CN105488697A - Potential customer mining method based on customer behavior characteristics - Google Patents
Potential customer mining method based on customer behavior characteristics Download PDFInfo
- Publication number
- CN105488697A CN105488697A CN201510903856.4A CN201510903856A CN105488697A CN 105488697 A CN105488697 A CN 105488697A CN 201510903856 A CN201510903856 A CN 201510903856A CN 105488697 A CN105488697 A CN 105488697A
- Authority
- CN
- China
- Prior art keywords
- page
- data
- feature
- user
- browsing
- 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
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a potential customer mining method based on customer behavior characteristics. The potential customer mining method comprises the following steps: a first step: data preprocessing; 1) data cleaning: deleting unnecessary recording rows at first; 2) forming a URL rule list; 3) user marking: accessing a log sheet to jointly identify the user through vinfo and client ID; 4) extracting features: with a session as a unit, analyzing the access source, the number of browsed pages, the number of browsed product detail pages, the number of browsed products, the page browsing duration, the product detail page browsing duration, the time of looking up a screening list, whether looking up a service topic and the first time browsing time period of the user in a single day of each user in single session, using whether the user is tend to purchase as a category attribute, and forming a training sample by the characteristic; 5) screening a training set; a second step: simplifying the characteristic attributes based on a rough set to improve the classification precision; and a third step: establishing a random forest potential customer identification model based on the customer behavior characteristics.
Description
Technical field
The present invention relates to and excavate potential customers field, in particular to a kind of potential customers' method for digging based on customer action feature by analyzing web site user access logs.
Background technology
At present in the electronic commerce times that market competition is day by day fierce, the more new client of continuous expansion, effectively excavate potential customers colony from numerous viewers, and make great efforts potential customers to be converted into real client, enterprise just can obtain more Multi benefit and market competition advantage.The object that potential customers excavate formulates corresponding service strategy for website exactly to be provided reference frame accurately and makes corresponding decision.
The basic data that potential customers excavate derives from the access log of website, and access log have recorded the access behavioural information of a certain website of client access, and these information are easy to obtain.
Have recorded the IP of visitor in access log, log in ID, access time, VINFO, browse the information such as product IDs, REFERER (last access the page), REQUEST (page of access), SEARCH_WORD (search word), PROD_ID (browsing product), ORDER_ID.
Table 1 access log information
Iptonumber | Visitor ip |
Vinfo | Cookie |
Login_id | Log in id |
Visit_time | Access time |
Request | Request |
Referrer | Source |
User_agent | Institute's use machine |
Prod_id | Product id |
Search_word | Search word |
Order_id | Order id |
Policy_id | Declaration form id |
User_agent | Machine id |
Wherein, REFERER and REQUEST analyzes access source, access whereabouts and judges whether visitor whether buy by purpose, add the topmost information of the behaviors such as shopping cart.These behaviors are excavated to the behavioural characteristic extracting client, these behavioural characteristics comparatively effectively can reflect the classification of client, the client such as with which kind of access behavioural characteristic is loyalty customer, the client with which kind of access behavioural characteristic is pure visitor, and the client with which kind of access behavioural characteristic is potential customers.
Therefore the behavioural characteristic how finding out potential customers from the access log of website is exactly the problem that excavation potential customers need to solve.
Summary of the invention
Goal of the invention: the invention provides a kind of potential customers' method for digging based on customer action feature, for corresponding service strategy is formulated in website, and reference frame is accurately provided and makes corresponding decision.
Technical scheme: for achieving the above object, the technical solution used in the present invention is: a kind of potential customers' method for digging based on customer action feature, is characterized in that:
Step one: data prediction;
Step1: data cleansing
Original log record have accumulated a large amount of client's browsing informations, is much the redundant information irrelevant with data mining, the information such as such as picture, short-message verification, Logo picture, first needs to delete unwanted record row;
Step2: form URL list of rules
Analyze the REQUEST field in a new station web data, to when comprising ' confirm ', represent purpose purchase etc., final formation URL list of rules; During subsequent calculations feature, do not need to analyze request field one by one, according to request field with the url coupling in url list of rules, url_name can be obtained;
Step3: user label
Combine with vinfo, iptonumber, Customer ID (login_id) to identify user in access log table;
Vinfo: be equivalent to cookie, indicates a computing machine;
Iptonumber:ip address, same computer logs in different place, has different ip;
Login_id: Member Entrance id, login_id=-1 when non-member logs in.
Step4: feature extraction
In units of a session, analyze the access source of each user in single session, browsing pages number, browse product details number of pages, browse product number, page browsing duration, product details page browsing duration, check filtered list number of times, whether check business topic, user's odd-numbered day browses the period first, whether user checks the characteristic attributes such as shopping cart, and using user, whether purpose is bought as category attribute, finally forms training sample with this feature;
Step5: screening training set
Behavioral data information in web daily record is the behavioural information data that in certain time period, total user produces on a new website, station, this wherein just includes the people's (loyalty customer) repeatedly done shopping, the people (existing customer) that shopping number of times is few, potential customers and browsed site home page, but the behavioral data that the people (pure viewer) not browsing commodity in any website produces;
By analyzing the purchase number of times in a period of time, getting rid of the customer data repeatedly bought, choosing the client that initial purchase is carried out to a certain product or the client do not bought after browsing as excavation object;
Step 2: based on the Characteristic Attribute Reduction of rough set;
For category attribute, 11 characteristic attributes that step one is extracted, some is likely redundancy.According to rough set theory, under the prerequisite not affecting classification performance, redundant attributes can be divided out, thus reduce operand, improve nicety of grading.
Method step:
First relative positive field is utilized to ask core Core:
Step1: initialization data Core=φ, C={a
1, a
2..., a
jj=1,2 ... 11, a
jfor characteristic attribute, D={a
12be category attribute, calculate relative positive field POS
c(D);
Step2:B=C-{a
j, calculate relative positive field POS
b, and compare POS (D)
c(D), POS
b(D).If POS
c(D) ≠ POS
b(D), then a
jfor core attributes, Core=Core ∩ B, whether each attribute of cycle criterion is core attributes.
Step3: return Core, terminates.
Next utilizes attribute dependability to ask yojan Reduce:
Step1: initialization data, residue attribute RestAtt=C-Core, Reduce=Core,
Step2: compare POS
core(D), POS
c(D), if equal, then Core is yojan, otherwise forwards step3 to;
Step3: each residue attribute a in circulation RestAtt
jif,
select the attribute a making K value maximum
k, make Reduce=Reduce ∪ { a
k, RestAtt=RestAtt-{a
k, and compare POS
restAttand POS (D)
c(D), if equal, forward step4 to, otherwise continue circulation.
Step4: return Reduce, terminates.
Reduce is now the characteristic attribute of final input sorter.Add this step of attribute selection based on rough set.
Step 3: based on the random forest potential customers model of cognition of customer action feature
Random forests algorithm uses the lingware bag randomForest4.6-6 of R3.0.2 software to realize, program connects oracle database by data source ODBC, use function get_data () to obtain desired data, use function cal_feture () to calculate data characteristics; After screening training set, call random forest disaggregated model model_rf and prediction is carried out to characteristic obtain potential customers ip and cookie information, finally by ip and cookie search in data with existing table potential customers user profile and in write into Databasce.
In step 3:
Step1: connection data storehouse, the function of function get_data () for obtain desired data from database, and parameter chan is DataBase combining, and cal_number is the required date obtaining data,
data=sqlQuery(chan,sql,stringsAsFactors=FALSE)
In being wrapped by RODBC, odbcConnect () function is set up R and is connected with oracle database:
chan=odbcConnect("dm_xyz",uid='######',pwd='******')
Wherein, parameter d m_xyz is the system DSN name of data source ODBC, and uid is user name, and pwd is user login code;
After building database connects, obtain desired data in database by performing sql statement; And in sql statement, add the data cleansing rule of step one;
Step2:URL mates, and upgrades browsing pages information
Read in the URL rule txt document of step 2 by this locality, according to the key word of the REQUEST fields match URL rule in data, upgrade VISIT_PAGE field, the record without occurrence is then set to "-1 ".
Step3: feature calculation cal_feature (data)
The function of function cal_feature is the odd-numbered day Data Segmentation that get_data function obtains is become different to browse session, calculates feature finally obtain characteristic data set to single session.
Step 4: potential customers' model of cognition performance verification
Utilizing oracle edit and storage process, judging that the potential customers that dig out are digging out the real ratio bought in day after date one month, as model performance checking index.If the follow-up buying rate of the client doped every day is higher and relatively more steady, prove that model performance is better.Give modelling effect index.
Beneficial effect of the present invention: the invention provides a kind of potential customers' method for digging based on customer action feature, stable random forests algorithm is used to set up disaggregated model, have the high and data feature accurately of efficiency, can formulate corresponding service strategy for website provides reference frame accurately and makes corresponding decision.
Accompanying drawing explanation
Fig. 1 is the structural drawing of whole program, and wherein model_rf.Rdata is housebroken disaggregated model.
Embodiment
Step one: data prediction;
Step1: data cleansing
Original log record have accumulated a large amount of client's browsing informations, is much the redundant information irrelevant with data mining, the information such as such as picture, short-message verification, Logo picture, first needs to delete unwanted record row.
Need the REQUEST that the record of deletion is capable as follows
Step2: form the new station URL list of rules of the applicant
Analyze the REQUEST field in the new station web data of the applicant, when such as analysis request comprises ' baoxian ', insurance topic is checked in representative, when comprising ' confirm ', represents purpose purchase etc., the new station URL list of rules of final formation.During subsequent calculations feature, do not need to analyze request field one by one, according to request field with the url coupling in url list of rules, url_name can be obtained, as shown in table 2.
The new station url rule of table 2
Step3: user label
Combine with vinfo, iptonumber, Customer ID (login_id) to identify user in a new website access log sheet.
Vinfo: be equivalent to cookie, indicates a computing machine;
Iptonumber:ip address, same computer logs in different place, has different ip;
Login_id: new a station Member Entrance id, login_id=-1 when non-member logs in.
Step4: feature extraction
In units of a session, analyze the access source of each user in single session, browsing pages number, browse product details number of pages, browse product number, page browsing duration, product details page browsing duration, check filtered list number of times, whether check insurance topic, whether check insurance dictionary, user's odd-numbered day browses the period first, whether user checks the characteristic attributes such as shopping cart, and using user, whether purpose is bought as category attribute, finally forms training sample.
A) feature 1: access source, according to first referer of each session, distinguishes the access source of client.Advertisement putting, search engine, mail, directly access, other.
B) feature 2: browsing pages number, gets the page number that in a session, user browses.
C) feature 3: browse product details number of pages, gets user in a session and browses product details number of pages.
D) feature 4: page browsing duration, in a session, the duration of browsing of each page of user is averaged.
E) feature 5: product details page browsing duration, in a session, the duration of browsing of each product details page of user is averaged.
F) feature 6: the number of times checking filtered list, observing ruquest in a session has ' number of times of viewsearchlist '.
G) feature 7: whether check insurance topic.Observe in ruquest and whether have ' baoxian '.
H) feature 8: whether check insurance dictionary.Observe in ruquest and whether have ' toptag '.
I) feature 9: browse the period.A session access time visit_time first
J) feature 10: be
noly check shopping cart, be ' 1 ', no is ' 0 '; Whether check shopping cart observes in ruquest whether have shopping_car.
K) category attribute: whether purpose is bought, and be ' 1 ', no is ' 0 '; Whether purpose is bought is judge whether have confirm in ruquest, containing confirm, the buying behavior of generation purpose is described.
Step5: screening training set
Behavioral data information in web daily record is the behavioural information data that in certain time period, total user produces on a new website, station, this wherein just includes the people's (loyalty customer) repeatedly done shopping, the people (existing customer) that shopping number of times is few, potential customers and browsed site home page, but the behavioral data that the people (pure viewer) not browsing commodity in any website produces.
Result can be made to produce larger error if all data to be directly used for train classification models.For avoiding causing error, other types customer action should be excluded to the interference building model accuracy.
By analyzing the purchase number of times in a period of time, exclude the customer data repeatedly bought, the present invention chooses the client carrying out initial purchase to a certain product or the client do not bought after browsing as excavation object.
Step6: screening characteristic attribute
Pass through rough set theory, get rid of redundant attributes, the characteristic attribute finally obtained have access source, browsing pages number, browse product details number of pages, browse product number, page browsing duration, product details page browsing duration, searching times, whether check insurance topic, whether check insure dictionary, whether user check shopping cart.
Step 3: based on the random forest potential customers model of cognition of customer action feature
Random forests algorithm uses the lingware bag randomForest4.6-6 of R3.0.2 software to realize, program connects oracle database by data source (ODBC), use function get_data () to obtain desired data, use function cal_feture () to calculate data characteristics.After screening training set, call random forest disaggregated model model_rf and prediction is carried out to characteristic obtain potential customers ip and cookie information, finally by ip and cookie search in data with existing table potential customers user profile and in write into Databasce.
Step1: connection data storehouse
The function of function get_data () for obtain desired data from database, and parameter chan is DataBase combining, and cal_number is the required date obtaining data.
data=sqlQuery(chan,sql,stringsAsFactors=FALSE)
In being wrapped by RODBC, odbcConnect () function is set up R and is connected with oracle database:
chan=odbcConnect("dm_xyz",uid='######',pwd='******')
Wherein, parameter d m_xyz is the system DSN name of data source (ODBC), and uid is user name, and pwd is user login code.
After building database connects, obtain desired data in database by performing sql statement.And in sql statement, add the data cleansing rule of step one.
Step2:URL mates, and upgrades browsing pages information
Read in the URL rule txt document of step 2 by this locality, according to the key word of the REQUEST fields match URL rule in data, upgrade VISIT_PAGE field, the record without occurrence is then set to "-1 ".
Step3: feature calculation cal_feature (data)
The function of function cal_feature is the odd-numbered day Data Segmentation that get_data function obtains is become different to browse session, calculates feature finally obtain characteristic data set to single session.
(1) cookie information
(2) whether log in
(3) browsing pages number and the page on average browse duration
# browsing pages number
page_tag=which(tmp$VISIT_PAGE!='-1')
page_n=length(page_tag)
# product details page number of pages
Prod_tag=which (tmp $ VISIT_PAGE==' product details page ')
page_prod=length(prod_tag)
The # page and product details page browse duration (page_n-1)
The request time of time=strptime (tmp [page_tag, 2], " %Y-%m-%d%H:%M:%S ") # actual pages
Stay_time=as.vector (diff (time)) the # page request mistiming is as the residence time of the page
Page_time_avg=sum (stay_time, na.rm=T)/page_n# page average access duration
Prod_time=stay_time [which (page_tag%in%prod_tag)] # product details page total residence time
Prod_time_avg=sum (prod_time, na.rm=T)/average duration of page_prod# product details page
(4) number of times of filtered list is checked
# filtered list number of times (0 expression is not searched for)
Sear_n=length (which (tmp $ VISIT_PAGE==" search listing "))
(5) whether shopping cart was checked
(6) insurance topic whether was checked
(7) insurance dictionary whether was checked
(8) type of source web, judges source web according to REFERER and REFERER_SOURCE_WORD field keys.
(9) whether purpose buys (predictive variable)
Final synthesis obs observational record returns, and screening first purchase and the user do not bought after browsing, form training sample.
Step4: more potential customers' information table data update_info (channe, cal_number) in new database
This function is the topmost function of whole program, for predicting potential customers, obtaining potential customers' information and write into Databasce.Get_data () function and cal_feature () function can be called in function.
(1) obtain data, calculate feature and prediction potential customers
Data=get_data (channel, cal_number) # obtains the data on cal_number corresponding date
Feature=cal_feature (data) # calculates this day data characteristic of correspondence data
Buy_flag field is set to the factor by feature [, 14]=as.factor (feature [, 14]) #
Feature0=feature [which (feature $ buy_flag==0) ,] # extraction is labeled as the record of 0 as predicted object
Pre_rf=predict (model_rf, feature0 [, 3:14]) # model is predicted
Potential_ip=feature0 [which (pre_rf==1), 1:2] # label taking is designated as ip and cookie of 1 as potential customers
(2) by login_id, association user_info table, upgrades user basic information
Essential information comprises the information such as age, sex, mailbox, birthday of user, so that the Promotion Strategy under some lines is done in website.
Step5: start-up routine identifies potential customers automatically
Only need perform update_info (channe, cal_number) function when performing whole program, before execution function, obtain system data, is pushed away cal_number parameter when performing as program the previous day system data.
Step6: model performance is verified
The potential customers' information table finally dug out associates a new station log sheet by vinfo, obtains each potential customers and digs out the access behavior of 30 days of day after date.If this client had successful payment mark in follow-up 30 days, namely request contains ' paysuccess ', and regular expression intercept obtain a new station log sheet in order ID in sequence information table payment status for pay the bill, now think and the follow-up certain generation buying behavior of these potential customers prove model success prediction.Therefore index is verified using follow-up buying rate as model performance.
It should be pointed out that under the premise without departing from the principles of the invention, do suitably amendment or replace, these are revised or replace and also should be considered as protection scope of the present invention.
Claims (3)
1., based on potential customers' method for digging of customer action feature, it is characterized in that:
Step one: data prediction;
1): data cleansing
Original log record have accumulated a large amount of client's browsing informations, is much the redundant information irrelevant with data mining, such as picture, short-message verification, Logo pictorial information, first needs to delete unwanted record row;
2): form URL list of rules
Analyze the REQUEST field in a new station web data, to when comprising ' confirm ', represent purpose purchase etc., final formation URL list of rules; During subsequent calculations feature, do not need to analyze request field one by one, according to request field with the url coupling in url list of rules, url_name can be obtained;
3): user label
Combine with vinfo, iptonumber, Customer ID to identify user in access log table;
Vinfo: be equivalent to cookie, indicates a computing machine;
Iptonumber:ip address, same computer logs in different place, has different ip;
Login_id: Member Entrance id, login_id=-1 when non-member logs in.
4): feature extraction
In units of a session, analyze the access source of each user in single session, browsing pages number, browse product details number of pages, browse product number, page browsing duration, product details page browsing duration, check filtered list number of times, whether check business topic, user's odd-numbered day browses the period first, whether user checks the characteristic attributes such as shopping cart, and using user, whether purpose is bought as category attribute, finally forms training sample with this feature;
5): screening training set
Behavioral data information in web daily record is the behavioural information data that in certain time period, total user produces on a new website, station, this wherein just includes the people and loyalty customer that repeatedly do shopping, the people that shopping number of times is few and existing customer, potential customers and browsed site home page, but the behavioral data not browsing that the people of commodity in any website and pure viewer produce;
By analyzing the purchase number of times in a period of time, excluding the customer data repeatedly bought, choosing the client that initial purchase is carried out to a certain product or the client do not bought after browsing as excavation object;
Step 2: based on the Characteristic Attribute Reduction of rough set;
For category attribute, 11 characteristic attributes that step one is extracted, redundant attributes according to rough set theory, under the prerequisite not affecting classification performance, must be divided out by the characteristic attribute of redundancy, thus reduces operand, improves nicety of grading;
Method step:
First relative positive field is utilized to ask core Core:
1): initialization data Core=φ, C={a
1, a
2..., a
jj=1,2 ... 11, a
jfor characteristic attribute, D={a
12be category attribute, calculate relative positive field POS
c(D);
2): B=C-{a
j, calculate relative positive field POS
b, and compare POS (D)
c(D), POS
b(D).If POS
c(D) ≠ POS
b(D), then a
jfor core attributes, Core=Core ∩ B, whether each attribute of cycle criterion is core attributes;
3): return Core, terminate;
Next utilizes attribute dependability to ask yojan Reduce:
1): initialization data, residue attribute RestAtt=C-Core, Reduce=Core,
2): compare POS
core(D), POS
c(D), if equal, then Core is yojan, otherwise forwards step3 to;
3): each residue attribute a in circulation RestAtt
jif,
select the attribute a making K value maximum
k, make Reduce=Reduce ∪ { a
k, RestAtt=RestAtt-{a
k, and compare POS
restAttand POS (D)
c(D), if equal, forward step4 to, otherwise continue circulation;
4): return Reduce, terminate;
Reduce is now the characteristic attribute of final input sorter;
Step 3: based on the random forest potential customers model of cognition of customer action feature;
Random forests algorithm uses the lingware bag randomForest4.6-6 of R3.0.2 software to realize, program connects oracle database by data source ODBC, use function get_data () to obtain desired data, use function cal_feture () to calculate data characteristics; After screening training set, call random forest disaggregated model model_rf and prediction is carried out to characteristic obtain potential customers ip and cookie information, finally by ip and cookie search in data with existing table potential customers user profile and in write into Databasce;
In step 3:
1): connection data storehouse, the function of function get_data () for obtain desired data from database, and parameter chan is DataBase combining, and cal_number is the required date obtaining data,
data=sqlQuery(chan,sql,stringsAsFactors=FALSE)
In being wrapped by RODBC, odbcConnect () function is set up R and is connected with oracle database:
chan=odbcConnect("dm_xyz",uid='######',pwd='******')
Wherein, parameter d m_xyz is the system DSN name of data source ODBC, and uid is user name, and pwd is user login code;
After building database connects, obtain desired data in database by performing sql statement; And in sql statement, add the data cleansing rule of step one;
2): URL mates, browsing pages information is upgraded;
Read in the URL rule txt document of step 2 by this locality, according to the key word of the REQUEST fields match URL rule in data, upgrade VISIT_PAGE field, the record without occurrence is then set to "-1 ";
Step3: feature calculation cal_feature (data)
The function of function cal_feature is the odd-numbered day Data Segmentation that get_data function obtains is become different to browse session, calculates feature finally obtain characteristic data set to single session;
Step 4: potential customers' model of cognition performance verification
Utilizing oracle edit and storage process, judging that the potential customers that dig out are digging out the real ratio bought in day after date one month, as model performance checking index.
2. potential customers' method for digging according to claim 1, is characterized in that, in units of a session, is analyzed as follows feature, finally forms training sample:
Feature 1: access source, according to first referer of each session, distinguishes the access source of client; Advertisement putting, search engine, mail, directly access, other;
Feature 2: browsing pages number, gets the page number that in a session, user browses;
Feature 3: browse product details number of pages, gets user in a session and browses product details number of pages;
Feature 4: page browsing duration, in a session, the duration of browsing of each page of user is averaged; ;
Feature 5: product details page browsing duration, in a session, the duration of browsing of each product details page of user is averaged;
Feature 6: the number of times checking filtered list, observing ruquest in a session has ' number of times of viewsearchlist ';
Feature 7: whether check insurance topic; Observe in ruquest and whether have ' baoxian ';
Feature 8: whether check insurance dictionary; Observe in ruquest and whether have ' toptag ';
Feature 9: browse the period; A session access time visit_time first
Feature 10: whether check shopping cart, be ' 1 ', no is ' 0 '; Whether check shopping cart observes in ruquest whether have shopping_car;
Category attribute: whether purpose is bought, and be ' 1 ', no is ' 0 '; Whether purpose is bought is judge whether have confirm in ruquest, containing confirm, the buying behavior of generation purpose is described.
3. potential customers' method for digging according to claim 1, is characterized in that, the feature extraction of data processing is:
(1) cookie information comprises
It is not the record value of '-1 ' that #cookie information gets VINFO field first
(2) whether log in
(3) browsing pages number and the page on average browse duration
# browsing pages number
page_tag=which(tmp$VISIT_PAGE!='-1')
page_n=length(page_tag)
# product details page number of pages
Prod_tag=which (tmp $ VISIT_PAGE==' product details page ')
page_prod=length(prod_tag)
The # page and product details page browse duration (page_n-1)
The request time of time=strptime (tmp [page_tag, 2], " %Y-%m-%d%H:%M:%S ") # actual pages
Stay_time=as.vector (diff (time)) the # page request mistiming is as the residence time of the page
Page_time_avg=sum (stay_time, na.rm=T)/page_n# page average access duration
Prod_time=stay_time [which (page_tag%in%prod_tag)] # product details page total residence time
Prod_time_avg=sum (prod_time, na.rm=T)/average duration of page_prod# product details page
(4) number of times of filtered list is checked
# filtered list number of times (0 expression is not searched for)
Sear_n=length (which (tmp $ VISIT_PAGE==" search listing "))
(5) whether shopping cart was checked
(6) insurance topic whether was checked
(7) insurance dictionary whether was checked
(8) type of source web, judges source web according to REFERER and REFERER_SOURCE_WORD field keys.
(9) time period of browsing, the different browsing time section of user is distinguished according to VISIT_TIME field.
(10) whether purpose purchase and predictive variable
Final synthesis obs observational record returns, and screening first purchase and the user do not bought after browsing, form training sample.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510903856.4A CN105488697A (en) | 2015-12-09 | 2015-12-09 | Potential customer mining method based on customer behavior characteristics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510903856.4A CN105488697A (en) | 2015-12-09 | 2015-12-09 | Potential customer mining method based on customer behavior characteristics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105488697A true CN105488697A (en) | 2016-04-13 |
Family
ID=55675664
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510903856.4A Pending CN105488697A (en) | 2015-12-09 | 2015-12-09 | Potential customer mining method based on customer behavior characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105488697A (en) |
Cited By (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106250481A (en) * | 2016-07-29 | 2016-12-21 | 深圳市永兴元科技有限公司 | Data digging methods based on big data and device |
CN106294587A (en) * | 2016-07-28 | 2017-01-04 | 焦点科技股份有限公司 | Special topic module drainage effect methods of exhibiting in the website of a kind of Rapid Implementation |
CN106294778A (en) * | 2016-08-11 | 2017-01-04 | 北京小米移动软件有限公司 | Information-pushing method and device |
CN106294823A (en) * | 2016-08-17 | 2017-01-04 | 上海云信留客信息科技有限公司 | Abnormality detection and the method for elimination for big data cleansing |
CN106375431A (en) * | 2016-08-31 | 2017-02-01 | 北京城市网邻信息技术有限公司 | Business opportunity recommendation method and device |
CN106713034A (en) * | 2016-12-23 | 2017-05-24 | 广州帷策智能科技有限公司 | Wechat public account making user group activation monitoring method and apparatus |
CN106991175A (en) * | 2017-04-06 | 2017-07-28 | 百度在线网络技术(北京)有限公司 | A kind of customer information method for digging, device, equipment and storage medium |
CN107516236A (en) * | 2017-07-22 | 2017-12-26 | 长沙兔子代跑网络科技有限公司 | A kind of method and device that generation race client is excavated according to user behavior data |
CN107526778A (en) * | 2017-07-22 | 2017-12-29 | 长沙兔子代跑网络科技有限公司 | A kind of method and device that generation race client is excavated according to user behavior data |
CN107590688A (en) * | 2017-08-24 | 2018-01-16 | 平安科技(深圳)有限公司 | The recognition methods of target customer and terminal device |
CN107679889A (en) * | 2017-09-08 | 2018-02-09 | 平安科技(深圳)有限公司 | The recognition methods of potential customers a kind of and terminal device |
CN107862556A (en) * | 2017-12-04 | 2018-03-30 | 北京奇艺世纪科技有限公司 | A kind of put-on method and system of VIP advertisements |
CN107886382A (en) * | 2016-09-29 | 2018-04-06 | 北京京东尚科信息技术有限公司 | The method, apparatus and system of channel drainage effect in analyzing web site station |
CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
CN108053263A (en) * | 2017-12-28 | 2018-05-18 | 北京金堤科技有限公司 | The method and device of potential user's data mining |
CN108256907A (en) * | 2018-01-09 | 2018-07-06 | 北京腾云天下科技有限公司 | A kind of construction method and computing device of customer grouping model |
CN108683949A (en) * | 2018-05-18 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of live streaming platform potential user |
WO2018191918A1 (en) * | 2017-04-20 | 2018-10-25 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for learning-based group tagging |
CN108932625A (en) * | 2017-05-23 | 2018-12-04 | 北京京东尚科信息技术有限公司 | Analysis method, device, medium and the electronic equipment of user behavior data |
CN109191169A (en) * | 2018-07-19 | 2019-01-11 | 国政通科技有限公司 | Precisely hit the method for high-end tourism potential user |
CN109255638A (en) * | 2017-07-13 | 2019-01-22 | 北京融和友信科技股份有限公司 | A kind of mathematical model for excavating potential customers |
CN109558396A (en) * | 2018-10-24 | 2019-04-02 | 深圳市万屏时代科技有限公司 | A kind of user demand data cleaning method and system |
CN109983490A (en) * | 2016-10-06 | 2019-07-05 | 邓白氏公司 | The Machine learning classifiers and prediction engine that the potential customers of artificial intelligence optimization determine are carried out on winning/losing classification |
CN109977977A (en) * | 2017-12-28 | 2019-07-05 | 中移信息技术有限公司 | A kind of method and corresponding intrument identifying potential user |
CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
CN110232589A (en) * | 2019-05-16 | 2019-09-13 | 浙江华坤道威数据科技有限公司 | A kind of intention customer analysis system based on big data |
CN110476159A (en) * | 2017-03-30 | 2019-11-19 | 日本电气株式会社 | Information processing system, characteristic value illustration method and characteristic value read-me |
CN110637316A (en) * | 2016-12-22 | 2019-12-31 | 奥恩全球运营有限公司,新加坡分公司 | System and method for intelligent prospective object recognition using online resources and neural network processing to classify tissue based on published material |
CN111091282A (en) * | 2019-12-10 | 2020-05-01 | 焦点科技股份有限公司 | Customer loyalty segmentation method based on user behavior data |
CN111292194A (en) * | 2018-12-06 | 2020-06-16 | 泰康保险集团股份有限公司 | Online insurance client data processing method, device, medium and electronic equipment |
CN111611514A (en) * | 2020-04-11 | 2020-09-01 | 上海淇玥信息技术有限公司 | Page display method and device based on user login information and electronic equipment |
US10769159B2 (en) | 2016-12-22 | 2020-09-08 | Aon Global Operations Plc, Singapore Branch | Systems and methods for data mining of historic electronic communication exchanges to identify relationships, patterns, and correlations to deal outcomes |
CN111681051A (en) * | 2020-06-08 | 2020-09-18 | 上海汽车集团股份有限公司 | Purchasing intention degree prediction method, device, storage medium and terminal |
CN111914187A (en) * | 2020-07-23 | 2020-11-10 | 向杰 | Method for recommending commodities and tracking recommending relation chain |
CN112070519A (en) * | 2019-06-11 | 2020-12-11 | 中国科学院沈阳自动化研究所 | Prediction method based on data global search and feature classification |
US10951695B2 (en) | 2019-02-14 | 2021-03-16 | Aon Global Operations Se Singapore Branch | System and methods for identification of peer entities |
CN112598007A (en) * | 2021-03-04 | 2021-04-02 | 浙江所托瑞安科技集团有限公司 | Method, device and equipment for screening picture training set and readable storage medium |
CN112667911A (en) * | 2021-01-14 | 2021-04-16 | 中山世达模型制造有限公司 | Method for searching potential customers by using social software big data |
TWI735932B (en) * | 2019-08-21 | 2021-08-11 | 崑山科技大學 | Real estate potential customer forecasting system and method thereof |
CN113538025A (en) * | 2020-04-14 | 2021-10-22 | 中国移动通信集团浙江有限公司 | Method and device for predicting replacement of terminal equipment |
CN113554460A (en) * | 2021-07-19 | 2021-10-26 | 北京沃东天骏信息技术有限公司 | Method and device for identifying potential user |
CN113934616A (en) * | 2021-12-16 | 2022-01-14 | 深圳市活力天汇科技股份有限公司 | Method for judging abnormal user based on user operation time sequence |
CN116418881A (en) * | 2023-04-18 | 2023-07-11 | 吉林省禹语网络科技有限公司 | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission |
CN116523572A (en) * | 2023-06-28 | 2023-08-01 | 悦享星光(北京)科技有限公司 | Client mining method and system based on client behavior characteristics |
CN116523600A (en) * | 2023-05-05 | 2023-08-01 | 佛山市大迈信息科技有限公司 | Customer classification method and system based on behavior analysis |
CN116418881B (en) * | 2023-04-18 | 2024-06-04 | 湖南供销电子商务股份有限公司 | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6839680B1 (en) * | 1999-09-30 | 2005-01-04 | Fujitsu Limited | Internet profiling |
CN102542335A (en) * | 2011-06-16 | 2012-07-04 | 广州市龙泰信息技术有限公司 | Mixed data mining method |
CN104142960A (en) * | 2013-05-10 | 2014-11-12 | 上海普华诚信信息技术有限公司 | Internet data analysis system |
CN105069654A (en) * | 2015-08-07 | 2015-11-18 | 新一站保险代理有限公司 | User identification based website real-time/non-real-time marketing investment method and system |
-
2015
- 2015-12-09 CN CN201510903856.4A patent/CN105488697A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6839680B1 (en) * | 1999-09-30 | 2005-01-04 | Fujitsu Limited | Internet profiling |
CN102542335A (en) * | 2011-06-16 | 2012-07-04 | 广州市龙泰信息技术有限公司 | Mixed data mining method |
CN104142960A (en) * | 2013-05-10 | 2014-11-12 | 上海普华诚信信息技术有限公司 | Internet data analysis system |
CN105069654A (en) * | 2015-08-07 | 2015-11-18 | 新一站保险代理有限公司 | User identification based website real-time/non-real-time marketing investment method and system |
Cited By (71)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106294587B (en) * | 2016-07-28 | 2019-05-10 | 焦点科技股份有限公司 | Thematic module drainage effect methods of exhibiting in a kind of website of Rapid Implementation |
CN106294587A (en) * | 2016-07-28 | 2017-01-04 | 焦点科技股份有限公司 | Special topic module drainage effect methods of exhibiting in the website of a kind of Rapid Implementation |
CN106250481A (en) * | 2016-07-29 | 2016-12-21 | 深圳市永兴元科技有限公司 | Data digging methods based on big data and device |
CN106294778A (en) * | 2016-08-11 | 2017-01-04 | 北京小米移动软件有限公司 | Information-pushing method and device |
CN106294778B (en) * | 2016-08-11 | 2019-09-10 | 北京小米移动软件有限公司 | Information-pushing method and device |
CN106294823A (en) * | 2016-08-17 | 2017-01-04 | 上海云信留客信息科技有限公司 | Abnormality detection and the method for elimination for big data cleansing |
CN106294823B (en) * | 2016-08-17 | 2019-03-22 | 上海云信留客信息科技有限公司 | The method of abnormality detection and elimination for big data cleaning |
CN106375431B (en) * | 2016-08-31 | 2019-12-31 | 北京城市网邻信息技术有限公司 | Business opportunity recommendation method and device |
CN106375431A (en) * | 2016-08-31 | 2017-02-01 | 北京城市网邻信息技术有限公司 | Business opportunity recommendation method and device |
CN107886382B (en) * | 2016-09-29 | 2021-11-30 | 北京京东尚科信息技术有限公司 | Method, device and system for analyzing channel drainage effect in website |
CN107886382A (en) * | 2016-09-29 | 2018-04-06 | 北京京东尚科信息技术有限公司 | The method, apparatus and system of channel drainage effect in analyzing web site station |
CN109983490A (en) * | 2016-10-06 | 2019-07-05 | 邓白氏公司 | The Machine learning classifiers and prediction engine that the potential customers of artificial intelligence optimization determine are carried out on winning/losing classification |
CN109983490B (en) * | 2016-10-06 | 2023-08-29 | 邓白氏公司 | Machine learning classifier and prediction engine for potential customer determination of artificial intelligence optimization on winning/losing classifications |
US10769159B2 (en) | 2016-12-22 | 2020-09-08 | Aon Global Operations Plc, Singapore Branch | Systems and methods for data mining of historic electronic communication exchanges to identify relationships, patterns, and correlations to deal outcomes |
US11455313B2 (en) | 2016-12-22 | 2022-09-27 | Aon Global Operations Se, Singapore Branch | Systems and methods for intelligent prospect identification using online resources and neural network processing to classify organizations based on published materials |
CN110637316B (en) * | 2016-12-22 | 2021-04-13 | 奥恩全球运营有限公司,新加坡分公司 | System and method for prospective object identification |
CN110637316A (en) * | 2016-12-22 | 2019-12-31 | 奥恩全球运营有限公司,新加坡分公司 | System and method for intelligent prospective object recognition using online resources and neural network processing to classify tissue based on published material |
CN106713034A (en) * | 2016-12-23 | 2017-05-24 | 广州帷策智能科技有限公司 | Wechat public account making user group activation monitoring method and apparatus |
US11727203B2 (en) | 2017-03-30 | 2023-08-15 | Dotdata, Inc. | Information processing system, feature description method and feature description program |
CN110476159A (en) * | 2017-03-30 | 2019-11-19 | 日本电气株式会社 | Information processing system, characteristic value illustration method and characteristic value read-me |
CN106991175A (en) * | 2017-04-06 | 2017-07-28 | 百度在线网络技术(北京)有限公司 | A kind of customer information method for digging, device, equipment and storage medium |
CN106991175B (en) * | 2017-04-06 | 2020-08-11 | 百度在线网络技术(北京)有限公司 | Customer information mining method, device, equipment and storage medium |
WO2018191918A1 (en) * | 2017-04-20 | 2018-10-25 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for learning-based group tagging |
CN109690571A (en) * | 2017-04-20 | 2019-04-26 | 北京嘀嘀无限科技发展有限公司 | Group echo system and method based on study |
CN109690571B (en) * | 2017-04-20 | 2020-09-18 | 北京嘀嘀无限科技发展有限公司 | Learning-based group tagging system and method |
CN108932625A (en) * | 2017-05-23 | 2018-12-04 | 北京京东尚科信息技术有限公司 | Analysis method, device, medium and the electronic equipment of user behavior data |
CN108932625B (en) * | 2017-05-23 | 2022-04-26 | 北京京东尚科信息技术有限公司 | User behavior data analysis method, device, medium and electronic equipment |
CN109255638A (en) * | 2017-07-13 | 2019-01-22 | 北京融和友信科技股份有限公司 | A kind of mathematical model for excavating potential customers |
CN109255638B (en) * | 2017-07-13 | 2022-04-26 | 北京融和友信科技股份有限公司 | Mathematical model for mining potential customers |
CN107516236A (en) * | 2017-07-22 | 2017-12-26 | 长沙兔子代跑网络科技有限公司 | A kind of method and device that generation race client is excavated according to user behavior data |
CN107526778A (en) * | 2017-07-22 | 2017-12-29 | 长沙兔子代跑网络科技有限公司 | A kind of method and device that generation race client is excavated according to user behavior data |
WO2019037202A1 (en) * | 2017-08-24 | 2019-02-28 | 平安科技(深圳)有限公司 | Method and apparatus for recognising target customer, electronic device and medium |
CN107590688A (en) * | 2017-08-24 | 2018-01-16 | 平安科技(深圳)有限公司 | The recognition methods of target customer and terminal device |
CN107679889A (en) * | 2017-09-08 | 2018-02-09 | 平安科技(深圳)有限公司 | The recognition methods of potential customers a kind of and terminal device |
CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
CN107862556A (en) * | 2017-12-04 | 2018-03-30 | 北京奇艺世纪科技有限公司 | A kind of put-on method and system of VIP advertisements |
CN108053263A (en) * | 2017-12-28 | 2018-05-18 | 北京金堤科技有限公司 | The method and device of potential user's data mining |
CN109977977A (en) * | 2017-12-28 | 2019-07-05 | 中移信息技术有限公司 | A kind of method and corresponding intrument identifying potential user |
CN108256907A (en) * | 2018-01-09 | 2018-07-06 | 北京腾云天下科技有限公司 | A kind of construction method and computing device of customer grouping model |
CN108683949A (en) * | 2018-05-18 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of extracting method and device of live streaming platform potential user |
CN109191169A (en) * | 2018-07-19 | 2019-01-11 | 国政通科技有限公司 | Precisely hit the method for high-end tourism potential user |
CN109558396A (en) * | 2018-10-24 | 2019-04-02 | 深圳市万屏时代科技有限公司 | A kind of user demand data cleaning method and system |
CN111292194A (en) * | 2018-12-06 | 2020-06-16 | 泰康保险集团股份有限公司 | Online insurance client data processing method, device, medium and electronic equipment |
CN111292194B (en) * | 2018-12-06 | 2023-08-22 | 泰康保险集团股份有限公司 | Online application client data processing method and device, medium and electronic equipment |
US10951695B2 (en) | 2019-02-14 | 2021-03-16 | Aon Global Operations Se Singapore Branch | System and methods for identification of peer entities |
CN110222272A (en) * | 2019-04-18 | 2019-09-10 | 广东工业大学 | A kind of potential customers excavate and recommended method |
CN110232589A (en) * | 2019-05-16 | 2019-09-13 | 浙江华坤道威数据科技有限公司 | A kind of intention customer analysis system based on big data |
CN112070519A (en) * | 2019-06-11 | 2020-12-11 | 中国科学院沈阳自动化研究所 | Prediction method based on data global search and feature classification |
CN112070519B (en) * | 2019-06-11 | 2024-03-05 | 中国科学院沈阳自动化研究所 | Prediction method based on data global search and feature classification |
TWI735932B (en) * | 2019-08-21 | 2021-08-11 | 崑山科技大學 | Real estate potential customer forecasting system and method thereof |
CN111091282A (en) * | 2019-12-10 | 2020-05-01 | 焦点科技股份有限公司 | Customer loyalty segmentation method based on user behavior data |
CN111091282B (en) * | 2019-12-10 | 2022-07-22 | 焦点科技股份有限公司 | Customer loyalty segmentation method based on user behavior data |
CN111611514A (en) * | 2020-04-11 | 2020-09-01 | 上海淇玥信息技术有限公司 | Page display method and device based on user login information and electronic equipment |
CN111611514B (en) * | 2020-04-11 | 2024-04-23 | 上海淇玥信息技术有限公司 | Page display method and device based on user login information and electronic equipment |
CN113538025B (en) * | 2020-04-14 | 2024-03-22 | 中国移动通信集团浙江有限公司 | Replacement prediction method and device for terminal equipment |
CN113538025A (en) * | 2020-04-14 | 2021-10-22 | 中国移动通信集团浙江有限公司 | Method and device for predicting replacement of terminal equipment |
CN111681051A (en) * | 2020-06-08 | 2020-09-18 | 上海汽车集团股份有限公司 | Purchasing intention degree prediction method, device, storage medium and terminal |
CN111681051B (en) * | 2020-06-08 | 2023-09-26 | 上海汽车集团股份有限公司 | Purchase intention prediction method and device, storage medium and terminal |
CN111914187B (en) * | 2020-07-23 | 2023-09-08 | 向杰 | Commodity recommendation and recommendation relation chain tracking method |
CN111914187A (en) * | 2020-07-23 | 2020-11-10 | 向杰 | Method for recommending commodities and tracking recommending relation chain |
CN112667911A (en) * | 2021-01-14 | 2021-04-16 | 中山世达模型制造有限公司 | Method for searching potential customers by using social software big data |
CN112598007B (en) * | 2021-03-04 | 2021-05-18 | 浙江所托瑞安科技集团有限公司 | Method, device and equipment for screening picture training set and readable storage medium |
CN112598007A (en) * | 2021-03-04 | 2021-04-02 | 浙江所托瑞安科技集团有限公司 | Method, device and equipment for screening picture training set and readable storage medium |
CN113554460A (en) * | 2021-07-19 | 2021-10-26 | 北京沃东天骏信息技术有限公司 | Method and device for identifying potential user |
CN113934616B (en) * | 2021-12-16 | 2022-03-18 | 深圳市活力天汇科技股份有限公司 | Method for judging abnormal user based on user operation time sequence |
CN113934616A (en) * | 2021-12-16 | 2022-01-14 | 深圳市活力天汇科技股份有限公司 | Method for judging abnormal user based on user operation time sequence |
CN116418881A (en) * | 2023-04-18 | 2023-07-11 | 吉林省禹语网络科技有限公司 | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission |
CN116418881B (en) * | 2023-04-18 | 2024-06-04 | 湖南供销电子商务股份有限公司 | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission |
CN116523600A (en) * | 2023-05-05 | 2023-08-01 | 佛山市大迈信息科技有限公司 | Customer classification method and system based on behavior analysis |
CN116523572A (en) * | 2023-06-28 | 2023-08-01 | 悦享星光(北京)科技有限公司 | Client mining method and system based on client behavior characteristics |
CN116523572B (en) * | 2023-06-28 | 2023-09-08 | 悦享星光(北京)科技有限公司 | Client mining method and system based on client behavior characteristics |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105488697A (en) | Potential customer mining method based on customer behavior characteristics | |
CN110020660B (en) | Integrity assessment of unstructured processes using Artificial Intelligence (AI) techniques | |
US11157926B2 (en) | Digital content prioritization to accelerate hyper-targeting | |
US11373106B2 (en) | System and method for detecting friction in websites | |
US8494897B1 (en) | Inferring profiles of network users and the resources they access | |
CN102236663B (en) | Query method, query system and query device based on vertical search | |
CN110222272A (en) | A kind of potential customers excavate and recommended method | |
CN109189904A (en) | Individuation search method and system | |
Aggrawal et al. | Brand analysis framework for online marketing: ranking web pages and analyzing popularity of brands on social media | |
US20060112111A1 (en) | System and methods for data analysis and trend prediction | |
US20130024282A1 (en) | Automatic purchase history tracking | |
CN106022800A (en) | User feature data processing method and device | |
EP2704080A1 (en) | Recommendation systems and methods | |
Al-Azmi | Data, text and web mining for business intelligence: a survey | |
CN111488385B (en) | Data processing method and device based on artificial intelligence and computer equipment | |
JP2009193465A (en) | Information processor, information providing system, information processing method, and program | |
Lee et al. | Fundamentals of big data network analysis for research and industry | |
US20190080352A1 (en) | Segment Extension Based on Lookalike Selection | |
EP2933734A1 (en) | Method and system for the structural analysis of websites | |
CN113901308A (en) | Knowledge graph-based enterprise recommendation method and recommendation device and electronic equipment | |
CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
Zhao et al. | Anatomy of a web-scale resale market: a data mining approach | |
CN109190027A (en) | Multi-source recommended method, terminal, server, computer equipment, readable medium | |
US20150142782A1 (en) | Method for associating metadata with images | |
KR20100046421A (en) | Method and server for estimating preference of commodity |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160413 |