CN108320170A - Improve the method, apparatus and electronic device of the conversion ratio of the article in shopping cart - Google Patents
Improve the method, apparatus and electronic device of the conversion ratio of the article in shopping cart Download PDFInfo
- Publication number
- CN108320170A CN108320170A CN201710032822.1A CN201710032822A CN108320170A CN 108320170 A CN108320170 A CN 108320170A CN 201710032822 A CN201710032822 A CN 201710032822A CN 108320170 A CN108320170 A CN 108320170A
- Authority
- CN
- China
- Prior art keywords
- shopping cart
- article
- attribution
- model
- score
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0239—Online discounts or incentives
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- 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]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of method for the conversion ratio improving the article in shopping cart.This method includes:Determine the article in shopping cart;Calculate the attribution score that article is not converted;And according to attribution score, adjusts the parameter of article and/or send message related with the article.The present invention can the commodity user that rests in shopping cart of Accurate Analysis the reason of not buying, to provide better marketing program.
Description
Technical field
The present invention relates to technical field of electronic commerce, and in particular to a kind of side for the conversion ratio improving the article in shopping cart
Method, device and electronic device.
Background technology
As e-commerce website, user undergoes search, browsing plus the flow purchased, placed an order.Shopping cart substantially from
The link that family places an order nearest.In general, the commodity inside shopping cart are the strongest commodity of user's purchase intention.Present institute
There is electric business company that can all encounter this problem, many of shopping cart of user commodity, but never places an order.Especially exist
During big rush, the commodity in shopping cart can increase substantially, and virtually can also Shopping cart service device be given to increase prodigious pressure in this way
Power.The commodity that Jingdone district rests in user's shopping cart according to incompletely statistics have nearly tens, then being supported by effective big data
And coordinate rational marketing program, the conversion ratio of shopping cart is improved with regard to most important.
Due to there is no the snapshot model of commodity in shopping cart, commodity to add purchase situation that can only pass through flow in data warehouse
Angle counts, that is, cart button is added in the commodity for counting each channel (such as using (APP), PC, wechat, hand Q etc.)
Click condition.Corresponding marketing program majority using single product land vertically, send out certificate marketing methods cooperation shopping cart price reduction prompting side
Formula.
As shown in Figure 1, existing technical solution includes data collection zone 101, big data model area 102, marketing program 103
These three important links.In data collection zone 101, each channel, such as the ends PC, mobile terminal, the ends APP, wechat, the ends hand Q are counted
Shopping cart click logs are added to collect.Then, pass through relatively simple model (such as shopping cart in big data model area 102
Click logs basic model and addition shopping cart time exponential model) analysis shopping cart, in order to provide suitable marketing program 103.Battalion
Pin scheme 103 may include that shopping cart price reduction is reminded, guidance promotees stock greatly and token is promoted at a reduced price.
It can be clearly seen that as follows, the prior art has the disadvantage that:(1) each channel in data collection zone passes through stream
The mode of click is measured to count the case where commodity add purchase, a statistics is not complete since some are buried, and causes plus the data of purchase are inaccurate;
(2) big data model area supports the marketing guidance in later stage not complete enough not to the commodity, the user's progress classification, Reasons that do not place an order
Face;(3) it is reminded using single user's shopping cart price reduction plus unified promotion plan, marketing methods mostly uses the mode of price reduction,
Sales volume is improved, but reduces gross profit.
Invention content
In view of this, according to the first aspect of the invention, providing a kind of side for the conversion ratio improving the article in shopping cart
Method.The method includes:The operation log of shopping cart is received from least one shopping cart system;According to the operation day of shopping cart
Will determines all items in current shopping cart;According to shopping cart plus purchase time model, filters out and to be counted from all items
Calculate the article of attribution score;The attribution score that the article that calculating sifting goes out is not converted;And according to the attribution score, adjustment
The parameter and/or transmission message related with the respective articles of respective articles.
In one embodiment, the method may include retain each product the last item operation note and with it is former
Shopping cart be compared, with all items in the current shopping cart of determination.
In one embodiment, the shopping cart adds purchase time model that can at least indicate user's time active recently
And/or article is added to the time of shopping cart, for excluding recent sluggish user and/or from shopping cart excluding purchasing
The article of overlong time in object vehicle.
In one embodiment, the method may include:For each in multiple attribution models, calculating sifting goes out
Attribution score of the article in attribution model, and the attribution score of multiple attribution models of calculating is sorted, to determine article
The reason of not being converted, wherein each attribution model has weight.
In one embodiment, the method can also include the parameter according to article, to object in each attribution model
It judges point, and the weight of attribution model is multiplied with the scoring, attribution score of the calculating article in the attribution model.
In one embodiment, the multiple attribution model includes price model, evaluation accounting model, shopping cart congener
Product model and Buying Cycle model, and the parameter of article includes that inventory information, pricing information, evaluation information, shopping cart are similar
Number of articles information and Buying Cycle information, the method further include:If inventory information is shortage of goods, it is determined that article is not turned
The reason of change is out of stock.
In one embodiment, message related with the respective articles includes that arrival information, price reduction information and article push away
Recommend at least one of information.
According to the second aspect of the invention, a kind of device for the conversion ratio improving the article in shopping cart is provided, including:It connects
Unit is received, is configured as receiving the operation log of shopping cart from least one shopping cart system;Determination unit is configured as basis
The operation log of shopping cart determines all items in current shopping cart;Screening unit, when being configured as adding purchase according to shopping cart
Between model filtered out from all items will be by the article of calculating attribution score;Computing unit is configured as what calculating sifting went out
The attribution score that article is not converted;And conversion ratio improves unit, is configured as adjusting homologue according to the attribution score
The parameter and/or transmission message related with the respective articles of product.
According to the third aspect of the invention we, a kind of electronic device is provided, including:It is executable to be configured as storage for memory
Instruction;And processor, it is configured as that the electronic device is made to execute when executing the executable instruction stored in memory
The method according to the first aspect of the invention.
The present invention can the commodity user that rests in shopping cart of Accurate Analysis the reason of not buying, and can be directed to and use
The reason of family is not bought provides accurate rational marketing program, improves the conversion ratio of shopping cart, can also be by touching up to (ratio more
Such as PUSH message, specially enjoy it is preferential) mode promote other unexpected marketing methods at a reduced price to realize to remove, for example reminding type, follow the wind
Formula, hungry marketing formula etc..By providing diversified marketing mode, while sales volume can be improved during promotion, protect
Card gross profit does not decline.
Description of the drawings
According to exemplary embodiment being described below in conjunction with exemplary drawings, the other details of the disclosure, aspect and excellent
Point will become obvious.
Fig. 1 shows the analysis shopping cart of the prior art to improve the signal of the method for the conversion ratio of the commodity in shopping cart
Figure.
Fig. 2 shows the flows according to the ... of the embodiment of the present invention for improving the method for the conversion ratio of the commodity in shopping cart
Figure.
Fig. 3 shows that user according to the ... of the embodiment of the present invention does not buy the details of attribution model.
Fig. 4 shows the example of the method according to the ... of the embodiment of the present invention for calculating attribution score.
Fig. 5 shows the flow chart of the method for the conversion ratio of the article in raising shopping cart according to the ... of the embodiment of the present invention.
Fig. 6 shows the block diagram of the device of the conversion ratio of the article in raising shopping cart according to the ... of the embodiment of the present invention.
Fig. 7 shows the schematic block diagram of the electronic device according to the ... of the embodiment of the present invention with form of computers.
Specific implementation mode
It explains below to the embodiment of the present invention, including the various details of the embodiment of the present invention to help to manage
Solution, they should be thought to be only exemplary.It therefore, it will be appreciated by the person skilled in the art that can be to being described herein
Embodiment make various modifications and change, without departing from scope and spirit of the present invention.
Fig. 2 shows the flows according to the ... of the embodiment of the present invention for improving the method for the conversion ratio of the commodity in shopping cart
Figure.It should be noted that term " conversion ratio " may refer to user and the commodity in shopping cart place an order.Generally, of the invention
Design includes:By the way of receiving shopping cart system message, in real time record user each channel (ends PC, the ends APP, the ends M,
Wechat end, the ends hand Q etc.) to the operation log of shopping cart (be added, change, delete, merge, place an order after delete etc.);For tens
Commodity in hundred million shopping cart are cleaned in conjunction with data such as user's browsing, evaluation, transaction, are not purchased to user and commodity
The classification, Reasons bought, to provide best marketing program for commodity and be that commodity attribute most accurately buys crowd.
It needs mainly to solve the problems, such as three aspects in three links according to the solutions of the embodiments of the present invention:Crawl precisely purchase
Object car data establishes user and does not buy attribution model, marketing program.Protocol procedures figure is as follows:
(1) data acquisition 22
It is communicated with online shopping vehicle system 21, by receiving the form of message, records operation of the user to shopping cart in real time
Daily record 221 is landed onto service document.Then, log file data is parsed, regular (for example, each two hour) to
Big data hadoop bottoms synchronize a data file 222.It, can be by system distribution since there are magnanimity commodity in shopping cart
It is deployed on very multiple servers.It during especially big rush, needs to increase server, data acquisition at this time must be by increased clothes
Business device Node leading-in, otherwise may lose data.
In data acquisition, detailed operation log of the user to shopping cart is received.Therefore, in order to determine each user
Shopping cart in commodity, can daily to daily record data carry out cleaning and iteration.It specifically, in one embodiment, can be with
Retain the last item operation note of the user in every commodity, and is compared with pervious shopping cart (such as the previous day).
In one embodiment, the commodity delete operation in operation log and lower single delete operation can be rejected, to finally go back original subscriber
Shopping cart commodity snapshot 223 determines all commodity in user's shopping cart.
(2) big data model 23
It is effectively promoted, really improve the conversion ratio of shopping cart also needs other than having accurate purchase data
Scene, the attribute of commodity, the attribute of user and the behavior in later stage that shopping user is added carry out detailed analysis, most end form
Cause model is not bought at user.
First, user is added shopping cart but has much the reason of purchase, such as:The prices of commodity is relatively high, commodity lack
Goods, the evaluation of commodity is bad, the commodity purchasing period does not arrive also, is compared with category commodity etc..Different originals can be directed to
Because proposing corresponding marketing program in marketing program.The various data moulds that big data model 23 described in detail below includes
Type.
May include that shopping cart adds purchase time model 231, shopping cart goods browse mould with reference to figure 2, in big data model 23
Block 232, user's portrait model 233, commodity portrait model 234 and user do not buy attribution model 235.
Shopping cart adds purchase time model 231 to can be used in all commodity for including from shopping cart filtering out and by calculating being returned
Because of the commodity of score.Since the commodity amount in shopping cart is huge, every commodity are all carried out with attribution score and is calculated consumption greatly
Measure resource, it is possible to add purchase time model using shopping cart, pointedly filter out the user for being worth analysis or commodity.
In one embodiment, shopping cart adds purchase time model that can at least indicate that user's time active recently and/or article are added
To the time of shopping cart, for excluding recent sluggish user and/or from excluding the overlong time in shopping cart in shopping cart
Article.In one embodiment, when user does not log in electric business website more than the specific threshold time, it is believed that the user is not
It is active, so as to not calculate attribution score to any commodity in its shopping cart.In one embodiment, when in shopping cart
When the time that commodity are added to shopping cart is more than another specific threshold time, it is believed that user in the recent period anticipates to the purchase of the commodity
Hope is not strong, so as to not calculate attribution score to the commodity.
Calculating user is described below and does not buy attribution model 235.It may include as mould that user, which does not buy attribution model 235,
Shopping cart goods browse module 232, user's portrait model 233 and the commodity portrait model 234 of type input parameter (being into ginseng).With
It can also include attribution as model output parameters (go out ginseng) as a result, attribution result can be with that attribution model 235 is not bought at family, which,
It is indicated, is described later on attribution score.
It includes into the non-purchasing model of user for joining and going out ginseng to be described in detail according to the ... of the embodiment of the present invention below with reference to Fig. 3
Details.
As shown in figure 3, in one embodiment, shopping cart goods browse module 232 may include user browsing behavior number
According to, including after the accumulative number for browsing certain single product page of user for example daily counted, the number for continuously browsing certain single product page plus purchase
Single product number of clicks etc..
In one embodiment, user's portrait model 233 may include user's representation data.User's representation data can lead to
It crosses history purchase analysis to obtain, including the category preference of such as user, user brand preference, user price susceptibility, Yong Huji
This information (such as gender, age).
In one embodiment, commodity portrait model 234 may include the inventory information of commodity, commodity pricing information,
The information such as information on commodity comment, commodity purchasing period, commodity season susceptibility.
The ginseng that goes out that user does not buy attribution model generally comprises for example:
1, commodity price is high:The price that competitor (day cat, Suning etc.) can be obtained by rate of exchange fairground, compares with competitor
Valence, or commodity historical sales price, the comprehensive assessment once currently sold price of commodity can be extracted by historical sales.
2, Out of Stock:Commodity stocks information can be grasped by inventory data.
3, commodity evaluation is bad:The evaluation information of commodity can be grasped by user's evaluation.
4, the commodity purchasing period does not arrive:Commodity are classified, for example durable goods, disappear product soon.Each commodity has oneself
Life cycle, for example, when user has purchased certain durable goods (such as big household appliances), or the consumer goods bought are in the recent period obviously not
When having consumed (such as mother and baby's articles for use), user generally in the recent period loses interest in the commodity.
5, other reasons:It can jump out rate etc. by analysis page stay time, the page and show that single product page content of pages is
Whether no abundant, visual effect meets customer need and whether shopping process is unimpeded etc..
6, it is compared with category commodity:Some in shopping cart all have intention with the commodity of category, but are also used for carrying out
Compare.
By data and experience obtain Out of Stock, commodity price, commodity evaluation these three the reason is that influence user not
The main reason for purchase, and the Buying Cycle of commodity, similar commodity are relatively next reasons.It is described in detail below from this five
Attribution score is not bought in a aspect calculating, the reason not being purchased with the commodity determined in shopping cart.
Specifically, if the reason of commodity are currently in state out of stock, and commodity are not bought can directly be classified as commodity and lack
Goods, that is to say, that shortage of goods has highest attribution score.Can also evaluate commodity price, commodity according to the importance of reason,
Similar commodity compare, the weight in commodity purchasing period is followed successively by 0.4,0.3,0.2,0.1, and specific point counting standard is following such as Fig. 4 institutes
Show.
Fig. 4 shows the example of the method according to the ... of the embodiment of the present invention for calculating attribution score.In this example, for valence
Lattice model, evaluation accounting model, shopping cart goods model and user's Buying Cycle and commodity periodic model, calculate separately each
The attribution score of a model, wherein price model, evaluation accounting model, with category contrast model, the weight of Buying Cycle successively
It is 0.4,0.3,0.2,0.1.Certainly, the weight of model above is without being limited thereto, and those skilled in the art can as needed rationally
The weight of each model is set, the reason not being purchased with the commodity truly reflected in shopping cart as far as possible.
In this embodiment, the attribution score of calculating is higher, and the possibility for showing commodity therefore reason and not being purchased is got over
Greatly.
In one embodiment, as shown in figure 4, being directed to price model, it can be arranged and obtain 0 when price is higher by 0 than competitor
Point, 10 points are obtained when being higher by 1%-3%, 15 points are obtained when being higher by 3%-5%, and 10 points are obtained when being higher by 5% or more.The above score is multiplied by
Model Weight 0.4 respectively obtains score 0,4,6,10.
In one embodiment, as shown in figure 4, for evaluation accounting model, it can be arranged to be on duty and obtain 0 when commenting accounting 0%
Point, difference obtains 10 points when commenting 10% or less accounting, difference obtains 15 points when commenting accounting 10-25%, difference obtains 20 points when commenting 25% or more accounting.
The above score is multiplied by Model Weight 0.3, respectively obtains score 0,3,4.5,6.
In one embodiment, as shown in figure 4, being directed to shopping cart goods model, can be arranged when same category in shopping cart
Commodity only there are one when obtain 0 point, with category commodity there are two when obtain 10 points, with category commodity there are three or more when obtain 15 points.
The above score is multiplied by Model Weight 0.2, respectively obtains score 0,2,3.
In one embodiment, as shown in figure 4, being directed to Buying Cycle model, can be arranged apart from user's time buying phase
It obtains 0 point within poor 0 day or less, 0 point is differed 1-5 days to obtain apart from user's time buying, differed 6-10 days apart from user's time buying and obtain 20
Point, differ 10 days or more to obtain 30 points apart from user's time buying.The above score is multiplied by Model Weight 0.1, respectively obtains score
0、1、2、3。
People in the art is appreciated that the score for above each model setting can be not limited to above example,
As long as the reason that the commodity that the score can truly reflect in shopping cart as far as possible are not purchased.
Thus, it is possible to enter to join through certain weight by all, the score of each reason (price, evaluation etc.) is obtained, so
Ranking can be carried out according to the height of score afterwards.In one embodiment, the reason of because influencing user's purchase, may have simultaneously
Many kinds, therefore we take front three to be classified as user not buy main cause are marketed to which pin is adopted in accurately guidance.
Show that each information in model of drawing a portrait for article (for example) distributes weight above with reference to Fig. 4
(3) marketing program 24
Different marketing program is formulated for different reasons.It is corresponding marketing program below.For example, being directed to price ratio
Higher commodity, system can provide rational price opinion automatically.For commodity out of stock, can instruct to adopt pin progress accordingly
It replenishes.In the case where no source of goods is supplemented, carry out the recommendation of similar clause (as sent message).For there is periodical purchase
The commodity bought then have been reminded to user (as sent message) in the Buying Cycle.In addition, for the user for comparing Young vogue,
Cri dernier cri commodity and style can irregularly be recommended.
Fig. 5 shows the method 500 of the conversion ratio of the article in raising shopping cart according to the ... of the embodiment of the present invention.The side
Method 500 includes:In step 501, the operation log of shopping cart is received from least one shopping cart system;In step 502, according to purchase
The operation log of object vehicle determines all items in current shopping cart;In step 503, according to shopping cart plus time model is purchased, from
Being filtered out in all items will be by the article of calculating attribution score;In step 504, what article that calculating sifting goes out was not converted returns
Because of score;And the parameter (such as price, quantity in stock etc.) of respective articles is adjusted according to the attribution score in step 505
And/or send message (such as price reduction information, arrival information, article recommendation information etc.) related with the respective articles.
In one embodiment, method 500 can also include retain each product the last item operation note and with
Preceding shopping cart is compared, with all items in the current shopping cart of determination.Wherein, the shopping cart adds purchase time model can
It is inactive in the recent period for excluding to refer at least to show that time that user is active recently and/or article are added to the time of shopping cart
User and/or from shopping cart exclude in shopping cart overlong time article.
In one embodiment, the method 500 may include:For each in multiple attribution models, sieve is calculated
Attribution score of the article selected in attribution model, and the attribution score of multiple attribution models of calculating is sorted, with determination
The reason of article is not converted, wherein each attribution model has weight (such as described above 0.4,0.3,0.2,0.1).
In one embodiment, the method 500 can also include the parameter according to article, right in each attribution model
Article scores, and the weight of attribution model is multiplied with the scoring, calculates attribution score of the article in the attribution model.
In one embodiment, multiple attribution models include price model, evaluation accounting model, shopping cart ware mould
Type and Buying Cycle model, and the parameter of article includes inventory information, pricing information, evaluation information, shopping cart ware
Information of number and Buying Cycle information, the method 500 further include:If inventory information is shortage of goods, it is determined that article is not turned
The reason of change is out of stock.
In one embodiment, message related with the article includes arrival information, price reduction information and article recommendation
At least one of breath.
Fig. 6 shows a kind of device 600 of conversion ratio improving the article in shopping cart according to the ... of the embodiment of the present invention.Institute
Stating device 600 includes:Receiving unit 601 is configured as receiving the operation log of shopping cart from least one shopping cart system;Really
Order member 602 is configured as determining all items in current shopping cart according to the operation log of shopping cart;Screening unit 603,
It is configured as adding purchase time model according to shopping cart that filtered out from all items will be by the article of calculating attribution score;It calculates single
Member 604, is configured as the attribution score that the article that calculating sifting goes out is not converted;And conversion ratio improves unit 605, is configured
To adjust the parameter of respective articles according to the attribution score and/or sending message related with the respective articles.
The more details of described device 600 are similar with method 500, are not repeated herein.
Fig. 7 is the schematic block diagram for showing the electronic device 700 according to the ... of the embodiment of the present invention with form of computers.
Device 700 may include processor 706 (for example, microprocessor (μ P), digital signal processor (DSP) etc.).Place
The either multiple processing of single treatment unit that reason device 706 can be performed for the different actions of flow described herein are single
Member.Device 700 can also include for receiving the input unit 702 of signal from other entities and for being carried to other entities
For the output unit 704 of signal.Input unit 702 and output unit 704 can be arranged to what single entities either detached
Entity.
In addition, device 700 may include having non-volatile or form of volatile memory at least one readable storage
Medium 708, e.g. electrically erasable programmable read-only memory (EEPROM), flash memory, and/or hard disk drive.Readable storage
Medium 708 includes computer program 710, which includes code/computer-readable instruction, by device 700
In processor 706 allow when executing hardware device 700 execute for example above in conjunction with flow described in Fig. 1 to 5 and its
Any deformation.
Computer program 710 can be configured with such as computer program module 710A~710E (only as an example, can
With more or less) computer program code of framework.Therefore, the code in the computer program of device 700 includes:Module
710A is used for ....Code in computer program further includes:Module 710B, is used for ....Code in computer program also wraps
It includes:Module 710C, is used for ..., such.
Although being implemented as computer program module above in conjunction with the code means in Fig. 7 the disclosed embodiments,
Device 700 is made to execute when being executed in processor 706 above in conjunction with the described actions of Fig. 1 to 5, however in alternative embodiment
In, at least one in the code means can at least be implemented partly as hardware circuit.
According to above to the description of the embodiment of the present invention, it is to be understood that the present invention can Accurate Analysis rest on shopping cart
In commodity user the reason of not buying, and the reason of can not be bought for user, provide accurate rational marketing program,
The conversion ratio of shopping cart is improved, can also be realized by way of touching up to (such as PUSH message, specially enjoy preferential) more and remove price reduction
Other unexpected marketing methods of promotion, such as reminding type, formula of following the wind, hungry marketing formula etc..By providing diversified marketing
Mode while can improving sales volume during promotion, ensures that gross profit does not decline.
Above detailed description has elaborated inspection method and system by using schematic diagram, flow chart and/or example
Numerous embodiments.In the case where this schematic diagram, flow chart and/or example include one or more functions and/or operation,
It will be understood by those skilled in the art that each function and/or operation in this schematic diagram, flow chart or example can be by various
Structure, hardware, software, firmware or substantially their arbitrary combination to realize individually and/or jointly.In one embodiment,
If the stem portion of theme described in the embodiment of the present invention can pass through application-specific integrated circuit (ASIC), field programmable gate array
(FPGA), digital signal processor (DSP) or other integrated formats are realized.However, those skilled in the art will appreciate that
The some aspects of embodiments disclosed herein can equally be realized in integrated circuits on the whole or partly, be embodied as
The one or more computer programs run on one or more computer are (for example, be embodied as in one or more computer
The one or more programs run in system), it is embodied as the one or more program (examples run on the one or more processors
Such as, it is embodied as the one or more programs run in one or more microprocessors), it is embodied as firmware, or substantially real
It is now the arbitrary combination of aforesaid way, and those skilled in the art will be provided with design circuit and/or write-in is soft according to the disclosure
The ability of part and/or firmware code.In addition, it would be recognized by those skilled in the art that the mechanism of theme described in the disclosure can be made
It is distributed for the program product of diversified forms, and no matter actually is used for executing the concrete type of the signal bearing medium of distribution
How, the exemplary embodiment of theme described in the disclosure is applicable in.The example of signal bearing medium includes but not limited to:It is recordable
Type medium, such as floppy disk, hard disk drive, compact-disc (CD), digital versatile disc (DVD), digital magnetic tape, computer storage;
And transmission type media, such as number and/or analogue communication medium are (for example, optical fiber cable, waveguide, wired communications links, channel radio
Believe link etc.).
Although exemplary embodiment describing the present invention with reference to several, it is to be understood that, term used is explanation and shows
Example property, term and not restrictive.The spirit or reality that can be embodied in a variety of forms without departing from invention due to the present invention
Matter, it should therefore be appreciated that above-described embodiment is not limited to any details above-mentioned, and should be spiritual defined by appended claims
Accompanying is all should be with the whole variations and remodeling widely explained, therefore fallen into claim or its equivalent scope in range to weigh
Profit requires to be covered.
It should be noted that the foregoing is merely a prefered embodiment of the invention and principle.It will be understood by those within the art that
The present invention is not limited to specific embodiments here.Those skilled in the art can make various significant changes, adjustment and replacement,
Without departing from protection scope of the present invention.The scope of the present invention is defined by the following claims.
Claims (15)
1. a kind of method for the conversion ratio improving the article in shopping cart, including:
The operation log of shopping cart is received from least one shopping cart system;
According to the operation log of shopping cart, all items in current shopping cart are determined;
According to shopping cart plus purchase time model, being filtered out from all items will be by the article of calculating attribution score;
The attribution score that the article that calculating sifting goes out is not converted;And
According to the attribution score, adjusts the parameter of respective articles and/or send message related with the respective articles.
2. according to the method described in claim 1, wherein:
Determine all items in current shopping cart include retain each product the last item operation note and with pervious purchase
Object vehicle is compared.
3. according to the method described in claim 1, wherein, the shopping cart adds purchase time model at least to indicate that user is active recently
Time and/or article be added to time of shopping cart, for excluding recent sluggish user and/or arranging from shopping cart
Except the article of the overlong time in shopping cart.
4. according to the method described in claim 1, further including:
For each in multiple attribution models, the attribution score of article that calculating sifting goes out in attribution model, and will meter
The attribution score sequence for the multiple attribution models calculated, to determine the reason of article is not converted, wherein each attribution model has
Weight.
5. method according to claim 4 further includes:
According to the parameter of article, score article in each attribution model, and
The weight of attribution model is multiplied with the scoring, calculates attribution score of the article in the attribution model.
6. according to the method described in claim 5, wherein, the multiple attribution model include price model, evaluation accounting model,
Shopping cart ware model and Buying Cycle model, and the parameter of article includes inventory information, pricing information, evaluation letter
Breath, shopping cart ware information of number and Buying Cycle information, the method further include:
If inventory information is shortage of goods, it is determined that the reason of article is not converted is out of stock.
7. according to the method described in claim 1, wherein, message related with the respective articles includes arrival information, price reduction
At least one of information and article recommendation information.
8. a kind of device for the conversion ratio improving the article in shopping cart, including:
Receiving unit is configured as receiving the operation log of shopping cart from least one shopping cart system;
Determination unit is configured as determining all items in current shopping cart according to the operation log of shopping cart;
Screening unit, is configured as adding purchase time model according to shopping cart that filtered out from all items will be by calculating attribution score
Article;
Computing unit is configured as the attribution score that the article that calculating sifting goes out is not converted;And
Conversion ratio improve unit, be configured as according to the attribution score adjust respective articles parameter and/or send with it is described
The related message of respective articles.
9. device according to claim 8, wherein:
The determination unit is additionally configured to retain the last item operation note of each product and be carried out with pervious shopping cart
Compare.
10. device according to claim 8, wherein the shopping cart adds purchase time model at least to indicate that user lives recently
The time of jump and/or article are added to the time of shopping cart, for excluding recent sluggish user and/or from shopping cart
Exclude the article of the overlong time in shopping cart.
11. device according to claim 8, wherein the computing unit is additionally configured to:
For each in multiple attribution models, the attribution score of article that calculating sifting goes out in attribution model, and will meter
The attribution score sequence for the multiple attribution models calculated, to determine the reason of article is not converted, wherein each attribution model has
Weight.
12. according to claim 11 described device, wherein the computing unit is additionally configured to:
According to the parameter of article, score article in each attribution model, and
The weight of attribution model is multiplied with the scoring, calculates attribution score of the article in the attribution model.
13. device according to claim 12, wherein the multiple attribution model includes price model, evaluation accounting mould
Type, shopping cart ware model and Buying Cycle model, and the parameter of article includes inventory information, pricing information, evaluation
Information, shopping cart ware information of number and Buying Cycle information, the method further include:
If inventory information is shortage of goods, it is determined that the reason of article is not converted is out of stock.
14. device according to claim 8, wherein message related with the respective articles includes arrival information, price reduction
At least one of information and article recommendation information.
15. a kind of electronic device, including:
Memory is configured as storage executable instruction;And
Processor is configured as that the electronic device is made to execute such as right when executing the executable instruction stored in memory
It is required that the method described in any one of 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710032822.1A CN108320170A (en) | 2017-01-16 | 2017-01-16 | Improve the method, apparatus and electronic device of the conversion ratio of the article in shopping cart |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710032822.1A CN108320170A (en) | 2017-01-16 | 2017-01-16 | Improve the method, apparatus and electronic device of the conversion ratio of the article in shopping cart |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108320170A true CN108320170A (en) | 2018-07-24 |
Family
ID=62892177
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710032822.1A Pending CN108320170A (en) | 2017-01-16 | 2017-01-16 | Improve the method, apparatus and electronic device of the conversion ratio of the article in shopping cart |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108320170A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126614A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术(北京)有限公司 | Attribution method, attribution device and storage medium |
CN113781145A (en) * | 2020-11-10 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Control method and device based on inspection robot |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105229689A (en) * | 2013-02-25 | 2016-01-06 | 安德里亚·赫希 | Article automatic powder adding is added to the method for virtual shopping cart |
US20160239867A1 (en) * | 2015-02-16 | 2016-08-18 | Adobe Systems Incorporated | Online Shopping Cart Analysis |
CN106447460A (en) * | 2016-10-17 | 2017-02-22 | 北京京东尚科信息技术有限公司 | Article awakening method based on shopping cart and article awakening device thereof |
CN107025565A (en) * | 2016-01-29 | 2017-08-08 | 北京京东尚科信息技术有限公司 | A kind of method and system for improving e-commerce website conversion ratio |
-
2017
- 2017-01-16 CN CN201710032822.1A patent/CN108320170A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105229689A (en) * | 2013-02-25 | 2016-01-06 | 安德里亚·赫希 | Article automatic powder adding is added to the method for virtual shopping cart |
US20160239867A1 (en) * | 2015-02-16 | 2016-08-18 | Adobe Systems Incorporated | Online Shopping Cart Analysis |
CN107025565A (en) * | 2016-01-29 | 2017-08-08 | 北京京东尚科信息技术有限公司 | A kind of method and system for improving e-commerce website conversion ratio |
CN106447460A (en) * | 2016-10-17 | 2017-02-22 | 北京京东尚科信息技术有限公司 | Article awakening method based on shopping cart and article awakening device thereof |
Non-Patent Citations (1)
Title |
---|
陈博: "《中国优秀硕士学位论文全文数据库(电子期刊)》", 30 October 2011 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126614A (en) * | 2018-11-01 | 2020-05-08 | 百度在线网络技术(北京)有限公司 | Attribution method, attribution device and storage medium |
CN111126614B (en) * | 2018-11-01 | 2024-01-16 | 百度在线网络技术(北京)有限公司 | Attribution method, attribution device and storage medium |
CN113781145A (en) * | 2020-11-10 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Control method and device based on inspection robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9773250B2 (en) | Product role analysis | |
TW201501059A (en) | Method and system for recommending information | |
JP2015528170A (en) | Method and device for determining hot selling goods for holidays | |
CN107862530A (en) | Establish the method and device of user's interpersonal relationships information | |
CN104820863A (en) | Consumer portrait generation method and device | |
US20110238615A1 (en) | Systems and methods for trend aware self-correcting entity relationship extraction | |
CN106970972A (en) | A kind of commodity method for pushing and device analyzed based on big data | |
CN107665448A (en) | For determining the method, apparatus and storage medium of consumption contributed value | |
CN104715409A (en) | Method and system for electronic commerce user purchasing power classification | |
CN102737315A (en) | Method and server for automatically triggering commodity attribute modification | |
CN104331818A (en) | Method and system capable of controlling differential pushing of merchant service information | |
CN106997515A (en) | Catering management method and device | |
CN108428153A (en) | Strategy adjusting method, server and the Developing Tactics system of presell commodity | |
US11727439B2 (en) | Generating optimized in-channel and cross-channel promotion recommendations using free shipping qualifier | |
CN108320170A (en) | Improve the method, apparatus and electronic device of the conversion ratio of the article in shopping cart | |
CN108470301A (en) | A kind of commodity network method of commerce | |
CN109934654A (en) | Method of Commodity Recommendation and system | |
JP6143930B1 (en) | Marketing support method, program, computer storage medium, and marketing support system | |
CN115510329B (en) | Brand marketing software management method based on cloud computing big data | |
CN114493705A (en) | Product sales influencing factor monitoring system oriented to full life cycle | |
CN110097425A (en) | A kind of shops's management system | |
CN114626921A (en) | E-commerce platform online shopping mall commodity sales promotion management method, system and computer storage medium | |
CN115345662A (en) | Live broadcast e-commerce data processing system based on block chain and big data | |
CN108510371A (en) | Dress ornament is newly sold integrated implementation method | |
CN114648389A (en) | Electronic commerce information processing system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180724 |
|
RJ01 | Rejection of invention patent application after publication |