CN108537635A - A kind of recommendation method and device of product - Google Patents
A kind of recommendation method and device of product Download PDFInfo
- Publication number
- CN108537635A CN108537635A CN201810296457.XA CN201810296457A CN108537635A CN 108537635 A CN108537635 A CN 108537635A CN 201810296457 A CN201810296457 A CN 201810296457A CN 108537635 A CN108537635 A CN 108537635A
- Authority
- CN
- China
- Prior art keywords
- product
- user
- virtual
- actual products
- virtual product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000003542 behavioural effect Effects 0.000 claims abstract description 21
- 238000013507 mapping Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims description 50
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 238000001556 precipitation Methods 0.000 claims 2
- 238000005516 engineering process Methods 0.000 abstract description 10
- 239000000047 product Substances 0.000 description 164
- 230000006399 behavior Effects 0.000 description 25
- 239000013065 commercial product Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 235000015203 fruit juice Nutrition 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 239000011800 void material Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000013066 combination product Substances 0.000 description 1
- 229940127555 combination product Drugs 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a kind of recommendation method and devices of product, are related to Internet technical field, can redefine product according to short-life cycle product characteristic, are that user recommends optimal product in conjunction with mainstream recommended technology.The present invention includes:Obtain the product data of actual products, and therefrom extract attribute information, according to the attribute information extracted, generate virtual product, and record the mapping relations of the actual products and the virtual product, the virtual product is selected according to the behavioral data of user, and according to the mapping relations, obtains actual products to be recommended.The present invention is suitable for the quick recommendation of product, and the user experience is improved.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of recommendation method and devices of product.
Background technology
With the rapid development of internet technology, explosive growth is all presented in information content all the time, in order to allow people
The information of oneself needs can be accurately obtained rapidly, and recommended technology emerges rapidly.Recommended technology is widely used, and is especially led in electric business
Domain is mainly used for recommending the product needed for user.
But current recommended technology group will derive from the analysis to entity products, for example collaborative filtering needs to mark
The product of standardization and abundant user behavior data, content-based recommendation need product information machine readable, easily conclude etc..This
A little data read field, video field etc. and are all easier to obtain in electric business field, news, but for the few finance of attribute latitude
Product is but difficult to obtain this kind of data, and it is difficult to be directly applied to financial field to lead to the recommended technology of mainstream.Especially finance production
The features such as product also have attribute variable at any time, and relativity is strong, and life cycle is short so that current recommended technology is difficult to apply
Financial field.
Invention content
The embodiment of the present invention provides a kind of recommendation method and device of product, can be according to short-life cycle product characteristic, weight
It is new to define product, it is that user recommends optimal product in conjunction with mainstream recommended technology.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that:
Product virtual:To product classification, new product is fictionalized.
User behavior data processing:Convert the behavior of user to the behavior to virtual product.
Virtual product is recommended:Analyze user behavior data, in conjunction with virtual product information, user tag information, user base
Attribute is that user recommends virtual goods.
User preference is analyzed:User's history buying behavior is analyzed, in conjunction with other product attributes of same time and sales information,
Vertical analysis is combined with horizontal analysis, generates user preference label, and such as preference new product label is recognized and raises progress percentage label,
The big amount Product labelling of preference, preference buy number label etc..
Product real-time recommendation:For each virtual product for recommending, in conjunction with user preference label, product information on sale,
The actual products that prediction user needs most.
The method of the present invention analyzes user behavior data, product data, to product secondary classification, from laterally and longitudinally two sides
Surface analysis user preference solves the problems such as product life cycle is short, attribute is variable, the uncertainty of user preference, carries significantly
High recommendation accuracy.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 a, Fig. 1 b are system architecture schematic diagram provided in an embodiment of the present invention;
Fig. 2 is a kind of method flow schematic diagram provided in an embodiment of the present invention;
Fig. 3 is the schematic diagram of specific example provided in an embodiment of the present invention;
Fig. 4 is another method flow schematic diagram provided in an embodiment of the present invention;
Fig. 5 is a kind of schematic device provided in an embodiment of the present invention.
Specific implementation mode
To make those skilled in the art more fully understand technical scheme of the present invention, below in conjunction with the accompanying drawings and specific embodiment party
Present invention is further described in detail for formula.Embodiments of the present invention are described in more detail below, the embodiment is shown
Example is shown in the accompanying drawings, and in which the same or similar labels are throughly indicated same or similar element or has identical or class
Like the element of function.It is exemplary below with reference to the embodiment of attached drawing description, is only used for explaining the present invention, and cannot
It is construed to limitation of the present invention.Those skilled in the art of the present technique are appreciated that unless expressly stated, odd number shape used herein
Formula " one ", "one", " described " and "the" may also comprise plural form.It is to be further understood that the specification of the present invention
The middle wording " comprising " used refers to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that
Other one or more features of presence or addition, integer, step, operation, element, component and/or their group.It should be understood that
When we say that an element is " connected " or " coupled " to another element, it can be directly connected or coupled to other elements, or
There may also be intermediary elements.In addition, " connection " used herein or " coupling " may include being wirelessly connected or coupling.Here make
Wording "and/or" includes any cell of one or more associated list items and all combines.The art
Technical staff is appreciated that unless otherwise defined all terms (including technical terms and scientific terms) used herein have
Meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.It should also be understood that such as general
Term, which should be understood that, those of defined in dictionary has a meaning that is consistent with the meaning in the context of the prior art, and
Unless being defined as here, will not be explained with the meaning of idealization or too formal.
The embodiment of the present invention specifically may be implemented in a kind of system as shown in Figure 1a, wherein:
Analysis Service implement body can be the server apparatus being individually made, such as:Rack, blade, tower or machine
Cabinet type server apparatus can also use work station, mainframe computer etc. to have stronger computing capability hardware device;It can also
The server cluster being made of multiple server apparatus.
User data and product data are run in Database Systems, for storing and managing user data and product data.
Database Systems specifically can be individually made, and the Analysis server of management, storage for data, can also be by multiple
The server cluster of Analysis server composition.The data of correspondence analysis server are run on the hardware device of Database Systems
Library, the data for managing and storing Analysis server.Common network database (Network specifically may be used
Database), relation data (Relational Database), tree shaped data library (Hierarchical Database), face
To object database (Object-oriented Database) and big data system architecture of new generation.
Analysis Service implement body can also be integrated in Database Systems, such as:By the partial analysis in server cluster
Server is divided into front-end server, is used to that with user terminal interaction data, this front-end server analysis clothes can be known as
Business device;And by server cluster another part server and most storage device (such as disk array, caching machine
Deng) all can serve as background data base and provide data access service for front-end server, and described in safeguarding on background data base
Problem base.
Optionally, system as shown in Figure 1 b can also include user terminal, and can specifically make independent one in fact is
System, or be integrated in a variety of different business application systems, such as smart mobile phone, tablet computer (Tablet Personal
Computer), laptop computer (Laptop Computer) or personal digital assistant (personal digital
Assistant, abbreviation PDA) etc..Application interface can be shown, in application interface by the application program of installation on user terminal
In specifically show the product information on sale of Analysis server transmission, and show and return to the response message of Analysis server, from
And " session " between user terminal and Analysis server is formed, and show the operation user of user terminal.
The embodiment of the present invention provides a kind of recommendation method of product, can specifically be realized by Analysis server, such as Fig. 2 institutes
Show, including:
S1, the product data for obtaining actual products, and therefrom extract attribute information.
Wherein, the actual products refer to specific product on sale, such as:According to the finance and money management production of fixed amount sale
Product, loan product etc..Wherein, actual products can be the finance and money management product of sale of having designed or reached the standard grade,
It can be fruit juice, the daily product that disappear soon, this kind of finance and money management product or the daily product that disappear soon such as the food, the paper handkerchief that now do, all have
Sales cycle is short, life of product is short, and this kind of product is commonly known as short-life cycle product, or is Short Lifecycle Products (Short
Life Cycle Products), refer to the product that market value is devalued within the shorter time.According to its devaluation
Property, Short Lifecycle Products can be divided into physics devaluation matter product, such as fresh flower and value devaluation product, as computer is hard
Part etc..The preference of technological progress and customer make the speed of model change constantly accelerate, and many products are because superseded and rapid
Devalue, such as the products such as computer, electronic product, electrical equipment, automobile and fashionable dress.This kind of product has other opposite products
Shorter sales cycle, and usually only primary order chance copes with best selling period, such as:Many on-line finance financing productions
Product usually have 30 days, 60 days, 90 days, half a year, the periods such as 1 year, the period is to then redeeming finance and money management product.
Attribute information specifically may include the sale temperature of product, access temperature, exposure temperature, concern temperature, production life cycle,
The indication informations such as product performance.
Specifically, can be from operational angle, the key message of analyzing influence user's decision, and extract and these influences
The corresponding attribute information of key message of user's decision, to facilitate subsequent analysis recommendation process.Such as:User more pays close attention to
The earning rate of finance and money management product, and it is relatively weak to attention rates such as the investment cycle of finance product, sale temperatures, then extract reason
The attribute informations such as earning rate, investment cycle, the sale temperature of property product, and finance product is preferentially grading according to user's attention rate
Row is integrated ordered, facilitates subsequent analysis recommendation process.
S2, according to the attribute information extracted, generate virtual product, and record the actual products and the virtual product
Mapping relations.
Wherein, the virtual product refers to:Extraction influences the key message phase of user's decision from specific product on sale
The attribute information answered generates corresponding product information further according to the corresponding attribute information of these key messages, and by these products
Information is stored, these product informations are identical with actual products on format, but the not corresponding product being truly present.And
Actual products can be the finance and money management product of sale of having designed or reached the standard grade, and can also be fruit juice, the food now done
The daily product that disappear soon such as product, paper handkerchief.The present embodiment influences the product attribute of user's decision according to being extracted from actual products, to product category
Property sliding-model control, then derives virtual product pond, and according to actual products in virtual product by the way of cartesian product
Projection in pond, which is rejected, merges virtual product, the transforming relationship of final output actual products and virtual product.This method will be true
Product is converted into virtual product, and product attribute is more targeted after conversion, and product general levels are more clear.
Further, after obtaining virtual product, virtual product can be loaded for a long time in the commercial product recommending used at present
Therefore strategy on the basis of above-mentioned flow, further includes:
After selecting generated virtual product according to the behavioral data of user, the virtual product selected and institute are established
State the correspondence of the behavioral data of user;According to the refreshing of the behavioral data of the user, the row of user described in synchronized update
For the virtual product corresponding to data.
It, only need to be according to the behavior number of user since virtual product is loaded for a long time in the commercial product recommending strategy used at present
It can ensure that virtual product can correspond to user demand according to real-time update virtual product.
In practical applications, since each node of operation system is easy to cause to be delayed due to various reasons, commercial product recommending
The execution of strategy often postpones several hours even several days.Currently used direct recommendation is really the scheme of product,
When message is finally pushed to user, the actual products recommended without or due to life-span of goods it is shorter so that citing
The overdue time in service life remains little.
In the present embodiment, virtual product exists for a long time in commercial product recommending strategy, in the level not undercarriage of logic flow, from
And convenient for after confirming the newest shopping intention of user, recommending and the more preferable local specialties of the associated timeliness of virtual product.
S3, the virtual product is selected according to the behavioral data of user, and according to the mapping relations, obtain to be recommended
Actual products.
Wherein user behavior data specifically includes:The behaviors such as click, concern, the purchase of user are based on user's primitive behavior
Data, analysis user such as current purchase amount applied, apply to purchase progress in the preference of product extrinsic characteristic aspect, most important, the party
Method can do comparative analysis in conjunction with the same period other products performance situation.
Mapping relations refer to:To the data that data prediction is crossed, according to product virtualization output as a result, using virtual product
Replace actual products, behavioral data of the structuring user's to virtual product.
It is described according to the attribute information extracted in the present embodiment step 2, virtual product is generated, includes specifically:
S21, product attribute discretization:Classification processing is carried out to the attribute information extracted, wherein the classification is to application
Family decision rule.
Mainly the attribute extracted is further processed:For category attribute, the influence based on each classification to user's decision,
Consider to its secondary classification.For connection attribute, distribution of the combination product on continuum carries out it at discrete place of branch mailbox
Reason.
S22, product virtual:According to sorted attribute information, virtual product is generated, and be stored in virtual product pond
In, wherein each classification at least maps a virtual product.
For the determinant attribute after product discretization, cartesian product operation is done, each data generated for operation reflects
It penetrates as a virtual product, all virtual products composition virtual products pond.
S23, virtual product filtering
Mainly the virtual product pond of generation is filtered, forms final virtual product pond, is divided into two steps, 1, in the void
In quasi- product pond, the virtual product projected without actual products is inquired, and do rejecting processing;;2, it is based on each virtual product upslide
The actual products distributed number of shadow, merges the virtual product of abnormal point or deconsolidation process.The virtual product finally generated
Pond, the corresponding actual products quantity of each virtual product is as impartial as possible, and the quantity of virtual product is unsuitable very few, generally slightly etc.
It is preferred in same period sale product number.
In the present embodiment step 3, the behavioral data according to user selects the virtual product, including:
S31, the behavioral data according to user carry out preference analysis for user, and obtain analysis result.
Specifically, user preference analysis refers to:By the laterally and longitudinally analysis to user's primitive behavior data, output is used
Family preference matrix.As shown in figure 3, Feature Engineering is specifically included, and data horizontal analysis, data vertical analysis, comprehensive analysis.
Feature Engineering:That is data prediction mainly cleans user's initial data, derives, and includes but not limited to pick
Other phases are obtained except deficiency of data, rejecting abnormalities access data, processing extreme value data, derivative New Set, association user attribute
Close information etc..
Data horizontal analysis:It to the attribute information extracted, is divided according to the time, obtains product in each period
In attribute information normalized done for each attribute, attribute information of the product in each period, including:
Sell temperature, access temperature, exposure temperature, concern temperature, production life cycle and product performance etc.;
Data vertical analysis:According to the behavioral data of user, the operation behavior within the period divided is determined, it is described
Operation behavior includes:It clicks, pay close attention to or buys, normalized is done for the preference data of each user.
Comprehensive analysis:According to data horizontal analysis result and data vertical analysis as a result, doing weighted calculation, the use is determined
Family is predicted by the preference of each attribute information for final products.
Each behavior for each user analyzes behavior time of origin point, object of action and belongs to identical virtual production
Other products of product, the different manifestations on each attribute.Operation weight by browse, pay close attention to, buy it is incremented by successively
S32, according to the analysis result, select the virtual product.
According to the user for the preference of each attribute information, virtual product recommendation list, the virtual production are generated
Include virtual product in product recommendation list.
Further, described and according to the mapping relations in the present embodiment step 3, actual products to be recommended are obtained,
Including:
By the virtual product in the virtual product recommendation list, actual products are resolved to;
The real-time property of parsed actual products is obtained, the real-time property includes:Product temperature and/or product into
Degree;
It is right according to the real-time property of the actual products parsed and the user for the preference of each attribute information
The actual products sequence parsed, obtains actual products recommendation list;
The actual products to be recommended are extracted from the actual products recommendation list.
The present embodiment provides a kind of recommendation method flows of product, as shown in figure 4, including product virtual module, user
Behavior processing module, user preference analysis module, virtual product recommending module, product real-time property computing module, actual products
Real-time recommendation module.
Product virtual module:To product classification, new product is fictionalized.The module is extracted from actual products influences user
Then the product attribute of decision derives virtual product pond to product attribute sliding-model control by the way of cartesian product, and
It is rejected according to projection of the actual products in virtual product pond and merges virtual product, final output actual products and virtual product
Transforming relationship.This module is extracted comprising product attribute, product attribute discretization, product virtual, virtual product filtering.
User behavior data processing module:Convert the behavior of user to the behavior to virtual product.The effect of this module
It is to be mapped to user on virtual product to the behavior of product, it includes data prediction, and virtual product maps two modules
User preference analysis module:User's history buying behavior is analyzed, in conjunction with other product attributes of same time and sale
Information, vertical analysis are combined with horizontal analysis, are generated user preference label, such as preference new product label, are recognized and raise progress percentage
Label, the big amount Product labelling of preference, preference buy number label etc..This module passes through the transverse direction to user's primitive behavior data
With vertical analysis, user preference matrix is exported.This module includes Feature Engineering, data horizontal analysis, data vertical analysis, synthesis
Analysis.
Virtual product recommending module:Analyze user behavior data, in conjunction with virtual product information, user tag information, user
Primary attribute is that user recommends virtual goods.This module takes mainstream recommended technology such as collaborative filtering, correlation rule, matrix decomposition
Product data after equal analyses are virtual and user behavior data, are generated for user recommended products list (virtual product).
Product real-time property computing module:This module mainly calculates the real-time property of product, such as product temperature, current schedules
Deng.
Product real-time recommendation module on sale:For each virtual product for recommending, in conjunction with user preference label, production on sale
Product information, the actual products that prediction user needs most.This module synthesis product real-time property, virtual product recommendation list and user
Preference data filters out from the corresponding actual products of virtual product and meets actual products expected from user, as consequently recommended
To the product of user.This module includes virtual recommended products reverse Mapping, recommendation list sequence, recommended products validity checking.
The embodiment of the present invention also provides a kind of device as shown in Figure 4, specifically includes:
Extraction module:The product data of actual products are obtained, and therefrom extract attribute information.
Processing module:According to the attribute information extracted, virtual product is generated, and record the actual products and the void
The mapping relations of quasi- product.
Recommending module:The virtual product is selected according to the behavioral data of user, and according to the mapping relations, acquisition waits for
The actual products of recommendation.
The processing module also carries out classification processing to the attribute information for being extracted, wherein the classification is to application
Family decision rule.According to sorted attribute information, virtual product is generated, and be stored in virtual product pond, wherein each
Classification at least maps a virtual product.In the virtual product pond, the virtual product projected without actual products is inquired, and do
Rejecting is handled.According to the distributed number of the actual products projected, each virtual product is merged and/or deconsolidation process.
The recommending module is additionally operable to the behavioral data according to user, carries out preference analysis for user, and analyzed
As a result.According to the analysis result, the virtual product is selected.
Further, the recommending module further includes resolving to the virtual product in the virtual product recommendation list
Actual products.The real-time property of parsed actual products is obtained, the real-time property includes:Product temperature and/or product
Progress.According to the real-time property of the actual products parsed and the user for the preference of each attribute information, to institute
The actual products sequence parsed, obtains actual products recommendation list.It is waited for described in extraction from the actual products recommendation list
The actual products of recommendation.
Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for equipment reality
For applying example, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to embodiment of the method
Part explanation.The above description is merely a specific embodiment, but protection scope of the present invention is not limited to
This, any one skilled in the art in the technical scope disclosed by the present invention, the variation that can readily occur in or replaces
It changes, should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of claim
Subject to enclosing.
Claims (10)
1. a kind of recommendation method of product, which is characterized in that including:
The product data of actual products are obtained, and therefrom extract attribute information;
According to the attribute information extracted, virtual product is generated, and record the mapping of the actual products and the virtual product
Relationship;
The virtual product is selected according to the behavioral data of user, and according to the mapping relations, obtains true production to be recommended
Product.
2. according to the method described in claim 1, it is characterized in that, further including:
After selecting generated virtual product according to the behavioral data of user, the virtual product selected and the use are established
The correspondence of the behavioral data at family;
According to the refreshing of the behavioral data of the user, the virtual product corresponding to the behavioral data of user described in synchronized update.
3. according to the method described in claim 1, it is characterized in that, described according to the attribute information extracted, the virtual production of generation
Product, including:
Classification processing is carried out to the attribute information extracted, wherein the corresponding user's decision rule of the classification;
According to sorted attribute information, virtual product is generated, and be stored in virtual product pond, wherein each is classified to
A virtual product is mapped less;
In the virtual product pond, the virtual product projected without actual products is inquired, and do rejecting processing;
According to the distributed number of the actual products projected, each virtual product is merged and/or deconsolidation process.
4. according to the method described in claim 1, it is characterized in that, the behavioral data according to user selects the virtual production
Product, including:
According to the behavioral data of user, preference analysis is carried out for user, and obtain analysis result;
According to the analysis result, the virtual product is selected.
5. according to the method described in claim 4, it is characterized in that, the behavioral data according to user, carries out for user
Preference analysis, including:
It to the attribute information extracted, is divided according to the time, obtains attribute information of the product in each period, it is described
Attribute information of the product in each period, including:It sells temperature, access temperature, exposure temperature, concern temperature, product week
Phase and product performance etc.;
According to the behavioral data of user, determine that the operation behavior within the period divided, the operation behavior include:Point
It hits, pay close attention to or buys;
According to the operation behavior within the period divided, preference of the user for each attribute information is determined.
6. according to the method described in claim 5, it is characterized in that, described according to the analysis result, the virtual production is selected
Product, including:
According to the user for the preference of each attribute information, virtual product recommendation list is generated, the virtual product pushes away
Recommend in list includes virtual product.
7. according to the method described in claim 6, it is characterized in that, described and according to the mapping relations, obtain to be recommended
Actual products, including:
By the virtual product in the virtual product recommendation list, actual products are resolved to;
The real-time property of parsed actual products is obtained, the real-time property includes:Product temperature and/or product progress;
According to the real-time property of the actual products parsed and the user for the preference of each attribute information, to being solved
The actual products of precipitation sort, and obtain actual products recommendation list;
The actual products to be recommended are extracted from the actual products recommendation list.
8. a kind of recommendation apparatus of product, which is characterized in that including:
Extraction module:The product data of actual products are obtained, and therefrom extract attribute information;
Processing module:According to the attribute information extracted, virtual product is generated, and record the actual products and the virtual production
The mapping relations of product;
Recommending module:The virtual product is selected according to the behavioral data of user, and according to the mapping relations, is obtained to be recommended
Actual products.
9. device according to claim 8, which is characterized in that further include the processing module, also to for being extracted
Attribute information carries out classification processing, wherein the corresponding user's decision rule of the classification;
According to sorted attribute information, virtual product is generated, and be stored in virtual product pond, wherein each is classified to
A virtual product is mapped less;
In the virtual product pond, the virtual product projected without actual products is inquired, and do rejecting processing;
According to the distributed number of the actual products projected, each virtual product is merged and/or deconsolidation process.
10. device according to claim 7, which is characterized in that the recommending module is additionally operable to the behavior number according to user
According to carrying out preference analysis for user, and obtain analysis result;And according to the analysis result, select the virtual product;
Virtual product in the virtual product recommendation list is resolved to actual products by the recommending module;
The real-time property of parsed actual products is obtained, the real-time property includes:Product temperature and/or product progress;
According to the real-time property of the actual products parsed and the user for the preference of each attribute information, to being solved
The actual products of precipitation sort, and obtain actual products recommendation list;
The actual products to be recommended are extracted from the actual products recommendation list.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810296457.XA CN108537635A (en) | 2018-03-30 | 2018-03-30 | A kind of recommendation method and device of product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810296457.XA CN108537635A (en) | 2018-03-30 | 2018-03-30 | A kind of recommendation method and device of product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108537635A true CN108537635A (en) | 2018-09-14 |
Family
ID=63483080
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810296457.XA Pending CN108537635A (en) | 2018-03-30 | 2018-03-30 | A kind of recommendation method and device of product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108537635A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109670903A (en) * | 2018-11-20 | 2019-04-23 | 深圳市腾讯信息技术有限公司 | Processing, device, storage medium and the electronic device of article |
CN109887070A (en) * | 2019-01-10 | 2019-06-14 | 珠海金山网络游戏科技有限公司 | A kind of virtual face's production method and device |
CN109886769A (en) * | 2019-01-10 | 2019-06-14 | 珠海金山网络游戏科技有限公司 | A kind of the displaying optimization method and device of virtual objects |
CN111222931A (en) * | 2018-11-23 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Product recommendation method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217334A (en) * | 2013-06-05 | 2014-12-17 | 北京京东尚科信息技术有限公司 | Product information recommendation method, device and system |
CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
CN107515896A (en) * | 2017-07-17 | 2017-12-26 | 阿里巴巴集团控股有限公司 | A kind of resource recommendation method, device and equipment |
US20180040012A1 (en) * | 2016-08-05 | 2018-02-08 | Linctronix Ltd. | Virtual and real market commodity recommendation and reward system |
-
2018
- 2018-03-30 CN CN201810296457.XA patent/CN108537635A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217334A (en) * | 2013-06-05 | 2014-12-17 | 北京京东尚科信息技术有限公司 | Product information recommendation method, device and system |
US20180040012A1 (en) * | 2016-08-05 | 2018-02-08 | Linctronix Ltd. | Virtual and real market commodity recommendation and reward system |
CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
CN107515896A (en) * | 2017-07-17 | 2017-12-26 | 阿里巴巴集团控股有限公司 | A kind of resource recommendation method, device and equipment |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109670903A (en) * | 2018-11-20 | 2019-04-23 | 深圳市腾讯信息技术有限公司 | Processing, device, storage medium and the electronic device of article |
CN111222931A (en) * | 2018-11-23 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Product recommendation method and system |
CN111222931B (en) * | 2018-11-23 | 2023-05-05 | 阿里巴巴集团控股有限公司 | Product recommendation method and system |
CN109887070A (en) * | 2019-01-10 | 2019-06-14 | 珠海金山网络游戏科技有限公司 | A kind of virtual face's production method and device |
CN109886769A (en) * | 2019-01-10 | 2019-06-14 | 珠海金山网络游戏科技有限公司 | A kind of the displaying optimization method and device of virtual objects |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ren et al. | Demand forecasting in retail operations for fashionable products: methods, practices, and real case study | |
CN106570778B (en) | A kind of method that data integration based on big data is calculated with line loss analyzing | |
US7007020B1 (en) | Distributed OLAP-based association rule generation method and system | |
TWI512653B (en) | Information providing method and apparatus, method and apparatus for determining the degree of comprehensive relevance | |
US8407104B2 (en) | Catalog based price search | |
CN102236851B (en) | The method and system that the multidimensional credit system composing power based on user calculates in real time | |
CN108537635A (en) | A kind of recommendation method and device of product | |
CN107230098A (en) | Method and system is recommended in a kind of timesharing of business object | |
CN104866484A (en) | Data processing method and device | |
CN101515360A (en) | Method and server for recommending network object information to user | |
CN102385727A (en) | ID-value assessment device, ID-value assessment system, and ID-value assessment method | |
KR101435096B1 (en) | Apparatus and method for prediction of merchandise demand using social network service data | |
CN105488705A (en) | Auxiliary system and method of online shopping | |
JP2020149468A (en) | Product management system and product management method | |
CN105303447A (en) | Method and device for carrying out credit rating through network information | |
CN106326318A (en) | Search method and device | |
CN110634015A (en) | Consumption habit analysis system based on computer software | |
CN106228401A (en) | A kind of marketing system | |
CN109615431A (en) | The system and method for data assets perception and pricing function are realized under big data background | |
CN111191713A (en) | User portrait method and device based on invoice data | |
WO2005022309A2 (en) | Manufacturing units of an item in response to demand for the item projected from page-view date | |
Wang et al. | Visual Analysis of E‐Commerce User Behavior Based on Log Mining | |
Sharawi et al. | Utilization of data visualization for knowledge discovery in modern logistic service companies | |
CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
Ure | Modelling critical mass for e-commerce: the case of Hong Kong |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210728 Address after: Room 834, Yingying building, 99 Tuanjie Road, yanchuangyuan, Jiangbei new district, Nanjing, Jiangsu 210000 Applicant after: Nanjing Xingyun Digital Technology Co.,Ltd. Address before: 210042 No.1, Suning Avenue, Xuanwu District, Nanjing City, Jiangsu Province Applicant before: SUNING.COM Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180914 |
|
RJ01 | Rejection of invention patent application after publication |