CN116883116A - Personalized commodity recommendation system driven by user behavior analysis and method thereof - Google Patents

Personalized commodity recommendation system driven by user behavior analysis and method thereof Download PDF

Info

Publication number
CN116883116A
CN116883116A CN202310917456.3A CN202310917456A CN116883116A CN 116883116 A CN116883116 A CN 116883116A CN 202310917456 A CN202310917456 A CN 202310917456A CN 116883116 A CN116883116 A CN 116883116A
Authority
CN
China
Prior art keywords
user
commodity
personalized
behavior data
module
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.)
Withdrawn
Application number
CN202310917456.3A
Other languages
Chinese (zh)
Inventor
汪庆伟
谢先正
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.)
Nanjing Smart Cloud Network Technology Co ltd
Original Assignee
Nanjing Smart Cloud Network Technology Co ltd
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 Nanjing Smart Cloud Network Technology Co ltd filed Critical Nanjing Smart Cloud Network Technology Co ltd
Priority to CN202310917456.3A priority Critical patent/CN116883116A/en
Publication of CN116883116A publication Critical patent/CN116883116A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to the technical field of intelligent recommendation, in particular to a personalized commodity recommendation system driven by user behavior analysis and a method thereof, comprising the following steps: the user behavior acquisition module: the method comprises the steps of collecting user behavior data; the behavior data processing module: the method is used for processing the collected user behavior data; the behavior data analysis module: the method is used for analyzing the processed user behavior data; and a personalized recommendation module: and the personalized commodity recommendation module is used for recommending personalized commodities to the user according to the analysis result of the behavior data analysis module. According to the invention, the behavior data analysis module is used for analyzing by taking the user behavior as a drive, mining and analyzing are carried out based on browsing information of the user and commodities possibly interested by the user, grading is carried out, and meanwhile, the personalized recommendation module is used for carrying out personalized recommendation of the commodities based on the relevance of regions and other users with similar behaviors, so that the accuracy of personalized recommendation is improved.

Description

Personalized commodity recommendation system driven by user behavior analysis and method thereof
Technical Field
The invention relates to the technical field of intelligent recommendation, in particular to a personalized commodity recommendation system driven by user behavior analysis and a method thereof.
Background
The world today is an informationized world, and the excessive amount of information makes the creation and solicitation of information challenging. The information creator wants the information created by the information creator to be available to others, and the information requester also wants to find the information needed by the information creator from a huge amount of information. How to quickly extract the information of interest from the information and recommend the information to the user in real time becomes a difficult problem to be solved. The personalized recommendation algorithm can track various operation data in the internet surfing process of the user, and recommend information which the user may be interested in to the user based on the operation data.
In the prior art, a common recommendation algorithm is a collaborative filtering algorithm based on items. The method is characterized in that preference similarity between adjacent items is calculated, and then similar items are recommended to a user to realize personalized recommendation. Compared with a collaborative filtering algorithm based on a user, the method has the advantages that the preference similarity result between adjacent items is more stable; the disadvantage is that the project update is faster and more numerous, computationally intensive. And new data can cause the change of the recommended result, and larger deviation of accuracy is easy to cause.
The invention provides a personalized commodity recommendation system driven by user behavior analysis and a method thereof, wherein the behavior data analysis module is used for analyzing by taking the user behavior as a drive, mining and analyzing are carried out on the basis of browsing information of a user and commodities possibly interested by the user, grading is carried out, and meanwhile, personalized recommendation of the commodities is carried out on the basis of the relevance of regions and other users with similar behaviors through the personalized recommendation module, so that the accuracy of personalized recommendation is improved.
Disclosure of Invention
The invention aims to solve the defects in the background technology by providing a personalized commodity recommendation system driven by user behavior analysis and a method thereof.
The technical scheme adopted by the invention is as follows:
provided is a personalized commodity recommendation system driven by user behavior analysis, comprising:
the user behavior acquisition module: the method comprises the steps of collecting user behavior data;
the behavior data processing module: the method is used for processing the collected user behavior data;
the behavior data analysis module: the method is used for analyzing the processed user behavior data;
and a personalized recommendation module: and the personalized commodity recommendation module is used for recommending personalized commodities to the user according to the analysis result of the behavior data analysis module.
As a preferred technical scheme of the invention: the user behavior data collected by the user behavior collection module comprises user basic information, browsing information of a user, search information, comment information, collection information, purchasing information and purchasing information, and the user behavior data set is formed together.
As a preferred technical scheme of the invention: and the behavior data processing module is used for carrying out data cleaning, outlier processing, data redundancy processing and data integration processing on the collected user behavior data.
As a preferred technical scheme of the invention: and the behavior data analysis module performs normalization processing based on the duration of browsing information of the user and scores the interest degree of the user on the commodity.
As a preferred technical scheme of the invention: the scoring process of the interest degree of the user on the commodity is specifically as follows:
setting the online total browsing duration t of the user i i The total page number of the commodity j searched by the user i is M, the browsing page number of the user i is M, the commodity information browsing time length is divided into M sections according to the browsing page number, and the total time length of the commodity j searched by the user i is t ij The total time required for complete browsing of the commodity j is t j The method comprises the steps of carrying out a first treatment on the surface of the The mathematical expectation of setting the duration of the user browsing information is browsing information scalar a:
wherein ,τk P is the average browsing duration in the kth time period k The ratio of the browsing duration to the total browsing duration in the kth time period;
setting up an interestingness scoring model based on user behavior analysis:
wherein ,δij Scoring function, t, for interest degree of user i on commodity j i Representing the total browsing duration of user i, p j Duration t of browsing commodity j for user ij Accounting for the total online browsing time t of the user i i Is a ratio of (2).
As a preferred technical scheme of the invention: the behavior data analysis module classifies scoring grades based on scoring results of the interestingness scoring model of the user behavior analysis.
As a preferred technical scheme of the invention: the grading of the scores is specifically as follows:
a: when delta ij When=0, the user has no interest, and score 0 is recorded;
b: when 0 is<δ ij When the interest level of the user is less than or equal to 0.2, 1 score is recorded;
c: when 0.2<δ ij When the interest degree of the user on the commodity j is less than or equal to 0.4, recording 2 points;
d: when 0.4<δ ij When the interest level of the user is less than or equal to 0.6, indicating that the interest level of the user is higher, and recording 3 points;
e: when 0.6<δ ij When the interest level of the user is less than or equal to 0.8, the interest level of the user is extremely high, and the score is recorded as 4;
f: when 0.8<δ ij When the interest level of the user is less than or equal to 1.0, the interest level of the user is extremely high, and 5 points are recorded.
As a preferred technical scheme of the invention: the personalized recommendation module radiates based on the distance between the user i and the commodity j:
wherein ,a radiation function d which is the distance between the user i and the commodity u iu For commodity u and useri, b and c are constants;
the scoring of the commodity u by the other users I with similar behaviors of the user I is obtained based on the following steps:
wherein sim (I, u) is the scoring similarity of user I and other users I having similar behaviors to user I to commodity u, Q iux×y and QIux×y The x y order scoring matrix for commodity u for user I and other user I with similar behavior to user I, and />The x multiplied by y order average scoring matrix is respectively used for the user I and other users I with similar behaviors;
fusing the geographic distance to recommend personalized commodities for the user:
wherein ,Riu For user i to predict score for commodity u, μ iu Scoring the interest level of user i for item u,and (5) the average value of scores of the user i on all commodity interest levels is obtained, and epsilon is a weight value.
As a preferred technical scheme of the invention: the personalized recommendation module is based on the predictive score R iu The recommendation is made to the user in order from high to low.
The personalized commodity recommending method driven by user behavior analysis comprises the following steps:
s1: collecting user behavior data through a user behavior collection module;
s2: the behavior data processing module processes the collected user behavior data;
s3: analyzing the processed user behavior data through a behavior data analysis module;
s4: and recommending personalized commodities to the user according to the prediction scoring sequence of the personalized recommendation module.
Compared with the prior art, the personalized commodity recommendation system and the personalized commodity recommendation method driven by user behavior analysis have the beneficial effects that:
according to the invention, the behavior data analysis module is used for analyzing by taking the user behavior as a drive, mining and analyzing are carried out based on browsing information of the user and commodities possibly interested by the user, grading is carried out, and meanwhile, the personalized recommendation module is used for carrying out personalized recommendation of the commodities based on the relevance of regions and other users with similar behaviors, so that the accuracy of personalized recommendation is improved.
Drawings
FIG. 1 is a system block diagram of a preferred embodiment of the present invention;
FIG. 2 is a flow chart of a method in a preferred embodiment of the invention.
The meaning of each label in the figure is: 100. a user behavior acquisition module; 200. a behavior data processing module; 300. a behavioral data analysis module; 400. and a personalized recommendation module.
Detailed Description
It should be noted that, under the condition of no conflict, the embodiments of the present embodiments and features in the embodiments may be combined with each other, and 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 obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a preferred embodiment of the present invention provides a personalized commodity recommendation system driven by user behavior analysis, comprising:
user behavior acquisition module 100: the method comprises the steps of collecting user behavior data;
behavior data processing module 200: the method is used for processing the collected user behavior data;
behavior data analysis module 300: the method is used for analyzing the processed user behavior data;
personalized recommendation module 400: and the system is used for recommending personalized commodities to the user according to the analysis result of the behavior data analysis module 300.
The user behavior data collected by the user behavior collection module 100 includes user basic information, browsing information of a user, search information, comment information, collection information, purchasing information and purchasing information, which together form a user behavior data set.
The behavior data processing module 200 performs data cleaning, outlier processing, data redundancy processing and data integration processing on the collected user behavior data.
The behavior data analysis module 300 performs normalization processing based on the duration of browsing information of the user, and scores the interest degree of the user on the commodity;
the scoring process of the interest degree of the user on the commodity is specifically as follows:
setting the online total browsing duration t of the user i i The total page number of the commodity j searched by the user i is M, the browsing page number of the user i is M, the commodity information browsing time length is divided into M sections according to the browsing page number, and the total time length of the commodity j searched by the user i is t ij The total time required for complete browsing of the commodity j is t j The method comprises the steps of carrying out a first treatment on the surface of the The mathematical expectation of setting the duration of the user browsing information is browsing information scalar a:
wherein ,τk P is the average browsing duration in the kth time period k The ratio of the browsing duration to the total browsing duration in the kth time period;
setting up an interestingness scoring model based on user behavior analysis:
wherein ,δij Scoring function, t, for interest degree of user i on commodity j i Representing the total browsing duration of user i, p j Duration t of browsing commodity j for user ij Accounting for the total online browsing time t of the user i i Is a ratio of (2).
The behavioral data analysis module 300 classifies scoring levels based on scoring results of the interestingness scoring model of the user behavioral analysis.
The grading of the scores is specifically as follows:
a: when delta ij When=0, the user has no interest, and score 0 is recorded;
b: when 0 is<δ ij When the interest level of the user is less than or equal to 0.2, 1 score is recorded;
c: when 0.2<δ ij When the interest degree of the user on the commodity j is less than or equal to 0.4, recording 2 points;
d: when 0.4<δ ij When the interest level of the user is less than or equal to 0.6, indicating that the interest level of the user is higher, and recording 3 points;
e: when 0.6<δ ij When the interest level of the user is less than or equal to 0.8, the interest level of the user is extremely high, and the score is recorded as 4;
f: when 0.8<δ ij When the interest level of the user is less than or equal to 1.0, the interest level of the user is extremely high, and 5 points are recorded.
The personalized recommendation module 400 radiates based on the distance between the user i and the commodity j:
wherein ,a radiation function d which is the distance between the user i and the commodity u iu The distances between the commodity u and the user i are constant, and b and c are constants;
the scoring of the commodity u by the other users I with similar behaviors of the user I is obtained based on the following steps:
wherein sim (I, u) is the scoring similarity of user I and other users I having similar behaviors to user I to commodity u, Q iux×y and QIux×y The x y order scoring matrix for commodity u for user I and other user I with similar behavior to user I, and />The x multiplied by y order average scoring matrix is respectively used for the user I and other users I with similar behaviors;
fusing the geographic distance to recommend personalized commodities for the user:
wherein ,Riu For user i to predict score for commodity u, μ iu Scoring the interest level of user i for item u,and (5) the average value of scores of the user i on all commodity interest levels is obtained, and epsilon is a weight value.
The personalized recommendation module 400 is based on the predictive score R iu The recommendation is made to the user in order from high to low.
Referring to fig. 2, there is provided a personalized commodity recommendation method driven by user behavior analysis, comprising the steps of:
s1: collecting user behavior data by the user behavior collection module 100;
s2: the behavior data processing module 200 processes the collected user behavior data;
s3: analyzing the processed user behavior data through the behavior data analysis module 300;
s4: personalized commodity recommendation is performed for the user according to the order of the predictive scores of the personalized recommendation module 400.
In this embodiment, the user behavior acquisition module 100 acquires basic information of a user, browsing information of the user, search information, comment information, collection information, purchase information, and the like, and constructs a user behavior data set. The behavior data processing module 200 performs data cleaning, outlier processing, data redundancy processing, and data integration processing on the collected user behavior data.
The behavioral data analysis module 300 performs normalization processing based on the duration of the user's browsing information, and scoring the user's degree of interest in the merchandise,
setting the total online browsing time length of the user at this time to be 20, setting the total page number of the commodity j searched by the user i to be 10, setting the browsing page number of the user i to be 3, dividing the commodity information browsing time length into 3 sections according to the browsing page number, setting the total time length of the commodity j searched by the user i to be 4, and setting the required total time length of the commodity j completely browsed to be 15; the mathematical expectation of setting the duration of the user browsing information is browsing information scalar a:
wherein m=3 means dividing the browsing time period of commodity information into 3 segments, τ k P is the average browsing duration in the kth time period k The ratio of the browsing duration to the total browsing duration in the kth time period;
setting up an interestingness scoring model based on user behavior analysis:
wherein ,δij scoring function, t, for interest degree of user i on commodity j i Representing the total browsing duration of user i, p j The time for browsing commodity j for the user accounts for the proportion of the total browsing time of the user i.
The behavior data analysis module 300 classifies the scoring grades based on the scoring results of the interestingness scoring model of the user behavior analysis:
a: when delta ij When=0, the user has no interest, and score 0 is recorded;
b: when 0 is<δ ij When the interest level of the user is less than or equal to 0.2, 1 score is recorded;
c: when 0.2<δ ij When the interest degree of the user on the commodity j is less than or equal to 0.4, recording 2 points;
d: when 0.4<δ ij When the interest level of the user is less than or equal to 0.6, indicating that the interest level of the user is higher, and recording 3 points;
e: when 0.6<δ ij And when the interest level of the user is less than or equal to 0.8, the interest level of the user is extremely high, and the score is recorded as 4.
F: when 0.8<δ ij When the interest level of the user is less than or equal to 1.0, the interest level of the user is extremely high, and 5 points are recorded.
Interest degree scoring function delta based on user i on commodity j ij The interest level score mu of the user i on all commodities is divided. The personalized recommendation module 400 then radiates based on the distance between the user i and the good j:
wherein ,a radiation function d which is the distance between the user i and the commodity u iu The distances between the commodity u and the user i are constant, and b and c are constants;
the scoring of the commodity u by the other users I with similar behaviors of the user I is obtained based on the following steps:
wherein sim (I, u) is the scoring similarity of user I and other users I having similar behaviors to user I to commodity u, Q iu6×6 and QIu6×6 A 6 x 6 order scoring matrix for the item u for user I and other user I having similar behavior to user I, and />A 6×6-order average scoring matrix for user I, respectively, other users I with similar behavior;
fusing the geographic distance to recommend personalized commodities for the user:
wherein ,Riu For user i to predict score for commodity u, μ iu Scoring the predicted interestingness level of item u for user i,and (5) the average value of scores of the user i on all commodity interest levels is obtained, and epsilon is a weight value.
The personalized recommendation module 400 sorts based on the final predictive score values and performs personalized commodity recommendation for the user according to the order of the predictive scores from high to low.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.

Claims (10)

1. A personalized commodity recommendation system driven by user behavior analysis is characterized in that: comprising the following steps:
user behavior acquisition module (100): the method comprises the steps of collecting user behavior data;
behavior data processing module (200): the method is used for processing the collected user behavior data;
behavior data analysis module (300): the method is used for analyzing the processed user behavior data;
personalized recommendation module (400): and the system is used for recommending personalized commodities to the user according to the analysis result of the behavior data analysis module (300).
2. The user behavior analysis driven personalized good recommendation system according to claim 1, wherein: the user behavior data collected by the user behavior collection module (100) comprises user basic information, user browsing information, search information, comment information, collection information, purchasing information and purchasing information, and the user behavior data set is formed together.
3. The user behavior analysis driven personalized good recommendation system according to claim 1, wherein: the behavior data processing module (200) performs data cleaning, outlier processing, data redundancy processing and data integration processing on the collected user behavior data.
4. A user behavior analysis driven personalized good recommendation system according to claim 2, wherein: the behavior data analysis module (300) performs normalization processing based on the duration of browsing information of the user and scores the interest degree of the user on the commodity.
5. The user behavior analysis driven personalized good recommendation system according to claim 4, wherein: the scoring process of the interest degree of the user on the commodity is specifically as follows:
let user i be t the current online total browsing time i The total page number of the commodity j searched by the user i is M, the browsing page number of the user i is M, the commodity information browsing time length is divided into M sections according to the browsing page number, and the total time length of the commodity j searched by the user i is t ij The total time required for complete browsing of the commodity j is t j The method comprises the steps of carrying out a first treatment on the surface of the The mathematical expectation of setting the duration of the user browsing information is browsing information scalar a:
wherein ,τk P is the average browsing duration in the kth time period k The ratio of the browsing duration to the total browsing duration in the kth time period;
setting up an interestingness scoring model based on user behavior analysis:
wherein ,δij Scoring function, t, for interest degree of user i on commodity j i Representing the total browsing duration of user i, p j Duration t of browsing commodity j for user ij Accounting for the total online browsing time t of the user i i Is a ratio of (2).
6. The user behavior analysis driven personalized good recommendation system according to claim 5, wherein: the behavioral data analysis module (300) classifies scoring rankings based on scoring results of the interestingness scoring model of the user behavioral analysis.
7. The user behavior analysis driven personalized good recommendation system according to claim 6, wherein: the grading of the scores is specifically as follows:
a: when delta ij When=0, the user has no interest, and score 0 is recorded;
b: when 0 is<δ ij When the interest level of the user is less than or equal to 0.2, 1 score is recorded;
c: when 0.2<δ ij When the interest degree of the user on the commodity j is less than or equal to 0.4, recording 2 points;
d: when 0.4<δ ij When the interest level of the user is less than or equal to 0.6, indicating that the interest level of the user is higher, and recording 3 points;
e: when 0.6<δ ij When the interest level of the user is less than or equal to 0.8, the interest level of the user is extremely high, and the score is recorded as 4;
f: when 0.8<δ ij When the interest level of the user is less than or equal to 1.0, the interest level of the user is extremely high, and 5 points are recorded.
8. The user behavior analysis driven personalized good recommendation system according to claim 7, wherein: the personalized recommendation module (400) radiates based on the distance of the user i from the commodity j:
wherein ,a radiation function d which is the distance between the user i and the commodity u iu The distances between the commodity u and the user i are constant, and b and c are constants;
the scoring of the commodity u by the other users I with similar behaviors of the user I is obtained based on the following steps:
wherein sim (I, u) is the scoring similarity of user I and other users I having similar behaviors to user I to commodity u, Q iux×y and QIux×y The x y order scoring matrix for commodity u for user I and other user I with similar behavior to user I, and />The x multiplied by y order average scoring matrix is respectively used for the user I and other users I with similar behaviors;
fusing the geographic distance to recommend personalized commodities for the user:
wherein ,Riu For user i to predict score for commodity u, μ iu Scoring the interest level of user i for item u,and (5) the average value of scores of the user i on all commodity interest levels is obtained, and epsilon is a weight value.
9. The user behavior analysis driven personalized good recommendation system according to claim 8, wherein: the personalized recommendation module (400) is based on the predictive score R iu The recommendation is made to the user in order from high to low.
10. A personalized commodity recommendation method driven by user behavior analysis, based on the personalized commodity recommendation system driven by user behavior analysis as set forth in any one of claims 1-9, characterized in that: the method comprises the following steps:
s1: collecting user behavior data through a user behavior collection module (100);
s2: the behavior data processing module (200) processes the collected user behavior data;
s3: analyzing the processed user behavior data through a behavior data analysis module (300);
s4: and recommending personalized commodities to the user according to the prediction scoring sequence of the personalized recommendation module (400).
CN202310917456.3A 2023-07-24 2023-07-24 Personalized commodity recommendation system driven by user behavior analysis and method thereof Withdrawn CN116883116A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310917456.3A CN116883116A (en) 2023-07-24 2023-07-24 Personalized commodity recommendation system driven by user behavior analysis and method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310917456.3A CN116883116A (en) 2023-07-24 2023-07-24 Personalized commodity recommendation system driven by user behavior analysis and method thereof

Publications (1)

Publication Number Publication Date
CN116883116A true CN116883116A (en) 2023-10-13

Family

ID=88271267

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310917456.3A Withdrawn CN116883116A (en) 2023-07-24 2023-07-24 Personalized commodity recommendation system driven by user behavior analysis and method thereof

Country Status (1)

Country Link
CN (1) CN116883116A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117196640A (en) * 2023-11-06 2023-12-08 青岛巨商汇网络科技有限公司 Full-flow visual management system and method based on service experience
CN117993956A (en) * 2024-04-01 2024-05-07 南京守约信息技术有限公司 Target client and market data processing method

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117196640A (en) * 2023-11-06 2023-12-08 青岛巨商汇网络科技有限公司 Full-flow visual management system and method based on service experience
CN117196640B (en) * 2023-11-06 2024-02-02 青岛巨商汇网络科技有限公司 Full-flow visual management system and method based on service experience
CN117993956A (en) * 2024-04-01 2024-05-07 南京守约信息技术有限公司 Target client and market data processing method
CN117993956B (en) * 2024-04-01 2024-06-11 南京守约信息技术有限公司 Target client and market data processing method

Similar Documents

Publication Publication Date Title
CN109191240B (en) Method and device for recommending commodities
CN111460130B (en) Information recommendation method, device, equipment and readable storage medium
US20220301024A1 (en) Sequential recommendation method based on long-term and short-term interests
CN116883116A (en) Personalized commodity recommendation system driven by user behavior analysis and method thereof
CN107833117B (en) Bayesian personalized sorting recommendation method considering tag information
CN109918563B (en) Book recommendation method based on public data
CN111340121B (en) Target feature determination method and device
CN112612973B (en) Personalized intelligent clothing matching recommendation method combining knowledge graph
CN111914172B (en) Medical information recommendation method and system based on user tags
CN102411754A (en) Personalized recommendation method based on commodity property entropy
CN111523055B (en) Collaborative recommendation method and system based on agricultural product characteristic attribute comment tendency
CN110348930A (en) Business object data processing method, the recommended method of business object information and device
CN113592588B (en) E-commerce platform commodity recommendation system and method based on big data collaborative filtering technology
CN108804541B (en) Electric trademark optimization system and optimization method
CN112862567B (en) Method and system for recommending exhibits in online exhibition
CN111506831A (en) Collaborative filtering recommendation module and method, electronic device and storage medium
CN112231593B (en) Financial information intelligent recommendation system
CN111310046A (en) Object recommendation method and device
CN106599047A (en) Information pushing method and device
CN109446402B (en) Searching method and device
CN112801803B (en) Financial product recommendation method and device
CN110851694A (en) Personalized recommendation system based on user memory network and tree structure depth model
CN110619552A (en) Member shopping data mining algorithm comprehensive engine
CN111310029B (en) Mixed recommendation method based on user commodity portrait and potential factor feature extraction
CN116304332A (en) Knowledge graph mixed recommendation method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20231013