CN110135871A - Calculate the method and apparatus that user purchases the phase again - Google Patents
Calculate the method and apparatus that user purchases the phase again Download PDFInfo
- Publication number
- CN110135871A CN110135871A CN201810105295.7A CN201810105295A CN110135871A CN 110135871 A CN110135871 A CN 110135871A CN 201810105295 A CN201810105295 A CN 201810105295A CN 110135871 A CN110135871 A CN 110135871A
- Authority
- CN
- China
- Prior art keywords
- user
- average daily
- consumption amount
- daily consumption
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000013461 design Methods 0.000 claims abstract description 11
- 230000005526 G1 to G0 transition Effects 0.000 claims description 28
- 238000003860 storage Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 10
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 9
- 239000010931 gold Substances 0.000 claims description 9
- 229910052737 gold Inorganic materials 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002123 temporal effect Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 14
- 238000006243 chemical reaction Methods 0.000 description 13
- 230000006399 behavior Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 230000006854 communication Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 241001269238 Data Species 0.000 description 4
- 241000209094 Oryza Species 0.000 description 4
- 235000007164 Oryza sativa Nutrition 0.000 description 4
- 235000013339 cereals Nutrition 0.000 description 4
- 235000013312 flour Nutrition 0.000 description 4
- 239000008267 milk Substances 0.000 description 4
- 210000004080 milk Anatomy 0.000 description 4
- 235000013336 milk Nutrition 0.000 description 4
- 239000000843 powder Substances 0.000 description 4
- 235000009566 rice Nutrition 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000005291 magnetic effect Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009469 supplementation Effects 0.000 description 2
- 244000061176 Nicotiana tabacum Species 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Abstract
The embodiment of the present invention provides a kind of method and apparatus that calculating user purchases the phase again, can accurately calculate the multiple purchase phase of user, user's buying habit be held, to design more effective suggested design for target user.This method comprises: obtaining the historical data that user buys specific products；According to the historical data, the true average daily consumption amount of user is calculated；The multiple purchase phase that user is directed to the product is calculated according to the true average daily consumption amount.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of calculating user to purchase the phase again.
Background technique
In recent years, with the high speed development of e-commerce, logistics service and Warehouse Service are constantly improve, product on line
The network user gradually switchs to convenience demand from low price demand, the product field that especially disappears fastly (disappear product fastly, fast-moving consumer goods (FMCG,
Fast Moving Consumer Goods) abbreviation, refer to that those service lifes are shorter, the faster consumer goods of consumption rate.
It is easiest to that people is allowed to understand that the product that disappear fastly include food, personal hygiene article, tobacco and the drinks and beverage of packaging.Why it is referred to as
Disappear fastly, be because they are articles for daily use first).Huge potential market attracts the positive of a large amount of electric business enterprises and retailer
Into becoming product on line and realize fast-developing important thrust.Using user's order data abundant, analysis and prediction user
Disappear the multiple purchase behaviors of product fastly, have become it is each company's prediction sales volume, a kind of important hand for promoting user experience, promoting conversion ratio
Section, while being also that electric business company optimizes user experience, enhance a shortcut of user's viscosity.
In the prior art, the product that disappear fastly purchase period calculating logic again and are mostly based on the following two kinds: being produced based on user's history purchase
The time interval of product calculates user and buys the Mean Time Between Replacement of this product, to predict the time that user buys next time；Or:
The daily consumption quantity of user is calculated based on History Order and product specification data, to predict the time that user buys next time.
In realizing process of the present invention, at least there are the following problems in the prior art for inventor's discovery:
(1) current user purchases time calculating again, is essentially all simply to buy certain part product time interval to user
Simple mean value computation is done, accuracy is difficult to ensure, is easy to be influenced by user's purchase Instable, result error is big；
(2) it does not differentiate between and normally buys and store goods, the purchase of other platforms situations such as, simply by consumption joint account,
The true average daily consumption of user cannot accurately be embodied；
(3) due to there is a large amount of third party businessman on electric business platform, the product specification data of these third party businessmans can be deposited
In certain missing, if simple have some deviations using calculating average daily quantity consumed based on product specification data；
(4) user experience influences limited.User purchases the displaying of product again at present, is more the history purchase for relying on user
Then product record is given simple exposure and is shown, is not directed to the multiple purchase period of user, makes intelligent guidance and prompt,
Conversion ratio hoisting power is limited.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of method and apparatus that calculating user purchases the phase again, can accurately calculate
The multiple purchase phase of user holds user's buying habit, to design more effective suggested design for target user.
To achieve the above object, according to an aspect of an embodiment of the present invention, it provides a kind of calculating user and purchases the phase again
Method.
The method that a kind of calculating user of the embodiment of the present invention purchases the phase again includes: the history for obtaining user and buying specific products
Data；According to the historical data, the true average daily consumption amount of user is calculated；It is calculated according to the true average daily consumption amount
User is directed to the multiple purchase phase of the product.
Optionally, the historical data includes following at least one information: user buys product value information, lower single time
Information, goods receiving time information, quantity purchase information and production unit cost information.
Optionally, according to the historical data, before the true average daily consumption amount for calculating user, the method is also wrapped
It includes: the historical data is cleaned, including being carried out based on user's portrait to the user data for not meeting default design conditions
It rejects, the missing values in the historical data handle and be filtered to abnormal data.
Optionally, the true average daily consumption amount for calculating user includes: with the time interval between user's adjacent purchase day
As a consumption section, the average daily consumption amount of user in a consumption section is set as an, each continuous consumption section daily consumes gold
Volume anAmplitude be g；It is daily consumed with respectively consuming the prediction of user described in the maximum value of the average daily consumption amount of section in stationary phase
The amount of money, the stationary phase refer to by compared with the average daily consumption amount of adjacent consumption section, the amplitude of average daily consumption amount is less than or equal to g
Consumption section composition period；Using the maximum value of other average daily consumption amounts of consumption section other than stationary phase as the user's
The average daily consumption amount of deviation, wherein other consumption sections other than the stationary phase refer to and the average daily consumption amount of adjacent consumption section
It compares, the amplitude of average daily consumption amount is greater than the consumption section of g；Daily disappeared using the average daily consumption amount of the prediction and the deviation
It consumes the amount of money and carries out mean value computation, obtain true average daily consumption amount.
Optionally, after the historical data for obtaining user's purchase specific products, the method also includes:
Partial history data are preselected as sample data；
The value that the amplitude g is adjusted using the sample data keeps the calculating of the true average daily consumption amount accurate
It spends optimal.
To achieve the above object, according to another aspect of an embodiment of the present invention, it provides a kind of calculating user and purchases the phase again
Device.
The device that a kind of calculating user of the embodiment of the present invention purchases the phase again includes: acquisition module, for obtaining user's purchase
The historical data of specific products；First computing module, for calculating the true average daily consumption gold of user according to the historical data
Volume；Second computing module, for calculating the multiple purchase phase that user is directed to the product according to the true average daily consumption amount.
Optionally, the historical data includes following at least one information: user buys product value information, lower single time
Information, goods receiving time information, quantity purchase information and production unit cost information.
Optionally, the acquisition module is also used to: according to the historical data, calculating the true average daily consumption gold of user
Before volume, the historical data is cleaned, including being drawn a portrait based on user to the user data for not meeting default design conditions
It is rejected, the missing values in the historical data handle and be filtered to abnormal data.
Optionally, first computing module is also used to: using the time interval between user's adjacent purchase day as one
Section is consumed, sets the average daily consumption amount of user in a consumption section as an, each average daily consumption amount a of continuous consumption sectionnAmplitude
For g；It is described steady respectively to consume the average daily consumption amount of prediction of user described in the maximum value of the average daily consumption amount of section in stationary phase
Periodically refer to by compared with the average daily consumption amount of adjacent consumption section, the amplitude of average daily consumption amount is less than or equal to the consumption section group of g
At period；Daily disappeared using the deviation of maximum value as the user of other average daily consumption amounts of consumption section other than stationary phase
Consume the amount of money, wherein other consumption sections other than the stationary phase refer to compared with the average daily consumption amount of adjacent consumption section, daily disappear
The amplitude for consuming the amount of money is greater than the consumption section of g；It is carried out using the average daily consumption amount of the prediction and the average daily consumption amount of the deviation
Mean value computation obtains true average daily consumption amount.
Optionally, described device further include: detection module, for obtain user buy specific products historical data it
Afterwards, partial history data are preselected as sample data；The value that the amplitude g is adjusted using the sample data, makes institute
The accuracy in computation for stating true average daily consumption amount is optimal.
To achieve the above object, according to an embodiment of the present invention in another aspect, providing a kind of electronic equipment.
The a kind of electronic equipment of the embodiment of the present invention includes: one or more processors；Storage device, for storing one
Or multiple programs, when one or more of programs are executed by one or more of processors, so that one or more of
Processor realizes the method that the calculating user of the embodiment of the present invention purchases the phase again.
To achieve the above object, another aspect according to an embodiment of the present invention, provides a kind of computer-readable medium.
A kind of computer-readable medium of the embodiment of the present invention, is stored thereon with computer program, and described program is processed
The method that the calculating user of the embodiment of the present invention purchases the phase again is realized when device executes.
One embodiment in foregoing invention has the following advantages that or the utility model has the advantages that in the embodiment of the present invention, is based on user
Portrait and user's history buying behavior, analysis find that user buys the same product to disappear under category fastly within long period of time
Price relatively, therefore using average daily consumption amount data calculate user the multiple purchase phase, so as to ignore due to product
The calculating offset issue of the incomplete average daily quantity consumed of bring of specification data makes the calculation in multiple purchase period more be bonded reality
Border scene；The present invention can cover the product of various consumer goods classification, such as milk powder, paper diaper, rice and flour coarse cereals household items
Class product, usage scenario is extensive, has directive significance to the sale of the consumer goods, applied in the practical business of electric business, Ke Yiwei
User makes intelligent guidance and prompt, conversion ratio hoisting power；By buying product value information, lower single time using user
The historical datas such as information, goods receiving time information, quantity purchase information and production unit cost information, so as to accurate, effective
User's history buying behavior is analyzed；By being carried out using true average daily consumption amount of the purchase computation model again to user
Before calculating, historical data is cleaned, is interfered so as to queueing problem data and abnormal data, improves the effect of calculating
Rate；Average daily consumption amount is calculated separately by the consumption section divided into stationary phase and Instable, so as to root
According to the true average daily consumption amount of the more accurate calculating user of normal data and deviation data；In the embodiment of the present invention, pass through
Selected part historical data is set as sample data, is adjusted as the parameter to multiple purchase computation model, it is multiple so as to ensure
The accuracy for purchasing computation model calculated result is optimal, improves the conversion ratio for being in purchase phase crowd.
Further effect possessed by above-mentioned non-usual optional way adds hereinafter in conjunction with specific embodiment
With explanation.
Detailed description of the invention
Attached drawing for a better understanding of the present invention, does not constitute an undue limitation on the present invention.Wherein:
Fig. 1 is the schematic diagram of the key step for the method that calculating user according to an embodiment of the present invention purchases the phase again；
Fig. 2 is the schematic diagram of the main logic for the method that calculating user according to an embodiment of the present invention purchases the phase again；
Fig. 3 is the schematic diagram of the main modular for the device that calculating user according to an embodiment of the present invention purchases the phase again；
Fig. 4 is that the embodiment of the present invention can be applied to exemplary system architecture figure therein；
Fig. 5 is adapted for the structural representation of the computer system for the terminal device or server of realizing the embodiment of the present invention
Figure.
Specific embodiment
Below in conjunction with attached drawing, an exemplary embodiment of the present invention will be described, including the various of the embodiment of the present invention
Details should think them only exemplary to help understanding.Therefore, those of ordinary skill in the art should recognize
It arrives, it can be with various changes and modifications are made to the embodiments described herein, without departing from scope and spirit of the present invention.Together
Sample, for clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.
Unlike 3C, big household electrical appliances category, user has stronger periodicity for the purchase of the product for the category that disappears fastly,
Meanwhile the income situation within the longer term due to most of user will not change significantly, the same product that disappear fastly of purchase
Product under class is nearly all located at same price, therefore the above-mentioned characteristic in the embodiment of the present invention for the product that disappear fastly disappears fastly to construct
The multiple purchase computation model of product, accurately to realize the calculating of the multiple purchase phase for the product that disappear fastly to user.
Fig. 1 is the method that calculating user according to an embodiment of the present invention purchases the phase again, as shown in Figure 1, the embodiment of the present invention
The method that user purchases the phase again is calculated mainly to include the following steps:
Step S101: the historical data that user buys specific products is obtained.In the embodiment of the present invention, historical data can with but
Be not limited to include following at least one information: user buys product value information, lower single temporal information, goods receiving time information, purchase
Buy quantity information and production unit cost information.
In addition, the embodiment of the present invention calculating again purchase the phase method can also include: historical data is cleaned, including
The user data for not meeting default design conditions is rejected based on user's portrait, the missing values in historical data have been carried out
It is apt to and abnormal data is filtered.
After step S101 gets user's history data, calculated since step S102.
Step S102: according to historical data, the true average daily consumption amount of user is calculated.In the embodiment of the present invention, utilize
Again purchase computation model calculate user true average daily consumption amount include: using user it is adjacent purchase day between time interval as
One consumption section sets the average daily consumption amount of user in a consumption section as an, each average daily consumption amount a of continuous consumption sectionn's
Amplitude is g；Respectively to consume the average daily consumption amount of prediction of user described in the maximum value of the average daily consumption amount of section, institute in stationary phase
Stating stationary phase refers to that by compared with the average daily consumption amount of adjacent consumption section, the amplitude of average daily consumption amount is less than or equal to the consumption of g
The period of Duan Zucheng；Using the maximum value of other average daily consumption amounts of consumption section other than stationary phase as the deviation day of the user
Equal consumption amount, wherein other consumption sections other than the stationary phase refer to compared with the average daily consumption amount of adjacent consumption section, day
The amplitude of equal consumption amount is greater than the consumption section of g；Utilize the average daily consumption amount of the prediction and the average daily consumption amount of the deviation
Mean value computation is carried out, true average daily consumption amount is obtained.
Step S103: the multiple purchase phase that user is directed to the product is calculated according to true average daily consumption amount.The embodiment of the present invention
In, the multiple purchase phase calculation formula purchased in computation model again can be with are as follows: purchases phase=purchase phase last time+(last time buys total amount/true again
Real average daily consumption amount).
In addition, in order to promote the accuracy that user purchases the calculating of phase again going through for specific products can be bought obtaining user
After history data, before calculating true average daily consumption amount, the calculating user of the embodiment of the present invention purchases in the method for phase also again
It may include: preselected partial history data as sample data, then using the value of sample data adjustment amplitude g, make
The accuracy in computation of the true average daily consumption amount is optimal.
In conclusion being found based on user's portrait and history buying behavior, analysis longer one in the embodiment of the present invention
The same product to disappear under category fastly of same user's purchase has similar price in section period.Therefore the true of user daily disappears
The consumption amount of money can approximately be equal to the average daily quantity consumed of user, avoid because the product specification data of third party businessman are not complete
And lead to not the problem of accurately measuring the true average daily quantity consumed of user.In the embodiment of the present invention, true average daily consumption gold
Volume is to obtain ordered series of numbers, and loop iteration operation based on the average daily consumption amount of the multiple consumption sections of user, is transported by measuring business
With middle GMV stretch rate and conversion ratio, the floating range for purchasing the value of computation model parameter again is determined.
Above-mentioned user's portrait refers to essential attribute (age, gender, region), purchasing power, behavior using existing user
The progress such as feature, hobby, psychological characteristics, social networks generally labeling (for example, mark this person be geek, family master
Woman etc.).In the present invention, the crowd for obviously not agreeing with the category is excluded using user's portrait, improves the precision of prediction.
In the multiple purchase computation model of the embodiment of the present invention, based on the assumption that and calculation formula realize again purchase the phase meter
It calculates.
Model hypothesis:
1, the same product to disappear under category fastly that normal users are bought within longer one period has similar price；
2, the quantity of the average daily consumable products of normal users is more stable, is not in biggish fluctuation；
3, it is small probability event (average daily consumption caused by storing goods twice in succession twice or more that normal users, which are continuously stored goods,
The case where amount significantly increases is small probability event)；
4, the behavior of storing goods refers to that dosage purchase within a short period of time is higher than the quantity of normal consumption, causes this period day's expenditure
The case where uprushing.
Calculation formula:
If the paper diaper that certain user buys X1, X2 ... Xn amount of money for Dn days in D1, D2 ... respectively, then have consumption section
Average daily consumption amount a in (as previously mentioned, using time interval between user's adjacent purchase day as a consumption section)n:
If the amplitude of the average daily consumption amount of money of each continuous consumption section is g, then have:
So, the average daily consumption amount E of the prediction of this user is as follows:
Wherein, 1 <=imThe integer of <=n, ifThenAnd
In the above-mentioned average daily consumption amount E calculation formula of prediction, expression takes stationary phase (i.e. by daily consuming in adjacent consumption section
In the period that consumption section of the amplitude of the amount of money less than or equal to g forms, g can carry out value according to the accuracy requirement actually calculated herein,
Such as it is taken as multiple continuous consumption sections in 15%), such as [a1,a2,a3],[a10,a11] ..., with putting down for each consumption section
Equal average daily consumption amount of the daily consumption amount of money as the consumption section finally takes the average daily consumption gold of all consumption sections in stationary phase
Prediction average daily consumption amount of the maximum value of volume as the user.
In addition, setting 15≤Dn-Dn-1≤ 30, for anIt is not in the stationary phase that amplitude g is 15%, then deviation daily consumes
Amount of money M calculation formula is as follows:
M=max { an-m.....an, wherein m is the integer more than or equal to 0
Formula expression takes the maximum value for not occurring average daily consumption amount in the calculation formula of above-mentioned E, and when calculating,
Limit the average daily consumption amount anConsumption section interval number of days Dn-Dn-1To be less than or equal to 30 more than or equal to 15.
Using both of the aforesaid formula, the true average daily consumption amount A of user is calculated are as follows:
A=Average { E, M }
The total amount of the last purchase product P of user is denoted as X, the purchase date is denoted as Dl, what user bought next time
Date predicted value is Dn, then the calculation formula of phase is purchased again are as follows:
Fig. 2 is the schematic diagram of the main logic for the method that calculating user according to an embodiment of the present invention purchases the phase again.It ties below
Fig. 2 is closed to describe to the main realization logic for the method that the calculating user of the embodiment of the present invention purchases the phase again in detail.
1. data cleansing:
The relevant historical data of user, such as the order table data of history purchase, including the purchase amount of money are extracted, when lower single
Between, goods receiving time, quantity purchase, cargo price.
The processing of shortage of data value and perfect, such as carried out with the mean value of user's history data or nearly 3 months data
Weighting.
Due to enterprise account, risk account will affect the precision of multiple purchase computation model calculated result, it is contemplated that this hair
The effective object of bright embodiment is consuming public mostly, therefore, can be in conjunction with the user of electric business platform in the embodiment of the present invention
Information data, air control data will be related to the abnormal users accounts such as enterprise account, risk account and be filtered.
User's order data after output cleaning.
2. calculating the multiple purchase phase of user using purchase computation model again:
According to user's order data of input, algorithm is brought into.
Export user, product, next time time buying.
3. purchasing the parameter testing of computation model again:
The calculated result of computation model will be purchased again in abovementioned steps 2, AB test is carried out, to verify calculated result.This hair
In bright embodiment, A version is to count the accuracy of the multiple purchase computation model calculated result of the embodiment of the present invention, and B version can be with
Mean value to use user to buy interval number of days predicts the date bought next time.It is proved by test, the accuracy rate of A version
For 31.6% (i.e. in forecast date and actual date deviation 3 days), the accuracy of B version is 9.7% (i.e. forecast date and reality
Date deviation 3 days or more).
In the embodiment of the present invention, the accuracy to the calculated result of multiple purchase computation model is also based on to adjust multiple purchase
The parameter of computation model.By loop iteration, the parameter of computation model is purchased in adjustment again, and the main adjusting consecutive intervals phase daily consumes
Amount of money amplitude parameter g is optimal the output calculated result of model.
4. the task of automation:
In the embodiment of the present invention, the needs based on business can be by the multiple purchase computation model application of the embodiment of the present invention
It in other business systems, i.e., is that other business systems are purchased computation model with this again and docked by exploitation business system interface, it is right
The user data of bottom carries out analysis prediction, obtains the multiple purchase phase of user, and export to business system, for each business system
Follow-up decision provides foundation.
Specifically, purchase computation model calculates the scheme for purchasing the phase again again used in through the invention, electric business can be helped
Platform more accurately calculates the average daily spending amount of user's fast-moving consumer goods, and then more accurately predicts user's time buying, leads to
It crosses and the friendly touching of target user is reached, promote user experience, user is allowed to feel the hommization of electric business platform, drawn high to realize
The effect of conversion ratio and GMV.It is shown according to experimental data, purchase computation model again is for crowd's conversion ratio in the purchase phase
3 times or so of non-purchase phase conversion ratio.It is specifically docked in business system, can include but is not limited to the following:
(1) according to user's time buying of prediction, the consumer goods product information that user requires supplementation with periodically is pushed, it is directly logical
It crosses touching and completes one-button-to-buy up to channel, promote single efficiency under user；
(2) sequence of optimization recommended products, the consumer goods product priority that user is required supplementation in the recent period are turned up, and promote user
Selection efficiency；
(3) consumer goods product Method for Sales Forecast, by the calculating of cycles consumed, one section of future as prediction consumer goods product
The factor of the sales volume of time, promotion sales volume predictablity rate, and then instruct inventory, price etc..
The technical solution that calculating user purchases the phase again according to embodiments of the present invention can be seen that be gone through based on user's portrait and user
History buying behavior, analysis find that user buys the same price for disappearing the product under category fastly within long period of time and relatively connects
Closely, therefore using average daily consumption amount data the multiple purchase phase of user is calculated, so as to ignore since product specification data are not complete
The calculating offset issue of the average daily quantity consumed of bring makes the calculation in multiple purchase period more be bonded actual scene；This hair
The bright product that can cover various consumer goods classification, such as milk powder, paper diaper, rice and flour coarse cereals household items class product use
Scene is extensive, has directive significance to the sale of the consumer goods, applied in the practical business of electric business, can make intelligence for user
Guidance and prompt, conversion ratio hoisting power；When by buying product value information, lower single temporal information using user, receiving
Between the historical datas such as information, quantity purchase information and production unit cost information, so as to it is accurate, effectively user's history is purchased
The behavior of buying is analyzed；By using again purchase computation model the true average daily consumption amount of user is calculated before, it is right
Historical data is cleaned, and is interfered so as to queueing problem data and abnormal data, is improved the efficiency of calculating；By dividing into
Consumption section in stationary phase and Instable calculates separately average daily consumption amount, so as to according to normal data and partially
The true average daily consumption amount of the more accurate calculating user of difference data；In the embodiment of the present invention, gone through by the way that selected part is arranged
History data are adjusted as sample data as the parameter to multiple purchase computation model, so as to ensure that multiple purchase computation model calculates
As a result accuracy is optimal, improves the conversion ratio for being in purchase phase crowd.
Fig. 3 is the schematic diagram of the main modular for the device that calculating user according to an embodiment of the present invention purchases the phase again.
The device 300 that the calculating user of the embodiment of the present invention purchases the phase again mainly includes following module: obtaining module 301, the
One computing module 302, the second computing module 303.
Wherein, it obtains module 301 and is used to obtain the historical data that user buys specific products；First computing module 302 is used
According to the historical data, the true average daily consumption amount of user is calculated；Second computing module 303 is used for according to described true
Average daily consumption amount calculates the multiple purchase phase that user is directed to the product.
Wherein, historical data includes following at least one information: user buy product value information, lower single temporal information,
Goods receiving time information, quantity purchase information and production unit cost information.
In the embodiment of the present invention, obtaining module 301 can also be used in: according to historical data, calculate the true average daily of user
Before consumption amount, historical data is cleaned, including being drawn a portrait based on user to the number of users for not meeting default design conditions
According to rejected, to the missing values in historical data carry out handle and abnormal data is filtered.
First computing module 302 can also be used in: using the time interval between user's adjacent purchase day as a consumption section,
The average daily consumption amount of user in a consumption section is set as an, each average daily consumption amount a of continuous consumption sectionnAmplitude be g；With
The average daily consumption amount of prediction of user described in the maximum value of the average daily consumption amount of section is respectively consumed in stationary phase, the stationary phase is
Refer to by compared with the average daily consumption amount of adjacent consumption section, consumption section composition of the amplitude of average daily consumption amount less than or equal to g when
Phase；Gold is daily consumed using the deviation of maximum value as the user of other average daily consumption amounts of consumption section other than stationary phase
Volume, wherein other consumption sections other than the stationary phase refer to that compared with the average daily consumption amount of adjacent consumption section, average daily consumption is golden
The amplitude of volume is greater than the consumption section of g；Using average daily consumption amount and the average daily consumption amount progress mean value computation of deviation is predicted, obtain
True average daily consumption amount.
In addition, device 300 may also include that detection module (not shown), for obtaining user's purchase specific products
Historical data after, preselect partial history data as sample data；The amplitude g is adjusted using the sample data
Value, keep the accuracy in computation of the true average daily consumption amount optimal.
From the above, it can be seen that in the embodiment of the present invention, based on user's portrait and user's history buying behavior, analysis
It was found that user buys the price of the same product under category that disappears fastly relatively within long period of time, therefore using average daily
Consumption amount data calculate the multiple purchase phase of user, so as to ignore since the infull bring of product specification data daily consumes number
The calculating offset issue of amount makes the calculation in multiple purchase period more be bonded actual scene；The present invention can cover a variety of
The product of consumer goods classification, such as milk powder, paper diaper, rice and flour coarse cereals household items class product, usage scenario is extensive, to the consumer goods
Sale there is directive significance, applied in the practical business of electric business, intelligent guidance and prompt can be made for user, converted
Rate hoisting power；Believed by buying product value information, lower single temporal information, goods receiving time information, quantity purchase using user
Breath and the historical datas such as production unit cost information, so as to it is accurate, effectively user's history buying behavior is analyzed；It is logical
It crosses using before purchase computation model calculates the true average daily consumption amount of user again, historical data is cleaned,
It is interfered so as to queueing problem data and abnormal data, improves the efficiency of calculating；By dividing into stationary phase and Instable
Interior consumption section calculates separately average daily consumption amount, so as to more accurate according to normal data and deviation data
Calculate the true average daily consumption amount of user；In the embodiment of the present invention, by setting selected part historical data as sample number
According to, it being adjusted as the parameter to multiple purchase computation model, the accuracy so as to ensure multiple purchase computation model calculated result is optimal,
Improve the conversion ratio for being in purchase phase crowd.
Fig. 4 shows to purchase phase method again using the calculating user of the embodiment of the present invention or calculate user purchases phase device again
Exemplary system architecture 400.
As shown in figure 4, system architecture 400 may include terminal device 401,402,403, network 404 and server 405.
Network 404 between terminal device 401,402,403 and server 405 to provide the medium of communication link.Network 404 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 401,402,403 and be interacted by network 404 with server 405, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 401,402,403
(merely illustrative) such as the application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform softwares.
Terminal device 401,402,403 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 405 can be to provide the server of various services, such as utilize terminal device 401,402,403 to user
The shopping class website browsed provides the back-stage management server (merely illustrative) supported.Back-stage management server can be to reception
To the data such as information query request analyze etc. processing, and by processing result (such as target push information, product letter
Breath -- merely illustrative) feed back to terminal device.
It is generally held by server 405 it should be noted that calculating user provided by the embodiment of the present invention and purchasing phase method again
Row, correspondingly, calculating user are purchased phase device again and are generally positioned in server 405.
It should be understood that the number of terminal device, network and server in Fig. 4 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Below with reference to Fig. 5, it illustrates the computer systems 500 for the terminal device for being suitable for being used to realize the embodiment of the present invention
Structural schematic diagram.Terminal device shown in Fig. 5 is only an example, function to the embodiment of the present invention and should not use model
Shroud carrys out any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into the program in random access storage device (RAM) 503 from storage section 508 and
Execute various movements appropriate and processing.In RAM 503, also it is stored with system 500 and operates required various programs and data.
CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interface 505 is connected to lower component: the importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net executes communication process.Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 510, in order to read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, disclosed embodiment, the process described above with reference to flow chart may be implemented as counting according to the present invention
Calculation machine software program.For example, embodiment disclosed by the invention includes a kind of computer program product comprising be carried on computer
Computer program on readable medium, the computer program include the program code for method shown in execution flow chart.?
In such embodiment, which can be downloaded and installed from network by communications portion 509, and/or from can
Medium 511 is dismantled to be mounted.When the computer program is executed by central processing unit (CPU) 501, system of the invention is executed
The above-mentioned function of middle restriction.
It should be noted that computer-readable medium shown in the present invention can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the present invention, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In invention, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module involved in the embodiment of the present invention can be realized by way of software, can also be by hard
The mode of part is realized.Described module also can be set in the processor, for example, can be described as: a kind of processor packet
It includes and obtains module, the first computing module and the second computing module.Wherein, the title of these modules is not constituted under certain conditions
Restriction to the module itself is also described as " buying the history of specific products for obtaining user for example, obtaining module
The module of data ".
As on the other hand, the present invention also provides a kind of computer-readable medium, which be can be
Included in equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying equipment.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the equipment, makes
Obtaining the equipment includes: the historical data for obtaining user and buying specific products；According to the historical data, the true day of user is calculated
Equal consumption amount；The multiple purchase phase that user is directed to the product is calculated according to the true average daily consumption amount.
Technical solution according to an embodiment of the present invention finds to use based on user's portrait and user's history buying behavior, analysis
The price of the same product under category that disappears fastly is bought relatively in family within long period of time, therefore using average daily consumption gold
Specified number is according to the multiple purchase phase for calculating user, so as to ignore the meter due to the incomplete average daily quantity consumed of bring of product specification data
Offset issue is calculated, the calculation in multiple purchase period is made more to be bonded actual scene；The present invention can cover various consumer goods
The product of classification, such as milk powder, paper diaper, rice and flour coarse cereals household items class product, usage scenario is extensive, the sale to the consumer goods
Intelligent guidance and prompt can be made for user applied in the practical business of electric business with directive significance, conversion ratio is promoted
Ability；By using user buy product value information, lower single temporal information, goods receiving time information, quantity purchase information and
The historical datas such as production unit cost information, so as to it is accurate, effectively user's history buying behavior is analyzed；By in benefit
Before being calculated with multiple purchase computation model the true average daily consumption amount of user, historical data is cleaned, so as to
It is interfered with queueing problem data and abnormal data, improves the efficiency of calculating；By dividing into disappearing in stationary phase and Instable
Consumption section calculates separately average daily consumption amount, so as to be used according to the more accurate calculating of normal data and deviation data
The true average daily consumption amount at family；In the embodiment of the present invention, by setting selected part historical data as sample data, it is used as
Parameter adjustment to multiple purchase computation model, the accuracy so as to ensure multiple purchase computation model calculated result is optimal, at raising
In the conversion ratio of purchase phase crowd.
Above-mentioned specific embodiment, does not constitute a limitation on the scope of protection of the present invention.Those skilled in the art should be bright
It is white, design requirement and other factors are depended on, various modifications, combination, sub-portfolio and substitution can occur.It is any
Made modifications, equivalent substitutions and improvements etc. within the spirit and principles in the present invention, should be included in the scope of the present invention
Within.
Claims (12)
1. a kind of method for calculating user and purchasing the phase again characterized by comprising
Obtain the historical data that user buys specific products；
According to the historical data, the true average daily consumption amount of user is calculated；
The multiple purchase phase that user is directed to the product is calculated according to the true average daily consumption amount.
2. the method according to claim 1, wherein the historical data includes following at least one information: using
Buy product value information, lower single temporal information, goods receiving time information, quantity purchase information and production unit cost information in family.
3. the method according to claim 1, wherein calculating the true day of user according to the historical data
Before equal consumption amount, the method also includes: the historical data is cleaned, including based on user's portrait to not meeting
The user data of default design conditions is rejected, the missing values in the historical data is carried out with processing and to abnormal data
It is filtered.
4. the method according to claim 1, wherein the true average daily consumption amount for calculating user includes:
Using the time interval between user's adjacent purchase day as a consumption section, sets the average daily of user in a consumption section and disappear
The consumption amount of money is an, each average daily consumption amount a of continuous consumption sectionnAmplitude be g；
It is described steady respectively to consume the average daily consumption amount of prediction of user described in the maximum value of the average daily consumption amount of section in stationary phase
Periodically refer to by compared with the average daily consumption amount of adjacent consumption section, the amplitude of average daily consumption amount is less than or equal to the consumption section group of g
At period；
Gold is daily consumed using the deviation of maximum value as the user of other average daily consumption amounts of consumption section other than stationary phase
Volume, wherein other consumption sections other than the stationary phase refer to that compared with the average daily consumption amount of adjacent consumption section, average daily consumption is golden
The amplitude of volume is greater than the consumption section of g；
Mean value computation is carried out using the average daily consumption amount of the prediction and the average daily consumption amount of the deviation, obtains really daily disappearing
Consume the amount of money.
5. according to the method described in claim 4, it is characterized in that, obtain user buy specific products historical data it
Afterwards, the method also includes:
Partial history data are preselected as sample data；
The value that the amplitude g is adjusted using the sample data makes the accuracy in computation of the true average daily consumption amount most
It is excellent.
6. a kind of device for calculating user and purchasing the phase again characterized by comprising
Module is obtained, the historical data of specific products is bought for obtaining user；
First computing module, for calculating the true average daily consumption amount of user according to the historical data；
Second computing module, for calculating the multiple purchase phase that user is directed to the product according to the true average daily consumption amount.
7. device according to claim 6, which is characterized in that the historical data includes following at least one information: being used
Buy product value information, lower single temporal information, goods receiving time information, quantity purchase information and production unit cost information in family.
8. device according to claim 6, which is characterized in that the acquisition module is also used to: according to the history number
According to, before the true average daily consumption amount for calculating user, the historical data is cleaned, including based on user draw a portrait to not
The user data for meeting default design conditions is rejected, the missing values in the historical data is carried out with processing and to exception
Data are filtered.
9. device according to claim 6, which is characterized in that first computing module is also used to:
Using the time interval between user's adjacent purchase day as a consumption section, sets the average daily of user in a consumption section and disappear
The consumption amount of money is an, each average daily consumption amount a of continuous consumption sectionnAmplitude be g；
It is described steady respectively to consume the average daily consumption amount of prediction of user described in the maximum value of the average daily consumption amount of section in stationary phase
Periodically refer to by compared with the average daily consumption amount of adjacent consumption section, the amplitude of average daily consumption amount is less than or equal to the consumption section group of g
At period；
Gold is daily consumed using the deviation of maximum value as the user of other average daily consumption amounts of consumption section other than stationary phase
Volume, wherein other consumption sections other than the stationary phase refer to that compared with the average daily consumption amount of adjacent consumption section, average daily consumption is golden
The amplitude of volume is greater than the consumption section of g；
Mean value computation is carried out using the average daily consumption amount of the prediction and the average daily consumption amount of the deviation, obtains really daily disappearing
Consume the amount of money.
10. device according to claim 9, which is characterized in that described device further include: detection module, for obtaining
After user buys the historical data of specific products, partial history data are preselected as sample data；Utilize the sample
The value of amplitude g described in data point reuse keeps the accuracy in computation of the true average daily consumption amount optimal.
11. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
Such as method as claimed in any one of claims 1 to 5 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810105295.7A CN110135871A (en) | 2018-02-02 | 2018-02-02 | Calculate the method and apparatus that user purchases the phase again |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810105295.7A CN110135871A (en) | 2018-02-02 | 2018-02-02 | Calculate the method and apparatus that user purchases the phase again |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110135871A true CN110135871A (en) | 2019-08-16 |
Family
ID=67567124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810105295.7A Pending CN110135871A (en) | 2018-02-02 | 2018-02-02 | Calculate the method and apparatus that user purchases the phase again |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135871A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461632A (en) * | 2020-06-18 | 2020-07-28 | 北京每日优鲜电子商务有限公司 | Commodity supply and demand balancing method and system, server and medium |
| CN113763076A (en) * | 2020-07-21 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Data filtering method and device |
| CN116127180A (en) * | 2022-11-09 | 2023-05-16 | 乾三(北京)科技有限公司 | Label configuration method, device, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5909023A (en) * | 1996-02-23 | 1999-06-01 | Hitachi, Ltd. | Online shopping support method and system for sales promotions based on the purchase history of users |
| JP2013003834A (en) * | 2011-06-16 | 2013-01-07 | Hitachi Consumer Electronics Co Ltd | Merchandise purchase recommendation device |
| CN103150660A (en) * | 2011-12-06 | 2013-06-12 | 阿里巴巴集团控股有限公司 | User message reminding method and device produced in network shopping platform |
| CN103578022A (en) * | 2012-07-19 | 2014-02-12 | 纽海信息技术（上海）有限公司 | Automatic online shopping device and automatic online shopping method |
| CN103971217A (en) * | 2014-02-24 | 2014-08-06 | 浙江大学 | Method and system of drug inventory management |
| CN106157097A (en) * | 2016-08-22 | 2016-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and system |
| CN107123017A (en) * | 2017-03-22 | 2017-09-01 | 重庆允升科技有限公司 | A kind of industrial goods source commodity recommends method |
| CN107451840A (en) * | 2016-05-31 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | A kind of Transaction Information method for pushing and device |
-
2018
- 2018-02-02 CN CN201810105295.7A patent/CN110135871A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5909023A (en) * | 1996-02-23 | 1999-06-01 | Hitachi, Ltd. | Online shopping support method and system for sales promotions based on the purchase history of users |
| JP2013003834A (en) * | 2011-06-16 | 2013-01-07 | Hitachi Consumer Electronics Co Ltd | Merchandise purchase recommendation device |
| CN103150660A (en) * | 2011-12-06 | 2013-06-12 | 阿里巴巴集团控股有限公司 | User message reminding method and device produced in network shopping platform |
| CN103578022A (en) * | 2012-07-19 | 2014-02-12 | 纽海信息技术（上海）有限公司 | Automatic online shopping device and automatic online shopping method |
| CN103971217A (en) * | 2014-02-24 | 2014-08-06 | 浙江大学 | Method and system of drug inventory management |
| CN107451840A (en) * | 2016-05-31 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | A kind of Transaction Information method for pushing and device |
| CN106157097A (en) * | 2016-08-22 | 2016-11-23 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation and system |
| CN107123017A (en) * | 2017-03-22 | 2017-09-01 | 重庆允升科技有限公司 | A kind of industrial goods source commodity recommends method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461632A (en) * | 2020-06-18 | 2020-07-28 | 北京每日优鲜电子商务有限公司 | Commodity supply and demand balancing method and system, server and medium |
| CN113763076A (en) * | 2020-07-21 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Data filtering method and device |
| CN116127180A (en) * | 2022-11-09 | 2023-05-16 | 乾三(北京)科技有限公司 | Label configuration method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee | A GA-based optimisation model for big data analytics supporting anticipatory shipping in Retail 4.0 | |
| Han et al. | Collection channel and production decisions in a closed-loop supply chain with remanufacturing cost disruption | |
| Giri et al. | Supply chain model with price-and trade credit-sensitive demand under two-level permissible delay in payments | |
| Ghasemy Yaghin et al. | Enhanced joint pricing and lotsizing problem in a two-echelon supply chain with logit demand function | |
| Dye et al. | Deterministic ordering policy with price-and stock-dependent demand under fluctuating cost and limited capacity | |
| CN108985809A (en) | Motivate method, apparatus, electronic equipment and the storage medium of push | |
| CN110135871A (en) | Calculate the method and apparatus that user purchases the phase again | |
| CN110109901A (en) | The method and apparatus for screening target object | |
| CN110020143A (en) | A kind of landing page generation method and device | |
| CN109961198A (en) | Related information generation method and device | |
| Choi et al. | Scheduling and co-ordination of multi-suppliers single-warehouse-operator single-manufacturer supply chains with variable production rates and storage costs | |
| CN109961299A (en) | The method and apparatus of data analysis | |
| CN109685537A (en) | Analysis method, device, medium and the electronic equipment of user behavior | |
| CN113065882A (en) | Commodity processing method and device and electronic equipment | |
| CN107451736A (en) | Intelligent refrigerator Internet of Things business management system, control method, device and refrigerator | |
| Deligiannis et al. | Predicting the optimal date and time to send personalized marketing messages to repeat buyers | |
| CN109934523A (en) | Information processing method and device | |
| Pakhira et al. | Two-level supply chain of a seasonal deteriorating item with time, price, and promotional cost dependent demand under finite time horizon | |
| CN110020112A (en) | Object Push method and its system | |
| CN109146533A (en) | Information-pushing method and device | |
| Liu et al. | Coordination of dual-channel supply chains with uncertain demand information | |
| CN109002925A (en) | Traffic prediction method and apparatus | |
| Miralles-Pechuán et al. | A 2020 perspective on “A novel methodology for optimizing display advertising campaigns using genetic algorithms” | |
| CN111612385B (en) | Method and device for clustering articles to be distributed | |
| CN110232620A (en) | Trade company's label determines method, apparatus, electronic equipment and readable storage medium storing program for executing |
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 |