CN115545828A - E-commerce data push analysis system based on artificial intelligence - Google Patents
E-commerce data push analysis system based on artificial intelligence Download PDFInfo
- Publication number
- CN115545828A CN115545828A CN202211175364.4A CN202211175364A CN115545828A CN 115545828 A CN115545828 A CN 115545828A CN 202211175364 A CN202211175364 A CN 202211175364A CN 115545828 A CN115545828 A CN 115545828A
- Authority
- CN
- China
- Prior art keywords
- commerce
- product
- push
- user
- purchase
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an e-commerce data pushing analysis system based on artificial intelligence, belongs to the field of e-commerce, and solves the problems that a commodity pushing page of an existing e-commerce platform is uniform in style, the number of pushed commodities is uniform, and an e-commerce data pushing mechanism is not optimized enough.
Description
Technical Field
The invention relates to the technical field of electronic commerce, in particular to an electronic commerce data pushing and analyzing system based on artificial intelligence.
Background
Electronic commerce is called e-commerce for short, and refers to transaction activities and related service activities performed in an electronic transaction mode on the internet, an intranet and a value-added network, so that each link of the traditional business activities is electronized and networked. Electronic commerce includes electronic money exchanges, supply chain management, electronic trading markets, network marketing, online transactions, electronic data exchanges, inventory management, and automated data collection systems. In this process, information technologies utilized include: internet, extranet, email, database, electronic directory and mobile phone.
Some commodity propelling movement pages often can appear in the E-commerce platform, and the most unified style of commodity propelling movement page, and propelling movement commodity figure is all unified, and when the commodity propelling movement is not conform to the user's demand, do not have corresponding perfect and improve, E-commerce data propelling movement mechanism is not enough optimized, consequently lacks an E-commerce data propelling movement analytic system based on artificial intelligence and solves the problem that above-mentioned exists.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an e-commerce data pushing and analyzing system based on artificial intelligence.
The technical problem to be solved by the invention is as follows:
how to push matched e-commerce data for a user based on e-commerce behaviors, and how to judge and analyze an e-commerce pushing effect after e-commerce pushing and perform intelligent adjustment.
In order to achieve the purpose, the invention is realized by the following technical scheme:
an e-commerce data pushing and analyzing system based on artificial intelligence comprises a user terminal, an e-commerce pushing module, a product analyzing module, a data collecting module, an intelligent adjusting module, a conversion analyzing module, a user behavior analyzing module and an e-commerce platform, wherein the data collecting module is used for collecting e-commerce behavior data of a user and sending the e-commerce behavior data to the e-commerce platform, and the e-commerce platform sends the e-commerce behavior data to the user behavior analyzing module; the user behavior analysis module is used for analyzing the e-commerce behavior of the user in the e-commerce platform to obtain the purchase level of the user and feeding the purchase level back to the e-commerce platform, and the e-commerce platform obtains e-commerce push parameters of the user according to the purchase level and sends the e-commerce push parameters to the e-commerce push module;
after the purchase level of the user is obtained, the data acquisition module is used for acquiring e-commerce product data of the user and sending the e-commerce product data to an e-commerce platform, and the e-commerce platform sends the e-commerce product data to the product analysis module; the product analysis module is used for analyzing the hot degree condition of the e-commerce products of the user to obtain product recommendation values of the e-commerce products of different product types of the user and feeding the product recommendation values back to the e-commerce platform, and the e-commerce platform sends the product recommendation values of the e-commerce products of different product types of the user to the e-commerce pushing module; the e-commerce pushing module is used for pushing e-commerce data adaptive to the user, pushing an e-commerce pushing package of the user to feed back to the e-commerce platform, the e-commerce platform sends the e-commerce pushing package of the user to the user terminal, and the user terminal end clicks the e-commerce pushing package to browse;
after the user terminal checks and browses the e-commerce push package, the data acquisition module is used for acquiring push purchase quantity and push collection quantity of products in the e-commerce push package corresponding to push types of the e-commerce products and sending the push purchase quantity and the push collection quantity to the e-commerce platform, and the e-commerce platform sends the push purchase quantity and the push collection quantity to the conversion analysis module;
the conversion analysis module is used for analyzing the conversion condition of the E-commerce push package and analyzing to generate a conversion effective signal or a conversion ineffective signal; the intelligent adjustment module is used for intelligently adjusting the e-commerce push package of the user.
Further, the e-commerce behavior data comprise the purchase times of the e-commerce products, the purchase time and the browsing times of each purchase, the browsing duration of each browsing and the collection number of the e-commerce products;
the e-commerce push parameters specifically comprise the number of product push types and the number of e-commerce products of each product push type;
the e-commerce product data specifically comprises product types of e-commerce products purchased by users in the e-commerce platform, product types of collected e-commerce products, purchase amount and collection amount of different product types;
the push purchase amount and the push collection amount are the real-time purchase amount and the real-time collection amount of the product push type after the user terminal browses the e-commerce push package.
Further, the analysis process of the user behavior analysis module is specifically as follows:
acquiring the purchase times of e-commerce products of a user and the collection times of the e-commerce products of the user in an e-commerce platform;
then, acquiring the purchasing time of each purchasing of the E-commerce products, calculating the time difference value of adjacent purchasing times to obtain a plurality of groups of purchasing interval time lengths, and adding and summing the plurality of groups of purchasing interval time lengths to divide the purchasing times to obtain the purchasing interval average time length of the E-commerce products of the user;
similarly, the browsing times and the corresponding browsing duration of the e-commerce product of the user are obtained, and the browsing duration of each browsing is added and summed up and divided by the browsing times to obtain the browsing average duration of the e-commerce product of the user;
and calculating the user purchase value of the user in the E-commerce platform, comparing the user purchase value with the user purchase threshold value, and judging that the purchase grade of the user is a third purchase grade, a second purchase grade or a first purchase grade.
Further, the purchase value of the user is in direct proportion to the purchase grade, and when the purchase value of the user is larger, the purchase grade of the user is higher;
the first purchase level is rated higher than the second purchase level, which is rated higher than the third purchase level.
Further, the analysis process of the product analysis module is specifically as follows:
acquiring product types of a user purchasing e-commerce products and collecting e-commerce products in the e-commerce platform;
dividing the electric fan products into corresponding product type sets according to the product types, and then counting the purchase quantity and the collection quantity of the product types in the product type sets;
and calculating the product recommendation values of the E-commerce products of different product types of the user.
Further, the pushing process of the e-commerce pushing module specifically comprises the following steps:
obtaining product recommendation values and e-commerce push parameters of different product types of e-commerce products of a user;
obtaining a product type recommendation table of the user E-commerce products in a descending order according to the numerical value of the product recommendation value;
selecting the number of the corresponding product push types and the number of e-commerce products of each product push type in a product type recommendation table according to e-commerce push parameters;
and selecting the obtained product pushing type number and the e-commerce product number of each product pushing type, and integrating to generate an e-commerce pushing package of the user.
Further, the analysis process of the transformation analysis module is specifically as follows:
according to the product pushing type in the e-commerce pushing package, acquiring the purchase amount and the collection amount of the product pushing type before e-commerce pushing and the pushing purchase amount and the pushing collection amount of the product pushing type after e-commerce pushing;
the purchase increment of different product push types is obtained by subtracting the purchase amount from the push purchase amount, and similarly, the collection increment of different product push types is obtained by subtracting the collection amount from the push collection amount;
distributing corresponding weight coefficients for the purchase increment and the collection increment respectively, and calculating to obtain product conversion values of different product push types after being pushed by the e-commerce;
if the product conversion value of any product push type in the E-commerce push package exceeds a set threshold value, generating a conversion effective signal;
and if the product conversion values of all the product push types in the E-commerce push package do not exceed the set threshold value, generating a conversion invalid signal.
Further, the conversion analysis module feeds back the effective conversion signal or the ineffective conversion signal to the server, if the server receives the effective conversion signal, no operation is performed, and if the server receives the ineffective conversion signal, a push adjustment instruction is generated and loaded to the intelligent adjustment module.
Further, the working process of the intelligent adjustment module is as follows:
and removing E-commerce products corresponding to the current product push type in the E-commerce push package, then reselecting the number of the product push types according with E-commerce push parameters and the number of the E-commerce products of each product push type from top to bottom in a product type recommendation table, and simultaneously integrating and generating a new E-commerce push package and re-pushing the new E-commerce push package to a corresponding user terminal.
Meanwhile, a working method of the e-commerce data pushing and analyzing system based on artificial intelligence is also provided, and the working method specifically comprises the following steps:
step S100, a user behavior analysis module analyzes the e-commerce behavior of a user in an e-commerce platform to obtain the purchase level of the user, and the e-commerce platform obtains e-commerce push parameters of the user according to the purchase level and sends the e-commerce push parameters to an e-commerce push module;
s200, analyzing the popularity condition of the e-commerce products of the user by using a product analysis module to obtain product recommendation values of the e-commerce products of different product types of the user, and sending the product recommendation values to an e-commerce pushing module;
step S300, the e-commerce pushing module is used for pushing e-commerce data adapted to the user to obtain an e-commerce pushing package of the user and sending the e-commerce pushing package to the user terminal;
step S400, after the user terminal clicks the E-commerce push package, analyzing the conversion condition of the E-commerce push package by using a conversion analysis module, and analyzing to generate a conversion effective signal or a conversion ineffective signal;
and S500, if the conversion invalid signal is generated, intelligently adjusting the e-commerce push package of the user through an intelligent adjustment module, adjusting to regenerate the e-commerce push package and pushing the e-commerce push package to the user terminal.
Compared with the prior art, the invention has the following beneficial effects:
the e-commerce behavior of the user in the e-commerce platform is analyzed through the user behavior analysis module to obtain the purchase grade of the user, then the e-commerce platform obtains e-commerce push parameters of the user according to the purchase grade and sends the e-commerce push parameters to the e-commerce push module, meanwhile, the product analysis module is used for analyzing the heat degree condition of e-commerce products of the user to obtain product recommendation values of e-commerce products of different product types of the user and send the product recommendation values to the e-commerce push module, and the e-commerce push module is used for pushing e-commerce data adaptive to the user to obtain an e-commerce push packet of the user and send the e-commerce push packet to a user terminal;
after the user terminal clicks the E-commerce push package, the conversion analysis module is used for analyzing the conversion condition of the E-commerce push package, a conversion effective signal or a conversion invalid signal is generated through analysis, if the conversion invalid signal is generated, the E-commerce push package of the user is intelligently adjusted through the intelligent adjustment module, the E-commerce push package is generated again through adjustment and pushed to the user terminal.
Advantages of additional aspects of the invention will be set forth in part in the description of the embodiments which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is an overall system block diagram of the present invention;
fig. 2 is a flow chart of the present invention.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention.
The embodiments and features of the embodiments of the invention may be combined with each other without conflict.
Example one
Referring to fig. 1, the invention provides an e-commerce data pushing and analyzing system based on artificial intelligence, which comprises a user terminal, an e-commerce pushing module, a product analysis module, a data acquisition module, an intelligent adjustment module, a conversion analysis module, a user behavior analysis module and an e-commerce platform, wherein the e-commerce pushing module is used for pushing and analyzing e-commerce data;
in specific implementation, the user terminal is used for registering and logging in the system after a user inputs personal information and sending the personal information to the e-commerce platform for storage; the personal information comprises the real name, the sex, the identification card number, the age and the like of the user;
specifically, the user terminal is a private mobile phone, a tablet computer, a desktop computer, and the like of the user;
meanwhile, after the authorization of the user terminal is agreed, the data acquisition module is used for acquiring the e-commerce behavior data of the user and sending the e-commerce behavior data to the e-commerce platform, and the e-commerce platform sends the e-commerce behavior data to the user behavior analysis module;
specifically, the e-commerce behavior data includes the purchase times of e-commerce products, the purchase time and browsing times of each purchase, the browsing duration of each browsing, the collection number of e-commerce products, and the like;
the user behavior analysis module is used for analyzing the e-commerce behavior of the user in the e-commerce platform, and the analysis process specifically comprises the following steps:
step S1, marking a user corresponding to the user terminal as i, i =1,2, \8230;, z, z are positive integers;
s2, acquiring the purchase times of the E-commerce products of the user, and marking the purchase times as GCi; then obtaining the purchasing time of each time of purchasing the E-commerce products, calculating the time difference value of adjacent purchasing times to obtain a plurality of groups of purchasing interval time lengths, and adding and summing the plurality of groups of purchasing interval time lengths to divide the purchasing times to obtain the purchasing interval average time length GJTi of the E-commerce products of the users;
s3, similarly, acquiring the browsing times and the corresponding browsing duration of the E-commerce product of the user, and adding and summing the browsing durations of each browsing and dividing the sum by the browsing times to obtain the browsing average duration LJTi of the E-commerce product of the user;
s4, finally acquiring the collection number of the E-commerce products of the user in the E-commerce platform, and marking the collection number of the E-commerce products as SCi;
step S5, calculating a user purchase value YGi of the user in the e-commerce platform through a formula YGi = (GCi × a1+ SCi × a2+ LJTi × a 3)/GJTi; in the formula, a1, a2 and a3 are proportionality coefficients with fixed numerical values, and the values of a1, a2 and a3 are all larger than zero;
s6, comparing the user purchase value with a user purchase threshold value;
if YGi < X1, the purchase level of the user is the third purchase level;
if the X1 is not more than YGi and less than X2, the purchase level of the user is a second purchase level;
if X2 is less than or equal to YGi, the purchase level of the user is the first purchase level; wherein X1 and X2 are both fixed numerical values of user purchase threshold, and X1 is less than X2;
it can be understood that the user purchase value is in direct proportion to the purchase level, when the user purchase value of the user is larger, the purchase level of the user is higher, therefore, the level of the first purchase level is higher than that of the second purchase level, and the level of the second purchase level is higher than that of the third purchase level;
the user behavior analysis module feeds back the purchase grade of the user to the e-commerce platform, and the e-commerce platform obtains e-commerce push parameters of the user according to the purchase grade and sends the e-commerce push parameters to the e-commerce push module;
the e-commerce push parameters specifically include the number of product push types and the number of e-commerce products of each product push type, for example, when a user is at a first purchase level, the number of product push types is 3 groups, the number of e-commerce products of each group is 10, when the user is at a second purchase level, the number of product push types is 2 groups, the number of e-commerce products of each group is 8, when the user is at a third purchase level, the number of product push types is 1 group, and the number of e-commerce products of each group is 6;
after the purchase level of the user is obtained, the data acquisition module is used for acquiring e-commerce product data of the user and sending the e-commerce product data to an e-commerce platform, and the e-commerce platform sends the e-commerce product data to the product analysis module;
specifically, the e-commerce product data is specific to a product type of an e-commerce product purchased by a user in an e-commerce platform, a product type of a collected e-commerce product, purchase amount and collection amount of different product types, and the like;
the product analysis module is used for analyzing the hot degree condition of the e-commerce product of the user, and the analysis process is as follows:
s101, acquiring product types of a user purchasing e-commerce products and collecting e-commerce products in an e-commerce platform;
step S102, dividing the fan products into corresponding product type sets according to the product types, and then counting the purchase quantity and the collection quantity of the product types in the product type sets;
step S103, calculating by using a combination formula to obtain the product recommendation values of the e-commerce products of different product types of the user, wherein the formula is as follows:
CTu = LGu × b1+ LCu × b2; in the formula, b1 and b2 are both weight coefficients with fixed numerical values, and the values of b1 and b2 are both larger than zero, wherein u represents the product type of the e-commerce product, LGu is the purchase quantity of the e-commerce product with different product types, and LCu is the collection quantity of the e-commerce product with different product types;
the product analysis module feeds back product recommendation values of e-commerce products of different product types of the user to the e-commerce platform, and the e-commerce platform sends the product recommendation values of the e-commerce products of different product types of the user to the e-commerce push module;
the e-commerce pushing module is used for pushing e-commerce data adapted to the user, and the pushing process specifically comprises the following steps:
step S201, obtaining the product recommendation values and E-commerce push parameters of the E-commerce products of different product types of the user obtained through calculation;
step S202, obtaining a product type recommendation table of the user E-commerce products in a descending order according to the numerical value of the product recommendation value;
step S203, selecting the number of the corresponding product push types and the number of the E-commerce products of each product push type in a product type recommendation table according to the E-commerce push parameters;
step S204, selecting the obtained product push type number and the E-commerce product number of each product push type to integrate and generate an E-commerce push package of the user;
the e-commerce pushing module feeds back an e-commerce pushing package of a user to the e-commerce platform, the e-commerce platform sends the e-commerce pushing package of the user to the user terminal, and the user terminal clicks the e-commerce pushing package to browse;
specifically, the e-commerce push package appears as follows during specific pushing: when the e-commerce platform App is opened, the pop-up window jumps out of a push page, the number of the push page is the same as the number of the product push types, and the number of e-commerce products on each page in the push page is the same as the number of the e-commerce products in each group;
after the user terminal checks and browses the e-commerce push package, the data acquisition module is used for acquiring the push purchase quantity and the push collection quantity of the product push type corresponding to the e-commerce product in the e-commerce push package, feeding the push purchase quantity and the push collection quantity back to the e-commerce platform, and the e-commerce platform sends the push purchase quantity and the push collection quantity to the conversion analysis module;
the pushed purchase quantity and the pushed collection quantity are the real-time purchase quantity and the real-time collection quantity of the product pushing type after the user terminal browses the E-commerce pushing package;
the conversion analysis module is used for analyzing the conversion condition of the e-commerce push package, and the analysis process is as follows:
step S301, acquiring purchase quantity and collection quantity of a product push type before E-commerce push and push purchase quantity and push collection quantity of the product push type after E-commerce push according to the product push type in the E-commerce push package;
step S302, the purchase increment of different product push types is obtained by subtracting the purchase amount from the pushed purchase amount, and similarly, the collection increment of different product push types is obtained by subtracting the collection amount from the pushed collection amount;
step S303, distributing corresponding weight coefficients for the purchase increment and the collection increment respectively, and calculating to obtain product conversion values of different product pushing types after being pushed by the e-commerce;
step S304, if the product conversion value of any product push type in the E-commerce push package exceeds a set threshold value, generating a conversion effective signal;
if the product conversion values of all product push types in the E-commerce push package do not exceed a set threshold value, generating a conversion invalid signal;
the conversion analysis module feeds back a conversion effective signal or a conversion invalid signal to the server, if the server receives the conversion effective signal, no operation is carried out, and if the server receives the conversion invalid signal, a push adjustment instruction is generated and loaded to the intelligent adjustment module;
the intelligent adjustment module is used for carrying out intelligent adjustment on the E-commerce push package of the user after receiving the intelligent adjustment instruction, and specifically comprises the following steps:
removing e-commerce products corresponding to the current product push type in the e-commerce push package, then reselecting the number of the product push types according with the e-commerce push parameters and the number of the e-commerce products of each product push type from top to bottom in a product type recommendation table, and simultaneously integrating and generating a new e-commerce push package and re-pushing the new e-commerce push package to a corresponding user terminal;
the above formulas are all calculated by taking the numerical value of the dimension, the formula is a formula of the latest real situation obtained by collecting a large amount of data and performing software simulation, the preset parameters in the formula are set by the technicians in the field according to the actual situation, if the weight coefficient and the scale coefficient exist, the set size is a specific numerical value obtained by quantizing each parameter, the subsequent comparison is convenient, and as for the size of the weight coefficient and the scale coefficient, the proportional relation between the parameter and the quantized numerical value is not influenced.
Example two
Referring to fig. 2, based on another concept of the present invention, a working method of an artificial intelligence-based e-commerce data push analysis system is provided, which specifically includes:
step S100, a data acquisition module acquires e-commerce behavior data of a user and sends the e-commerce behavior data to an e-commerce platform, the e-commerce platform sends the e-commerce behavior data to a user behavior analysis module, the e-commerce behavior of the user in the e-commerce platform is analyzed through the user behavior analysis module, the user corresponding to a user terminal is marked as i, the purchase times GCi of the e-commerce product of the user are acquired, then the purchase time of the e-commerce product each time is acquired, the time difference of adjacent purchase times is calculated to obtain a plurality of groups of purchase interval durations, the purchase interval durations are added and summed up and divided by the purchase times to obtain the purchase interval average duration GJTi of the e-commerce product of the user, and similarly, the browsing times and the corresponding browsing duration of the e-commerce product of the user are acquired, adding and summing the browsing time duration of each browsing, dividing the browsing time duration by the browsing frequency to obtain the browsing average time duration LJTi of the e-commerce product of the user, finally obtaining the collection number SCi of the e-commerce product of the user in an e-commerce platform, calculating a user purchase value YGi of the user in the e-commerce platform through a formula YGi = (GCi × a1+ SCi × a2+ LJTi × a 3)/GJTi, comparing the user purchase value with a user purchase threshold value, if YGi is less than X1, the purchase level of the user is a third purchase level, if X1 is less than YGi and less than X2, the purchase level of the user is a second purchase level, if X2 is less than YGi, the purchase level of the user is a first purchase level, feeding back the purchase level of the user to the e-commerce platform by the user behavior analysis module, and sending the e-commerce platform to the e-commerce push parameter of the user according to the purchase level to the e-commerce push module;
step S200, after the purchase level of a user is obtained, a data acquisition module acquires e-commerce product data of the user and sends the e-commerce product data to an e-commerce platform, the e-commerce platform sends the e-commerce product data to a product analysis module, the product analysis module analyzes the heat condition of the e-commerce product of the user to obtain the product types of the e-commerce product purchased by the user and the e-commerce product collected by the user in the e-commerce platform, an electric fan product is divided into corresponding product type sets according to the product types, then the purchase quantity and the collection quantity of the product types in the product type sets are counted, the product recommendation values CTu of the e-commerce products of different product types of the user are obtained by calculation according to a combination formula CTu = LGu x b1+ LCu x b2, the product analysis module feeds the product recommendation values of the e-commerce products of different product types of the user back to the e-commerce platform, and the e-commerce platform sends the product recommendation values of the e-commerce products of different product types of the user to an e-commerce push module;
step S300, the e-commerce pushing module is used for pushing e-commerce data adaptive to a user, obtaining product recommendation values and e-commerce pushing parameters of different product types of e-commerce products of the user, obtaining a product type recommendation table of the e-commerce products of the user according to descending order of the numerical values of the product recommendation values, selecting corresponding product pushing type numbers and e-commerce product numbers of each product pushing type in the product type recommendation table according to the e-commerce pushing parameters, integrating the selected product pushing type numbers and the e-commerce product numbers of each product pushing type to generate an e-commerce pushing package of the user, feeding the e-commerce pushing package of the user back to the e-commerce platform by the e-commerce pushing module, sending the e-commerce pushing package of the user to a user terminal by the e-commerce platform, and browsing after the e-commerce pushing package is opened by the user terminal point;
step S400, after a user terminal checks and browses an e-commerce push package, a data acquisition module acquires a push purchase amount and a push collection amount of a product push type corresponding to an e-commerce product in the e-commerce push package, and feeds the push purchase amount and the push collection amount back to an e-commerce platform, the e-commerce platform sends the push purchase amount and the push collection amount to a conversion analysis module, the conversion analysis module is used for analyzing the conversion condition of the e-commerce push package, according to the product push type in the e-commerce push package, the purchase amount and the collection amount of the product push type before e-commerce push and the push purchase amount and the push collection amount of the product push type after e-commerce push are acquired, according to the product push type in the e-commerce push package, the purchase increase amount and the push collection amount of different product push types are acquired, similarly, the collection amount and the collection amount of different product push types are acquired by subtracting the collection amount to acquire the increase amount of different product push types, corresponding weight coefficients are respectively allocated to the purchase amount and subtract the purchase amount to acquire the purchase increase amount of different product push types, and invalid push conversion signal values of the push conversion package, if the push conversion signal is not generated, and the push signal is generated by the e-commerce server, and the push conversion server, if the invalid conversion module is not generated, the push conversion module, the invalid conversion module, the push conversion module is generated, and the push signal is generated, and the invalid conversion server, and the push signal is generated;
and S500, after receiving the intelligent adjustment instruction, the intelligent adjustment module is used for intelligently adjusting the e-commerce push package of the user, eliminating the e-commerce products corresponding to the current product push type in the e-commerce push package, then reselecting the number of the product push types according with the e-commerce push parameters and the number of the e-commerce products of each product push type from top to bottom in the product type recommendation table, and simultaneously integrating and generating a new e-commerce push package and re-pushing the new e-commerce push package to the corresponding user terminal.
In the embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied in the medium. The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: those skilled in the art can still make modifications or changes to the embodiments described in the foregoing embodiments, or make equivalent substitutions for some features, within the scope of the disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (9)
1. An e-commerce data pushing analysis system based on artificial intelligence is characterized by comprising a user terminal, an e-commerce pushing module, a product analysis module, a data acquisition module, an intelligent adjustment module, a conversion analysis module, a user behavior analysis module and an e-commerce platform, wherein the data acquisition module is used for acquiring e-commerce behavior data of a user and sending the e-commerce behavior data to the e-commerce platform, and the e-commerce platform sends the e-commerce behavior data to the user behavior analysis module; the user behavior analysis module is used for analyzing the e-commerce behavior of the user in the e-commerce platform to obtain the purchase level of the user and feeding the purchase level back to the e-commerce platform, and the e-commerce platform obtains e-commerce push parameters of the user according to the purchase level and sends the e-commerce push parameters to the e-commerce push module;
after the purchase level of the user is obtained, the data acquisition module is used for acquiring e-commerce product data of the user and sending the e-commerce product data to the e-commerce platform, and the e-commerce platform sends the e-commerce product data to the product analysis module; the product analysis module is used for analyzing the hot degree condition of the e-commerce products of the user to obtain product recommendation values of the e-commerce products of different product types of the user and feeding the product recommendation values back to the e-commerce platform, and the e-commerce platform sends the product recommendation values of the e-commerce products of different product types of the user to the e-commerce pushing module; the e-commerce pushing module is used for pushing e-commerce data adaptive to the user, feeding back an e-commerce pushing package of the pushed user to the e-commerce platform, sending the e-commerce pushing package of the user to the user terminal by the e-commerce platform, and browsing after the e-commerce pushing package is started by the user terminal point;
after the user terminal checks and browses the e-commerce push package, the data acquisition module is used for acquiring the push purchase quantity and the push collection quantity of the e-commerce products corresponding to the product push types in the e-commerce push package and sending the push purchase quantity and the push collection quantity to the e-commerce platform, and the e-commerce platform sends the push purchase quantity and the push collection quantity to the conversion analysis module;
the conversion analysis module is used for analyzing the conversion condition of the E-commerce push package and analyzing to generate a conversion effective signal or a conversion ineffective signal; the intelligent adjustment module is used for intelligently adjusting the E-business push package of the user.
2. The artificial intelligence-based e-commerce data push analysis system according to claim 1, wherein e-commerce behavior data is the number of purchases of e-commerce products and the purchase time, browsing times, browsing duration and e-commerce product collection number of each purchase;
the e-commerce push parameters specifically comprise the number of product push types and the number of e-commerce products of each product push type;
the e-commerce product data specifically comprises product types of e-commerce products purchased by users in the e-commerce platform, product types of collected e-commerce products, purchase amount and collection amount of different product types;
the push purchase amount and the push collection amount are real-time purchase amount and real-time collection amount of the product push type after the user terminal browses the e-commerce push package.
3. The system for pushing and analyzing E-commerce data based on artificial intelligence of claim 1, wherein the analysis process of the user behavior analysis module is as follows:
acquiring the purchase times of the E-commerce products of the user and the collection times of the E-commerce products of the user in an E-commerce platform;
then, acquiring the purchasing time of each purchasing of the E-commerce products, calculating the time difference value of adjacent purchasing times to obtain a plurality of groups of purchasing interval time lengths, and adding and summing the plurality of groups of purchasing interval time lengths to divide the purchasing times to obtain the purchasing interval average time length of the E-commerce products of the user;
similarly, the browsing times and the corresponding browsing duration of the e-commerce product of the user are obtained, and the browsing duration of each browsing is added and summed up and divided by the browsing times to obtain the browsing average duration of the e-commerce product of the user;
and calculating the user purchase value of the user in the E-commerce platform, comparing the user purchase value with the user purchase threshold value, and judging that the purchase grade of the user is a third purchase grade, a second purchase grade or a first purchase grade.
4. The artificial intelligence based e-commerce data push analysis system of claim 3, wherein the user purchase value is proportional to the purchase level, and when the user purchase value of the user is larger, the purchase level of the user is higher;
the first purchase level is rated higher than the second purchase level, which is rated higher than the third purchase level.
5. The system for pushing and analyzing E-commerce data based on artificial intelligence of claim 1, wherein the analysis process of the product analysis module is as follows:
acquiring product types of a user purchasing e-commerce products and collecting e-commerce products in an e-commerce platform;
dividing the fan products into corresponding product type sets according to the product types, and then counting the purchase amount and the collection amount of the product types in the product type sets;
and calculating the product recommendation values of the E-commerce products of different product types of the user.
6. The system for pushing and analyzing e-commerce data based on artificial intelligence of claim 1, wherein the pushing process of the e-commerce pushing module is specifically as follows:
obtaining product recommendation values and e-commerce push parameters of e-commerce products of different product types of a user;
obtaining a product type recommendation table of the user e-commerce products in a descending order according to the numerical value of the product recommendation value;
selecting the number of the corresponding product push types and the number of e-commerce products of each product push type in a product type recommendation table according to e-commerce push parameters;
and selecting the obtained product pushing type number and the e-commerce product number of each product pushing type, and integrating to generate an e-commerce pushing package of the user.
7. The system for pushing and analyzing E-commerce data based on artificial intelligence of claim 1, wherein the analysis process of the transformation analysis module is as follows:
according to the product pushing type in the e-commerce pushing package, acquiring the purchase amount and the collection amount of the product pushing type before e-commerce pushing and the pushing purchase amount and the pushing collection amount of the product pushing type after e-commerce pushing;
the purchase increment of different product push types is obtained by subtracting the purchase amount from the push purchase amount, and similarly, the collection increment of different product push types is obtained by subtracting the collection amount from the push collection amount;
distributing corresponding weight coefficients for the purchase increment and the collection increment respectively, and calculating to obtain product conversion values of different product pushing types after being pushed by the e-commerce;
if the product conversion value of any product push type in the E-commerce push package exceeds a set threshold value, generating a conversion effective signal;
and if the product conversion values of all the product push types in the E-commerce push package do not exceed the set threshold value, generating a conversion invalid signal.
8. The system according to claim 7, wherein the conversion analysis module feeds back a conversion valid signal or a conversion invalid signal to the server, and if the server receives the conversion valid signal, no operation is performed, and if the server receives the conversion invalid signal, a push adjustment command is generated and loaded to the intelligent adjustment module.
9. The e-commerce data push analysis system based on artificial intelligence of claim 1, wherein the intelligent adjustment module specifically comprises the following working processes:
and eliminating the e-commerce products corresponding to the current product push type in the e-commerce push package, then reselecting the number of the product push types according with the e-commerce push parameters and the number of the e-commerce products of each product push type from top to bottom in the product type recommendation table, and simultaneously integrating and generating a new e-commerce push package and re-pushing the new e-commerce push package to the corresponding user terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211175364.4A CN115545828A (en) | 2022-09-26 | 2022-09-26 | E-commerce data push analysis system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211175364.4A CN115545828A (en) | 2022-09-26 | 2022-09-26 | E-commerce data push analysis system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115545828A true CN115545828A (en) | 2022-12-30 |
Family
ID=84729542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211175364.4A Pending CN115545828A (en) | 2022-09-26 | 2022-09-26 | E-commerce data push analysis system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545828A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117217787A (en) * | 2023-08-28 | 2023-12-12 | 南京财经大学 | Consumption platform data analysis processing system based on management science |
| CN117236992A (en) * | 2023-11-15 | 2023-12-15 | 北京头条易科技有限公司 | Cross-platform general E-commerce conversion monitoring system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021337A (en) * | 2016-05-09 | 2016-10-12 | 房加科技（北京）有限公司 | A big data analysis-based intelligent recommendation method and system |
| CN110400183A (en) * | 2019-07-31 | 2019-11-01 | 电子科技大学中山学院 | Data analysis system of electronic commerce platform |
| CN113888287A (en) * | 2021-10-22 | 2022-01-04 | 新沂维志途电气工程研究院有限公司 | E-commerce big data deep mining system based on machine learning |
| CN113888286A (en) * | 2021-10-22 | 2022-01-04 | 李静芳 | Internet-based data processing method and system for electronic commerce |
| CN114428897A (en) * | 2020-10-15 | 2022-05-03 | 上海倍增智能科技有限公司 | High-quality product information sharing push system based on big data |
-
2022
- 2022-09-26 CN CN202211175364.4A patent/CN115545828A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021337A (en) * | 2016-05-09 | 2016-10-12 | 房加科技（北京）有限公司 | A big data analysis-based intelligent recommendation method and system |
| CN110400183A (en) * | 2019-07-31 | 2019-11-01 | 电子科技大学中山学院 | Data analysis system of electronic commerce platform |
| CN114428897A (en) * | 2020-10-15 | 2022-05-03 | 上海倍增智能科技有限公司 | High-quality product information sharing push system based on big data |
| CN113888287A (en) * | 2021-10-22 | 2022-01-04 | 新沂维志途电气工程研究院有限公司 | E-commerce big data deep mining system based on machine learning |
| CN113888286A (en) * | 2021-10-22 | 2022-01-04 | 李静芳 | Internet-based data processing method and system for electronic commerce |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117217787A (en) * | 2023-08-28 | 2023-12-12 | 南京财经大学 | Consumption platform data analysis processing system based on management science |
| CN117217787B (en) * | 2023-08-28 | 2024-05-07 | 南京财经大学 | Consumption platform data analysis processing system based on management science |
| CN117236992A (en) * | 2023-11-15 | 2023-12-15 | 北京头条易科技有限公司 | Cross-platform general E-commerce conversion monitoring system and method |
| CN117236992B (en) * | 2023-11-15 | 2024-02-06 | 北京头条易科技有限公司 | Cross-platform general E-commerce conversion monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115545828A (en) | E-commerce data push analysis system based on artificial intelligence | |
| CN108932585B (en) | Merchant operation management method and equipment, storage medium and electronic equipment thereof | |
| CN108256691A (en) | Refund Probabilistic Prediction Model construction method and device | |
| CN104866484A (en) | Data processing method and device | |
| KR102011028B1 (en) | Method for providing shopping mall service compensating margin to seller and customer | |
| CN111523748B (en) | Case distribution method, device and system | |
| CN108388974A (en) | Top-tier customer Optimum Identification Method and device based on random forest and decision tree | |
| CN109636482B (en) | Data processing method and system based on similarity model | |
| CN109583931B (en) | Transaction data processing method, device, electronic equipment and readable storage medium | |
| Shin et al. | Robust multiperiod inventory model considering trade-in program and refurbishment service: Implications to emerging markets | |
| CN111340606A (en) | Full-process income auditing method and device | |
| CN116629937A (en) | Marketing strategy recommendation method and device | |
| CN110232150B (en) | User data analysis method and device, readable storage medium and terminal equipment | |
| CN115510328A (en) | Commodity brand marketing data analysis method based on big data | |
| CN114896506A (en) | Product recommendation method, device, equipment and storage medium | |
| CN111199473A (en) | Anti-cheating method, device and system based on transaction record information | |
| CN113408982B (en) | Inventory management method and system for electronic commerce | |
| CN113095939B (en) | Block chain intelligent contract recommendation method and device | |
| CN114943582A (en) | Information recommendation method and system and recommendation server | |
| CN110544165B (en) | Credit risk score card creating method and device and electronic equipment | |
| CN110020728B (en) | Service model reinforcement learning method and device | |
| CN111667357A (en) | Bank product pushing method and device | |
| CN108346080B (en) | Flow package combination optimization method and device | |
| CN112581295A (en) | Product data processing method, device, equipment and medium based on field splitting | |
| CN111626572A (en) | Digital intelligent wind control method and related product |
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 |