.25 | 1/3＝0.33 | 1/4＝0.25 | 0.33/0.25＝1.33 |
The relation between commodity is browsed and bought to the calculated off-line of step 2, and concrete computation process again can in three steps, as Fig. 3:
21) obtain user's commodity data browsed and buy all at no distant date, sample data comprises user ID, browses commodity and buys product after searching for;
22) according to the needs of association rule algorithm, calculate degree of confidence, support, the molecule of lifting degree and denominator, i.e. things sum, total, the consequent total Sum fanction sum of preceding paragraph, according to step 21) sample data, things refers to user ID, and things adds up to 4; Preceding paragraph is for browsing commodity, and preceding paragraph sum refers to that each browses the number of times of commodity appearance; Consequent for buying product after search, consequent ading up to searches for the rear purchase number of times buying product, and rule is for browsing the corresponding relation between commodity and search rear purchase product, and rule adds up to the number of times that described corresponding relation occurs;
23) according to association rule algorithm formula, calculate: degree of confidence=regular sum/preceding paragraph sum, support=regular sum/things sum, lifting degree=degree of confidence/natural degree of confidence, wherein natural degree of confidence=consequent sum/things sum, degree of confidence represents the credibility of certain relation in correlation rule; Support represents the probability that in correlation rule, certain relation occurs; Lifting degree represents in correlation rule, whether certain relation can be used, and can obtain the incidence relation browsed commodity and buy between commodity.
3rd step is the hot item calculating electric business website, and concrete computation process can divide again 2 steps:
31) sales data of all commodity in electric business website in history or in a period of time is obtained.
32) calculate the sales data of each commodity, before appointment sales volume, TOPN is hot item.
Claims (3)
1., based on electric business's web site commodity recommend method of search behavior, it is characterized in that comprising the following steps:
Step one, according to association rule algorithm, the incidence relation in calculated off-line historical data between user search keyword and purchase commodity, as relation data one;
Step 2, according to association rule algorithm, the incidence relation that in calculated off-line historical data, user browses commodity and buys between commodity, as relation data two;
Step 3, calculated off-line goes out the current hot item sequence in electric business website, as relation data three;
Step 4, recommend to active user: according to the search keyword A of active user's input, finding the same with searching for keyword A from relation data one, according to the incidence relation of relation data one, buying commodity as Recommendations for front i that selects the wherein degree of association large; Recommendations, if met, are returned to search results pages by the number whether calculated recommendation commodity satisfy the demands, and recommending to terminate, if do not met, then carrying out step 5;
Step 5, according to 1-5 commodity browsed recently before user search, find with to browse commodity the same from relation data two, the purchase commodity of the front j selecting the wherein degree of association large supply commodity as step 4 recommendation results, and then the number whether calculated recommendation commodity satisfy the demands, if met, Recommendations are returned to search results pages, terminate to recommend; If do not met, then carry out step 6;
Step 6, sort from big to small according to the sales volume of hot item in current electric business website, i.e. relation data three, obtain large front k the commodity of sales volume and supply commodity as step 5 recommendation results, then, then the number whether calculated recommendation commodity satisfy the demands, if met, Recommendations are returned to search results pages, terminates to recommend; If do not met, also terminate to recommend.
2. a kind of electric business's web site commodity recommend method based on search behavior according to claim 1, is characterized in that step one is specially:
11) obtain the commodity data of user's search word all at no distant date and purchase, sample data buys product after comprising user ID, search keyword and search;
12) according to the needs of association rule algorithm, calculate the degree of confidence of every rule, support, the molecule of lifting degree and denominator, i.e. things sum, total, the consequent total Sum fanction sum of preceding paragraph, according to step 11) sample data, things refers to user ID, and things adds up to 4; Preceding paragraph is search keyword, and preceding paragraph sum refers to the number of times that each search keyword occurs; Consequent for buying product after search, the consequent purchase number of times ading up to search rear purchase product, rule is search keyword and searches for the rear corresponding relation bought between product, and rule adds up to the number of times that described corresponding relation occurs;
13) according to association rule algorithm formula, calculate: degree of confidence=regular sum/preceding paragraph sum, support=regular sum/things sum, lifting degree=degree of confidence/natural degree of confidence, wherein natural degree of confidence=consequent sum/things sum, degree of confidence represents the credibility of certain relation in correlation rule; Support represents the probability that in correlation rule, certain relation occurs; Lifting degree represents in correlation rule, whether certain relation can be used, the incidence relation that can obtain search word and buy between commodity.
3. a kind of electric business's web site commodity recommend method based on search behavior according to claim 1, is characterized in that step 2 is specially:
21) obtain user's commodity data browsed and buy all at no distant date, sample data comprises user ID, browses commodity and buys product after searching for;
22) according to the needs of association rule algorithm, calculate degree of confidence, support, the molecule of lifting degree and denominator, i.e. things sum, total, the consequent total Sum fanction sum of preceding paragraph, according to step 21) sample data, things refers to user ID, and things adds up to 4; Preceding paragraph is for browsing commodity, and preceding paragraph sum refers to that each browses the number of times of commodity appearance; Consequent for buying product after search, consequent ading up to searches for the rear purchase number of times buying product, and rule is for browsing the corresponding relation between commodity and search rear purchase product, and rule adds up to the number of times that described corresponding relation occurs;
23) according to association rule algorithm formula, calculate: degree of confidence=regular sum/preceding paragraph sum, support=regular sum/things sum, lifting degree=degree of confidence/natural degree of confidence, wherein natural degree of confidence=consequent sum/things sum, degree of confidence represents the credibility of certain relation in correlation rule; Support represents the probability that in correlation rule, certain relation occurs; Lifting degree represents in correlation rule, whether certain relation can be used, and can obtain the incidence relation browsed commodity and buy between commodity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410606971.0A CN104317945A (en) | 2014-10-31 | 2014-10-31 | E-commerce website commodity recommending method on basis of search behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410606971.0A CN104317945A (en) | 2014-10-31 | 2014-10-31 | E-commerce website commodity recommending method on basis of search behaviors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104317945A true CN104317945A (en) | 2015-01-28 |
Family
ID=52373177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410606971.0A Pending CN104317945A (en) | 2014-10-31 | 2014-10-31 | E-commerce website commodity recommending method on basis of search behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104317945A (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915210A (en) * | 2015-06-17 | 2015-09-16 | 遵义随订科技技术开发有限公司 | Digitized purchasing phone application management system |
| CN105005913A (en) * | 2015-06-29 | 2015-10-28 | 成都亿邻通科技有限公司 | Method for promoting group purchase service quality |
| CN105023171A (en) * | 2015-06-29 | 2015-11-04 | 成都亿邻通科技有限公司 | Method for recommending group purchase to user |
| CN105046518A (en) * | 2015-06-29 | 2015-11-11 | 成都亿邻通科技有限公司 | Method of recommending group buying services |
| CN105046517A (en) * | 2015-06-29 | 2015-11-11 | 成都亿邻通科技有限公司 | Group buying method of recommending user consumption |
| CN105159937A (en) * | 2015-08-03 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Information pushing method and apparatus |
| CN105630946A (en) * | 2015-12-23 | 2016-06-01 | 百度在线网络技术（北京）有限公司 | Big data based field cross recommendation method and apparatus |
| CN105678567A (en) * | 2015-12-31 | 2016-06-15 | 宁波领视信息科技有限公司 | Accurate prediction system based on big data deep learning |
| CN105760523A (en) * | 2016-02-29 | 2016-07-13 | 百度在线网络技术（北京）有限公司 | Information push method and information push device |
| CN106407349A (en) * | 2016-09-06 | 2017-02-15 | 北京三快在线科技有限公司 | Product recommendation method and device |
| WO2017063420A1 (en) * | 2015-10-12 | 2017-04-20 | 百度在线网络技术（北京）有限公司 | User demand determining method and apparatus |
| CN107609123A (en) * | 2017-09-14 | 2018-01-19 | 西安领讯卓越信息技术有限公司 | A kind of method presented based on news commending system polymerization news |
| WO2018014764A1 (en) * | 2016-07-19 | 2018-01-25 | 阿里巴巴集团控股有限公司 | Method and device for selecting commodity object, and determining model and usage popularity |
| CN107730336A (en) * | 2016-08-12 | 2018-02-23 | 苏宁云商集团股份有限公司 | Commodity method for pushing and device in a kind of online transaction |
| CN107767172A (en) * | 2017-10-12 | 2018-03-06 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, server and medium |
| CN107944896A (en) * | 2016-10-13 | 2018-04-20 | 北京京东尚科信息技术有限公司 | Determine the method and device of commodity association degree |
| CN107958075A (en) * | 2017-12-11 | 2018-04-24 | 重庆邮电大学 | A kind of method that the transfer of consumer's purchase intention is judged based on web search index |
| CN108509497A (en) * | 2018-02-23 | 2018-09-07 | 阿里巴巴集团控股有限公司 | Information recommendation method, device and electronic equipment |
| CN108776914A (en) * | 2018-05-22 | 2018-11-09 | 广州品唯软件有限公司 | A kind of user individual goods browse method and device based on neural network |
| CN108805622A (en) * | 2018-06-11 | 2018-11-13 | 深圳乐信软件技术有限公司 | Method of Commodity Recommendation, device, equipment and storage medium |
| CN109191263A (en) * | 2018-09-19 | 2019-01-11 | 惠龙易通国际物流股份有限公司 | Purchase vehicle management system and method based on e-commerce platform |
| CN109766491A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product search method, device, computer equipment and storage medium |
| CN110992146A (en) * | 2019-12-02 | 2020-04-10 | 泰康保险集团股份有限公司 | Service information pushing method, device, equipment and storage medium |
| CN111062788A (en) * | 2019-12-28 | 2020-04-24 | 广东奥园奥买家电子商务有限公司 | E-commerce platform commodity recommendation method, device and equipment based on search |
| CN111104583A (en) * | 2018-10-10 | 2020-05-05 | 武汉斗鱼网络科技有限公司 | Live broadcast room recommendation method, storage medium, electronic device and system |
| CN111882401A (en) * | 2020-08-03 | 2020-11-03 | 施兴明 | E-commerce automatic reminding method and system |
| CN112102037A (en) * | 2020-09-16 | 2020-12-18 | 汤涛 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
| CN112488781A (en) * | 2020-11-10 | 2021-03-12 | 北京三快在线科技有限公司 | Search recommendation method and device, electronic equipment and readable storage medium |
| CN112734511A (en) * | 2020-12-30 | 2021-04-30 | 昆山巨星行动电子商务有限公司 | Commodity search recommendation method based on e-commerce system and application |
| CN113254778A (en) * | 2021-06-07 | 2021-08-13 | 汇智数字科技控股(深圳)有限公司 | Amazon platform-based ASIN group keyword recommendation method |
| CN113361605A (en) * | 2021-06-07 | 2021-09-07 | 汇智数字科技控股(深圳)有限公司 | Product similarity quantification method based on Amazon keywords |
| CN113378072A (en) * | 2021-08-16 | 2021-09-10 | 武汉卓尔数字传媒科技有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| CN117575747A (en) * | 2024-01-19 | 2024-02-20 | 山东街景智能制造科技股份有限公司 | Personalized recommendation method based on user analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592223A (en) * | 2011-01-18 | 2012-07-18 | 卓望数码技术（深圳）有限公司 | Commodity recommending method and commodity recommending system |
| CN103218719A (en) * | 2012-01-19 | 2013-07-24 | 阿里巴巴集团控股有限公司 | Method and system of e-commerce website navigation |
| CN103839167A (en) * | 2012-11-21 | 2014-06-04 | 大连灵动科技发展有限公司 | Commodity candidate set recommendation method |
-
2014
- 2014-10-31 CN CN201410606971.0A patent/CN104317945A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592223A (en) * | 2011-01-18 | 2012-07-18 | 卓望数码技术（深圳）有限公司 | Commodity recommending method and commodity recommending system |
| CN103218719A (en) * | 2012-01-19 | 2013-07-24 | 阿里巴巴集团控股有限公司 | Method and system of e-commerce website navigation |
| CN103839167A (en) * | 2012-11-21 | 2014-06-04 | 大连灵动科技发展有限公司 | Commodity candidate set recommendation method |
Cited By (45)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915210A (en) * | 2015-06-17 | 2015-09-16 | 遵义随订科技技术开发有限公司 | Digitized purchasing phone application management system |
| CN104915210B (en) * | 2015-06-17 | 2019-02-15 | 遵义随订科技技术开发有限公司 | Digitlization is with ordering mobile phone application management system |
| CN105005913A (en) * | 2015-06-29 | 2015-10-28 | 成都亿邻通科技有限公司 | Method for promoting group purchase service quality |
| CN105023171A (en) * | 2015-06-29 | 2015-11-04 | 成都亿邻通科技有限公司 | Method for recommending group purchase to user |
| CN105046518A (en) * | 2015-06-29 | 2015-11-11 | 成都亿邻通科技有限公司 | Method of recommending group buying services |
| CN105046517A (en) * | 2015-06-29 | 2015-11-11 | 成都亿邻通科技有限公司 | Group buying method of recommending user consumption |
| CN105159937A (en) * | 2015-08-03 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Information pushing method and apparatus |
| CN105159937B (en) * | 2015-08-03 | 2018-09-28 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| WO2017063420A1 (en) * | 2015-10-12 | 2017-04-20 | 百度在线网络技术（北京）有限公司 | User demand determining method and apparatus |
| US10459996B2 (en) | 2015-12-23 | 2019-10-29 | Baidu Online Network Technology (Beijing) Co., Ltd | Big data based cross-domain recommendation method and apparatus |
| WO2017107416A1 (en) * | 2015-12-23 | 2017-06-29 | 百度在线网络技术（北京）有限公司 | Cross-field recommendation method and apparatus based on big data |
| CN105630946B (en) * | 2015-12-23 | 2019-03-19 | 百度在线网络技术（北京）有限公司 | A kind of field intersection recommended method and device based on big data |
| CN105630946A (en) * | 2015-12-23 | 2016-06-01 | 百度在线网络技术（北京）有限公司 | Big data based field cross recommendation method and apparatus |
| CN105678567A (en) * | 2015-12-31 | 2016-06-15 | 宁波领视信息科技有限公司 | Accurate prediction system based on big data deep learning |
| CN105760523A (en) * | 2016-02-29 | 2016-07-13 | 百度在线网络技术（北京）有限公司 | Information push method and information push device |
| WO2018014764A1 (en) * | 2016-07-19 | 2018-01-25 | 阿里巴巴集团控股有限公司 | Method and device for selecting commodity object, and determining model and usage popularity |
| CN107730336A (en) * | 2016-08-12 | 2018-02-23 | 苏宁云商集团股份有限公司 | Commodity method for pushing and device in a kind of online transaction |
| CN106407349A (en) * | 2016-09-06 | 2017-02-15 | 北京三快在线科技有限公司 | Product recommendation method and device |
| CN107944896A (en) * | 2016-10-13 | 2018-04-20 | 北京京东尚科信息技术有限公司 | Determine the method and device of commodity association degree |
| CN107609123A (en) * | 2017-09-14 | 2018-01-19 | 西安领讯卓越信息技术有限公司 | A kind of method presented based on news commending system polymerization news |
| CN107609123B (en) * | 2017-09-14 | 2021-12-14 | 强春娟 | Method for aggregating news presentations based on news recommendation system |
| CN107767172A (en) * | 2017-10-12 | 2018-03-06 | 百度在线网络技术（北京）有限公司 | Information-pushing method, device, server and medium |
| CN107958075A (en) * | 2017-12-11 | 2018-04-24 | 重庆邮电大学 | A kind of method that the transfer of consumer's purchase intention is judged based on web search index |
| CN107958075B (en) * | 2017-12-11 | 2021-02-26 | 重庆邮电大学 | Method for judging consumer purchase intention transfer based on network search index |
| CN108509497A (en) * | 2018-02-23 | 2018-09-07 | 阿里巴巴集团控股有限公司 | Information recommendation method, device and electronic equipment |
| CN108776914A (en) * | 2018-05-22 | 2018-11-09 | 广州品唯软件有限公司 | A kind of user individual goods browse method and device based on neural network |
| CN108805622A (en) * | 2018-06-11 | 2018-11-13 | 深圳乐信软件技术有限公司 | Method of Commodity Recommendation, device, equipment and storage medium |
| CN109191263A (en) * | 2018-09-19 | 2019-01-11 | 惠龙易通国际物流股份有限公司 | Purchase vehicle management system and method based on e-commerce platform |
| CN111104583A (en) * | 2018-10-10 | 2020-05-05 | 武汉斗鱼网络科技有限公司 | Live broadcast room recommendation method, storage medium, electronic device and system |
| CN111104583B (en) * | 2018-10-10 | 2024-01-05 | 河南星易网络科技有限公司 | Live broadcast room recommendation method, storage medium, electronic equipment and system |
| CN109766491A (en) * | 2018-12-18 | 2019-05-17 | 深圳壹账通智能科技有限公司 | Product search method, device, computer equipment and storage medium |
| CN110992146A (en) * | 2019-12-02 | 2020-04-10 | 泰康保险集团股份有限公司 | Service information pushing method, device, equipment and storage medium |
| CN111062788A (en) * | 2019-12-28 | 2020-04-24 | 广东奥园奥买家电子商务有限公司 | E-commerce platform commodity recommendation method, device and equipment based on search |
| CN111882401A (en) * | 2020-08-03 | 2020-11-03 | 施兴明 | E-commerce automatic reminding method and system |
| CN112102037A (en) * | 2020-09-16 | 2020-12-18 | 汤涛 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
| CN112102037B (en) * | 2020-09-16 | 2021-05-07 | 广州伊的家网络科技有限公司 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
| CN112488781A (en) * | 2020-11-10 | 2021-03-12 | 北京三快在线科技有限公司 | Search recommendation method and device, electronic equipment and readable storage medium |
| CN112734511A (en) * | 2020-12-30 | 2021-04-30 | 昆山巨星行动电子商务有限公司 | Commodity search recommendation method based on e-commerce system and application |
| CN113254778A (en) * | 2021-06-07 | 2021-08-13 | 汇智数字科技控股(深圳)有限公司 | Amazon platform-based ASIN group keyword recommendation method |
| CN113254778B (en) * | 2021-06-07 | 2023-05-09 | 汇智数字科技控股(深圳)有限公司 | ASIN group keyword recommendation method based on Amazon platform |
| CN113361605A (en) * | 2021-06-07 | 2021-09-07 | 汇智数字科技控股(深圳)有限公司 | Product similarity quantification method based on Amazon keywords |
| CN113361605B (en) * | 2021-06-07 | 2024-05-24 | 汇智数字科技控股(深圳)有限公司 | Product similarity quantification method based on Amazon keywords |
| CN113378072A (en) * | 2021-08-16 | 2021-09-10 | 武汉卓尔数字传媒科技有限公司 | Object recommendation method and device, electronic equipment and storage medium |
| CN117575747A (en) * | 2024-01-19 | 2024-02-20 | 山东街景智能制造科技股份有限公司 | Personalized recommendation method based on user analysis |
| CN117575747B (en) * | 2024-01-19 | 2024-04-05 | 山东街景智能制造科技股份有限公司 | Personalized recommendation method based on user analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104317945A (en) | E-commerce website commodity recommending method on basis of search behaviors | |
| Wu et al. | Turning clicks into purchases: Revenue optimization for product search in e-commerce | |
| Shaikh et al. | Recommendation system in e-commerce websites: a graph based approached | |
| TWI522942B (en) | User favorites data processing method and device, user favorite data searching method and device, and user favorite system | |
| CN108665333B (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN102789462B (en) | A kind of item recommendation method and system | |
| CN105824912A (en) | Personalized recommending method and device based on user portrait | |
| Yu | The dynamic competitive recommendation algorithm in social network services | |
| US9727906B1 (en) | Generating item clusters based on aggregated search history data | |
| US20170206551A1 (en) | Personalized Recommendation Computation in Real Time using Incremental Matrix Factorization and User Factor Clustering | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| Gogna et al. | DiABlO: Optimization based design for improving diversity in recommender system | |
| EP2612286A1 (en) | Product recommendations | |
| CN106777051A (en) | A kind of many feedback collaborative filtering recommending methods based on user's group | |
| CN105426528A (en) | Retrieving and ordering method and system for commodity data | |
| CN103824213A (en) | Individualized recommendation method based on user preferences and commodity properties | |
| TW201220233A (en) | by which category information of long tail keywords is provided for users within a specified time period | |
| US10970296B2 (en) | System and method for data mining and similarity estimation | |
| Hasan et al. | Query suggestion for e-commerce sites | |
| CN110503497A (en) | A kind of electric business management platform Method of Commodity Recommendation of the consumption habit based on client | |
| Choi et al. | An auxiliary recommendation system for repetitively purchasing items in E-commerce | |
| US20150248481A1 (en) | Search ranking diversity based on aspect affinity | |
| CN109410001A (en) | A kind of Method of Commodity Recommendation, system, electronic equipment and storage medium | |
| Ghuli et al. | A collaborative filtering recommendation engine in a distributed environment | |
| CN105447045A (en) | Information ordering method and device and information providing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Mao Shaohua Inventor after: Liu Kaizhou Inventor after: Wu Jun Inventor after: Yan Xiaochun Inventor after: Chen Youguang Inventor after: Hou Bing Inventor before: Mao Shaohua Inventor before: Liu Kaizhou Inventor before: Yan Xiaochun Inventor before: Chen Youguang Inventor before: Hou Bing |
|
| COR | Change of bibliographic data | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150128 |
|
| RJ01 | Rejection of invention patent application after publication |