CN115760223B - Clothing electronic commerce intelligent monitoring analysis system based on data analysis - Google Patents
Clothing electronic commerce intelligent monitoring analysis system based on data analysis Download PDFInfo
- Publication number
- CN115760223B CN115760223B CN202211468799.8A CN202211468799A CN115760223B CN 115760223 B CN115760223 B CN 115760223B CN 202211468799 A CN202211468799 A CN 202211468799A CN 115760223 B CN115760223 B CN 115760223B
- Authority
- CN
- China
- Prior art keywords
- target
- customer
- clothing
- clothes
- sales
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 238000007405 data analysis Methods 0.000 title claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims description 27
- 235000000100 Hibiscus rosa sinensis Nutrition 0.000 claims description 21
- 240000008254 Rosa chinensis Species 0.000 claims description 21
- 235000000664 Rosa chinensis Nutrition 0.000 claims description 21
- 235000016785 Rosa della China Nutrition 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 10
- 238000012854 evaluation process Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 description 8
- 238000012797 qualification Methods 0.000 description 7
- 238000007792 addition Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003334 potential effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of clothing electronic business monitoring and analysis, and particularly discloses a clothing electronic business intelligent monitoring and analysis system based on data analysis.
Description
Technical Field
The invention belongs to the technical field of clothing electronic commerce monitoring and analysis, and relates to an intelligent clothing electronic commerce monitoring and analysis system based on data analysis.
Technical Field
In recent years, with the rapid development of economy and the rapid improvement of science level, the clothing electronics business industry is growing, and the fashion of purchasing female clothing by electronics business is gradually accepted by the masses, but in order to ensure the safety of female clothing of electronics business, the monitoring and analysis of female clothing electronics business goods are also becoming important because consumers often have goods return problems.
At present, the female clothing electronic commerce goods monitoring is mainly performed according to sales volume of female clothing electronic commerce, and the female clothing electronic commerce goods returning information is not combined for analysis, and obviously, the female clothing electronic commerce monitoring analysis has the following defects: 1. at present, the demand that each customer possibly generates goods returned is not analyzed, the demand of the subsequent goods supplement of the store cannot be guaranteed to a certain extent, the phenomenon that overstocked clothes exist in the store due to excessive subsequent goods supplement of the store is easily caused, and then normal operation of the subsequent store cannot be guaranteed.
2. At present, historical purchase information of each customer is not analyzed, so that target clothing return probability coefficients corresponding to each customer cannot be obtained, return pre-judging capacity of a store is reduced to a certain extent, adverse effects on the store are easily generated, improvement of sales volume level of the store is not facilitated, potential effects are easily caused, and after-sales processing capacity of the store is reduced.
Disclosure of Invention
In view of the problems of the prior art, the invention provides a clothing electronic commerce intelligent monitoring and analyzing system based on data analysis, which is used for solving the technical problems.
In order to achieve the above and other objects, the present invention adopts the following technical scheme: the invention provides a clothing electronic commerce intelligent monitoring and analyzing system based on data analysis, which comprises a store information acquisition module, a customer purchase information acquisition module, a customer basic information acquisition module, a customer history information acquisition module, a customer return probability evaluation module, a store clothing sales amount estimation module, a warehouse replenishment analysis module and an electronic commerce information base.
The store information acquisition module is used for acquiring the stock quantity corresponding to the target clothing of the target electronic store.
The customer purchase information acquisition module is used for acquiring the purchase information of each customer in the target electronic shop at the current time.
The customer basic information acquisition module is used for extracting basic information corresponding to each customer from the electronic commerce information base, wherein the basic information comprises height and weight.
The customer history information acquisition module is used for extracting the history purchase information corresponding to each customer in the target electronic store from the electronic commerce information base.
The customer return probability evaluation module is used for evaluating and obtaining target clothing return probability coefficients corresponding to all customers according to the purchase information and the historical purchase information of the customers in the target electronic store at the present time.
The store clothing sales volume estimation module is used for extracting historical sales information of the target electronic store from the electronic store information base, and further analyzing and obtaining target clothing pre-sales volume corresponding to the current month of the target electronic store.
And the warehouse replenishment analysis module is used for comprehensively judging and analyzing the replenishment demands of the target electric shops according to the target clothing return probability coefficient corresponding to each customer, the target clothing pre-sales volume corresponding to the target electric shops and the stock volume corresponding to the target clothing.
In the preferred technical scheme of the application, the purchasing information of each customer in the target electronic shop at the present time comprises the number of the purchased target clothes, the corresponding size of the purchased target clothes, the corresponding price of the target clothes and the corresponding style of the target clothes.
In a preferred technical solution of the present application, the historical purchase information includes a type of style of the historical purchase clothing and a size of the historical purchase clothing.
In the preferred technical scheme of the application, the target clothing return probability coefficient corresponding to each customer is obtained through evaluation, and the specific evaluation process is as follows: a1, acquiring purchasing information and historical purchasing information of each customer at the current time at a target electronic store, further acquiring the target clothing size and style of each customer purchased at the current time at the target electronic store, and simultaneously acquiring the historical purchasing clothing style and size of each customer.
A2, comparing the size of the target clothes corresponding to the current target electric shop with the size of the historic purchased clothes, if the size of the target clothes purchased by the current target electric shop is inconsistent with the size of the historic purchased clothes, judging that the target clothes purchased by the current target electric shop is a pre-returned clothes, further judging that the return estimated coefficient alpha' of the customer to the clothes is a non-returned clothes, otherwise, judging that the clothes purchased by the current target electric shop is a non-returned clothes, and obtaining the primary size return estimated coefficient alpha corresponding to the target clothes purchased by the current target electric shop s ，α s Take the value of alpha 'or alpha', and alpha>α', where s is denoted as the number corresponding to each customer, s=1, 2.
A3, purchasing information of each marked customer according to the history of the target electronic store shop extracted from the electronic store information base, and further obtaining the height, weight and size of each marked customer purchased by the history of the target electronic store shopComparing the height and weight of each marked customer with the height and weight of each customer, comparing the height and weight of each customer with the weight grade corresponding to each height and weight stored in the database to obtain the weight grade corresponding to each customer, simultaneously comparing the height and weight of each marked customer with the weight grade corresponding to each height and weight stored in the database to obtain the weight grade corresponding to each marked customer, comparing the weight grade corresponding to each customer with the weight grade corresponding to each marked customer, judging that the height and weight of each customer belong to the same grade with the height and weight of each marked customer if the weight grade corresponding to a certain customer is identical with the weight grade corresponding to a certain marked customer, obtaining the number corresponding to each marked customer with the same level of height and weight of each customer, marking each marked customer with the same level of height and weight of each customer as each reference customer, obtaining the qualification rate of the size corresponding to each reference customer, comparing and screening the qualification rate of the size corresponding to each reference customer, screening the sizes with the front qualification rate, comparing the size with the target clothing size corresponding to the current target electric store of each customer, and obtaining the size return evaluation coefficient beta corresponding to the target clothing of each customer in the current target electric store according to the analysis mode of the preliminary return evaluation coefficient corresponding to the target clothing of each customer in the current target electric store s 。
In the preferred technical scheme of the application, the target clothing return probability coefficient corresponding to each customer is obtained through evaluation, and the specific evaluation process is as follows: b1, comparing the style of the target clothes corresponding to the current target electric shop with the style of the historic purchasing clothes, if the style of the target clothes corresponding to the current target electric shop is not consistent with the style of the historic purchasing clothes, determining that the target clothes purchased by the current target electric shop is the required return clothes, further determining that the return estimated index x' of the customer to the clothes, otherwise, determining that the target clothes purchased by the current target electric shop is the unnecessary return clothes, and determining that the customer is the target return clothesThe return estimated index χ' of the target clothing is obtained to obtain the size return analysis index χ corresponding to the target clothing purchased by each customer at the target electronic shop at the current time s The value of χ is χ ' or χ ", and χ ' is '>χ″。
B2, further utilize the formulaCalculating to obtain target clothing return probability coefficient delta corresponding to each customer s Wherein a1 and a2 are respectively expressed as weight factors corresponding to the size and style of the customer, a3 and a4 are respectively expressed as preliminary size return evaluation coefficients and influence factors corresponding to the size return evaluation coefficients, and a1>a2。
In the preferred technical scheme of the application, the historical sales information of the target electronic shop comprises target clothing sales amount of each month in each past year.
In the preferred technical scheme of the application, the analysis obtains the target clothing pre-sales corresponding to the current month of the target electronic shop, and the specific analysis process is as follows: c1, extracting target clothing sales amounts of each month of each year of the target electronic store according to historical sales information of the target electronic store, substituting the target clothing sales amounts of each month of each year of the target electronic store into a clothing sales trend model diagram to obtain sales trends corresponding to the target clothing sales amounts of each month of each year of the target electronic store, and further utilizing a calculation formulaCalculating sales increase rate epsilon corresponding to each year of the target electric store i Where i is denoted as the number corresponding to each year, i=1, 2,.. m is the number corresponding to each month, m=1, 2,.. im Expressed as the target sales of clothing corresponding to the mth month in the ith year,/-th year>Expressed as target clothing sales corresponding to the m-1 th month in the ith year, and m expressed as the total number of months.
C2, further obtaining the corresponding China rose of the target garment from the electronic commerce information base according to the current China rose, comparing the date of the China rose corresponding to the current China rose with the corresponding China rose of the target garment, judging that the current China rose is the China rose if the date of the China rose corresponding to the current China rose is consistent with the comparison of the China rose corresponding to the target garment, and further obtaining the sales growth coefficient corresponding to the target garmentOtherwise, judging that the current month is the off-season month, and further obtaining a sales growth coefficient corresponding to the target clothing>Thereby obtaining sales growth evaluation coefficient corresponding to the target clothing> The value is +.>Or->And->
C3, extracting target clothing sales corresponding to the current month of the set year from target clothing sales of each month of each past year of the target electronic store, and further according to an analysis formulaCalculating to obtain target clothing pre-sales quantity phi corresponding to the current month of the target electric shop, wherein XS is expressed as target clothing sales quantity corresponding to the current month of the set year, j is expressed as total number of the past year, and e is expressed as a natural constant.
In the preferred technical scheme of the application, the comprehensive judgment and analysis target electronic shop is required for replenishment, and the specific judgment process is as follows: r1, comparing the target clothing return probability coefficient corresponding to each customer with the set clothing standard return probability coefficient, if the target clothing return probability coefficient corresponding to a certain customer is greater than or equal to the set clothing standard return probability coefficient, judging the customer as the customer needing to return, counting the total number of the customers needing to return, extracting the number of the target clothing corresponding to the customer needing to return from the purchasing information of each customer on the target electric store shop according to the current time, extracting the number corresponding to each customer needing to return, counting the total number corresponding to the customer needing to return, and calculating the stock quantity corresponding to the target clothing of the target electric store according to the calculation formula M 0 ＝M 1 +M 2 *M 3 Calculating to obtain the estimated stock quantity M of the corresponding target clothing of the target electric shop 0 Wherein M is 1 Representing the corresponding stock quantity of target clothing of a target electronic shop, M 2 Indicated as the total number of customer correspondences in need of return, M 3 Representing the corresponding target number of garments purchased for the customer in need of return.
R2, comparing the estimated stock quantity of the target clothes corresponding to the target electric shop with the target clothes pre-sales quantity corresponding to the current month of the target electric shop, judging that the target electric shop needs to be restocked if the estimated stock quantity of the target clothes corresponding to the target electric shop is larger than or equal to the target clothes pre-sales quantity corresponding to the current month of the target electric shop, and judging that the target electric shop does not need to be restocked if the estimated stock quantity of the target clothes corresponding to the target electric shop is smaller than the target clothes pre-sales quantity corresponding to the current month of the target electric shop.
In a preferred technical scheme of the application, the electronic commerce information base is used for storing the basic information corresponding to the target clothing and the corresponding to each customer, and also used for storing the historical purchasing information of each marked customer of the target electronic shop, the historical sales information, the basic information corresponding to each customer, the historical purchasing information of each customer corresponding to the target electronic shop and the historical purchasing information of each marked customer of the target electronic shop, wherein the historical purchasing information comprises height and weight, size and size acceptance rate.
As described above, the intelligent monitoring and analyzing system for clothing electronic commerce based on data analysis provided by the invention has at least the following beneficial effects: according to the intelligent monitoring and analyzing system for the clothing electronic commerce based on the data analysis, the target clothing return probability coefficient corresponding to each customer is obtained through analyzing each customer buying target clothing in the target electronic commerce, the target clothing pre-sales volume corresponding to the current month of the target electronic commerce is obtained through analysis according to the historical sales information of the target electronic commerce, and then the replenishment demand of the target electronic commerce is comprehensively judged and analyzed according to the stock volume corresponding to the target clothing.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the connection of the modules of the system of the present invention.
Detailed Description
The foregoing is merely illustrative of the principles of the invention, and various modifications, additions and substitutions for those skilled in the art will be apparent to those having ordinary skill in the art without departing from the principles of the invention or from the scope of the invention as defined in the accompanying claims.
Referring to fig. 1, an intelligent monitoring and analyzing system for clothing electronic commerce based on data analysis includes a store information acquisition module, a customer purchase information acquisition module, a customer basic information acquisition module, a customer history information acquisition module, a customer return probability evaluation module, a store clothing sales volume estimation module, a warehouse replenishment analysis module and an electronic commerce information base.
The customer return probability evaluation module is connected with the store information acquisition module, the customer purchase information acquisition module, the customer basic information acquisition module and the customer history information acquisition module, the warehouse replenishment analysis module is connected with the customer return probability evaluation module and the store clothing sales volume estimation module, and the electronic commerce information base is connected with the store information acquisition module, the customer purchase information acquisition module, the customer basic information acquisition module and the customer history information acquisition module.
The store information acquisition module is used for acquiring the stock quantity corresponding to the target clothing of the target electronic store.
The customer purchase information acquisition module is used for acquiring the purchase information of each customer in the target electronic shop at the current time.
As a further optimization of the above scheme, the purchase information of each customer at the current time at the target electronic shop includes the number of purchased target clothes, the size corresponding to the purchased target clothes, the price corresponding to the target clothes and the style type corresponding to the target clothes.
The customer basic information acquisition module is used for extracting basic information corresponding to each customer from the electronic commerce information base, wherein the basic information comprises height and weight.
The customer history information acquisition module is used for extracting the history purchase information corresponding to each customer in the target electronic store from the electronic commerce information base.
As a further optimization of the above, the historical purchase information includes a historical purchase garment style type and a historical purchase garment size.
In one particular embodiment, the style type with the most historic purchased garments is referred to as the historic purchased garment style type, and the size with the most historic purchased garments is referred to as the historic purchased garment size.
The customer return probability evaluation module is used for evaluating and obtaining target clothing return probability coefficients corresponding to all customers according to the purchase information and the historical purchase information of the customers in the target electronic store at the present time.
As a further optimization of the above scheme, the evaluation obtains the target clothing return probability coefficient corresponding to each customer, and the specific evaluation process is as follows: a1, acquiring purchasing information and historical purchasing information of each customer at the current time at a target electronic store, further acquiring the target clothing size and style of each customer purchased at the current time at the target electronic store, and simultaneously acquiring the historical purchasing clothing style and size of each customer.
A2, comparing the size of the target clothes corresponding to the current target electric shop with the size of the historic purchased clothes, if the size of the target clothes purchased by the current target electric shop is inconsistent with the size of the historic purchased clothes, judging that the target clothes purchased by the current target electric shop is a pre-returned clothes, further judging that the return estimated coefficient alpha' of the customer to the clothes is a non-returned clothes, otherwise, judging that the clothes purchased by the current target electric shop is a non-returned clothes, and obtaining the primary size return estimated coefficient alpha corresponding to the target clothes purchased by the current target electric shop s ，α s Take the value of alpha 'or alpha', and alpha>α', where s is denoted as the number corresponding to each customer, s=1, 2.
A3, purchasing information of each marked customer according to the history of the target electronic shop, which is extracted from the electronic commerce information base, so as to obtain the height, weight and size of each marked customer purchased by the history of the target electronic shop, comparing the height and weight of each marked customer with the height and weight of each customer, and storing the height and weight of each customer with a databaseThe weight grade corresponding to the height and the weight of each customer is compared to obtain the weight grade corresponding to each customer, the height and the weight of each marked customer are compared with the weight grade corresponding to each height and the weight stored in a database to obtain the weight grade corresponding to each marked customer, the weight grade corresponding to each customer is compared with the weight grade corresponding to each marked customer, if the weight grade corresponding to a certain customer is matched with the weight grade corresponding to a certain marked customer, the height and the weight of the customer are judged to belong to the same grade, the number corresponding to each marked customer with the height and the weight of each customer belonging to the same grade is obtained, each marked customer with the height and the weight of each customer belonging to the same grade is marked as each reference customer, the qualification rate corresponding to each reference customer is obtained, the qualification rate of the sizes corresponding to each reference customer is compared with each other, the qualification rate of the sizes corresponding to the reference customers are compared with each other, the qualification rate is compared with the target clothing corresponding to the target electric store, the customer's height and the target clothing is analyzed in the target clothing price-backing-down mode corresponding to the target electric store, and the target clothing price-backing-down coefficient is obtained s 。
In a specific embodiment, the top ranking size is selected as the first ranking size.
As a further optimization of the above scheme, the evaluation obtains the target clothing return probability coefficient corresponding to each customer, and the specific evaluation process is as follows: b1, comparing the style of the target clothes corresponding to the current target electric shop with the style of the historic purchasing clothes, if the style of the target clothes corresponding to the current target electric shop is not consistent with the style of the historic purchasing clothes, determining that the target clothes purchased by the current target electric shop is the required return clothes, further estimating the return index χ' of the customer to the clothes, otherwise, determining that the target clothes purchased by the current target electric shop is the return target clothesTo obtain the corresponding size returns analysis index χ of the target clothing when each customer purchases the target clothing at the target electronic shop s The value of χ is χ ' or χ ", and χ ' is '>χ″。
In a specific embodiment, the style specific classification process comprises the steps of extracting title characters corresponding to target clothes corresponding to a target electronic shop, dividing the title characters corresponding to the target clothes into keywords, matching the keywords with keywords corresponding to style types stored in a database, and further obtaining style types corresponding to the target clothes by using a keyword matching formula.
B2, further utilize the formulaCalculating to obtain target clothing return probability coefficient delta corresponding to each customer s Wherein a1 and a2 are respectively expressed as weight factors corresponding to the size and style of the customer, a3 and a4 are respectively expressed as preliminary size return evaluation coefficients and influence factors corresponding to the size return evaluation coefficients, and a1>a2。
The embodiment of the invention guarantees the demand of the subsequent replenishment of the store to a certain extent, avoids the phenomenon that overstocked clothes exist in the store caused by excessive subsequent replenishment of the store, and further guarantees the normal operation of the subsequent store.
According to the method and the device for determining the target clothing return probability coefficient, the historical purchase information of each customer is analyzed to obtain the target clothing return probability coefficient corresponding to each customer, so that the return pre-determination capability of the store is improved to a certain extent, the sales volume level of the store is improved, and the after-sales processing capability of the store is improved.
The store clothing sales volume estimation module is used for extracting historical sales information of the target electronic store from the electronic store information base, and further analyzing and obtaining target clothing pre-sales volume corresponding to the current month of the target electronic store.
As a further optimization of the above solution, the historical sales information of the target electronic shop includes target clothing sales for each month of each year.
As a further optimization of the above scheme, the analysis obtains the target clothing pre-sales corresponding to the current month of the target electronic shop, and the specific analysis process is as follows: c1, extracting target clothing sales amounts of each month of each year of the target electronic store according to historical sales information of the target electronic store, substituting the target clothing sales amounts of each month of each year of the target electronic store into a clothing sales trend model diagram to obtain sales trends corresponding to the target clothing sales amounts of each month of each year of the target electronic store, and further utilizing a calculation formulaCalculating sales increase rate epsilon corresponding to each year of the target electric store i Where i is denoted as the number corresponding to each year, i=1, 2,.. m is the number corresponding to each month, m=1, 2,.. im Expressed as the target sales of clothing corresponding to the mth month in the ith year,/-th year>Expressed as target clothing sales corresponding to the m-1 th month in the ith year, and m expressed as the total number of months.
C2, further obtaining the month of the flourishing season corresponding to the target clothing from the electronic commerce information base according to the month date corresponding to the current month, comparing the month date corresponding to the current month with the month of the flourishing season corresponding to the target clothing, and judging that the current month is the month of the flourishing season if the month date corresponding to the current month is consistent with the month comparison of the flourishing season corresponding to the target clothing, thereby obtaining the sales growth coefficient corresponding to the target clothingOtherwise, judging that the current month is the off-season month, and further obtaining a sales growth coefficient corresponding to the target clothing>Thereby obtaining the sales corresponding to the target clothingIncrease evaluation coefficient-> The value is +.>Or->And->
C3, extracting target clothing sales corresponding to the current month of the set year from target clothing sales of each month of each past year of the target electronic store, and further according to an analysis formulaCalculating to obtain target clothing pre-sales quantity phi corresponding to the current month of the target electric shop, wherein XS is expressed as target clothing sales quantity corresponding to the current month of the set year, j is expressed as total number of the past year, and e is expressed as a natural constant.
In one particular embodiment, the set year is expressed as the previous year corresponding to the current year.
And the warehouse replenishment analysis module is used for comprehensively judging and analyzing the replenishment demands of the target electric shops according to the target clothing return probability coefficient corresponding to each customer, the target clothing pre-sales volume corresponding to the target electric shops and the stock volume corresponding to the target clothing.
As further optimization of the scheme, the comprehensive judgment and analysis target electronic shop is used for replenishing the goods, and the specific judgment process is as follows: r1, comparing the target clothing return probability coefficient corresponding to each customer with the set clothing standard return probability coefficient, and judging that the customer is needed if the target clothing return probability coefficient corresponding to a certain customer is greater than or equal to the set clothing standard return probability coefficientThe method comprises the steps of taking the number of customers needing to be returned, counting the total number of the customers needing to be returned, extracting the number of target clothes corresponding to the purchase of the customers needing to be returned according to the purchase information of each customer at the target electronic store, further extracting the number corresponding to each customer needing to be returned, counting the total number corresponding to the customers needing to be returned, and utilizing a calculation formula M according to the stock quantity corresponding to the target clothes of the target electronic store 0 ＝M 1 +M 2 *M 3 Calculating to obtain the estimated stock quantity M of the corresponding target clothing of the target electric shop 0 Wherein M is 1 Representing the corresponding stock quantity of target clothing of a target electronic shop, M 2 Indicated as the total number of customer correspondences in need of return, M 3 Representing the corresponding target number of garments purchased for the customer in need of return.
R2, comparing the estimated stock quantity of the target clothes corresponding to the target electric shop with the target clothes pre-sales quantity corresponding to the current month of the target electric shop, judging that the target electric shop needs to be restocked if the estimated stock quantity of the target clothes corresponding to the target electric shop is larger than or equal to the target clothes pre-sales quantity corresponding to the current month of the target electric shop, and judging that the target electric shop does not need to be restocked if the estimated stock quantity of the target clothes corresponding to the target electric shop is smaller than the target clothes pre-sales quantity corresponding to the current month of the target electric shop.
As a further optimization of the above solution, the electronic commerce information base is configured to store the basic information corresponding to the target garment and the basic information corresponding to each customer, and further configured to store the historical purchasing information of each target electronic shop, the historical sales information, the basic information corresponding to each customer, the historical purchasing information corresponding to each customer at the target electronic shop, and the historical purchasing information of each target electronic shop, wherein the historical purchasing information includes height and weight, size and size acceptance rate.
The foregoing is merely illustrative and explanatory of the principles of the invention, as various modifications and additions may be made to the specific embodiments described, or similar thereto, by those skilled in the art, without departing from the principles of the invention or beyond the scope of the appended claims.
Claims (8)
1. An intelligent monitoring and analyzing system for clothing electronic commerce based on data analysis is characterized in that: the system comprises a store information acquisition module, a customer purchase information acquisition module, a customer basic information acquisition module, a customer history information acquisition module, a customer return probability evaluation module, a store clothing sales amount estimation module, a warehouse replenishment analysis module and an electronic commerce information base;
the store information acquisition module is used for acquiring the stock quantity corresponding to the target clothing of the target electronic store;
the customer purchase information acquisition module is used for acquiring the purchase information of each customer in the target electronic shop at the present time;
the customer basic information acquisition module is used for extracting basic information corresponding to each customer from the electronic commerce information base, wherein the basic information comprises height and weight;
the customer history information acquisition module is used for extracting the history purchase information corresponding to each customer in the target electronic store from the electronic commerce information base;
the customer return probability evaluation module is used for evaluating and obtaining target clothing return probability coefficients corresponding to all customers according to the purchase information and the historical purchase information of each customer in the target electronic store at the present time;
the store clothing sales volume estimation module is used for extracting historical sales information of a target electronic store from the electronic store information base, and further analyzing and obtaining target clothing pre-sales volume corresponding to the current month of the target electronic store;
the warehouse replenishment analysis module is used for comprehensively judging and analyzing the replenishment demands of the target electric shops according to the target clothing return probability coefficient corresponding to each customer, the target clothing pre-sales volume corresponding to the target electric shops and the stock volume corresponding to the target clothing;
the evaluation is carried out to obtain target clothing return probability coefficients corresponding to all customers, and the specific evaluation process is as follows:
a1, acquiring purchasing information and historical purchasing information of each customer at the current time at a target electronic store, further acquiring the target clothing size and style of each customer purchased at the current time at the target electronic store, and simultaneously acquiring the historical purchasing clothing style and size of each customer;
a2, comparing the size of the target clothes corresponding to the current target electric shop with the size of the historic purchased clothes, if the size of the target clothes purchased by the current target electric shop is inconsistent with the size of the historic purchased clothes, judging that the target clothes purchased by the current target electric shop is a pre-returned clothes, further judging that the return estimated coefficient alpha' of the customer to the clothes is a non-returned clothes, otherwise, judging that the clothes purchased by the current target electric shop is a non-returned clothes, and obtaining the primary size return estimated coefficient alpha corresponding to the target clothes purchased by the current target electric shop s ，α s Take the value of alpha 'or alpha', and alpha>α', where s is denoted as the number corresponding to each customer, s=1, 2.
A3, purchasing information of each marked customer according to the history of the target electronic shop, which is extracted from the electronic commerce information base, so as to obtain the height and the weight and the size of each marked customer, comparing the height and the weight of each marked customer with the height and the weight of each customer, comparing the height and the weight of each customer with the weight levels corresponding to the heights and the weights stored in the database, so as to obtain the weight levels corresponding to each customer, comparing the height and the weight of each marked customer with the weight levels corresponding to the heights and the weights stored in the database, so as to obtain the weight levels corresponding to each marked customer, comparing the weight levels corresponding to each customer with the weight levels corresponding to each marked customer, judging that each customer belongs to the same level with the height and the weight of each marked customer if the weight levels corresponding to a certain marked customer are consistent, so as to obtain the numbers corresponding to the heights and the weight of each marked customer in the same level, and comparing the heights and the weight of each marked customer belonging to the same levelThe customer marks are all reference customers, the good rating of the sizes corresponding to all the reference customers is obtained, the good rating of the sizes corresponding to all the reference customers is compared and screened, the sizes with the good rating arranged in front are obtained, the sizes with the good rating arranged in front are compared with the sizes of the target clothes corresponding to the current target electric store of all the customers, and the size return evaluation coefficient beta corresponding to the current target electric store of all the customers is obtained according to the same analysis mode of the preliminary return evaluation coefficient corresponding to the target clothes purchased by the current target electric store of all the customers s 。
2. The garment e-commerce intelligent monitoring and analysis system based on data analysis of claim 1, wherein: the purchasing information of each customer at the target electronic shop at the present time comprises the number of the purchased target clothes, the corresponding size of the purchased target clothes, the corresponding price of the target clothes and the corresponding style type of the target clothes.
3. The garment e-commerce intelligent monitoring and analysis system based on data analysis of claim 2, wherein: the historical purchase information includes a historical purchase garment style and a historical purchase garment size.
4. The garment e-commerce intelligent monitoring and analysis system based on data analysis of claim 1, wherein: the evaluation is carried out to obtain target clothing return probability coefficients corresponding to all customers, and the specific evaluation process is as follows:
b1, comparing the style of the target clothes corresponding to the current target electric shop with the style of the historic purchasing clothes, if the style of the target clothes corresponding to the current target electric shop is not consistent with the style of the historic purchasing clothes, determining that the target clothes purchased by the current target electric shop is the required return clothes, further estimating the return index χ' of the customer to the clothes, otherwise, determining that the target clothes purchased by the current target electric shop is the unnecessary returnThe goods clothing and the goods returning estimated index χ' of the customer to the target clothing are obtained, so as to obtain the size goods returning analysis index χ corresponding to the target clothing purchased by each customer at the target electronic shop at the present time s ，χ s The value of χ ' or χ ", and χ ' is '>χ″；
B2, further utilize the formulaCalculating to obtain target clothing return probability coefficient delta corresponding to each customer s Wherein a1 and a2 are respectively expressed as weight factors corresponding to the size and style of the customer, a3 and a4 are respectively expressed as preliminary size return evaluation coefficients and influence factors corresponding to the size return evaluation coefficients, and a1>a2。
5. The garment e-commerce intelligent monitoring and analysis system based on data analysis of claim 1, wherein: the historical sales information of the target electronic store includes target clothing sales for each month of the past year.
6. The intelligent monitoring and analyzing system for clothing electronic commerce based on data analysis of claim 5, wherein: the analysis is carried out to obtain the target clothing pre-sales corresponding to the current month of the target electronic shop, and the specific analysis process is as follows:
c1, extracting target clothing sales amounts of each month of each year of the target electronic store according to historical sales information of the target electronic store, substituting the target clothing sales amounts of each month of each year of the target electronic store into a clothing sales trend model diagram to obtain sales trends corresponding to the target clothing sales amounts of each month of each year of the target electronic store, and further utilizing a calculation formulaCalculating sales increase rate epsilon corresponding to each year of the target electric store i Where i is a number corresponding to each year, i=1, 2,..M=1, 2,. The. im Expressed as the target sales of clothing corresponding to the mth month in the ith year,/-th year>Expressed as target clothing sales corresponding to the m-1 th month in the ith year, m expressed as the total number of months;
c2, further obtaining the corresponding China rose of the target garment from the electronic commerce information base according to the current China rose, comparing the date of the China rose corresponding to the current China rose with the corresponding China rose of the target garment, judging that the current China rose is the China rose if the date of the China rose corresponding to the current China rose is consistent with the comparison of the China rose corresponding to the target garment, and further obtaining the sales growth coefficient corresponding to the target garmentOtherwise, judging the current month as the off-season month, and further obtaining the sales growth coefficient corresponding to the target clothingThereby obtaining sales growth evaluation coefficient corresponding to the target clothing> The value is +.>Or->And->
C3, target clothes from target electronic store to each month of each yearThe sales amount is used for extracting the target clothing sales amount corresponding to the current month of the set year, and then the target clothing sales amount is calculated according to an analysis formulaCalculating to obtain target clothing pre-sales quantity phi corresponding to the current month of the target electric shop, wherein XS is expressed as target clothing sales quantity corresponding to the current month of the set year, j is expressed as total number of the past year, and e is expressed as a natural constant.
7. The intelligent monitoring and analyzing system for clothing electronic commerce based on data analysis of claim 6, wherein: the comprehensive judgment and analysis target electronic shop is characterized by comprising the following specific judgment processes:
r1, comparing the target clothing return probability coefficient corresponding to each customer with the set clothing standard return probability coefficient, if the target clothing return probability coefficient corresponding to a certain customer is greater than or equal to the set clothing standard return probability coefficient, judging the customer as the customer needing to return, counting the total number of the customers needing to return, extracting the number of the target clothing corresponding to the customer needing to return from the purchasing information of each customer on the target electric store shop according to the current time, extracting the number corresponding to each customer needing to return, counting the total number corresponding to the customer needing to return, and calculating the stock quantity corresponding to the target clothing of the target electric store according to the calculation formula M 0 ＝M 1 +M 2 *M 3 Calculating to obtain the estimated stock quantity M of the corresponding target clothing of the target electric shop 0 Wherein M is 1 Representing the corresponding stock quantity of target clothing of a target electronic shop, M 2 Indicated as the total number of customer correspondences in need of return, M 3 Representing a corresponding target clothing amount purchased for a customer in need of return;
r2, comparing the estimated stock quantity of the target clothes corresponding to the target electric shop with the target clothes pre-sales quantity corresponding to the current month of the target electric shop, judging that the target electric shop needs to be restocked if the estimated stock quantity of the target clothes corresponding to the target electric shop is larger than or equal to the target clothes pre-sales quantity corresponding to the current month of the target electric shop, and judging that the target electric shop does not need to be restocked if the estimated stock quantity of the target clothes corresponding to the target electric shop is smaller than the target clothes pre-sales quantity corresponding to the current month of the target electric shop.
8. The garment e-commerce intelligent monitoring and analysis system based on data analysis of claim 1, wherein: the electronic commerce information base is used for storing the China rose corresponding to the target clothing and the basic information corresponding to each customer, the method is also used for storing historical purchasing information of each marked customer of the target electronic store, historical sales information, basic information corresponding to each customer, historical purchasing information corresponding to each customer in the target electronic store and historical purchasing information of each marked customer of the target electronic store, wherein the historical purchasing information comprises height and weight, size and size good rating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211468799.8A CN115760223B (en) | 2022-11-22 | 2022-11-22 | Clothing electronic commerce intelligent monitoring analysis system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211468799.8A CN115760223B (en) | 2022-11-22 | 2022-11-22 | Clothing electronic commerce intelligent monitoring analysis system based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115760223A CN115760223A (en) | 2023-03-07 |
| CN115760223B true CN115760223B (en) | 2023-12-26 |
Family
ID=85335227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211468799.8A Active CN115760223B (en) | 2022-11-22 | 2022-11-22 | Clothing electronic commerce intelligent monitoring analysis system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115760223B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003208506A (en) * | 2002-01-11 | 2003-07-25 | Jcb:Kk | Customer evaluating information forming method, customer evaluating information forming device and program used therefor |
| CN101000668A (en) * | 2006-01-12 | 2007-07-18 | 鸿富锦精密工业（深圳）有限公司 | Check system and method for harmful component of product |
| JP2009169699A (en) * | 2008-01-16 | 2009-07-30 | Nomura Research Institute Ltd | Sales information analysis device |
| CN114565422A (en) * | 2022-03-28 | 2022-05-31 | 杉数科技(北京)有限公司 | Warehouse sales prediction method and device, storage medium and equipment |
| CN115115315A (en) * | 2022-07-18 | 2022-09-27 | 深圳泽熙网络科技有限公司 | E-commerce commodity inventory quantity dynamic reminding management system based on cloud computing |
| CN115204974A (en) * | 2022-07-07 | 2022-10-18 | 深圳市积加跨境网络科技有限公司 | Internet e-commerce commodity replenishment control method |
| CN115358661A (en) * | 2022-07-25 | 2022-11-18 | 上海日播至美服饰制造有限公司 | Returned clothing processing method, returned clothing processing equipment and storage medium |
-
2022
- 2022-11-22 CN CN202211468799.8A patent/CN115760223B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003208506A (en) * | 2002-01-11 | 2003-07-25 | Jcb:Kk | Customer evaluating information forming method, customer evaluating information forming device and program used therefor |
| CN101000668A (en) * | 2006-01-12 | 2007-07-18 | 鸿富锦精密工业（深圳）有限公司 | Check system and method for harmful component of product |
| JP2009169699A (en) * | 2008-01-16 | 2009-07-30 | Nomura Research Institute Ltd | Sales information analysis device |
| CN114565422A (en) * | 2022-03-28 | 2022-05-31 | 杉数科技(北京)有限公司 | Warehouse sales prediction method and device, storage medium and equipment |
| CN115204974A (en) * | 2022-07-07 | 2022-10-18 | 深圳市积加跨境网络科技有限公司 | Internet e-commerce commodity replenishment control method |
| CN115115315A (en) * | 2022-07-18 | 2022-09-27 | 深圳泽熙网络科技有限公司 | E-commerce commodity inventory quantity dynamic reminding management system based on cloud computing |
| CN115358661A (en) * | 2022-07-25 | 2022-11-18 | 上海日播至美服饰制造有限公司 | Returned clothing processing method, returned clothing processing equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 电子商务网络销售企业的退货管理;何军;崇大志;;中国科技信息(第04期) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115760223A (en) | 2023-03-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107665448A (en) | For determining the method, apparatus and storage medium of consumption contributed value | |
| CN105138690B (en) | The method and apparatus for determining keyword | |
| CN108389069A (en) | Top-tier customer recognition methods based on random forest and logistic regression and device | |
| CN115115315A (en) | E-commerce commodity inventory quantity dynamic reminding management system based on cloud computing | |
| CN108256802B (en) | Crowd search algorithm-based multi-supplier order distribution cloud processing method | |
| US20200219022A1 (en) | Method and apparatus for determining similarity between user and merchant, and electronic device | |
| CN108364191A (en) | Top-tier customer Optimum Identification Method and device based on random forest and logistic regression | |
| CN113034238B (en) | Commodity brand feature extraction and intelligent recommendation management method based on electronic commerce platform transaction | |
| CN112561543A (en) | E-commerce platform false transaction order monitoring method and system based on full-period logistics data analysis and cloud server | |
| CN113538012A (en) | Buyer user intelligent management method based on internet e-commerce platform data analysis | |
| CN112488605A (en) | Big data-based product inventory and sales prediction auxiliary system | |
| CN110033324A (en) | Data processing method, device, electronic equipment and computer readable storage medium | |
| CN111445133B (en) | Material management method and device, computer equipment and storage medium | |
| CN114707933A (en) | Intelligent factory inventory intelligent management method, system and storage medium | |
| CN116187808A (en) | Electric power package recommendation method based on virtual power plant user-package label portrait | |
| CN115760223B (en) | Clothing electronic commerce intelligent monitoring analysis system based on data analysis | |
| White | Measurement biases in consumer price indexes | |
| CN113222427A (en) | Fresh electric commercial commodity quality intelligent monitoring and management method based on multi-dimensional characteristic data analysis | |
| CN113506173A (en) | Credit risk assessment method and related equipment thereof | |
| CN113139768B (en) | Goods shortage monitoring method based on unmanned vending machine | |
| CN116012115A (en) | Crowd interest dynamic labeling method based on commodity map and supply chain | |
| CN114971805A (en) | Electronic commerce platform commodity intelligent analysis recommendation system based on deep learning | |
| CN114971083A (en) | Method for purchasing, predicting and selling goods | |
| CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
| CN111639274A (en) | Online commodity intelligent sorting method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231204 Address after: No.329 Mochou Road, Qinhuai District, Nanjing, Jiangsu 210000 Applicant after: Nanjing Jianyi Network Technology Co.,Ltd. Address before: No. 750, Heping Avenue, Wuchang District, Wuhan City, Hubei Province 430061 Applicant before: Wuhan Qinchun Garment Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |