CN107862566A - A kind of Method of Commodity Recommendation and system - Google Patents
A kind of Method of Commodity Recommendation and system Download PDFInfo
- Publication number
- CN107862566A CN107862566A CN201710966780.9A CN201710966780A CN107862566A CN 107862566 A CN107862566 A CN 107862566A CN 201710966780 A CN201710966780 A CN 201710966780A CN 107862566 A CN107862566 A CN 107862566A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- hobby
- purchased
- collection
- 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
-
- 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
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Abstract
The present invention relates to a kind of Method of Commodity Recommendation and system；Method includes：Obtain the purchaser record of user；The item property of commodity has been purchased by default commodity data library inquiry；Item property according to commodity have been purchased matches potential purpose commodity in merchandising database；Recommend potential purpose commodity to user.System includes：Acquisition module is recorded, for obtaining the purchaser record of user；Attribute query module, for having purchased the item property of commodity by default commodity data library inquiry；Matching module, for matching potential purpose commodity in merchandising database according to the item property for having purchased commodity；Recommending module, for recommending potential purpose commodity to user.For electric business platform, active marketing is carried out to user, Consumer's Experience is favorably improved and increases the satisfaction of user；For user, according to the potential purpose commodity of the purchaser record personalized recommendation of user, time and cost are selected in saving.
Description
Technical field
The present invention relates to e-commerce field, more particularly to a kind of Method of Commodity Recommendation and system.
Background technology
Ecommerce is the commercial activity centered on the exchange of commodities using information network technique as means.Ecommerce pole
The earth effect life style of people, when needing certain commodity, more and more people are more willing to buy by electric business platform.
This brings strong impact to traditional business model, while also welcomes the opportunity of preciousness for the development of ecommerce.
Type of merchandize number on electric business platform is various, and user requires a great deal of time just can be a feast for the eyes
The commodity of oneself needs are selected in commodity.Therefore, electric business platform all can be user's Recommendations.In the prior art, it is generally logical
Cross Sales Volume of Commodity and browse record come it is strong to user's Recommendations, the less pertinence of such mode, it is impossible to accurate recommendation use
Commodity required for family.
The content of the invention
In order to overcome the above-mentioned deficiencies of the prior art, the present invention proposes a kind of Method of Commodity Recommendation and system, by using
The purchaser record analysis item property at family, it is with strong points so as to recommend potential purpose commodity to user, can needed for commodity it is accurate
Recommend user.
The technical scheme that the present invention solves above-mentioned technical problem is as follows：A kind of Method of Commodity Recommendation, specifically includes step：
The purchaser record of user is obtained, is determined to have purchased commodity according to the purchaser record；
The item property of commodity has been purchased by default commodity data library inquiry, has been stored in the merchandising database multigroup
Commodity sign code and item property corresponding to mutually；
Item property according to commodity have been purchased matches potential purpose commodity in merchandising database, exports potential purpose commodity
Corresponding commodity sign code；
First hobby commodity collection is obtained according to the commodity sign code of output, and recommended according to the first hobby commodity collection to user
Potential purpose commodity.
The beneficial effects of the present invention are：Item property is analyzed by the purchaser record of user, it is latent so as to recommend to user
In purpose commodity, specific aim is stronger, and the degree of accuracy is higher.For electric business platform, active marketing is carried out to user, is favorably improved
Consumer's Experience and the satisfaction of increase user；For user, according to the potential purpose business of the purchaser record personalized recommendation of user
Time and cost are selected in product, saving.
Further, default merchandising database specifically includes：
Establish the mapping table of commodity sign code and item property；
Typing instruction is received, is instructed according to typing and commodity sign code and item property is entered into mapping table；
Mapping table is updated, preserves the commodity sign code and item property of new typing；
Specifically, the typing instruction comes from electric business platform or businessman.
The beneficial effect of above-mentioned technical proposal is：By presetting merchandising database, commodity are returned with big data
Class, for as potential purpose goods matching and the basis recommended.Commodity data is established using open data access
Storehouse, electric business platform can update mapping table, and businessman can also update mapping table, multi-faceted collection commodity data, more
Add it is comprehensive and efficient, realization match exactly and recommend potential purpose commodity.
Further, the item property includes direct application field and the type of merchandise, according to the item property for having purchased commodity
Potential purpose commodity are matched in merchandising database to specifically include：
Obtain the item property for having purchased commodity；
Direct application field according to commodity have been purchased determines matching range, and the matching range is with having purchased the direct of commodity
Other commodity of application field identical；The type of merchandise according to commodity have been purchased is associated in matching range, obtains potential meaning
To the type of merchandise of commodity；
Calculate relevant parameter of each commodity with having purchased commodity, the relevant parameter in the type of merchandise of potential purpose commodity
For characterizing the Matching Relationship between commodity；Specifically, relevant parameter is calculated according to minutia, quantifies the supporting pass between commodity
System, the minutia are commodity function and commodity price etc., and the process for calculating relevant parameter is according to commodity function or business
The potential purpose commodity of product calculation of price and the relevant parameter for having purchased commodity；
It is ranked up according to relevant parameter, obtains more than one potential purpose commodity, and is sequentially output according to sequence potential
The commodity sign code of purpose commodity.
The beneficial effect of above-mentioned technical proposal is：Each commodity have its corresponding item property, including directly apply
Field and the type of merchandise, potential purpose commodity are determined according to item property analysis, and according to matching somebody with somebody between relevant parameter quantization commodity
Set relation, potential purpose commodity can be recommended to user from commodity has been purchased；In addition, commodity have been purchased with different commodity
There is different Matching Relationships, be ranked up according to relevant parameter, obtain more than one potential purpose commodity, allow client to have more multiselect
Select, improve the success rate of commercial product recommending.
Further, it is additionally included in the first hobby commodity collection and potential purpose business is matched according to the purchaser record of other users
Product, the second hobby commodity collection is obtained, and potential purpose commodity are recommended to user according to the second hobby commodity collection, specifically included：
According to the commodity sign code for having purchased commodity, the purchaser record that have purchased the other users for having purchased commodity is filtered out；
According to the purchaser record of other users, when analysis other users are purchasing commodity in the first hobby commodity collection
The coordinates bought；
Count the sales volume of all coordinates；
Be ranked up according to the sales volume of coordinates, obtain more than one potential purpose commodity, and according to sequence according to
The commodity sign code of the secondary potential purpose commodity of output, the second hobby commodity collection is obtained, and like commodity collection to user according to second
Recommend potential purpose commodity.
The beneficial effect of above-mentioned technical proposal is：Potential purpose business is determined according to the analysis of the purchaser record of other users
Product, the coordinates that user can also buy when having purchased commodity is analyzed on the whole, can be needed from the consumption of general user
Hair is obtained, recommends potential purpose commodity to user；Combined with above-mentioned according to the potential purpose commodity of item property matching, in the first happiness
Potential purpose commodity are matched according to the purchaser record of other users in good commodity collection, gone out from item property and the angle of user's request
Recommendations are sent out, further improve the success rate of commercial product recommending；The sales volume of coordinates reflect to a certain extent with
The Matching Relationship of commodity has been purchased, has been ranked up according to sales volume, more than one potential purpose commodity has been obtained, allows client to have more
Selection.
Further, it is additionally included in the second hobby commodity collection and potential purpose is matched according to the consumption habit of the different consumer groups
Commodity, the 3rd hobby commodity collection is obtained, and potential purpose commodity are recommended to user according to the 3rd hobby commodity collection, specifically included：
User is presorted according to age bracket, user is divided into first stage user, second stage user and the 3rd
Phase user；
The consumption habit of first stage user, second stage user and phase III user are analyzed respectively, in the second hobby
The 3rd hobby commodity collection corresponding to each phase user is analyzed in commodity collection, likes commodity described in the 3rd hobby commodity collection
Collection includes more than one potential purpose commodity；
A certain user is analyzed according to purchaser record and belongs to first stage user or second stage user or phase III user,
Determine the 3rd hobby commodity collection corresponding to the user；
The 3rd hobby commodity collection exports the commodity sign code of potential purpose commodity according to corresponding to the user, and is pushed away to user
Recommend potential purpose commodity.
The beneficial effect of above-mentioned technical proposal is：In traditional business model, the people of each age level can be relatively more flat
Participate；Different from traditional business model, the consumer groups of the main force of ecommerce more concentrate, directive property is stronger.Cause
This, presorts the different consumer groups to user according to age bracket, analyzes and likes corresponding to the consumer of each age bracket
Commodity collection, the age bracket of user is analyzed further according to purchaser record, so as to recommend potential purpose commodity in corresponding hobby commodity collection.
Combined with above-mentioned from item property and the angle Recommendations of user's request, add from this dimension of consumption habit, enter
One step improves the success rate of commercial product recommending.
The technical scheme that the present invention solves above-mentioned technical problem is as follows：A kind of commercial product recommending system, including：
Acquisition module is recorded, commodity have been purchased for obtaining the purchaser record of user, and according to purchaser record determination；
Attribute query module, for having purchased the item property of commodity, the commodity by default commodity data library inquiry
Multigroup mutually corresponding commodity sign code and item property are stored in database；
Matching module, for matching potential purpose commodity in merchandising database according to the item property for having purchased commodity, and
Export commodity sign code corresponding to potential purpose commodity；
Recommending module, for obtaining the first hobby commodity collection according to the commodity sign code of output, and according to the first hobby business
Product collection recommends potential purpose commodity to user.
Further, a kind of commercial product recommending system, in addition to for presetting the database module of merchandising database, the data
Library module includes：
Relation table establishes unit, for establishing the mapping table of commodity sign code and item property；
Typing unit, for receiving typing instruction, and instructed according to typing and commodity sign code and item property are entered into
In mapping table；
Storage unit, for updating mapping table, and preserve the commodity sign code and item property of new typing.
Further, the item property includes direct application field and the type of merchandise, and the matching module includes：
Attribute acquiring unit, the item property of commodity is purchased for obtaining；
Field determining unit, for determining matching range, the matching range according to the direct application field for having purchased commodity
For direct other commodity of application field identical with having purchased commodity；
Type association unit, for being associated according to the type of merchandise for having purchased commodity in matching range, obtain potential
The type of merchandise of purpose commodity；
Parameter calculation unit, each commodity are with having purchased associating for commodity in the type of merchandise for calculating potential purpose commodity
Parameter, the relevant parameter are used to characterize the Matching Relationship between commodity；
Output unit, for being ranked up according to relevant parameter, more than one potential purpose commodity is obtained, and according to sequence
It is sequentially output the commodity sign code of potential purpose commodity.
Further, the matching module is additionally operable to be matched according to the purchaser record of other users in the first hobby commodity collection
Potential purpose commodity, the second hobby commodity collection is obtained, and potential purpose commodity, institute are recommended to user according to the second hobby commodity collection
Stating matching module also includes：
Screening unit is recorded, for according to the commodity sign codes of commodity has been purchased, filtering out other that have purchased and purchased commodity
The purchaser record of user；
Supporting analytic unit, for the purchaser record according to other users, other use are analyzed in the first hobby commodity collection
The coordinates that family is bought when having purchased commodity；
Quantity statistics unit, for counting the sales volume of all coordinates；
The output unit is additionally operable to be ranked up according to the sales volume of coordinates, obtains more than one potential purpose
Commodity, and the commodity sign code for being sequentially output potential purpose commodity according to sorting, obtain the second hobby commodity collection, and according to second
Like commodity collection and recommend potential purpose commodity to user.
Further, the matching module is additionally operable in the second hobby commodity collection according to the consumption habit of the different consumer groups
Potential purpose commodity are matched, obtain the 3rd hobby commodity collection, and potential purpose business is recommended to user according to the 3rd hobby commodity collection
Product, the matching module also include：
Presort unit, for being presorted according to age bracket to user, user is divided into first stage user, second
Phase user and phase III user；
Analytic unit is liked, for analyzing disappearing for first stage user, second stage user and phase III user respectively
Take custom, the 3rd hobby commodity collection corresponding to each phase user, the 3rd hobby are analyzed in the second hobby commodity collection
Commodity collection includes more than one potential purpose commodity；
Category analysis unit, for being analyzed according to purchaser record, a certain user belongs to first stage user or second stage is used
Family or phase III user, and determine the 3rd hobby commodity collection corresponding to the user；
The output unit is additionally operable to the business that the 3rd hobby commodity collection according to corresponding to the user exports potential purpose commodity
Product identification code, and recommend potential purpose commodity to user.
Brief description of the drawings
Fig. 1 is a kind of flow chart of Method of Commodity Recommendation of the present invention；
Fig. 2 is a kind of schematic diagram of commercial product recommending system of the present invention.
In accompanying drawing, the list of parts representated by each label is as follows：
1st, acquisition module is recorded, 2, attribute query module, 3, matching module, 4, recommending module, 5, database module.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
As shown in figure 1, Fig. 1 is a kind of flow chart of Method of Commodity Recommendation of the present invention.A kind of Method of Commodity Recommendation, specific bag
Include step：
S1. the purchaser record of user is obtained, is determined to have purchased commodity according to the purchaser record；
S2. the item property of commodity has been purchased by default commodity data library inquiry, has been stored in the merchandising database
Multigroup mutually corresponding commodity sign code and item property；
S3. potential purpose commodity are matched in merchandising database according to the item property for having purchased commodity, exports potential purpose
Commodity sign code corresponding to commodity；
S4. the first hobby commodity collection is obtained according to the commodity sign code of output, and likes commodity collection to user according to first
Recommend potential purpose commodity.
User can leave purchaser record when being done shopping on electric business platform, can determine some user's by purchaser record
Commodity are purchased, so that it is determined which commodity the user has.The present invention is exactly the commodity possessed from user, by dividing
Analysis item property matches to obtain potential purpose commodity, and recommends potential purpose commodity to user.Potential purpose commodity are user
Possible commodity interested and related to having purchased commodity.The effect of commodity sign code is to identify and distinguish between different commodity, such as A
The commodity sign code of commodity is ABC123, and the commodity sign code of B commodity is DEF456, facilitates system identification.Pass through user's
Purchaser record analyzes item property, and so as to recommend potential purpose commodity to user, specific aim is stronger, and the degree of accuracy is higher.To electric business
For platform, active marketing is carried out to user, Consumer's Experience is favorably improved and increases the satisfaction of user；For user,
According to the potential purpose commodity of the purchaser record personalized recommendation of user, time and cost are selected in saving.
Specifically, default merchandising database specifically includes：
Establish the mapping table of commodity sign code and item property；Merchandising database is by preserving commodity sign code and right
The mapping table of item property is answered to form；
Typing instruction is received, is instructed according to typing and commodity sign code and item property is entered into mapping table；Its
In, typing instruction can be sent by the operation maintenance personnel of electric business platform, can also be sent by businessman；That is, electric business platform can be voluntarily
Merchandising database is improved in exploitation, can also open to businessman, merchandising database is improved jointly with businessman；
Mapping table is updated, preserves the commodity sign code and item property of new typing.
, all can the new commodity sign code of typing and business when receiving typing instruction every time after the completion of mapping table is established
Product attribute is recorded, while also updates mapping table to preserve the commodity sign code of new typing and item property.
By presetting merchandising database, commodity are sorted out with big data, for as potential purpose goods matching
With the basis of recommendation.Merchandising database is established using open data access, electric business platform can update mapping relations
Table, businessman can also update mapping table, and multi-faceted collection commodity data is more comprehensively and efficient, and realization matches exactly
With the potential purpose commodity of recommendation.
Preferably, potential purpose commodity are matched in merchandising database according to the item property for having purchased commodity to specifically include：
The item property for having purchased commodity is obtained, the item property includes direct application field and the type of merchandise；Illustrate
Bright item property：Direct application field include digital product, family product, dress ornament, with articles for use etc.；By taking digital product as an example,
The type of merchandise includes mobile phone, tablet personal computer, slr camera etc.；It above are only for example, direct application field and commodity class
Type is not limited only to this；
Direct application field according to commodity have been purchased determines matching range, and the matching range is with having purchased the direct of commodity
Other commodity of application field identical；As when to have purchased commodity be digital product, matching range is defined as direct application field to count
Other commodity of code product；
The type of merchandise according to commodity have been purchased is associated in matching range, obtains the commodity class of potential purpose commodity
Type；As when to have purchased commodity be digital camera, its peripheral product or auxiliary products, potential purpose commodity are determined according to commodity have been purchased
The type of merchandise should be corresponding with digital camera camera battery, RAM card and camera lens etc.；
Calculate relevant parameter of each commodity with having purchased commodity, the relevant parameter in the type of merchandise of potential purpose commodity
For characterizing the Matching Relationship between commodity；Specifically, relevant parameter is calculated according to minutia, quantifies the supporting pass between commodity
System, the minutia are commodity function and commodity price etc., and the process for calculating relevant parameter is according to commodity function or business
The potential purpose commodity of product calculation of price and the relevant parameter for having purchased commodity；For example, when it is quilt to have purchased commodity, according to commodity work(
Potential purpose commodity can be analyzed as quilt cover, pillow and mosquito net etc.；
It is ranked up according to relevant parameter, obtains more than one potential purpose commodity, and is sequentially output according to sequence potential
The commodity sign code of purpose commodity；For example, when it is quilt to have purchased commodity, the Matching Relationship of quilt cover, pillow and mosquito net and quilt
Successively decrease, so corresponding relevant parameter is also to successively decrease.It is quilt cover, pillow and mosquito to obtain potential purpose commodity according to relevant parameter
The commodity sign code of account, successively quilt cover, pillow and mosquito net.
Each commodity have its corresponding item property, including direct application field and the type of merchandise, according to item property
Analysis determines potential purpose commodity, and quantifies the Matching Relationship between commodity according to relevant parameter, can go out in itself from commodity have been purchased
Hair, recommend potential purpose commodity to user；In addition, purchased commodity has different Matching Relationships with different commodity, join according to association
Number is ranked up, and is obtained more than one potential purpose commodity, is allowed client to have more more options, improve the success rate of commercial product recommending.
Preferably, it is additionally included in the first hobby commodity collection and potential purpose business is matched according to the purchaser record of other users
Product, the second hobby commodity collection is obtained, and potential purpose commodity are recommended to user according to the second hobby commodity collection, specifically included：
According to the commodity sign code for having purchased commodity, the purchaser record that have purchased the other users for having purchased commodity is filtered out；Such as A
The commodity sign code of commodity is ABC123, filters out the purchase that have purchased the other users that commodity sign code is ABC123 corresponding goods
Buy record；
According to the purchaser record of other users, when analysis other users are purchasing commodity in the first hobby commodity collection
The coordinates bought；The coordinates that other users can also be bought when buying A commodity is determined, if user is in bull's machine
When, it may can also buy the coordinates such as diaphragm and protective case；
Count the sales volume of all coordinates；
Be ranked up according to the sales volume of coordinates, obtain more than one potential purpose commodity, and according to sequence according to
The commodity sign code of the secondary potential purpose commodity of output, the second hobby commodity collection is obtained, and like commodity collection to user according to second
Recommend potential purpose commodity；As user can also buy A diaphragms and B diaphragms in bull's machine, and in this premise of bull's machine
Under, higher than the sales volume of B diaphragms, now available potential purpose commodity are that A diaphragms and B are protected for the sale of A diaphragms
Film, and preferential recommendation A diaphragms.
Potential purpose commodity are determined according to the analysis of the purchaser record of other users, user is analyzed on the whole and is purchasing
The coordinates that can be also bought during commodity, potential purpose commodity can be recommended to user from the consumption demand of general user；
Combined according to the potential purpose commodity of item property matching with above-mentioned, while recommended from item property and the angle of user's request
Commodity, further improve the success rate of commercial product recommending；The sales volume of coordinates reflects and has purchased business to a certain extent
The Matching Relationship of product, is ranked up according to sales volume, obtains more than one potential purpose commodity, allows client to have more more options.
Preferably, it is additionally included in the second hobby commodity collection and potential purpose is matched according to the consumption habit of the different consumer groups
Commodity, the 3rd hobby commodity collection is obtained, and potential purpose commodity are recommended to user according to the 3rd hobby commodity collection, specifically included：
User is presorted according to age bracket, user is divided into first stage user, second stage user and the 3rd
Phase user；Wherein, first stage user is 18-23 year, mostly User；Second stage user is 24-30 year, mostly non-
Student, the user just to work；Second stage user is more than 31 years old, the user for the longer period of time that mostly worked；Above-mentioned year
Age section is only for example, and can be presorted as required in practical application；
The consumption habit of first stage user, second stage user and phase III user are analyzed respectively, in the second hobby
The 3rd hobby commodity collection corresponding to each phase user is analyzed in commodity collection, the 3rd hobby commodity collection includes more than one
Potential purpose commodity；Specifically, consumption habit is analyzed according to the method for big data, if first stage user is mostly User,
And analyzed by big data, the hobby commodity collection of User generally includes sporting goods, digital product, clothes, snacks, books
Deng therefore, hobby commodity collection includes the potential purpose commodity such as digital product, snacks, books corresponding to first stage user；
A certain user is analyzed according to purchaser record and belongs to first stage user or second stage user or phase III user,
Determine the 3rd hobby commodity collection corresponding to the user；Specifically, analysis purchaser record judges that the user belongs to first stage user
Either second stage user or phase III user, the ship-to for such as working as certain user is office building, and more purchase lunch break beds,
During the commodity such as boudoir, eyedrops, breakfast, can determine whether the user is second stage user or phase III user, is further confirmed that
Corresponding hobby commodity collection；
The 3rd hobby commodity collection exports the commodity sign code of potential purpose commodity according to corresponding to the user, and is pushed away to user
Recommend potential purpose commodity.
In traditional business model, the people of each age level can more fifty-fifty participate；Different from traditional commerce
Pattern, the consumer groups of the main force of ecommerce more concentrate, directive property is stronger.Therefore, the different consumer groups according to age bracket
User is presorted, analyzes hobby commodity collection corresponding to the consumer of each age bracket, analyzes and uses further according to purchaser record
The age bracket at family, so as to recommend potential purpose commodity in corresponding hobby commodity collection.With above-mentioned from item property and user's request
Angle set out Recommendations combination, add from this dimension of consumption habit, further improve the success rate of commercial product recommending.
As shown in Fig. 2 a kind of commercial product recommending system, including：
Acquisition module 1 is recorded, commodity have been purchased for obtaining the purchaser record of user, and according to purchaser record determination；
Attribute query module 2, for having purchased the item property of commodity, the commodity by default commodity data library inquiry
Multigroup mutually corresponding commodity sign code and item property are stored in database；
Matching module 3, for matching potential purpose commodity in merchandising database according to the item property for having purchased commodity, and
Export commodity sign code corresponding to potential purpose commodity；
Recommending module 4, for obtaining the first hobby commodity collection according to the commodity sign code of output, and according to the first hobby business
Product collection recommends potential purpose commodity to user.
A kind of commercial product recommending system, in addition to for presetting the database module 5 of merchandising database, the database module
5 include：
Relation table establishes unit, for establishing the mapping table of commodity sign code and item property；
Typing unit, for receiving typing instruction, and instructed according to typing and commodity sign code and item property are entered into
In mapping table；
Storage unit, for updating mapping table, and preserve the commodity sign code and item property of new typing.
The item property includes direct application field and the type of merchandise, and the matching module 3 includes：
Attribute acquiring unit, the item property of commodity is purchased for obtaining；
Field determining unit, for determining matching range, the matching range according to the direct application field for having purchased commodity
For direct other commodity of application field identical with having purchased commodity；
Type association unit, for being associated according to the type of merchandise for having purchased commodity in matching range, obtain potential
The type of merchandise of purpose commodity；
Parameter calculation unit, each commodity are with having purchased associating for commodity in the type of merchandise for calculating potential purpose commodity
Parameter, the relevant parameter are used to characterize the Matching Relationship between commodity；
Output unit, for being ranked up according to relevant parameter, more than one potential purpose commodity is obtained, and according to sequence
It is sequentially output the commodity sign code of potential purpose commodity.
The matching module 3 is additionally operable to match potential meaning according to the purchaser record of other users in the first hobby commodity collection
To commodity, the second hobby commodity collection is obtained, and potential purpose commodity, the matching are recommended to user according to the second hobby commodity collection
Module 3 also includes：
Screening unit is recorded, for according to the commodity sign codes of commodity has been purchased, filtering out other that have purchased and purchased commodity
The purchaser record of user；
Supporting analytic unit, for the purchaser record according to other users, other use are analyzed in the first hobby commodity collection
The coordinates that family is bought when having purchased commodity；
Quantity statistics unit, for counting the sales volume of all coordinates；
The output unit is additionally operable to be ranked up according to the sales volume of coordinates, obtains more than one potential purpose
Commodity, and the commodity sign code for being sequentially output potential purpose commodity according to sorting, obtain the second hobby commodity collection, and according to second
Like commodity collection and recommend potential purpose commodity to user.
The matching module 3 is additionally operable to be matched according to the consumption habit of the different consumer groups in the second hobby commodity collection and dived
In purpose commodity, the 3rd hobby commodity collection is obtained, and potential purpose commodity are recommended to user according to the 3rd hobby commodity collection, it is described
Matching module 3 also includes：
Presort unit, for being presorted according to age bracket to user, user is divided into first stage user, second
Phase user and phase III user；
Analytic unit is liked, for analyzing disappearing for first stage user, second stage user and phase III user respectively
Take custom, the 3rd hobby commodity collection corresponding to each phase user, the 3rd hobby are analyzed in the second hobby commodity collection
Commodity collection includes more than one potential purpose commodity；
Category analysis unit, for being analyzed according to purchaser record, a certain user belongs to first stage user or second stage is used
Family or phase III user, and determine the 3rd hobby commodity collection corresponding to the user；
The output unit is additionally operable to according to the 3rd commodity sign code liked commodity collection and export potential purpose commodity, and to
User recommends potential purpose commodity.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Claims (10)
1. a kind of Method of Commodity Recommendation, it is characterised in that specifically include step：
The purchaser record of user is obtained, is determined to have purchased commodity according to the purchaser record；
The item property of commodity has been purchased by default commodity data library inquiry, has been stored in the merchandising database multigroup mutual
Corresponding commodity sign code and item property；
Item property according to commodity have been purchased matches potential purpose commodity in merchandising database, and it is corresponding to export potential purpose commodity
Commodity sign code；
First hobby commodity collection is obtained according to the commodity sign code of output, and it is potential to user's recommendation according to the first hobby commodity collection
Purpose commodity.
2. a kind of Method of Commodity Recommendation according to claim 1, it is characterised in that default merchandising database specifically includes：
Establish the mapping table of commodity sign code and item property；
Typing instruction is received, is instructed according to typing and commodity sign code and item property is entered into mapping table；
Mapping table is updated, preserves the commodity sign code and item property of new typing.
3. a kind of Method of Commodity Recommendation according to claim 1 or 2, it is characterised in that the item property includes direct
Application field and the type of merchandise, potential purpose commodity are matched in merchandising database according to the item property for having purchased commodity and specifically wrapped
Include：
Obtain the item property for having purchased commodity；
Direct application field according to commodity have been purchased determines matching range, and the matching range is the direct application with having purchased commodity
Other commodity of field identical；
The type of merchandise according to commodity have been purchased is associated in matching range, obtains the type of merchandise of potential purpose commodity；
Relevant parameter of each commodity with having purchased commodity, the relevant parameter in the type of merchandise of potential purpose commodity is calculated to be used for
Characterize the Matching Relationship between commodity；
It is ranked up according to relevant parameter, obtains more than one potential purpose commodity, and potential purpose is sequentially output according to sequence
The commodity sign code of commodity.
4. a kind of Method of Commodity Recommendation according to claim 3, it is characterised in that be additionally included in the first hobby commodity collection
Potential purpose commodity are matched according to the purchaser record of other users, obtain the second hobby commodity collection, and according to the second hobby commodity
Collect to user and recommend potential purpose commodity, specifically include：
According to the commodity sign code for having purchased commodity, the purchaser record that have purchased the other users for having purchased commodity is filtered out；
According to the purchaser record of other users, purchased when analysis other users are purchasing commodity in the first hobby commodity collection
The coordinates bought；
Count the sales volume of all coordinates；
It is ranked up according to the sales volume of coordinates, obtains more than one potential purpose commodity, and it is defeated successively according to sorting
Go out the commodity sign code of potential purpose commodity, obtain the second hobby commodity collection, and recommend to user according to the second hobby commodity collection
Potential purpose commodity.
5. a kind of Method of Commodity Recommendation according to claim 4, it is characterised in that be additionally included in the second hobby commodity collection
Potential purpose commodity are matched according to the consumption habit of the different consumer groups, obtain the 3rd hobby commodity collection, and according to the 3rd hobby
Commodity collection recommends potential purpose commodity to user, specifically includes：
User is presorted according to age bracket, user is divided into first stage user, second stage user and phase III
User；
The consumption habit of first stage user, second stage user and phase III user are analyzed respectively, like commodity second
The 3rd hobby commodity collection corresponding to each phase user is analyzed in collection, it is potential that the 3rd hobby commodity collection includes more than one
Purpose commodity；
A certain user is analyzed according to purchaser record and belongs to first stage user or second stage user or phase III user, it is determined that
3rd hobby commodity collection corresponding to the user；
The commodity sign code of potential purpose commodity is exported according to the 3rd hobby commodity collection, and recommends potential purpose commodity to user.
A kind of 6. commercial product recommending system, it is characterised in that including：
Acquisition module (1) is recorded, commodity have been purchased for obtaining the purchaser record of user, and according to purchaser record determination；
Attribute query module (2), for having purchased the item property of commodity, the commodity number by default commodity data library inquiry
According to stored in storehouse it is multigroup mutually corresponding to commodity sign code and item property；
Matching module (3), for matching potential purpose commodity in merchandising database according to the item property for having purchased commodity, and it is defeated
Go out commodity sign code corresponding to potential purpose commodity；
Recommending module (4), for obtaining the first hobby commodity collection according to the commodity sign code of output, and according to the first hobby commodity
Collect to user and recommend potential purpose commodity.
7. a kind of commercial product recommending system according to claim 6, it is characterised in that also include being used to preset merchandising database
Database module (5), the database module (5) includes：
Relation table establishes unit, for establishing the mapping table of commodity sign code and item property；
Typing unit, for receiving typing instruction, and instructed according to typing and commodity sign code and item property are entered into mapping
In relation table；
Storage unit, for updating mapping table, and preserve the commodity sign code and item property of new typing.
8. a kind of commercial product recommending system according to claim 6 or 7, it is characterised in that the item property includes direct
Application field and the type of merchandise, the matching module (3) include：
Attribute acquiring unit, the item property of commodity is purchased for obtaining；
Field determining unit, for determining matching range according to the direct application field for having purchased commodity, the matching range be with
Direct other commodity of application field identical of commodity are purchased；
Type association unit, for being associated according to the type of merchandise for having purchased commodity in matching range, obtain potential purpose
The type of merchandise of commodity；
Parameter calculation unit, each commodity associate ginseng with purchased commodity in the type of merchandise for calculating potential purpose commodity
Number, the relevant parameter are used to characterize the Matching Relationship between commodity；
Output unit, for being ranked up according to relevant parameter, more than one potential purpose commodity is obtained, and according to sequence successively
Export the commodity sign code of potential purpose commodity.
9. a kind of commercial product recommending system according to claim 8, it is characterised in that the matching module (3) is additionally operable to
Potential purpose commodity are matched according to the purchaser record of other users in first hobby commodity collection, obtain the second hobby commodity collection, and
Potential purpose commodity are recommended to user according to the second hobby commodity collection, the matching module (3) also includes：
Screening unit is recorded, for according to the commodity sign code for having purchased commodity, filtering out and have purchased the other users for having purchased commodity
Purchaser record；
Supporting analytic unit, for the purchaser record according to other users, analysis other users exist in the first hobby commodity collection
The coordinates bought during commodity is purchased；
Quantity statistics unit, for counting the sales volume of all coordinates；
The output unit is additionally operable to be ranked up according to the sales volume of coordinates, obtains more than one potential purpose business
Product, and the commodity sign code for being sequentially output potential purpose commodity according to sorting, the second hobby commodity collection is obtained, and according to the second happiness
Good commodity collection recommends potential purpose commodity to user.
10. a kind of commercial product recommending system according to claim 9, it is characterised in that the matching module (3) is additionally operable to
Potential purpose commodity are matched according to the consumption habit of the different consumer groups in second hobby commodity collection, obtain the 3rd hobby commodity
Collection, and potential purpose commodity are recommended to user according to the 3rd hobby commodity collection, the matching module (3) also includes：
Presort unit, for being presorted according to age bracket to user, user is divided into first stage user, second stage
User and phase III user；
Like analytic unit, the consumption for analyzing first stage user, second stage user and phase III user respectively is practised
It is used, the 3rd hobby commodity collection corresponding to each phase user, the 3rd hobby commodity are analyzed in the second hobby commodity collection
Collection includes more than one potential purpose commodity；
Category analysis unit, for according to purchaser record analyze a certain user belong to first stage user or second stage user or
Phase III user, and determine the 3rd hobby commodity collection corresponding to the user；
The output unit is additionally operable to the commodity mark that the 3rd hobby commodity collection according to corresponding to the user exports potential purpose commodity
Know code, and recommend potential purpose commodity to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710966780.9A CN107862566A (en) | 2017-10-17 | 2017-10-17 | A kind of Method of Commodity Recommendation and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710966780.9A CN107862566A (en) | 2017-10-17 | 2017-10-17 | A kind of Method of Commodity Recommendation and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107862566A true CN107862566A (en) | 2018-03-30 |
Family
ID=61696245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710966780.9A Pending CN107862566A (en) | 2017-10-17 | 2017-10-17 | A kind of Method of Commodity Recommendation and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107862566A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034980A (en) * | 2018-08-23 | 2018-12-18 | 深圳码隆科技有限公司 | A kind of collocation Method of Commodity Recommendation, device and user terminal |
| CN109034972A (en) * | 2018-07-24 | 2018-12-18 | 合肥爱玩动漫有限公司 | Commodity method for pushing based on player preferences in a kind of game |
| CN109147188A (en) * | 2018-07-25 | 2019-01-04 | 厦门理工学院 | A kind of method and apparatus of intelligence tea table identification water filling |
| CN109242612A (en) * | 2018-08-22 | 2019-01-18 | 中国平安人寿保险股份有限公司 | A kind of method and apparatus of Products Show |
| CN109544298A (en) * | 2018-11-23 | 2019-03-29 | 丁娜 | A kind of information dissemination method and system based on block chain technology |
| WO2020085086A1 (en) * | 2018-10-23 | 2020-04-30 | 株式会社ピーステックラボ | Commodity recommendation system |
| CN112001777A (en) * | 2020-08-24 | 2020-11-27 | 知小二(广州)科技有限公司 | E-commerce platform data analysis system based on cloud computing |
| CN112580686A (en) * | 2020-11-19 | 2021-03-30 | 青岛檬豆网络科技有限公司 | Aluminum electrolytic capacitor purchase prediction method based on Markov distance KNN algorithm |
| CN112950304A (en) * | 2019-12-11 | 2021-06-11 | 北京沃东天骏信息技术有限公司 | Information pushing method, device, equipment and storage medium |
| CN113610608A (en) * | 2021-08-19 | 2021-11-05 | 创优数字科技(广东)有限公司 | User preference recommendation method and device, electronic equipment and storage medium |
| CN113643099A (en) * | 2021-08-30 | 2021-11-12 | 北京沃东天骏信息技术有限公司 | Commodity data processing method, commodity data processing device, commodity data processing apparatus, storage medium, and program product |
| CN113657935A (en) * | 2021-08-16 | 2021-11-16 | 中网赢商(苏州)信息技术有限公司 | Network marketing system and working method thereof |
| CN113744019A (en) * | 2021-01-12 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254028A (en) * | 2011-07-22 | 2011-11-23 | 青岛理工大学 | Personalized commodity recommending method and system which integrate attributes and structural similarity |
| CN102609869A (en) * | 2012-02-03 | 2012-07-25 | 纽海信息技术（上海）有限公司 | Commodity purchasing system and method |
| CN103544632A (en) * | 2013-07-22 | 2014-01-29 | 杭州师范大学 | Method and system for individually recommending network commodities |
| CN104599160A (en) * | 2015-02-06 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Commodity recommendation method and commodity recommendation device |
| CN106411908A (en) * | 2016-10-13 | 2017-02-15 | 网易乐得科技有限公司 | Recommendation method and device |
-
2017
- 2017-10-17 CN CN201710966780.9A patent/CN107862566A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254028A (en) * | 2011-07-22 | 2011-11-23 | 青岛理工大学 | Personalized commodity recommending method and system which integrate attributes and structural similarity |
| CN102609869A (en) * | 2012-02-03 | 2012-07-25 | 纽海信息技术（上海）有限公司 | Commodity purchasing system and method |
| CN103544632A (en) * | 2013-07-22 | 2014-01-29 | 杭州师范大学 | Method and system for individually recommending network commodities |
| CN104599160A (en) * | 2015-02-06 | 2015-05-06 | 腾讯科技（深圳）有限公司 | Commodity recommendation method and commodity recommendation device |
| CN106411908A (en) * | 2016-10-13 | 2017-02-15 | 网易乐得科技有限公司 | Recommendation method and device |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109034972A (en) * | 2018-07-24 | 2018-12-18 | 合肥爱玩动漫有限公司 | Commodity method for pushing based on player preferences in a kind of game |
| CN109147188A (en) * | 2018-07-25 | 2019-01-04 | 厦门理工学院 | A kind of method and apparatus of intelligence tea table identification water filling |
| CN109242612A (en) * | 2018-08-22 | 2019-01-18 | 中国平安人寿保险股份有限公司 | A kind of method and apparatus of Products Show |
| CN109242612B (en) * | 2018-08-22 | 2023-06-27 | 中国平安人寿保险股份有限公司 | Product recommendation method and device |
| CN109034980A (en) * | 2018-08-23 | 2018-12-18 | 深圳码隆科技有限公司 | A kind of collocation Method of Commodity Recommendation, device and user terminal |
| CN109034980B (en) * | 2018-08-23 | 2021-12-28 | 深圳码隆科技有限公司 | Collocation commodity recommendation method and device and user terminal |
| WO2020085086A1 (en) * | 2018-10-23 | 2020-04-30 | 株式会社ピーステックラボ | Commodity recommendation system |
| CN109544298A (en) * | 2018-11-23 | 2019-03-29 | 丁娜 | A kind of information dissemination method and system based on block chain technology |
| CN112950304A (en) * | 2019-12-11 | 2021-06-11 | 北京沃东天骏信息技术有限公司 | Information pushing method, device, equipment and storage medium |
| CN112001777A (en) * | 2020-08-24 | 2020-11-27 | 知小二(广州)科技有限公司 | E-commerce platform data analysis system based on cloud computing |
| CN112580686A (en) * | 2020-11-19 | 2021-03-30 | 青岛檬豆网络科技有限公司 | Aluminum electrolytic capacitor purchase prediction method based on Markov distance KNN algorithm |
| CN112580686B (en) * | 2020-11-19 | 2023-05-02 | 青岛檬豆网络科技有限公司 | KNN algorithm aluminum electrolytic capacitor purchase prediction method based on Mahalanobis distance |
| CN113744019A (en) * | 2021-01-12 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
| CN113657935A (en) * | 2021-08-16 | 2021-11-16 | 中网赢商(苏州)信息技术有限公司 | Network marketing system and working method thereof |
| CN113610608A (en) * | 2021-08-19 | 2021-11-05 | 创优数字科技(广东)有限公司 | User preference recommendation method and device, electronic equipment and storage medium |
| CN113643099A (en) * | 2021-08-30 | 2021-11-12 | 北京沃东天骏信息技术有限公司 | Commodity data processing method, commodity data processing device, commodity data processing apparatus, storage medium, and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862566A (en) | A kind of Method of Commodity Recommendation and system | |
| US20220138831A1 (en) | Method of Providing Fashion Item Recommendation Service Using User's Body Type and Purchase History | |
| US7792706B2 (en) | Method and system of providing recommendations during online shopping | |
| Wong et al. | Intelligent product cross-selling system with radio frequency identification technology for retailing | |
| US8762226B2 (en) | Item discovery tools and methods for shopping in an electronic commerce environment | |
| JP6027679B2 (en) | Method and device for determining hot selling goods for holidays | |
| KR101476613B1 (en) | System for ubiquitous smart shopping | |
| CN106503258A (en) | A kind of precise search method in website station | |
| CN102667777A (en) | Retrieval support system, retrieval support method, and retrieval support program | |
| JP2010524090A (en) | Computer system for rule-based clothing matching and filtering, taking into account fit rules and fashion rules | |
| CN105138690B (en) | The method and apparatus for determining keyword | |
| CN110969512B (en) | Commodity recommendation method and device based on user purchasing behavior | |
| KR20130047799A (en) | System for ubiquitous smart shopping | |
| CN102073737A (en) | Method and system for automatically providing real-time purchasing suggestion for network retailer | |
| US20210383452A1 (en) | Commodity recommendation system | |
| US20140214617A1 (en) | Pricing intelligence for non-identically identified products | |
| KR101707660B1 (en) | An e-commerce system based on interest category using related keywords | |
| CN110287410A (en) | The fusion method of a variety of proposed algorithms of user under a kind of O2O electric business scene | |
| CN113344676A (en) | Electronic commerce big data information management system | |
| CN105321095A (en) | Consumption service system and method for integrating iBeacon indoor positioning technology and information logistics cloud platform through telecommunication | |
| CN112035624A (en) | Text recommendation method and device and storage medium | |
| CN116362831A (en) | Commodity recommendation method and related equipment | |
| JPH0728902A (en) | Analysis system for good seller commodity | |
| Wong et al. | Intelligent apparel product cross-selling using radio frequency identification (RFID) technology for fashion retailing | |
| CN111192114A (en) | Automatic clothing recommendation system and method and background server |
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 |
Application publication date: 20180330 |
|
| RJ01 | Rejection of invention patent application after publication |