CN112506997B - Big data user mining method based on cross-border e-commerce platform - Google Patents
Big data user mining method based on cross-border e-commerce platform Download PDFInfo
- Publication number
- CN112506997B CN112506997B CN202011466869.7A CN202011466869A CN112506997B CN 112506997 B CN112506997 B CN 112506997B CN 202011466869 A CN202011466869 A CN 202011466869A CN 112506997 B CN112506997 B CN 112506997B
- Authority
- CN
- China
- Prior art keywords
- country
- shopping
- user
- historical
- same
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005065 mining Methods 0.000 title claims abstract description 18
- 238000012216 screening Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Abstract
The invention discloses a big data user mining method based on a cross-border e-commerce platform, which comprises the steps of acquiring the registered country and all historical shopping records of a user on the cross-border e-commerce platform, further constructing a shopping parameter set and a logistics receiving place country set, analyzing the real country and the preferred shopping category of the registered user and the preferred purchasing merchant corresponding to the preferred shopping category according to the shopping parameter set and the logistics receiving place country set, analyzing the optimal preferred purchasing merchant corresponding to the same preferred shopping category by the user in the same country, recommending the optimal preferred purchasing merchant to a new user of which the registered country is the country registered on the cross-border e-commerce platform, reflecting the deep mining of the shopping data of the user, improving the utilization rate of the shopping data of the user, realizing the intelligent recommending function of the registered new user, perfecting the use function of the cross-border e-commerce platform and improving the intelligent level of the cross-border e-commerce platform, the use experience of the user is enhanced.
Description
Technical Field
The invention belongs to the technical field of data processing, relates to an e-commerce platform data processing technology, and particularly relates to a big data user mining method based on a cross-border e-commerce platform.
Background
With the recent dramatic development of network communication and information technology in the world, the traditional business model is changing. Electronic commerce gradually has the leading position of modern commerce, so that a plurality of electronic commerce platforms are born, wherein a cross-border electronic commerce platform is one of the electronic commerce platforms, and the cross-border electronic commerce refers to an international business activity that a transaction subject belongs to different relations, the transaction is achieved through the electronic commerce platform, payment and settlement are carried out, and the transaction is completed by delivering commodities through cross-border logistics. The appearance of the cross-border e-commerce platform not only creates a new growth point for foreign trade in China, but also brings a new opportunity for logistics enterprises in China.
However, the existing cross-border e-commerce platform only embodies the purchasing function of the user, the embodied function is still imperfect, for example, in the aspect of mining and utilizing shopping data of the user, the existing cross-border e-commerce platform has low utilization rate of the shopping data of the user, so that the intelligent level of the existing cross-border e-commerce platform is low, and in order to improve the utilization rate of the shopping data of the user by the cross-border e-commerce platform, a big data user mining method based on the cross-border e-commerce platform is designed.
Disclosure of Invention
In order to achieve the purpose, the big data user mining method for the cross-border e-commerce platform provided by the invention deeply mines the shopping data of each user registered on the cross-border e-commerce platform, so that the utilization rate of the cross-border e-commerce platform on the shopping data of the user is improved.
The purpose of the invention can be realized by the following technical scheme:
a big data user mining method based on a cross-border e-commerce platform comprises the following steps:
s1, acquiring a registered country and historical shopping records: acquiring a registered country and all historical shopping records under a user login account on a cross-border e-commerce platform according to the user login account, numbering the acquired historical shopping records according to the sequence of shopping time, and sequentially marking the historical shopping records as 1,2.. i.. n;
s2, constructing a shopping parameter set and a logistics receiving area country set: shopping parameters and logistics information are obtained from all marked historical shopping records, and the shopping parameters corresponding to all the obtained historical shopping records form a shopping parameter set Gw(gw1,gw2,...,gwi,...,gwn)，gwi represents a numerical value corresponding to the w-th shopping parameter of the ith historical shopping record, w represents a shopping parameter, w is p1, p2, p3, p4, p1, p2, p3 and p4 represent shopping categories, purchasing merchants, purchasing quantity and purchasing amount, meanwhile, a logistics receiving place address is extracted from logistics information corresponding to each obtained historical shopping record, a receiving place country corresponding to the extracted logistics receiving place address is analyzed, and then the receiving place country corresponding to each obtained historical shopping record forms a logistics receiving place country set C (C1, C2,. # as.
S3, analyzing the true country of the user: matching the receiving country corresponding to each historical shopping record in the logistics receiving country set with the registered country under the user login account, counting the number of the historical shopping records successfully matched with the registered country under the user login account if the matching is successful, counting the matching success coefficient, comparing the matching success coefficient with the preset standard matching success coefficient, taking the registered country under the user login account as the real country of the user if the matching success coefficient is greater than the preset standard matching success coefficient, screening the receiving country corresponding to each historical shopping record in the logistics receiving country set to obtain the receiving country inconsistent with the registered country under the user login account if the matching success coefficient is less than the preset standard matching success coefficient, comparing the receiving countries, checking whether the same receiving country exists, if the same receiving place country exists, counting the number of the same receiving place countries, marking each same receiving place country as a candidate real country, counting the occurrence frequency of each candidate real country, further counting the proportion coefficient corresponding to each candidate real country, thereby obtaining the candidate real country with the maximum proportion coefficient from the candidate real country, comparing the proportion coefficient corresponding to the candidate real country with the maximum proportion coefficient with the registration country matching success coefficient under the user login account, if the proportion coefficient corresponding to the candidate real country with the maximum proportion coefficient is larger than the registration country matching success coefficient under the user login account, taking the candidate real country with the maximum proportion coefficient as the real country of the user, if the proportion coefficient corresponding to the candidate real country with the maximum proportion coefficient is smaller than the registration country matching success coefficient under the user login account, taking the registered country under the user login account as the real country of the user, and if the matching fails, selecting a receiving place country from the logistics receiving place country set as the real country of the user;
s4, analyzing shopping categories preferred by the user: extracting shopping categories corresponding to all historical shopping records from a shopping parameter set, comparing the shopping categories with each other, analyzing whether the same shopping categories exist or not, counting the number of the same shopping categories if the same shopping categories exist, marking each same shopping category as a candidate shopping category, counting the number of the historical shopping records corresponding to each candidate shopping category, comparing the number of the historical shopping records corresponding to each candidate shopping category, and screening the candidate shopping category with the largest number of the historical shopping records as a preferred shopping category of the user;
s5, analyzing preferred purchasing merchants corresponding to the user preferred purchasing categories: obtaining each historical shopping record number corresponding to the preferred shopping category, further obtaining the shopping parameters of each historical shopping record corresponding to the preferred shopping category from the shopping parameter set according to each historical shopping record number corresponding to the preferred shopping category, which can be marked as 1,2w(fw1,fw2,...,fwa,...,fwl)，fwa represents a numerical value corresponding to the w-th shopping parameter of the a-th historical shopping record of the preferred shopping category, so that purchasing merchants of the preferred shopping category corresponding to all the historical shopping records are extracted from a preferred shopping category shopping parameter set, all the purchasing merchants are compared with each other to check whether the same purchasing merchants exist, if the same purchasing merchants exist, the number of the same purchasing merchants is counted, all the same purchasing merchants are marked as candidate purchasing merchants, all the candidate purchasing merchants are numbered and marked as A, B.I.N, the number of the historical shopping records corresponding to all the candidate purchasing merchants and the number corresponding to all the historical shopping records are counted, the number corresponding to all the historical shopping records can be marked as 1, 2.j.m, and further according to all the historical shopping record numbers corresponding to all the candidate purchasing merchants, the purchase quantity and the purchase amount of each historical shopping record corresponding to each candidate purchaser are extracted from the shopping parameter set to form a candidate purchaser preference parameter set Ru Z(ru Z1,ru Z2,...,ru Zj,...,ru Zm)，ru Zj is a numerical value corresponding to the u-th preference parameter of the jth historical shopping record of the jth candidate buyer corresponding to the preference shopping category, u is a preference parameter, u is s1, s2, s1 and s2 are respectively a purchase quantity and a purchase amount, Z is a candidate buyer number, and Z is A, BCalculating preference coefficients corresponding to the candidate purchasers according to the candidate purchasers preference parameter set and the number of historical shopping records corresponding to the candidate purchasers, and sequencing the candidate purchasers from large to small according to the preference coefficients corresponding to the candidate purchasers, wherein the first candidate purchasers are marked as preference purchasers corresponding to the preferred shopping category of the user;
s6, analyzing the optimal preferred purchasing merchants corresponding to the national users: obtaining the registered country and all historical shopping records of each user by each user registered on the cross-border E-commerce platform according to the method of S1-S5, further analyzing the real country and preferred shopping category of each user and the preferred shopping merchant corresponding to the preferred shopping category, comparing the real country of each user with the analyzed real country of the user, screening out the users consistent with the analyzed real country of the user, marking the screened users consistent with the analyzed real country of the user as the users of the same country, comparing the preferred shopping categories corresponding to the users of the same country, screening out the users of the same country consistent with the preferred shopping categories of the user, marking the screened users of the same country consistent with the preferred shopping categories of the user as the users of the same country, continuously comparing the preferred shopping merchants corresponding to the users of the same country of the same category, whether the same preference purchasing merchants exist or not is analyzed, if the same preference purchasing merchants exist, the number of the same preference purchasing merchants is counted, the occurrence frequency of each same preference purchasing merchant is counted, the same preference purchasing merchant with the largest occurrence frequency is obtained from the statistics, and the same preference purchasing merchant with the largest occurrence frequency is used as the best preference purchasing merchant corresponding to the preference shopping category of the national user;
and S7, recommending the new user, namely recommending the optimal preferred purchasing merchant corresponding to the preferred shopping category of the country user as a recommended merchant to the new user registered on the cross-border e-commerce platform and with the country of the registered country.
Preferably, the shopping parameters include shopping category, purchasing merchant, purchasing amount and purchasing amount.
Preferably, the successful matching means that the receiving country corresponding to a certain historical shopping record is consistent with the registered country under the user login account.
Preferably, the calculation method of the matching success coefficient is
x represents the number of the historical shopping records successfully matched with the registered country, and n represents the total number of the historical shopping records.
Preferably, the calculation method of the proportion coefficient corresponding to each candidate real country is to divide the frequency of occurrence of each candidate real country by the total number of the historical shopping records.
Preferably, the failure of matching means that the receiving country corresponding to all the historical shopping records of the user is inconsistent with the registered country under the login account of the user.
Preferably, the specific operation procedure of selecting one receiving country from the logistics receiving country set as the real country of the user when the matching fails in S3 performs the following steps:
h1: comparing receiving area countries corresponding to each historical shopping record in the logistics receiving area country set with each other, checking whether the same receiving area country exists, counting the number of the same receiving area country if the same receiving area country exists, and counting the frequency of the same receiving area country;
h2: and according to the occurrence frequency of the same receiving place country, extracting the same receiving place country with the most occurrence frequency from the same receiving place country as the real country of the user.
Preferably, the calculation formula of the preference coefficient corresponding to each candidate purchaser is
In the formula
Expressing a preference coefficient corresponding to the Z-th candidate purchaser corresponding to the preferred shopping category, and expressing Z as a candidate purchaser number, wherein Z is A, Bs1 Zj、rs2 Zj respectively representsThe purchase quantity and the purchase amount of the jth historical shopping record of the jth candidate purchaser corresponding to the preferred shopping category fp3a、fp4a represents the purchase quantity and purchase amount corresponding to the a-th historical shopping record of the preferred shopping category, mZThe number of historical purchases corresponding to the Z-th candidate purchaser corresponding to the preferred shopping category is expressed, and l is the number of historical purchases corresponding to the preferred shopping category.
The invention has the following beneficial effects:
(1) according to the invention, the registered country and all historical shopping records of the user are acquired on the cross-border e-commerce platform, the real country and the preferred shopping category of the registered user and the preferred purchasing merchant corresponding to the preferred shopping category are further analyzed, so that the optimal preferred purchasing merchant corresponding to the same preferred shopping category by the user of the same country is analyzed, and the optimal preferred purchasing merchant is recommended to the new user of which the registered country is the country registered on the cross-border e-commerce platform, the deep excavation of the shopping data of the user is embodied, the utilization rate of the shopping data of the user is improved, the intelligent recommendation function of the registered new user is realized, the use function of the cross-border e-commerce platform is perfected by the intelligent recommendation function, the intelligent level of the cross-border e-commerce platform is improved, and the use experience of the user is enhanced.
(2) The invention integrates the country registered by the user on the cross-border e-commerce platform and the logistics receiving place country corresponding to each historical shopping record of the user in the process of analyzing the real country of the registered user, avoids the one-sidedness and the unreliability caused by only adopting the country registered by the user on the cross-border e-commerce platform as the real country of the user, and improves the reliability of analyzing the optimal preferred purchasing merchant corresponding to the same preferred shopping category by the user of the same country in the later stage.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a flow chart 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.
Referring to fig. 1, a big data user mining method based on a cross-border e-commerce platform includes the following steps:
s1, acquiring a registered country and historical shopping records: acquiring a registered country and all historical shopping records under a user login account on a cross-border e-commerce platform according to the user login account, numbering the acquired historical shopping records according to the sequence of shopping time, and sequentially marking the historical shopping records as 1,2.. i.. n;
s2, constructing a shopping parameter set and a logistics receiving area country set: acquiring shopping parameters and logistics information of each marked historical shopping record, wherein the shopping parameters comprise shopping categories, purchasing merchants, purchasing quantity and purchasing amount, and forming a shopping parameter set G by the shopping parameters corresponding to each acquired historical shopping recordw(gw1,gw2,...,gwi,...,gwn)，gwi represents a numerical value corresponding to the w-th shopping parameter of the ith historical shopping record, w represents a shopping parameter, w is p1, p2, p3, p4, p1, p2, p3 and p4 represent shopping categories, purchasing merchants, purchasing quantity and purchasing amount, meanwhile, a logistics receiving place address is extracted from logistics information corresponding to each obtained historical shopping record, a receiving place country corresponding to the extracted logistics receiving place address is analyzed, and then the receiving place country corresponding to each obtained historical shopping record forms a logistics receiving place country set C (C1, C2,. # as.
S3, analyzing the true country of the user: collecting all histories in the state set of the logistics receiving placesThe receiving country corresponding to the shopping records are respectively matched with the registered country under the user login account, if the matching is successful, the successful matching refers to that the receiving country corresponding to a certain historical shopping record is consistent with the registered country under the user login account, the number of the historical shopping records successfully matched with the registered country under the user login account is counted, and the coefficient of successful matching is counted
x is the number of historical shopping records successfully matched with the registered country, n is the total number of the historical shopping records, the matching success coefficient is compared with the preset standard matching success coefficient, if the matching success coefficient is larger than the preset standard matching success coefficient, the registered country under the user login account number is used as the real country of the user, if the matching success coefficient is smaller than the preset standard matching success coefficient, the receiving country which is inconsistent with the registered country under the user login account number is screened from the receiving country corresponding to each historical shopping record in the logistics receiving country set and is compared with each other, whether the same receiving country exists or not is checked, if the same receiving country exists, the number of the same receiving country is counted, each same receiving country is marked as a candidate real country, and the frequency of occurrence of each candidate real country is counted, and further counting the occupation ratio coefficient corresponding to each candidate real country, wherein the calculation method of the occupation ratio coefficient corresponding to each candidate real country is to divide the frequency of occurrence of each candidate real country by the total number of the historical shopping records so as to obtain the candidate real country with the maximum occupation ratio coefficient from the history shopping records, compare the occupation ratio coefficient corresponding to the candidate real country with the maximum occupation ratio coefficient with the registration country matching success coefficient under the user login account, if the occupation ratio coefficient corresponding to the candidate real country with the maximum occupation ratio coefficient is greater than the registration country matching success coefficient under the user login account, use the candidate real country with the maximum occupation ratio coefficient as the real country of the user, and if the occupation ratio coefficient corresponding to the candidate real country with the maximum occupation ratio coefficient is less than the registration country matching success coefficient under the user login account, use the candidate real country with the maximum occupation ratio coefficient as the real country of the userIf the matching fails, namely that the receiving country corresponding to all historical shopping records of the user is inconsistent with the registered country under the user login account, selecting one receiving country from the logistics receiving country set as the real country of the user, and executing the following steps in a specific operation process:
h1: comparing receiving area countries corresponding to each historical shopping record in the logistics receiving area country set with each other, checking whether the same receiving area country exists, counting the number of the same receiving area country if the same receiving area country exists, and counting the frequency of the same receiving area country;
h2: according to the occurrence frequency of each identical receiving place country, extracting the identical receiving place country with the most occurrence frequency as the real country of the user;
in the embodiment, the country registered by the user on the cross-border e-commerce platform and the logistics receiving place country corresponding to each historical shopping record of the user are integrated in the process of analyzing the real country of the registered user, the one-sidedness and the unreliability caused by only adopting the country registered by the user on the cross-border e-commerce platform as the real country of the user are avoided, and the method for analyzing the real country of the user when the matching is successful and the matching is failed is detailed in a hierarchical mode by the analysis method, has the characteristic of strong operability, and improves the reliability of analyzing the optimal preferred purchasing merchant corresponding to the same preferred shopping category by the user of the same country in the later stage.
S4, analyzing shopping categories preferred by the user: extracting shopping categories corresponding to all historical shopping records from a shopping parameter set, comparing the shopping categories with each other, analyzing whether the same shopping categories exist or not, counting the number of the same shopping categories if the same shopping categories exist, marking each same shopping category as a candidate shopping category, counting the number of the historical shopping records corresponding to each candidate shopping category, comparing the number of the historical shopping records corresponding to each candidate shopping category, and screening the candidate shopping category with the largest number of the historical shopping records as a preferred shopping category of the user;
s5, analyzing preferred purchasing merchants corresponding to the user preferred purchasing categories: obtaining each historical shopping record number corresponding to the preferred shopping category, further obtaining the shopping parameters of each historical shopping record corresponding to the preferred shopping category from the shopping parameter set according to each historical shopping record number corresponding to the preferred shopping category, which can be marked as 1,2w(fw1,fw2,...,fwa,...,fwl)，fwa represents a numerical value corresponding to the w-th shopping parameter of the a-th historical shopping record of the preferred shopping category, so that purchasing merchants of the preferred shopping category corresponding to all the historical shopping records are extracted from a preferred shopping category shopping parameter set, all the purchasing merchants are compared with each other to check whether the same purchasing merchants exist, if the same purchasing merchants exist, the number of the same purchasing merchants is counted, all the same purchasing merchants are marked as candidate purchasing merchants, all the candidate purchasing merchants are numbered and marked as A, B.J.I.N, the number of the historical shopping records corresponding to all the candidate purchasing merchants and the number corresponding to all the shopping records are counted, the number corresponding to all the shopping records can be marked as 1, 2.j.m, and further according to all the historical shopping record numbers corresponding to all the candidate purchasing merchants, the purchase quantity and the purchase amount of each historical shopping record corresponding to each candidate purchaser are extracted from the shopping parameter set to form a candidate purchaser preference parameter set Ru Z(ru Z1,ru Z2,...,ru Zj,...,ru Zm)，ru Zj is a numerical value corresponding to the u-th preference parameter of the jth historical shopping record of the jth candidate buyer corresponding to the preference shopping category, u is a preference parameter, u is s1, s2, s1 and s2 are respectively a purchase quantity and a purchase amount, Z is a candidate buyer number, Z is A, B
In the formula
Expressing a preference coefficient corresponding to the Z-th candidate purchaser corresponding to the preferred shopping category, and expressing Z as a candidate purchaser number, wherein Z is A, Bs1 Zj、rs2 Z jRespectively representing the purchase quantity and the purchase amount of the jth historical shopping record of the jth candidate purchaser corresponding to the preferred shopping category, fp3a、fp4a represents the purchase quantity and purchase amount corresponding to the a-th historical shopping record of the preferred shopping category, mZExpressing the number of historical purchasing records corresponding to the Z-th candidate purchasing merchant corresponding to the preferred purchasing category, and expressing l as the number of historical purchasing records corresponding to the preferred purchasing category, and sequencing the candidate purchasing merchants according to the preference coefficients corresponding to the candidate purchasing merchants from large to small, wherein the candidate purchasing merchants ranked at the first place are marked as preferred purchasing merchants corresponding to the preferred purchasing category of the user;
the calculation formula of the preference coefficient of each preferred purchasing merchant set by the embodiment integrates the purchase quantity, purchase amount and purchase times of purchasing the preferred purchasing category commodity at each preferred purchasing merchant, embodies the comprehensiveness of the preference coefficient statistics, so that the statistical preference coefficient intuitively and comprehensively shows the purchase preference degree of the user at the purchasing merchant, the greater the preference coefficient is, the greater the purchase preference degree of the user at the purchasing merchant is, and the more reliable reference basis is provided for the subsequent statistics of the best preferred purchasing merchant corresponding to the preferred purchasing category by the national user.
S6, analyzing the optimal preferred purchasing merchants corresponding to the national users: obtaining the registered country and all historical shopping records of each user by each user registered on the cross-border E-commerce platform according to the method of S1-S5, further analyzing the real country and preferred shopping category of each user and the preferred purchasing merchants corresponding to the preferred shopping category, comparing the real country of each user with the analyzed real country of the user, screening out the users consistent with the analyzed real country of the user, marking the screened users consistent with the analyzed real country of the user as the same country users, comparing the preferred shopping categories corresponding to the same country users at the moment, screening out the same country users consistent with the shopping categories of the user, marking the screened same country users consistent with the shopping categories of the user as the same country users of the same shopping category, continuing comparing the preferred purchasing merchants corresponding to the same country users of the same shopping category, whether the same preference purchasing merchants exist or not is analyzed, if the same preference purchasing merchants exist, the number of the same preference purchasing merchants is counted, the occurrence frequency of each same preference purchasing merchant is counted, the same preference purchasing merchant with the largest occurrence frequency is obtained from the statistics, and the same preference purchasing merchant with the largest occurrence frequency is used as the best preference purchasing merchant corresponding to the preference shopping category of the national user;
and S7, recommending the new user, namely recommending the optimal preferred purchasing merchant corresponding to the preferred shopping category of the country user as a recommended merchant to the new user registered on the cross-border e-commerce platform and with the country of the registered country.
According to the invention, the shopping data of the user on the cross-border e-commerce platform is deeply mined, so that the utilization rate of the shopping data of the user is improved, the intelligent recommendation function for registering a new user is realized, the use function of the cross-border e-commerce platform is perfected by the intelligent recommendation function, the intelligent level of the cross-border e-commerce platform is improved, the defects of low intelligent level caused by imperfect functions and low utilization rate of the shopping data of the user existing in the current cross-border e-commerce platform are overcome, and the use experience of the user is enhanced.
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. A big data user mining method based on a cross-border e-commerce platform is characterized by comprising the following steps: the method comprises the following steps:
s1, acquiring a registered country and historical shopping records: acquiring a registered country and all historical shopping records under a user login account on a cross-border e-commerce platform according to the user login account, numbering the acquired historical shopping records according to the sequence of shopping time, and sequentially marking the historical shopping records as 1,2.. i.. n;
s2, constructing a shopping parameter set and a logistics receiving area country set: shopping parameters and logistics information are obtained from all marked historical shopping records, and the shopping parameters corresponding to all the obtained historical shopping records form a shopping parameter set Gw(gw1,gw2,…,gwi,...,gwn)，gwi represents a numerical value corresponding to the w-th shopping parameter of the ith historical shopping record, w represents a shopping parameter, w is p1, p2, p3, p4, p1, p2, p3 and p4 represent shopping categories, purchasing merchants, purchasing quantity and purchasing amount, meanwhile, a logistics receiving place address is extracted from logistics information corresponding to each obtained historical shopping record, a receiving place country corresponding to the extracted logistics receiving place address is analyzed, and then the receiving place country corresponding to each obtained historical shopping record forms a logistics receiving place country set C (C1, C2,. # as.
S3, analyzing the true country of the user: matching the receiving country corresponding to each historical shopping record in the logistics receiving country set with the registered country under the user login account, counting the number of the historical shopping records successfully matched with the registered country under the user login account if the matching is successful, counting the matching success coefficient, comparing the matching success coefficient with the preset standard matching success coefficient, taking the registered country under the user login account as the real country of the user if the matching success coefficient is greater than the preset standard matching success coefficient, screening the receiving country corresponding to each historical shopping record in the logistics receiving country set to obtain the receiving country inconsistent with the registered country under the user login account if the matching success coefficient is less than the preset standard matching success coefficient, comparing the receiving countries, checking whether the same receiving country exists, if the same receiving place country exists, counting the number of the same receiving place countries, marking each same receiving place country as a candidate real country, counting the occurrence frequency of each candidate real country, further counting the proportion coefficient corresponding to each candidate real country, thereby obtaining the candidate real country with the maximum proportion coefficient from the candidate real country, comparing the proportion coefficient corresponding to the candidate real country with the maximum proportion coefficient with the registration country matching success coefficient under the user login account, if the proportion coefficient corresponding to the candidate real country with the maximum proportion coefficient is larger than the registration country matching success coefficient under the user login account, taking the candidate real country with the maximum proportion coefficient as the real country of the user, if the proportion coefficient corresponding to the candidate real country with the maximum proportion coefficient is smaller than the registration country matching success coefficient under the user login account, taking the registered country under the user login account as the real country of the user, and if the matching fails, selecting a receiving place country from the logistics receiving place country set as the real country of the user;
s4, analyzing shopping categories preferred by the user: extracting shopping categories corresponding to all historical shopping records from a shopping parameter set, comparing the shopping categories with each other, analyzing whether the same shopping categories exist or not, counting the number of the same shopping categories if the same shopping categories exist, marking each same shopping category as a candidate shopping category, counting the number of the historical shopping records corresponding to each candidate shopping category, comparing the number of the historical shopping records corresponding to each candidate shopping category, and screening the candidate shopping category with the largest number of the historical shopping records as a preferred shopping category of the user;
s5, analyzing preferred purchasing merchants corresponding to the user preferred purchasing categories: obtaining each historical shopping record number corresponding to the preferred shopping category, further obtaining the shopping parameters of each historical shopping record corresponding to the preferred shopping category from the shopping parameter set according to each historical shopping record number corresponding to the preferred shopping category, which can be marked as 1,2w(fw1,fw2,...,fwa,...,fwl)，fwa represents a numerical value corresponding to the w-th shopping parameter of the a-th historical shopping record of the preferred shopping category, so that purchasing merchants of the preferred shopping category corresponding to all the historical shopping records are extracted from a preferred shopping category shopping parameter set, all the purchasing merchants are compared with each other to check whether the same purchasing merchants exist, if the same purchasing merchants exist, the number of the same purchasing merchants is counted, all the same purchasing merchants are marked as candidate purchasing merchants, all the candidate purchasing merchants are numbered and marked as A, B.I.N, the number of the historical shopping records corresponding to all the candidate purchasing merchants and the number corresponding to all the historical shopping records are counted, the number corresponding to all the historical shopping records can be marked as 1, 2.j.m, and further according to all the historical shopping record numbers corresponding to all the candidate purchasing merchants, the purchase quantity and the purchase amount of each historical shopping record corresponding to each candidate purchaser are extracted from the shopping parameter set to form a candidate purchaser preference parameter set Ru Z(ru Z1,ru Z2,...,ru Zj,...,ru Zm)，ru Zj represents a numerical value corresponding to the u-th preference parameter of the jth historical shopping record of the jth candidate purchaser corresponding to the preferred shopping category, u represents a preference parameter, u is s1, s2, s1 and s2 respectively represent purchase quantity and purchase amount, Z represents a candidate purchaser number, Z is A, B.
S6, analyzing the optimal preferred purchasing merchants corresponding to the national users: obtaining the registered country and all historical shopping records of each user by each user registered on the cross-border E-commerce platform according to the method of S1-S5, further analyzing the real country and preferred shopping category of each user and the preferred shopping merchant corresponding to the preferred shopping category, comparing the real country of each user with the analyzed real country of the user, screening out the users consistent with the analyzed real country of the user, marking the screened users consistent with the analyzed real country of the user as the users of the same country, comparing the preferred shopping categories corresponding to the users of the same country, screening out the users of the same country consistent with the preferred shopping categories of the user, marking the screened users of the same country consistent with the preferred shopping categories of the user as the users of the same country, continuously comparing the preferred shopping merchants corresponding to the users of the same country of the same category, whether the same preference purchasing merchants exist or not is analyzed, if the same preference purchasing merchants exist, the number of the same preference purchasing merchants is counted, the occurrence frequency of each same preference purchasing merchant is counted, the same preference purchasing merchant with the largest occurrence frequency is obtained from the statistics, and the same preference purchasing merchant with the largest occurrence frequency is used as the best preference purchasing merchant corresponding to the preference shopping category of the national user;
and S7, recommending the new user, namely recommending the optimal preferred purchasing merchant corresponding to the preferred shopping category of the country user as a recommended merchant to the new user registered on the cross-border e-commerce platform and with the country of the registered country.
2. The big data user mining method based on the cross-border e-commerce platform as claimed in claim 1, wherein: the shopping parameters include shopping category, purchasing merchant, purchase amount, and purchase amount.
3. The big data user mining method based on the cross-border e-commerce platform as claimed in claim 1, wherein: the successful matching means that the receiving country corresponding to a certain historical shopping record is consistent with the registered country under the login account of the user.
4. The big data user mining method based on the cross-border e-commerce platform as claimed in claim 1, wherein: the calculation method of the matching success coefficient comprises the following steps
x represents the number of the historical shopping records successfully matched with the registered country, and n represents the total number of the historical shopping records.
5. The big data user mining method based on the cross-border e-commerce platform as claimed in claim 1, wherein: the calculation method of the proportion coefficient corresponding to each candidate real country is to divide the occurrence frequency of each candidate real country by the total number of the historical shopping records.
6. The big data user mining method based on the cross-border e-commerce platform as claimed in claim 1, wherein: the matching failure means that the receiving country corresponding to all the historical shopping records of the user is inconsistent with the registered country under the login account of the user.
7. The big data user mining method based on the cross-border e-commerce platform as claimed in claim 1, wherein: the specific operation process of selecting one receiving place country from the logistics receiving place country set as the real country of the user when the matching fails in the S3 executes the following steps:
h1: comparing receiving area countries corresponding to each historical shopping record in the logistics receiving area country set with each other, checking whether the same receiving area country exists, counting the number of the same receiving area country if the same receiving area country exists, and counting the frequency of the same receiving area country;
h2: and according to the occurrence frequency of the same receiving place country, extracting the same receiving place country with the most occurrence frequency from the same receiving place country as the real country of the user.
8. The big data user mining method based on the cross-border e-commerce platform as claimed in claim 1, wherein: the calculation formula of the preference coefficient corresponding to each candidate purchaser is
In the formula
Expressing a preference coefficient corresponding to the Z-th candidate purchaser corresponding to the preferred shopping category, and expressing Z as a candidate purchaser number, wherein Z is A, Bs1 Zj、rs2 Zj represents the purchase quantity and purchase amount of the jth historical shopping record of the jth candidate purchaser corresponding to the preferred shopping category respectively, fp3a、fp4a represents the purchase quantity and purchase amount corresponding to the a-th historical shopping record of the preferred shopping category, mZThe number of historical purchases corresponding to the Z-th candidate purchaser corresponding to the preferred shopping category is expressed, and l is the number of historical purchases corresponding to the preferred shopping category.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011466869.7A CN112506997B (en) | 2020-12-14 | 2020-12-14 | Big data user mining method based on cross-border e-commerce platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011466869.7A CN112506997B (en) | 2020-12-14 | 2020-12-14 | Big data user mining method based on cross-border e-commerce platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112506997A CN112506997A (en) | 2021-03-16 |
| CN112506997B true CN112506997B (en) | 2021-06-29 |
Family
ID=74972156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011466869.7A Expired - Fee Related CN112506997B (en) | 2020-12-14 | 2020-12-14 | Big data user mining method based on cross-border e-commerce platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112506997B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113034238B (en) * | 2021-04-13 | 2022-04-15 | 优优祝福(北京)科技有限公司 | Commodity brand feature extraction and intelligent recommendation management method based on electronic commerce platform transaction |
| CN116862625B (en) * | 2023-09-05 | 2023-11-21 | 武汉森全科技有限公司 | Online recommendation method for fresh fruits based on Internet big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101206751A (en) * | 2007-12-25 | 2008-06-25 | 北京科文书业信息技术有限公司 | Customer recommendation system based on data digging and method thereof |
| US7499401B2 (en) * | 2002-10-21 | 2009-03-03 | Alcatel-Lucent Usa Inc. | Integrated web cache |
| US7599323B2 (en) * | 2002-10-17 | 2009-10-06 | Alcatel-Lucent Usa Inc. | Multi-interface mobility client |
| CN104572765A (en) * | 2013-10-25 | 2015-04-29 | 西安群丰电子信息科技有限公司 | Method and system for finding vest account based on behavior analysis of user account |
| CN107194720A (en) * | 2017-05-11 | 2017-09-22 | 杭州光速科技有限公司 | A kind of advertisement placement method based on cross-border electric business service platform |
| CN107633430A (en) * | 2017-09-20 | 2018-01-26 | 哈尔滨工业大学 | A kind of Method of Commodity Recommendation based on community of colony |
| CN110648188A (en) * | 2018-06-27 | 2020-01-03 | 江苏特易信息科技有限公司 | Cross-border trade BPO service recommendation system based on user preference |
| CN111177549A (en) * | 2019-12-25 | 2020-05-19 | 杭州龙席网络科技股份有限公司 | Client recommendation method suitable for export-type cross-border trade |
| CN111815358A (en) * | 2020-07-09 | 2020-10-23 | 湖南数客星球信息技术有限公司 | Big data user mining method and system based on cross-border e-commerce platform |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050267812A1 (en) * | 2004-05-17 | 2005-12-01 | Jensen Scott C | Method for providing discount offers to a user |
| US20140129371A1 (en) * | 2012-11-05 | 2014-05-08 | Nathan R. Wilson | Systems and methods for providing enhanced neural network genesis and recommendations |
-
2020
- 2020-12-14 CN CN202011466869.7A patent/CN112506997B/en not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7599323B2 (en) * | 2002-10-17 | 2009-10-06 | Alcatel-Lucent Usa Inc. | Multi-interface mobility client |
| US7499401B2 (en) * | 2002-10-21 | 2009-03-03 | Alcatel-Lucent Usa Inc. | Integrated web cache |
| CN101206751A (en) * | 2007-12-25 | 2008-06-25 | 北京科文书业信息技术有限公司 | Customer recommendation system based on data digging and method thereof |
| CN104572765A (en) * | 2013-10-25 | 2015-04-29 | 西安群丰电子信息科技有限公司 | Method and system for finding vest account based on behavior analysis of user account |
| CN107194720A (en) * | 2017-05-11 | 2017-09-22 | 杭州光速科技有限公司 | A kind of advertisement placement method based on cross-border electric business service platform |
| CN107633430A (en) * | 2017-09-20 | 2018-01-26 | 哈尔滨工业大学 | A kind of Method of Commodity Recommendation based on community of colony |
| CN110648188A (en) * | 2018-06-27 | 2020-01-03 | 江苏特易信息科技有限公司 | Cross-border trade BPO service recommendation system based on user preference |
| CN111177549A (en) * | 2019-12-25 | 2020-05-19 | 杭州龙席网络科技股份有限公司 | Client recommendation method suitable for export-type cross-border trade |
| CN111815358A (en) * | 2020-07-09 | 2020-10-23 | 湖南数客星球信息技术有限公司 | Big data user mining method and system based on cross-border e-commerce platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112506997A (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110415087B (en) | Electronic commerce transaction system based on internet | |
| CN103577988B (en) | A kind of method and apparatus for recognizing specific user | |
| CN112102037B (en) | Live E-commerce platform commodity content intelligent pushing management system based on big data | |
| CN112506997B (en) | Big data user mining method based on cross-border e-commerce platform | |
| CN108038696B (en) | Method and system for detecting bill swiping based on equipment identification code and social group information | |
| CN106780012A (en) | A kind of internet credit methods and system | |
| US20090070289A1 (en) | Methods, Systems, and Computer Program Products for Estimating Accuracy of Linking of Customer Relationships | |
| CN108573432B (en) | Transaction supervision system and method for electronic commerce | |
| CN106779996A (en) | Business data method for digging and system in a kind of supply chain finance | |
| CN113034238B (en) | Commodity brand feature extraction and intelligent recommendation management method based on electronic commerce platform transaction | |
| KR20020086695A (en) | System and method for detecting fraudulent transactions | |
| CN108932614B (en) | Payment channel routing method and system | |
| CN114119001B (en) | Intelligent management and analysis platform for cash collection of commodity sales based on artificial intelligence | |
| CN113052657B (en) | Online commodity intelligent matching recommendation method based on user behavior analysis and cloud server | |
| CN105631783A (en) | Objective and quantitative Chinese patent evaluation system and method | |
| CN109993538A (en) | Identity theft detection method based on probability graph model | |
| CN111695979A (en) | Method, device and equipment for analyzing relation between raw material and finished product | |
| CN108022163A (en) | Obtain method, apparatus, equipment and the storage medium of the Fee Amount tax rate | |
| CN113159885A (en) | E-commerce platform virtual commodity order delivery method | |
| CN113095914B (en) | Order management method, system, equipment and computer storage medium for electronic commerce platform | |
| CN113837855B (en) | Cloud network-based cross-border value-added tax batch intelligent processing method, device and equipment | |
| CN113191857A (en) | Cloud platform e-commerce data processing method and system based on big data | |
| CN114971805A (en) | Electronic commerce platform commodity intelligent analysis recommendation system based on deep learning | |
| CN114936784A (en) | Supplier selection method, supplier selection system and supplier selection equipment | |
| CN110570301B (en) | Risk identification method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210611 Address after: 210012 8 / F, building 5, 170-1 software Avenue, Yuhuatai District, Nanjing City, Jiangsu Province Applicant after: Nanjing Xiyin e-commerce Co.,Ltd. Address before: Wangu mobile Internet technology park, No.16, Xiaoxing Road, Yuhuatai District, Nanjing City, Jiangsu Province, 210012 Applicant before: Nanjing Hanwei Information Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210629 |