CN109242649A - A kind of Method of Commodity Recommendation and relevant apparatus - Google Patents
A kind of Method of Commodity Recommendation and relevant apparatus Download PDFInfo
- Publication number
- CN109242649A CN109242649A CN201811287656.0A CN201811287656A CN109242649A CN 109242649 A CN109242649 A CN 109242649A CN 201811287656 A CN201811287656 A CN 201811287656A CN 109242649 A CN109242649 A CN 109242649A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- similarity
- classification information
- data
- 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
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Method of Commodity Recommendation, system, device and computer readable storage mediums, the target category information of end article generic is obtained first, then the classification information to be recommended for being greater than preset threshold with the similarity of target category information is determined, and by the end article information recommendation in the corresponding merchandise news of classification information to be recommended to User Page corresponding with end article.Due to being the target category information of first determining end article, and most like class is determined using the similarity between classification information, class namely to be recommended, and the end article information in class to be recommended is recommended, therefore it can recommend the commodity of other maximally related classes out for user, the coordinates of end article can namely be recommended for user, and no longer only recommend same class commodity similar with end article, therefore the product that can comprehensively recommend related category for end article, keeps recommendation results more comprehensive.
Description
Technical field
The present invention relates to technical field of data processing, more specifically to a kind of Method of Commodity Recommendation, system, device
And computer readable storage medium.
Background technique
With the development of computer and internet, more and more users' selection passes through shopping at network.In order to more preferably use
Family provides electric business service, usually after user buys or browsed a certain product, just recommends similar product for the user, from
And user is made more easily to check the information of like product.But result recommended to the user is usually not comprehensive enough at present, uses
The range that family can choose is too small.
Therefore, how comprehensive Recommendations, be those skilled in the art's problem to be solved.
Summary of the invention
The purpose of the present invention is to provide a kind of Method of Commodity Recommendation, system, device and computer readable storage medium, with
Comprehensive Recommendations.
To achieve the above object, the embodiment of the invention provides following technical solutions:
A kind of Method of Commodity Recommendation, comprising:
Obtain the target category information of end article generic；
The determining classification information to be recommended for being greater than preset threshold with the similarity of the target category information；
By the end article information recommendation in merchandise news corresponding with the classification information to be recommended to the target
The corresponding User Page of commodity.
Wherein, the similarity of the determination and the target category information be greater than preset threshold classification information to be recommended it
Before, further includes:
The user for extracting predetermined number buys data；Wherein, it includes user information and the use that the user, which buys data,
The corresponding classification information of family information and purchase number corresponding with the classification information；
Data, which are bought, using the user determines the similarity between every two classification information.
Wherein, the user for extracting predetermined number buys data, comprising:
Extracting has the user of all users of purchaser record to buy data in preset time.
It is wherein, described to determine the similarity between every two classification information using user purchase data, comprising:
Data are bought to the user using Pearson came Similarity algorithm to calculate, and are obtained between every two classification information
Similarity.
It is wherein, described to determine the similarity between every two classification information using user purchase data, comprising:
Using m-cosine similarity algorithm to the user buy data calculate, obtain every two classification information it
Between similarity.
Present invention also provides a kind of commercial product recommending systems, comprising:
Module is obtained, for obtaining the target category information of end article generic；
Determining module, the classification to be recommended for being greater than preset threshold for the determining similarity with the target category information are believed
Breath；
Recommending module, for by the end article information recommendation in merchandise news corresponding with the classification information to be recommended
To User Page corresponding with the end article.
Wherein, further includes:
Extraction module, the user for extracting predetermined number buy data；Wherein, it includes user that the user, which buys data,
Information, classification information corresponding with the user information and the corresponding purchase number with the classification information；
Similarity calculation module, it is similar between every two classification information for being determined using user purchase data
Degree.
Wherein, the extraction module has the user of all users of purchaser record to purchase specifically for extracting in preset time
Buy data.
Present invention also provides a kind of devices for recommending the commodity, comprising:
Memory, for storing computer program；
Processor is realized when for executing the computer program such as the step of the Method of Commodity Recommendation.
Present invention also provides a kind of computer readable storage medium, meter is stored on the computer readable storage medium
Calculation machine program is realized when the computer program is executed by processor such as the step of the Method of Commodity Recommendation.
By above scheme it is found that a kind of Method of Commodity Recommendation provided by the invention, comprising: obtain the affiliated class of end article
Other target category information；The determining classification information to be recommended for being greater than preset threshold with the similarity of the target category information；
By the end article information recommendation in merchandise news corresponding with the classification information to be recommended to corresponding with the end article
User Page.
It can be seen that a kind of Method of Commodity Recommendation provided by the present application, obtains the target of end article generic first
Then classification information determines the classification information to be recommended for being greater than preset threshold with the similarity of target category information, and will be to
Recommend the end article information recommendation extremely User Page corresponding with end article in the corresponding merchandise news of classification information.Due to
In this programme it is the target category information of first determining end article, and determines most phase using the similarity between classification information
As class, that is, determine the class to be recommended for being greater than preset threshold with target category information similarity, and will be in class to be recommended
End article information recommended, therefore the commodity of other maximally related classes out can be recommended for user, that is, can be
User recommends the coordinates of end article, and no longer only recommends similar with end article same class commodity, therefore can be with
The product for comprehensively recommending related category for end article, keeps recommendation results more comprehensive.Present invention also provides a kind of quotient
Above-mentioned technical effect equally may be implemented in product recommender system, device and computer readable storage medium.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of Method of Commodity Recommendation flow chart disclosed by the embodiments of the present invention；
Fig. 2 is a kind of specific Method of Commodity Recommendation flow chart disclosed by the embodiments of the present invention；
Fig. 3 is a kind of commercial product recommending system structural schematic diagram disclosed by the embodiments of the present invention；
Fig. 4 is a kind of device for recommending the commodity structural schematic diagram disclosed by the embodiments of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a kind of Method of Commodity Recommendation, system, device and computer readable storage mediums, with complete
The Recommendations in face.
Referring to Fig. 1, a kind of Method of Commodity Recommendation provided in an embodiment of the present invention is specifically included:
S101 obtains the target category information of end article generic.
It should be noted that user may no longer pay close attention to such commodity, but match after browsing or buying a commodity
The commodity of other classes of set, therefore when in the present solution, carrying out commercial product recommending using end article, end article institute is obtained first
Belong to the target category information of classification.
It should be noted that end article is Recommendations foundation, for example, user is after buying A commodity, then A commodity
As foundation, recommend other commodity for user.
Classification information is the information of class belonging to commodity, if A commodity belong to women's dress class, therefore, class described in end article A
Target category information, be the information of women's dress class, in the present solution, target category information includes the number of target category.
S102, the determining classification information to be recommended for being greater than preset threshold with the similarity of the target category information.
In the present solution, it needs to be determined that similarity between classification information, and by the similarity between classification information,
The information of classification to be recommended and classification to be recommended is determined in all categories.Classification information to be recommended is then and target class
Similarity between other information is greater than the classification information of preset threshold.
It should be noted that preset threshold can be set according to specific service conditions, usual similarity value indicates when being 0
Dissmilarity, being worth when being 1 indicates most like, therefore the similarity between classification information value, preset threshold usually between 0 to 1
Usually not less than 0.5.
It should be noted that in the present solution, the similarity between all categories information can be predefined out, and at it
In directly determine out the classification information to be recommended that similarity value between target category information is greater than preset threshold.
For example, target category information is women's dress class, class number 1, women's shoes class (class number 2) and women's dress class it
Between similarity be 0.811894, similarity between luggage class (class number 3) and women's dress class is 0.768943, movement family
Similarity between outer class (class number 4) and women's dress class is 0.641858, and preset threshold 0.65 then corresponds to target category
Information, classification information to be recommended are women's shoes category information and luggage category information.
It should be noted that target category information and oneself similarity value should be 1, thus can also serve as oneself to
Recommend classification information, for example, women's dress class can also serve as the classification to be recommended of oneself, and using women's dress category information as women's dress class
The classification information to be recommended of information.
S103, by the end article information recommendation in merchandise news corresponding with the classification information to be recommended to it is described
The corresponding User Page of end article.
Specifically, after classification information to be recommended has been determined, so that it may in the corresponding merchandise news of classification information to be recommended
Middle determining end article information, and by end article information recommendation to User Page corresponding with end article, it is selected for user
It selects.
It should be noted that specifically needed in classification information to be recommended by those commodity end article the most, it can basis
Actual conditions determine, can also determine, be not specifically limited at random in this programme.
It can be seen that a kind of Method of Commodity Recommendation provided by the embodiments of the present application, first acquisition end article generic
Target category information, then determine with the similarity of target category information be greater than preset threshold classification information to be recommended,
And by the end article information recommendation in the corresponding merchandise news of classification information to be recommended to user page corresponding with end article
Face.Due to being the target category information by determining end article in this programme, and utilize the similarity between classification information
It determines most like class, that is, determines the class to be recommended for being greater than preset threshold with target category information similarity, and will
End article information in class to be recommended is recommended, therefore can recommend the commodity of other maximally related classes out for user,
It is exactly that can recommend the coordinates of end article for user, and no longer only recommend same class quotient similar with end article
Product, therefore can comprehensively recommend the product of related category for end article, keep recommendation results more comprehensive.
A kind of specific Method of Commodity Recommendation provided by the embodiments of the present application is introduced below, one kind described below
Specific Method of Commodity Recommendation makes specific introduction to the calculating of similarity, and other content is situated between in the above-described embodiments
It continues, particular content may refer to above-described embodiment, and the embodiment of the present application will be repeated no longer.
Referring to fig. 2, a kind of specific Method of Commodity Recommendation provided by the embodiments of the present application, on the basis of above-described embodiment
On, further includes:
S201, the user for extracting predetermined number buy data；Wherein, the user buy data include user information, with
The corresponding classification information of user information and purchase number corresponding with the classification information.
Specifically, the user for extracting predetermined number first buys data, that is, extracts historical user and buy data.
It should be noted that it includes user information, classification corresponding with user information letter that each user, which buys data,
Breath and purchase number corresponding with classification information, specifically, user information include that Customs Assigned Number, classification information include that classification is compiled
Number.
The user of predetermined number, which buys data and can be whole users, buys data, can also be with if data volume is too big
Selected section user buys data, it is to be understood that preferential to select user active if selected section user buys receipt
The user for spending higher part user buys data.
In a specific embodiment, extracting has the user of all users of purchaser record to buy number in preset time
According to.
Preset time, which can be, is also possible to some months for 1 year, and how preset time is specifically arranged carries out according to the actual situation,
It is not specifically limited in this programme.
S202 buys data using the user and determines the similarity between every two classification information.
Specifically, data are bought using user, calculates the similarity between every two classification information, to utilize similarity
Determine the corresponding classification information to be recommended of target category information.
In the present solution, the calculating of similarity can be calculated by Pearson came algorithm or cosine similarity.
Specifically, as using Pearson came algorithm, then it is referred to following steps progress:
The first step determines that all users buy data, and needs to calculate two classification informations of similarity, in this programme
In, it includes that a plurality of user buys data that user, which buys receipt, and it includes user id that each user, which buys data, corresponding with user id
Classification id, purchase number corresponding with each classification id of the user id.Wherein all users buy data prefs
It indicates, needs to calculate two classification informations of similarity, the id of as two classifications is indicated with p1 and p2.
Second step is utilized respectively the summation that sum formula calculates the purchase number of the corresponding all users of p1 class, with p2
The summation of the purchase number of the corresponding all users of class；
Third step is utilized respectively square of the squared purchase number that the corresponding all users of p1 class are calculated with formula
With the quadratic sum of the purchase number of all users corresponding with p2 class.
4th step is utilized respectively the product for the purchase number for asking sum of products formula to calculate the corresponding all users of p1 class
The sum of, the sum of products of the purchase number of all users corresponding with p2 class.
5th step is purchased in conjunction with summation, quadratic sum, the sum of products of p1 class purchase number with p2 class using Pearson came algorithm
The summation, quadratic sum, the sum of products for buying number calculate Pearson came value, which is similar between p1 class and p2 class
Degree.
The first step is repeated to the 5th step, until it is equal that user is bought the similarity value between any two class involved in data
It calculates.
The code content of Pearson came algorithm can refer to following specific examples:
#prefs is whole team's column data, and p1, p2 are that the data for needing to compare returns to the similarity calculated, and there are also identical
Element number
It should be noted that above-mentioned code is a kind of concrete implementation example, practical implementation can also use it
He completes code, is not specifically limited in this programme.
Cosine similarity algorithm is such as used, then is referred to following steps progress:
The first step determines that all users buy data, and needs to calculate two classification informations of similarity, in this programme
In, it includes that a plurality of user buys data that user, which buys receipt, and it includes user id that each user, which buys data, corresponding with user id
Classification id, purchase number corresponding with each classification id of the user id.Wherein all users buy data prefs
It indicates, needs to calculate two classification informations of similarity, the id of as two classifications is indicated with p1 and p2.
Second step is utilized respectively the sum of products and inner product formula, calculates the purchase number of the corresponding all users of p1 class
The sum of products of the purchase number of all users corresponding with p2 class；
Third step is utilized respectively a square sum formula, calculates the quadratic sum that the corresponding all users of p1 class buy number
The quadratic sum of the purchase number of all users corresponding with p2 class；
4th step must not the sum of products, the quadratic sum of third step calculating p1 and p2 with second using preparatory similar algorithm
Between similarity.
The first step is repeated to the 4th step, until it is equal that user is bought the similarity value between any two class involved in data
It calculates.
The code content of cosine similarity algorithm can refer to following specific examples:
#prefs is whole team's column data, and p1, p2 are that the data for needing to compare returns to the similarity calculated, and there are also identical
Element number
It should be noted that above-mentioned code is a kind of concrete implementation example, practical implementation can also use it
He completes code, is not specifically limited in this programme.
A kind of commercial product recommending system provided by the embodiments of the present application is introduced below, a kind of commodity described below push away
Recommending system can be cross-referenced with any of the above-described embodiment.
Referring to Fig. 3, a kind of commercial product recommending system provided by the embodiments of the present application is specifically included:
Module 301 is obtained, for obtaining the target category information of end article generic.
Determining module 302, for the determining class to be recommended for being greater than preset threshold with the similarity of the target category information
Other information.
Recommending module 303, for by the end article information in merchandise news corresponding with the classification information to be recommended
Recommend to User Page corresponding with the end article.
In a specific embodiment, the commercial product recommending system, on the basis of the above embodiments, further includes:
Extraction module, the user for extracting predetermined number buy data；Wherein, it includes user that the user, which buys data,
Information, classification information corresponding with the user information and the corresponding purchase number with the classification information.
In a specific embodiment, extraction module, which is specifically used for extracting, all of purchaser record in preset time
The user of user buys data.
Similarity calculation module, it is similar between every two classification information for being determined using user purchase data
Degree.
In a specific embodiment, similarity calculation module is specifically used for using Pearson came Similarity algorithm to described
User buys data and calculates, and obtains the similarity between every two classification information.
In a specific embodiment, similarity calculation module is specifically used for utilizing m-cosine similarity algorithm pair
The user buys data and calculates, and obtains the similarity between every two classification information.
The commercial product recommending system of the present embodiment is for realizing Method of Commodity Recommendation above-mentioned, therefore in commercial product recommending system
The embodiment part of the visible Method of Commodity Recommendation hereinbefore of specific embodiment, for example, obtaining module 301, determining module
302, recommending module 303 is respectively used to realize step S101, S102, S103 in above-mentioned Method of Commodity Recommendation, so, it is specific
Embodiment is referred to the description of corresponding various pieces embodiment, and details are not described herein.
A kind of device for recommending the commodity provided by the embodiments of the present application is introduced below, a kind of commodity described below push away
Recommending device can be cross-referenced with any of the above-described embodiment.
Referring to fig. 4, a kind of device for recommending the commodity provided by the embodiments of the present application, specifically includes:
Memory 401, for storing computer program；
Processor 402, realizing the Method of Commodity Recommendation embodiment as described in any when for executing the computer program
Step.
Specifically, memory 401 includes non-volatile memory medium, built-in storage.Non-volatile memory medium storage
There are operating system and computer-readable instruction, which is that the operating system and computer in non-volatile memory medium can
The operation of reading instruction provides environment.Processor 402 provides calculating and control ability for the device for recommending the commodity, may be implemented above-mentioned
Step provided by one Method of Commodity Recommendation embodiment.
Present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer
Step provided by above-described embodiment may be implemented when program is executed by processor.The storage medium may include: USB flash disk, movement
Hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), the various media that can store program code such as magnetic or disk.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of Method of Commodity Recommendation characterized by comprising
Obtain the target category information of end article generic；
The determining classification information to be recommended for being greater than preset threshold with the similarity of the target category information；
By the end article information recommendation in merchandise news corresponding with the classification information to be recommended to the end article
Corresponding User Page.
2. the method according to claim 1, wherein the determination and the similarity of the target category information are big
Before the classification information to be recommended of preset threshold, further includes:
The user for extracting predetermined number buys data；Wherein, it includes that user information and the user believe that the user, which buys data,
Cease corresponding classification information and purchase number corresponding with the classification information；
Data, which are bought, using the user determines the similarity between every two classification information.
3. according to the method described in claim 2, it is characterized in that, the user for extracting predetermined number buys data, comprising:
Extracting has the user of all users of purchaser record to buy data in preset time.
4. according to the method described in claim 2, it is characterized in that, described determine every two using user purchase data
Similarity between classification information, comprising:
Data are bought to the user using Pearson came Similarity algorithm to calculate, and are obtained similar between every two classification information
Degree.
5. according to the method described in claim 2, it is characterized in that, described determine every two using user purchase data
Similarity between classification information, comprising:
Data are bought to the user using m-cosine similarity algorithm to calculate, and are obtained between every two classification information
Similarity.
6. a kind of commercial product recommending system characterized by comprising
Module is obtained, for obtaining the target category information of end article generic；
Determining module, for the determining classification information to be recommended for being greater than preset threshold with the similarity of the target category information；
Recommending module, for by the end article information recommendation in merchandise news corresponding with the classification information to be recommended to
The corresponding User Page of the end article.
7. system according to claim 6, which is characterized in that further include:
Extraction module, the user for extracting predetermined number buy data；Wherein, it includes user's letter that the user, which buys data,
Breath, classification information corresponding with the user information and the corresponding purchase number with the classification information；
Similarity calculation module determines the similarity between every two classification information for buying data using the user.
8. system according to claim 7, which is characterized in that the extraction module is specifically used for extracting in preset time
There is the user of all users of purchaser record to buy data.
9. a kind of device for recommending the commodity characterized by comprising
Memory, for storing computer program；
Processor, realizing the Method of Commodity Recommendation as described in any one of claim 1 to 5 when for executing the computer program
Step.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the step of the Method of Commodity Recommendation as described in any one of claim 1 to 5 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287656.0A CN109242649A (en) | 2018-10-31 | 2018-10-31 | A kind of Method of Commodity Recommendation and relevant apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287656.0A CN109242649A (en) | 2018-10-31 | 2018-10-31 | A kind of Method of Commodity Recommendation and relevant apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242649A true CN109242649A (en) | 2019-01-18 |
Family
ID=65079802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811287656.0A Pending CN109242649A (en) | 2018-10-31 | 2018-10-31 | A kind of Method of Commodity Recommendation and relevant apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242649A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689383A (en) * | 2019-10-12 | 2020-01-14 | 腾讯科技（深圳）有限公司 | Information pushing method and device, server and storage medium |
| CN111292164A (en) * | 2020-01-21 | 2020-06-16 | 上海风秩科技有限公司 | Commodity recommendation method and device, electronic equipment and readable storage medium |
| CN111553763A (en) * | 2020-04-26 | 2020-08-18 | 上海风秩科技有限公司 | Article recommendation method and device, electronic equipment and readable storage medium |
| CN111754300A (en) * | 2020-06-22 | 2020-10-09 | 深圳市分期乐网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
| CN111951049A (en) * | 2020-08-14 | 2020-11-17 | 中国工商银行股份有限公司 | Commodity similarity-based recommendation method and device |
| CN112232880A (en) * | 2019-12-23 | 2021-01-15 | 北京来也网络科技有限公司 | Commodity recommendation method and device combining RPA and AI |
| CN112925993A (en) * | 2021-04-08 | 2021-06-08 | 国网电子商务有限公司 | Collaborative filtering recommendation method and device, storage medium and equipment |
| CN112966098A (en) * | 2021-03-15 | 2021-06-15 | 中国美术学院 | Product and matching supply relation visualization method and system thereof |
| CN113065919A (en) * | 2021-04-08 | 2021-07-02 | 北京京东乾石科技有限公司 | Data pushing method and device |
| CN113077319A (en) * | 2021-04-19 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | Dynamic recommendation method and device for micro detail page |
| CN113327151A (en) * | 2021-06-03 | 2021-08-31 | 广州华多网络科技有限公司 | Commodity object recommendation method and device, computer equipment and storage medium |
| CN113327145A (en) * | 2020-02-28 | 2021-08-31 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device |
| CN116029798A (en) * | 2023-03-22 | 2023-04-28 | 北京新发地农产品网络配送中心有限责任公司 | User demand recommendation method, system, electronic equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106372961A (en) * | 2016-08-23 | 2017-02-01 | 北京小米移动软件有限公司 | Commodity recommendation method and device |
| CN108198051A (en) * | 2018-03-01 | 2018-06-22 | 口碑(上海)信息技术有限公司 | Across the Method of Commodity Recommendation and device of merchandise classification |
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
-
2018
- 2018-10-31 CN CN201811287656.0A patent/CN109242649A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106372961A (en) * | 2016-08-23 | 2017-02-01 | 北京小米移动软件有限公司 | Commodity recommendation method and device |
| CN108665329A (en) * | 2017-03-29 | 2018-10-16 | 北京京东尚科信息技术有限公司 | A kind of Method of Commodity Recommendation based on user browsing behavior |
| CN108198051A (en) * | 2018-03-01 | 2018-06-22 | 口碑(上海)信息技术有限公司 | Across the Method of Commodity Recommendation and device of merchandise classification |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689383A (en) * | 2019-10-12 | 2020-01-14 | 腾讯科技（深圳）有限公司 | Information pushing method and device, server and storage medium |
| CN110689383B (en) * | 2019-10-12 | 2023-08-22 | 腾讯科技（深圳）有限公司 | Information pushing method, device, server and storage medium |
| CN112232880A (en) * | 2019-12-23 | 2021-01-15 | 北京来也网络科技有限公司 | Commodity recommendation method and device combining RPA and AI |
| CN112232880B (en) * | 2019-12-23 | 2024-04-09 | 北京来也网络科技有限公司 | Goods recommendation method and device combining RPA and AI |
| CN111292164A (en) * | 2020-01-21 | 2020-06-16 | 上海风秩科技有限公司 | Commodity recommendation method and device, electronic equipment and readable storage medium |
| CN113327145A (en) * | 2020-02-28 | 2021-08-31 | 北京沃东天骏信息技术有限公司 | Article recommendation method and device |
| CN111553763A (en) * | 2020-04-26 | 2020-08-18 | 上海风秩科技有限公司 | Article recommendation method and device, electronic equipment and readable storage medium |
| CN111553763B (en) * | 2020-04-26 | 2023-03-24 | 上海风秩科技有限公司 | Article recommendation method and device, electronic equipment and readable storage medium |
| CN111754300A (en) * | 2020-06-22 | 2020-10-09 | 深圳市分期乐网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
| CN111951049A (en) * | 2020-08-14 | 2020-11-17 | 中国工商银行股份有限公司 | Commodity similarity-based recommendation method and device |
| CN112966098A (en) * | 2021-03-15 | 2021-06-15 | 中国美术学院 | Product and matching supply relation visualization method and system thereof |
| CN113065919A (en) * | 2021-04-08 | 2021-07-02 | 北京京东乾石科技有限公司 | Data pushing method and device |
| CN112925993A (en) * | 2021-04-08 | 2021-06-08 | 国网电子商务有限公司 | Collaborative filtering recommendation method and device, storage medium and equipment |
| CN113077319A (en) * | 2021-04-19 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | Dynamic recommendation method and device for micro detail page |
| CN113327151A (en) * | 2021-06-03 | 2021-08-31 | 广州华多网络科技有限公司 | Commodity object recommendation method and device, computer equipment and storage medium |
| CN116029798A (en) * | 2023-03-22 | 2023-04-28 | 北京新发地农产品网络配送中心有限责任公司 | User demand recommendation method, system, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109242649A (en) | A kind of Method of Commodity Recommendation and relevant apparatus | |
| CN107481114B (en) | Commodity recommendation method and device, electronic commerce system and storage medium | |
| US20150220915A1 (en) | Electronic Smart Wallet | |
| US9460464B2 (en) | Systems and methods for displaying items | |
| CN111292164B (en) | Commodity recommendation method and device, electronic equipment and readable storage medium | |
| CN108269117B (en) | Data pushing and determining method and device and computer terminal | |
| CN107679904A (en) | A kind of method and device of Recommendations | |
| US20140164220A1 (en) | Payment instrument selection | |
| CN114169936A (en) | Method and device for providing preference information | |
| CN110413870A (en) | Method of Commodity Recommendation, device and server | |
| US20190205938A1 (en) | Dynamic product placement based on perceived value | |
| CN103942193A (en) | Information pushing method and device | |
| Joghee | RETRACTED ARTICLE: Internet of Things-assisted E-marketing and distribution framework | |
| JP2014115951A (en) | Apparatus, program and method for optimizing attribute information, apparatus, program and method for selecting recommendation object | |
| JP6522037B2 (en) | Provision apparatus, provision method, and provision program | |
| CN111724229A (en) | Object recommendation method and device, and object display method and device | |
| JP7140588B2 (en) | Decision device, decision method and decision program | |
| CN108596712B (en) | Single-class collaborative filtering method based on article sequence, storage medium and server | |
| WO2017166535A1 (en) | Method and apparatus for uniform settlement of online shopping | |
| CN106030641A (en) | Micropayment compensation for user-generated game content | |
| WO2016109056A1 (en) | Dynamic product placement based on perceived value | |
| CN106919609B (en) | Product information pushing method and device | |
| CN110020135B (en) | Demand determination method, resource recommendation method and related device | |
| CN112651762A (en) | Information determining method, information displaying method, commodity transaction processing method and electronic equipment | |
| CN104751309A (en) | Stock management method and system for electronic transactions by utilizing processor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |