CN113570421A - E-commerce marketing system based on big data analysis - Google Patents
E-commerce marketing system based on big data analysis Download PDFInfo
- Publication number
- CN113570421A CN113570421A CN202111111309.4A CN202111111309A CN113570421A CN 113570421 A CN113570421 A CN 113570421A CN 202111111309 A CN202111111309 A CN 202111111309A CN 113570421 A CN113570421 A CN 113570421A
- Authority
- CN
- China
- Prior art keywords
- product
- products
- module
- browsing
- level
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an e-commerce marketing system based on big data analysis, which relates to the technical field of e-commerce marketing and comprises the following components: the marketing platform is used for connecting the client and the cloud service platform; the marketing platform faces to the client and is used for displaying products and collecting information; the client is used for bearing the marketing platform; the cloud service platform comprises a terminal server and a cloud server; the marketing platform is in real-time data connection with the cloud server; the big data analysis module is used for grading the product display module and the product recommendation module respectively; the big data pushing module combines the product display modules and the product recommendation modules in different levels to form a product data combination package, and pushes the product data combination package to a marketing platform; adjusting the frequency of the product data combination package pushed to the marketing platform; the invention aims to provide richer product recommendation for users, improves the diversity and interest of product display, helps consumers to obtain more commodity display space, and improves the purchasing enthusiasm of consumers.
Description
Technical Field
The invention relates to the technical field of E-commerce marketing, in particular to an E-commerce marketing system based on big data analysis.
Background
Electronic marketing is a novel marketing mode which takes the internet as a media platform, makes and implements the activities of marketing enterprises in a new mode, method and operation concept through a series of charm network marketing plans and more effectively promotes the realization of individual and organizational transaction activities.
The electronic marketing is characterized by huge data information; therefore, the method is more beneficial to data mining and analysis, combines users, commodities and marketing modes through data mining, can evaluate marketing effects and mine potential users, can recommend products better according to the demand conditions of different consumer groups and different regions, and purposefully stimulates the user demands. However, in the current product display marketing system, more products which are interested by consumers are recommended based on the user figures of the consumers, the recommendation success rate and efficiency are higher, but the mining of the interest points of the consumers is reduced, the possibility of product purchase is reduced, and the further development of the consumers is not facilitated, so that other possibilities of the consumers are expanded while the interest of the consumers is met, the consumers are helped to obtain more commodity display spaces, and the purchase enthusiasm of the consumers is improved.
Disclosure of Invention
In order to overcome the problem that the product recommendation method in the prior art in the background art cannot fully mine the interest points of consumers, improve the diversity and interest of product display, better meet the requirements of people and widen the purchasing interest and possibility of the consumers to other products, the invention provides an e-commerce marketing system based on big data analysis.
The technical scheme adopted by the invention for solving the defects is as follows: an e-commerce marketing system based on big data analysis is provided, comprising:
the marketing platform is used for connecting the client and the cloud service platform; the marketing platform comprises a product display module, a product recommendation module, a product transaction module, a product retrieval module and a user information management module; the marketing platform faces to the client and is used for displaying products and collecting information;
the client is used for bearing a marketing platform and comprises a mobile phone or tablet computer app client and a PC webpage client;
the cloud service platform comprises a terminal server and a cloud server; the marketing platform is in real-time data connection with the cloud server; the terminal server comprises a big data storage module, a big data analysis module and a big data pushing module;
the big data analysis module establishes a user purchase model by matching the customer characteristics and the consumption behavior characteristics, and grades the products in the product display module and the products in the product recommendation module respectively according to the user purchase model;
the big data pushing module combines and sorts the products of different levels to form a product data combined package, and pushes the product data combined package to a marketing platform;
and setting a threshold value for dividing products in the product display module and products in the product recommendation module by the big data analysis module, and adjusting the frequency of a product data combination packet pushed to the marketing platform through real-time data exchange between the marketing platform and the cloud service platform.
The product display module comprises n-level page display, wherein 1 is less than or equal to n is less than or equal to 3; the product display module is used for displaying products and comprises a level 1 page, and the level 1 page comprises a plurality of pages; the product displayed through the level 1 page enters a detail page of the product, the detail page is a level 2 page, a product recommending module is also included in the level 2 page, the product in the product recommending module enters a level 3 page, the level 3 page also includes a product recommending module, and the page where the product enters is clicked again or the level 3 page is clicked.
Further, the big data storage module comprises transaction data, a browsing log, a searching log, user information data, product display keyword data and product characteristic information;
transaction data, browsing logs, searching logs and user information data collected by the marketing platform are subjected to data exchange in real time and stored in the big data storage module;
and inputting product characteristic information through a marketing platform background, displaying keyword data of the product, and storing the keyword data in a big data storage module.
Furthermore, the big data is cleaned and removed through a big data analysis module;
based on the big data user portrait and transaction data, browsing logs, searching logs, and extracting client features and consumption behavior features; marking the customer by a big data user picture to determine a product for level 1 page display;
constructing a user purchase model for page display of products in a product display module, and setting an initial display level p as a level 1, wherein the level 1 is an optimal display level;
extracting keywords of purchased products according to purchasing habits of customers, then performing correlation matching of the keywords of the purchased products to obtain initial recommended keyword products, and setting the level q of the initial recommended keyword products as level 1, wherein the level 1 is an optimal display level.
Furthermore, products meeting the requirements are set to be in a level 1 display level based on the customer characteristics and the consumption behavior characteristics, the products are displayed by the product display module and the product recommendation module, and the level 1 recommended keyword products are displayed by the product recommendation module.
Furthermore, the threshold value of the browsing times of the products in the product display module and the product recommendation module is set to be n1, and the threshold value of the browsing time of the products is set to be m 1; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; comparing the browsing log data with a product browsing frequency threshold n1 and a product browsing time threshold m1 respectively, and adjusting the display level p +1 when the comparison result is less than n1 and less than m 1; and when the p is greater than 5, the big data analysis module cleans the product data and removes the product characteristics from the customer characteristics and the consumption behavior characteristics of the user representation.
Furthermore, setting the threshold value of the browsing times of the products in the product recommending module as n2 and the threshold value of the browsing time of the products as m 2; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; respectively comparing the browsing log data with a product browsing frequency threshold n2 and a product browsing time threshold m2, and adjusting the recommended keyword product level q +1 when the comparison result is smaller than n2 and smaller than m 2; when q is greater than 5, the big data analysis module cleans the product data and does not recommend the product in the product recommendation module; however, when the corresponding keyword of the product appears in the search log, the product level q is reset by resetting the recommended keyword, and the level q =1 is reset until the product data is cleaned again by the big data analysis module when q >5, so that the product is not recommended in the product recommendation module.
Furthermore, the product recommending module is used for displaying products screened based on the user purchasing model and products screened based on the recommended keywords; setting products positioned at the front three and the rear three of the product recommending module as products with a display level p; products positioned in the middle of the product recommendation module are randomly arranged for products of a display level p and products of a recommended keyword product level q; the method aims to keep the first three recommended products as products which are interesting to the user, and the user can see more product displays when sliding down a recommendation menu, so that the condition that the recommended keyword products are too obtrusive is avoided.
Comparing browsing logs of products of a recommended keyword product level q by a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the recommended keyword product display time t is not less than 150min, matching the product information of the recommended keyword product to the behavior characteristics of consumers; and the recommended keyword products are marked as products with the display level p.
Comparing browsing logs of products of a recommended keyword product level q by a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the display time t of the recommended keyword product is less than or equal to 30min and q =5, the display of the recommended keyword product is eliminated.
The invention has the advantages that: the E-commerce marketing system based on big data analysis comprises a marketing platform, a client and a cloud service platform; the product display module and the product recommendation module are respectively graded through a user purchase model, the product display modules and the product recommendation modules in different grades are combined to form a product data combination package, and the product data combination package is pushed to a marketing platform; the method of the invention correspondingly displays the products according to different grades, and adjusts the marketing strategy of the products according to the browsing condition of the user; the aim of providing richer product recommendations for users is fulfilled, the diversity and interest of product display are improved, the requirements of people are better met, and the purchase interest and possibility of other products by consumers are widened.
Drawings
The present application is further described below with reference to the accompanying drawings:
fig. 1 is a block diagram of an e-commerce marketing system based on big data analysis according to the present invention.
Detailed Description
According to the above structural features of the present application, the embodiments of the present application will be further explained:
example 1
An e-commerce marketing system based on big data analysis, comprising:
the marketing platform is used for connecting the client and the cloud service platform;
the marketing platform comprises a product display module used for displaying products;
the product recommendation module is used for recommending related products;
the product transaction module is used for performing online transaction of products;
the product retrieval module is used for retrieving related products;
the user information management module is used for registering and logging in the user and managing the registered user information;
the marketing platform faces to the client and is used for displaying products and collecting information;
the client is used for bearing a marketing platform and comprises a mobile phone or tablet computer app client and a PC webpage client;
the cloud service platform comprises a terminal server and a cloud server; the marketing platform is in real-time data connection with the cloud server; the terminal server comprises a big data storage module, a big data analysis module and a big data pushing module;
the big data analysis module establishes a user purchase model by matching the customer characteristics and the consumption behavior characteristics, and grades the products in the product display module and the products in the product recommendation module respectively according to the user purchase model;
the big data pushing module combines and sorts the products of different levels to form a product data combined package, and pushes the product data combined package to a marketing platform;
and setting a threshold value for dividing the product display module and the product recommendation module by the big data analysis module, and adjusting the frequency of the product data combination packet pushed to the marketing platform through real-time data exchange between the marketing platform and the cloud service platform.
Example 2
Based on the embodiment 1, the method further comprises the following steps:
s1: the user registers and registers on the marketing platform through a client, such as a mobile phone or tablet computer app client, a PC webpage client and the like, and the big data storage module stores user information.
S2: the big data analysis module marks the user registration information as client characteristics and consumption behavior characteristics, recommends an initial product for the user, and sets the display level p of the initial display product as level 1; extracting keywords of purchased products according to purchasing habits of customers, then performing correlation matching of the keywords of the purchased products to obtain an initial recommended keyword product, and setting the level q of the initial recommended keyword product as level 1; displaying p1 products on a level 1 page and a level 2 page, and preferentially displaying the products on the level 1 page; the q1 level product is displayed on a level 2 page and a level 3 page;
s3: transaction data, browsing logs, searching logs and user information data collected by the marketing platform are subjected to data exchange in real time and stored in the big data storage module; the big data analysis module cleans and eliminates information such as transaction data, browsing logs, searching logs and the like of a user;
s4: setting the threshold value of the browsing times of the products in the product display module and the product recommendation module as n1 and the threshold value of the browsing time of the products as m 1; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; comparing the browsing log data with a product browsing frequency threshold n1 and a product browsing time threshold m1 respectively, and adjusting the display level p +1 when the comparison result is less than n1 and less than m 1;
s5: when p is greater than 5, the big data analysis module cleans the product data and removes the product characteristics from the customer characteristics and the consumption behavior characteristics of the user portrait;
s6: setting a threshold value of the browsing times of the products in the product recommending module as n2 and a threshold value of the browsing time of the products as m 2; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; respectively comparing the browsing log data with a product browsing frequency threshold n2 and a product browsing time threshold m2, and adjusting the recommended keyword product level q +1 when the comparison result is smaller than n2 and smaller than m 2;
s7: when q is greater than 5, the big data analysis module cleans the product data and does not recommend the product in the product recommendation module;
when the corresponding keywords of the product appear again in the search log, resetting the product level q of the recommended keywords and resetting the level q =1 until the product data is cleaned again through the big data analysis module when the q is greater than 5, and recommending the product in the product recommendation module is not carried out;
s8: in the product recommending module, the product recommending module is used for displaying products screened based on the user purchasing model and products screened based on the recommended keywords; setting products positioned at the front three and the rear three of the product recommending module as products of a display level p, wherein the products are products of a certain category;
the products in the middle of the product recommendation module are randomly arranged in a display level p and a recommended keyword product level q; forming a product data combination package in the arrangement mode, and pushing the product data combination package to a marketing platform;
s9: comparing the browsing logs of the products of the recommended keyword product level q through a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the recommended keyword product display time t is not less than 150min, matching the product information of the recommended keyword product to the behavior characteristics of consumers; the recommended keyword products are marked as products with a display level p;
s10: comparing the browsing logs of the products of the recommended keyword product level q through a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the display time t of the recommended keyword product is less than or equal to 30min and q =5, eliminating the display of the recommended keyword product;
setting a threshold value for dividing the product display module and the product recommendation module by the big data analysis module, and adjusting the grade of a product in the product display module and the grade of a product in the product recommendation module through the threshold value; the frequency of product data combination packages pushed to the marketing platform is adjusted through real-time data exchange between the marketing platform and the cloud service platform, and the purpose is to adjust the display sequence of products of different levels.
Example 3
Taking a certain example of the king of a user as an example, the E-commerce marketing system based on big data analysis comprises the following contents:
d1, downloading apps by a certain user king through a mobile phone end, and performing registration login or performing registration login through a webpage end; the registration content comprises birth date, gender, address, mobile phone number, and attention fields (such as digital code, food, living goods, etc.); some registered content of king includes birth date: in 1993, gender: female, address: slightly, mobile phone number: field selection, field selection: mother and infant, food, living goods;
d2, the big data analysis module marks the user registration information as customer characteristics and consumption behavior characteristics, and recommends an initial product for the user; the client characteristics are as follows: pregnant women, infant mothers, prepared pregnancies, women, etc.; consumption behavior characteristics: maternal and infant products, maternal and infant food, milk powder, cribs, bibs, baby wipes, and the like;
the following product categories are recommended for the user: baby milk powder, baby bibs, baby buttocks washing devices and the like, wherein the display level p is set to be 1 level; if the product display level p =1 of the baby bib is recommended, namely the keyword comprises the baby and the product display level setting p =1 of the bib, and the product display level is independent of brands; displaying different products with the display level p =1 on a product display module, wherein the products are positioned on a level 1 or level 2 page;
according to the initial keywords: generating related keywords randomly according to the keywords such as mother and infant, food, milk powder, bib and the like: setting an initial recommended keyword product level q as level 1, if the recommended keyword product level q =1 of the small night lamp, displaying the product in a product recommendation module, and setting the product in a level 2 or 3 page;
d3, according to some trading data of user's king, browsing log, searching log and user information data real-time data exchange, storing in big data storage module;
according to the browsing condition and transaction condition of a certain king, the products browsed by the certain king are mainly baby bibs and breast pumps; and (4) displaying a search log: newly adding keywords, namely urine insulation pads, baby diapers, baby pillows and the like;
therefore, the display level p =1 of the new products such as the urine isolation pad and the baby pillow is used for displaying on the product display module and is located on the level 1 or level 2 page.
D4, setting the threshold value of the browsing times of the products in the product display module and the product recommendation module as n1 and the threshold value of the browsing time of the products as m 1; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; comparing the browsing log data with a product browsing frequency threshold n1 and a product browsing time threshold m1 respectively, and adjusting the display level p +1 when the comparison result is less than n1 and less than m 1;
setting a threshold value of browsing times of products in a product display module and a product recommendation module as n1= 5-30 times; the product browsing time threshold value is m1=1-15 min;
according to a certain browsing log of a king, a big data analysis module identifies and compares products with a display level p = 1; products such as baby milk powder, baby bibs, baby flatus, and the like;
wherein during the 1 st day period: if the browsing time n1 of the infant milk powder is 5 to less than 30, and the browsing time m1=2min, the display level p =1+1=2 of the infant milk powder is adjusted; the product display level of the display level p =1 is better than the product of the display level p = 2;
over a 2 day period: the browsing times of the infant milk powder are 10-30, the browsing time m1=20min, the infant milk powder is not adjusted, and the display level p =2 is kept unchanged;
the big data analysis module adjusts the product display level according to the browsing condition of the user, so that the product display level with high attention degree is maintained at p =2 or 3; the new product display level p =1, and the level is reduced only after the attention is reduced; when the display level p =5 of the product, the big data analysis module will clear the product of the level so as to accurately describe the purchasing habit, the consumption behavior characteristics and the like for the product;
when the user reappears the removed product keywords in the search log, the display level p =1 of the product is redistributed, the steps are repeated until the display level p reaches 5 again, and then data removal is performed again;
d5, setting the threshold value of the browsing times of the products in the product recommending module as n2 and the threshold value of the browsing time of the products as m 2; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; respectively comparing the browsing log data with a product browsing frequency threshold n2 and a product browsing time threshold m2, and adjusting the recommended keyword product level q +1 when the comparison result is smaller than n2 and smaller than m 2;
setting a threshold value of browsing times of a product in a product recommending module as n2= 2-20 times; the product browsing time threshold value is m1=1-10 min;
according to a certain browsing log of a king, a big data analysis module identifies and compares products with recommended keyword product level q = 1; products such as slippers, mosquito-repellent liquid, small night lights, etc.;
as a small night light product, during day 1: if the browsing times n2 of the small night light are 18-20, and the browsing time m2=7min, the recommended keyword product level q =1+1=2 of the small night light is adjusted; recommending a product with the product display level of the keyword product level q =1 being better than the product with the product level q =2 of the keyword;
over a 2 day period: if the browsing times n2 of the small night light are 32 more than 20, and the browsing time m2=20min, the small night light is not adjusted, and the display level p =2 is kept unchanged;
as with the slipper product, at day 1: if the browsing times n2 of the slipper product are 2 less than 20 and the browsing time m2=1min, the recommended keyword product level q =1+1=2 of the slipper is adjusted;
over a 2 day period: if the browsing times n2 of the slipper product are 1 less than 20 and the browsing time m2=0.5min, the recommended keyword product level q =2+1=3 of the slipper is adjusted;
when a user enters a level 2 page through a baby bib in the product display module, the level 2 page describes a product and is provided with a product recommending module, and recommended products, such as a small night light, are displayed in the product recommending module; the user may be interested in the small night lamp, and then click on the related products of the small night lamp, when the product of the small night lamp is maintained between q = 1-5 for a certain time, the user has the purchasing desire for the related products of the small night lamp, and the consumption behavior characteristics of the user at the current stage are met; if the recommended product does not attract the user, replacing, and newly adding a related product for testing;
through the replacement of the recommended products, the interest points of the user are improved, and the situation that the recommended products accord with the interests of the user but the purchasing desire is reduced due to long time and the exploration degree of the user on the products is reduced, and the loyalty of the user on a marketing platform is reduced in long time is avoided;
therefore, certain products which are not concerned by the user are continuously provided, the aesthetic fatigue of the user is reduced, the fun of the user for selecting the products is enhanced, the potential product interest points of the user can be found, and the user portrait can be more finely constructed.
The big data analysis module adjusts the product display level according to the browsing condition of the user, so that the recommended keyword product level of the product with high attention is maintained at q =2 or 3; newly adding a recommended keyword product grade q =1, and only after the attention degree is reduced, carrying out grade reduction; when the recommended keyword level q of the product is =5, the big data analysis module will remove the product of the level so as to accurately describe the purchasing habit, the consumption behavior characteristics and the like for the product;
when the user reappears the removed product keywords in the search log, the product level q of the recommended keywords is not distributed; the display level p =1 of the product is redistributed, and the step D4 is repeated until the display level p reaches 5 again, and then data clearing is carried out again;
d6, in the product recommending module, the product recommending module is used for displaying the products screened based on the user purchasing model and the products screened based on the recommending keywords; setting products positioned at the front three and the rear three of the product recommending module as products of a display level p, wherein the products are products of a certain category;
for example, in a product recommendation module, the baby bibs with the P =2 are arranged in the front three positions, when search words such as baby pillows appear, the display level P =1 of the baby pillows is located in front of the baby milk powder, and the arrangement is adjusted; the last three products p = 2-5, such as baby milk powder and the like;
the products in the middle of the product recommendation module are randomly arranged in a display level p and a recommended keyword product level q;
for example: products such as the breast pumps with the level p =2 and the slippers with the recommended keyword product level q =2 are displayed, related products are randomly arranged, and the recommended arrangement and the arrangement frequency of the products are adjusted according to the browsing condition, the transaction condition and the search condition of a user;
d7, comparing the browsing logs of the products of the recommended keyword product level q through a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the recommended keyword product display time t is not less than 150min, matching the product information of the recommended keyword product to the behavior characteristics of consumers; the recommended keyword products are marked as products with a display level p;
if the recommended keyword product level q =2 of the small night light, comparing the browsing logs of the small night light through a big data analysis module, keeping the browsing times of the small night light for more than 20 times in 3 days, keeping the browsing time for more than 15min and keeping for 3 days; at this time, the big data analysis module removes the recommended keyword product level of the small night lamp product, and repeats the step D4 after the display level p =1 is redistributed until the display level p reaches 5 again, and then data is cleared;
d8, comparing the browsing logs of the products of the recommended keyword product level q through a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the display time t of the recommended keyword product is less than or equal to 30min and q =5, eliminating the display of the recommended keyword product; the recommended keyword product display time t is the sum of the time for a user to browse the product since the recommended keyword product is displayed;
if the recommended keyword product level q of the slippers is =5, comparing browsing logs of a small night lamp through a big data analysis module, wherein the browsing times of the small night lamp are less than 20 times, the browsing time is less than 1min, and the sum of the browsing times of the user on the product is t ≦ 30min since the slippers are recommended; at the moment, the big data analysis module removes the recommended keyword product grade of the slipper product and eliminates the display of the recommended keyword product;
when the user reappears the removed product keywords in the search log, the display level p =1 of the product is redistributed, the steps are repeated until the display level p reaches 5 again, and then data removal is performed again;
in view of the above, it will be apparent to those skilled in the art from this disclosure that various changes, modifications, substitutions, and alterations can be made without departing from the spirit and scope of the invention.
Claims (10)
1. The utility model provides an electricity merchant marketing system based on big data analysis which characterized in that: the method comprises the following steps:
the marketing platform is used for connecting the client and the cloud service platform; the marketing platform comprises a product display module, a product recommendation module, a product transaction module, a product retrieval module and a user information management module; the marketing platform faces to the client and is used for displaying products and collecting information;
the client is used for bearing a marketing platform and comprises a mobile phone or tablet computer app client and a PC webpage client;
the cloud service platform comprises a terminal server and a cloud server; the marketing platform is in real-time data connection with the cloud server; the terminal server comprises a big data storage module, a big data analysis module and a big data pushing module;
the big data analysis module establishes a user purchase model by matching the customer characteristics and the consumption behavior characteristics, and grades the products in the product display module and the products in the product recommendation module respectively according to the user purchase model;
the big data pushing module combines and sorts the products of different levels to form a product data combined package, and pushes the product data combined package to a marketing platform; and setting a threshold value for dividing the product display module and the product recommendation module by the big data analysis module, and adjusting the frequency of the product data combination packet pushed to the marketing platform through real-time data exchange between the marketing platform and the cloud service platform.
2. The big data analysis-based e-commerce marketing system of claim 1, wherein: the product display module comprises n-level page display, wherein 1 ≦ n ≦ 3.
3. The big data analysis-based e-commerce marketing system of claim 1, wherein: the big data storage module comprises transaction data, a browsing log, a searching log, user information data, product display keyword data and product characteristic information; transaction data, browsing logs, searching logs and user information data collected by the marketing platform are subjected to data exchange in real time and stored in the big data storage module; and inputting product characteristic information through a marketing platform background, displaying keyword data of the product, and storing the keyword data in a big data storage module.
4. The big data analysis-based e-commerce marketing system of claim 1, wherein: cleaning and eliminating the big data through a big data analysis module; based on the big data user portrait and transaction data, browsing logs, searching logs, and extracting client features and consumption behavior features; constructing a user purchase model for displaying the product in the product display module on a page, and setting an initial display level p as level 1; extracting keywords of purchased products according to purchasing habits of customers, then performing correlation matching of the keywords of the purchased products to obtain initial recommended keyword products, and setting the level q of the initial recommended keyword products as level 1.
5. The big-data-analysis-based e-commerce marketing system of claim 4, wherein: based on the customer characteristics and the consumption behavior characteristics, products meeting the requirements are set to be in a level 1 display level, the products are displayed by a product display module and a product recommendation module, and the level 1 recommended keyword products are displayed by the product recommendation module.
6. The big-data-analysis-based e-commerce marketing system of claim 4, wherein: setting the threshold value of the browsing times of the products in the product display module and the product recommendation module as n1 and the threshold value of the browsing time of the products as m 1; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; and comparing the browsing log data with a product browsing time threshold n1 and a product browsing time threshold m1 respectively, and adjusting the display level p +1 when the comparison result is less than n1 and less than m 1.
7. The big-data-analysis-based e-commerce marketing system of claim 4, wherein: setting a threshold value of the browsing times of the products in the product recommending module as n2 and a threshold value of the browsing time of the products as m 2; calling a browsing log of the product, wherein the browsing log comprises data such as browsing times and browsing time of the product; and comparing the browsing log data with a product browsing frequency threshold n2 and a product browsing time threshold m2 respectively, and adjusting the recommended keyword product level q +1 when the comparison result is smaller than n2 and smaller than m 2.
8. The big-data-analysis-based e-commerce marketing system of claim 4, wherein: the product recommending module is used for displaying products screened based on the user purchasing model and products screened based on the recommended keywords; setting products positioned at the front three and the rear three of the product recommending module as products with a display level p; products in the middle of the product recommendation module are randomly arranged for products of a display level p and products of a recommended keyword product level q.
9. The big-data-analysis-based e-commerce marketing system of claim 8, wherein: comparing the browsing logs of the products of the recommended keyword product level q through a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the recommended keyword product display time t is not less than 150min, matching the product information of the recommended keyword product to the behavior characteristics of consumers; and the recommended keyword products are marked as products with the display level p.
10. The big-data-analysis-based e-commerce marketing system of claim 8, wherein: comparing the browsing logs of the products of the recommended keyword product level q through a big data analysis module; setting recommended keyword product display time as t; after the level q is adjusted, when the display time t of the recommended keyword product is less than or equal to 30min and q =5, the display of the recommended keyword product is eliminated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111309.4A CN113570421A (en) | 2021-09-23 | 2021-09-23 | E-commerce marketing system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111309.4A CN113570421A (en) | 2021-09-23 | 2021-09-23 | E-commerce marketing system based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113570421A true CN113570421A (en) | 2021-10-29 |
Family
ID=78174072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111111309.4A Pending CN113570421A (en) | 2021-09-23 | 2021-09-23 | E-commerce marketing system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570421A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114201680A (en) * | 2021-12-13 | 2022-03-18 | 中数通信息有限公司 | Method for recommending marketing product content to user |
| CN116805254A (en) * | 2023-08-22 | 2023-09-26 | 深圳市感恩网络科技有限公司 | Product marketing state evaluation system based on big data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218719A (en) * | 2012-01-19 | 2013-07-24 | 阿里巴巴集团控股有限公司 | Method and system of e-commerce website navigation |
| WO2017122936A1 (en) * | 2016-01-15 | 2017-07-20 | 전자부품연구원 | Method for producing and distributing promotional materials on basis of small business promotional strategy, and device therefor |
| CN108615182A (en) * | 2018-05-09 | 2018-10-02 | 广州链通互联网科技有限公司 | A kind of method and system that product intelligent is recommended |
| CN109584018A (en) * | 2018-12-04 | 2019-04-05 | 雄商网络科技（上海）有限公司 | A kind of internet marketing cloud service platform |
| CN111652648A (en) * | 2020-06-03 | 2020-09-11 | 陈包容 | Method for intelligently generating personalized combined promotion scheme and system with same |
| CN111831891A (en) * | 2019-04-18 | 2020-10-27 | 第四范式（北京）技术有限公司 | Material recommendation method and system |
| CN112862530A (en) * | 2021-02-09 | 2021-05-28 | 江之龙 | Marketing system based on big data |
| CN113256369A (en) * | 2021-05-08 | 2021-08-13 | 徐州工业职业技术学院 | E-commerce marketing system based on big data analysis |
-
2021
- 2021-09-23 CN CN202111111309.4A patent/CN113570421A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218719A (en) * | 2012-01-19 | 2013-07-24 | 阿里巴巴集团控股有限公司 | Method and system of e-commerce website navigation |
| WO2017122936A1 (en) * | 2016-01-15 | 2017-07-20 | 전자부품연구원 | Method for producing and distributing promotional materials on basis of small business promotional strategy, and device therefor |
| CN108615182A (en) * | 2018-05-09 | 2018-10-02 | 广州链通互联网科技有限公司 | A kind of method and system that product intelligent is recommended |
| CN109584018A (en) * | 2018-12-04 | 2019-04-05 | 雄商网络科技（上海）有限公司 | A kind of internet marketing cloud service platform |
| CN111831891A (en) * | 2019-04-18 | 2020-10-27 | 第四范式（北京）技术有限公司 | Material recommendation method and system |
| CN111652648A (en) * | 2020-06-03 | 2020-09-11 | 陈包容 | Method for intelligently generating personalized combined promotion scheme and system with same |
| CN112862530A (en) * | 2021-02-09 | 2021-05-28 | 江之龙 | Marketing system based on big data |
| CN113256369A (en) * | 2021-05-08 | 2021-08-13 | 徐州工业职业技术学院 | E-commerce marketing system based on big data analysis |
Non-Patent Citations (1)
| Title |
|---|
| 易静: "《跨境电商实务操作教程》", 30 June 2017, 武汉：武汉大学出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114201680A (en) * | 2021-12-13 | 2022-03-18 | 中数通信息有限公司 | Method for recommending marketing product content to user |
| CN116805254A (en) * | 2023-08-22 | 2023-09-26 | 深圳市感恩网络科技有限公司 | Product marketing state evaluation system based on big data |
| CN116805254B (en) * | 2023-08-22 | 2023-12-22 | 深圳市感恩网络科技有限公司 | Product marketing state evaluation system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11301868B2 (en) | Method for predictive analytics for finding related array entries | |
| Liao et al. | Investigating online social media users’ behaviors for social commerce recommendations | |
| US6968315B1 (en) | Method and apparatus for advertising over a communications network | |
| CN108009897A (en) | A kind of real-time recommendation method of commodity, system and readable storage medium storing program for executing | |
| CN106934498A (en) | The recommendation method and system of hotel's house type in OTA websites | |
| CN108280128A (en) | A kind of method and apparatus of displaying personal page | |
| CN113570421A (en) | E-commerce marketing system based on big data analysis | |
| CN107332910A (en) | Information-pushing method and device | |
| CN111899047A (en) | Resource recommendation method and device, computer equipment and computer-readable storage medium | |
| CN108228579A (en) | Network interaction system | |
| WO2022095701A1 (en) | Method and device for recommending objects, equipment, and storage medium | |
| Mokhtarian et al. | Trivariate probit models of pre-purchase/purchase shopping channel choice: Clothing purchases in Northern California | |
| JP6976207B2 (en) | Information processing equipment, information processing methods, and programs | |
| CN107301592A (en) | The method and device excavated for commodity substitute | |
| Bartók et al. | Online grocery shopping: the customers' perspective in the Czech Republic | |
| Yue et al. | Marketing organic and conventional potatoes in Germany | |
| CN110378770A (en) | A kind of method and device that e-commerce operation selects money to recommend | |
| CN112258301B (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation system, readable storage medium and electronic equipment | |
| CN113689259A (en) | Commodity personalized recommendation method and system based on user behaviors | |
| CN116645141B (en) | Multi-dimensional feature-fused chain store site selection recommendation method | |
| CN115496566A (en) | Regional specialty recommendation method and system based on big data | |
| CN115760202A (en) | Product operation management system and method based on artificial intelligence | |
| CN113298568A (en) | Method and device for delivering advertisements | |
| CN106529692A (en) | Intelligent network ordering platform | |
| JPWO2020031232A1 (en) | Information processing system, information processing method, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211029 |