CN114648391A - Online shopping information recommendation method - Google Patents

Online shopping information recommendation method Download PDF

Info

Publication number
CN114648391A
CN114648391A CN202210538239.9A CN202210538239A CN114648391A CN 114648391 A CN114648391 A CN 114648391A CN 202210538239 A CN202210538239 A CN 202210538239A CN 114648391 A CN114648391 A CN 114648391A
Authority
CN
China
Prior art keywords
commodity
performance data
data
recommended
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210538239.9A
Other languages
Chinese (zh)
Other versions
CN114648391B (en
Inventor
陈妍
周黎耀
文泽雄
罗雪琴
金赞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University of Technology
Original Assignee
Hunan University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan University of Technology filed Critical Hunan University of Technology
Priority to CN202210538239.9A priority Critical patent/CN114648391B/en
Publication of CN114648391A publication Critical patent/CN114648391A/en
Application granted granted Critical
Publication of CN114648391B publication Critical patent/CN114648391B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides an online shopping information recommendation method, which belongs to the technical field of online shopping commodity recommendation. Extracting corresponding influence factors from the data of purchased commodities, then extracting points of interest purchased by the user from the influence factors and the related attributes, carrying out measurement of variation trend and commodity data screening according to the processing related attributes and the recommended commodities to obtain performance attribute data of the recommended commodities, and then determining the recommended commodities by combining with the actual consumption capacity and habits of the user.

Description

Online shopping information recommendation method
Technical Field
The invention relates to the technical field of online shopping commodity recommendation, in particular to an online shopping information recommendation method.
Background
With the continuous expansion of the electronic commerce scale, the number and the types of the commodities are rapidly increased, and a customer needs to spend a great deal of time to find the commodity which the customer wants to buy. This process of browsing through large amounts of unrelated information and products will undoubtedly result in a constant loss of consumers who are overwhelmed by the problem of information overload.
The existing recommendation systems mainly recommend users by using historical purchase records of the users and social network relations of the users, and the methods can only passively predict and recommend commodities purchased by the users next time, and can rarely guide or attract the users to select to purchase some commodities. In the existing recommendation method, the user preference is analyzed by utilizing the similarity between purchased commodities, but the relationship among the purchased commodities is ignored, and the commodities are not independent but have a dependency relationship. Such as: when choosing to buy the jacket, we analyze whether the jacket is more harmonious with the purchased lower clothes, shoes and accessories, and then choose whether to buy the jacket. The commodity with high score is not combined with any other commodity to be high score, and the commodity with medium score is not combined with any other commodity to be medium score, so that the commodity with medium score is possibly combined to be high score. The combination of these commodities is not simply a linear addition, but a non-linear relationship, and some commodity combinations are even exponential increasing relationships. If it is considered that the purchased goods cannot be matched with any goods or matched with any goods in a moderate way, the user cannot use the purchased goods to the maximum extent, and the purchased goods can only become transparent.
In addition, while some recommendations are about collocation, artificial collocation criteria and picture convolution are used, and the resulting collocation combinations are subjectively and harmonically collocated commodity combinations and are not targeted to a particular target user.
Disclosure of Invention
The invention aims to provide an online shopping information recommendation method, which solves the technical problems mentioned in the background technology.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a method for recommending online shopping information comprises the following steps:
step 1: collecting purchased commodity data of a user and analyzing factor data influencing purchase;
step 2: designing and recommending a target commodity according to user information, and analyzing influence factors of the target commodity;
and step 3: calculating the relevant attributes and influence weights of commodity purchase according to the collected purchased commodity data of the user;
and 4, step 4: trend comparison is carried out on the relative attributes of the purchased commodities to obtain the quantity of all commodity performance data, and then the quantity of all commodity performance data is compared with the performance data of the recommended target commodity sold on the network to obtain the quantity of clustered commodity performance data;
and 5: summing the data quantity of the performance of the clustered commodities, and then combining the influence factors of the priceX k Namely accurately recommended goods.
Further, the specific process of step 1 is: collecting data set of commodity kinds purchased by usercaseIs shown as
Figure 563155DEST_PATH_IMAGE001
，mFor the number of commodity types, each commodity type comprises performance data, commodity attribution and price data of the commodity, and the data are collectedcaseFactoring into priceX k And performance dataY j Whereink =1，2，...，t，tIndicating the number of price influencing factors, whereinj =1，2，...，n，nNumber representing performance parameter, user-associated data sampleS i The corresponding recommended ordinal number data are respectivelyx ik Andy ij 。
further, the specific process of step 2 is: according to user basic informationInformation, time information and user daily behavior information are used for designing a target recommended commodity, then performance data of the target recommended commodity is obtained and becomes target performance data, and the corresponding value isy joFrom the influence of priceX k The related attribute directly influencing the target performance data is selected and set as
Figure 145446DEST_PATH_IMAGE002
。
Further, the specific process of step 3 is: selecting commodity category data set purchased by usercasePerformance data and associated attributes in
Figure 539518DEST_PATH_IMAGE003
The corresponding data is expressed as case*Based on entropy weight method and data set case*Computing a commodity category datasetcaseSelected correlation attributes
Figure 232668DEST_PATH_IMAGE002
Weight of, distinguish
Figure 284979DEST_PATH_IMAGE002
The influence degree on the performance data and the weight of the obtained related attribute are recorded as
Figure 38171DEST_PATH_IMAGE004
。
Further, the specific process of step 4 is: performing correlation attributes
Figure 919540DEST_PATH_IMAGE003
The method comprises the steps of measuring relative variation trends and screening commodity data, wherein the commodity performance data are regarded as an N-dimensional variable set, and differences of different commodity performance data can be regarded asNResults of dimensional variable movement, change and development, based on the correlation attributes
Figure 681959DEST_PATH_IMAGE002
Calculating and measuring the original purchased commodity performance data of the user and the target commodity performance number to be recommendedAccording to the relative change trend of the relevant attributes, screening out the commodity performance data with the degree of the relative change trend of the relevant attributes of the commodity performance data to be recommended, and setting the commodity performance data to be the most similar to the relative change trend of the relevant attributes of the commodity performance data to be recommendedS * ={S 1 * ，S 2 * ，...，S p * }，pThe amount of commodity performance data obtained for clustering.
Further, the specific process of step 5 is: for clustering resultsS * ={S 1 * ，S 2 * ，...，S p * Weighting and clustering, then weighting and summing the clustering results to obtain a summation result which is the commodity performance data required to be recommended, and then combining the influence factors of the priceX k And obtaining the recommended specific commodity.
Further, in step 1, the influence factor of the priceX k And performance dataY j Using the feature variable training model as the data input of the training model, calculating the importance ranking standard of each feature variable, eliminating the least important K features, retaining the rest features, judging the number of the rest features to meet the purchasing requirement, and if the number of the rest features meets the purchasing requirement, determining the influence factor of the priceX k To select performance dataY j Is related to the attribute
Figure 332384DEST_PATH_IMAGE002
And if not, repeating the calculation.
Further, the weight distribution process of the correlation attribute based on the entropy weight method is as follows:
step 3.1: form a new matrix according to the following formula
Figure 990898DEST_PATH_IMAGE005
：
Figure 359562DEST_PATH_IMAGE006
Step 3.2: by polarization method
Figure 394515DEST_PATH_IMAGE005
Normalizing to obtain a new matrix
Figure 663560DEST_PATH_IMAGE007
Then to carry out
Figure 492975DEST_PATH_IMAGE007
The normalization process, the range differentiation method, and the normalization method are as follows:
Figure 348936DEST_PATH_IMAGE008
Figure 187579DEST_PATH_IMAGE009
；
wherein the content of the first and second substances,
Figure 547016DEST_PATH_IMAGE010
is composed of
Figure 812912DEST_PATH_IMAGE011
ToiGo to the firstsA column element;
Figure 625011DEST_PATH_IMAGE012
is composed of
Figure 267344DEST_PATH_IMAGE011
To (1)sColumns; in the same way, the method for preparing the composite material,
Figure 245403DEST_PATH_IMAGE013
is composed of
Figure 682200DEST_PATH_IMAGE007
To (1)iGo to the firstsThe elements of the column are, in turn,
Figure 247174DEST_PATH_IMAGE014
is composed of
Figure 693198DEST_PATH_IMAGE015
Normalized values;
step 3.3: then
Figure 761649DEST_PATH_IMAGE003
To middlesThe information entropy of the relevant attribute is defined as:
Figure 369347DEST_PATH_IMAGE016
step 3.4: performance dataY j Is provided withsThe related attributes are set as influencing factorsX c For performance dataY j The influence weight of (a) is:
Figure 421617DEST_PATH_IMAGE017
Figure 140174DEST_PATH_IMAGE018
is a factor of influenceX c The entropy of information of (1).
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
the method extracts corresponding influence factors from the data of purchased commodities, extracts points of interest purchased by the user from the influence factors and related attributes, selects recommended commodity categories according to actual conditions, performs trend measurement and commodity data screening according to the processing of the related attributes and the recommended commodities to obtain performance attribute data of the recommended commodities, and then determines the recommended commodities by combining the actual consumption capacity and habits of the user.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings by way of examples of preferred embodiments. It should be noted, however, that the numerous details set forth in the description are merely for the purpose of providing the reader with a thorough understanding of one or more aspects of the present invention, which may be practiced without these specific details.
As shown in fig. 1, a method for recommending online shopping information includes the following steps:
step 1: data of purchased goods of a user is collected and factor data affecting the purchase is analyzed. Collecting data set of commodity kinds purchased by usercaseIs shown as
Figure 92825DEST_PATH_IMAGE001
，mFor the number of commodity types, each commodity type comprises performance data, commodity attribution and price data of the commodity, and the data setscaseFactoring into priceX k And performance dataY j Whereink =1，2，...，t，tIndicating the number of price influencing factors, whereinj =1，2，...，n，nNumber representing performance parameter, user-associated data sampleS i The corresponding recommended ordinal number data are respectivelyx ik Andy ij . The collected data is the data purchased by the user on the internet, and if the data of the purchase sold off line can be counted, the data can be counted together. The performance data is the purpose bought by the user, and then the actual quoted purchase price is the consumption level and income of the user at ordinary times.
Step 2: and designing and recommending the target commodity according to the user information, and analyzing influence factors of the target commodity. Designing a target recommended commodity according to the basic information, the time information and the daily behavior information of the user, then obtaining the performance data of the target recommended commodity to become target performance data, wherein the corresponding value isy joFrom the influence of priceX k The related attribute directly influencing the target performance data is selected and set as
Figure 871425DEST_PATH_IMAGE002
. Influence factor of priceX k And performance dataY j Using the feature variable training model as the data input of the training model, calculating the importance ranking standard of each feature variable, eliminating the least important K features, retaining the rest features, judging the number of the rest features to meet the purchasing requirement, and if the number of the rest features meets the purchasing requirement, determining the influence factor of the priceX k To select performance dataY j Is related to the attribute
Figure 410991DEST_PATH_IMAGE002
And if not, repeating the calculation.
And step 3: and calculating the related attributes and the influence weight of the commodity purchase according to the collected purchased commodity data of the user. Selecting commodity category data set purchased by usercasePerformance data and associated attributes in
Figure 933239DEST_PATH_IMAGE003
The corresponding data is expressed as case*Based on entropy weight method and data set case*Calculating a commodity category datasetcaseSelected correlation attributes
Figure 241860DEST_PATH_IMAGE002
Weight of (2), differentiation
Figure 988099DEST_PATH_IMAGE002
The influence degree on the performance data and the weight of the obtained related attribute are recorded as
Figure 749382DEST_PATH_IMAGE004
。
Step 3.1: form a new matrix according to the following formula
Figure 75321DEST_PATH_IMAGE005
：
Figure 238449DEST_PATH_IMAGE006
Step 3.2: by polarization method
Figure 857387DEST_PATH_IMAGE005
Normalizing to obtain a new matrix
Figure 371545DEST_PATH_IMAGE007
Then to carry out
Figure 970017DEST_PATH_IMAGE007
The normalization process, the range differentiation method, and the normalization method are as follows:
Figure 987651DEST_PATH_IMAGE008
Figure 810114DEST_PATH_IMAGE009
；
wherein the content of the first and second substances,
Figure 280409DEST_PATH_IMAGE010
is composed of
Figure 213730DEST_PATH_IMAGE011
To (1)iGo to the firstsA column element;
Figure 820292DEST_PATH_IMAGE012
is composed of
Figure 46612DEST_PATH_IMAGE011
To (1)sColumns; in the same way, the method for preparing the composite material,
Figure 269783DEST_PATH_IMAGE013
is composed of
Figure 475636DEST_PATH_IMAGE007
To (1)iGo to the firstsThe elements of the column are, in turn,
Figure 467863DEST_PATH_IMAGE014
is composed of
Figure 366549DEST_PATH_IMAGE015
Normalized values;
step 3.3: then the
Figure 811437DEST_PATH_IMAGE003
To middlesThe information entropy of the relevant attribute is defined as:
Figure 617719DEST_PATH_IMAGE016
step 3.4: performance dataY j Is provided withsSetting the influence factor according to the correlation attributeX c For performance dataY j The influence weight of (a) is:
Figure 933294DEST_PATH_IMAGE017
Figure 534039DEST_PATH_IMAGE018
is a factor of influenceX c The entropy of the information of (c).
And 4, step 4: and performing trend comparison on the relative attributes of the purchased commodities to obtain the quantity of all commodity performance data, and then comparing the quantity of all commodity performance data with the performance data of the recommended target commodity sold on the network to obtain the quantity of the clustered commodity performance data. Performing correlation attributes
Figure 433600DEST_PATH_IMAGE003
And (4) measuring relative change trend and screening commodity data. The specific process of measuring the change trend and screening the commodity data comprises the following steps: noting relevant attributes of target performance data for recommended goods
Figure 777993DEST_PATH_IMAGE003
Data of
Figure 948075DEST_PATH_IMAGE019
Target data, selecting a group of data relatively close to the target data from the cases as a comparison reference according to the difference rate, wherein the selection principle is to make the reference
Figure 719722DEST_PATH_IMAGE020
The smaller the difference from the value of the alignment property in O, the better. For each one
Figure 404781DEST_PATH_IMAGE021
Adding a row and associated variables
Figure 756128DEST_PATH_IMAGE022
Dimension identical label
Figure 577453DEST_PATH_IMAGE023
For recording data corresponding to the relevant attributes
Figure 988843DEST_PATH_IMAGE024
Relative to the change trend of the benchmark, and then dividing the related attribute data of each commodity data in case
Figure 394154DEST_PATH_IMAGE024
And a reference
Figure 283613DEST_PATH_IMAGE025
Each attribute data is correspondingly compared one by one and marked if
Figure 225024DEST_PATH_IMAGE026
Then, then
Figure 541736DEST_PATH_IMAGE027
Is + or is-and the same comparison is carried out, and the related attributes of the target data are measured
Figure 935808DEST_PATH_IMAGE019
Relative reference
Figure 628958DEST_PATH_IMAGE025
The relative trend of (2) is recorded as
Figure 424875DEST_PATH_IMAGE028
. Will be provided with
Figure 178068DEST_PATH_IMAGE029
And with
Figure 557971DEST_PATH_IMAGE030
The corresponding elements in (1) are compared one by one and judged
Figure 523653DEST_PATH_IMAGE029
And with
Figure 174077DEST_PATH_IMAGE030
Relative of middle correlation attribute
Figure 98171DEST_PATH_IMAGE019
Whether or not the change trends are the same, if
Figure 466836DEST_PATH_IMAGE027
And
Figure 501788DEST_PATH_IMAGE031
if both are + or-then will
Figure 6718DEST_PATH_IMAGE027
Rewriting to 1, otherwise will
Figure 101713DEST_PATH_IMAGE027
Rewritten to 0. According to each group of data, the label of the comparison result of the relative change trend of the related attributes of all the performance dataT i Are summed to obtainST i It is calculated as follows:
Figure 456209DEST_PATH_IMAGE032
ST i has a value of [ 2 ]0，s]Is an integer of at mosts，iIs a positive integer.
According to calculationST i By integer numerical sizeST i Grade, the larger the value, the higher the grade, the same valueST i Dividing into the same grade, descending according to grade, and screening before taking outK 1Of a gradeST i Value subscript thereofiCorresponding tocaseThe performance data of the at least one sensor,K 1is a positive integer which is a multiple of,
Figure 826010DEST_PATH_IMAGE033
is recorded asS * ={S 1 * ，S 2 * ，...，S p * }，pIs the number of performance data samples obtained.
The commodity performance data is regarded as an N-dimensional variable set, and the difference of different commodity performance data can be regarded asNResults of dimensional variable movements, changes and developments, according to the associated attributes
Figure 451027DEST_PATH_IMAGE002
Calculating and measuring the relative change trend of the related attributes of the original purchased commodity performance data of the user and the target commodity performance data to be recommended, screening out the commodity performance data which is closest to the degree of the relative change trend of the related attributes of the commodity performance data to be recommended, and setting the commodity performance data as the commodity performance data to be recommendedS * ={S 1 * ，S 2 * ，...，S p * }，pThe amount of commodity performance data obtained for clustering.
And 5: summing the quantity of the performance data of the clustered commodities, and then combining the influence factors of the priceX k Namely accurately recommended goods. For clustering resultsS * ={S 1 * ，S 2 * ，...，S p * Weighting and clustering, then weighting and summing the clustering results to obtain a summation result which is the commodity performance data required to be recommended, and then combining the influence factors of the priceX k And obtaining the recommended specific commodity.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.

Claims (8)

1. A method for recommending online shopping information is characterized by comprising the following steps:
step 1: collecting purchased commodity data of a user and analyzing factor data influencing purchase;
step 2: designing and recommending a target commodity according to user information, and analyzing influence factors of the target commodity;
and step 3: calculating the relevant attributes and influence weights of commodity purchase according to the collected purchased commodity data of the user;
and 4, step 4: trend comparison is carried out on the relative attributes of the purchased commodities to obtain the quantity of all commodity performance data, and then the quantity of all commodity performance data is compared with the performance data of the recommended target commodity sold on the network to obtain the quantity of clustered commodity performance data;
and 5: summing the data quantity of the performance of the clustered commodities, and then combining the influence factors of the priceX k Namely accurately recommended goods.
2. The online shopping information recommending method according to claim 1, characterized in that: the specific process of the step 1 is as follows: collecting data set of commodity kinds purchased by usercaseIs shown as
Figure 793194DEST_PATH_IMAGE001
，mThe number of commodity types per unitEach commodity type includes performance data, commodity attribution and price data of the commodity, and the data setcaseFactoring into priceX k And performance dataY j Whereink =1，2，...，t，tIndicating the number of price influencing factors, whereinj =1，2，...， n，nNumber representing performance parameter, user-associated data sampleS i The corresponding recommended ordinal number data are respectivelyx ik Andy ij 。
3. the online shopping information recommendation method according to claim 1, characterized in that: the specific process of the step 2 is as follows: designing a target recommended commodity according to the basic information, the time information and the daily behavior information of the user, then obtaining the performance data of the target recommended commodity to become target performance data, wherein the corresponding value isy joFrom the influence of priceX k Selecting the related attribute directly influencing the target performance data, and setting the related attribute as
Figure 241493DEST_PATH_IMAGE002
。
4. The online shopping information recommendation method according to claim 1, characterized in that: the specific process of the step 3 is as follows: selecting commodity category data set purchased by usercasePerformance data and associated attributes in
Figure 926290DEST_PATH_IMAGE003
The corresponding data is expressed as case*Based on entropy weight method and data set case*Computing a commodity category datasetcaseSelected correlation attributes
Figure 852658DEST_PATH_IMAGE002
Weight of, distinguish
Figure 339134DEST_PATH_IMAGE002
The influence degree on the performance data and the weight of the obtained related attribute are recorded as
Figure 692755DEST_PATH_IMAGE004
。
5. The online shopping information recommendation method according to claim 1, characterized in that: the specific process of the step 4 is as follows: performing correlation attributes
Figure 366313DEST_PATH_IMAGE003
The commodity performance data is regarded as an N-dimensional variable set, and the difference of different commodity performance data can be regarded asNResults of dimensional variable movement, change and development, based on the correlation attributes
Figure 96371DEST_PATH_IMAGE002
Calculating and measuring the relative change trend of the related attributes of the original purchased commodity performance data of the user and the target commodity performance data to be recommended, screening out the commodity performance data which is closest to the degree of the relative change trend of the related attributes of the commodity performance data to be recommended, and setting the commodity performance data as the commodity performance data to be recommendedS * ={S 1 * ，S 2 * ，...，S p * }，pThe amount of commodity performance data obtained for clustering.
6. The online shopping information recommendation method according to claim 1, characterized in that: the specific process of the step 5 is as follows: for clustering resultsS * ={S 1 * ，S 2 * ，...，S p * Weighting and clustering, then weighting and summing the clustering results to obtain a summation result which is the commodity performance data required to be recommended, and then combining the influence factors of the priceX k And obtaining the recommended specific commodity.
7. The online shopping information recommendation method according to claim 3, characterized in that: in step 1, the influence factor of the priceX k And performance dataY j Using the feature variable training model as the data input of the training model, calculating the importance ranking standard of each feature variable, eliminating the least important K features, retaining the rest features, judging the number of the rest features to meet the purchasing requirement, and if the number of the rest features meets the purchasing requirement, determining the influence factor of the priceX k To select performance dataY j Is related to the attribute
Figure 171775DEST_PATH_IMAGE002
And if not, repeating the calculation.
8. The online shopping information recommendation method according to claim 4, characterized in that: the weight distribution process of the correlation attribute based on the entropy weight method comprises the following steps:
step 3.1: form a new matrix according to the following formula
Figure 696297DEST_PATH_IMAGE005
：
Figure 355686DEST_PATH_IMAGE006
Step 3.2: by polarization method
Figure 623856DEST_PATH_IMAGE005
Normalizing to obtain a new matrix
Figure 553766DEST_PATH_IMAGE007
Then to carry out
Figure 514769DEST_PATH_IMAGE007
The normalization treatment is carried out on the mixture,the range differentiation and normalization methods are as follows:
Figure 162919DEST_PATH_IMAGE008
Figure 172463DEST_PATH_IMAGE009
；
wherein the content of the first and second substances,
Figure 347093DEST_PATH_IMAGE010
is composed of
Figure 88784DEST_PATH_IMAGE011
ToiGo to the firstsA column element;
Figure 614443DEST_PATH_IMAGE012
is composed of
Figure 598317DEST_PATH_IMAGE011
To (1)sA column; in the same way, the method for preparing the composite material,
Figure 627453DEST_PATH_IMAGE013
is composed of
Figure 805625DEST_PATH_IMAGE007
To (1)iGo to the firstsThe number of column elements is such that,
Figure 287422DEST_PATH_IMAGE014
is composed of
Figure 576452DEST_PATH_IMAGE015
Normalized values;
step 3.3: then
Figure 663356DEST_PATH_IMAGE016
To middlesInformation entropy definition of correlation attributesComprises the following steps:
Figure 137063DEST_PATH_IMAGE017
step 3.4: performance dataY j Is provided withsThe related attributes are set as influencing factorsX c For performance dataY j The influence weight of (a) is:
Figure 981522DEST_PATH_IMAGE018
Figure 933298DEST_PATH_IMAGE019
is a factor of influenceX c The entropy of information of (1).
CN202210538239.9A 2022-05-18 2022-05-18 Online shopping information recommendation method Active CN114648391B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210538239.9A CN114648391B (en) 2022-05-18 2022-05-18 Online shopping information recommendation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210538239.9A CN114648391B (en) 2022-05-18 2022-05-18 Online shopping information recommendation method

Publications (2)

Publication Number Publication Date
CN114648391A true CN114648391A (en) 2022-06-21
CN114648391B CN114648391B (en) 2022-08-12

Family

ID=81996802

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210538239.9A Active CN114648391B (en) 2022-05-18 2022-05-18 Online shopping information recommendation method

Country Status (1)

Country Link
CN (1) CN114648391B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103412948A (en) * 2013-08-27 2013-11-27 北京交通大学 Cluster-based collaborative filtering commodity recommendation method and system
CN106897911A (en) * 2017-01-10 2017-06-27 南京邮电大学 A kind of self adaptation personalized recommendation method based on user and article
US20180053142A1 (en) * 2016-08-19 2018-02-22 Stitch Fix, Inc. Systems and methods for improving recommendation systems
CN109064285A (en) * 2018-08-02 2018-12-21 西北大学 A kind of acquisition commercial product recommending sequence and Method of Commodity Recommendation
CN110827129A (en) * 2019-11-27 2020-02-21 中国联合网络通信集团有限公司 Commodity recommendation method and device
CN111242732A (en) * 2020-01-09 2020-06-05 北京慧博科技有限公司 Commodity recommendation model-based recommendation method
CN111815415A (en) * 2020-07-14 2020-10-23 北京邮电大学 Commodity recommendation method, system and equipment
CN111861679A (en) * 2020-08-04 2020-10-30 深圳市创智园知识产权运营有限公司 Commodity recommendation method based on artificial intelligence
CN112085549A (en) * 2019-06-14 2020-12-15 上海逸宅网络科技有限公司 Commodity recommendation method for E-commerce platform based on data processing technology
CN112131480A (en) * 2020-09-30 2020-12-25 中国海洋大学 Personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning
CN112667899A (en) * 2020-12-30 2021-04-16 杭州智聪网络科技有限公司 Cold start recommendation method and device based on user interest migration and storage equipment

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103412948A (en) * 2013-08-27 2013-11-27 北京交通大学 Cluster-based collaborative filtering commodity recommendation method and system
US20180053142A1 (en) * 2016-08-19 2018-02-22 Stitch Fix, Inc. Systems and methods for improving recommendation systems
CN106897911A (en) * 2017-01-10 2017-06-27 南京邮电大学 A kind of self adaptation personalized recommendation method based on user and article
CN109064285A (en) * 2018-08-02 2018-12-21 西北大学 A kind of acquisition commercial product recommending sequence and Method of Commodity Recommendation
CN112085549A (en) * 2019-06-14 2020-12-15 上海逸宅网络科技有限公司 Commodity recommendation method for E-commerce platform based on data processing technology
CN110827129A (en) * 2019-11-27 2020-02-21 中国联合网络通信集团有限公司 Commodity recommendation method and device
CN111242732A (en) * 2020-01-09 2020-06-05 北京慧博科技有限公司 Commodity recommendation model-based recommendation method
CN111815415A (en) * 2020-07-14 2020-10-23 北京邮电大学 Commodity recommendation method, system and equipment
CN111861679A (en) * 2020-08-04 2020-10-30 深圳市创智园知识产权运营有限公司 Commodity recommendation method based on artificial intelligence
CN112131480A (en) * 2020-09-30 2020-12-25 中国海洋大学 Personalized commodity recommendation method and system based on multilayer heterogeneous attribute network representation learning
CN112667899A (en) * 2020-12-30 2021-04-16 杭州智聪网络科技有限公司 Cold start recommendation method and device based on user interest migration and storage equipment

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
R LIAN: "The construction of personalized web page recommendation system in e-commerce", 《RESTRICTIONS APPLY》 *
仲秋雁等: "考虑用户兴趣和能力的众包任务推荐方法", 《系统工程理论与实践》 *
王冬梅: "面向延时敏感投资者的KIA产品众筹周期与价格决策", 《系统工程学报》 *
石力: "社区电商用户复购行为预测及推荐算法研究", 《中国博士学位论文全文数据库 信息科技辑》 *

Also Published As

Publication number Publication date
CN114648391B (en) 2022-08-12

Similar Documents

Publication Publication Date Title
CN106485562B (en) Commodity information recommendation method and system based on user historical behaviors
Dogan et al. Customer segmentation by using RFM model and clustering methods: a case study in retail industry
CN108629665B (en) Personalized commodity recommendation method and system
Chen et al. Developing recommender systems with the consideration of product profitability for sellers
Adomavicius et al. Impact of data characteristics on recommender systems performance
Greenstein-Messica et al. Personal price aware multi-seller recommender system: Evidence from eBay
CN112667899A (en) Cold start recommendation method and device based on user interest migration and storage equipment
CN110148023A (en) The electric power integral Method of Commodity Recommendation and system that logic-based returns
CN116431931B (en) Real-time incremental data statistical analysis method
CN111724235A (en) Online commodity recommendation method based on user novelty
CN116452261B (en) Advertisement delivery data processing method based on cross-border E-commerce service platform
CN112100512A (en) Collaborative filtering recommendation method based on user clustering and project association analysis
CN116205675A (en) Data acquisition method and device based on thread division
CN115578163A (en) Personalized pushing method and system for combined commodity information
CN105303447A (en) Method and device for carrying out credit rating through network information
Kim et al. A new recommender system to combine content-based and collaborative filtering systems
Baier et al. Profit uplift modeling for direct marketing campaigns: approaches and applications for online shops
Gholamian et al. Improving electronic customers' profile in recommender systems using data mining techniques
CN114648391B (en) Online shopping information recommendation method
Zhao et al. Bank customer churn prediction based on support vector machine: Taking a commercial bank's VIP customer churn as the example
AlRossais et al. Improving cold-start recommendations using item-based stereotypes
Pinto et al. Hybrid recommendation system based on collaborative filtering and fuzzy numbers
Tang et al. Service recommendation based on dynamic user portrait: an integrated approach
Prabhu et al. FI-FCM algorithm for business intelligence
Taralik et al. Channel preferences and attitudes of domestic buyers in purchase decision processes of high-value electronic devices

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant