CN110135871B - Method and device for calculating user repurchase period - Google Patents
Method and device for calculating user repurchase period Download PDFInfo
- Publication number
- CN110135871B CN110135871B CN201810105295.7A CN201810105295A CN110135871B CN 110135871 B CN110135871 B CN 110135871B CN 201810105295 A CN201810105295 A CN 201810105295A CN 110135871 B CN110135871 B CN 110135871B
- Authority
- CN
- China
- Prior art keywords
- user
- consumption amount
- daily
- consumption
- period
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000004364 calculation method Methods 0.000 claims description 81
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 description 14
- 230000006399 behavior Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 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
- 230000003287 optical effect Effects 0.000 description 4
- 239000000843 powder Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 235000009566 rice Nutrition 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000001965 increasing effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000012946 outsourcing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005526 G1 to G0 transition Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 235000013410 fast food Nutrition 0.000 description 1
- 210000001503 joint 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
- 238000006467 substitution reaction 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
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method and a device for calculating the re-purchase period of a user, which can accurately calculate the re-purchase period of the user and grasp the purchase habit of the user, thereby designing a more effective recommendation scheme for a target user. The method comprises the following steps: acquiring historical data of a user purchasing a specific product; calculating the real-day consumption amount of the user according to the historical data; and calculating the repurchase period of the user for the product according to the real daily average consumption amount.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method for calculating a user repurchase period.
Background
With the recent development of electronic commerce, the network users of online products are gradually changed from low price demands to convenience demands, especially in the field of quick-service products (quick-service products, short for quick-service consumer products (FMCG, fast Moving Consumer Goods)), which are consumer products having a short service life and a high consumption speed. The huge potential market attracts the positive entry of a large number of e-commerce enterprises and retail enterprises, and becomes an important thrust for realizing the rapid development of online products. The method has the advantages that the rich order data of the user are utilized to analyze and predict the re-purchase behavior of the quick consumer, so that the method becomes an important means for predicting sales volume, improving user experience and improving conversion rate of all companies, and meanwhile, the method is a shortcut for optimizing user experience and enhancing user viscosity of e-commerce companies.
In the prior art, the fast food repurchase period calculation logic is mostly based on the following two types: calculating an average interval time for the user to purchase the product based on the time interval for the user to purchase the product historically, thereby predicting the time for the user to purchase next time; or: the daily consumption amount of the user is calculated based on the historical order and the product specification data, thereby predicting the time of the user's next purchase.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
(1) The current user repurchase time calculation is basically simple, the time interval of purchasing a certain product by the user is simply calculated by means of average value, the accuracy is difficult to ensure, the influence of the purchase unstable period of the user is easy to cause, and the result deviation is large;
(2) The conditions of normal purchase, stock, purchase on other platforms and the like are not distinguished, the consumption is simply combined and calculated, and the real daily average consumption of a user cannot be accurately reflected;
(3) Because a large number of third-party merchants exist on the electronic commerce platform, certain defects exist in product specification data of the third-party merchants, and if the average daily consumption amount is calculated based on the product specification data by simple use, some deviation exists;
(4) The user experience has limited impact. At present, the display of the re-purchased products of the user is more dependent on the history purchase product records of the user, then simple exposure display is given, intelligent guidance and prompt are not made aiming at the re-purchase period of the user, and the conversion rate improving capability is limited.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a method and a device for calculating the repurchase period of a user, which can accurately calculate the repurchase period of the user and grasp the buying habit of the user, thereby designing a more effective recommendation scheme for a target user.
To achieve the above object, according to one aspect of the embodiments of the present invention, there is provided a method of calculating a user repurchase period.
The method for calculating the user repurchase period comprises the following steps: acquiring historical data of a user purchasing a specific product; calculating the real-day consumption amount of the user according to the historical data; and calculating the repurchase period of the user for the product according to the real daily average consumption amount.
Optionally, the history data includes at least one of the following information: the user purchases product amount information, order time information, receipt time information, purchase quantity information, and product unit price information.
Optionally, before calculating the real-day consumption amount of the user according to the history data, the method further comprises: and cleaning the historical data, including removing the user data which does not meet the preset calculation conditions based on the user image, processing the missing values in the historical data and filtering the abnormal data.
Optionally, calculating the real-day average consumption amount of the user includes: taking the time interval between adjacent purchase days of the user as a consumption section, setting the daily average consumption amount of the user in the consumption section as a n, and setting the amplitude of the daily average consumption amount a n of each continuous consumption section as g; the predicted daily consumption amount of the user is set to the maximum value of the daily consumption amount of each consumption section in the stable period, wherein the stable period is a period consisting of consumption sections with the amplitude of the daily consumption amount being less than or equal to g compared with the daily consumption amount of the adjacent consumption sections; taking the maximum value of the daily average consumption amount of other consumption sections except the stable period as the deviation daily average consumption amount of the user, wherein the other consumption sections except the stable period refer to consumption sections with the amplitude of the daily average consumption amount being larger than g compared with the daily average consumption amount of the adjacent consumption sections; and calculating the average value by utilizing the predicted average daily consumption amount and the deviation average daily consumption amount to obtain the real average daily consumption amount.
Optionally, after obtaining the historical data of the user purchasing the particular product, the method further comprises:
pre-selecting a part of history data as sample data;
and adjusting the value of the amplitude g by using the sample data so as to optimize the calculation accuracy of the real daily average consumption amount.
To achieve the above object, according to another aspect of the embodiments of the present invention, there is provided an apparatus for calculating a user repurchase period.
The device for calculating the user repurchase period comprises the following components: the acquisition module is used for acquiring historical data of a user purchasing a specific product; the first calculation module is used for calculating the real-day consumption amount of the user according to the historical data; and the second calculation module is used for calculating the repurchase period of the user for the product according to the real daily average consumption amount.
Optionally, the history data includes at least one of the following information: the user purchases product amount information, order time information, receipt time information, purchase quantity information, and product unit price information.
Optionally, the acquiring module is further configured to: before the real-day consumption amount of the user is calculated according to the historical data, the historical data is cleaned, and the method comprises the steps of removing the user data which does not meet preset calculation conditions based on user images, processing missing values in the historical data and filtering abnormal data.
Optionally, the first computing module is further configured to: taking the time interval between adjacent purchase days of the user as a consumption section, setting the daily average consumption amount of the user in the consumption section as a n, and setting the amplitude of the daily average consumption amount a n of each continuous consumption section as g; the predicted daily consumption amount of the user is set to the maximum value of the daily consumption amount of each consumption section in the stable period, wherein the stable period is a period consisting of consumption sections with the amplitude of the daily consumption amount being less than or equal to g compared with the daily consumption amount of the adjacent consumption sections; taking the maximum value of the daily average consumption amount of other consumption sections except the stable period as the deviation daily average consumption amount of the user, wherein the other consumption sections except the stable period refer to consumption sections with the amplitude of the daily average consumption amount being larger than g compared with the daily average consumption amount of the adjacent consumption sections; and calculating the average value by utilizing the predicted average daily consumption amount and the deviation average daily consumption amount to obtain the real average daily consumption amount.
Optionally, the apparatus further comprises: a detection module for pre-selecting a part of the history data as sample data after acquiring the history data of the user purchasing the specific product; and adjusting the value of the amplitude g by using the sample data so as to optimize the calculation accuracy of the real daily average consumption amount.
To achieve the above object, according to still another aspect of the embodiments of the present invention, there is provided an electronic device.
An electronic device of an embodiment of the present invention includes: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the method for calculating the user repurchase period.
To achieve the above object, according to still another aspect of the embodiments of the present invention, there is provided a computer-readable medium.
A computer readable medium of an embodiment of the present invention has stored thereon a computer program which, when executed by a processor, implements a method of calculating a user repurchase period of an embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: in the embodiment of the invention, based on the user portrait and the user historical purchasing behavior, the price of the product purchased by the user in the same quick-service class in a longer period of time is found to be relatively close by analysis, so that the re-purchase period of the user is calculated by adopting the daily consumption amount data, the calculation deviation problem of the daily consumption amount caused by incomplete product specification data can be omitted, and the calculation mode of the re-purchase period is more fit with an actual scene; the invention can cover various consumer products, such as daily-use department products of milk powder, paper diapers, rice and flour coarse cereals and the like, has wide application prospect, has guiding significance on the sales of consumer products, is applied to the actual business of electronic commerce, can make intelligent guidance and prompt for users, and improves the conversion rate; by utilizing historical data such as product amount information, order time information, receiving time information, purchase quantity information, product unit price information and the like of the user, the historical purchasing behavior of the user can be accurately and effectively analyzed; the historical data is cleaned before the real-day consumption amount of the user is calculated by using the repurchase calculation model, so that interference of problem data and abnormal data can be eliminated, and the calculation efficiency is improved; the daily average consumption amount is calculated respectively by dividing the daily average consumption amount into a stable period and a non-stable period, so that the real daily average consumption amount of a user can be calculated more accurately according to normal data and deviation data; in the embodiment of the invention, the selected part of historical data is used as sample data to be used for parameter adjustment of the repurchase calculation model, so that the accuracy of the calculation result of the repurchase calculation model can be ensured to be optimal, and the conversion rate of the crowd in the purchase period can be improved.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of a method of calculating a user's repurchase period according to an embodiment of the invention;
FIG. 2 is a schematic diagram of the main logic of a method of calculating a user's repurchase period according to an embodiment of the invention;
FIG. 3 is a schematic diagram of the major modules of an apparatus for calculating a user's repurchase period according to an embodiment of the present invention;
FIG. 4 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
fig. 5 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Different from 3C and large household appliances, the user has strong periodicity on the purchase of the quick-service products, meanwhile, the income situation of most users does not have obvious change in a longer period, and the products under the same quick-service products purchased by the user are almost at the same price, so that the quick-service product repurchase calculation model is built aiming at the characteristics of the quick-service products in the embodiment of the invention, and the calculation of the repurchase period of the quick-service products of the user is accurately realized.
Fig. 1 is a method for calculating a user repurchase period according to an embodiment of the present invention, and as shown in fig. 1, the method for calculating a user repurchase period according to an embodiment of the present invention mainly includes the following steps:
Step S101: historical data of a user purchasing a particular product is obtained. In the embodiment of the present invention, the history data may include, but is not limited to, at least one of the following information: the user purchases product amount information, order time information, receipt time information, purchase quantity information, and product unit price information.
In addition, the method for calculating the repurchase period according to the embodiment of the invention can further comprise the following steps: and cleaning the historical data, including removing the user data which does not meet the preset calculation conditions based on the user image, perfecting the missing values in the historical data and filtering the abnormal data.
After the user history data is acquired in step S101, calculation is started from step S102.
Step S102: and calculating the real-day consumption amount of the user according to the historical data. In the embodiment of the invention, calculating the real-day average consumption amount of the user by using the repurchase calculation model comprises the following steps: taking the time interval between adjacent purchase days of the user as a consumption section, setting the daily average consumption amount of the user in the consumption section as a n, and setting the amplitude of the daily average consumption amount a n of each continuous consumption section as g; the predicted daily consumption amount of the user is set to the maximum value of the daily consumption amount of each consumption section in the stable period, wherein the stable period is a period consisting of consumption sections with the amplitude of the daily consumption amount being less than or equal to g compared with the daily consumption amount of the adjacent consumption sections; taking the maximum value of the daily average consumption amount of other consumption sections except the stable period as the deviation daily average consumption amount of the user, wherein the other consumption sections except the stable period refer to consumption sections with the amplitude of the daily average consumption amount being larger than g compared with the daily average consumption amount of the adjacent consumption sections; and calculating the average value by utilizing the predicted average daily consumption amount and the deviation average daily consumption amount to obtain the real average daily consumption amount.
Step S103: and calculating the repurchase period of the user for the product according to the real daily average consumption amount. In the embodiment of the invention, the formula for calculating the repurchase period in the repurchase calculation model can be as follows: re-purchase period = last purchase period + (last purchase total/real day all spent).
In addition, in order to improve accuracy of calculating the user repurchase period, after acquiring the historical data of the user purchasing the specific product and before calculating the real average daily consumption amount, the method for calculating the user repurchase period according to the embodiment of the invention further may include: and pre-selecting part of historical data as sample data, and then adjusting the value of the amplitude g by using the sample data to optimize the calculation accuracy of the real daily average consumption amount.
In summary, in the embodiment of the present invention, based on the user portrait and the historical purchasing behavior, the products purchased by the same user in a longer period of time under the same quick-service category are found to have similar price. Therefore, the daily average consumption amount of the user can be approximately equal to the daily average consumption amount of the user, and the problem that the daily average consumption amount of the user cannot be accurately measured due to incomplete product specification data of third-party merchants is avoided. In the embodiment of the invention, the real daily average consumption amount is obtained based on the daily average consumption amounts of a plurality of consumption sections of a user, and the number series are circularly iterated, and the floating range of the value of the repeated purchase calculation model parameter is determined by measuring the GMV pull-up rate and the conversion rate in commercial operation.
The user representation is generally labeled (for example, labeling the person as a house man, a housewife, etc.) by using basic attributes (age, sex, region), purchasing ability, behavior characteristics, interests, psychological characteristics, social networks, etc. of the existing user. In the invention, the crowd which is obviously not fit with the category is excluded by using the user image, so that the prediction accuracy is improved.
In the repurchase calculation model of the embodiment of the invention, the calculation of the repurchase period is realized based on the following assumption and calculation formula.
Model assumptions:
1. products purchased by normal users in the same quick-service class in a longer period of time have similar price;
2. the daily consumption products of normal users are stable in quantity, and large fluctuation cannot occur;
3. the normal user can store goods twice or more continuously, which is a small probability event (namely, the situation that daily average consumption is obviously increased caused by storing goods twice continuously is a small probability event);
4. The stocking behavior refers to a situation in which the amount purchased in a shorter period of time is higher than the amount normally consumed, causing a sudden increase in daily consumption during that period.
The calculation formula is as follows:
Assuming that a user purchases diapers of X1 and X2 … … Xn on days D1 and D2 … … Dn, respectively, there is a consumption period (as described above, the time interval between the adjacent purchase days of the user is taken as one consumption period), and the daily consumption amount a n is equal to the total consumption amount a n:
let the amplitude of the average daily consumption amount of each continuous consumption segment be g, there are:
Then the predicted average daily consumption amount E for this user is as follows:
wherein 1 < = i m < = n, if Then/>And is also provided with
In the above calculation formula of the predicted daily average consumption amount E, the period in which the stable period is taken (i.e., the period consisting of consumption segments with the amplitude of the daily average consumption amount in the adjacent consumption segments being less than or equal to g, where g may be taken according to the accuracy requirement of actual calculation, for example, 15%) is represented, and a plurality of continuous consumption segments, such as [ a 1,a2,a3],[a10,a11 ] … …, take the average daily consumption amount of each consumption segment as the daily average consumption amount of the consumption segment, and finally take the maximum value of the daily average consumption amounts of all the consumption segments in the stable period as the predicted daily average consumption amount of the user.
In addition, if 15.ltoreq.D n-Dn-1.ltoreq.30, for a n that is not in the stationary phase with an amplitude g of 15%, the calculation formula of the average consumption amount M of the deviation day is as follows:
M=max { a n-m.....an }, where M is an integer of 0 or more
The formula indicates that the maximum value of the average daily consumption amount is not found in the calculation formula of E, and the number of days D n-Dn-1 of the interval between the consumption segments defining the average daily consumption amount a n is 15 or more and 30 or less when calculated.
Using the two formulas, calculating the real-day consumption amount A of the user as follows:
A＝Average{E,M}
The total amount of the last purchased product P of the user is marked as X, the purchase date is marked as Dl, the predicted value of the next purchased date of the user is D n, and the calculation formula of the re-purchase period is as follows:
FIG. 2 is a schematic diagram of the main logic of a method of calculating a user's repurchase period according to an embodiment of the invention. The following describes in detail the main implementation logic of the method for calculating the user repurchase period according to the embodiment of the present invention with reference to fig. 2.
1. Data cleaning:
historical data related to the user, such as order form data of historical purchases, including purchase amount, time of placement, time of receipt, purchase quantity, and unit price of the commodity, is extracted.
The processing and refinement of the data missing values is weighted, for example, with the average of the user's historical data or the data of the last 3 months.
Because the enterprise account number and the risk account number influence the accuracy of the calculation result of the repurchase calculation model, the embodiment of the invention can be used for filtering abnormal user accounts related to the enterprise account number, the risk account number and the like by combining the user information data and the wind control data of the electronic commerce platform in consideration of the fact that most of the acting objects of the embodiment of the invention are mass consumers.
And outputting the cleaned user order data.
2. Calculating the repurchase period of the user by using the repurchase calculation model:
and carrying in an algorithm according to the input user order data.
Outputting the user, the product and the next purchase time.
3. Parameter debugging of the purchased computing model:
And (3) carrying out AB test on the calculation result of the repurchase calculation model in the step (2) so as to verify the calculation result. In the embodiment of the invention, the version A is the accuracy of the calculated result of the re-purchase calculation model of the embodiment of the invention, and the version B can be the date of the next purchase predicted by using the average value of the purchase interval days of the user. Tests prove that the accuracy of the A version is 31.6 percent (i.e. the predicted date deviates from the actual date by 3 days), and the accuracy of the B version is 9.7 percent (i.e. the predicted date deviates from the actual date by more than 3 days).
In the embodiment of the invention, the parameters of the outsourcing calculation model can be adjusted based on the accuracy of the calculation result of the outsourcing calculation model. Through loop iteration, parameters of the purchased calculation model are adjusted, and the consumption amount amplitude parameter g on the days of continuous intervals is mainly adjusted, so that the output calculation result of the model is optimal.
4. Automation task:
In the embodiment of the invention, based on the needs of businesses, the repurchase calculation model of the embodiment of the invention can be applied to other business systems, namely, by developing a business system interface, other business systems are in butt joint with the repurchase calculation model, the underlying user data is analyzed and predicted, the repurchase period of the user is obtained, and the obtained repurchase period is output to the business systems, so that the basis is provided for the subsequent decision of each business system.
Specifically, the scheme for calculating the repurchase period by using the repurchase calculation model can help an e-commerce platform to accurately calculate the daily average consumption amount of the consumer goods rapidly, further accurately predict the purchase time of the user, and improve the user experience by friendly touch of a target user, so that the user feels humanized of the e-commerce platform, and the effect of increasing the conversion rate and GMV is achieved. According to experimental data, the conversion rate of the repurchase calculation model for the crowd in the purchasing period is about 3 times of the conversion rate of the non-purchasing period. Specific interfacing into a commercial system may include, but is not limited to, the following:
(1) According to the predicted purchasing time of the user, consumer product information which needs to be supplemented by the user is pushed periodically, one-key purchasing is completed directly through the touch channel, and the ordering efficiency of the user is improved;
(2) Optimizing the ordering of recommended products, increasing the priority of consumer product which needs to be supplemented recently by a user, and improving the product selecting efficiency of the user;
(3) And (3) predicting sales of the consumer product, wherein the sales prediction accuracy is improved by calculating the consumption period as a factor for predicting the sales of the consumer product in a future period of time, so as to guide inventory, pricing and the like.
According to the technical scheme for calculating the user re-purchase period, according to the technical scheme, based on the user portrait and the user historical purchasing behavior, the price of the product purchased by the user in the same quick-service product class in a longer period of time is found to be relatively close by analysis, so that the re-purchase period of the user is calculated by adopting daily consumption amount data, the calculation deviation problem of daily consumption amount caused by incomplete product specification data can be omitted, and the calculation mode of the re-purchase period is more fit with an actual scene; the invention can cover various consumer products, such as daily-use department products of milk powder, paper diapers, rice and flour coarse cereals and the like, has wide application prospect, has guiding significance on the sales of consumer products, is applied to the actual business of electronic commerce, can make intelligent guidance and prompt for users, and improves the conversion rate; by utilizing historical data such as product amount information, order time information, receiving time information, purchase quantity information, product unit price information and the like of the user, the historical purchasing behavior of the user can be accurately and effectively analyzed; the historical data is cleaned before the real-day consumption amount of the user is calculated by using the repurchase calculation model, so that interference of problem data and abnormal data can be eliminated, and the calculation efficiency is improved; the daily average consumption amount is calculated respectively by dividing the daily average consumption amount into a stable period and a non-stable period, so that the real daily average consumption amount of a user can be calculated more accurately according to normal data and deviation data; in the embodiment of the invention, the selected part of historical data is used as sample data to be used for parameter adjustment of the repurchase calculation model, so that the accuracy of the calculation result of the repurchase calculation model can be ensured to be optimal, and the conversion rate of the crowd in the purchase period can be improved.
Fig. 3 is a schematic diagram of main modules of an apparatus for calculating a user repurchase period according to an embodiment of the present invention.
The device 300 for calculating the user repurchase period according to the embodiment of the invention mainly comprises the following modules: an acquisition module 301, a first calculation module 302, a second calculation module 303.
Wherein, the obtaining module 301 is configured to obtain historical data of a user purchasing a specific product; the first calculating module 302 is configured to calculate a real-day consumption amount of the user according to the historical data; the second calculating module 303 is configured to calculate a repurchase period of the user for the product according to the real average daily consumption amount.
Wherein the history data includes at least one of the following information: the user purchases product amount information, order time information, receipt time information, purchase quantity information, and product unit price information.
In the embodiment of the present invention, the obtaining module 301 may further be configured to: before the real-day consumption amount of the user is calculated according to the historical data, the historical data is cleaned, and the method comprises the steps of removing the user data which does not meet preset calculation conditions based on user images, processing missing values in the historical data and filtering abnormal data.
The first computing module 302 may also be configured to: taking the time interval between adjacent purchase days of the user as a consumption section, setting the daily average consumption amount of the user in the consumption section as a n, and setting the amplitude of the daily average consumption amount a n of each continuous consumption section as g; the predicted daily consumption amount of the user is set to the maximum value of the daily consumption amount of each consumption section in the stable period, wherein the stable period is a period consisting of consumption sections with the amplitude of the daily consumption amount being less than or equal to g compared with the daily consumption amount of the adjacent consumption sections; taking the maximum value of the daily average consumption amount of other consumption sections except the stable period as the deviation daily average consumption amount of the user, wherein the other consumption sections except the stable period refer to consumption sections with the amplitude of the daily average consumption amount being larger than g compared with the daily average consumption amount of the adjacent consumption sections; and calculating the average value by using the predicted daily average consumption amount and the deviation daily average consumption amount to obtain the real daily average consumption amount.
Furthermore, the apparatus 300 may further comprise: a detection module (not shown in the figure) for, after acquiring the history data of the user purchasing the specific product, pre-selecting a part of the history data as sample data; and adjusting the value of the amplitude g by using the sample data so as to optimize the calculation accuracy of the real daily average consumption amount.
As can be seen from the above description, in the embodiment of the present invention, based on the user portrait and the user historical purchasing behavior, the price of the product purchased by the user in the same quick-service product class in a longer period of time is found to be relatively close by analysis, so that the re-purchase period of the user is calculated by adopting the daily consumption amount data, and thus the calculation deviation problem of the daily consumption amount caused by the incomplete product specification data can be omitted, and the calculation mode of the re-purchase period is more fit with the actual scene; the invention can cover various consumer products, such as daily-use department products of milk powder, paper diapers, rice and flour coarse cereals and the like, has wide application prospect, has guiding significance on the sales of consumer products, is applied to the actual business of electronic commerce, can make intelligent guidance and prompt for users, and improves the conversion rate; by utilizing historical data such as product amount information, order time information, receiving time information, purchase quantity information, product unit price information and the like of the user, the historical purchasing behavior of the user can be accurately and effectively analyzed; the historical data is cleaned before the real-day consumption amount of the user is calculated by using the repurchase calculation model, so that interference of problem data and abnormal data can be eliminated, and the calculation efficiency is improved; the daily average consumption amount is calculated respectively by dividing the daily average consumption amount into a stable period and a non-stable period, so that the real daily average consumption amount of a user can be calculated more accurately according to normal data and deviation data; in the embodiment of the invention, the selected part of historical data is used as sample data to be used for parameter adjustment of the repurchase calculation model, so that the accuracy of the calculation result of the repurchase calculation model can be ensured to be optimal, and the conversion rate of the crowd in the purchase period can be improved.
Fig. 4 illustrates an exemplary system architecture 400 to which the computing user repurchase period method or computing user repurchase period device of embodiments of the invention may be applied.
As shown in fig. 4, the system architecture 400 may include terminal devices 401, 402, 403, a network 404, and a server 405. The network 404 is used as a medium to provide communication links between the terminal devices 401, 402, 403 and the server 405. The network 404 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 405 via the network 404 using the terminal devices 401, 402, 403 to receive or send messages or the like. Various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only) may be installed on the terminal devices 401, 402, 403.
The terminal devices 401, 402, 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 405 may be a server providing various services, such as a background management server (by way of example only) providing support for shopping-type websites browsed by users using the terminal devices 401, 402, 403. The background management server may analyze and process the received data such as the product information query request, and feedback the processing result (e.g., the target push information, the product information—only an example) to the terminal device.
It should be noted that, the method for calculating the user repurchase period provided in the embodiment of the present invention is generally executed by the server 405, and accordingly, the device for calculating the user repurchase period is generally disposed in the server 405.
It should be understood that the number of terminal devices, networks and servers in fig. 4 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 5, there is illustrated a schematic diagram of a computer system 500 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 5 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 5, the computer system 500 includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU501, ROM 502, and RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following components are connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, and the like; an output portion 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as needed so that a computer program read therefrom is mounted into the storage section 508 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 509, and/or installed from the removable media 511. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 501.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes an acquisition module, a first calculation module, and a second calculation module. The names of these modules do not constitute a limitation on the module itself in some cases, and for example, the acquisition module may also be described as "a module for acquiring history data of a user purchasing a specific product".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include: acquiring historical data of a user purchasing a specific product; calculating the real-day consumption amount of the user according to the historical data; and calculating the repurchase period of the user for the product according to the real daily average consumption amount.
According to the technical scheme of the embodiment of the invention, based on the user portrait and the historical purchasing behavior of the user, the price of the product purchased by the user in the same quick-service product class in a longer period of time is found to be relatively close by analysis, so that the re-purchase period of the user is calculated by adopting the daily consumption amount data, the calculation deviation problem of the daily consumption amount caused by incomplete product specification data can be ignored, and the calculation mode of the re-purchase period is more fit with an actual scene; the invention can cover various consumer products, such as daily-use department products of milk powder, paper diapers, rice and flour coarse cereals and the like, has wide application prospect, has guiding significance on the sales of consumer products, is applied to the actual business of electronic commerce, can make intelligent guidance and prompt for users, and improves the conversion rate; by utilizing historical data such as product amount information, order time information, receiving time information, purchase quantity information, product unit price information and the like of the user, the historical purchasing behavior of the user can be accurately and effectively analyzed; the historical data is cleaned before the real-day consumption amount of the user is calculated by using the repurchase calculation model, so that interference of problem data and abnormal data can be eliminated, and the calculation efficiency is improved; the daily average consumption amount is calculated respectively by dividing the daily average consumption amount into a stable period and a non-stable period, so that the real daily average consumption amount of a user can be calculated more accurately according to normal data and deviation data; in the embodiment of the invention, the selected part of historical data is used as sample data to be used for parameter adjustment of the repurchase calculation model, so that the accuracy of the calculation result of the repurchase calculation model can be ensured to be optimal, and the conversion rate of the crowd in the purchase period can be improved.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of calculating a user's repurchase period, comprising:
Acquiring historical data of a user purchasing a specific product;
According to the historical data, calculating the real daily average consumption amount of the user, wherein the method comprises the following steps: taking the time interval between adjacent purchase days of the user as a consumption section, setting the daily average consumption amount of the user in the consumption section as a n, and setting the amplitude of the daily average consumption amount a n of each continuous consumption section as g; the predicted daily consumption amount of the user is set to the maximum value of the daily consumption amount of each consumption section in the stable period, wherein the stable period is a period consisting of consumption sections with the amplitude of the daily consumption amount being less than or equal to g compared with the daily consumption amount of the adjacent consumption sections; taking the maximum value of the daily average consumption amount of other consumption sections except the stable period as the deviation daily average consumption amount of the user, wherein the other consumption sections except the stable period refer to consumption sections with the amplitude of the daily average consumption amount being larger than g compared with the daily average consumption amount of the adjacent consumption sections; calculating the average value by utilizing the predicted average daily consumption amount and the deviation average daily consumption amount to obtain the real average daily consumption amount;
And calculating the re-purchase period of the user for the product according to the real average daily consumption amount, wherein the re-purchase period is the sum of the last purchase period and the quotient of the total last purchase amount divided by the real average daily consumption amount.
2. The method of claim 1, wherein the historical data includes at least one of the following information: the user purchases product amount information, order time information, receipt time information, purchase quantity information, and product unit price information.
3. The method of claim 1, wherein prior to calculating the real-day average consumption amount of the user based on the historical data, the method further comprises: and cleaning the historical data, including removing the user data which does not meet the preset calculation conditions based on the user image, processing the missing values in the historical data and filtering the abnormal data.
4. The method of claim 1, wherein after obtaining historical data for a user purchasing a particular product, the method further comprises:
pre-selecting a part of history data as sample data;
and adjusting the value of the amplitude g by using the sample data so as to optimize the calculation accuracy of the real daily average consumption amount.
5. An apparatus for calculating a period of user repurchase, comprising:
The acquisition module is used for acquiring historical data of a user purchasing a specific product;
The first calculation module is used for calculating the real average daily consumption amount of the user according to the historical data, and comprises the following steps: taking the time interval between adjacent purchase days of the user as a consumption section, setting the daily average consumption amount of the user in the consumption section as a n, and setting the amplitude of the daily average consumption amount a n of each continuous consumption section as g; the predicted daily consumption amount of the user is set to the maximum value of the daily consumption amount of each consumption section in the stable period, wherein the stable period is a period consisting of consumption sections with the amplitude of the daily consumption amount being less than or equal to g compared with the daily consumption amount of the adjacent consumption sections; taking the maximum value of the daily average consumption amount of other consumption sections except the stable period as the deviation daily average consumption amount of the user, wherein the other consumption sections except the stable period refer to consumption sections with the amplitude of the daily average consumption amount being larger than g compared with the daily average consumption amount of the adjacent consumption sections; calculating the average value by utilizing the predicted average daily consumption amount and the deviation average daily consumption amount to obtain the real average daily consumption amount;
And the second calculation module is used for calculating the repurchase period of the user for the product according to the real average daily consumption amount, wherein the repurchase period is the sum of the last purchase period and the quotient of the total last purchase amount divided by the real average daily consumption amount.
6. The apparatus of claim 5, wherein the historical data comprises at least one of the following information: the user purchases product amount information, order time information, receipt time information, purchase quantity information, and product unit price information.
7. The apparatus of claim 5, wherein the acquisition module is further configured to: before the real-day consumption amount of the user is calculated according to the historical data, the historical data is cleaned, and the method comprises the steps of removing the user data which does not meet preset calculation conditions based on user images, processing missing values in the historical data and filtering abnormal data.
8. The apparatus of claim 5, wherein the apparatus further comprises: a detection module for pre-selecting a part of the history data as sample data after acquiring the history data of the user purchasing the specific product; and adjusting the value of the amplitude g by using the sample data so as to optimize the calculation accuracy of the real daily average consumption amount.
9. An electronic device, comprising:
One or more processors;
Storage means for storing one or more programs,
When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.
10. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810105295.7A CN110135871B (en) | 2018-02-02 | 2018-02-02 | Method and device for calculating user repurchase period |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810105295.7A CN110135871B (en) | 2018-02-02 | 2018-02-02 | Method and device for calculating user repurchase period |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110135871A CN110135871A (en) | 2019-08-16 |
| CN110135871B true CN110135871B (en) | 2024-06-18 |
Family
ID=67567124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810105295.7A Active CN110135871B (en) | 2018-02-02 | 2018-02-02 | Method and device for calculating user repurchase period |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135871B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110689402A (en) * | 2019-09-04 | 2020-01-14 | 北京三快在线科技有限公司 | Method and device for recommending merchants, electronic equipment and readable storage medium |
| 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 |
| CN112396380A (en) * | 2020-11-26 | 2021-02-23 | 北京沃东天骏信息技术有限公司 | Method and device for regularly sending articles, computer equipment and storage medium |
| 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 (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09231264A (en) * | 1996-02-23 | 1997-09-05 | Hitachi Ltd | On-line shopping support method and system |
| JP2013003834A (en) * | 2011-06-16 | 2013-01-07 | Hitachi Consumer Electronics Co Ltd | Merchandise purchase recommendation device |
| 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 |
-
2018
- 2018-02-02 CN CN201810105295.7A patent/CN110135871B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110135871A (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110135871B (en) | Method and device for calculating user repurchase period | |
| US10824533B2 (en) | Optimization of power and computational density of a data center | |
| CN107274209A (en) | The method and apparatus for predicting advertising campaign sales data | |
| CN110135878B (en) | Method and device for determining sales price | |
| CN110109901B (en) | Method and device for screening target object | |
| CN109961299A (en) | The method and apparatus of data analysis | |
| CN110866625A (en) | Promotion index information generation method and device | |
| US20150161635A1 (en) | Dynamic price elasticity in unstructured marketplace data | |
| CN112749323B (en) | Method and device for constructing user portrait | |
| US11669762B2 (en) | Apparatus and method for forecasted performance level adjustment and modification | |
| CN110827102A (en) | Method and device for adjusting goods price ratio | |
| CN110490682B (en) | Method and device for analyzing commodity attributes | |
| CN109872211A (en) | A kind of method and apparatus of object recommendation | |
| CN110796461B (en) | Method and device for evaluating correctness of selection | |
| CN112990951B (en) | Method and device for determining access quantity of item | |
| JP2017010402A (en) | Prediction device, prediction method and prediction program | |
| CN112418898A (en) | Article demand data analysis method and device based on multi-time window fusion | |
| JP2020154782A (en) | Proposal device, proposal method, and proposal program | |
| WO2018213058A1 (en) | System and method for managing limit orders | |
| CN113743972B (en) | Method and device for generating article information | |
| CN108876421A (en) | A kind of method and system for predicting commodity dynamic sales volume | |
| CN113361834B (en) | Method and device for determining distribution amount | |
| EP3968256A1 (en) | Scheduling displays on a terminal device | |
| US20220164405A1 (en) | Intelligent machine learning content selection platform | |
| Luo et al. | A technical note on the dynamic nonstationary inventory-pricing control model with lost sale |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |