CN108109056A - A kind of recommendation method and system of commodity - Google Patents
A kind of recommendation method and system of commodity Download PDFInfo
- Publication number
- CN108109056A CN108109056A CN201810021493.5A CN201810021493A CN108109056A CN 108109056 A CN108109056 A CN 108109056A CN 201810021493 A CN201810021493 A CN 201810021493A CN 108109056 A CN108109056 A CN 108109056A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- characteristic information
- recommendation
- buying
- 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
Abstract
The invention discloses a kind of recommendation method and system of commodity, are related to big data field.This method includes：Obtain the User action log that user generates when buying or browsing commodity；User action log is handled, obtains characteristic information of the user when buying or browsing commodity；Characteristic information is weighted according to default weight coefficient, obtains the recommendation rank of commodity；Commodity are recommended according to rank is recommended.A kind of recommendation method and system of commodity provided by the invention, the User action log generated by obtaining user when buying or browsing commodity, and the purchase of user or the characteristic information of navigation patterns are extracted accordingly, the recommendation rank of commodity is obtained according to characteristic information, and commodity are recommended accordingly, it disclosure satisfy that demand is launched in the advertisement of different user, the advertisement that customization is provided for various users is recommended, with the advantages of with strong points, highly practical.
Description
Technical field
The present invention relates to big data field more particularly to a kind of recommendation method and system of commodity.
Background technology
In store, channel door and most of commodity transactions application, it will usually by advertisement position or recommend the side such as column
Formula recommends fast-selling or emerging good to visiting subscriber, and no matter current recommendation effect faces the user of what demand, only
It can the big business that either commodity of fresh product or recommended user are browsed, bought of the several sales volumes of fixed recommendation some or certain
Product have the shortcomings that poor practicability.
The content of the invention
The technical problems to be solved by the invention be provide in view of the deficiencies of the prior art a kind of commodity recommendation method and
System.
The technical solution that the present invention solves above-mentioned technical problem is as follows：
A kind of recommendation method of commodity, including：
Obtain the User action log that user generates when buying or browsing commodity；
The User action log is handled, obtains characteristic information of the user when buying or browsing commodity；
The characteristic information is weighted according to default weight coefficient, obtains the recommendation rank of the commodity；
Commodity are recommended according to the recommendation rank.
The beneficial effects of the invention are as follows：A kind of recommendation method of commodity provided by the invention is being bought by obtaining user
Or the User action log generated during browsing commodity, and the purchase of user or the characteristic information of navigation patterns are extracted accordingly, according to
Characteristic information obtains the recommendation rank of commodity, and commodity are recommended accordingly, and disclosure satisfy that the advertisement of different user is launched needs
It asks, the advertisement that customization is provided for various users is recommended, and has the advantages of with strong points, highly practical.
Based on the above technical solutions, the present invention can also be improved as follows.
Further, it is described that the User action log is handled, it obtains the user and is buying or browsing commodity
When characteristic information, specifically include：
Analysis cleaning is carried out to the User action log, obtains the action trail chain of the user；
Reduction process is carried out to the action trail chain, obtains feature letter of the user when buying or browsing commodity
Breath.
Advantageous effect using above-mentioned further scheme is：By being cleaned to User action log, and to generation
Action trail chain carries out reduction process, can be convenient for extracting the characteristic information of user from complicated user behavior data, reduce
The data volume of processing improves treatment effeciency.
Further, it is described that analysis cleaning is carried out to the User action log, the action trail chain of the user is obtained,
It specifically includes：
The User action log is cleaned, removes the invalid data in the User action log and format error
Data；
It according to the data structuring objects in the User action log after cleaning, and is hashed, the category of the object
Property includes：Time of the act and user identifier；
Reduction process carries out the data according to the user identifier, and by the data after reduction process by described
Time of the act is ranked up；
The data after sequence are connected to obtain the action trail chain of the user.
Further, the characteristic information includes：Time buying characteristic information, purchase number characteristic information and the type of merchandise
Characteristic information；
It is described that the characteristic information is weighted according to default weight coefficient, the recommendation rank of the commodity is obtained,
It specifically includes：
According to default weight coefficient respectively to the time buying characteristic information, the purchase number characteristic information and institute
It states type of merchandise characteristic information to be weighted, and the recommendation rank of the commodity is obtained according to weighted results.
Advantageous effect using above-mentioned further scheme is：By default weight coefficient to time buying characteristic information,
Purchase number characteristic information and type of merchandise characteristic information are weighted, and can be convenient for precisely, efficiently carrying out commodity for user
Recommend.
Further, it is described that commodity are recommended according to the recommendation rank, it specifically includes：
The required parameter of commodity platform is obtained by the form of external safe interface；
The required parameter is analyzed, obtains characteristic information to be called；
According to the characteristic information to be called and the recommendation rank generation recommendation results, and the recommendation results are sent out
Give the commodity platform；
The commodity platform recommends commodity according to the recommendation results.
Advantageous effect using above-mentioned further scheme is：Asking for commodity platform is obtained by the form of external safe interface
Parameter is sought, and recommendation results are sent to corresponding commodity platform after being handled, realizes the cross-platform of user's characteristic information
It is shared, improve the durability of data.
The another technical solution that the present invention solves above-mentioned technical problem is as follows：
A kind of commending system of commodity, including：Processor and commodity platform, wherein, the processor includes：
Acquiring unit, for obtaining the User action log that user generates when buying or browsing commodity；
First processing units for handling the User action log, obtain the user and are buying or browsing
Characteristic information during commodity；
Second processing unit for being weighted according to default weight coefficient to the characteristic information, obtains the business
The recommendation rank of product；
The commodity platform is used to recommend commodity according to the recommendation rank.
Further, the first processing units are specifically used for carrying out analysis cleaning to the User action log, obtain
The action trail chain of the user, and reduction process is carried out to the action trail chain, it obtains the user and is buying or browsing
Characteristic information during commodity.
Further, the first processing units are specifically used for cleaning the User action log, described in removal
Invalid data and format error data in User action log, and the data in the User action log after cleaning
Object is constructed, and the data and the object are hashed, the attribute of the object includes：Time of the act and user's mark
Know, and reduction process carries out the data according to the user identifier, and the data after reduction process are pressed into the row
It is ranked up for the time, and the data after sequence is connected to obtain the action trail chain of the user.
Further, the characteristic information includes：Time buying characteristic information, purchase number characteristic information and the type of merchandise
Characteristic information；
The second processing unit be specifically used for according to default weight coefficient respectively to the time buying characteristic information,
The purchase number characteristic information and the type of merchandise characteristic information are weighted, and obtain the commodity according to weighted results
Recommendation rank.
Further, the processor further includes：
Interface unit, for obtaining the required parameter of commodity platform by the form of external safe interface, to the request
Parameter is analyzed, and obtains characteristic information to be called, according to the characteristic information to be called and the recommendation rank generation
Recommendation results, and the recommendation results are sent to the commodity platform；
The commodity platform is specifically used for recommending commodity according to the recommendation results.
The beneficial effects of the invention are as follows：A kind of commending system of commodity provided by the invention is being bought by obtaining user
Or the User action log generated during browsing commodity, and the purchase of user or the characteristic information of navigation patterns are extracted accordingly, according to
Characteristic information obtains the recommendation rank of commodity, and commodity are recommended accordingly, and disclosure satisfy that the advertisement of different user is launched needs
It asks, the advertisement that customization is provided for various users is recommended, and has the advantages of with strong points, highly practical.
The advantages of additional aspect of the invention, will be set forth in part in the description, and will partly become from the following description
It obtains substantially or is recognized by present invention practice.
Description of the drawings
Fig. 1 is the flow diagram that a kind of one embodiment of the recommendation method of commodity of the present invention provides；
Fig. 2 is the structural framing figure that a kind of one embodiment of the commending system of commodity of the present invention provides；
Fig. 3 is the structural framing figure that a kind of another embodiment of the commending system of commodity of the present invention provides.
Specific embodiment
The principle and features of the present invention will be described below with reference to the accompanying drawings, and illustrated embodiment is served only for explaining the present invention,
It is not intended to limit the scope of the present invention.
As shown in Figure 1, be the flow diagram that a kind of one embodiment of the recommendation method of commodity of the present invention provides, the party
Method includes：
S1 obtains the User action log that user generates when buying or browsing commodity.
It should be noted that User action log refers to user when buying or browsing commodity, what background system generated
Record has the purchase of user or the set of navigation patterns data.
For example, User action log can be：Xx times, xx user buy (or browsing) xx commodity by xx platforms.
It should be noted that can by each platform commodity place an order and process of purchase in front end page carry out intrusive mood
Or the slotting code of non-intrusion type buries a little, gathers User action log.
S2 handles User action log, obtains characteristic information of the user when buying or browsing commodity.
It should be noted that the order of magnitude of the user journal usually collected can be very big, therefore big data can be used
Analysis method carries out analysis cleaning treatment to the User action log collected.
For example, analysis cleaning can include removal invalid data or format error data etc..
It should be noted that the temporal characteristics, commodity platform when characteristic information refers to user's purchase or browses commodity are special
Sign, merchandise classification feature etc..For example, for user's first, user's first is liked browsing commodity between 7 points to 9 points at night, that
Temporal characteristics in the characteristic information of user's first can be with for 7 points to 9 points.
S3 is weighted characteristic information according to default weight coefficient, obtains the recommendation rank of commodity.
It should be noted that weight coefficient refers to that the characteristic information for calculating certain user is calculating multiplier when recommending rank
Coefficient can be set by commodity platform according to actual demand.
For example, it is assumed that in characteristic information, for certain part flow summation concessionaire's product of user's second purchase, temporal characteristics are
Morning buying behavior, weight coefficient 2, merchandise classification are characterized as data traffic class commodity, weight coefficient 3, then Yong Huyi
Class of traffic commodity are bought in the morning 10 times, then buy recommendation rank in the morning of flow summation concessionaire's product to be：10*2*
3=60.
10 * morning buying behavior weight coefficient 2* class of traffic goods weight coefficients 3=60
S4 recommends commodity according to rank is recommended.
For example, it is assumed that for user's second, the recommendation rank of the flow summation bag of morning purchase is 60, and user's second is under
Period at noon bought 2 flow summation concessionaire's product, and temporal characteristics are buying behavior in afternoon, weight coefficient 3, then the stream
Buy recommendation rank in the afternoon of amount superposition concessionaire's product：2*3*3=18.
By comparing it can be found that for user's second, the recommendation rank of concessionaire's product is superimposed in morning purchase class of traffic
Higher, therefore, the advertisement that can carry out class of traffic commodity to the user in the upper period of the day from 11 a.m. to 1 p.m are recommended.
It should be noted that the recommended advertisements of commodity can be launched on the commodity platform or other platforms used in user
Deng.
The recommendation methods of commodity provided in this embodiment a kind of is generated by obtaining user when buying or browsing commodity
User action log, and the purchase of user or the characteristic information of navigation patterns are extracted accordingly, commodity are obtained according to characteristic information
Recommend rank, and commodity are recommended accordingly, disclosure satisfy that demand is launched in the advertisement of different user, it is fixed to be provided for various users
The advertisement of inhibition and generation is recommended, and has the advantages of with strong points, highly practical.
Fig. 2 is the structural framing figure that a kind of one embodiment of the commending system of commodity of the present invention provides, and this method includes：
S1 obtains the User action log that user generates when buying or browsing commodity.
It should be noted that the explanation and preferred embodiment of step same with the above-mentioned embodiment, are referred to above-mentioned
Embodiment, details are not described herein.
S2 handles User action log, obtains characteristic information of the user when buying or browsing commodity.
Preferably, characteristic information includes：Time buying characteristic information, purchase number characteristic information and type of merchandise feature letter
Breath.
S3 is weighted characteristic information according to default weight coefficient, obtains the recommendation rank of commodity.
S4 recommends commodity according to rank is recommended.
Preferably, in step S2, can specifically include：
S21 carries out analysis cleaning to User action log, obtains the action trail chain of user.
It should be noted that the action trail chain of user is referred in units of user, what is stored in the form of time chain should
The set of user's buying behavior data.
For example, for the action trail chain of user third, one of element can be：During x x month x day x, x is put down
Platform, purchase, x commodity.When another element can be x x month x day x, x platforms, browsing, x commodity.So by the two elements
It is together in series in chronological order, has just obtained the action trail chain of user third.
S22 carries out reduction process to action trail chain, obtains characteristic information of the user when buying or browsing commodity.
It should be noted that after carrying out reduction process, the characteristic information of user is extracted.For example, can be：Xx user x
Buy xx type of article xx times by the moon, time buying feature is the xx periods.
Preferably, all characteristic informations of each user can also be synthesized, forms the feature portrait of user.
The feature portrait of user in units of user, can visually show the purchase row of user by the form of image
For distribution and buying behavior tendency etc..
Preferably, in step S21, can specifically include：
S211 cleans User action log, removes invalid data and format error number in User action log
According to.
S212 according to the data structuring objects in the User action log after cleaning, and is hashed, the attribute bag of object
It includes：Time of the act and user identifier.
It should be noted that time of the act refers to that user generates the time point of navigation patterns after purchase, user identifier refers to
Be mark that user identifies each user.
S213, according to user identifier to data carry out reduction process, and by the data after reduction process by time of the act into
Row sequence.
S214 connects the data after sequence to obtain the action trail chain of user.
Preferably, in step S3, can specifically include：
It is special to time buying characteristic information, purchase number characteristic information and the type of merchandise respectively according to default weight coefficient
Reference breath is weighted, and obtains the recommendation rank of commodity according to weighted results.
For example, purchase number characteristic information can be assigned to higher weight, to recommend what is often bought or browse to user
Commodity can also assign type of merchandise characteristic information higher weight, to recommend the business with its normal purchase or browsing to user
Commodity as condition can also assign higher weight to time buying characteristic information, with when user's desire to purchase is strong
Between section to user's Recommendations.
Preferably, in step S4, can specifically include：
S41 obtains the required parameter of commodity platform by the form of external safe interface.
S42 analyzes required parameter, obtains characteristic information to be called.
S43 according to characteristic information to be called and recommends rank generation recommendation results, and recommendation results is sent to commodity
Platform.
S44, commodity platform recommend commodity according to recommendation results.
For example, the characteristic information and the correspondence of weight that certain commodity platform is set are as follows：
PC ends platform-class of traffic commodity-idle flow bag 3；Night flow bag 2；Common discharge bag 1
PC ends platform-voice class commodity-world voice packet 5；Domestic voice snack bag 2；Normal speech bag 1.
Wherein, number refers to corresponding weight.
It is assumed that the characteristic information of user's fourth is：Night flow bag is bought 2 times, domestic voice snack bag 3 times, then commodity
Recommendation degree is shown in Table 1：
| Idle flow bag | 3 |
| Night flow bag | 2*2 times=4 |
| Common discharge bag | 1 |
| International voice packet | 5 |
| Domestic voice snack bag | 2*3 times=6 |
| Normal speech bag | 1 |
Table 1
So recommendation degree is arranged from high to low, it is possible to obtain consequently recommended items list and be followed successively by：Domestic voice adds
Meal bag, international voice packet, night flow bag, idle flow bag, normal speech bag, common discharge bag.
It should be noted that commodity platform can also set the weight of time buying feature etc., so that commercial product recommending is more
It is practical.
The recommendation methods of commodity provided in this embodiment a kind of is generated by obtaining user when buying or browsing commodity
User action log, and the purchase of user or the characteristic information of navigation patterns are extracted accordingly, commodity are obtained according to characteristic information
Recommend rank, and commodity are recommended accordingly, disclosure satisfy that demand is launched in the advertisement of different user, it is fixed to be provided for various users
The advertisement of inhibition and generation is recommended, and has the advantages of with strong points, highly practical.
And by being cleaned to User action log, and reduction process, Neng Goubian are carried out to the action trail chain of generation
In the characteristic information that user is extracted from complicated user behavior data, the data volume of processing is reduced, improves treatment effeciency.
And by default weight coefficient to time buying characteristic information, purchase number characteristic information and type of merchandise feature
Information is weighted, and can be convenient for precisely, efficiently carrying out commercial product recommending for user.
And the required parameter of commodity platform is obtained by the form of external safe interface, and by recommendation results after being handled
Corresponding commodity platform is sent to, realizes the cross-platform sharing of user's characteristic information, improves the durability of data.
Fig. 3 is the structural framing figure that a kind of another embodiment of the commending system of commodity of the present invention provides, which includes：
Processor 1, commodity platform 2 and user terminal 3, wherein, processor 1 includes：
Acquiring unit 11, for obtaining the User action log that user generates when user terminal 3 is bought or browses commodity；
First processing units 12 for handling User action log, obtain user when buying or browsing commodity
Characteristic information；
Second processing unit 13 for being weighted according to default weight coefficient to characteristic information, obtains pushing away for commodity
Recommend rank；
Commodity platform 2 is used to recommend commodity according to recommendation rank.
Preferably, first processing units 12 are specifically used for carrying out analysis cleaning to User action log, obtain the row of user
For track chain, and reduction process is carried out to action trail chain, obtain characteristic information of the user when buying or browsing commodity.
Preferably, first processing units 12 are specifically used for cleaning User action log, remove User action log
In invalid data and format error data, and data structuring objects in the User action log after cleaning, and by number
It is hashed according to object, the attribute of object includes：Time of the act and user identifier, and data are returned according to user identifier
It about handles, and the data after reduction process is ranked up by time of the act, and the data after sequence are connected to obtain user's
Action trail chain.
Preferably, characteristic information includes：Time buying characteristic information, purchase number characteristic information and type of merchandise feature letter
Breath；
Second processing unit 13 is specifically used for according to default weight coefficient respectively to time buying characteristic information, purchase time
Number characteristic information and type of merchandise characteristic information are weighted, and obtain the recommendation rank of commodity according to weighted results.
Preferably, processor 1 further includes：
Interface unit 14 for obtaining the required parameter of commodity platform 2 by the form of external safe interface, joins request
Number is analyzed, and obtains characteristic information to be called, according to characteristic information to be called and recommends rank generation recommendation results, and
Recommendation results are sent to commodity platform 2；
Commodity platform 2 is specifically used for recommending commodity according to recommendation results.
The commending systems of commodity provided in this embodiment a kind of is generated by obtaining user when buying or browsing commodity
User action log, and the purchase of user or the characteristic information of navigation patterns are extracted accordingly, commodity are obtained according to characteristic information
Recommend rank, and commodity are recommended accordingly, disclosure satisfy that demand is launched in the advertisement of different user, it is fixed to be provided for various users
The advertisement of inhibition and generation is recommended, and has the advantages of with strong points, highly practical.
Reader should be understood that in the description of this specification, reference term " one embodiment ", " some embodiments ", " show
The description of example ", " specific example " or " some examples " etc. mean to combine the specific features of the embodiment or example description, structure,
Material or feature are contained at least one embodiment of the present invention or example.In the present specification, above-mentioned term is shown
The statement of meaning property need not be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the different embodiments described in this specification or example and different embodiments or exemplary spy
Sign is combined and combines.
It is apparent to those skilled in the art that for convenience of description and succinctly, the dress of foregoing description
The specific work process with unit is put, may be referred to the corresponding process in preceding method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed apparatus and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit, is only
A kind of division of logic function, can there is an other dividing mode in actual implementation, for example, multiple units or component can combine or
Person is desirably integrated into another system or some features can be ignored or does not perform.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
Component may or may not be physical location, you can be located at a place or can also be distributed to multiple networks
On unit.Some or all of unit therein can be selected to realize the mesh of the embodiment of the present invention according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that unit is individually physically present or two or more units integrate in a unit.It is above-mentioned integrated
The form that hardware had both may be employed in unit is realized, can also be realized in the form of SFU software functional unit.
If integrated unit is realized in the form of SFU software functional unit and is independent production marketing or in use, can
To be stored in a computer read/write memory medium.Based on such understanding, technical scheme substantially or
Saying all or part of the part contribute to the prior art or the technical solution can be embodied in the form of software product
Out, which is stored in a storage medium, is used including some instructions so that a computer equipment
(can be personal computer, server or the network equipment etc.) performs all or part of each embodiment method of the present invention
Step.And foregoing storage medium includes：USB flash disk, mobile hard disk, are deposited at read-only memory (ROM, Read-OnlyMemory) at random
The various media that can store program code such as access to memory (RAM, RandomAccessMemory), magnetic disc or CD.
More than, it is only specific embodiment of the invention, but protection scope of the present invention is not limited thereto, and it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be wanted with right
Subject to the protection domain asked.
Claims (10)
1. a kind of recommendation method of commodity, which is characterized in that including：
Obtain the User action log that user generates when buying or browsing commodity；
The User action log is handled, obtains characteristic information of the user when buying or browsing commodity；
The characteristic information is weighted according to default weight coefficient, obtains the recommendation rank of the commodity；
Commodity are recommended according to the recommendation rank.
2. recommendation method according to claim 1, which is characterized in that it is described that the User action log is handled,
Characteristic information of the user when buying or browsing commodity is obtained, is specifically included：
Analysis cleaning is carried out to the User action log, obtains the action trail chain of the user；
Reduction process is carried out to the action trail chain, obtains characteristic information of the user when buying or browsing commodity.
3. recommendation method according to claim 2, which is characterized in that described to the User action log analyze clearly
It washes, obtains the action trail chain of the user, specifically include：
The User action log is cleaned, removes invalid data and format error number in the User action log
According to；
It according to the data structuring objects in the User action log after cleaning, and is hashed, the attribute bag of the object
It includes：Time of the act and user identifier；
Reduction process carries out the data according to the user identifier, and the data after reduction process are pressed into the behavior
Time is ranked up；
The data after sequence are connected to obtain the action trail chain of the user.
4. recommendation method according to any one of claim 1 to 3, which is characterized in that the characteristic information includes：Purchase
Temporal characteristics information, purchase number characteristic information and type of merchandise characteristic information；
It is described that the characteristic information is weighted according to default weight coefficient, the recommendation rank of the commodity is obtained, specifically
Including：
According to default weight coefficient respectively to the time buying characteristic information, the purchase number characteristic information and the business
Category type characteristic information is weighted, and obtains the recommendation rank of the commodity according to weighted results.
5. recommendation method according to any one of claim 1 to 3, which is characterized in that described according to the recommendation rank
Commodity are recommended, are specifically included：
The required parameter of commodity platform is obtained by the form of external safe interface；
The required parameter is analyzed, obtains characteristic information to be called；
According to the characteristic information to be called and the recommendation rank generation recommendation results, and the recommendation results are sent to
The commodity platform；
The commodity platform recommends commodity according to the recommendation results.
6. a kind of commending system of commodity, which is characterized in that including：Processor and commodity platform, wherein, the processor bag
It includes：
Acquiring unit, for obtaining the User action log that user generates when buying or browsing commodity；
First processing units for handling the User action log, obtain the user and are buying or browsing commodity
When characteristic information；
Second processing unit for being weighted according to default weight coefficient to the characteristic information, obtains the commodity
Recommend rank；
The commodity platform is used to recommend commodity according to the recommendation rank.
7. commending system according to claim 6, which is characterized in that the first processing units are specifically used for the use
Family user behaviors log carries out analysis cleaning, obtains the action trail chain of the user, and the action trail chain is carried out at reduction
Reason obtains characteristic information of the user when buying or browsing commodity.
8. commending system according to claim 7, which is characterized in that the first processing units are specifically used for the use
Family user behaviors log is cleaned, and removes invalid data and format error data in the User action log, and according to cleaning
The data structuring objects in the User action log afterwards, and the data and the object are hashed, the object
Attribute include：Time of the act and user identifier, and reduction process is carried out to the data according to the user identifier, and will return
About treated, and the data are ranked up by the time of the act, and the data after sequence are connected to obtain the user
Action trail chain.
9. the commending system according to any one of claim 6 to 8, which is characterized in that the characteristic information includes：Purchase
Temporal characteristics information, purchase number characteristic information and type of merchandise characteristic information；
The second processing unit is specifically used for according to default weight coefficient respectively to the time buying characteristic information, described
Purchase number characteristic information and the type of merchandise characteristic information are weighted, and obtain pushing away for the commodity according to weighted results
Recommend rank.
10. the commending system according to any one of claim 6 to 8, which is characterized in that the processor further includes：
Interface unit, for obtaining the required parameter of commodity platform by the form of external safe interface, to the required parameter
It is analyzed, obtains characteristic information to be called, recommended according to the characteristic information to be called and the recommendation rank generation
As a result, and the recommendation results are sent to the commodity platform；
The commodity platform is specifically used for recommending commodity according to the recommendation results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810021493.5A CN108109056A (en) | 2018-01-10 | 2018-01-10 | A kind of recommendation method and system of commodity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810021493.5A CN108109056A (en) | 2018-01-10 | 2018-01-10 | A kind of recommendation method and system of commodity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108109056A true CN108109056A (en) | 2018-06-01 |
Family
ID=62218528
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810021493.5A Pending CN108109056A (en) | 2018-01-10 | 2018-01-10 | A kind of recommendation method and system of commodity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108109056A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846708A (en) * | 2018-06-29 | 2018-11-20 | 中国联合网络通信集团有限公司 | User's buying behavior prediction technique, device, equipment and storage medium |
| CN109214886A (en) * | 2018-08-14 | 2019-01-15 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, system and storage medium |
| CN109636433A (en) * | 2018-10-16 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Feeding card identification method, device, equipment and storage medium based on big data analysis |
| CN110458638A (en) * | 2019-06-26 | 2019-11-15 | 平安科技（深圳）有限公司 | A kind of Method of Commodity Recommendation and device |
| CN110634040A (en) * | 2018-06-22 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Information recommendation method and device |
| CN111429203A (en) * | 2020-03-02 | 2020-07-17 | 北京明略软件系统有限公司 | Commodity recommendation method and device based on user behavior data |
| CN111556205A (en) * | 2020-04-21 | 2020-08-18 | 北京思特奇信息技术股份有限公司 | Method and system for recommending telecommunication products to target users |
| CN112101980A (en) * | 2020-08-04 | 2020-12-18 | 北京思特奇信息技术股份有限公司 | Method and system for analyzing purchase preference of user |
| CN112132660A (en) * | 2020-09-25 | 2020-12-25 | 尚娱软件（深圳）有限公司 | Commodity recommendation method, system, device and storage medium |
| CN112784178A (en) * | 2021-01-18 | 2021-05-11 | 仙境文化传媒(武汉)有限公司 | Interest exploration device and method based on recommendation system |
| CN112950256A (en) * | 2021-02-02 | 2021-06-11 | 广东便捷神科技股份有限公司 | Method and system for pushing customized advertisement form based on App |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004094382A (en) * | 2002-08-29 | 2004-03-25 | Ntt Comware Corp | Recommendation device and advertisement distribution method |
| CN103970753A (en) * | 2013-01-28 | 2014-08-06 | 北大方正集团有限公司 | Pushing method and pushing device for related knowledge |
| US20160092781A1 (en) * | 2014-09-02 | 2016-03-31 | Sri International | Similarity metric relativized to a user's preferences |
| CN105956161A (en) * | 2016-05-17 | 2016-09-21 | 北京奇虎科技有限公司 | Information recommendation method and apparatus |
| CN106021337A (en) * | 2016-05-09 | 2016-10-12 | 房加科技（北京）有限公司 | A big data analysis-based intelligent recommendation method and system |
| CN106202516A (en) * | 2016-07-24 | 2016-12-07 | 广东聚联电子商务股份有限公司 | A kind of e-commerce platform merchandise display method according to timing node |
| CN106910108A (en) * | 2017-01-24 | 2017-06-30 | 武汉奇米网络科技有限公司 | A kind of items list methods of exhibiting and system |
| CN107230136A (en) * | 2017-05-31 | 2017-10-03 | 合肥亿迈杰软件有限公司 | A kind of shopping sequence method for pushing based on big data |
| CN107507041A (en) * | 2017-09-08 | 2017-12-22 | 北京京东尚科信息技术有限公司 | The construction method and construction device of user model |
-
2018
- 2018-01-10 CN CN201810021493.5A patent/CN108109056A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004094382A (en) * | 2002-08-29 | 2004-03-25 | Ntt Comware Corp | Recommendation device and advertisement distribution method |
| CN103970753A (en) * | 2013-01-28 | 2014-08-06 | 北大方正集团有限公司 | Pushing method and pushing device for related knowledge |
| US20160092781A1 (en) * | 2014-09-02 | 2016-03-31 | Sri International | Similarity metric relativized to a user's preferences |
| CN106021337A (en) * | 2016-05-09 | 2016-10-12 | 房加科技（北京）有限公司 | A big data analysis-based intelligent recommendation method and system |
| CN105956161A (en) * | 2016-05-17 | 2016-09-21 | 北京奇虎科技有限公司 | Information recommendation method and apparatus |
| CN106202516A (en) * | 2016-07-24 | 2016-12-07 | 广东聚联电子商务股份有限公司 | A kind of e-commerce platform merchandise display method according to timing node |
| CN106910108A (en) * | 2017-01-24 | 2017-06-30 | 武汉奇米网络科技有限公司 | A kind of items list methods of exhibiting and system |
| CN107230136A (en) * | 2017-05-31 | 2017-10-03 | 合肥亿迈杰软件有限公司 | A kind of shopping sequence method for pushing based on big data |
| CN107507041A (en) * | 2017-09-08 | 2017-12-22 | 北京京东尚科信息技术有限公司 | The construction method and construction device of user model |
Non-Patent Citations (1)
| Title |
|---|
| 杨旭 等: "《数据科学导论》", 31 January 2017, 北京理工大学出版社 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634040A (en) * | 2018-06-22 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Information recommendation method and device |
| CN108846708A (en) * | 2018-06-29 | 2018-11-20 | 中国联合网络通信集团有限公司 | User's buying behavior prediction technique, device, equipment and storage medium |
| CN109214886A (en) * | 2018-08-14 | 2019-01-15 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, system and storage medium |
| CN109214886B (en) * | 2018-08-14 | 2023-09-22 | 平安科技（深圳）有限公司 | Commodity recommendation method, system and storage medium |
| CN109636433A (en) * | 2018-10-16 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Feeding card identification method, device, equipment and storage medium based on big data analysis |
| CN110458638B (en) * | 2019-06-26 | 2023-08-15 | 平安科技（深圳）有限公司 | Commodity recommendation method and device |
| CN110458638A (en) * | 2019-06-26 | 2019-11-15 | 平安科技（深圳）有限公司 | A kind of Method of Commodity Recommendation and device |
| CN111429203A (en) * | 2020-03-02 | 2020-07-17 | 北京明略软件系统有限公司 | Commodity recommendation method and device based on user behavior data |
| CN111556205A (en) * | 2020-04-21 | 2020-08-18 | 北京思特奇信息技术股份有限公司 | Method and system for recommending telecommunication products to target users |
| CN112101980A (en) * | 2020-08-04 | 2020-12-18 | 北京思特奇信息技术股份有限公司 | Method and system for analyzing purchase preference of user |
| CN112101980B (en) * | 2020-08-04 | 2024-04-02 | 北京思特奇信息技术股份有限公司 | Method and system for analyzing purchasing preference of user |
| CN112132660A (en) * | 2020-09-25 | 2020-12-25 | 尚娱软件（深圳）有限公司 | Commodity recommendation method, system, device and storage medium |
| CN112132660B (en) * | 2020-09-25 | 2023-12-26 | 尚娱软件（深圳）有限公司 | Commodity recommendation method, system, equipment and storage medium |
| CN112784178A (en) * | 2021-01-18 | 2021-05-11 | 仙境文化传媒(武汉)有限公司 | Interest exploration device and method based on recommendation system |
| CN112950256A (en) * | 2021-02-02 | 2021-06-11 | 广东便捷神科技股份有限公司 | Method and system for pushing customized advertisement form based on App |
| CN112950256B (en) * | 2021-02-02 | 2023-05-23 | 广东便捷神科技股份有限公司 | Method and system for customizing advertisement form based on App pushing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108109056A (en) | A kind of recommendation method and system of commodity | |
| CN109685631B (en) | Personalized recommendation method based on big data user behavior analysis | |
| US9087335B2 (en) | Multidimensional personal behavioral tomography | |
| Wang et al. | A personalized recommender system for the cosmetic business | |
| Krishna Reddy et al. | A graph based approach to extract a neighborhood customer community for collaborative filtering | |
| US7299194B1 (en) | Method and system for researching sales effects of advertising using association analysis | |
| US8700607B2 (en) | Applying data regression and pattern mining to predict future demand | |
| Hu et al. | Knowledge discovery of weighted RFM sequential patterns from customer sequence databases | |
| US20030055707A1 (en) | Method and system for integrating spatial analysis and data mining analysis to ascertain favorable positioning of products in a retail environment | |
| US20030128231A1 (en) | Dynamic path analysis | |
| Hahsler et al. | Implications of probabilistic data modeling for mining association rules | |
| Liu et al. | Mobile commerce product recommendations based on hybrid multiple channels | |
| CN110135948A (en) | A kind of recommender system and method for Electronic Commerce platform commodity | |
| CN111899075A (en) | Personalized commodity recommendation method and device based on user behaviors | |
| CN112085549A (en) | Commodity recommendation method for E-commerce platform based on data processing technology | |
| CN106327230A (en) | Abnormal user detection method and device | |
| Wu et al. | Discovery of associated consumer demands: Construction of a co-demanded product network with community detection | |
| CN106919609B (en) | Product information pushing method and device | |
| Srivastava et al. | Improved market basket analysis with utility mining | |
| CN110517001A (en) | A kind of timeliness guest room commodity go the method, apparatus and system of inventory | |
| Prassas et al. | Dynamic recommendations in internet retailing | |
| Srivastava | Motif analysis in the amazon product co-purchasing network | |
| Geyer-Schulz et al. | Others also use: A robust recommender system for scientific libraries | |
| Cho et al. | Development of a personalized recommendation procedure based on data mining techniques for internet shopping malls | |
| Suresh | Application of Retail Analytics Using Association Rule Mining In Data Mining Techniques With Respect To Retail Supermarket* A. Pappu Rajan |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180601 |