CN107507042A - Marketing method and system based on user's portrait - Google Patents
Marketing method and system based on user's portrait Download PDFInfo
- Publication number
- CN107507042A CN107507042A CN201710833409.5A CN201710833409A CN107507042A CN 107507042 A CN107507042 A CN 107507042A CN 201710833409 A CN201710833409 A CN 201710833409A CN 107507042 A CN107507042 A CN 107507042A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- hotel
- prediction model
- judging
- 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
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of marketing method based on user's portrait and system, the marketing method to include:S1, user data is obtained, the user data includes user's representation data;S2, by decision Tree algorithms or XGBoost algorithms the user data is handled, establish single Probabilistic Prediction Model under user;S3, lower single probability according to single Probabilistic Prediction Model prediction user under the user;S4, the market content according to corresponding to lower single probability to user's transmission of the user.The present invention establishes on line under user under single Probabilistic Prediction Model and offline user single Probabilistic Prediction Model to predict lower single probability of user respectively by the user data drawn a portrait including user;Using user of the lower single probability less than given threshold as reward voucher targeted customer, realization more accurately finds targeted customer to retrieve user, and realization is effectively improved reward voucher effect, so as to save cost, and realizes maximum revenue.
Description
Technical field
The present invention relates to grass roots marketing techniques field, more particularly to a kind of marketing method and system based on user's portrait.
Background technology
Existing marketing model to user mainly by providing reward voucher to stimulate user to be consumed, so as to improve use
Family order volume etc..Existing reward voucher issue policy is usually by the way of general hair reward voucher, still, because the reward voucher is sent out
The user for consumption of natively having a mind to place an order can also be sent the coupon to by putting strategy, be turned so as to cause to reach lifting order
The purpose of change, or even the situation that can also cause income to lose.
The content of the invention
The technical problem to be solved in the present invention is to overcome the marketing model using general hair reward voucher of prior art, deposit
The purpose of lifting order conversion can not reached, or even, and it is an object of the present invention to provide one kind is based on the defects of can also cause income to lose
The marketing method and system of user's portrait.
The present invention is that solve above-mentioned technical problem by following technical proposals:
The present invention provides a kind of marketing method based on user's portrait, and the marketing method includes:
S1, user data is obtained, the user data includes user's representation data;
S2, by decision Tree algorithms or a kind of XGBoost (machine learning algorithm) algorithm to the user data at
Reason, establishes single Probabilistic Prediction Model under user;
S3, lower single probability according to single Probabilistic Prediction Model prediction user under the user;
S4, the market content according to corresponding to lower single probability to user's transmission of the user.
It is preferred that also include before step S2:
Judge whether user installs competing product and be to be lost in user or any active ues, judge user do not install competing product and
Be be lost in user when, or judge the competing product of user installation and be loss user when, according to the decision Tree algorithms to the user
Data are handled, and establish single Probabilistic Prediction Model under offline user;
Judging the competing product of user installation and when being any active ues, the user data is being entered according to the XGBoost algorithms
Row processing, establishes on line single Probabilistic Prediction Model under user.
It is preferred that also include before step S2:
Judging that user do not install competing product and when being any active ues, judging whether user is ox user, is judging user
When not being ox user, continue to judge whether user is high frequency user, when being judged as NO, send ladder and purchase certificate again to user;
The ladder purchases certificate and characterizes that number is more when user purchases again again, the more preferential situation of the coupon discount of acquisition.
It is preferred that step S4 is specifically included:
Judge whether lower single probability of the user is less than given threshold, when being judged as YES, send market content to institute
State user;
The market content includes sending reward voucher, sends at least one of advertising campaign information and service guarantee.
It is preferred that the user data for establishing single Probabilistic Prediction Model under the offline user browses including user's history
At least one of data, user's history order data and user's representation data;
User's representation data includes user to the sensitivity information of reward voucher, user preference information, customer consumption energy
At least one of force information, the generous stingy degree information of user, user's value information and liveness information of user;
The user data for establishing single Probabilistic Prediction Model under user on the line browses number including the user's history
According to, the user's history order data, user's representation data, user's displaying live view data, user's real time orders data, use
Hotel's historical data is moved at family, user moves in hotel's real time data, tripartite and competing product real time data and user order train ticket or
At least one of air ticket real time data;
The user, which moves in hotel's historical data, includes hotel's historical sales data, hotel's grade historical data and hotel
At least one of history Housing Price data;
The user, which moves in hotel's real time data, includes hotel's real-time sale amount data, hotel's grade real time data and hotel
At least one of real-time Housing Price data.
The present invention also provides a kind of marketing system based on user's portrait, and the marketing system includes acquiring unit, processing
Unit, predicting unit and transmitting element;
The acquiring unit is used to obtain user data, and the user data includes user's representation data;
The processing unit is used to handle the user data by decision Tree algorithms or XGBoost algorithms, builds
Single Probabilistic Prediction Model under vertical user;
The predicting unit is used for lower single probability that user is predicted according to single Probabilistic Prediction Model under the user;
The transmitting element is used for the market content according to corresponding to lower single probability to user's transmission of the user.
It is preferred that the marketing system also includes the first judging unit;
First judging unit is used to judging whether user to install competing product and be to be lost in user or any active ues,
Judge that user does not install competing product and is when being lost in user, or judging the competing product of user installation and when being loss user, described in calling
Processing unit;
The processing unit is used to handle the user data according to the decision Tree algorithms, establishes offline user
Lower single Probabilistic Prediction Model;
First judging unit is judging the competing product of user installation and when being any active ues, is continuing to call the processing single
Member;
The processing unit is additionally operable to handle the user data according to the XGBoost algorithms, establishes on line
Single Probabilistic Prediction Model under user.
It is preferred that the marketing system also includes the second judging unit;
Second judging unit is used to judge that user do not install competing product and when being any active ues, judge user whether be
Ox user, when it is not ox user to judge user, continue to judge whether user is high frequency user, when being judged as NO, adjust
With the transmitting element;
The transmitting element is additionally operable to transmission ladder and purchases certificate again to user;
The ladder purchases certificate and characterizes that number is more when user purchases again again, the more preferential situation of the coupon discount of acquisition.
It is preferred that the marketing system also includes the 3rd judging unit;
3rd judging unit is used to judge whether lower single probability of the user is less than given threshold, is being judged as YES
When, market content is sent to the user;
The market content includes sending reward voucher, sends at least one of advertising campaign information and service guarantee.
It is preferred that the user data for establishing single Probabilistic Prediction Model under the offline user browses including user's history
At least one of data, user's history order data and user's representation data;
User's representation data includes user to the sensitivity information of reward voucher, user preference information, customer consumption energy
At least one of force information, the generous stingy degree information of user, user's value information and liveness information of user;
The user data for establishing single Probabilistic Prediction Model under user on the line browses number including the user's history
According to, the user's history order data, user's representation data, user's displaying live view data, user's real time orders data, use
Hotel's historical data is moved at family, user moves in hotel's real time data, tripartite and competing product real time data and user order train ticket or
At least one of air ticket real time data;
The user, which moves in hotel's historical data, includes hotel's historical sales data, hotel's grade historical data and hotel
At least one of history Housing Price data;
The user, which moves in hotel's real time data, includes hotel's real-time sale amount data, hotel's grade real time data and hotel
At least one of real-time Housing Price data.
The positive effect of the present invention is:
The present invention first determines whether that whether user installs competing product and be to be lost in user or any active ues, and user is divided into not
Install competing product and be lost in user, the competing product of installation and be lost in user, competing product are not installed and be any active ues and the competing product of installation and
It is the type of any active ues four, and the user data by being drawn a portrait including user establishes on line single probabilistic forecasting mould under user respectively
Single Probabilistic Prediction Model predicts lower single probability of user under type and offline user, and lower single probability is less than to the user of given threshold
As reward voucher targeted customer, realization more accurately finds targeted customer to retrieve different types of user;Meanwhile pass through software
Client, the mode for the multiple channels such as interior letter, short message or Email of standing send most effective conjunction to different types of user respectively
The market contents such as suitable reward voucher are marketed, and are effectively improved reward voucher effect, so as to save cost, and realize income most
Bigization.
Brief description of the drawings
Fig. 1 is the flow chart of the marketing method based on user's portrait of embodiments of the invention 1;
Fig. 2 is the flow chart of the marketing method based on user's portrait of embodiments of the invention 2;
Fig. 3 is the flow chart of the marketing method based on user's portrait of embodiments of the invention 3;
Fig. 4 is the flow chart of the marketing method based on user's portrait of embodiments of the invention 4;
Fig. 5 is the first pass of reminder process on the line of the marketing method based on user's portrait of embodiments of the invention 4
Figure;
Fig. 6 is the second procedure of reminder process on the line of the marketing method based on user's portrait of embodiments of the invention 4
Figure;
Fig. 7 is the structural representation of the marketing system based on user's portrait of embodiments of the invention 5.
Embodiment
The present invention is further illustrated below by the mode of embodiment, but does not therefore limit the present invention to described reality
Apply among a scope.
Embodiment 1
As shown in figure 1, the flow chart of the marketing method based on user's portrait for the present embodiment.
The marketing method based on user's portrait of the present embodiment includes:
S101, obtain user data;
S102, judge whether user installs competing product and be to be lost in user or any active ues, judging that user do not install
Competing product and be lost in user when, the user data is handled according to the decision Tree algorithms, offline user is established and places an order
Probabilistic Prediction Model;
Wherein, establish the user data of single Probabilistic Prediction Model under the offline user including user's history browse data,
At least one of user's history order data and user's representation data.
User's representation data includes user to the sensitivity information of reward voucher, user preference information, customer consumption energy
At least one of force information, the generous stingy degree information of user, user's value information and liveness information of user.
It is lost in user to refer to once use marketing trade company APP (Application, computer applied algorithm), descended singly,
But do not agree be robbed by rival to have very much come the user for browsing or placing an order, such user again in nearest a period of time
The user walked, therefore be referred to as being lost in user.Any active ues refer to often or are used marketing trade company APP user.
S103, lower single probability according to single Probabilistic Prediction Model prediction user under the offline user;
S104, judge whether lower single probability of the user is less than given threshold, when being judged as YES, send market content
To the user.
The market content includes sending reward voucher, sends at least one of advertising campaign information and service guarantee.
Wherein, service guarantee is mainly price guarantee and/or has room guarantee etc. to shop, it is therefore intended that improves the experience of user
Sense so that user does not have to have any worry misgivings when subscribing order.
Market content (sends the use of market content failure for client by software client, stand interior letter, short message respectively
Family) and at least one of EDM (Email Direct Marketing, Email Marketing) channel.
The present embodiment belongs to the situation do not installed competing product and be loss user for user, is established by user data offline
Single Probabilistic Prediction Model under user, single probability under user is predicted, using user of the lower single probability less than given threshold as reward voucher
Targeted customer, realization more accurately find targeted customer to retrieve user, and send market content to corresponding user;Meanwhile
Most effective suitable reward voucher is sent by way of software client, the multiple channels such as interior letter, short message and/or Email of standing
Marketed etc. marketing methods, realization is effectively improved reward voucher effect, so as to save cost, and realizes maximum revenue.
Embodiment 2
As shown in Fig. 2 the marketing method based on user's portrait of the present embodiment is compared with Example 1, difference is:
The marketing method based on user's portrait of the present embodiment includes:
S201, obtain user data;
S202, judge that whether user installs competing product and be to be lost in user or any active ues, is judging that user installation is competing
Product and be lost in user when, the user data is handled according to the decision Tree algorithms, offline user is established and places an order generally
Rate forecast model;
S203, lower single probability according to single Probabilistic Prediction Model prediction user under the user;
S204, judge whether lower single probability of the user is less than given threshold, when being judged as YES, send market content
To the user.
The present embodiment belongs to the situation installed competing product and be loss user for user, and offline use is established by user data
Single Probabilistic Prediction Model under family, single probability under user is predicted, using user of the lower single probability less than given threshold as reward voucher mesh
User is marked, realization more accurately finds targeted customer to retrieve user, and sends market content to corresponding user;It is meanwhile logical
Cross software client, the mode for the multiple channels such as interior letter, short message and/or Email of standing sends most effective suitable reward voucher etc.
Marketing methods are marketed, and realization is effectively improved reward voucher effect, so as to save cost, and realizes maximum revenue.
Embodiment 3
As shown in figure 3, the marketing method based on user's portrait of the present embodiment is compared with Example 1, difference is:
The marketing method based on user's portrait of the present embodiment includes:
S301, obtain user data;
S302, judge that whether user installs competing product and be to be lost in user or any active ues, is judging that user installation is competing
Product and when being any active ues, handle the user data according to the XGBoost algorithms, establish offline user and place an order generally
Rate forecast model;
Wherein, the user data for establishing single Probabilistic Prediction Model under user on the line is clear including the user's history
Look at data, the user's history order data, user's representation data, user's displaying live view data, user's real time orders number
According to, user moves in hotel's historical data, user moves in hotel's real time data, tripartite and competing product real time data and user order train
At least one of ticket or air ticket real time data.
User's representation data includes user to the sensitivity information of reward voucher, user preference information, customer consumption energy
At least one of force information, the generous stingy degree information of user, user's value information and liveness information of user.
Tripartite and competing product real time data include tripartite's data, the installation data of competing product software and real-time log-on data and production
Product (the same house type in such as hotel) price comparison information.
The user, which moves in hotel's historical data, includes hotel's historical sales data, hotel's grade historical data and hotel
At least one of history Housing Price data;
The user, which moves in hotel's real time data, includes hotel's real-time sale amount data, hotel's grade real time data and hotel
At least one of real-time Housing Price data.
S303, lower single probability according to single Probabilistic Prediction Model prediction user under the user;
S304, judge whether lower single probability of the user is less than given threshold, when being judged as YES, send market content
To the user.
The market content includes sending reward voucher, sends at least one of advertising campaign information and service guarantee.
Wherein, service guarantee is mainly price guarantee and/or has room guarantee etc. to shop, it is therefore intended that improves the experience of user
Sense so that user does not have to have any worry misgivings when subscribing order.
Market content (sends the use of market content failure for client by software client, stand interior letter, short message respectively
Family) and at least one of EDM channel.
The present embodiment belongs to the competing product of installation for user and is the situation of any active ues, is established on line and used by user data
Single Probabilistic Prediction Model under family, single probability under user is predicted, using user of the lower single probability less than given threshold as reward voucher mesh
User is marked, realization more accurately finds targeted customer to retrieve user, and sends market content to corresponding user;It is meanwhile logical
Cross software client, the mode for the multiple channels such as interior letter, short message and/or Email of standing sends most effective suitable reward voucher etc.
Marketing methods are marketed, and realization is effectively improved reward voucher effect, so as to save cost, and realizes maximum revenue.
Embodiment 4
As shown in figure 4, the marketing method based on user's portrait of the present embodiment is compared with Example 1, difference is:
The marketing method based on user's portrait of the present embodiment includes:
S401, obtain user data;
S402, judge whether user installs competing product and be to be lost in user or any active ues, judging that user do not install
Competing product and when being any active ues, continue step S403;
S403, judge whether user is ox user, when it is not ox user to judge user, continue whether to judge user
It is high frequency user, when being judged as NO, sends ladder and purchase certificate again to user;
The ladder purchases certificate and characterizes that number is more when user purchases again again, the more preferential situation of the coupon discount of acquisition.
Meanwhile in user competing product are not installed and are any active ues, and neither ox user nor during high frequency user, then
Coupon reminder information is sent to user between in due course, such as enters on line to remind during user browses marketing trade company APP
Or by the mode such as short message prompting under line, promote the multiple purchase rate of old user, improve stickiness of the user to the trade company APP that markets.
Wherein, as shown in figure 5, reminder process includes on line:
S5011, when user enters the client-side search page or the web page browsing page, judge whether user has participated in work
It is dynamic, when being judged as YES, show that user preferential certificate obtains feelings in user's active client searched page or the web page browsing page
Condition;
S5012, judge user whether click on check reward voucher obtain details, when being judged as YES, active client is searched
The rope page or web page browsing page layout switch are that floating layer shows that user preferential certificate obtains details page;When being judged as NO, continue to walk
Rapid S5013;
S5013, judge whether user places an order, when being judged as YES, sent in the page that user completes to place an order to user
Reward voucher obtains situation.
As shown in fig. 6, reminder process also includes on line:
S5021, when user enters the client-side search page or the web page browsing page, judge whether user has participated in work
It is dynamic, when being judged as NO, show that preferential activity is reminded in user's active client searched page or the web page browsing page;
S5022, judge user whether click on check it is preferential activity remind details, when being judged as YES, by active client
Searched page or web page browsing page layout switch are that floating layer shows that details page is reminded in preferential activity;
S5023, judge whether user clicks on activity, when being judged as YES, reward voucher quantity is from this activity
Order after start to accumulate, continue step S5022;When judging that user does not click on activity, continue step S5024;
S5024, judge whether user places an order, when being judged as YES, continue to judge whether user has been participating in activity, sentencing
When disconnected user does not participate in activity, complete the page that places an order in user and show preferential activity prompting, continue to judge user whether point
Activity is hit, when being judged as YES, reward voucher quantity is accumulated since this order, continues step S5025;Judging user
When having been participating in activity, continue step S5025;
Step S5025, the page for completing to place an order in user is shown to user and sends new reward voucher acquisition situation.
The present embodiment belongs to the situation do not installed competing product and be any active ues for user, as user neither ox user
Nor during high frequency user, send ladder to user and purchase certificate again to guide online user's activity, and in due course between give
User sends coupon reminder information, so as to promote the multiple purchase rate of old user, improves stickiness of the user to the trade company APP that markets, has
Reward voucher effect is improved to effect, so as to save cost, and realizes maximum revenue.
Embodiment 5
As shown in fig. 7, the structural representation of the marketing system based on user's portrait for the present embodiment.The marketing system
Including acquiring unit 1, processing unit 2, predicting unit 3, transmitting element 4, the first judging unit 5, the second judging unit 6 and the 3rd
Judging unit 7.
The acquiring unit 1 is used to obtain user data;
The processing unit 2 is used to handle the user data by decision Tree algorithms or XGBoost algorithms, builds
Single Probabilistic Prediction Model under vertical user;
The predicting unit 3 is used for lower single probability that user is predicted according to single Probabilistic Prediction Model under the user;
The transmitting element 4 is used for the market content according to corresponding to lower single probability to user's transmission of the user.
The market content includes sending reward voucher, sends at least one of advertising campaign information and service guarantee.
Wherein, service guarantee is mainly price guarantee and/or has room guarantee etc. to shop, it is therefore intended that improves the experience of user
Sense so that user does not have to have any worry misgivings when subscribing order.
Market content (sends the use of market content failure for client by software client, stand interior letter, short message respectively
Family) and at least one of EDM channel.
First judging unit 5 is used to judging whether user to install competing product and be to be lost in user or any active ues,
Judge user do not install competing product and be lost in user when, or judge the competing product of user installation and be lost in user when, calling institute
State processing unit 1;
The processing unit 1 is used to handle the user data according to the decision Tree algorithms, establishes offline use
Single Probabilistic Prediction Model under family;
Wherein, establish the user data of single Probabilistic Prediction Model under the offline user including user's history browse data,
At least one of user's history order data and user's representation data.
User's representation data includes user to the sensitivity information of reward voucher, user preference information, customer consumption energy
At least one of force information, the generous stingy degree information of user, user's value information and liveness information of user.
First judging unit 5 is judging the competing product of user installation and when being any active ues, is continuing to call the processing single
Member 1;
The processing unit 1 is additionally operable to handle the user data according to the XGBoost algorithms, establishes on line
Single Probabilistic Prediction Model under user.
Wherein, the user data for establishing single Probabilistic Prediction Model under user on the line is clear including the user's history
Look at data, the user's history order data, user's representation data, user's displaying live view data, user's real time orders number
According to, user moves in hotel's historical data, user moves in hotel's real time data, tripartite and competing product real time data and user order train
At least one of ticket or air ticket real time data;
The user, which moves in hotel's historical data, includes hotel's historical sales data, hotel's grade historical data and hotel
At least one of history Housing Price data;
The user, which moves in hotel's real time data, includes hotel's real-time sale amount data, hotel's grade real time data and hotel
At least one of real-time Housing Price data.
Second judging unit 6 is used to judge that user do not install competing product and when being any active ues, whether judges user
It is ox user, when it is not ox user to judge user, continues to judge whether user is high frequency user, when being judged as NO,
Call transmitting element 4;
The transmitting element 4 is additionally operable to transmission ladder and purchases certificate again to user;
The ladder purchases certificate and characterizes that number is more when user purchases again again, the more preferential situation of the coupon discount of acquisition.
3rd judging unit 7 is used to judge whether lower single probability of the user is less than given threshold, is being judged as
When being, market content is sent to the user.
Wherein, in user not install competing product and being any active ues, and neither ox user nor during high frequency user,
User preferential certificate information is reminded between in due course, such as enters on line to remind or pass through during user browses marketing trade company APP
The mode such as short message prompting under line, promote the multiple purchase rate of old user, improve stickiness of the user for the trade company APP that markets.
The marketing system includes also including the 4th judging unit 8, the 5th judging unit 9 and the 6th judging unit 10, the
Seven judging units 11 and the 8th judging unit 12.
4th judging unit 8 is used for when user enters the client-side search page or the web page browsing page, judges to use
Whether family activity, when being judged as YES, show that user is excellent in active client searched page or the web page browsing page
Favour certificate obtains situation;
5th judging unit 9 is used to judge whether user checks that reward voucher obtains details, will current visitor when being judged as YES
Family end searched page or web page browsing page layout switch are that floating layer shows that user preferential certificate obtains details;When being judged as NO, call
6th judging unit 10;
6th judging unit 10 is used to judge whether user places an order, and when being judged as YES, calls transmitting element 4;
The page that the transmitting element 4 is additionally operable to complete to place an order in user obtains situation to the reward voucher that user sends.
4th judging unit 8 is additionally operable to when user enters the client-side search page or the web page browsing page, is judged
Whether user's activity, when being judged as NO, show preferential in active client searched page or the web page browsing page
Activity is reminded;
7th judging unit 11 is used to judge whether user checks that details are reminded in preferential activity, when being judged as YES,
It is that floating layer shows that details are reminded in preferential activity by active client searched page or web page browsing page layout switch;
8th judging unit 12 is used to judge whether user clicks on activity, when being judged as YES, reward voucher number
Amount after the order of this activity accumulate, continue to call the 7th judging unit 11;When being judged as NO, continue
Call the 6th judging unit 10;
6th judging unit 10 is additionally operable to judge whether user places an order, and when being judged as YES, continues to judge that user is
It is no to have been participating in activity, when judging that user does not participate in activity, show that preferential activity is reminded in the page that user completes to place an order,
Continue to judge whether user clicks on activity, when being judged as YES, reward voucher quantity is accumulated since this order, calls hair
Send unit 4;When judging that user has been participating in activity, continue to call transmitting element 4;
It is described to call the page that transmitting element 4 is additionally operable to complete to place an order in user to send new reward voucher acquisition feelings to user
Condition.
Although the foregoing describing the embodiment of the present invention, it will be appreciated by those of skill in the art that these
It is merely illustrative of, protection scope of the present invention is defined by the appended claims.Those skilled in the art is not carrying on the back
On the premise of principle and essence from the present invention, various changes or modifications can be made to these embodiments, but these are changed
Protection scope of the present invention is each fallen within modification.
Claims (10)
1. a kind of marketing method based on user's portrait, it is characterised in that the marketing method includes:
S1, user data is obtained, the user data includes user's representation data;
S2, by decision Tree algorithms or XGBoost algorithms the user data is handled, establish single probabilistic forecasting under user
Model;
S3, lower single probability according to single Probabilistic Prediction Model prediction user under the user;
S4, the market content according to corresponding to lower single probability to user's transmission of the user.
2. the marketing method as claimed in claim 1 based on user's portrait, it is characterised in that also include before step S2:
Judge whether user installs competing product and be to be lost in user or any active ues, judging that user do not install competing product and be to flow
During appraxia family, or judge the competing product of user installation and be lost in user when, according to the decision Tree algorithms to the user data
Handled, establish single Probabilistic Prediction Model under offline user;
Judging the competing product of user installation and when being any active ues, according to the XGBoost algorithms to the user data at
Reason, establish on line single Probabilistic Prediction Model under user.
3. the marketing method as claimed in claim 2 based on user's portrait, it is characterised in that also include before step S2:
Judging that user do not install competing product and when being any active ues, judging whether user is ox user, judging that user is not
During ox user, continue to judge whether user is high frequency user, when being judged as NO, send ladder and purchase certificate again to user;
The ladder purchases certificate and characterizes that number is more when user purchases again again, the more preferential situation of the coupon discount of acquisition.
4. the marketing method as claimed in claim 1 based on user's portrait, it is characterised in that step S4 is specifically included:
Judge whether lower single probability of the user is less than given threshold, when being judged as YES, send market content to the use
Family;
The market content includes sending reward voucher, sends at least one of advertising campaign information and service guarantee.
5. the marketing method as claimed in claim 2 based on user's portrait, it is characterised in that establish the offline user and place an order
The user data of Probabilistic Prediction Model browses data, user's history order data and user's representation data including user's history
At least one of;
User's representation data, which includes user, to be believed the sensitivity information of reward voucher, user preference information, customer consumption ability
At least one of liveness information of breath, the generous degree information of user, user's value information and user;
The user data for establishing single Probabilistic Prediction Model under user on the line browses data, institute including the user's history
State user's history order data, user's representation data, user's displaying live view data, user's real time orders data, user enter
Firmly hotel's historical data, user move in hotel's real time data, tripartite and competing product real time data and user's order train ticket or air ticket
At least one of real time data;
The user, which moves in hotel's historical data, includes hotel's historical sales data, hotel's grade historical data and hotel's history
At least one of Housing Price data;
It is real-time including hotel's real-time sale amount data, hotel's grade real time data and hotel that the user moves in hotel's real time data
At least one of Housing Price data.
6. a kind of marketing system based on user's portrait, it is characterised in that the marketing system includes acquiring unit, processing list
Member, predicting unit and transmitting element;
The acquiring unit is used to obtain user data, and the user data includes user's representation data;
The processing unit is used to handle the user data by decision Tree algorithms or XGBoost algorithms, establishes and uses
Single Probabilistic Prediction Model under family;
The predicting unit is used for lower single probability that user is predicted according to single Probabilistic Prediction Model under the user;
The transmitting element is used for the market content according to corresponding to lower single probability to user's transmission of the user.
7. the marketing system as claimed in claim 6 based on user's portrait, it is characterised in that the marketing system also includes the
One judging unit;
First judging unit is used to judging whether user to install competing product and be to be lost in user or any active ues, is judging
User do not install competing product and be lost in user when, or judge the competing product of user installation and be loss user when, call the processing
Unit;
The processing unit is used to handle the user data according to the decision Tree algorithms, establishes offline user and places an order
Probabilistic Prediction Model;
First judging unit is judging the competing product of user installation and when being any active ues, is continuing to call the processing unit;
The processing unit is additionally operable to handle the user data according to the XGBoost algorithms, establishes user on line
Lower single Probabilistic Prediction Model.
8. the marketing system as claimed in claim 7 based on user's portrait, it is characterised in that the marketing system also includes the
Two judging units;
Second judging unit is used to judge that user do not install competing product and when being any active ues, judges whether user is ox
User, when it is not ox user to judge user, continue to judge whether user is high frequency user, when being judged as NO, call institute
State transmitting element;
The transmitting element is additionally operable to transmission ladder and purchases certificate again to user;
The ladder purchases certificate and characterizes that number is more when user purchases again again, the more preferential situation of the coupon discount of acquisition.
9. the marketing system as claimed in claim 6 based on user's portrait, it is characterised in that the marketing system also includes the
Three judging units;
3rd judging unit is used to judge whether lower single probability of the user is less than given threshold, when being judged as YES,
Market content is sent to the user;
The market content includes sending reward voucher, sends at least one of advertising campaign information and service guarantee.
10. the marketing system as claimed in claim 7 based on user's portrait, it is characterised in that establish under the offline user
The user data of single Probabilistic Prediction Model browses data, user's history order data and the user including user's history and drawn
As at least one of data;
User's representation data, which includes user, to be believed the sensitivity information of reward voucher, user preference information, customer consumption ability
At least one of liveness information of breath, the generous stingy degree information of user, user's value information and user;
The user data for establishing single Probabilistic Prediction Model under user on the line browses data, institute including the user's history
State user's history order data, user's representation data, user's displaying live view data, user's real time orders data, user enter
Firmly hotel's historical data, user move in hotel's real time data, tripartite and competing product real time data and user's order train ticket or air ticket
At least one of real time data;
The user, which moves in hotel's historical data, includes hotel's historical sales data, hotel's grade historical data and hotel's history
At least one of Housing Price data;
It is real-time including hotel's real-time sale amount data, hotel's grade real time data and hotel that the user moves in hotel's real time data
At least one of Housing Price data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710833409.5A CN107507042A (en) | 2017-09-15 | 2017-09-15 | Marketing method and system based on user's portrait |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710833409.5A CN107507042A (en) | 2017-09-15 | 2017-09-15 | Marketing method and system based on user's portrait |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107507042A true CN107507042A (en) | 2017-12-22 |
Family
ID=60697352
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710833409.5A Pending CN107507042A (en) | 2017-09-15 | 2017-09-15 | Marketing method and system based on user's portrait |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107507042A (en) |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108182605A (en) * | 2018-01-11 | 2018-06-19 | 厦门快商通信息技术有限公司 | A kind of user's behavior prediction method and system based on user's portrait |
CN108200082A (en) * | 2018-01-25 | 2018-06-22 | 上海携程商务有限公司 | OTA platforms are used to identify that user's malice to brush single method and system |
CN108256981A (en) * | 2018-02-27 | 2018-07-06 | 北京小度信息科技有限公司 | Service recommendation method, device, electronic equipment and computer readable storage medium |
CN108416624A (en) * | 2018-02-27 | 2018-08-17 | 深圳乐信软件技术有限公司 | A kind of discount coupon method for pushing, device, storage medium and intelligent terminal |
CN108805615A (en) * | 2018-05-28 | 2018-11-13 | 广州招点信息科技有限公司 | A kind of preferential movable method for pushing and system based on consumer consumption behavior |
CN109146580A (en) * | 2018-09-30 | 2019-01-04 | 青岛大学 | A kind of O2O coupon distribution method and system based on big data analysis |
CN109493113A (en) * | 2018-09-29 | 2019-03-19 | 口碑(上海)信息技术有限公司 | A kind of providing method and device of favor information |
CN109583932A (en) * | 2018-09-29 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and electronic equipment of generation activity crowd |
CN109670871A (en) * | 2018-12-22 | 2019-04-23 | 拉扎斯网络科技(上海)有限公司 | Recall method and device, electronic equipment and storage medium |
CN109740072A (en) * | 2018-12-29 | 2019-05-10 | 携程计算机技术(上海)有限公司 | Hotel's sort method and system under OTA platform based on POI |
CN109829592A (en) * | 2019-03-07 | 2019-05-31 | 深圳市丰巢科技有限公司 | A kind of attrition prediction method, apparatus, equipment and the storage medium of express delivery cabinet user |
CN110135900A (en) * | 2019-05-09 | 2019-08-16 | 达疆网络科技(上海)有限公司 | A kind of real-time discount coupon distribution method based on user behavior |
CN110335106A (en) * | 2019-05-28 | 2019-10-15 | 成都美美臣科技有限公司 | A method of increasing conversion in e-commerce website and sale is urgent |
CN110766431A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for judging whether user is sensitive to coupon |
CN110766507A (en) * | 2019-02-25 | 2020-02-07 | 北京嘀嘀无限科技发展有限公司 | Resource allocation method and device |
CN111080338A (en) * | 2019-11-11 | 2020-04-28 | 中国建设银行股份有限公司 | User data processing method and device, electronic equipment and storage medium |
CN111144935A (en) * | 2019-12-17 | 2020-05-12 | 武汉海云健康科技股份有限公司 | Big data-based sleep member awakening method and system, server and medium |
CN111242661A (en) * | 2018-11-29 | 2020-06-05 | 北京京东尚科信息技术有限公司 | Coupon issuing method and device, computer system and medium |
CN111415199A (en) * | 2020-03-20 | 2020-07-14 | 重庆锐云科技有限公司 | Customer prediction updating method and device based on big data and storage medium |
CN111831892A (en) * | 2019-04-19 | 2020-10-27 | 拉扎斯网络科技(上海)有限公司 | Information recommendation method, information recommendation device, server and storage medium |
CN112801597A (en) * | 2021-03-29 | 2021-05-14 | 北京每日优鲜电子商务有限公司 | Method, device, electronic equipment and medium for processing article inventory |
CN112991110A (en) * | 2021-04-25 | 2021-06-18 | 湖南知名未来科技有限公司 | Multi-dimensional portrait standard client type identification method and intellectual property monitoring system |
CN113344635A (en) * | 2021-06-24 | 2021-09-03 | 深圳市小摩豆网络科技有限公司 | Customer consumption behavior habit management and analysis method |
CN113570419A (en) * | 2021-08-30 | 2021-10-29 | 上海通联金融服务有限公司 | Method for sending red packet by combining standard model, storage medium and terminal |
CN113743721A (en) * | 2021-07-29 | 2021-12-03 | 深圳市东信时代信息技术有限公司 | Marketing strategy generation method and device, computer equipment and storage medium |
CN113763112A (en) * | 2021-02-25 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information pushing method and device |
CN113793180A (en) * | 2021-09-15 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | User preference analysis method, device, equipment and computer storage medium |
CN114549066A (en) * | 2022-02-15 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing mode determining method and device and computer storage medium |
CN114549071A (en) * | 2022-02-18 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing strategy determination method and device, computer equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106203746A (en) * | 2016-09-30 | 2016-12-07 | 携程计算机技术(上海)有限公司 | Hotel group divides and the method for requirement forecasting |
CN106204063A (en) * | 2016-06-30 | 2016-12-07 | 北京奇艺世纪科技有限公司 | A kind of paying customer's method for digging and device |
CN106296278A (en) * | 2016-08-04 | 2017-01-04 | 上海携程商务有限公司 | Reward voucher distribution method and system |
CN106846041A (en) * | 2016-12-26 | 2017-06-13 | 携程计算机技术(上海)有限公司 | The distribution method and system of reward voucher |
-
2017
- 2017-09-15 CN CN201710833409.5A patent/CN107507042A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106204063A (en) * | 2016-06-30 | 2016-12-07 | 北京奇艺世纪科技有限公司 | A kind of paying customer's method for digging and device |
CN106296278A (en) * | 2016-08-04 | 2017-01-04 | 上海携程商务有限公司 | Reward voucher distribution method and system |
CN106203746A (en) * | 2016-09-30 | 2016-12-07 | 携程计算机技术(上海)有限公司 | Hotel group divides and the method for requirement forecasting |
CN106846041A (en) * | 2016-12-26 | 2017-06-13 | 携程计算机技术(上海)有限公司 | The distribution method and system of reward voucher |
Cited By (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108182605A (en) * | 2018-01-11 | 2018-06-19 | 厦门快商通信息技术有限公司 | A kind of user's behavior prediction method and system based on user's portrait |
CN108200082B (en) * | 2018-01-25 | 2021-03-26 | 上海携程商务有限公司 | Method and system for identifying malicious user billing of OTA platform |
CN108200082A (en) * | 2018-01-25 | 2018-06-22 | 上海携程商务有限公司 | OTA platforms are used to identify that user's malice to brush single method and system |
CN108256981A (en) * | 2018-02-27 | 2018-07-06 | 北京小度信息科技有限公司 | Service recommendation method, device, electronic equipment and computer readable storage medium |
CN108416624A (en) * | 2018-02-27 | 2018-08-17 | 深圳乐信软件技术有限公司 | A kind of discount coupon method for pushing, device, storage medium and intelligent terminal |
CN108256981B (en) * | 2018-02-27 | 2021-01-01 | 北京小度信息科技有限公司 | Service recommendation method and device, electronic equipment and computer-readable storage medium |
CN108805615A (en) * | 2018-05-28 | 2018-11-13 | 广州招点信息科技有限公司 | A kind of preferential movable method for pushing and system based on consumer consumption behavior |
CN108805615B (en) * | 2018-05-28 | 2021-09-10 | 广州招点信息科技有限公司 | Preferential activity pushing method and system based on user consumption behaviors |
CN110766431A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Method and device for judging whether user is sensitive to coupon |
CN109583932A (en) * | 2018-09-29 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and electronic equipment of generation activity crowd |
CN109493113A (en) * | 2018-09-29 | 2019-03-19 | 口碑(上海)信息技术有限公司 | A kind of providing method and device of favor information |
CN109146580A (en) * | 2018-09-30 | 2019-01-04 | 青岛大学 | A kind of O2O coupon distribution method and system based on big data analysis |
CN111242661A (en) * | 2018-11-29 | 2020-06-05 | 北京京东尚科信息技术有限公司 | Coupon issuing method and device, computer system and medium |
CN109670871A (en) * | 2018-12-22 | 2019-04-23 | 拉扎斯网络科技(上海)有限公司 | Recall method and device, electronic equipment and storage medium |
CN109740072A (en) * | 2018-12-29 | 2019-05-10 | 携程计算机技术(上海)有限公司 | Hotel's sort method and system under OTA platform based on POI |
CN110766507A (en) * | 2019-02-25 | 2020-02-07 | 北京嘀嘀无限科技发展有限公司 | Resource allocation method and device |
CN109829592A (en) * | 2019-03-07 | 2019-05-31 | 深圳市丰巢科技有限公司 | A kind of attrition prediction method, apparatus, equipment and the storage medium of express delivery cabinet user |
CN109829592B (en) * | 2019-03-07 | 2023-03-21 | 深圳市丰巢科技有限公司 | Loss prediction method, device, equipment and storage medium for express cabinet users |
CN111831892A (en) * | 2019-04-19 | 2020-10-27 | 拉扎斯网络科技(上海)有限公司 | Information recommendation method, information recommendation device, server and storage medium |
CN110135900A (en) * | 2019-05-09 | 2019-08-16 | 达疆网络科技(上海)有限公司 | A kind of real-time discount coupon distribution method based on user behavior |
CN110335106A (en) * | 2019-05-28 | 2019-10-15 | 成都美美臣科技有限公司 | A method of increasing conversion in e-commerce website and sale is urgent |
CN111080338A (en) * | 2019-11-11 | 2020-04-28 | 中国建设银行股份有限公司 | User data processing method and device, electronic equipment and storage medium |
CN111080338B (en) * | 2019-11-11 | 2024-05-24 | 建信金融科技有限责任公司 | User data processing method and device, electronic equipment and storage medium |
CN111144935A (en) * | 2019-12-17 | 2020-05-12 | 武汉海云健康科技股份有限公司 | Big data-based sleep member awakening method and system, server and medium |
CN111415199A (en) * | 2020-03-20 | 2020-07-14 | 重庆锐云科技有限公司 | Customer prediction updating method and device based on big data and storage medium |
CN113763112A (en) * | 2021-02-25 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Information pushing method and device |
CN112801597A (en) * | 2021-03-29 | 2021-05-14 | 北京每日优鲜电子商务有限公司 | Method, device, electronic equipment and medium for processing article inventory |
CN112991110A (en) * | 2021-04-25 | 2021-06-18 | 湖南知名未来科技有限公司 | Multi-dimensional portrait standard client type identification method and intellectual property monitoring system |
CN112991110B (en) * | 2021-04-25 | 2024-02-02 | 湖南知名未来科技有限公司 | Customer type identification method of multi-dimensional portrait standard and intellectual property monitoring system |
CN113344635A (en) * | 2021-06-24 | 2021-09-03 | 深圳市小摩豆网络科技有限公司 | Customer consumption behavior habit management and analysis method |
CN113743721A (en) * | 2021-07-29 | 2021-12-03 | 深圳市东信时代信息技术有限公司 | Marketing strategy generation method and device, computer equipment and storage medium |
CN113570419A (en) * | 2021-08-30 | 2021-10-29 | 上海通联金融服务有限公司 | Method for sending red packet by combining standard model, storage medium and terminal |
CN113793180A (en) * | 2021-09-15 | 2021-12-14 | 北京沃东天骏信息技术有限公司 | User preference analysis method, device, equipment and computer storage medium |
CN114549066A (en) * | 2022-02-15 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing mode determining method and device and computer storage medium |
CN114549071A (en) * | 2022-02-18 | 2022-05-27 | 上海钧正网络科技有限公司 | Marketing strategy determination method and device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107507042A (en) | Marketing method and system based on user's portrait | |
US20200258096A1 (en) | Online serving threshold and delivery policy adjustment | |
US10939233B2 (en) | System and method for real-time prediction of mobile device locations | |
EP3371762B1 (en) | Systems and methods for performance driven dynamic geo-fence based targeting | |
US11093950B2 (en) | Customer activity score | |
CN102870133A (en) | Bid landscape tool | |
CN106997549A (en) | The method for pushing and system of a kind of advertising message | |
KR20150035754A (en) | Modifying targeting criteria for an advertising campaign based on advertising campaign budget | |
US20130151331A1 (en) | System and methods thereof for an adaptive learning of advertisements behavior and providing a recommendation respective thereof | |
CN110991875A (en) | Platform user quality evaluation system | |
CN107067274A (en) | One DSP real time bid ad system based on blended learning model | |
US11386454B1 (en) | Systems, methods, and devices for optimizing advertisement placement | |
CN113256345B (en) | Self-defining method and device of advertisement putting strategy and computer equipment | |
CN105528377A (en) | A processing method, device and system for search results | |
CN103177129A (en) | Internet real-time information recommendation and prediction system | |
US11720917B2 (en) | Methods, systems, and media for managing online advertising campaigns based on causal conversion metrics | |
WO2020151471A1 (en) | Offline store operation control method, system and device, and storage medium | |
CN115936782A (en) | Advertisement putting effect estimation method and device, electronic equipment and storage medium | |
US20140229282A1 (en) | Use of natural query events to improve online advertising campaigns | |
US10402853B1 (en) | Methods, systems, and media for managing online advertising campaigns based on causal conversion metrics | |
KR20110067584A (en) | Method, system and computer-readable recording medium for providing advertisement metric information together with advertisement content | |
CN111340265A (en) | Off-line intervention method and device for driver, electronic equipment and computer storage medium | |
US20130275206A1 (en) | Per colo distribution in online advertising | |
CN110135899A (en) | A kind of differentiation discount coupon distribution method based on user's access-hours | |
CN112561589B (en) | Advertisement delivery method, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171222 |