CN115601080A - Industrial big data management method and system based on cloud server and storage medium - Google Patents
Industrial big data management method and system based on cloud server and storage medium Download PDFInfo
- Publication number
- CN115601080A CN115601080A CN202211027418.2A CN202211027418A CN115601080A CN 115601080 A CN115601080 A CN 115601080A CN 202211027418 A CN202211027418 A CN 202211027418A CN 115601080 A CN115601080 A CN 115601080A
- Authority
- CN
- China
- Prior art keywords
- hardware
- commodities
- various
- lost
- commodity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an industrial big data management method, an industrial big data management system and a storage medium based on a cloud server.
Description
Technical Field
The invention belongs to the technical field of industrial big data management, particularly relates to household hardware commodity sales management data management, and particularly relates to an industrial big data management method, an industrial big data management system and a storage medium based on a cloud server.
Background
With the continuous development of social economy, the living standard of people is improved, the requirements on the decoration of a home space are continuously improved, and the hardware fittings are widely used in home products. The normal use of many house products all need have the cooperation of hardware just can realize, in case hardware fitting goes wrong, the use of whole house product will receive the influence so. In the using process of home products, hardware accessories are easy to damage due to frequent matching use, under the condition, the purchasing demand of home hardware accessories is gradually increased, the competition of home hardware markets is aggravated by the situation, the defects of the traditional selling channel are exposed, in order to obtain the dominant position in the competition, a plurality of home hardware commodities are sold on line, on one hand, the range of purchasing crowds is enlarged, and on the other hand, the selling cost is reduced.
Because home hardware accessories include a plurality of types, such as hardware handles, zippers, hangers, screws and the like, all hardware commodities are not sold in good market due to the influence of various factors in the online sales process of home hardware merchants, so that the good market hardware commodities and the unsalable market hardware commodities always exist. For such a situation, at present, home hardware merchants often stop at the current situation, sales operation data and user ordering information of commodities are not fully utilized, and therefore, attribute analysis of consumer groups of marketable hardware commodities and prediction of reasons for late selling of the marketable hardware commodities are lacked, so that the home hardware merchants cannot perform online recommendation on the marketable hardware commodities and rectification and improvement on the late selling hardware commodities, further difficulty in further improving preference heat of the marketable hardware commodities and difficulty in converting the late selling state of the late selling hardware commodities are caused, and therefore the type coverage of the home hardware merchants in the home hardware markets is limited to a certain extent, and long-term development of the home hardware merchants is not facilitated.
Disclosure of Invention
In view of the above, the invention provides an industrial big data management method, an industrial big data management system and a storage medium based on a cloud server, which effectively solve the problems mentioned in the background technology by fully utilizing sales operation data and user ordering information corresponding to various hardware commodities of a household hardware merchant on an e-commerce platform to analyze consumer group attributes of popular hardware commodities and predict sale reasons of sale-delayed hardware commodities.
The invention is realized by adopting the following technical scheme.
In a first aspect, the invention provides an industrial big data management method based on a cloud server, which comprises the following steps:
a: counting the types and the quantity of hardware commodities of a target home hardware merchant in a sale state, and respectively marking the hardware commodities as 1,2, ·, i, ·, n;
b: collecting sales operation data corresponding to various hardware commodities of a target home hardware merchant in an e-commerce platform in a set time period;
c: analyzing preference heat corresponding to various hardware commodities based on corresponding sales operation data of the various hardware commodities in a set time period;
d: dividing various hardware commodities into popular hardware commodities and unsalable hardware commodities according to preference heat corresponding to the various hardware commodities;
e: extracting ordering records corresponding to various popular hardware commodities from an e-commerce platform within a set time period;
f: extracting an order-placing user account and an order-placing address from each order-placing record corresponding to various popular hardware commodities, and further collecting user basic information corresponding to the order-placing user account from an e-commerce platform;
g: analyzing the attributes of the consumer groups corresponding to various popular hardware commodities based on the basic information and the ordering address of the user corresponding to the ordering user account number in each ordering record corresponding to various popular hardware commodities;
h: analyzing the dotting value rate, the favorable evaluation rate and the price reasonableness of various lost hardware commodities in a set time period, and predicting the corresponding lost reasons of the various lost hardware commodities;
i: and displaying the consumer group attributes corresponding to various popular hardware commodities and the sale reasons corresponding to various sale-delayed hardware commodities to a target home hardware merchant in a background mode.
In one implementation manner of the first aspect of the present invention, the sales operation data includes sales volume, click volume, purchase amount, and collection amount.
In an implementation manner of the first aspect of the present invention, the analyzing the preference heat corresponding to each hardware product based on the sales operation data corresponding to each hardware product in the set time period specifically includes:
c-1: the sales operation data corresponding to various hardware commodities in a set time period form a hardware merchantSales operation data set G w ＝{g w 1,g w 2,…,g w i,…,g w n}，g w i represents sales operation data corresponding to the ith hardware commodity in a set time period, w represents sales operation data, and w = SA or GV or AC or SU, wherein SA, GV, AC and SU represent sales volume, click volume, purchase volume and collection volume respectively;
c-2: extracting proportion factors corresponding to sale, click, purchase and collection from a data management base;
c-3: the method comprises the steps of obtaining the display amount of various hardware commodities in a set time period, and further leading the display amount of the hardware commodities into a preference heat analysis formula by combining with a hardware commodity sales operation data set and proportion factors corresponding to sales, clicking, purchase adding and collection
Obtaining the corresponding preference heat of various hardware commodities
Wherein g is SA i、g GV i、g AC i、g SU i represents the sales volume, click volume, purchase volume and collection volume corresponding to the ith hardware product in a set time period, i represents the hardware product type number, i =1,2 i Expressed as the display amount, lambda, of the ith hardware commodity in a set time period SA 、λ GV 、λ AC 、λ SU And e is a natural constant.
In an implementation manner of the first aspect of the present invention, in the step D, the dividing manner corresponding to the dividing manner according to the preference heat corresponding to each hardware commodity is to compare the preference heat corresponding to each hardware commodity with a set preference heat threshold, if the preference heat corresponding to a certain hardware commodity is greater than or equal to the set preference heat threshold, divide the hardware commodity into the best-selling hardware commodity, and otherwise divide the hardware commodity into the late-selling hardware commodity.
In an implementation manner of the first aspect of the present invention, the user basic information includes a user gender and a user age, and the consumer group attributes include a preferred consumer group gender, a preferred consumer group age group, and a preferred consumer deal area.
In an implementation manner of the first aspect of the present invention, the analyzing attributes of the consumer group corresponding to each popular hardware commodity in the step G refers to the following steps:
g-1, extracting the gender of the user from the basic information of the user, comparing the gender of the user corresponding to the order placing user account number in each order placing record corresponding to each popular hardware commodity, and classifying the order placing records corresponding to the same gender of the user in each popular hardware commodity to obtain an order placing record set corresponding to males and an order placing record set corresponding to females in each popular hardware commodity;
g-2, respectively counting the number of order placing records in the order placing record set corresponding to males and the number of order placing records in the order placing record set corresponding to females in various marketable hardware commodities, and selecting the gender with the most order placing records as the gender of the preference consumer group corresponding to various marketable hardware commodities;
g-3, extracting the age of the user from the basic information of the user, matching the age with the age interval corresponding to each predefined age group, and matching the age groups of the user corresponding to each order record;
g-4, comparing the age groups of the users corresponding to the various ordering records of the various marketable hardware commodities, and classifying the ordering records corresponding to the same age group in the various marketable hardware commodities to obtain an ordering record set corresponding to each age group in the various marketable hardware commodities;
g-5, counting the number of order placing records in an order placing record set corresponding to each age group in various marketable hardware commodities respectively, and screening out the age group with the most order placing records as the age group of the preference consumer group corresponding to the various marketable hardware commodities;
g-6, extracting order placing areas from the order placing addresses, comparing the order placing areas corresponding to the order placing records of various popular hardware commodities, classifying the order placing records corresponding to the same order placing areas of the various popular hardware commodities, and obtaining order placing record sets corresponding to the order placing areas of the various popular hardware commodities;
and G-7, counting the number of order placing records in an order placing record set corresponding to each order placing area in various popular hardware commodities respectively, and extracting the order placing area with the most order placing records from the order placing records to serve as a preferential consumer transaction area corresponding to the various popular hardware commodities.
In an implementation manner of the first aspect of the present invention, in the H, a specific analysis process corresponding to analysis of the click value rate, the bad rating rate and the price reasonableness of various hardware products sold at a late stage in a set time period is as follows:
h-1, extracting click rate from sales operation data corresponding to various lost hardware commodities, comparing the click rate with the display amount of the various lost hardware commodities in a set time period, and calculating the click rate corresponding to the various lost hardware commodities according to the calculation formula
CT j The click rate corresponding to the jth unsalable hardware commodity is represented, j represents the number of the unsalable hardware commodity, and j =1,2 GV j、Z j Respectively representing the click quantity and the display quantity of the jth lost sales hardware commodity in a set time period;
h-2, extracting sales volume from sales operation data corresponding to various lost sales hardware commodities, comparing the sales volume with click volume of various lost sales hardware commodities in a set time period, and calculating conversion rate corresponding to various lost sales hardware commodities according to a calculation formula
IR j Expressed as the conversion rate, g, corresponding to the jth lost-selling hardware commodity SA j represents the sales volume of the jth lost hardware commodity in a set time period;
h-3, subtracting the click quantity corresponding to various lost hardware commodities from the sales quantity to obtain conversion failure click quantities corresponding to various lost hardware commodities, and acquiring click duration corresponding to each conversion failure click;
h-4, carrying out mean value calculation on click duration corresponding to each conversion failure click of various lost hardware commodities to obtain conversion failure average click duration corresponding to various lost hardware commodities, and marking as AF j ；
H-5, passing click rate, conversion rate and conversion failure average click duration corresponding to various lost hardware commodities through a click value rate calculation formula
Obtaining the corresponding point-like value rate eta of various lost-selling hardware commodities j T represents the duration corresponding to the set time period, and a represents the weight factor corresponding to the click rate;
h-6, counting the total evaluation quantity and the poor evaluation quantity formed by various lost hardware commodities in a set time period, and further calculating the poor evaluation rate corresponding to the various lost hardware commodities according to the total evaluation quantity and the poor evaluation quantity;
h-7, screening the same type of commodities corresponding to various lost hardware commodities from the E-commerce platform in a set time period, and counting the number of the screened same type of commodities;
h-8, obtaining the selling unit prices of various lost hardware commodities corresponding to the same commodities, and further carrying out mean value processing on the selling unit prices to obtain the average selling unit prices of various lost hardware commodities corresponding to the same commodities as the reference selling unit prices corresponding to the various lost hardware commodities;
h-9, obtaining the sale unit prices corresponding to various lost sales hardware commodities, comparing the sale unit prices with the reference sale unit prices corresponding to the lost sales hardware commodities, and calculating the price reasonableness corresponding to the various lost sales hardware commodities.
In an implementation manner of the first aspect of the present invention, the specific prediction manner for predicting the cause of lost sales corresponding to various lost sales hardware products is as follows: comparing the corresponding clickthrough value rate, the poor evaluation rate and the price reasonableness of various unsmooth hardware commodities with the set clickthrough value rate, the poor evaluation rate and the price reasonableness in the selling state respectively, if the clickthrough value rate of a certain unsmooth hardware commodity is smaller than the clickthrough value rate in the selling state, predicting that the corresponding unsmooth reason of the unsmooth hardware commodity is not enough in attraction of a commodity display interface, if the poor evaluation rate of the certain unsmooth hardware commodity is larger than the poor evaluation rate in the selling state, predicting that the corresponding unsmooth reason of the unsmooth hardware commodity is not good in quality, and if the price reasonableness of the certain unsmooth hardware commodity is smaller than the price reasonableness in the selling state, predicting that the corresponding unsmooth hardware commodity is unreasonable in price.
In a second aspect, the invention provides an industrial big data management system based on a cloud server, which comprises the following modules:
the hardware commodity sales statistics module is used for counting the types and the quantity of hardware commodities of a target home hardware merchant in a sales state, and marking the hardware commodities as 1,2, a.
The system comprises a sales operation data acquisition module, a data processing module and a data processing module, wherein the sales operation data acquisition module is used for acquiring sales operation data corresponding to various hardware commodities of a target household hardware merchant in an e-commerce platform in a set time period;
the hardware commodity type preference heat degree analysis module is used for analyzing preference heat degrees corresponding to various hardware commodities based on sales operation data corresponding to the various hardware commodities in a set time period;
the hardware commodity type dividing module is used for dividing various hardware commodities into mass-market hardware commodities and unsalable hardware commodities according to preference heat corresponding to the various hardware commodities;
the order taking record extraction module is used for extracting order taking records corresponding to various popular hardware commodities from the E-commerce platform within a set time period;
the system comprises a user basic information acquisition module, a data processing module and a data processing module, wherein the user basic information acquisition module is used for extracting an order-placing user account and an order-placing address from each order-placing record corresponding to various popular hardware commodities and further acquiring user basic information corresponding to the order-placing user account from an e-commerce platform;
the system comprises a popular hardware commodity consumption crowd attribute analysis module, a commodity ordering module and a commodity ordering module, wherein the popular hardware commodity consumption crowd attribute analysis module is used for analyzing the consumption crowd attributes corresponding to various popular hardware commodities based on user basic information and ordering addresses corresponding to ordering user accounts in ordering records corresponding to various popular hardware commodities;
the system comprises a lost sales reason prediction module, a price analysis module and a price analysis module, wherein the lost sales reason prediction module is used for analyzing the click value rate, the poor evaluation rate and the price reasonableness of various lost sales hardware commodities in a set time period so as to predict the corresponding lost sales reasons of the various lost sales hardware commodities;
and the background display terminal is used for displaying the consumer group attributes corresponding to various popular hardware commodities and the sale reasons corresponding to various sale reasons to the target home hardware merchants in a background manner.
In a third aspect, the invention provides an industrial big data management storage medium based on a cloud server, wherein a computer program is burned in the storage medium, and when the computer program runs in a memory of the server, the industrial big data management method based on the cloud server is realized.
By combining all the technical schemes, the invention has the advantages and positive effects that:
(1) According to the method, the sales operation data of various hardware commodities of a target home hardware merchant on an e-commerce platform are collected, the various hardware commodities are divided into the current sold hardware commodities and the current sold hardware commodities, the subsequent processing of the current sold hardware commodities and the current sold hardware commodities is realized, the utilization rate of the commodity sales operation data and the user ordering information is greatly improved, the defect that the current situation of the current sold hardware commodities and the current sold hardware commodities cannot be stopped by the current home hardware merchant is overcome, a targeted reference basis is provided for online recommendation of the current sold hardware commodities and rectification of the current sold hardware commodities by the home hardware merchant, the preference hot degree of the current sold hardware commodities is further improved, the possibility of conversion of the current sold hardware commodities to the current sold hardware commodities by the home hardware merchant is provided, and the development of the home hardware merchant in a long-distance is facilitated to the home hardware merchant.
(2) According to the invention, when the attributes of the consumers corresponding to the popular hardware commodities are analyzed by combining the ordering information of the user, the characteristics of ages, sexes and ordering areas of the consumers are fully considered, so that the sexes of the preference consumers, the age groups of the preference consumers and the traffic areas of the preference consumers corresponding to the popular hardware commodities are analyzed, the comprehensive analysis of the attributes of the consumers is realized, more specific recommendation crowds are provided for the subsequent online recommendation of the popular hardware commodities, the screening accuracy of the recommendation crowds is improved by reducing the screening range of the recommendation crowds, the invalid recommendation is effectively avoided, the recommendation effect is improved to the greatest extent, and the method has a strong practical value.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a flow chart of the steps of a method of the present invention;
fig. 2 is a schematic diagram of the system module connection according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example 1
Referring to fig. 1, the present invention provides a cloud server-based industrial big data management method, including the following steps:
a: counting the types and the quantity of hardware commodities of a target home hardware merchant in a sale state, and respectively marking the hardware commodities as 1,2, ·, i, ·, n;
b: collecting sales operation data corresponding to various hardware commodities of a target home hardware merchant in an e-commerce platform in a set time period, wherein the sales operation data comprise sales volume, click volume, purchase amount and collection amount;
c: the preference heat corresponding to various hardware commodities is analyzed based on the corresponding sales operation data of various hardware commodities in the set time period, and the preference heat comprises the following specific steps:
c-1: the sales operation data corresponding to various hardware commodities in a set time period form a hardware commodity sales operation data set G w ＝{g w 1,g w 2,…,g w i,…,g w n}，g w i represents sales operation data corresponding to the ith hardware commodity in a set time period, w represents sales operation data, and w = SA or GV or AC or SU, wherein SA, GV, AC and SU represent sales volume, click volume, purchase volume and collection volume respectively;
c-2: extracting proportion factors corresponding to sale, click, purchase and collection from a data management base;
c-3: the method comprises the steps of obtaining the display amount of various hardware commodities in a set time period, and further leading the display amount of the hardware commodities into a preference heat analysis formula by combining with a hardware commodity sales operation data set and proportion factors corresponding to sales, clicking, purchase adding and collection
Obtaining the corresponding preference heat of various hardware commodities
Wherein g is SA i、g GV i、g AC i、g SU i represents the sales volume, click volume, purchase volume and collection volume corresponding to the ith hardware product in a set time period, i represents the hardware product type number, i =1,2 i Expressed as the display amount, lambda, of the ith hardware commodity in a set time period SA 、λ GV 、λ AC 、λ SU Respectively expressed as salesThe proportion factors corresponding to the amount, the click amount, the purchase amount and the collection amount are expressed as natural constants;
the above-mentioned display amount is the number of times that the user displays the commodity by inputting the keyword of the searched commodity after the commodity is released;
it should be noted that, in the above-mentioned preference popularity analysis formula, the influence of the sales volume, the click volume, the purchase adding volume and the collection volume on the preference popularity is positive influence, and the results of the sales, the click, the purchase adding and the collection actions on the preference popularity are different, so that the proportion factors corresponding to the sales, the click, the purchase adding and the collection are different, wherein the sales has the purchase action to make the proportion factor the largest, and the purchase adding and the collection only have the purchase tendency to make the proportion factor the second time, and the click means that there is the browsing action, which has the possibility of the purchase tendency to make the proportion factor the smallest;
d: the method comprises the steps that various hardware commodities are divided into sold hardware commodities and unsalaked hardware commodities according to preference heat degrees corresponding to the various hardware commodities, the preference heat degrees corresponding to the various hardware commodities are compared with a set preference heat degree threshold, if the preference heat degree corresponding to a certain hardware commodity is larger than or equal to the set preference heat degree threshold, the hardware commodity is divided into sold hardware commodities, and if not, the hardware commodity is divided into unsalated hardware commodities;
e: extracting ordering records corresponding to various popular hardware commodities from an e-commerce platform within a set time period;
f: extracting an order placing user account and an order placing address from each order placing record corresponding to various popular hardware commodities, and further collecting user basic information corresponding to the order placing user account from an e-commerce platform, wherein the user basic information comprises user gender and user age;
g: analyzing the attributes of the consumer groups corresponding to various popular hardware commodities based on the basic user information and the ordering address corresponding to the ordering user account number in each ordering record corresponding to various popular hardware commodities, wherein the attributes of the consumer groups comprise preference consumer group gender, preference consumer group age groups and preference consumer person transaction areas;
in the above, the analysis of the attributes of the consumer groups corresponding to various marketable hardware commodities refers to the following steps:
g-1, extracting the gender of the user from the basic information of the user, comparing the gender of the user corresponding to the order placing user account number in each order placing record corresponding to each popular hardware commodity, and classifying the order placing records corresponding to the same gender of the user in each popular hardware commodity to obtain an order placing record set corresponding to males and an order placing record set corresponding to females in each popular hardware commodity;
g-2, respectively counting the number of order placing records in the order placing record set corresponding to males and the number of order placing records in the order placing record set corresponding to females in various marketable hardware commodities, and selecting the gender with the most order placing records as the gender of the preference consumer group corresponding to various marketable hardware commodities;
g-3, extracting the age of the user from the basic information of the user, matching the age with the age interval corresponding to each predefined age range, and matching the age range of the user corresponding to each order record;
g-4, comparing the age groups of the users corresponding to the various ordering records of the various marketable hardware commodities, and classifying the ordering records corresponding to the same age group in the various marketable hardware commodities to obtain an ordering record set corresponding to each age group in the various marketable hardware commodities;
g-5, counting the number of order placing records in an order placing record set corresponding to each age group in various marketable hardware commodities respectively, and screening out the age group with the most order placing records as the age group of the preference consumer group corresponding to the various marketable hardware commodities;
g-6, extracting order placing areas from the order placing addresses, comparing the order placing areas corresponding to the order placing records of various popular hardware commodities, classifying the order placing records corresponding to the same order placing areas of the various popular hardware commodities, and obtaining order placing record sets corresponding to the order placing areas of the various popular hardware commodities;
in one embodiment, the above-mentioned listing of places of ordering specifically refers to provincial regions, such as Guangdong province;
g-7, counting the number of order placing records in an order placing record set corresponding to each order placing area in various marketable hardware commodities respectively, and extracting the order placing area with the most order placing records from the number of order placing records as a preferred consumer transaction area corresponding to the various marketable hardware commodities;
according to the embodiment of the invention, when the attributes of the consumption groups corresponding to the popular hardware commodities are analyzed by combining the ordering information of the user, the characteristics of the age, the gender and the ordering area of the consumption groups are fully considered, so that the gender, the age section and the traffic area of the preference consumption people corresponding to the popular hardware commodities are analyzed, the comprehensive analysis of the attributes of the consumption groups is realized, more specific recommendation groups are provided for the follow-up online recommendation of the popular hardware commodities, the screening accuracy of the recommendation groups is improved by reducing the screening range of the recommendation groups, the invalid recommendation is effectively avoided, the recommendation effect is improved to the greatest extent, and the method has a high practical value.
H: performing click value rate, poor evaluation rate and price reasonableness analysis on various lost hardware commodities in a set time period, and predicting the corresponding lost reasons of the various lost hardware commodities;
the specific analysis process corresponding to the analysis of the criticizing value rate, the poor evaluation rate and the price reasonableness of various lost hardware commodities in the set time period is as follows:
h-1, extracting click rate from sales operation data corresponding to various lost sales hardware commodities, comparing the click rate with the display amount of the various lost sales hardware commodities in a set time period, and calculating the click rate corresponding to the various lost sales hardware commodities according to a calculation formula
CT j The click rate corresponding to the jth unsalable hardware commodity is represented, j represents the number of the unsalable hardware commodity, and j =1,2 GV j、Z j Respectively representing the click rate and the display rate of the jth lost hardware commodity in a set time period, wherein the click rate is higher when the click rate is higher;
h-2, extracting sales volume from sales operation data corresponding to various lost sales hardware commodities, comparing the sales volume with click volume of various lost sales hardware commodities in a set time period, and calculating conversion rate corresponding to various lost sales hardware commodities according to a calculation formula
IR j Expressed as the conversion rate, g, corresponding to the jth lost-selling hardware commodity SA j is the sales volume of the jth lost hardware commodity in a set time period, wherein the larger the sales volume is, the larger the proportion of the user converted into the purchasing behavior in browsing the commodity is;
h-3, subtracting the click quantity corresponding to the various lost hardware commodities from the sales quantity to obtain the conversion failure click quantity corresponding to the various lost hardware commodities, and obtaining the click duration corresponding to each conversion failure click;
the conversion failure click quantity refers to the ratio that a user does not convert into a purchasing behavior when browsing commodities, and the longer the click duration corresponding to each conversion failure click is, the longer the browsing duration of the user on the commodity display page is, so that the browsing desire of the user on the commodity display page is further reflected;
h-4, calculating the mean value of click duration corresponding to each conversion failure click corresponding to each lost hardware commodity to obtain the conversion failure average click duration corresponding to each lost hardware commodity, and recording the conversion failure average click duration as AF j ；
H-5, calculating click rate, conversion rate and conversion failure average click duration corresponding to various unsalable hardware commodities according to a click value rate calculation formula
Obtaining the corresponding point value rate eta of various lost hardware commodities j T represents the duration corresponding to the set time period, and a represents the weight factor corresponding to the click rate;
it should be noted that the click rate, the conversion rate and the average click duration of conversion failure in the click value rate calculation formula all have positive influences on the click value rate, and the click value rate reflects the attraction of the commodity display page to the user to a certain extent;
h-6, counting the total evaluation quantity and the poor evaluation quantity formed in the set time period by various lost hardware commodities, and further calculating the poor evaluation rate corresponding to the various lost hardware commodities according to the total evaluation quantity and the poor evaluation quantity, wherein the calculation formula is
ξ j Expressed as the corresponding poor rating, x, of the jth lost sales hardware commodity j 、X j The j-th late sale hardware commodity sale quality evaluation method comprises the steps of respectively representing the bad evaluation quantity and the total evaluation quantity formed in a set time period by the j-th late sale hardware commodity, wherein the larger the bad evaluation quantity is, the larger the bad evaluation rate is, and the bad evaluation rate reflects the sale quality of the commodity to a certain extent;
h-7, screening the same type of commodities corresponding to various lost hardware commodities from the E-commerce platform in a set time period, and counting the number of the screened same type of commodities;
h-8, obtaining the selling unit prices of various lost hardware commodities corresponding to the same commodities, and further carrying out mean value processing on the selling unit prices to obtain the average selling unit prices of various lost hardware commodities corresponding to the same commodities as the reference selling unit prices corresponding to the various lost hardware commodities;
it should be noted that the evaluation of the price reasonableness corresponding to various lost hardware commodities is implemented by taking the same type of commodities of various lost commodities on an e-commerce platform as an evaluation basis, so that evaluation errors can be effectively reduced, and the truth degree and reliability of evaluation results are improved;
h-9, obtaining the sale unit prices corresponding to various lost hardware commodities, comparing the sale unit prices with the reference sale unit prices corresponding to the lost hardware commodities, and calculating the price reasonableness sigma corresponding to the various lost hardware commodities j The calculation formula is
p j 、p′ j Respectively showing the sale unit price and the reference sale unit price corresponding to the jth lost sale hardware commodity, wherein certain lost sale hardware commodityThe closer the corresponding sale unit price is to the reference sale unit price, the greater the price reasonability of the sale-delayed hardware commodity is, and the price reasonability reflects the acceptance degree of the commodity sale price of the user to a certain degree;
the specific prediction mode for predicting the reason of the lost sales corresponding to various lost sales hardware products is as follows: comparing the corresponding clickthrough value rate, the poor evaluation rate and the price reasonableness of various unsmooth hardware commodities with the set clickthrough value rate, the poor evaluation rate and the price reasonableness in the selling state respectively, if the clickthrough value rate of a certain unsmooth hardware commodity is smaller than the clickthrough value rate in the selling state, predicting that the corresponding unsmooth reason of the unsmooth hardware commodity is not enough in attraction of a commodity display interface, if the poor evaluation rate of the certain unsmooth hardware commodity is larger than the poor evaluation rate in the selling state, predicting that the corresponding unsmooth reason of the unsmooth hardware commodity is not good in quality, and if the price reasonableness of the certain unsmooth hardware commodity is smaller than the price reasonableness in the selling state, predicting that the corresponding unsmooth hardware commodity is unreasonable in price.
I: and displaying the consumer group attributes corresponding to various popular hardware commodities and the sale reasons corresponding to various sale-delayed hardware commodities to a target home hardware merchant in a background mode.
According to the embodiment of the invention, the sales operation data of various hardware commodities of a target home hardware merchant on an e-commerce platform is collected, the various hardware commodities are divided into the current sold hardware commodity and the current sold hardware commodity based on the collected sales operation data, and the current sold hardware commodity is predicted to be a reason for the current sold commodity based on the sales operation data corresponding to the current sold hardware commodity, so that the subsequent processing of the current sold hardware commodity and the current sold hardware commodity is realized, the utilization rate of the commodity sales operation data and the current selling information of the user is greatly improved, the defect that the current situation of the current sold hardware commodity and the current sold hardware commodity cannot be stopped by the current home hardware merchant is overcome, a targeted reference basis is provided for online recommendation and rectification of the current sold hardware commodity of the home hardware merchant, the preference heat of the current sold hardware commodity is further improved, and the possible conversion of the current sold hardware commodity to the current sold hardware commodity is also provided for the home hardware merchant, and the home hardware merchant is beneficial to the development of the home hardware merchant in a long-distance.
Example 2
Referring to fig. 2, the invention provides an industrial big data management system based on a cloud server, which includes the following modules:
the hardware commodity sales statistics module is used for counting the types and the quantity of hardware commodities of a target home hardware merchant in a sales state, and marking the hardware commodities as 1,2, a.
The system comprises a sales operation data acquisition module, a data processing module and a data processing module, wherein the sales operation data acquisition module is used for acquiring sales operation data corresponding to various hardware commodities of a target household hardware merchant in an e-commerce platform in a set time period;
the hardware commodity type preference heat degree analysis module is used for analyzing preference heat degrees corresponding to various hardware commodities based on sales operation data corresponding to the various hardware commodities in a set time period;
the hardware commodity type dividing module is used for dividing various hardware commodities into popular hardware commodities and unsalable hardware commodities according to preference heat corresponding to the various hardware commodities;
the order placing record extracting module is used for extracting order placing records corresponding to various marketable hardware commodities from the E-commerce platform within a set time period;
the system comprises a user basic information acquisition module, a data processing module and a data processing module, wherein the user basic information acquisition module is used for extracting an ordering user account and an ordering address from each ordering record corresponding to various popular hardware commodities, and further acquiring user basic information corresponding to the ordering user account from an e-commerce platform;
the system comprises a popular hardware commodity consumption crowd attribute analysis module, a commodity ordering module and a commodity ordering module, wherein the popular hardware commodity consumption crowd attribute analysis module is used for analyzing the consumption crowd attributes corresponding to various popular hardware commodities based on user basic information and ordering addresses corresponding to ordering user accounts in ordering records corresponding to various popular hardware commodities;
the system comprises a lost sales reason prediction module, a price analysis module and a price analysis module, wherein the lost sales reason prediction module is used for analyzing the dotting value rate, the favorable evaluation rate and the price reasonableness of various lost sales hardware commodities in a set time period so as to predict the corresponding lost sales reasons of the various lost sales hardware commodities;
and the background display terminal is used for displaying the consumer group attributes corresponding to various popular hardware commodities and the sale reasons corresponding to various sale reasons to the target home hardware merchants in a background manner.
The sales hardware commodity type statistical module is connected with the sales operation data acquisition module, the sales operation data acquisition module is respectively connected with the hardware commodity type preference heat degree analysis module and the delayed sales hardware commodity delay reason prediction module, the hardware commodity type preference heat degree analysis module is connected with the hardware commodity type division module, the hardware commodity type division module is respectively connected with the high-selling hardware commodity ordering record extraction module and the delayed sales reason prediction module, the high-selling hardware commodity ordering record extraction module is connected with the user basic information acquisition module, the user basic information acquisition module is connected with the high-selling hardware commodity consumption crowd attribute analysis module, and the high-selling hardware commodity consumption crowd attribute analysis module and the delayed sales reason prediction module are both connected with the background display terminal.
Example 3
The invention provides an industrial big data management storage medium based on a cloud server, wherein a computer program is burnt in the storage medium, and when the computer program runs in a memory of the server, the industrial big data management method based on the cloud server is realized.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (10)
1. A cloud server-based industrial big data management method is characterized by comprising the following steps:
a: counting the types and the quantity of hardware commodities of a target home hardware merchant in a sale state, and respectively marking the hardware commodities as 1,2,. 1, i,. 1, n;
b: acquiring sales operation data corresponding to various hardware commodities of a target home hardware merchant in an e-commerce platform within a set time period;
c: analyzing preference heat corresponding to various hardware commodities based on sales operation data corresponding to the hardware commodities in a set time period;
d: dividing various hardware commodities into popular hardware commodities and unsalable hardware commodities according to preference heat corresponding to the various hardware commodities;
e: extracting ordering records corresponding to various popular hardware commodities from an e-commerce platform within a set time period;
f: extracting an order placing user account and an order placing address from each order placing record corresponding to various popular hardware commodities, and further collecting user basic information corresponding to the order placing user account from an e-commerce platform;
g: analyzing the consumer group attributes corresponding to various popular hardware commodities based on the user basic information and the ordering address corresponding to the ordering user account in each ordering record corresponding to various popular hardware commodities;
h: performing click value rate, poor evaluation rate and price reasonableness analysis on various lost hardware commodities in a set time period, and predicting the corresponding lost reasons of the various lost hardware commodities;
i: and displaying the consumer group attributes corresponding to various popular hardware commodities and the sale reasons corresponding to various sale-delayed hardware commodities to a target home hardware merchant in a background mode.
2. The industrial big data management method based on the cloud server, according to claim 1, characterized in that: the sales operation data includes sales volume, click through volume, purchase volume and collection volume.
3. The industrial big data management method based on the cloud server, according to claim 2, is characterized in that: analyzing preference heat corresponding to various hardware commodities based on sales operation data corresponding to the various hardware commodities in a set time period specifically comprises:
c-1: the sales operation data corresponding to various hardware commodities in a set time period form a hardware commodity sales operation data set G w ＝{g w 1,g w 2,…,g w i,…,g w n}，g w i represents sales operation data corresponding to the ith hardware commodity in a set time period, w represents sales operation data, and w = SA or GV or AC or SU, wherein SA, GV, AC and SU represent sales volume, click volume, purchase volume and collection volume respectively;
c-2: extracting proportion factors corresponding to sale, click, purchase and collection from a data management base;
c-3: the display amount of various hardware commodities in a set time period is obtained, and then the display amount is led into a preference heat analysis formula in combination with a hardware commodity sales operation data set and proportion factors corresponding to sales, clicking, additional purchasing and collection
Obtaining the preference heat corresponding to various hardware commodities
Wherein g is SA i、g GV i、g AC i、g SU i represents the sales volume, click volume, purchase volume and collection volume corresponding to the ith hardware product in a set time period, i represents the hardware product type number, i =1,2 i Expressed as the display amount, lambda, of the ith hardware commodity in a set time period SA 、λ GV 、λ AC 、λ SU And e is a natural constant.
4. The industrial big data management method based on the cloud server, according to claim 1, characterized in that: and D, dividing various hardware commodities into popular hardware commodities and unsalable hardware commodities according to the preference heat degrees corresponding to the various hardware commodities in a dividing mode, comparing the preference heat degrees corresponding to the various hardware commodities with the set preference heat degree threshold value, if the preference heat degrees corresponding to certain hardware commodities are greater than or equal to the set preference heat degree threshold value, dividing the hardware commodities into popular hardware commodities, and otherwise, dividing the hardware commodities into unsalable hardware commodities.
5. The industrial big data management method based on the cloud server as claimed in claim 1, wherein: the user basic information comprises the gender and the age of the user, and the attributes of the consumer groups comprise the gender, the age range and the transaction area of the preferred consumer groups.
6. The industrial big data management method based on the cloud server, according to claim 5, characterized in that: and G, analyzing the attributes of the consumer groups corresponding to various marketable hardware commodities according to the following steps:
g-1, extracting user gender from the basic information of the user, comparing the user gender corresponding to the order placing user account number in each order placing record corresponding to each popular hardware commodity, and classifying the order placing records corresponding to the same user gender in each popular hardware commodity to obtain an order placing record set corresponding to a male and an order placing record set corresponding to a female in each popular hardware commodity;
g-2, respectively counting the number of order placing records in the order placing record set corresponding to males and the number of order placing records in the order placing record set corresponding to females in various marketable hardware commodities, and selecting the gender with the most order placing records as the gender of the preference consumer group corresponding to various marketable hardware commodities;
g-3, extracting the age of the user from the basic information of the user, matching the age with the age interval corresponding to each predefined age range, and matching the age range of the user corresponding to each order record;
g-4, comparing the age groups of the users corresponding to the various ordering records of the various marketable hardware commodities, and classifying the ordering records corresponding to the same age group in the various marketable hardware commodities to obtain an ordering record set corresponding to each age group in the various marketable hardware commodities;
g-5, counting the number of order placing records in an order placing record set corresponding to each age group in various marketable hardware commodities respectively, and screening out the age group with the most order placing records as the age group of the preference consumer group corresponding to the various marketable hardware commodities;
g-6, extracting order placing areas from the order placing addresses, comparing the order placing areas corresponding to the order placing records of various popular hardware commodities, classifying the order placing records corresponding to the same order placing areas of the various popular hardware commodities, and obtaining order placing record sets corresponding to the order placing areas of the various popular hardware commodities;
and G-7, counting the number of order placing records in an order placing record set corresponding to each order placing area in various popular hardware commodities respectively, and extracting the order placing area with the most order placing records from the order placing records to serve as a preferential consumer transaction area corresponding to the various popular hardware commodities.
7. The industrial big data management method based on the cloud server, according to claim 2, is characterized in that: and in the H, the concrete analysis processes corresponding to the analysis of the criticizing value rate, the poor evaluation rate and the price reasonableness of various lost hardware commodities within a set time period are as follows:
h-1, extracting click rate from sales operation data corresponding to various lost hardware commodities, comparing the click rate with the display amount of the various lost hardware commodities in a set time period, and calculating the click rate corresponding to the various lost hardware commodities according to the calculation formula
CT j Is denoted as jthThe click rate corresponding to the hardware commodity with lost sales, j is represented by the serial number of the hardware commodity with lost sales, j =1,2 GV j、Z j Respectively representing the click quantity and the display quantity of the jth lost hardware commodity in a set time period;
h-2, extracting sales volume from sales operation data corresponding to various lost sales hardware commodities, comparing the sales volume with click volume of various lost sales hardware commodities in a set time period, and calculating conversion rate corresponding to various lost sales hardware commodities according to a calculation formula
IR j Expressed as the conversion rate, g, corresponding to the jth lost-selling hardware commodity SA j represents the sales volume of the jth lost hardware commodity in the set time period;
h-3, subtracting the click quantity corresponding to the various lost hardware commodities from the sales quantity to obtain the conversion failure click quantity corresponding to the various lost hardware commodities, and obtaining the click duration corresponding to each conversion failure click;
h-4, carrying out mean value calculation on click duration corresponding to each conversion failure click of various lost hardware commodities to obtain conversion failure average click duration corresponding to various lost hardware commodities, and marking as AF j ；
H-5, passing click rate, conversion rate and conversion failure average click duration corresponding to various lost hardware commodities through a click value rate calculation formula
Obtaining the corresponding point value rate eta of various lost hardware commodities j T represents the duration corresponding to the set time period, and a represents the weight factor corresponding to the click rate;
h-6, counting the total evaluation quantity and the poor evaluation quantity formed in the set time period by various lost hardware commodities, and further calculating the poor evaluation rate corresponding to the various lost hardware commodities according to the total evaluation quantity and the poor evaluation quantity;
h-7, screening the same type of commodities corresponding to various lost hardware commodities from the E-commerce platform in a set time period, and counting the number of the screened same type of commodities;
h-8, obtaining the selling unit prices of various lost hardware commodities corresponding to the same commodities, and further carrying out mean value processing on the selling unit prices to obtain the average selling unit prices of various lost hardware commodities corresponding to the same commodities as the reference selling unit prices corresponding to the various lost hardware commodities;
h-9, obtaining the selling unit prices corresponding to various lost hardware commodities, comparing the selling unit prices with the reference selling unit prices corresponding to the lost hardware commodities, and calculating the price reasonableness corresponding to the various lost hardware commodities.
8. The industrial big data management method based on the cloud server, according to claim 1, characterized in that: the specific prediction mode for predicting the corresponding sale-delaying reasons of various sale-delaying hardware commodities is as follows: comparing the corresponding clickthrough value rate, the poor evaluation rate and the price reasonableness of various unsmooth hardware commodities with the set clickthrough value rate, the poor evaluation rate and the price reasonableness in the selling state respectively, if the clickthrough value rate of a certain unsmooth hardware commodity is smaller than the clickthrough value rate in the selling state, predicting that the corresponding unsmooth reason of the unsmooth hardware commodity is not enough in attraction of a commodity display interface, if the poor evaluation rate of the certain unsmooth hardware commodity is larger than the poor evaluation rate in the selling state, predicting that the corresponding unsmooth reason of the unsmooth hardware commodity is not good in quality, and if the price reasonableness of the certain unsmooth hardware commodity is smaller than the price reasonableness in the selling state, predicting that the corresponding unsmooth hardware commodity is unreasonable in price.
9. The utility model provides an industry big data management system based on high in clouds server which characterized in that includes following module:
the hardware commodity sale type counting module is used for counting the number of types of hardware commodities of a target home hardware merchant in a sale state, and marking the hardware commodities in 1,2, i, n;
the system comprises a sales operation data acquisition module, a sales operation data acquisition module and a sales operation data acquisition module, wherein the sales operation data acquisition module is used for acquiring sales operation data corresponding to various hardware commodities of a target home hardware merchant in an e-commerce platform within a set time period;
the hardware commodity type preference heat degree analysis module is used for analyzing preference heat degrees corresponding to various hardware commodities based on sales operation data corresponding to the various hardware commodities in a set time period;
the hardware commodity type dividing module is used for dividing various hardware commodities into popular hardware commodities and unsalable hardware commodities according to preference heat corresponding to the various hardware commodities;
the order taking record extraction module is used for extracting order taking records corresponding to various popular hardware commodities from the E-commerce platform within a set time period;
the system comprises a user basic information acquisition module, a data processing module and a data processing module, wherein the user basic information acquisition module is used for extracting an order-placing user account and an order-placing address from each order-placing record corresponding to various popular hardware commodities and further acquiring user basic information corresponding to the order-placing user account from an e-commerce platform;
the system comprises a best-selling hardware commodity consumption crowd attribute analysis module, a list ordering module and a list ordering module, wherein the best-selling hardware commodity consumption crowd attribute analysis module is used for analyzing consumption crowd attributes corresponding to various best-selling hardware commodities based on user basic information and list ordering addresses corresponding to list ordering user accounts in various list ordering records corresponding to various best-selling hardware commodities;
the device comprises a lost sale reason prediction module, a price analysis module and a price analysis module, wherein the lost sale reason prediction module is used for analyzing the click value rate, the poor evaluation rate and the price reasonableness of various lost sale hardware commodities in a set time period, so as to predict the corresponding lost sale reasons of the various lost sale hardware commodities;
and the background display terminal is used for displaying the consumer group attributes corresponding to various popular hardware commodities and the sale reasons corresponding to various sale-delayed hardware commodities to the target home hardware merchant in a background mode.
10. The utility model provides an industry big data management storage medium based on high in the clouds server which characterized in that: the commodity search storage medium is burned with a computer program, and the computer program realizes the method of any one of the above claims 1-8 when running in the memory of the server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211027418.2A CN115601080A (en) | 2022-08-25 | 2022-08-25 | Industrial big data management method and system based on cloud server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211027418.2A CN115601080A (en) | 2022-08-25 | 2022-08-25 | Industrial big data management method and system based on cloud server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115601080A true CN115601080A (en) | 2023-01-13 |
Family
ID=84842987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211027418.2A Pending CN115601080A (en) | 2022-08-25 | 2022-08-25 | Industrial big data management method and system based on cloud server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115601080A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109336A (en) * | 2023-04-13 | 2023-05-12 | 厦门蝉羽网络科技有限公司 | Method, system and storage medium for analysis and management of popularization data of electronic shop |
| CN117010947A (en) * | 2023-10-07 | 2023-11-07 | 太平金融科技服务（上海）有限公司 | NPS investigation method, device, equipment and storage medium based on business activity |
-
2022
- 2022-08-25 CN CN202211027418.2A patent/CN115601080A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109336A (en) * | 2023-04-13 | 2023-05-12 | 厦门蝉羽网络科技有限公司 | Method, system and storage medium for analysis and management of popularization data of electronic shop |
| CN117010947A (en) * | 2023-10-07 | 2023-11-07 | 太平金融科技服务（上海）有限公司 | NPS investigation method, device, equipment and storage medium based on business activity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107067283B (en) | E-commerce consumption customer flow prediction method based on historical merchant records and user behaviors | |
| CN115601080A (en) | Industrial big data management method and system based on cloud server and storage medium | |
| CN104463630B (en) | A kind of Products Show method and system based on net purchase insurance products characteristic | |
| De Silva et al. | Does the sun ‘shine’on art prices? | |
| TWI793412B (en) | Consumption prediction system and consumption prediction method | |
| CN109255651A (en) | A kind of search advertisements conversion intelligent Forecasting based on big data | |
| CN108389069A (en) | Top-tier customer recognition methods based on random forest and logistic regression and device | |
| Zhuang et al. | Price elasticities of key agricultural commodities in China | |
| CN111352976A (en) | Search advertisement conversion rate prediction method and device for shopping nodes | |
| CN114782076A (en) | Online shopping mall consumption platform lottery and point exchange intelligent management method and system and computer storage medium | |
| CN116320626A (en) | Method and system for calculating live broadcast heat of electronic commerce | |
| CN116049543A (en) | Comprehensive energy efficiency service business mixed recommendation method, system and storage medium | |
| CN111414542A (en) | Real estate customer group identification and marketing method | |
| CN114493700A (en) | Alliance platform alliance merchant data analysis processing system based on cloud computing | |
| CN114764732A (en) | Commodity recommendation method and equipment and computer-readable storage medium | |
| Du et al. | Clustering heat users based on consumption data | |
| WO2023197502A1 (en) | Comprehensive power evaluation method and apparatus | |
| CN113283960B (en) | Vertical e-commerce platform commodity intelligent recommendation method based on big data analysis and cloud computing and cloud service platform | |
| CN114971805A (en) | Electronic commerce platform commodity intelligent analysis recommendation system based on deep learning | |
| Golley et al. | Chinese household consumption, energy requirements and carbon emissions | |
| CN115471272A (en) | Business marketing big data analysis system, method and device | |
| Şahin et al. | Application of random forest algorithm for the prediction of online food delivery service delay | |
| Magliozzi et al. | List segmentation strategies in direct marketing | |
| CN117670187B (en) | Storage classification associated management system for intelligent logistics | |
| CN111160834A (en) | Inventory prediction method based on daily order and inventory |
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 |