CN113052657B - Online commodity intelligent matching recommendation method based on user behavior analysis and cloud server - Google Patents
Online commodity intelligent matching recommendation method based on user behavior analysis and cloud server Download PDFInfo
- Publication number
- CN113052657B CN113052657B CN202110357227.1A CN202110357227A CN113052657B CN 113052657 B CN113052657 B CN 113052657B CN 202110357227 A CN202110357227 A CN 202110357227A CN 113052657 B CN113052657 B CN 113052657B
- Authority
- CN
- China
- Prior art keywords
- clothing
- candidate
- seller
- coefficient
- sold
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000009467 reduction Effects 0.000 claims abstract description 28
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 2
- 239000003086 colorant Substances 0.000 claims 1
- 238000010276 construction Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006872 improvement 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
- 239000002699 waste material Substances 0.000 description 1
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
- G06F16/20—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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an online commodity intelligent matching recommendation method based on user behavior analysis and a cloud server, wherein each candidate seller is screened from a platform according to purchasing clothing information issued by a buyer user on a second-hand clothing transaction platform for children, and selling parameters corresponding to each candidate seller are obtained, so that the current comprehensive brand-new coefficient, the durability coefficient, the transaction credit coefficient, the price reduction strength coefficient and the transaction distance coefficient of the clothing sold by each candidate seller are counted, the comprehensive recommendation coefficients corresponding to the candidate sellers are calculated comprehensively, the recommendation and ranking of the candidate sellers are carried out, the defect that the recommendation mode of the existing online second-hand transaction platform is too simple is overcome, the screening range of the buyer user is narrowed by the recommendation result, the screening efficiency of the buyer user is improved, the comprehensive matching degree of the recommendation result is improved on the one hand, and the comprehensive value of the recommendation result is improved on the other hand, the purchasing experience of the buyer user is greatly enhanced.
Description
Technical Field
The invention belongs to the technical field of online commodity recommendation, and particularly relates to an online commodity intelligent matching recommendation method based on user behavior analysis and a cloud server.
Background
With the vigorous development of domestic electronic commerce, online consumption has become a life style of people. The improvement of the consumption level and the simplification of the consumption process lead to a plurality of impulsive consumption and irrational consumption of people, and the quantity of personal idle articles is more and more, so that not only is the resource waste caused, but also the happiness of people is influenced, and the rapid development of an online second-hand transaction platform is promoted.
However, in the development process of the current online second-hand trading platform, some user experience problems are also generated, such as low comprehensive matching degree of commodity recommendation, which is embodied in that after the buyer user issues the information of buying commodities on the online second-hand trading platform, the platform screens the commodities which accord with the information of the buying commodities from the platform according to the commodity information issued by the buyer user, and then recommends the commodities, because the recommendation mode of the platform in the recommendation process is too simple, namely only one recommendation mode is followed, such as price recommendation, brand-new commodity recommendation, seller credit recommendation and the like, the recommendation result only reflects the single characteristic of the commodities and cannot reflect the comprehensive characteristic of the commodities, the screening range of the buyer user is invisibly expanded, the screening efficiency of the buyer user is reduced, and further on the one hand, the comprehensive matching degree of the recommendation result is reduced, and on the other hand, the comprehensive value of the recommendation result is low, greatly influencing the purchasing experience of the buyer user.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an online commodity intelligent matching recommendation method and a cloud server based on user behavior analysis, which are high in recommendation matching degree and recommendation comprehensive value, by taking a second-hand clothing transaction platform for children as an example, and effectively solves the problems in the background art.
The purpose of the invention can be realized by the following technical scheme:
in a first aspect, the invention provides an online commodity intelligent matching recommendation method based on user behavior analysis, which comprises the following steps:
s1, buyer purchase clothing information publishing: acquiring account information registered by a buyer user on a second-hand-used children garment transaction platform, and acquiring shopping garment information issued by the buyer user on the second-hand-used children garment transaction platform, wherein the issued shopping garment information comprises garment type, child age, child gender and issuing duration;
s2, counting candidate sellers: acquiring user information of all sellers on a second-hand clothing transaction platform for children, numbering, acquiring types, suitable ages of children, suitable sexes of children and issuing dates of the sellers, and acquiring current dates, and calculating issuing duration of the sellers for selling the clothing according to the issuing dates and the current dates of the sellers for selling the clothing, so that the clothing-buying information issued by the buyers is respectively matched with the types, suitable ages of children, suitable sexes of children and issuing durations of the sellers corresponding to the sellers for selling the clothing one by one, and the sellers meeting the clothing-buying information of the buyers are screened out and marked as candidate sellers, and the numbers of the candidate sellers are counted and marked as 1,2.
S3, constructing a selling parameter set of the candidate seller: obtaining the purchase date, purchase price, clothing image at purchase time, clothing image at present release time, sale price, seller credit level and seller geographic position of the clothing corresponding to the candidate seller from the clothing sale information corresponding to each candidate seller respectively to form a candidate seller sale parameter set Qu(qu1,qu2,...,qui,...,qun)，qui is data corresponding to the sale parameters of the ith candidate seller, u is the sale parameters, and u is p1, p2, p3, p4, p5, p6 and p7 which are respectively represented as a purchase date, a purchase price, a clothing image at the time of purchase, a clothing image at the time of current release, a sale price, a seller credit rating and a seller geographic position;
s4, the use duration of clothes sold by candidate sellers is counted: respectively extracting the purchase date of the clothing sold by each candidate seller from the sale parameter set of the candidate sellers, and acquiring the current date, thereby counting the service life of the clothing sold by each candidate seller;
s5, analyzing and counting the current comprehensive brand new coefficient of the clothes sold by the candidate seller correspondingly: respectively extracting a clothing image when each candidate seller corresponds to the clothing sold by the seller and a clothing image when the clothing is issued currently from a candidate seller selling parameter set, comparing the clothing image when each candidate seller corresponds to the clothing sold by the seller and the clothing image when the clothing is issued currently, checking whether damage and stains exist, focusing the clothing image when each candidate seller corresponds to the current issuing on a damaged and stained area if the damage and stains exist, and simultaneously extracting the outline of the damaged area and the outline of the stained area, thereby obtaining the damaged area and the stain area corresponding to the clothing when each candidate seller corresponds to the current issuing of the clothing sold by the seller, and obtaining the damaged area and the stain area corresponding to the clothing when each candidate seller corresponds to the current issuing according to each candidate sellerThe clothing image of the candidate seller corresponding to the current issue of the sold clothing acquires the clothing surface area of each candidate seller corresponding to the current issue of the sold clothing, so that the brand new coefficient of the current surface of each candidate seller corresponding to the sold clothing is counted, meanwhile, the color chromaticity of the clothing at the time of purchase and the color chromaticity of the clothing at the time of current issue are acquired from the clothing image of each candidate seller corresponding to the purchase of the sold clothing and the clothing image at the time of current issue, so that the brand new coefficient of the current color of the clothing at the time of sale of each candidate seller is counted, the size parameter of the clothing at the time of purchase is acquired from the clothing image of each candidate seller corresponding to the purchase of the sold clothing, and a size parameter set G of the candidate seller at the time of clothing purchase is formedr(gr1,gr2,...,gri,…,grn)，gri is a numerical value corresponding to the clothes size parameter when the ith candidate seller sells the clothes for purchase, r is a size parameter, r is x1, x2, x3 and x4 which are respectively expressed as the clothes length, the sleeve length, the chest circumference and the waist circumference, the size parameter of the clothes at the current issuing time is obtained from the clothes image of the clothes at the current issuing time corresponding to each candidate seller, and a set G 'of the size parameter at the current issuing time of the clothes at the candidate seller for selling the clothes is formed'r(g′r1,g′r2,…,g′ri,…,g′rn)，g′ri represents a numerical value corresponding to the size parameter of the clothing sold by the ith candidate seller when the clothing is currently released, and therefore, the brand-new coefficient of the current size of the clothing sold by each candidate seller is counted according to the size parameter set when the clothing sold by the candidate seller is purchased and the size parameter set when the clothing sold by the candidate seller is currently released, and the brand-new coefficient of the current comprehensive of the clothing sold by each candidate seller is counted according to the brand-new coefficient of the current surface, the brand-new coefficient of the current color and the brand-new coefficient of the current size of the clothing sold by each candidate seller;
s6, carrying out statistics on durability coefficients of corresponding sold clothes by candidate sellers: according to the service duration of the clothes sold by each candidate seller and the current comprehensive brand new coefficient, the durability coefficient of the clothes sold by each candidate seller is counted;
s7, acquiring the corresponding transaction credit coefficient of the candidate seller: extracting the credit rating corresponding to each candidate seller from the selling parameter set of the candidate sellers, comparing the credit rating with the transaction credit coefficient corresponding to each credit rating in the transaction platform database, and screening out the transaction credit coefficient corresponding to each candidate seller;
s8, carrying out price reduction force coefficient statistics on the corresponding sold clothes of the candidate seller: extracting the purchase price and the sale price of the clothing sold by each candidate seller from the sale parameter set of the candidate sellers, and counting the price reduction coefficient of the clothing sold by each candidate seller according to the purchase price, the sale price and the use duration of the clothing sold by each candidate seller;
s9, acquiring a transaction distance coefficient corresponding to the candidate seller: extracting the geographic position corresponding to each candidate seller from the selling parameter set of the candidate sellers, acquiring the geographic position of the buyer from purchasing information issued by the buyer, counting the logistics transportation distance between the buyer and each candidate seller according to the geographic position corresponding to each candidate seller and the geographic position of the buyer, comparing the obtained logistics transportation distance between the buyer and each candidate seller with the transaction distance coefficients corresponding to various logistics transportation distances in the transaction platform database, and screening out the transaction distance coefficient corresponding to each candidate seller;
s10, counting the corresponding comprehensive recommendation coefficients of the candidate sellers: and counting the comprehensive recommendation coefficient corresponding to each candidate seller according to the current comprehensive brand-new coefficient, the durability coefficient, the transaction credit coefficient, the price reduction degree coefficient and the transaction distance coefficient of the clothing sold by each candidate seller, sequencing the candidate sellers according to the descending order of the comprehensive recommendation coefficient to obtain the recommendation sequencing result of each candidate seller, and pushing the recommendation sequencing result to the child second-hand clothing transaction platform interface corresponding to the buyer user account according to the account information registered by the buyer user on the child second-hand clothing transaction platform.
In one possible implementation manner of the first aspect, the calculation formula of the brand-new coefficient of the current surface of the sold clothes for each candidate seller is
εiExpressed as the brand-new coefficient of the current surface of the corresponding sold clothing of the ith candidate seller, sdi、swi represents the damage area and stain area corresponding to the clothing when the clothing is sold by the ith candidate seller at the current release time, SiExpressed as the surface area of the garment at the time of the current release of the sold garment for the ith candidate seller.
In one implementation manner of the first aspect, the calculation formula of the brand-new coefficient of the current color of the sold clothes for each candidate seller is
χiExpressed as the current color brand-new coefficient of the ith candidate seller corresponding to the sold clothes, CiColor chromaticity of the clothing at the time of purchase, expressed as the ith candidate seller corresponding to the clothing sold, ciExpressed as the color shade of the current issue time clothing for the sale of clothing by the ith candidate seller.
In one possible implementation manner of the first aspect, the calculation formula of the brand-new coefficient of the current dimension of the clothing sold by each candidate seller is
δiExpressed as the brand-new coefficient of the current size of the corresponding sold clothing of the ith candidate seller.
In one possible implementation manner of the first aspect, the calculation formula of the current comprehensive brand-new coefficient of the sold clothes of each candidate seller is
Expressed as the current comprehensive brand-new coefficient of the ith candidate seller corresponding to the sold clothes.
In one possible implementation manner of the first aspect, the durability factor of each candidate seller corresponding to the sold clothing is calculated according to the formula
λiExpressed as the durability coefficient of the corresponding sold clothing of the ith candidate seller, gamma is expressed as the brand-new coefficient of the predefined clothing at the time of purchase, and
Tithe length of use of the corresponding clothes selling time of the ith candidate seller is expressed.
In an implementation manner of the first aspect, the calculation formula of the price reduction degree coefficient of each candidate seller corresponding to the sold clothing is
σiThe price reduction force coefficient, q, of the corresponding sold clothing of the ith candidate seller is expressedp2i、qp5i is respectively expressed as the purchase price and the sale price of the clothing sold by the ith candidate seller, TiThe length of use of the corresponding clothes selling time of the ith candidate seller is expressed.
In an implementation manner of the first aspect, a calculation formula of the comprehensive recommendation coefficient corresponding to each candidate seller is
ψiExpressed as the comprehensive recommendation coefficient corresponding to the ith candidate seller,
λi、σi、ξi、
the comprehensive brand-new coefficient, the durability coefficient, the price reduction force coefficient, the transaction credit coefficient and the transaction distance coefficient are respectively expressed as the current comprehensive brand-new coefficient, the durability coefficient, the price reduction force coefficient, the transaction credit coefficient and the transaction distance coefficient of the corresponding clothing sold by the ith candidate seller, a, b, c, d and e are respectively expressed as the recommendation weight coefficients corresponding to the current comprehensive brand-new coefficient, the durability coefficient, the price reduction force coefficient, the transaction credit coefficient and the transaction distance coefficient of the clothing sold by the seller, a + b + c + d + e is 1, and a > b > c > d > e.
In a second aspect, the invention provides a cloud server, which includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being communicatively connected with at least one online commodity intelligent matching recommendation device, the machine-readable storage medium is used for storing a program, an instruction, or a code, and the processor is used for executing the program, the instruction, or the code in the machine-readable storage medium to execute the online commodity intelligent matching recommendation method based on user behavior analysis.
Based on any one of the above aspects, the invention has the following beneficial effects:
(1) according to the invention, each candidate seller is screened out from the platform according to the shopping clothing information issued by the buyer user on the second-hand clothing transaction platform for children, and the selling parameters corresponding to each candidate seller are obtained, so that the current comprehensive brand-new coefficient, the durability coefficient, the transaction credit coefficient, the price reduction strength coefficient and the transaction distance coefficient of the clothing sold by each candidate seller are counted, the comprehensive recommendation coefficient corresponding to each candidate seller is comprehensively calculated, and then each candidate seller is recommended and ranked according to the corresponding comprehensive recommendation coefficient to obtain the recommended ranking result and is pushed to the buyer user, thereby realizing the comprehensive intelligent recommendation of the online second-hand transaction platform, overcoming the defect that the recommendation mode of the current online transaction platform is too simple and convenient, reducing the screening range of the buyer user and improving the screening efficiency of the buyer user, meanwhile, on one hand, the comprehensive matching degree of the recommendation result is improved, on the other hand, the comprehensive value of the recommendation result is improved, the purchasing experience of the buyer user is greatly enhanced, and the recommendation level of the online second-hand transaction platform is improved.
(2) According to the method, in the process of obtaining the current comprehensive brand-new coefficients of the clothes sold by each candidate seller, the brand-new surface condition, the brand-new color condition and the brand-new size condition of the clothes sold by the candidate seller are integrated, and compared with the method that the comprehensive brand-new coefficients are evaluated only according to the brand-new surface condition of the clothes sold by the candidate seller, the evaluation mode avoids the problem of evaluating one-sidedness, shows the current comprehensive quality of the clothes sold by the candidate seller in an all-around manner, and shows the stereoscopic impression of the quality of the clothes sold by each candidate seller for the buyer user.
(3) According to the invention, the price reduction degree coefficient of the clothing sold by each candidate seller replaces the selling price of the clothing sold by each candidate seller to serve as the influence coefficient in the comprehensive recommendation coefficient of the candidate seller in the aspect of price, so that the problem that the price advantage of the commodity sold by each candidate seller cannot be reflected at the core due to the fact that the selling price is simply taken as the influence coefficient in the aspect of price in the comprehensive recommendation coefficient of the candidate seller is avoided, and the probability that a buyer user purchases a good-quality and low-price commodity is improved.
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 method 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.
Referring to fig. 1, a first aspect of the present invention provides an online commodity intelligent matching recommendation method based on user behavior analysis, including the following steps:
s1, buyer purchase clothing information publishing: acquiring account information registered by a buyer user on a second-hand-used children garment transaction platform, and acquiring shopping garment information issued by the buyer user on the second-hand-used children garment transaction platform, wherein the issued shopping garment information comprises garment type, child age, child gender and issuing duration;
s2, counting candidate sellers: acquiring user information of all sellers on a second-hand clothing transaction platform for children, numbering, acquiring types, suitable ages of children, suitable sexes of children and release dates of corresponding clothes sold by all sellers, acquiring the current date, and calculating the release duration of the clothes sold by all sellers according to the release date and the current date of the clothes sold by all sellers, wherein the calculation method is that the release date of the clothes sold by all sellers is subtracted from the current date to obtain the release duration of the clothes sold by all sellers, so that the shopping garment information released by a buyer is respectively matched with the types, suitable ages of children, suitable sexes of children and the release duration corresponding to all sellers one by one, and all sellers conforming to the shopping garment information of the buyer are screened out and marked as candidate sellers, and the numbers of all candidate sellers are counted, respectively denoted as 1,2.. i.. n;
s3, constructing a selling parameter set of the candidate seller: obtaining the purchase date, purchase price, clothing image at purchase time, clothing image at present release time, sale price, seller credit level and seller geographic position of the clothing corresponding to the candidate seller from the sale clothing information corresponding to each candidate seller respectively to form a candidate seller sale parameter set Qu(qu1,qu2,…,qui,…,qun)，qui is data corresponding to the sale parameters of the ith candidate seller, u is the sale parameters, and u is p1, p2, p3, p4, p5, p6 and p7 which are respectively represented as a purchase date, a purchase price, a clothing image at the time of purchase, a clothing image at the time of current release, a sale price, a seller credit rating and a seller geographic position;
s4, the use duration of clothes sold by candidate sellers is counted: respectively extracting the purchase date of the clothing sold by each candidate seller from the sale parameter set of the candidate sellers, and acquiring the current date, thereby counting the use duration of the clothing sold by each candidate seller;
s5, analyzing and counting the current comprehensive brand new coefficient of the clothes sold by the candidate seller correspondingly: respectively extracting a clothing image at the time of purchase and a clothing image at the time of current release of the clothing corresponding to each candidate seller from the selling parameter set of the candidate sellers, and comparing the clothes image of each candidate seller corresponding to the clothes sold when purchasing with the clothes image when issuing currently, checking whether damage and stains exist, if so, focusing the clothing image corresponding to the current issue time of each candidate seller in the damaged and smudged areas, extracting the outlines of the damaged areas and the outlines of the smudged areas at the same time, thereby obtaining the damage area and stain area corresponding to the clothing when the clothing is currently released and sold corresponding to each candidate seller, and acquiring the clothing surface area of each candidate seller corresponding to the currently issued clothing according to the clothing image of each candidate seller corresponding to the currently issued clothing, so as to count brand new coefficients of the current surfaces of the clothing sold by each candidate seller corresponding to the clothing.
εiExpressed as the brand-new coefficient of the current surface of the corresponding sold clothing of the ith candidate seller, sdi、swi represents the damage area and stain area corresponding to the clothing when the clothing is sold by the ith candidate seller at the current release time, SiThe clothing surface area is expressed as the clothing surface area when the clothing sold by the ith candidate seller is currently released, and meanwhile, the color chromaticity of the clothing when the clothing is purchased and the color chromaticity of the clothing when the clothing is currently released are obtained from the clothing image when the clothing sold by each candidate seller is purchased and the clothing image when the clothing is currently released, so that the current color coefficient of the clothing sold by each candidate seller is counted
χiExpressed as the current color brand-new coefficient of the ith candidate seller corresponding to the sold clothes, CiColor chromaticity of the clothing at the time of purchase, expressed as the ith candidate seller corresponding to the clothing sold, ciThe color chromaticity of the current issued clothing corresponding to the clothing sold by the ith candidate seller is shown as followsObtaining the dimension parameter of the clothing when purchasing from the clothing image when purchasing of the clothing corresponding to each candidate seller, and forming a dimension parameter set G when purchasing the clothing when selling the candidate sellerr(gr1,gr2,…,gri,…,grn)，gri is a numerical value corresponding to the clothes size parameter when the ith candidate seller sells the clothes for purchase, r is a size parameter, r is x1, x2, x3 and x4 which are respectively expressed as the clothes length, the sleeve length, the chest circumference and the waist circumference, the size parameter of the clothes at the current issuing time is obtained from the clothes image of the clothes at the current issuing time corresponding to each candidate seller, and a set G 'of the size parameter at the current issuing time of the clothes at the candidate seller for selling the clothes is formed'r(g′r1,g′r2,…,g′ri,…,g′rn)，g′ri represents a numerical value corresponding to the garment size parameter when the ith candidate seller sells the garment currently issued, so as to count brand new coefficients of the current size of the garment sold by each candidate seller according to the size parameter set when the candidate seller sells the garment for purchase and the size parameter set when the candidate seller sells the garment for current issuance
δiExpressed as the brand-new coefficient of the current size of the clothing sold by the ith candidate seller, and the brand-new coefficient of the current surface, the brand-new coefficient of the current color and the brand-new coefficient of the current size of the clothing sold by each candidate seller are combined to count the brand-new coefficient of the current combination of the clothing sold by each candidate seller
Representing the current comprehensive brand-new coefficient of the corresponding sold clothing of the ith candidate seller;
in the embodiment, in the process of acquiring the current comprehensive brand-new coefficients of the clothes sold by each candidate seller, the brand-new surface condition, the brand-new color condition and the brand-new size condition of the clothes sold by the candidate seller are integrated, and compared with the prior method that the brand-new comprehensive coefficients are evaluated only according to the brand-new surface condition of the clothes sold by the candidate seller, the evaluation mode avoids the problem of evaluating one-sidedness, shows the current comprehensive quality of the clothes sold by the candidate seller in an all-around manner, and shows the three-dimensional sense of the quality of the clothes sold by each candidate seller for the buyer user;
s6, carrying out statistics on durability coefficients of corresponding sold clothes by candidate sellers: according to the service duration and the current comprehensive brand-new coefficient of the clothes sold by each candidate seller, the durability coefficient of the clothes sold by each candidate seller is counted
λiExpressed as the durability coefficient of the corresponding sold clothing of the ith candidate seller, gamma is expressed as the brand-new coefficient of the predefined clothing at the time of purchase, and
Tithe using time of the clothes sold corresponding to the ith candidate seller is expressed;
the durability coefficient of the clothing sold by each candidate seller indirectly reflects the quality of the clothing sold by each candidate seller, and provides a relevant recommendation basis for the candidate statistics of the comprehensive recommendation coefficient corresponding to each candidate seller;
s7, acquiring the corresponding transaction credit coefficient of the candidate seller: extracting credit grades corresponding to the candidate sellers from the candidate seller selling parameter set, comparing the credit grades with transaction credit coefficients corresponding to various credit grades in a transaction platform database, wherein the credit grades comprise good credit, excellent credit and excellent credit, and screening the transaction credit coefficients corresponding to the candidate sellers;
s8, carrying out price reduction force coefficient statistics on the corresponding sold clothes of the candidate seller: extracting the purchase price and the sale price of the clothing sold by each candidate seller from the sale parameter set of the candidate sellers, and counting the price reduction coefficient of the clothing sold by each candidate seller according to the purchase price, the sale price and the use duration of the clothing sold by each candidate seller
σiThe price reduction force coefficient, q, of the corresponding sold clothing of the ith candidate seller is expressedp2i、qp5i is respectively expressed as the purchase price and the sale price of the clothing sold by the ith candidate seller, TiThe using time of the clothes sold corresponding to the ith candidate seller is expressed;
in the embodiment, the price reduction degree coefficient of the clothing sold by each candidate seller replaces the selling price of the clothing sold by each candidate seller to serve as the influence coefficient in the comprehensive recommendation coefficient of the candidate seller in the aspect of price, so that the problem that the price advantage of the commodity sold by each candidate seller cannot be reflected at the core caused by only taking the selling price as the influence coefficient in the aspect of price in the comprehensive recommendation coefficient of the candidate seller is solved, for example, under the same selling price, the price advantage of the commodity with the higher price reduction degree coefficient is more obvious, and the probability that a buyer user purchases the commodity with high quality and low price is improved.
S9, acquiring a transaction distance coefficient corresponding to the candidate seller: extracting the geographic position corresponding to each candidate seller from the selling parameter set of the candidate sellers, acquiring the geographic position of the buyer from purchasing information issued by the buyer, counting the logistics transportation distance between the buyer and each candidate seller according to the geographic position corresponding to each candidate seller and the geographic position of the buyer, comparing the obtained logistics transportation distance between the buyer and each candidate seller with the transaction distance coefficients corresponding to various logistics transportation distances in the transaction platform database, and screening out the transaction distance coefficient corresponding to each candidate seller;
s10, counting the corresponding comprehensive recommendation coefficients of the candidate sellers: according to the current comprehensive brand-new coefficient, the durability coefficient, the transaction credit coefficient, the price reduction degree coefficient and the transaction distance coefficient of the clothes sold by each candidate seller, calculating the comprehensive recommendation coefficient corresponding to each candidate seller
ψiExpressed as the comprehensive recommendation coefficient corresponding to the ith candidate seller,
λi、σi、ξi、
the method comprises the steps that a, b, c, d and e respectively represent a current comprehensive brand-new coefficient, a durability coefficient, a price reduction force coefficient, a transaction credit coefficient and a transaction distance coefficient of clothing sold by the ith candidate seller, a recommendation weight coefficient corresponding to the current comprehensive brand-new coefficient, the durability coefficient, the price reduction force coefficient, the transaction credit coefficient and the transaction distance coefficient of the clothing sold by the seller is represented by a, b, c, d and e respectively, a + b + c + d + e is 1, a > b > c > d > e, and then the candidate sellers are ranked according to the sequence of the comprehensive recommendation coefficients from large to small to obtain a recommendation ranking result of the candidate sellers, and the recommendation ranking result is pushed to a child second-hand clothing transaction platform interface corresponding to an account number of a buyer user according to account number information registered by the buyer user on the child second-hand clothing transaction platform.
The comprehensive recommendation coefficients corresponding to the candidate sellers counted by the embodiment synthesize the current comprehensive brand-new coefficient, the durability coefficient, the transaction credit coefficient, the price reduction degree coefficient and the transaction distance coefficient of the clothes sold by the candidate sellers, embody the comprehensive matching recommendation of the candidate sellers, realize the quantitative display of the comprehensive matching degree of the candidate sellers, make up the defect that the current online second-hand transaction platform recommendation mode is too simple, reduce the screening range of buyer users in the recommendation result, improve the screening efficiency of the buyer users, improve the comprehensive matching degree of the recommendation result on the one hand, improve the comprehensive value of the recommendation result on the other hand, greatly enhance the purchasing experience of the buyer users, and further improve the recommendation level of the online second-hand transaction platform.
A second aspect of the present invention provides a cloud server, where the cloud server includes a processor, a machine-readable storage medium, and a network interface, where the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one online commodity intelligent matching recommendation device, the machine-readable storage medium is used to store a program, an instruction, or a code, such as a program instruction/module corresponding to the online commodity intelligent matching recommendation method based on user behavior analysis in this embodiment of the present invention, and the processor is used to execute the program, the instruction, or the code in the machine-readable storage medium, so as to execute the online commodity intelligent matching recommendation method based on user behavior analysis.
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 (9)
1. An online commodity intelligent matching recommendation method based on user behavior analysis is characterized by comprising the following steps: the method comprises the following steps:
s1, buyer purchase clothing information publishing: acquiring account information registered by a buyer user on a second-hand-used children garment transaction platform, and acquiring shopping garment information issued by the buyer user on the second-hand-used children garment transaction platform, wherein the issued shopping garment information comprises garment type, child age, child gender and issuing duration;
s2, counting candidate sellers: acquiring user information of all sellers on a second-hand clothing transaction platform for children, numbering, acquiring types, suitable ages of children, suitable sexes of children and issuing dates of the sellers, and acquiring current dates, and calculating issuing duration of the sellers for selling the clothing according to the issuing dates and the current dates of the sellers for selling the clothing, so that the clothing-buying information issued by the buyers is respectively matched with the types, suitable ages of children, suitable sexes of children and issuing durations of the sellers corresponding to the sellers for selling the clothing one by one, and the sellers meeting the clothing-buying information of the buyers are screened out and marked as candidate sellers, and the numbers of the candidate sellers are counted and marked as 1,2.
S3, selling candidate sellersAnd (3) parameter set construction: obtaining the purchase date, purchase price, clothing image at purchase time, clothing image at present release time, sale price, seller credit level and seller geographic position of the clothing corresponding to the candidate seller from the clothing sale information corresponding to each candidate seller respectively to form a candidate seller sale parameter set Qu(qu1,qu2,…,qui,…,qun)，qui is data corresponding to the sale parameters of the ith candidate seller, u is the sale parameters, and u is p1, p2, p3, p4, p5, p6 and p7 which are respectively represented as a purchase date, a purchase price, a clothing image at the time of purchase, a clothing image at the time of current release, a sale price, a seller credit rating and a seller geographic position;
s4, the use duration of clothes sold by candidate sellers is counted: respectively extracting the purchase date of the clothing sold by each candidate seller from the sale parameter set of the candidate sellers, and acquiring the current date, thereby counting the service life of the clothing sold by each candidate seller;
s5, analyzing and counting the current comprehensive brand new coefficient of the clothes sold by the candidate seller correspondingly: respectively extracting a clothing image when each candidate seller corresponds to the clothing sold by the seller and a clothing image when the clothing is issued currently from a candidate seller selling parameter set, comparing the clothing image when each candidate seller corresponds to the clothing sold by the seller with the clothing image when the clothing is issued currently, checking whether damage and stains exist, focusing the clothing image when each candidate seller corresponds to the clothing sold by the seller at the current time in a damaged and stained area if the damage and stains exist, simultaneously extracting the outline of the damaged area and the outline of the stain area, thereby obtaining the damaged area and the stain area corresponding to the clothing when the clothing is issued by each candidate seller at the current time, obtaining the clothing surface area when each candidate seller corresponds to the clothing sold by the seller at the current time according to the clothing image when each candidate seller corresponds to the clothing sold by the seller at the current time, and counting the brand new coefficient of the current surface of each candidate seller corresponding to the clothing sold by the seller, at the same time, the color chroma of the clothes at the time of purchase and the color chroma of the clothes at the time of current release are obtained from the clothes image at the time of purchase and the clothes image at the time of current release of the clothes sold corresponding to each candidate seller, and the clothes images are obtained byCounting the brand-new coefficients of the current colors of the clothes sold by the candidate sellers, acquiring the size parameters of the clothes purchased from the clothes images of the clothes sold by the candidate sellers corresponding to the clothes, and forming a size parameter set G of the clothes purchased by the candidate sellersr(gr1,gr2,...,gri,...,grn)，gri is a numerical value corresponding to the clothes size parameter when the ith candidate seller sells the clothes for purchase, r is a size parameter, r is x1, x2, x3 and x4 which are respectively expressed as the clothes length, the sleeve length, the chest circumference and the waist circumference, the size parameter of the clothes at the current issuing time is obtained from the clothes image of the clothes at the current issuing time corresponding to each candidate seller, and a set G 'of the size parameter at the current issuing time of the clothes at the candidate seller for selling the clothes is formed'r(g′r1,g′r2,...,g′ri,...,g′rn)，g′ri represents a numerical value corresponding to the size parameter of the clothing sold by the ith candidate seller when the clothing is currently released, and therefore, the brand-new coefficient of the current size of the clothing sold by each candidate seller is counted according to the size parameter set when the clothing sold by the candidate seller is purchased and the size parameter set when the clothing sold by the candidate seller is currently released, and the brand-new coefficient of the current comprehensive of the clothing sold by each candidate seller is counted according to the brand-new coefficient of the current surface, the brand-new coefficient of the current color and the brand-new coefficient of the current size of the clothing sold by each candidate seller;
s6, carrying out statistics on durability coefficients of corresponding sold clothes by candidate sellers: according to the service duration of the clothes sold by each candidate seller and the current comprehensive brand new coefficient, the durability coefficient of the clothes sold by each candidate seller is counted;
s7, acquiring the corresponding transaction credit coefficient of the candidate seller: extracting the credit rating corresponding to each candidate seller from the selling parameter set of the candidate sellers, comparing the credit rating with the transaction credit coefficient corresponding to each credit rating in the transaction platform database, and screening out the transaction credit coefficient corresponding to each candidate seller;
s8, carrying out price reduction force coefficient statistics on the corresponding sold clothes of the candidate seller: extracting the purchase price and the sale price of the clothing sold by each candidate seller from the sale parameter set of the candidate sellers, and counting the price reduction coefficient of the clothing sold by each candidate seller according to the purchase price, the sale price and the use duration of the clothing sold by each candidate seller;
s9, acquiring a transaction distance coefficient corresponding to the candidate seller: extracting the geographic position corresponding to each candidate seller from the selling parameter set of the candidate sellers, acquiring the geographic position of the buyer from purchasing information issued by the buyer, counting the logistics transportation distance between the buyer and each candidate seller according to the geographic position corresponding to each candidate seller and the geographic position of the buyer, comparing the obtained logistics transportation distance between the buyer and each candidate seller with the transaction distance coefficients corresponding to various logistics transportation distances in the transaction platform database, and screening out the transaction distance coefficient corresponding to each candidate seller;
s10, counting the corresponding comprehensive recommendation coefficients of the candidate sellers: and counting the comprehensive recommendation coefficient corresponding to each candidate seller according to the current comprehensive brand-new coefficient, the durability coefficient, the transaction credit coefficient, the price reduction degree coefficient and the transaction distance coefficient of the clothing sold by each candidate seller, sequencing the candidate sellers according to the descending order of the comprehensive recommendation coefficient to obtain the recommendation sequencing result of each candidate seller, and pushing the recommendation sequencing result to the child second-hand clothing transaction platform interface corresponding to the buyer user account according to the account information registered by the buyer user on the child second-hand clothing transaction platform.
2. The online commodity intelligent matching recommendation method based on user behavior analysis as claimed in claim 1, wherein: the calculation formula of the brand-new coefficient of the current surface of the clothes sold by each candidate seller is
εiExpressed as the brand-new coefficient of the current surface of the corresponding sold clothing of the ith candidate seller, sdi、swi represents the damage area and stain area corresponding to the clothing when the clothing is sold by the ith candidate seller at the current release time, SiShowing the corresponding clothes selling of the ith candidate sellerSurface area of garment at front issue.
3. The online commodity intelligent matching recommendation method based on user behavior analysis as claimed in claim 1, wherein: the calculation formula of the brand-new coefficient of the current color of the clothes sold by each candidate seller is
χiExpressed as the current color brand-new coefficient of the ith candidate seller corresponding to the sold clothes, CiColor chromaticity of the clothing at the time of purchase, expressed as the ith candidate seller corresponding to the clothing sold, ciExpressed as the color shade of the current issue time clothing for the sale of clothing by the ith candidate seller.
4. The online commodity intelligent matching recommendation method based on user behavior analysis as claimed in claim 1, wherein: the calculation formula of the brand-new coefficient of the current size of the clothes sold by each candidate seller is as follows
δiExpressed as the brand-new coefficient of the current size of the corresponding sold clothing of the ith candidate seller.
5. The online commodity intelligent matching recommendation method based on user behavior analysis as claimed in claim 1, wherein: the calculation formula of the current comprehensive brand-new coefficient of the clothes sold by each candidate seller is
Expressed as the current comprehensive brand-new coefficient of the ith candidate seller corresponding to the sold clothes.
6. The method of claim 1The online commodity intelligent matching recommendation method based on user behavior analysis is characterized by comprising the following steps: the calculation formula of the durability coefficient of each candidate seller corresponding to the sold clothes is
λiExpressed as the durability coefficient of the corresponding sold clothing of the ith candidate seller, gamma is expressed as the brand-new coefficient of the predefined clothing at the time of purchase, and
Tithe length of use of the corresponding clothes selling time of the ith candidate seller is expressed.
7. The online commodity intelligent matching recommendation method based on user behavior analysis as claimed in claim 1, wherein: the calculation formula of the price reduction strength coefficient of the clothes sold by each candidate seller is
σiThe price reduction force coefficient, q, of the corresponding sold clothing of the ith candidate seller is expressedp2i、qp5i is respectively expressed as the purchase price and the sale price of the clothing sold by the ith candidate seller, TiThe length of use of the corresponding clothes selling time of the ith candidate seller is expressed.
8. The online commodity intelligent matching recommendation method based on user behavior analysis as claimed in claim 1, wherein: the calculation formula of the comprehensive recommendation coefficient corresponding to each candidate seller is
ψiExpressed as the comprehensive recommendation coefficient corresponding to the ith candidate seller,
、λi、σi、ξi、
the comprehensive brand-new coefficient, the durability coefficient, the price reduction force coefficient, the transaction credit coefficient and the transaction distance coefficient are respectively expressed as the current comprehensive brand-new coefficient, the durability coefficient, the price reduction force coefficient, the transaction credit coefficient and the transaction distance coefficient of the corresponding clothing sold by the ith candidate seller, a, b, c, d and e are respectively expressed as the recommendation weight coefficients corresponding to the current comprehensive brand-new coefficient, the durability coefficient, the price reduction force coefficient, the transaction credit coefficient and the transaction distance coefficient of the clothing sold by the seller, a + b + c + d + e is 1, and a > b > c > d > e.
9. A cloud server, characterized by: the cloud server comprises a processor, a machine-readable storage medium and a network interface, wherein the machine-readable storage medium, the network interface and the processor are connected through a bus system, the network interface is used for being in communication connection with at least one online commodity intelligent matching recommendation device, the machine-readable storage medium is used for storing programs, instructions or codes, and the processor is used for executing the programs, the instructions or the codes in the machine-readable storage medium so as to execute the online commodity intelligent matching recommendation method based on the user behavior analysis according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110357227.1A CN113052657B (en) | 2021-04-01 | 2021-04-01 | Online commodity intelligent matching recommendation method based on user behavior analysis and cloud server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110357227.1A CN113052657B (en) | 2021-04-01 | 2021-04-01 | Online commodity intelligent matching recommendation method based on user behavior analysis and cloud server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113052657A CN113052657A (en) | 2021-06-29 |
| CN113052657B true CN113052657B (en) | 2021-12-21 |
Family
ID=76517524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110357227.1A Active CN113052657B (en) | 2021-04-01 | 2021-04-01 | Online commodity intelligent matching recommendation method based on user behavior analysis and cloud server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113052657B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113487390B (en) * | 2021-08-02 | 2024-02-23 | 深圳市唯忆珠宝科技有限公司 | Jewelry seller recommendation method, device, equipment and storage medium |
| CN116012085B (en) * | 2023-02-01 | 2023-12-12 | 南京木美传媒科技有限公司 | Automatic identification and recovery system for electronic card |
| CN116012034A (en) * | 2023-03-23 | 2023-04-25 | 北京装库创意科技有限公司 | Distribution transaction method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699501A (en) * | 2006-12-19 | 2010-04-28 | 姜伟 | Old goods internet sale system and use method thereof |
| CN104778594A (en) * | 2015-04-30 | 2015-07-15 | 刘寅华 | Novel intelligent online clothes shopping platform system and method |
| CN105989528A (en) * | 2015-02-06 | 2016-10-05 | 白忠泽 | Article transfer method based on mobile Internet and system thereof |
| CN106886825A (en) * | 2017-04-01 | 2017-06-23 | 贵州大学 | A kind of waste mold transaction recovery system and its transaction recovery method |
| CN109087144A (en) * | 2018-08-10 | 2018-12-25 | 广州朗讯猛虎汽车检测有限公司 | A kind of detection of used car and valuation system |
| CN110046934A (en) * | 2019-04-10 | 2019-07-23 | 杭州估估宝电子商务有限公司 | A kind of idle clothing valuation system and method based on data mining |
| CN112200329A (en) * | 2020-10-28 | 2021-01-08 | 李亚辉 | Reverse logistics system for recycling and resale of old commodities |
| CN112381589A (en) * | 2020-12-04 | 2021-02-19 | 南京浪脆电子商务有限公司 | Intelligent commodity evaluation management system of commodity transaction platform based on cloud computing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140316946A1 (en) * | 2013-04-23 | 2014-10-23 | Christine M. Sanders | Event-driven sales platform and notification system and method |
-
2021
- 2021-04-01 CN CN202110357227.1A patent/CN113052657B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699501A (en) * | 2006-12-19 | 2010-04-28 | 姜伟 | Old goods internet sale system and use method thereof |
| CN105989528A (en) * | 2015-02-06 | 2016-10-05 | 白忠泽 | Article transfer method based on mobile Internet and system thereof |
| CN104778594A (en) * | 2015-04-30 | 2015-07-15 | 刘寅华 | Novel intelligent online clothes shopping platform system and method |
| CN106886825A (en) * | 2017-04-01 | 2017-06-23 | 贵州大学 | A kind of waste mold transaction recovery system and its transaction recovery method |
| CN109087144A (en) * | 2018-08-10 | 2018-12-25 | 广州朗讯猛虎汽车检测有限公司 | A kind of detection of used car and valuation system |
| CN110046934A (en) * | 2019-04-10 | 2019-07-23 | 杭州估估宝电子商务有限公司 | A kind of idle clothing valuation system and method based on data mining |
| CN112200329A (en) * | 2020-10-28 | 2021-01-08 | 李亚辉 | Reverse logistics system for recycling and resale of old commodities |
| CN112381589A (en) * | 2020-12-04 | 2021-02-19 | 南京浪脆电子商务有限公司 | Intelligent commodity evaluation management system of commodity transaction platform based on cloud computing |
Non-Patent Citations (1)
| Title |
|---|
| 基于MVC三层架构的校园电子商务平台的设计与实现;林豪杰;《中国优秀硕士学位论文全文数据库（电子期刊）（信息科技辑）》;20120630;I138-1027 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113052657A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113052657B (en) | Online commodity intelligent matching recommendation method based on user behavior analysis and cloud server | |
| Tan et al. | Impact of live chat on purchase in electronic markets: The moderating role of information cues | |
| Indarto et al. | The effect of brand image and product attributes on customer satisfaction and customer loyalty | |
| CN102741874B (en) | For using mobile device to buy the system and method for product from retail division | |
| Fan et al. | Trade liberalization and firms’ export performance in China: Theory and evidence | |
| US20140040160A1 (en) | System and method of rating a product | |
| CN110766428A (en) | Data value evaluation system and method | |
| JP4597427B2 (en) | Product assessment method, sales method with product assessment function and product assessment system | |
| CN112785336A (en) | Internet consignment transaction platform and method for ancient and modern artworks | |
| CN112506997B (en) | Big data user mining method based on cross-border e-commerce platform | |
| CN110866220A (en) | Selection recommendation system in e-commerce activity process | |
| US20200104892A1 (en) | Group reverse auction shopping method and implementation on a computer network | |
| JP6085802B2 (en) | Method and system for identifying defective products based on user purchase behavior | |
| CN108280691A (en) | A kind of designer's brand B2C2B is wholesale and community is sold platform | |
| CN108765086A (en) | A kind of credit assessment method of 7 degree of freedom one | |
| Savel’eva et al. | Method of determining the efficiency of price and non-price competition in service sector | |
| CN111695937A (en) | Method, device and computer readable storage medium for analyzing user buyback | |
| CN112750015A (en) | Electronic transaction system for ferrous metal material | |
| CN110728560A (en) | Agricultural product transaction management system based on Internet of things | |
| Kim et al. | An online sales platform based design of limited edition production and sales systems | |
| Hariadi et al. | Determinants of Online Purchase Intention in Indonesia | |
| Kaushik et al. | Online Auction System with AI | |
| KR102600682B1 (en) | Intelligent price information comparison server for open market sales manager and its program | |
| KR20030046242A (en) | System for providing consumer satisfaction for commodity and system for rewarding customer by usin g lottery providing higher priority to earlier purchaser based on purchase information | |
| CN116308466B (en) | Data information acquisition and intelligent analysis method, system, equipment and storage 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: 20211202 Address after: 518000 the 11th floor of Zhongdian Difu building, Zhenhua Road, Fuqiang community, Huaqiang North Street, Futian District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Wooke Extraordinary Technology Co.,Ltd. Address before: 430200 Hongqi village, Daqiao New District, Jiangxia Economic Development Zone, Wuhan City, Hubei Province Applicant before: Wuhan changlai e-commerce Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An online product intelligent matching recommendation method based on user behavior analysis and cloud server Effective date of registration: 20220720 Granted publication date: 20211221 Pledgee: Shenzhen small and medium sized small loan Co.,Ltd. Pledgor: Shenzhen Wooke Extraordinary Technology Co.,Ltd. Registration number: Y2022440020133 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20231226 Granted publication date: 20211221 Pledgee: Shenzhen small and medium sized small loan Co.,Ltd. Pledgor: Shenzhen Wooke Extraordinary Technology Co.,Ltd. Registration number: Y2022440020133 |