CN116523600A - Customer classification method and system based on behavior analysis - Google Patents

Customer classification method and system based on behavior analysis Download PDF

Info

Publication number
CN116523600A
CN116523600A CN202310492661.XA CN202310492661A CN116523600A CN 116523600 A CN116523600 A CN 116523600A CN 202310492661 A CN202310492661 A CN 202310492661A CN 116523600 A CN116523600 A CN 116523600A
Authority
CN
China
Prior art keywords
browsing
payment
user
total
behavior information
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.)
Pending
Application number
CN202310492661.XA
Other languages
Chinese (zh)
Inventor
傅敦镖
刘艺
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.)
Foshan Damai Information Technology Co ltd
Original Assignee
Foshan Damai Information 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 Foshan Damai Information Technology Co ltd filed Critical Foshan Damai Information Technology Co ltd
Priority to CN202310492661.XA priority Critical patent/CN116523600A/en
Publication of CN116523600A publication Critical patent/CN116523600A/en
Pending 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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0609—Buyer or seller confidence or verification

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of data processing, in particular to a customer classification method and system based on behavior analysis. A behavior analysis based customer classification system comprising: the behavior information acquisition module is used for acquiring behavior information; the behavior information analysis module is used for analyzing behavior information, and comprises calculation and judgment of product browsing duration, browsing total duration and similar product browsing total duration; the mark adding module is used for adding marks to the user codes according to the analysis result of the behavior information analysis module, and the marks comprise: purchase indicia, non-purchase indicia, payment indicia, and non-payment indicia; and the client classification module is used for classifying the users according to the marks on the user codes. According to the invention, through analyzing the browsing behavior and the payment behavior of the user, whether the user has the purchasing desire and the payment capability is judged, the user is classified, and the accurate pushing strategy is adopted by the auxiliary platform side.

Description

Customer classification method and system based on behavior analysis
Technical Field
The invention relates to the technical field of data processing, in particular to a customer classification method and system based on behavior analysis.
Background
On-line shopping platforms or on-line platforms such as company product pages are an indispensable channel for the enterprises to sell products. With the continuous expansion of online shopping crowd, the maintenance for clients is more difficult, and by classifying clients and adopting corresponding maintenance modes for different clients according to classification results, the workload of client maintenance can be remarkably reduced. However, the classification of the clients is generally performed on labels of the clients themselves, such as age, gender, preference, etc., and the manner is limited to the clients themselves, so that the clients cannot be well assisted in the platform side for maintenance.
Disclosure of Invention
The invention provides a customer classification method and a system based on behavior analysis, which are used for judging whether a user has purchasing desire and payment capability or not by analyzing browsing behaviors and payment behaviors of the user, classifying the customer and assisting a platform side to adopt an accurate pushing strategy.
A method of classifying clients based on behavioral analysis, comprising:
the interval preset period is used for acquiring behavior information corresponding to a user in the preset period according to a user code, the behavior information comprises browsing information and payment information, wherein the browsing information comprises browsing content ID, browsing times and single browsing duration, and the payment information comprises: paying the total amount and the successful times of payment;
calculating the browsing time length, the browsing total time length and the browsing total time length of similar products through the behavior information;
judging whether the browsing total duration zeta exceeds a first threshold value, if so, adding the user code with a purchase mark; if the browsing total time length does not exceed the first threshold value, browsing the same type of products for total time length gamma i Judging the size of the same product with the second threshold value, wherein the second threshold value is smaller than the first threshold value, and if the same product browses the same product, the browsing total duration gamma is longer i If the second threshold is exceeded, adding the user code to the purchase mark; if the similar product browsing total time length gamma does not appear i When the second threshold value is exceeded, the product browsing time epsilon is one by one n Determining the size of the first threshold value and the second threshold value is smaller than the third threshold valueIf the value is the product browsing duration epsilon n If the third threshold is exceeded, adding the user code to the purchase mark; if the product browsing duration epsilon does not appear n If the third threshold is exceeded, adding the user code to the non-purchase indicia;
judging whether the successful payment times exceed a fourth threshold value, if so, adding a payment mark to the user code; if the number of successful payment times does not exceed the fourth threshold, judging whether the total payment amount exceeds a fifth threshold, and if the total payment amount exceeds the fifth threshold, adding a payment mark to the user code; if the total payment amount does not exceed the fifth threshold, adding a non-payment mark to the user code;
classifying users corresponding to the user codes with the purchase marks and the payment marks as class A clients; classifying users corresponding to the user codes with the purchase marks and the non-payment marks as B-class clients; classifying users corresponding to the user codes with the non-purchase marks and the payment marks as class C clients; the users corresponding to the user codes having the non-purchase indicia and the non-payment indicia are classified as class D customers.
Preferably, the calculation of the browsing duration of the product and the browsing total duration comprises the following steps: traversing the browse content ID, for each browse content ID delta n Wherein n=1, 2,3, N is the total number of browsing content IDs in a preset period coded by the user, and the browsing content IDv is obtained n Corresponding browsing times m and single browsing time length T n，m Wherein m=1, 2, 3.M, M corresponds to the total number of browsing times of the browsing content ID, according to the browsing times M and the single browsing time length T n，m Calculate the browsing content ID delta n Corresponding product browsing durationCalculating the total browsing duration
Preferably, the calculation of the browsing total duration of the like products comprises the following steps of: traversing all browsing content ID delta n Classifying the browsing content IDs into I browsing content sets according to the product types, wherein i=1, 2, 3. I is the total number of the browsing content sets, namely the total number of the product types browsed by the user in the preset period, sequentially selecting the browsing content sets, and executing the following operations for each browsing content set: marking the browsing content ID in the browsing content set as alpha j Wherein j=1, 2,3, J is the total number of browsing content IDs in the browsing content set, each browsing content ID alpha j Corresponding product browsing duration epsilon n Is marked as beta j Calculating the browsing total duration of similar products
Preferably, classifying the browsing content IDs into i browsing content sets according to the product type includes the steps of: and obtaining corresponding browsing contents according to the browsing content IDs, extracting keywords from the browsing contents, selecting the first e keywords with highest word frequency as keyword groups, performing unsupervised cluster analysis on the keyword groups corresponding to each browsing content ID, and forming each cluster group as a browsing content set.
Preferably, the unsupervised clustering analysis employs a K-means clustering algorithm.
Preferably, the method also comprises the analysis of abnormal behaviors, and specifically comprises the following steps: acquiring abnormal behavior information corresponding to a user in a preset period according to the user code at intervals, wherein the abnormal behavior information comprises the successful payment times and refund times; counting the successful payment number as S, counting the refund number as T, and judgingWhether or not it is true, wherein mu is a preset coefficient, if soIf not, classifying the user corresponding to the user code as a malicious user; if it is->And (3) the method is true and no operation is performed.
A behavior analysis based customer classification system comprising:
the behavior information acquisition module is used for acquiring behavior information, the behavior information comprises browsing information and payment information, wherein the browsing information comprises browsing content ID, browsing times and single browsing duration, and the payment information comprises: paying the total amount and the successful times of payment;
the behavior information analysis module is used for analyzing behavior information, and comprises calculation and judgment of product browsing duration, browsing total duration and similar product browsing total duration;
the mark adding module is used for adding marks to the user codes according to the analysis result of the behavior information analysis module, and the marks comprise: purchase indicia, non-purchase indicia, payment indicia, and non-payment indicia;
and the client classification module is used for classifying the users according to the marks on the user codes.
Preferably, the method further comprises:
the abnormal behavior information acquisition module is used for acquiring abnormal behavior information;
the abnormal behavior information analysis module is used for analyzing the abnormal behavior information.
The invention has the following advantages:
1. according to the invention, through analyzing the browsing behavior and the payment behavior of the user, whether the user has the purchasing desire and the payment capability is judged, the user is classified, and the accurate pushing strategy is adopted by the auxiliary platform side.
2. According to the invention, through analyzing the refund times of the users, the users with excessive refund times are classified as malicious users, so that the users are reminded of the product seller, and the loss caused by the fact that products such as customized products are returned after being sold is avoided.
Drawings
Fig. 1 is a schematic structural diagram of a customer classification system based on behavior analysis in an embodiment of the present invention.
Detailed Description
In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example 1
A method of classifying clients based on behavioral analysis, comprising:
the interval preset period is used for acquiring behavior information corresponding to a user in the preset period according to a user code, the behavior information comprises browsing information and payment information, wherein the browsing information comprises browsing content ID, browsing times and single browsing duration, and the payment information comprises: paying the total amount and the successful times of payment;
traversing the browse content ID, for each browse content ID delta n Wherein n=1, 2,3, N is the total number of browsing content ID in preset period of user code and the browsing content ID delta is obtained n Corresponding browsing times m and single browsing time length T n，m Wherein m=1, 2, 3.M, M corresponds to the total number of browsing times of the browsing content ID, according to the browsing times M and the single browsing time length T n，m Calculate the browsing content ID delta n Corresponding product browsing durationCalculating browsing total duration +.>Judging whether the total browsing duration zeta exceeds a first threshold value or not, wherein the first threshold value is set in advance by a user, if the total browsing duration zeta exceeds the first threshold value, the user is allowed to conduct a large number of browsing actions in a preset period, for example, the number of web browsing times of the product of the company exceeds 70 hours in one week, at the moment, the user can be considered to have purchasing desire for the product of the company, and the user code is added with a purchasing mark; if the total browsing duration does not exceed the first threshold, traversing all the browsing content ID delta n And classifying the browse content ID into I browse content sets according to the product type, i=1, 2,3,i is the total number of browsing content sets, namely the total number of types of products browsed by the user in the preset period, the browsing content sets are sequentially selected, and the following operations are executed for each browsing content set: marking the browsing content ID in the browsing content set as alpha j Wherein j=1, 2,3, J is the total number of browsing content IDs in the browsing content set, each browsing content ID alpha j Corresponding product browsing duration epsilon n Is marked as beta j Calculating the browsing total duration of the similar products>Browsing all similar products for a total time period gamma i Judging the size of the same product with the second threshold value, wherein the second threshold value is smaller than the first threshold value, and if the same product browses the same product, the browsing total duration gamma is longer i When the browsing amount of a certain type of product reaches the second threshold value, the user can be considered to have a purchasing desire even if the total browsing duration is not enough to the first threshold value, and the purchasing mark is added to the user code; if the similar product browsing total time length gamma does not appear i When the second threshold value is exceeded, the product browsing time epsilon is one by one n Judging the size of the product with a third threshold value, wherein the third threshold value is smaller than the second threshold value, and if the product browsing duration epsilon appears n When the browsing amount of the user for the single product reaches the third threshold value within the preset period, the user still can be considered to have the purchasing desire, and the user code is added with the purchasing mark; if the product browsing duration epsilon does not appear n If the third threshold is exceeded, the user is considered to have no desire to purchase, and the user code is added with a non-purchase flag.
Specifically described herein, and classifying the browsing content IDs into i browsing content sets according to the product types, specifically includes the following: and obtaining corresponding browsing contents, such as detail pages of products or comment pages of products, according to the browsing content IDs, extracting the text contents, extracting 20 key words with highest word frequency to form key words, and carrying out cluster analysis on the key words corresponding to each browsing content ID through a K-means clustering algorithm to form each cluster which is a browsing content set.
Judging whether the successful payment times exceed a fourth threshold value, wherein the successful payment times are the times of the user completing the payment in a preset period, the fourth threshold value is set by the user and is used for representing the frequency of purchasing products in the preset period, if the successful payment times exceed the fourth threshold value, the user is indicated to conduct a large number of payment behaviors in the preset period, the payment capability is approved, and the user code is added with a payment mark; if the number of successful payment times does not exceed the fourth threshold, judging whether the total payment amount exceeds the fifth threshold, if the total payment amount exceeds the fifth threshold, indicating that the amount spent by the user in a preset period exceeds the fifth threshold set in advance, and at the moment, considering that the client has sufficient payment capability, and adding a payment mark to the user code; if the total amount of payment does not exceed the fifth threshold, indicating that the user does not have trusted payment capability, adding the user code to a non-payment token.
The users corresponding to the user codes with the purchase marks and the payment marks are classified into A-class clients, wherein the A-class clients can have the purchase desire and the payment capacity at the same time, in this case, the user has higher possibility of completing the purchase behavior, and the A-class clients can be pushed with the highest priority when new products are marketed subsequently; the users corresponding to the user codes with the purchase marks and the non-payment marks are classified into B-class clients, the B-class clients only have the purchase desire, but lack payment capability, the purchase behavior cannot be completed, and the B-class clients can adopt a mode of pushing products of the same type and with lower price to promote the completion of the purchase behavior; classifying users corresponding to the user codes with the non-purchase marks and the payment marks as C-class clients, wherein the users do not have a purchase desire for company products, only occasionally make a large share of purchase behavior in a preset period in the presence of heart blood, the purchase behavior of the C-class clients can not be expected, and the pushing on the product content is adopted for the C-class clients; users corresponding to the user codes with non-purchase marks and non-payment marks are classified as class D customers, and such users cannot basically complete the expected purchase behavior, and maintain a normal push strategy.
According to the invention, through analyzing the browsing behavior and the payment behavior of the user, whether the user has the purchasing desire and the payment capability is judged, the user is classified, and the accurate pushing strategy is adopted by the auxiliary platform side.
In the actual operation of the shopping platform, some users purchase some products in order to obtain high-value compensation, and identify the authenticity of the products, if true, the products are applied for return; if the result is false, reporting is carried out, and compensation is obtained; when such a method is used on some customized products, although the products are not wrong, if the products are returned, the customized products cannot be sold later, and the loss of shops is caused, so that the users need to be identified, and the analysis of abnormal behaviors comprises the following steps: acquiring abnormal behavior information corresponding to a user in a preset period according to the user code at intervals, wherein the abnormal behavior information comprises the successful payment times and refund times; counting the successful payment number as S, counting the refund number as T, and judgingWhether or not this is true, where μ is a predetermined coefficient, which in practice is typically set to 0.7, if +.>If not, namely when the refund number exceeds the seven times of the total payment number, the user can be considered not to make normal shopping, and the user corresponding to the user code is classified as a malicious user; if it is->If the user is established, the behavior of the user is normal shopping, and no operation is performed; when the product seller confirms the order, the user code in the malicious user can be referred, and if the user is the malicious user, the product seller can choose to directly cancel the order, so that the loss is avoided.
According to the invention, through analyzing the refund times of the users, the users with excessive refund times are classified as malicious users, so that the users are reminded of the product seller, and the loss caused by the fact that products such as customized products are returned after being sold is avoided.
Example 2
Referring to fig. 1, a customer classification system based on behavioral analysis, comprising:
the behavior information acquisition module is used for acquiring behavior information, the behavior information comprises browsing information and payment information, wherein the browsing information comprises browsing content ID, browsing times and single browsing duration, and the payment information comprises: paying the total amount and the successful times of payment;
the behavior information analysis module is used for analyzing behavior information, and comprises calculation and judgment of product browsing duration, browsing total duration and similar product browsing total duration;
the mark adding module is used for adding marks to the user codes according to the analysis result of the behavior information analysis module, and the marks comprise: purchase indicia, non-purchase indicia, payment indicia, and non-payment indicia;
and the client classification module is used for classifying the users according to the marks on the user codes.
A customer classification system based on behavioral analysis, as shown in fig. 1, further comprising:
the abnormal behavior information acquisition module is used for acquiring abnormal behavior information;
the abnormal behavior information analysis module is used for analyzing the abnormal behavior information.
It will be understood that modifications and variations will be apparent to those skilled in the art from the foregoing description, and it is intended that all such modifications and variations be included within the scope of the following claims. Parts of the specification not described in detail belong to the prior art known to those skilled in the art.

Claims (8)

1. A method of classifying clients based on behavioral analysis, comprising:
the interval preset period is used for acquiring behavior information corresponding to a user in the preset period according to a user code, the behavior information comprises browsing information and payment information, wherein the browsing information comprises browsing content ID, browsing times and single browsing duration, and the payment information comprises: paying the total amount and the successful times of payment;
calculating the browsing time length, the browsing total time length and the browsing total time length of similar products through the behavior information;
judging whether the browsing total duration zeta exceeds a first threshold value, if so, adding the user code with a purchase mark; if the browsing total time length does not exceed the first threshold value, browsing the same type of products for total time length gamma i Judging the size of the same product with the second threshold value, wherein the second threshold value is smaller than the first threshold value, and if the same product browses the same product, the browsing total duration gamma is longer i If the second threshold is exceeded, adding the user code to the purchase mark; if the similar product browsing total time length gamma does not appear i When the second threshold value is exceeded, the product browsing time epsilon is one by one n Judging the size of the product with a third threshold value, wherein the third threshold value is smaller than the second threshold value, and if the product browsing duration epsilon appears n If the third threshold is exceeded, adding the user code to the purchase mark; if the product browsing duration epsilon does not appear n If the third threshold is exceeded, adding the user code to the non-purchase indicia;
judging whether the successful payment times exceed a fourth threshold value, if so, adding a payment mark to the user code; if the number of successful payment times does not exceed the fourth threshold, judging whether the total payment amount exceeds a fifth threshold, and if the total payment amount exceeds the fifth threshold, adding a payment mark to the user code; if the total payment amount does not exceed the fifth threshold, adding a non-payment mark to the user code;
classifying users corresponding to the user codes with the purchase marks and the payment marks as class A clients; classifying users corresponding to the user codes with the purchase marks and the non-payment marks as B-class clients; classifying users corresponding to the user codes with the non-purchase marks and the payment marks as class C clients; the users corresponding to the user codes having the non-purchase indicia and the non-payment indicia are classified as class D customers.
2. The method for classifying clients based on behavioral analysis according to claim 1, wherein the calculation of the browsing duration of the product and the browsing total duration comprises the steps of: traversing the browse content ID, for each browse content ID delta n Wherein n=1, 2,3, N is the total number of browsing content ID in preset period of user code and the browsing content ID delta is obtained n Corresponding browsing times m and single browsing time length T n，m Wherein m=1, 2, 3.M, M corresponds to the total number of browsing times of the browsing content ID, according to the browsing times M and the single browsing time length T n，m Calculate the browsing content ID delta n Corresponding product browsing durationCalculating browsing total duration +.>
3. The method for classifying clients based on behavioral analysis according to claim 2, wherein the calculation of the total browsing duration of the like products comprises the steps of: traversing all browsing content ID delta n Classifying the browsing content IDs into I browsing content sets according to the product types, wherein i=1, 2, 3. I is the total number of the browsing content sets, namely the total number of the product types browsed by the user in the preset period, sequentially selecting the browsing content sets, and executing the following operations for each browsing content set: marking the browsing content ID in the browsing content set as alpha j Wherein j=1, 2,3, J is the total number of browsing content IDs in the browsing content set, each browsing content ID alpha j Corresponding product browsing duration epsilon n Is marked as beta j Calculating the browsing total duration of similar products
4. A method of classifying clients based on behavioral analysis according to claim 3, wherein classifying the browsed content IDs into i browsed content sets according to product types comprises the steps of: and obtaining corresponding browsing contents according to the browsing content IDs, extracting keywords from the browsing contents, selecting the first e keywords with highest word frequency as keyword groups, performing unsupervised cluster analysis on the keyword groups corresponding to each browsing content ID, and forming each cluster group as a browsing content set.
5. A method of classifying clients based on behavioral analysis according to claim 4, wherein the unsupervised clustering analysis uses a K-means clustering algorithm.
6. A method of classifying clients based on behavioral analysis according to claim 1, further comprising the analysis of abnormal behavior by: acquiring abnormal behavior information corresponding to a user in a preset period according to the user code at intervals, wherein the abnormal behavior information comprises the successful payment times and refund times; counting the successful payment number as mu, counting the refund number as T, and judgingWhether or not it is true, wherein μ is a preset coefficient, if yes>If not, classifying the user corresponding to the user code as a malicious user; if it is->And (3) the method is true and no operation is performed.
7. A behavior analysis-based customer classification system, comprising:
the behavior information acquisition module is used for acquiring behavior information, the behavior information comprises browsing information and payment information, wherein the browsing information comprises browsing content ID, browsing times and single browsing duration, and the payment information comprises: paying the total amount and the successful times of payment;
the behavior information analysis module is used for analyzing behavior information, and comprises calculation and judgment of product browsing duration, browsing total duration and similar product browsing total duration;
the mark adding module is used for adding marks to the user codes according to the analysis result of the behavior information analysis module, and the marks comprise: purchase indicia, non-purchase indicia, payment indicia, and non-payment indicia;
and the client classification module is used for classifying the users according to the marks on the user codes.
8. A customer classification system based on behavioral analysis as set forth in claim 7 further comprising:
the abnormal behavior information acquisition module is used for acquiring abnormal behavior information;
the abnormal behavior information analysis module is used for analyzing the abnormal behavior information.
CN202310492661.XA 2023-05-05 2023-05-05 Customer classification method and system based on behavior analysis Pending CN116523600A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310492661.XA CN116523600A (en) 2023-05-05 2023-05-05 Customer classification method and system based on behavior analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310492661.XA CN116523600A (en) 2023-05-05 2023-05-05 Customer classification method and system based on behavior analysis

Publications (1)

Publication Number Publication Date
CN116523600A true CN116523600A (en) 2023-08-01

Family

ID=87389906

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310492661.XA Pending CN116523600A (en) 2023-05-05 2023-05-05 Customer classification method and system based on behavior analysis

Country Status (1)

Country Link
CN (1) CN116523600A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120089996A1 (en) * 2005-09-14 2012-04-12 Jorey Ramer Categorization of a mobile user profile based on browse and viewing behavior
CN105488697A (en) * 2015-12-09 2016-04-13 焦点科技股份有限公司 Potential customer mining method based on customer behavior characteristics
CN110335098A (en) * 2019-04-24 2019-10-15 上海恺英网络科技有限公司 Order recognition methods and equipment at production payment center service end
CN110880006A (en) * 2018-09-05 2020-03-13 广州视源电子科技股份有限公司 User classification method and device, computer equipment and storage medium
CN114266613A (en) * 2021-11-19 2022-04-01 中国联合网络通信集团有限公司 Method, device, equipment and readable storage medium for determining malicious order user

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120089996A1 (en) * 2005-09-14 2012-04-12 Jorey Ramer Categorization of a mobile user profile based on browse and viewing behavior
CN105488697A (en) * 2015-12-09 2016-04-13 焦点科技股份有限公司 Potential customer mining method based on customer behavior characteristics
CN110880006A (en) * 2018-09-05 2020-03-13 广州视源电子科技股份有限公司 User classification method and device, computer equipment and storage medium
CN110335098A (en) * 2019-04-24 2019-10-15 上海恺英网络科技有限公司 Order recognition methods and equipment at production payment center service end
CN114266613A (en) * 2021-11-19 2022-04-01 中国联合网络通信集团有限公司 Method, device, equipment and readable storage medium for determining malicious order user

Similar Documents

Publication Publication Date Title
US8812351B2 (en) Method of analyzing credit card transaction data
JP4360759B2 (en) Method and system for investigating advertising sales effects using correlation analysis
Ghose et al. Designing ranking systems for consumer reviews: The impact of review subjectivity on product sales and review quality
US20140325056A1 (en) Scoring quality of traffic to network sites
US20120047014A1 (en) Method and system for using email receipts for targeted advertising
US9800678B2 (en) Apparatus and method for processing information and program for the same
Sun et al. Predicting stages in omnichannel path to purchase: A deep learning model
KR20200048183A (en) Method and apparatus for online product recommendation considering reliability of product
JP6679451B2 (en) Selection device, selection method, and selection program
US20190080352A1 (en) Segment Extension Based on Lookalike Selection
CN114782076B (en) Online mall consumption platform lottery integral exchange intelligent management method, system and computer storage medium
CN113516496B (en) Advertisement conversion rate estimation model construction method, device, equipment and medium thereof
WO2016157427A1 (en) Information processing device, information processing method, and information processing program
CN112396433A (en) Method and system for identifying false commodity comments based on behavior of person to be evaluated
JP2021099718A (en) Information processing device and program
CN111861679A (en) Commodity recommendation method based on artificial intelligence
CN112016756A (en) Data prediction method and device
CN111461827A (en) Product evaluation information pushing method and device
CN103597485A (en) Pattern extraction device and method
TWI747290B (en) Customer grouping service customized marketing method and system
Chou et al. The RFM Model Analysis for VIP Customer: A case study of golf clothing brand
JP2010086171A (en) Advertisement charging management system
CN116523600A (en) Customer classification method and system based on behavior analysis
CN111460300B (en) Network content pushing method, device and storage medium
Jain et al. Application of association rule mining in a clothing retail store

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