CN112102037A - Live E-commerce platform commodity content intelligent pushing management system based on big data - Google Patents
Live E-commerce platform commodity content intelligent pushing management system based on big data Download PDFInfo
- Publication number
- CN112102037A CN112102037A CN202010975882.9A CN202010975882A CN112102037A CN 112102037 A CN112102037 A CN 112102037A CN 202010975882 A CN202010975882 A CN 202010975882A CN 112102037 A CN112102037 A CN 112102037A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- module
- transaction
- characteristic
- 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.)
- Granted
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
Abstract
The invention discloses a big data-based intelligent pushing management system for commodity contents of a live telecommuter platform, which comprises a keyword searching and screening module, a commodity characteristic parameter dividing and extracting module, a user similar transaction information acquiring and analyzing module, a characteristic parameter correlation matching module, a commodity monthly sales amount extracting module, a commodity goodness of evaluation statistical analysis module, a commodity comprehensive pushing sequence analysis module and a background pushing module, wherein each commodity which accords with commodity keywords is screened from the live telecommuter platform by inputting the commodity keywords, the total correlation degree, monthly sales amount and goodness of each commodity with the deviation of a user are counted to obtain the comprehensive pushing coefficient of each commodity, and then the commodities pushed by the platform are pushed to be matched with the deviation of the user according to the comprehensive pushing coefficient of each commodity in a sequence from large to small, so that the experience of the user is enhanced, the user is prevented from spending a large amount of time to search the commodities which are matched with the deviation, the user's preferential shopping demand is satisfied.
Description
Technical Field
The invention belongs to the technical field of E-commerce platform management, and particularly relates to a live E-commerce platform commodity content intelligent pushing management system based on big data.
Background
With the improvement of the permeability of mobile shopping, the traditional e-commerce platform looks at the change from increment to stock competition, the whole flow rate is reduced, the customer acquisition cost is increased, and the appearance of live broadcast e-commerce breaks through the current situations that consumers cannot see, touch and feel commodities to a great extent.
When people shop on a live E-commerce platform, a series of commodities matched with input commodity keywords can be pushed by a platform background by inputting the commodity keywords into a search box on the platform. However, commodities pushed by the existing live telecommuter platform cannot be pushed according to the deviation of a user, the intelligent level is not high, the user needs to spend a large amount of time to search commodities matched with the deviation of the pushed commodities from the pushed commodities, the shopping interest of people is influenced, the user experience is poor, and in order to enhance the user experience, the intelligent push management system for the commodity contents of the live telecommuter platform based on big data is designed.
Disclosure of Invention
The invention aims to provide a big-data-based live broadcast e-commerce platform commodity content intelligent pushing management system, which screens commodities which accord with commodity keywords from a live broadcast e-commerce platform by inputting the commodity keywords, counts the total association degree, monthly sales volume and favorable rating of the commodities with the deviation of a user to obtain the comprehensive pushing coefficient of the commodities, orders the commodities from large to small according to the comprehensive pushing coefficient of the commodities, pushes the commodities to a search interface of the live broadcast e-commerce platform according to the ordering, and solves the problems mentioned in the background technology.
The purpose of the invention can be realized by the following technical scheme:
an intelligent pushing management system for commodity contents of a live telecommerce platform based on big data comprises a keyword searching and screening module, a commodity characteristic parameter dividing and extracting module, a user similar transaction information acquiring and analyzing module, a characteristic parameter correlation matching module, a commodity monthly sales amount extracting module, a commodity goodness of evaluation statistical analysis module, a commodity comprehensive pushing sequence analyzing module and a background pushing module, wherein the keyword searching and screening module is respectively connected with the commodity characteristic parameter dividing and extracting module, the commodity monthly sales amount extracting module and the commodity goodness of evaluation statistical analysis module, the characteristic parameter correlation matching module is respectively connected with the commodity characteristic parameter dividing and extracting module and the user similar transaction information acquiring and analyzing module, the commodity comprehensive pushing sequence analyzing module is respectively connected with the characteristic parameter correlation matching module, the commodity monthly sales amount extracting module and the commodity goodness of evaluation statistical analysis module, the background pushing module is connected with the commodity comprehensive pushing sequence analysis module;
the keyword searching and screening module is used for screening commodities which accord with the commodity keywords from a plurality of live broadcast commodities on a live broadcast E-commerce platform by inputting the commodity keywords into a search box of the live broadcast E-commerce platform, numbering a plurality of screened commodities in a preset sequence, and sequentially marking the commodities as 1,2.
The commodity characteristic parameter division and extraction module is used for dividing each characteristic parameter of the commodity types represented by the commodity key words, extracting the self characteristics corresponding to each characteristic parameter from the live detailed contents of the commodities according to each characteristic parameter divided by the commodity type of each numbered commodity, wherein the self characteristics corresponding to each characteristic parameter of each extracted commodity form a commodity characteristic set Gi(gi1,gi2,...,gij,...,gim)，gij represents the self characteristic corresponding to the jth characteristic parameter of the ith commodity, and the commodity characteristic parameter dividing and extracting module sends each commodity characteristic set formed by the self characteristics corresponding to various characteristic parameters of each extracted commodity to the characteristic parameter association matching module;
the user similar transaction information acquisition and analysis module is used for screening out transaction commodity information consistent with input commodity keywords from all transaction information of a user in a login account of the live telecast platform and analyzing the deviation characteristics of the user, and comprises a similar transaction information acquisition module and a transaction information characteristic analysis module, wherein the process of acquiring the transaction information by the similar transaction information acquisition module is as follows:
s1, calculating a screening end time point: calculating a screening finishing time point according to a preset time period and a current time point;
s2, acquiring transaction information in a preset time period: acquiring all transaction information of the user under the user login account, extracting the transaction completion time of each transaction of the user, comparing the extracted transaction completion time of each transaction of the user with the calculated screening end time point, judging whether the transaction completion time of each transaction of the user is before the screening end time point, retaining the transaction information of the transaction completion time before the screening end time point, and removing the transaction information of the transaction completion time after the screening end time point;
s3, transaction commodity type information extraction: counting transaction times of the acquired user transaction information in a preset time period, and extracting the commodity type of each transaction;
s4: and (3) commodity type matching: comparing and matching the extracted commodity type of each transaction of the user with the commodity key words, judging whether the commodity type is consistent with the commodity key words, retaining transaction information of the commodity type consistent with the commodity key words according to a judgment result, and arranging the retained transaction information of each transaction according to the sequence of transaction completion time;
the transaction information characteristic analysis module is used for extracting self characteristics corresponding to all characteristic parameters of the transaction commodities from the reserved transaction information of each time, analyzing user deviation characteristics corresponding to all the characteristic parameters according to the self characteristics corresponding to all the characteristic parameters of the transaction commodities in the extracted transaction information, and sending the user deviation characteristics corresponding to all the analyzed characteristic parameters to the characteristic parameter association matching module;
the characteristic parameter association matching module receives each commodity characteristic set sent by the commodity characteristic parameter division and extraction module, receives user deviation characteristics corresponding to each characteristic parameter of commodities sent by the user similar transaction information acquisition and analysis module, arranges each characteristic parameter of each commodity in each received commodity characteristic set, selects self characteristics corresponding to a single characteristic parameter of one commodity each time according to sequence to be matched with the user deviation characteristics corresponding to the same characteristic parameter, if the self characteristics are consistent and the matching is successful, the characteristic parameter of the commodity is associated with the user deviation, the association degree is xi, if the self characteristics are inconsistent and the matching is failed, the characteristic parameter of the commodity is not associated with the user deviation, the next characteristic parameter matching of the commodity is continued, the total association degree of the commodity and the user deviation is counted, and after the total association degree of the commodity and the user deviation is counted, calculating the total association degree of the next commodity with the user deviation to further obtain the total association degree of each commodity in each commodity feature set with the user deviation, and simultaneously sending the statistical result to a commodity comprehensive pushing sequence analysis module;
the commodity monthly sales extraction module extracts commodity monthly sales from the live detailed contents of the commodities selected by the keyword search screening module, obtains the monthly sales of the commodities and sends the monthly sales to the commodity comprehensive pushing sequence analysis module;
the commodity good evaluation rate statistical analysis module is used for counting the total effective evaluation number of the commodities and the good evaluation number of the commodities from the commodity evaluation of the commodities screened by the keyword search screening module, further calculating the good evaluation rate of the commodities to obtain the good evaluation rate of each commodity, and sending the good evaluation rate to the commodity comprehensive pushing sequence analysis module;
the commodity comprehensive pushing sequence analysis module receives the total association degree of each commodity and user deviation sent by the characteristic parameter association matching module, receives the monthly sales amount of each commodity sent by the commodity monthly sales amount extraction module, receives the good evaluation rate of each commodity sent by the commodity good evaluation rate statistical analysis module, carries out commodity comprehensive pushing coefficient statistics, and arranges each commodity according to the commodity comprehensive pushing coefficient of each commodity counted and the sequence of the commodity comprehensive pushing coefficient from large to small;
and the background pushing module is used for pushing each commodity arranged by the commodity comprehensive pushing sequence analysis module to a live telecast platform interface according to the arrangement sequence.
As a preferred technical scheme, the commodity screening process of screening the commodity conforming to the commodity key words by the key word searching and screening module through inputting the commodity key words comprises the following steps:
h1: extracting a commodity name from each commodity on a live broadcast e-commerce platform;
h2: the system background carries out character recognition on the input commodity keywords and the name of each commodity on the live E-commerce platform, if all the commodity keywords are recognized in a certain commodity name, the commodity is reserved, and if the commodity keywords are not recognized or only partial commodity keywords are recognized in the certain commodity name, the step H3 is executed;
h3: and removing the commodity, and identifying the next commodity name and the commodity key word.
As a preferred technical scheme, in the commodity type matching step of the similar transaction information acquisition module, in the process of judging whether the commodity type of each transaction of the user is consistent with the commodity keyword, if the commodity type of each transaction of the user is inconsistent with the commodity keyword, it is indicated that all transaction information in a preset time period of the user is not associated with the commodity keyword, and then, the operation of the transaction information characteristic analysis module and the characteristic parameter association matching module is not performed.
As a preferred technical scheme, if the number of times of the reserved user transaction information is only once in the process of extracting self characteristic analysis user deviation characteristics corresponding to each characteristic parameter of the transaction commodity from the reserved user transaction information in each transaction information in the transaction information characteristic analysis module, the self characteristics corresponding to each characteristic parameter of the transaction commodity in the extracted transaction information are taken as the user deviation characteristics; if the number of times of the reserved user transaction information is more than one, executing the following user deviation characteristic analysis steps:
w1: counting the reserved transaction times of the users, sequentially extracting self characteristics corresponding to each characteristic parameter of commodities of each transaction, selecting one characteristic parameter each time, comparing the self characteristics corresponding to the commodities of each transaction under the extracted characteristic parameters, judging whether the same self characteristics exist or not, if the same self characteristics do not exist, indicating that the characteristic parameters do not have user deviation, not performing association matching of the characteristic parameters by a subsequent characteristic parameter association matching module, executing step W4, if the same self characteristics exist, counting the number of the same self characteristics, if the same self characteristics only have one, executing step W2, if the same self characteristics have a plurality, marking each same self characteristic as a candidate user deviation characteristic, and executing step W3;
w2: the same self characteristics are used as user deviation characteristics under the commodity characteristic parameters;
w3: counting transaction times corresponding to the candidate user deviation features, and screening the candidate user deviation features with the largest transaction times as user deviation features;
w4: and performing user biased characteristic analysis on the next characteristic parameter according to the sequence of W1-W3 until all the characteristic parameters of the commodity are analyzed.
As a preferred technical scheme, the calculation formula of the total association degree of the commodity and the user preference is etai＝kiξ，ηiExpressed as the total degree of association, k, of the ith item with the user's biasiThe number of characteristic parameters, k, of the product, which is expressed as the association between the ith product and the user's preferencei＝1,2...j....m。
As a preferred technical scheme, the method for counting the total effective evaluation number of the commodity in the commodity good evaluation rate statistical analysis module is to count the total evaluation number of the commodity and remove the invalid evaluation number to obtain the total effective evaluation number.
As a preferred technical scheme, the calculation formula of the good evaluation rate of the commodities is
σiExpressed as the good rating, p, of the ith goodGood tastei is the number of good evaluations of the ith commodity, pGeneral assemblyi is expressed as the total effective evaluation number of the ith commodity.
As the preferred technical scheme, the calculation formula of the commodity comprehensive push coefficient is
Expressed as the overall push coefficient, S, for the ith goodiThe monthly sales volume of the ith commodity is shown, and a, b and c are respectively shown as a pushing influence coefficient of the total association degree of the commodity and the user bias, a pushing influence coefficient of the monthly sales volume of the commodity and a pushing influence coefficient of the good appraisal rate of the commodity.
The invention has the beneficial effects that:
1. the invention screens each commodity which accords with the key words from a plurality of commodities on a live telecommerce platform by inputting the commodity key words, counts monthly sales volume and favorable rate of each commodity, screens transaction information which is matched with the commodity key words from all transaction information under a user login account number by the input key words, further analyzes user deviation characteristics which correspond to each characteristic parameter of the commodity from the transaction information, simultaneously correlates and matches self characteristics which correspond to each characteristic parameter of each commodity which is screened by the input commodity key words with the user deviation characteristics by a platform background to obtain the total correlation degree of each commodity and the user deviation, counts the comprehensive push coefficient of each commodity by combining a commodity comprehensive push sequence analysis module, sorts and pushes according to the magnitude of the comprehensive push coefficient, and can lead the commodity pushed by the live telecommerce platform to be matched with the user, the intelligent shopping system has the advantages of being high in intelligent level, enhancing the use experience of a user, avoiding the situation that the user spends a large amount of time to search goods matched with the user's deviation, improving the shopping interest of the user, and meeting the user's demand for deviation shopping.
2. According to the invention, by setting a commodity comprehensive pushing coefficient calculation formula and combining the total association degree of the commodity and the user bias, the monthly sales volume of the commodity and the good evaluation rate of the commodity, the comprehensive pushing coefficient of each commodity is counted, the counted comprehensive pushing coefficient not only reflects the association degree of the commodity and the user bias, but also reflects the characteristics of the commodity, and the commodity is sorted and pushed from large to small according to the magnitude of the comprehensive pushing coefficient, so that the singleness of sorting and pushing only by adopting the association degree of the commodity and the user is avoided, and the comprehensiveness of sorting of the pushed commodities is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a block diagram of a system module of the present invention;
FIG. 2 is a flow chart of similar transaction information acquisition module steps of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Please refer to fig. 1-2, a live broadcast e-commerce platform commodity content intelligent push management system based on big data comprises a keyword search screening module, a commodity characteristic parameter division extraction module, a user similar transaction information acquisition and analysis module, a characteristic parameter association matching module, a commodity monthly sales extraction module, a commodity goodness statistical analysis module, a commodity comprehensive push sequence analysis module and a background push module, wherein the keyword search screening module is respectively connected with the commodity characteristic parameter division extraction module, the commodity monthly sales extraction module and the commodity goodness statistical analysis module, the characteristic parameter association matching module is respectively connected with the commodity characteristic parameter division extraction module and the user similar transaction information acquisition and analysis module, the commodity comprehensive push sequence analysis module is respectively connected with the characteristic parameter association matching module, the commodity monthly sales extraction module and the commodity goodness statistical analysis module, the background pushing module is connected with the commodity comprehensive pushing sequence analysis module.
The keyword search screening module is used for screening commodities which accord with the commodity keywords from a plurality of live broadcast commodities on a live broadcast E-commerce platform by inputting the commodity keywords into a search box of the live broadcast E-commerce platform, and the screening process comprises the following steps:
h1: extracting a commodity name from each commodity on a live broadcast e-commerce platform;
h2: the system background carries out character recognition on the input commodity keywords and the name of each commodity on the live E-commerce platform, if all the commodity keywords are recognized in a certain commodity name, the commodity is reserved, and if the commodity keywords are not recognized or only partial commodity keywords are recognized in the certain commodity name, the step H3 is executed;
h3: and removing the commodity, and identifying the next commodity name and the commodity key word.
And numbering a plurality of screened commodities in a preset sequence, wherein the commodities are marked as 1,2.
In this embodiment, the input commodity keyword represents a commodity category, and each commodity screened according to the commodity keyword is each commodity belonging to the commodity category.
The commodity characteristic parameter division and extraction module is used for dividing each characteristic parameter of the commodity types represented by the commodity key words, extracting the self characteristics corresponding to each characteristic parameter from the live detailed contents of the commodities according to each characteristic parameter divided by the commodity type of each numbered commodity, wherein the self characteristics corresponding to each characteristic parameter of each extracted commodity form a commodity characteristic set Gi(gi1,gi2,...,gij,...,gim)，gij is the self-feature corresponding to the jth feature parameter of the ith commodity, and the commodity feature parameter dividing and extracting module sends each commodity feature set formed by the self-features corresponding to the various feature parameters of each extracted commodity to the feature parameter association matching module.
The user similar transaction information acquisition and analysis module is used for screening out transaction commodity information consistent with input commodity keywords from all transaction information of a user in a login account of the live telecast platform and analyzing the deviation characteristics of the user, and comprises a similar transaction information acquisition module and a transaction information characteristic analysis module, wherein the process of acquiring the transaction information by the similar transaction information acquisition module is as follows:
s1, calculating a screening end time point: calculating a screening finishing time point according to a preset time period and a current time point;
s2, acquiring transaction information in a preset time period: acquiring all transaction information of the user under the user login account, extracting the transaction completion time of each transaction of the user, comparing the extracted transaction completion time of each transaction of the user with the calculated screening end time point, judging whether the transaction completion time of each transaction of the user is before the screening end time point, retaining the transaction information of the transaction completion time before the screening end time point, and removing the transaction information of the transaction completion time after the screening end time point;
s3, transaction commodity type information extraction: counting transaction times of the acquired user transaction information in a preset time period, and extracting commodity types of each transaction, wherein the method for extracting the commodity types of the transactions is to extract keywords with commodity type characteristics from transaction commodity names;
s4: and (3) commodity type matching: the extracted commodity types of each transaction of the user are compared and matched with the commodity key words, whether the commodity types of each transaction of the user are consistent or not is judged, if the commodity types of each transaction of the user are not consistent with the commodity key words, all transaction information in a preset time period of the user are not related with the commodity key words, operation of a transaction information characteristic analysis module and a characteristic parameter related matching module is not performed, if the commodity types of a certain transaction are consistent with the commodity key words, the transaction information with the commodity types consistent with the commodity key words is reserved, if the commodity types of a certain transaction are not consistent with the commodity key words, the transaction information is removed, and meanwhile, the reserved transaction information of each transaction is arranged according to the transaction completion time sequence.
In this embodiment, the commodity category is extracted from each transaction information that is retained, and the extracted commodity category is compared with the commodity keyword, and if the extracted commodity category is consistent with the commodity keyword, it indicates that the transaction commodity of the transaction information also belongs to the commodity category represented by the input commodity keyword, and the transaction commodity has all characteristic parameters of the commodity category.
The transaction information characteristic analysis module is used for extracting self characteristics corresponding to each characteristic parameter of the transaction commodity from each piece of reserved transaction information, analyzing user deviation characteristics corresponding to each characteristic parameter according to the self characteristics corresponding to each characteristic parameter of each transaction commodity in each piece of extracted transaction information, and if the number of times of the reserved user transaction information is only one, extracting the self characteristics corresponding to each characteristic parameter of the transaction commodity in the transaction information as the user deviation characteristics; if the number of times of the reserved user transaction information is more than one, executing the following user deviation characteristic analysis steps:
w1: counting the reserved transaction times of the users, sequentially extracting self characteristics corresponding to each characteristic parameter of commodities of each transaction, selecting one characteristic parameter each time, comparing the self characteristics corresponding to the commodities of each transaction under the extracted characteristic parameters, judging whether the same self characteristics exist or not, if the same self characteristics do not exist, indicating that the characteristic parameters do not have user deviation, not performing association matching of the characteristic parameters by a subsequent characteristic parameter association matching module, executing step W4, if the same self characteristics exist, counting the number of the same self characteristics, if the same self characteristics only have one, executing step W2, if the same self characteristics have a plurality, marking each same self characteristic as a candidate user deviation characteristic, and executing step W3;
w2: the same self characteristics are used as user deviation characteristics under the commodity characteristic parameters;
w3: counting transaction times corresponding to the candidate user deviation features, if the transaction times corresponding to the candidate user deviation features are different, screening the candidate user deviation feature with the largest transaction times as the user deviation feature, and if the transaction times corresponding to the candidate user deviation features are the same and the transaction times are different candidate user deviation features with the largest transaction times, indicating that the user has a plurality of deviation features corresponding to the characteristic parameter of the commodity, wherein one candidate user deviation feature can be arbitrarily selected as the user deviation feature under the condition;
w4: and performing user biased characteristic analysis on the next characteristic parameter according to the sequence of W1-W3 until all the characteristic parameters of the commodity are analyzed.
And sending the user deviation characteristics corresponding to the analyzed characteristic parameters to a characteristic parameter association matching module.
The characteristic parameter association matching module receives the commodity characteristic parameter sent by the commodity characteristic parameter division and extraction moduleEach commodity feature set receives user deviation features corresponding to each feature parameter of commodities sent by a user similar transaction information acquisition and analysis module, each feature parameter of each commodity in each received commodity feature set is arranged, self features corresponding to a single feature parameter of each commodity are selected in sequence each time to be matched with user deviation features corresponding to the same feature parameter, if the self features are consistent and indicate that matching is successful, the feature parameter of the commodity is associated with the user deviation, the association degree is recorded as xi, if the self features are inconsistent and indicate that matching is failed, the feature parameter of the commodity is not associated with the user deviation, next feature parameter matching of the commodity is continued, therefore, the total association degree of the commodity and the user deviation is counted, and after the total association degree of the commodity and the user deviation is counted, the total association degree of the next commodity and the user deviation is calculated, further obtaining the total association degree eta of each commodity in each commodity feature set and the user deviationi＝kiξ，ηiExpressed as the total degree of association, k, of the ith item with the user's biasiThe number of characteristic parameters, k, of the product, which is expressed as the association between the ith product and the user's preferenceiAnd (1, 2.. j.. m), the characteristic parameter association matching module sends the statistical result to the commodity comprehensive pushing sequence analysis module.
The commodity monthly sales extraction module extracts commodity monthly sales from the live detailed contents of the commodities selected by the keyword search screening module, obtains the monthly sales of the commodities, and sends the monthly sales to the commodity comprehensive pushing sequence analysis module.
The commodity good evaluation rate statistical analysis module is used for counting the total effective evaluation number and the commodity good evaluation number of a plurality of commodities screened by the keyword search screening module from the commodity evaluation, wherein the method for counting the total effective evaluation number of the commodities is to count the total evaluation number of the commodities and remove the ineffective evaluation number to obtain the total effective evaluation number, and then the commodity good evaluation rate is calculated to obtain the good evaluation rate of each commodity
σiExpressed as the good rating, p, of the ith goodGood tastei is the number of good evaluations of the ith commodity, pGeneral assemblyAnd i represents the total effective evaluation number of the ith commodity, and the commodity good evaluation rate statistical analysis module sends the counted good evaluation rate of each commodity to the commodity comprehensive pushing sequence analysis module.
The commodity comprehensive pushing sequence analysis module receives the total association degree of each commodity and the user deviation sent by the characteristic parameter association matching module, receives the monthly sales amount of each commodity sent by the commodity monthly sales amount extraction module, receives the good appraisal rate of each commodity sent by the commodity good appraisal rate statistical analysis module, and counts the commodity comprehensive pushing coefficient
Expressed as the overall push coefficient, S, for the ith goodiThe commodity display method is characterized in that the commodity display method comprises the steps of displaying monthly sales volume of the ith commodity, displaying a pushing influence coefficient of the total association degree of the commodity and a user bias, a pushing influence coefficient of the monthly sales volume of the commodity and a pushing influence coefficient of good appraisal rate of the commodity, and arranging the commodities according to the counted magnitude of the comprehensive commodity pushing coefficient of the commodities in the order from large to small of the comprehensive commodity pushing coefficient.
According to the embodiment, by setting a calculation formula of the comprehensive commodity pushing coefficient, the comprehensive pushing coefficient of each commodity is counted by combining the total association degree of the commodity and the user deviation, the monthly sales volume of the commodity and the good commodity rating, the counted comprehensive pushing coefficient not only reflects the association degree of the commodity and the user deviation, but also reflects the quality of the commodity, and the commodities are sorted and pushed from large to small according to the size of the comprehensive pushing coefficient, the commodities arranged in front are high in association degree with the user deviation, the quality of the commodities is high, the singleness of sorting and pushing only by adopting the association degree of the commodity and the user is avoided, and the comprehensiveness of sorting of the pushed commodities is improved.
The background pushing module is used for pushing commodities arranged by the commodity comprehensive pushing sequence analysis module to the live telecast platform interface according to the arrangement sequence, and a user can select the commodities with satisfactory quality and deviation only by browsing the commodities arranged in front of the live telecast platform interface, so that the condition that the user spends a large amount of time to search the commodities matched with the deviation of the user is avoided, the use experience of the user is enhanced, the shopping interest of the user is improved, and the biased shopping requirement of the user is met.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (8)
1. The utility model provides a live electricity merchant platform commodity content intelligence propelling movement management system based on big data which characterized in that: comprises a keyword searching and screening module, a commodity characteristic parameter dividing and extracting module, a user similar transaction information acquiring and analyzing module, a characteristic parameter correlation matching module, a commodity monthly sales extracting module, a commodity good evaluation rate statistical analyzing module, a commodity comprehensive pushing sequence analyzing module and a background pushing module, the system comprises a keyword searching and screening module, a commodity characteristic parameter dividing and extracting module, a commodity monthly sales amount extracting module and a commodity good appraisal rate statistical analysis module, wherein the keyword searching and screening module is respectively connected with the commodity characteristic parameter dividing and extracting module, the commodity monthly sales amount extracting module and the commodity good appraisal rate statistical analysis module;
the keyword searching and screening module is used for screening commodities which accord with the commodity keywords from a plurality of live broadcast commodities on a live broadcast E-commerce platform by inputting the commodity keywords into a search box of the live broadcast E-commerce platform, numbering a plurality of screened commodities in a preset sequence, and sequentially marking the commodities as 1,2.
The commodity characteristic parameter dividing and extracting module is used for representing commodity key wordsThe method comprises the steps of dividing each characteristic parameter of the commodity type, extracting self characteristics corresponding to each characteristic parameter from the live detailed contents of the commodities of the numbered commodities according to the various characteristic parameters divided by the commodity type, wherein the self characteristics corresponding to the various characteristic parameters of each extracted commodity form a commodity characteristic set Gi(gi1,gi2,...,gij,...,gim)，gij represents the self characteristic corresponding to the jth characteristic parameter of the ith commodity, and the commodity characteristic parameter dividing and extracting module sends each commodity characteristic set formed by the self characteristics corresponding to various characteristic parameters of each extracted commodity to the characteristic parameter association matching module;
the user similar transaction information acquisition and analysis module is used for screening out transaction commodity information consistent with input commodity keywords from all transaction information of a user in a login account of the live telecast platform and analyzing the deviation characteristics of the user, and comprises a similar transaction information acquisition module and a transaction information characteristic analysis module, wherein the process of acquiring the transaction information by the similar transaction information acquisition module is as follows:
s1, calculating a screening end time point: calculating a screening finishing time point according to a preset time period and a current time point;
s2, acquiring transaction information in a preset time period: acquiring all transaction information of the user under the user login account, extracting the transaction completion time of each transaction of the user, comparing the extracted transaction completion time of each transaction of the user with the calculated screening end time point, judging whether the transaction completion time of each transaction of the user is before the screening end time point, retaining the transaction information of the transaction completion time before the screening end time point, and removing the transaction information of the transaction completion time after the screening end time point;
s3, transaction commodity type information extraction: counting transaction times of the acquired user transaction information in a preset time period, and extracting the commodity type of each transaction;
s4: and (3) commodity type matching: comparing and matching the extracted commodity type of each transaction of the user with the commodity key words, judging whether the commodity type is consistent with the commodity key words, retaining transaction information of the commodity type consistent with the commodity key words according to a judgment result, and arranging the retained transaction information of each transaction according to the sequence of transaction completion time;
the transaction information characteristic analysis module is used for extracting self characteristics corresponding to all characteristic parameters of the transaction commodities from the reserved transaction information of each time, analyzing user deviation characteristics corresponding to all the characteristic parameters according to the self characteristics corresponding to all the characteristic parameters of the transaction commodities in the extracted transaction information, and sending the user deviation characteristics corresponding to all the analyzed characteristic parameters to the characteristic parameter association matching module;
the characteristic parameter association matching module receives each commodity characteristic set sent by the commodity characteristic parameter division and extraction module, receives user deviation characteristics corresponding to each characteristic parameter of commodities sent by the user similar transaction information acquisition and analysis module, arranges each characteristic parameter of each commodity in each received commodity characteristic set, selects self characteristics corresponding to a single characteristic parameter of one commodity each time according to sequence to be matched with the user deviation characteristics corresponding to the same characteristic parameter, if the self characteristics are consistent and the matching is successful, the characteristic parameter of the commodity is associated with the user deviation, the association degree is xi, if the self characteristics are inconsistent and the matching is failed, the characteristic parameter of the commodity is not associated with the user deviation, the next characteristic parameter matching of the commodity is continued, the total association degree of the commodity and the user deviation is counted, and after the total association degree of the commodity and the user deviation is counted, calculating the total association degree of the next commodity with the user deviation to further obtain the total association degree of each commodity in each commodity feature set with the user deviation, and simultaneously sending the statistical result to a commodity comprehensive pushing sequence analysis module;
the commodity monthly sales extraction module extracts commodity monthly sales from the live detailed contents of the commodities selected by the keyword search screening module, obtains the monthly sales of the commodities and sends the monthly sales to the commodity comprehensive pushing sequence analysis module;
the commodity good evaluation rate statistical analysis module is used for counting the total effective evaluation number of the commodities and the good evaluation number of the commodities from the commodity evaluation of the commodities screened by the keyword search screening module, further calculating the good evaluation rate of the commodities to obtain the good evaluation rate of each commodity, and sending the good evaluation rate to the commodity comprehensive pushing sequence analysis module;
the commodity comprehensive pushing sequence analysis module receives the total association degree of each commodity and user deviation sent by the characteristic parameter association matching module, receives the monthly sales amount of each commodity sent by the commodity monthly sales amount extraction module, receives the good evaluation rate of each commodity sent by the commodity good evaluation rate statistical analysis module, carries out commodity comprehensive pushing coefficient statistics, and arranges each commodity according to the commodity comprehensive pushing coefficient of each commodity counted and the sequence of the commodity comprehensive pushing coefficient from large to small;
and the background pushing module is used for pushing each commodity arranged by the commodity comprehensive pushing sequence analysis module to a live telecast platform interface according to the arrangement sequence.
2. The live E-commerce platform commodity content intelligent pushing management system based on big data as claimed in claim 1, wherein: the commodity screening process for screening the commodity according with the commodity key words by the key word searching and screening module through inputting the commodity key words comprises the following steps:
h1: extracting a commodity name from each commodity on a live broadcast e-commerce platform;
h2: the system background carries out character recognition on the input commodity keywords and the name of each commodity on the live E-commerce platform, if all the commodity keywords are recognized in a certain commodity name, the commodity is reserved, and if the commodity keywords are not recognized or only partial commodity keywords are recognized in the certain commodity name, the step H3 is executed;
h3: and removing the commodity, and identifying the next commodity name and the commodity key word.
3. The live E-commerce platform commodity content intelligent pushing management system based on big data as claimed in claim 1, wherein: in the commodity type matching step of the similar transaction information acquisition module, in the process of judging whether the commodity type of each transaction of the user is consistent with the commodity key word, if the commodity type of each transaction of the user is inconsistent with the commodity key word, all transaction information in a preset time period of the user is not associated with the commodity key word, and then the operation of the transaction information characteristic analysis module and the characteristic parameter association matching module is not carried out.
4. The live E-commerce platform commodity content intelligent pushing management system based on big data as claimed in claim 1, wherein: if the times of the reserved user transaction information are only once in the process of extracting the characteristic analysis user deviation characteristics corresponding to each characteristic parameter of the transaction commodity from the reserved user transaction information in the transaction information characteristic analysis module, extracting the self characteristics corresponding to each characteristic parameter of the transaction commodity in the transaction information as the user deviation characteristics; if the number of times of the reserved user transaction information is more than one, executing the following user deviation characteristic analysis steps:
w1: counting the reserved transaction times of the users, sequentially extracting self characteristics corresponding to each characteristic parameter of commodities of each transaction, selecting one characteristic parameter each time, comparing the self characteristics corresponding to the commodities of each transaction under the extracted characteristic parameters, judging whether the same self characteristics exist or not, if the same self characteristics do not exist, indicating that the characteristic parameters do not have user deviation, not performing association matching of the characteristic parameters by a subsequent characteristic parameter association matching module, executing step W4, if the same self characteristics exist, counting the number of the same self characteristics, if the same self characteristics only have one, executing step W2, if the same self characteristics have a plurality, marking each same self characteristic as a candidate user deviation characteristic, and executing step W3;
w2: the same self characteristics are used as user deviation characteristics under the commodity characteristic parameters;
w3: counting transaction times corresponding to the candidate user deviation features, and screening the candidate user deviation features with the largest transaction times as user deviation features;
w4: and performing user biased characteristic analysis on the next characteristic parameter according to the sequence of W1-W3 until all the characteristic parameters of the commodity are analyzed.
5. The live E-commerce platform commodity content intelligent pushing management system based on big data as claimed in claim 1, wherein: the calculation formula of the total association degree of the commodity and the user preference is etai＝kiξ，ηiExpressed as the total degree of association, k, of the ith item with the user's biasiThe number of characteristic parameters, k, of the product, which is expressed as the association between the ith product and the user's preferencei＝1,2...j....m。
6. The live E-commerce platform commodity content intelligent pushing management system based on big data as claimed in claim 1, wherein: the method for counting the total effective evaluation number of the commodity in the commodity good evaluation rate statistical analysis module is to count the total evaluation number of the commodity and remove the invalid evaluation number to obtain the total effective evaluation number.
7. The live E-commerce platform commodity content intelligent pushing management system based on big data as claimed in claim 1, wherein: the good appraisal rate of the commodity is calculated by the following formula
σiExpressed as the good rating, p, of the ith goodGood tastei is the number of good evaluations of the ith commodity, pGeneral assemblyi is expressed as the total effective evaluation number of the ith commodity.
8. The live E-commerce platform commodity content intelligent pushing management system based on big data as claimed in claim 1, wherein: the calculation formula of the commodity comprehensive push coefficient is
Expressed as the overall push coefficient, S, for the ith goodiThe monthly sales volume of the ith commodity is shown, and a, b and c are respectively shown as a pushing influence coefficient of the total association degree of the commodity and the user bias, a pushing influence coefficient of the monthly sales volume of the commodity and a pushing influence coefficient of the good appraisal rate of the commodity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010975882.9A CN112102037B (en) | 2020-09-16 | 2020-09-16 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010975882.9A CN112102037B (en) | 2020-09-16 | 2020-09-16 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112102037A true CN112102037A (en) | 2020-12-18 |
| CN112102037B CN112102037B (en) | 2021-05-07 |
Family
ID=73759499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010975882.9A Active CN112102037B (en) | 2020-09-16 | 2020-09-16 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112102037B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112817951A (en) * | 2021-01-19 | 2021-05-18 | 立梦(上海)企业管理咨询有限公司 | Data analysis method for new media marketing |
| CN112866759A (en) * | 2021-01-08 | 2021-05-28 | 南京浪脆电子商务有限公司 | E-commerce live broadcast platform based on deep learning and cloud computing and cloud communication server |
| CN113744020A (en) * | 2021-01-15 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Commodity file processing method and device, electronic equipment and storage medium |
| CN114663237A (en) * | 2022-04-07 | 2022-06-24 | 武汉卓诺世环电子商务有限公司 | Data acquisition and analysis method and equipment based on online transaction platform and computer storage medium |
| CN115033799A (en) * | 2022-07-04 | 2022-09-09 | 武汉历历晴川网络科技有限公司 | Commodity searching method, system and storage medium |
| WO2022220738A1 (en) * | 2021-04-15 | 2022-10-20 | Grabtaxi Holdings Pte. Ltd. | Communications server apparatus, method and communications system for providing a recommendation of offerings by merchants to a user |
| CN116528010A (en) * | 2023-03-24 | 2023-08-01 | 广州市原象信息科技有限公司 | Live broadcast cargo-carrying service scheduling recommendation method and system |
| CN116957709A (en) * | 2023-06-05 | 2023-10-27 | 上海朗晖慧科技术有限公司 | Manifest transaction management system and method based on digital cloud platform |
| CN117135379A (en) * | 2023-10-26 | 2023-11-28 | 武汉耳东信息科技有限公司 | Live broadcast platform data analysis management system based on big data |
| CN117541275A (en) * | 2024-01-09 | 2024-02-09 | 深圳市微购科技有限公司 | Intelligent terminal commodity sales management system based on cloud technology |
| CN117788123A (en) * | 2024-02-23 | 2024-03-29 | 南京简亿网络科技有限公司 | Personalized shopping guide system for electronic commerce |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035927A (en) * | 2013-03-05 | 2014-09-10 | 百度在线网络技术（北京）有限公司 | User behavior-based search method and system |
| CN104317945A (en) * | 2014-10-31 | 2015-01-28 | 亚信科技（南京）有限公司 | E-commerce website commodity recommending method on basis of search behaviors |
| CN104881807A (en) * | 2015-06-26 | 2015-09-02 | 陆健 | Method and device for recommending goods information |
| CN108320213A (en) * | 2018-01-31 | 2018-07-24 | 深圳春沐源控股有限公司 | Electric business Method of Commodity Recommendation and electric business Platform Server |
| CN108614832A (en) * | 2016-12-12 | 2018-10-02 | 苏宁云商集团股份有限公司 | A kind of user individual commercial articles searching implementation method and device |
| CN109189904A (en) * | 2018-08-10 | 2019-01-11 | 上海中彦信息科技股份有限公司 | Individuation search method and system |
| US20190098352A1 (en) * | 2017-09-22 | 2019-03-28 | WooJu JUNG | Method of recommending personal broadcasting contents |
| CN109636545A (en) * | 2018-12-26 | 2019-04-16 | 广州市耀锋电子网络科技有限公司 | A kind of electric business platform commercial product recommending algorithm |
| CN111310019A (en) * | 2018-12-11 | 2020-06-19 | 阿里巴巴集团控股有限公司 | Information recommendation method, information processing method, system and equipment |
| CN111429203A (en) * | 2020-03-02 | 2020-07-17 | 北京明略软件系统有限公司 | Commodity recommendation method and device based on user behavior data |
-
2020
- 2020-09-16 CN CN202010975882.9A patent/CN112102037B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035927A (en) * | 2013-03-05 | 2014-09-10 | 百度在线网络技术（北京）有限公司 | User behavior-based search method and system |
| CN104317945A (en) * | 2014-10-31 | 2015-01-28 | 亚信科技（南京）有限公司 | E-commerce website commodity recommending method on basis of search behaviors |
| CN104881807A (en) * | 2015-06-26 | 2015-09-02 | 陆健 | Method and device for recommending goods information |
| CN108614832A (en) * | 2016-12-12 | 2018-10-02 | 苏宁云商集团股份有限公司 | A kind of user individual commercial articles searching implementation method and device |
| US20190098352A1 (en) * | 2017-09-22 | 2019-03-28 | WooJu JUNG | Method of recommending personal broadcasting contents |
| KR101983635B1 (en) * | 2017-09-22 | 2019-05-29 | 정우주 | A method of recommending personal broadcasting contents |
| CN108320213A (en) * | 2018-01-31 | 2018-07-24 | 深圳春沐源控股有限公司 | Electric business Method of Commodity Recommendation and electric business Platform Server |
| CN109189904A (en) * | 2018-08-10 | 2019-01-11 | 上海中彦信息科技股份有限公司 | Individuation search method and system |
| CN111310019A (en) * | 2018-12-11 | 2020-06-19 | 阿里巴巴集团控股有限公司 | Information recommendation method, information processing method, system and equipment |
| CN109636545A (en) * | 2018-12-26 | 2019-04-16 | 广州市耀锋电子网络科技有限公司 | A kind of electric business platform commercial product recommending algorithm |
| CN111429203A (en) * | 2020-03-02 | 2020-07-17 | 北京明略软件系统有限公司 | Commodity recommendation method and device based on user behavior data |
Non-Patent Citations (2)
| Title |
|---|
| RAJESH SHUKLA ET AL.: "An Improved Recommendation Approach based on User"s Standard and Interests", 《INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS》 * |
| 石雁: "基于查询偏好的个性化搜索引擎的研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112866759A (en) * | 2021-01-08 | 2021-05-28 | 南京浪脆电子商务有限公司 | E-commerce live broadcast platform based on deep learning and cloud computing and cloud communication server |
| CN113744020A (en) * | 2021-01-15 | 2021-12-03 | 北京沃东天骏信息技术有限公司 | Commodity file processing method and device, electronic equipment and storage medium |
| CN112817951A (en) * | 2021-01-19 | 2021-05-18 | 立梦(上海)企业管理咨询有限公司 | Data analysis method for new media marketing |
| WO2022220738A1 (en) * | 2021-04-15 | 2022-10-20 | Grabtaxi Holdings Pte. Ltd. | Communications server apparatus, method and communications system for providing a recommendation of offerings by merchants to a user |
| CN114663237A (en) * | 2022-04-07 | 2022-06-24 | 武汉卓诺世环电子商务有限公司 | Data acquisition and analysis method and equipment based on online transaction platform and computer storage medium |
| CN115033799A (en) * | 2022-07-04 | 2022-09-09 | 武汉历历晴川网络科技有限公司 | Commodity searching method, system and storage medium |
| CN115033799B (en) * | 2022-07-04 | 2023-01-17 | 郑州易赛诺信息技术有限公司 | Commodity searching method, system and storage medium |
| CN116528010B (en) * | 2023-03-24 | 2024-03-19 | 广州市原象信息科技有限公司 | Live broadcast cargo-carrying service scheduling recommendation method and system |
| CN116528010A (en) * | 2023-03-24 | 2023-08-01 | 广州市原象信息科技有限公司 | Live broadcast cargo-carrying service scheduling recommendation method and system |
| CN116957709A (en) * | 2023-06-05 | 2023-10-27 | 上海朗晖慧科技术有限公司 | Manifest transaction management system and method based on digital cloud platform |
| CN116957709B (en) * | 2023-06-05 | 2024-04-23 | 上海朗晖慧科技术有限公司 | Manifest transaction management system and method based on digital cloud platform |
| CN117135379A (en) * | 2023-10-26 | 2023-11-28 | 武汉耳东信息科技有限公司 | Live broadcast platform data analysis management system based on big data |
| CN117135379B (en) * | 2023-10-26 | 2023-12-22 | 武汉耳东信息科技有限公司 | Live broadcast platform data analysis management system based on big data |
| CN117541275A (en) * | 2024-01-09 | 2024-02-09 | 深圳市微购科技有限公司 | Intelligent terminal commodity sales management system based on cloud technology |
| CN117788123A (en) * | 2024-02-23 | 2024-03-29 | 南京简亿网络科技有限公司 | Personalized shopping guide system for electronic commerce |
| CN117788123B (en) * | 2024-02-23 | 2024-04-30 | 南京简亿网络科技有限公司 | Personalized shopping guide system for electronic commerce |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112102037B (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112102037B (en) | Live E-commerce platform commodity content intelligent pushing management system based on big data | |
| CN110415087B (en) | Electronic commerce transaction system based on internet | |
| CN107146089B (en) | Method and device for identifying bill swiping and electronic equipment | |
| CN113034238B (en) | Commodity brand feature extraction and intelligent recommendation management method based on electronic commerce platform transaction | |
| CN104077407B (en) | A kind of intelligent data search system and method | |
| JP2000003394A (en) | Personal merchandising system | |
| CN101661487A (en) | Method and system for searching information items | |
| CN111667337A (en) | Commodity evaluation ordering method and system | |
| CN116757794A (en) | Big data-based product recommendation method in wine selling applet | |
| CN111915409A (en) | Article recommendation method, device and equipment based on article and storage medium | |
| CN116431931A (en) | Real-time incremental data statistical analysis method | |
| CN112417284A (en) | Method and device for pushing display information | |
| CN116739836B (en) | Restaurant data analysis method and system based on knowledge graph | |
| CN113129078A (en) | Social software advertisement information delivery method based on feature recognition and data visualization analysis | |
| CN107944946B (en) | Commodity label generation method and device | |
| CN107766229B (en) | Method for evaluating correctness of commodity search system by using metamorphic test | |
| CN112070552A (en) | Electronic commerce platform based on big data | |
| CN110968670A (en) | Method, device, equipment and storage medium for acquiring attributes of popular commodities | |
| CN115033799B (en) | Commodity searching method, system and storage medium | |
| TWI626609B (en) | Production method and system for personal product and vaccine purchase combination | |
| CN115563176A (en) | Electronic commerce data processing system and method | |
| CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
| CN116091162A (en) | E-commerce commodity recommendation method and device | |
| CN115115403A (en) | Method and device for classifying customers in target customer group, electronic equipment and storage medium | |
| CN115131108A (en) | E-commerce commodity screening system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210423 Address after: Room 101, building 19, Tianan headquarters center, 555 Panyu Avenue North, Donghuan street, Panyu District, Guangzhou, Guangdong 511400 Applicant after: GUANGZHOU YIDEJIA NETWORK TECHNOLOGY Co.,Ltd. Address before: 223300 No. 111 Changjiang West Road, Huaiyin District, Jiangsu, Huaian Applicant before: Tang Tao |