CN108460629A - User, which markets, recommends method, apparatus, terminal device and storage medium - Google Patents
User, which markets, recommends method, apparatus, terminal device and storage medium Download PDFInfo
- Publication number
- CN108460629A CN108460629A CN201810138039.8A CN201810138039A CN108460629A CN 108460629 A CN108460629 A CN 108460629A CN 201810138039 A CN201810138039 A CN 201810138039A CN 108460629 A CN108460629 A CN 108460629A
- Authority
- CN
- China
- Prior art keywords
- user
- activity
- recommendation
- prize
- target
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
It markets the invention discloses a kind of user and recommends method, apparatus, terminal device and storage medium.User marketing recommendation method, including：The activity for obtaining user participates in information, and participating in information based on the activity generates and sends the first recommendation information, wherein first recommendation information includes the first recommendation activity；Recommend movable feedback information if not receiving user in preset time and participating in any described first, obtains user's portrait；Relevant matches are carried out based on user portrait and existing movable prize, target is obtained and recommends prize；Recommend prize based on the target, generate and send the second recommendation information, wherein second recommendation information includes the second recommendation activity corresponding with target recommendation prize.When recommending using the relevant marketing of user marketing recommendation method progress user, targeted information recommendation can be effectively performed according to user's feature.
Description
Technical field
Recommend method, apparatus, terminal device the present invention relates to field of information processing more particularly to a kind of user marketing and deposits
Storage media.
Background technology
Existing enterprise or platform all can be that existing or potential user sends activity recommendation information, should to attract user to participate in
The activity of enterprise or platform, to pull the growth of business.But existing activity recommendation information does not have specific aim, it is difficult to transfer
The interest of user so that the participation of user is not high, and the validity of activity recommendation information push is not high.
Invention content
A kind of user of offer of the embodiment of the present invention, which markets, recommends method, apparatus, terminal device and storage medium, to solve to live
Move the not high problem of the validity of pushed information.
In a first aspect, the embodiment of the present invention provides a kind of user's marketing recommendation method, including：
The activity for obtaining user participates in information, and participating in information based on the activity generates and sends the first recommendation information,
In, first recommendation information includes the first recommendation activity；
Recommend movable feedback information if not receiving user in preset time and participating in any described first, obtains use
It draws a portrait at family；
Relevant matches are carried out based on user portrait and existing movable prize, target is obtained and recommends prize；
Recommend prize based on the target, generates and sends the second recommendation information, wherein second recommendation information includes
The second recommendation activity corresponding with target recommendation prize.
Second aspect, the embodiment of the present invention provide a kind of user's marketing recommendation apparatus, including：
First generates sending module, and the activity for obtaining user participates in information, and participating in information based on the activity generates
And send the first recommendation information, wherein first recommendation information includes the first recommendation activity；
User's portrait acquisition module, if participating in any first recommendation work for not receiving user in preset time
Dynamic feedback information then obtains user's portrait；
Target recommends prize acquisition module, for carrying out correlation based on user portrait and existing movable prize
Match, obtains target and recommend prize；
Second generates sending module, for based on target recommendation prize, generating and sending the second recommendation information,
In, second recommendation information includes the second recommendation activity corresponding with target recommendation prize.
The third aspect, the embodiment of the present invention provide a kind of terminal device, including memory, processor and are stored in described
In memory and the computer program that can run on the processor, the processor are realized when executing the computer program
The step of user's marketing recommendation method.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, the computer-readable storage medium
Matter is stored with computer program, and the computer program realizes the step of user's marketing recommendation method when being executed by processor
Suddenly.
The user that the embodiment of the present invention is provided, which markets, to be recommended in method, apparatus, terminal device and storage medium, is obtained and is used
The activity at family participates in information, and participating in information based on activity generates and sends the first recommendation information, and movable history is participated in from user
This dimension of record information sets out, and generates and participates in the first closely related recommendation information of activity condition with user, first recommendation
Information can preferably reflect that user participates in movable hobby, market for user and recommend to provide important references, can realize more preferable
, more targeted user markets and recommends.If it is movable not receive any first recommendation of user's participation in preset time
Feedback information then obtains user's portrait, and user draws a portrait can reflect the behavioural habits and hobby of user on the whole, pass through
User's portrait can carry out more reasonable, more targeted marketing to user to be recommended.Based on user's portrait and existing movable prize
Carry out relevant matches, obtain target recommend prize, based on target recommend prize, generate and send the second recommendation information, with
Family portrait is reference basis, by the relevant matches of user's portrait and existing movable prize, is needed from this user of movable prize
The dimension asked is set out, and matching obtains target and recommends prize, prize can be recommended to attract more users according to the target, realized high
Effect, accurate user, which market, to be recommended.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is a flow chart of user's marketing recommendation method in the embodiment of the present invention 1.
Fig. 2 is a particular flow sheet of step S10 in Fig. 1.
Fig. 3 is a particular flow sheet of step S30 in Fig. 1.
Fig. 4 is a particular flow sheet of step S31 in Fig. 3.
Fig. 5 is a particular flow sheet of step S32 in Fig. 3.
Fig. 6 is the particular flow sheet after step S40 in Fig. 1.
Fig. 7 is a functional block diagram of user's marketing recommendation apparatus in the embodiment of the present invention 2.
Fig. 8 is a schematic diagram of terminal device in the embodiment of the present invention 4.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained without creative efforts
Example, shall fall within the protection scope of the present invention.
Embodiment 1
Fig. 1 shows a flow chart of user's marketing recommendation method in the present embodiment.User marketing recommendation method can be applied
In the terminal device that the financial institutions such as common carrier, bank and insurance or other mechanisms configure, for carrying out user's marketing
Recommend, specifically can be applicable in the user's marketing commending system of installation on the terminal device.The user market commending system refer to
For carrying out the system that specific aim marketing is recommended to user.Wherein, which is that can carry out setting for human-computer interaction with user
It is standby, including but not limited to equipment such as computer, smart mobile phone and tablet.As shown in Figure 1, the user markets, recommendation method includes as follows
Step：
S10：The activity for obtaining user participates in information, and participating in information based on activity generates and sends the first recommendation information,
In, the first recommendation information includes the first recommendation activity.
Wherein, activity participates in the history information that information refers to user's activity, all activities that user participated in
It will preserve and record, for subsequently targetedly being analyzed according to the history information of user's activity, make
Go out and more rationally, reliably recommends.First recommendation information is to participate in information according to the activity of user, and specific aim recommendation is carried out for user
Information.
In the present embodiment, the history information (i.e. activity participates in information) of user's activity, the historical record are obtained
Information includes all activities participated in of user.Specifically, by taking common carrier as an example, for example, user participated in each
100 integrals can be got by dialing the moon full 500 minutes, which can be used in exchanging the purposes such as telephone expenses or prize；Each moon is spent
Expense flow reaches 1G and send 200M flows at once；1 year total telephone recharge is expired 1000 yuan of country for giving one month and is answered for 200 minutes
The free universal flow being free of charge with 1G.Above-mentioned activity is carried out as unit of Month And Year, it is possible to understand that ground is with week, day
The activity of unit too is covered by activity and participates in information, and activity periodically short to a certain extent is better able to adjust
The enthusiasm and enhancing client's viscosity for employing family, can allow user to be obtained from activity and participate in movable reward, make in a short time
User participate in it is movable during can obtain satisfaction and there is sense, realize and having of making of user targetedly sought
Pin is recommended.For example, official's application program in a certain common carrier gets the activity of integral equipped with registering daily, register continuous
Man Yizhou rewards dual-integration rewards the activities such as random novelties in full one month；Weekly with family number (such as 551,552 and 553
Family number) full 5 times or more the universal flows for giving a month 100M of member's call.
In the present embodiment, user's marketing commending system obtains input by user first and recommends active instruction, according to the instruction
Calling storage, the movable of user participates in information in the database, and participating in information according to activity generates and sends the first recommendation information,
First recommendation information may include multiple first recommendation activities.Information, which is participated in, based on activity generates and sends the first recommendation
Breath participates in movable this dimension of history information from user, generates and participate in movable history information with user
The first closely related recommendation information, first recommendation information can preferably reflect that user participates in movable hobby, be user
Marketing is recommended to provide important references, realizes that better, more targeted user markets and recommends.
In a specific embodiment, as shown in Fig. 2, in step S10, the activity for obtaining user participates in information, based on work
The dynamic information that participates in generates and sends the first recommendation information, specifically comprises the following steps：
S11：The activity for obtaining user participates in information, and the corresponding Activity Type of acquisition of information is participated in based on activity.
In the present embodiment, user's marketing commending system obtains input by user first and recommends active instruction, according to the instruction
Calling storage, the movable of user participates in information in the database, which participates in the historical record letter of information, that is, user's activity
Breath can understand user's movable participation corresponding to various activities type according to the history information, and then determine user
More interested Activity Type.Specifically, the participation that information can be participated in by activity determines the activity (packet of user preferences
Include activity description, manner and activity reward).The height of participation can participate in movable number and frequency by user
Calculations such as (such as one day several times, and one month several times) are configured.
User market commending system call and obtain storage in the database user activity participate in information after, will execute
The operations such as amount of activity setting, classification and statistics.For example, when user monthly register number be 5 times, weekly with family member
Call is 5 times full, when dialing completely 500 yuan of full 200 minutes and 1 year total telephone recharges each moon, and amount of activity need to be arranged first,
The amount of activity presets the amount of activity recommended to user, then classifies to each activity, i.e., variety classes
Activity point under different SSs, by amount of activity setting, classification and statistics can refine and differentiation activity, can
Prominent and embodiment activity feature, finally under the corresponding statistical rules of each activity counting user participation activity situation.Such as
The situation of above-mentioned user's participation activity, since Activity Type is fewer, the default amount of activity recommended is set as 1 i.e.
Can, then classify to the activity of different Activity Types, and united to activity according to the corresponding statistical rules of each activity
Meter obtains statistical result.Such as the situation of above-mentioned user's participation activity, it is full can to learn that user is conversed with family member weekly
5 times the Comparison of Gardening Activities for giving a month 100M universal flow is interested, then corresponding activity point can be searched according to the activity
Class table obtains Activity Type corresponding with the activity from activity classification table.Wherein, activity classification table is the note being pre-created
The tables of data of type belonging to the activity of recording, user markets commending system being capable of or phase identical by tables of data acquisition Activity Type
Close activity, to carry out specific aim marketing.
It can it is to be appreciated that giving the 100M universal flows activity in month for full 5 times with family member call weekly
To be classified as { family's class counts class, conversational class }, user's marketing commending system is searched according to the standard of classification in tables of data
The same or similar Activity Type of type (have identical select identical Activity Type), which can reflect user's participation
Movable hobby and user are to the receiving degree of activity description, manner and movable prize, from movable dimension, energy
Enough bases are somebody's turn to do the dimension closely related with user and provide reliable the user reference and reference of marketing recommendation.
S12：Selection activity corresponding with Activity Type, as the first recommendation activity.
Wherein, the first recommendation activity refers to participating in information according to the activity of user, and the work of specific aim recommendation is carried out for user
It is dynamic.It is corresponding by inquiring the determination of activity classification table and activity participation information in user's marketing commending system in the present embodiment
After Activity Type, work corresponding with Activity Type is obtained by preset amount of activity according to the corresponding Activity Type
Dynamic, if for example, preset amount of activity is 2, system will pick out two activities for meeting Activity Type, specifically choose
It is to participate in movable total degree by being selected from high to low according to user's history to select principle.It is opposite with Activity Type by selecting
The activity answered can provide reliable activity recommendation from user to movable dimension.
S13：The first recommendation information is generated based on the first recommendation activity, and sends the first recommendation information.
In the present embodiment, corresponding first recommendation information is generated according to the first recommendation activity of acquisition, and by this first
Recommendation information is sent to the client of user, allows users to receive first closely related with User Activity participation information and pushes away
Recommend information.Wherein, the first recommendation information includes at least one first recommendation activity, i.e. the first recommendation information allows to recommend multiple phases
The activity of pass.By generating and sending the first recommendation information, enables to user to get the first recommendation activity in time, contribute to
Enhance user's stickiness and improves user's satisfaction.
In step S11-S13, by acquisition and the same or similar activity of Activity Type, generated and sent based on the activity
The first recommendation information can provide reliable activity recommendation from the dimension of user's activity, be conducive to enhance user
Stickiness and raising user's satisfaction, so that the specific aim marketing about user is better achieved.
S20：Recommend movable feedback information if not receiving user in preset time and participating in any first, obtains use
It draws a portrait at family.
Wherein, first recommends movable feedback information, that is, user in the first recommendation activity for receiving the first recommendation information
Afterwards, if having the participation movable feedback information of the first recommendation.User's portrait is also known as user role, delineating target as one kind and uses
Family, the effective tool for contacting user's demand and design direction, user's portrait are widely used in each field.
In the present embodiment, if (such as one week or one month, specific setting should be according to the first recommendation activity within a preset period of time
The characteristics of be arranged) be not received by user and participate in any first and recommend movable feedback information, then it is assumed that in movable single dimension
The characteristics of there is no describe user well on degree, should get on the characteristics of describing user from other dimensions, be used with reaching to be directed to
Family is effectively recommended, and therefore, it is necessary to obtain user's portrait.User's portrait is that one kind delineating target user, contact user tells
Seek the effective tool with design direction, can more comprehensively, the characteristics of reflecting user to deeper, based on user the characteristics of can carry
For more, more effective decision references, the user for the more fitting user's feature of making that can be drawn a portrait by user, which markets, to be recommended.
S30：Relevant matches are carried out based on user's portrait and existing movable prize, target is obtained and recommends prize.
Wherein, existing movable prize refers to the existing prize being arranged for various activities.Such as telephone expenses are sent according to charge filling
And flow, according to entity prize (such as daily necessities and the sports goods manners such as registered, share, open an account and registered and give
Equal entities prize), according to a variety of accumulated point exchanging prizes (can be entity prize and virtual prize) etc. of integral setting.Target pushes away
It refers to that the user's marketing that is used to carry out for based on user's portrait and existing movable prize obtain after relevant matches pushes away to recommend prize
The prize recommended.
It, can comprehensively, embody to deep layer according to user's portrait based on user's portrait and existing movable prize in the present embodiment
The characteristics of user and existing movable prize can be accounted for from the dimension of user demand, and the two is carried out correlation
Match, obtains target and recommend prize.Wherein, the related intimate degree of two Variable Factors can be weighed, be embodied to relevant matches,
Here two variables are the user tag that user characteristics are embodied in user's portrait and existing movable prize respectively.It is appreciated that
Ground carries out relevant matches by user's portrait and existing movable product, and can draw a portrait embodied user's feature according to user,
Such as reading is liked by degree, likes degree to movement, likes degree to food, likes degree to telephone expenses and flow
User's feature carries out relevant matches by existing movable prize according to user's feature, obtains the target for being bonded user's feature
Recommend prize, can be obtained and user in conjunction with the dimension (passing through existing movable prize to embody) of user's feature and user demand
The very strong target of feature correlation recommends prize, to encourage user to recommend prize to participate in correlated activation to obtain target, improves
The reliability that user's marketing is recommended, further enhances user's stickiness.
In a specific embodiment, it as shown in figure 3, in step S30, is carried out based on user's portrait and existing movable prize
Relevant matches obtain target and recommend prize, specifically comprise the following steps：
S31：Obtain the weight accounting of user tag in user's portrait, the top n that weight selection accounting sorts from high to low
User tag, as target user's label.
Wherein, user's portrait includes user tag, and user tag is that user is specific on certain dimension in user's portrait
It embodies, such as：Hobby, browsing record and consumer record etc..User tag can intuitively show user in certain dimension
Hobby feature, portray description by being carried out from multiple dimensions to user, can corresponding recommendation be set according to user tag
Mode such as combines the dimension (existing activity prize) of user demand to be analyzed, makes the recommendation side based on user demand dimension
Formula.
In the present embodiment, user's marketing commending system obtains the weight accounting of each user tag in user's portrait, and selects
Preceding N (N refers to more than 0 natural number) a user tag that weighting weight accounting sorts from high to low, as reflection user's main feature
Target user's label.It is to be appreciated that there is a large amount of user tag for portraying user's feature in user's portrait, it is therefore desirable to select
Take representative user tag, particular by weight selection accounting it is high before several user tags represent the main of user
Feature, such as：It is movement (35%), food (20%) and finery that a certain user, which accounts for the former user tag of weight respectively,
(15%), then it is chosen for target user's label of reflection user's main feature.
It should be noted that as movement class user tag be to belong to a major class, under be further divided into basketball, football
With the user tag of the groups such as soldier's pang ball, and the characteristics of the user tag of these groups can further reflect user, therefore,
Subdividable in user tag, the top n that can from high to low sort by weight accounting to the user tag of major class is small
The user tag of class is screened, and obtains more representative user tag, the user tag of qualified group is selected as
Final target user's label.
S32：Relevant matches are carried out based on target user's label and existing movable prize, it is highest existing to obtain correlation
Movable prize recommends prize as target.
In the present embodiment, relevant matches are carried out based on target user's label and existing movable prize, pass through existing activity
Prize carries out relevant matches, obtains the highest existing movable prize of correlation for being bonded user's feature, recommends as target
Prize, by combining the dimension (passing through existing movable prize to embody) of user's feature and user demand, choose correlation highest,
The target that user's feature can most be represented recommends prize, can improve the reliability that user's marketing is recommended, and increases user and is based on the mesh
Mark recommends prize to participate in the target and recommends the corresponding movable probability of prize.
In a specific embodiment, it as shown in figure 4, in step S31, is carried out based on user's portrait and existing movable prize
Relevant matches obtain target and recommend prize, specifically comprise the following steps：
S311：User tag in being drawn a portrait based on user obtains target labels list.
Wherein, target labels list is the data list for recording, preserving user tag, which can carry out visually
Change displaying, for checking；Can also a logic be stored in database, user market commending system call when just obtain the mesh
The data about user tag preserved in mark list of labels.
In the present embodiment, the user tag in being drawn a portrait based on user, acquisition has been pre-created relevant with user tag
User tag is stored in data list, can quickly obtain by target labels list, the target labels list in the form of data
Take with the relevant target labels list of user tag, facilitate user market commending system the target mark is directly invoked by database
Sign list.
S312：From in target labels list obtain user portrait in user tag weight accounting, weight selection accounting from
The top n user tag of high to Low sequence, as target user's label.
In the present embodiment, user market commending system be based on target labels list, from got in the table user portrait in
The weight accounting situation of user tag, and used by the top n that the comparison weight selection accounting of weight size sorts from high to low
Family label, as target user's label.Since the hobby that the weight accounting of user tag can largely embody user is special
Point selects the top n user tag of weight accounting from high to low as target user's label, can be by being subsequently based on the target
User tag and existing movable prize carry out relevant matches to determine that target recommends prize, can cater to the happiness of user well
It is good.
In a specific embodiment, as shown in figure 5, in step S32, based on target user's label and existing movable prize
Relevant matches are carried out, the highest existing movable prize of correlation is obtained, recommends prize as target, specifically include following step
Suddenly：
S321：The correlation of target user's label and existing movable prize, cosine similarity are calculated based on cosine similarity
Calculation formula isWherein, U indicates that the feature vector of target user's label, I indicate existing
The feature vector of movable prize.
In the present embodiment, the feature vector of target user's label is to reflect each existing movable prize of target user's label
User's feature that target user's label reflects is converted into the data that computer can identify by user's feature data characterization.
And the feature vector of existing movable prize is by user demand data characterization, i.e., user demand being converted into computer can know
Other data.Specifically, the matrix that can be tieed up by initializing a 1*n, sets all elements in matrix to when initial
0, obtain following row vector：[0,0,0,0,0,0 ..., 0], wherein a shared n 0.Such as：Target user's label
In carry the label of basketball, and basketball then changes the 0 of corresponding position when corresponding position is the 3rd in the initialization matrix
It is 1, i.e., matrix is expressed as [0,0,1,0,0,0 ..., 0].Correspondingly, a 1*n is also initialized to existing movable prize
The matrix of dimension, and pre-set corresponding coefficient of relationship γ, such as with the relevant existing movable prize of basketball can there are many,
When such as existing movable prize being basketball, setting coefficient of relationship γ is 0.8, and when such as existing movable prize is ankle guard, relationship system is arranged
Number γ is 0.3, and when such as existing movable prize is dumbbell, setting coefficient of relationship γ is 0.1.In each existing movable prize in matrix
Upper corresponding position replaces the 0 of initialization with coefficient of relationship γ, and if basketball is 1 in the corresponding position of matrix, ankle guard is in matrix
Corresponding position is 4, and dumbbell is 6 in the corresponding position of matrix, then the corresponding matrix of existing movable prize be [0.8,0,0,0.3,
0,0.1 ..., 0], coefficient of relationship γ can reflect have movable prize and target user's label (here with basketball
Proportion degree), can more reasonably embody the proportion relationship of existing movable prize and target user's label, be conducive to improve
The accuracy and reliability of correlativity calculation result.By target user's label and existing movable prize with feature vector (feature
Matrix) indicate after, be based on cosine similarityCalculate target user's label and existing activity prize
The correlation of product, the feature vector of feature vector and existing movable prize by creating target user's label, is based on cosine phase
The correlation that target user's label and existing movable prize are calculated and obtained like degree pushes away subsequently to obtain target based on the correlation
It recommends prize and provides effective decision judgement, the user's marketing for being advantageously implemented fitting user's actual features is recommended.
S322：The highest existing movable prize of correlation is obtained, recommends prize as target.
In the present embodiment, according to the correlation of the step S321 target user's labels obtained and existing movable prize, by this
The highest existing movable prize of correlation recommends prize as target, can be from the dimension knot of user demand (existing activity prize)
User's feature that target user's label embodies is closed, more objective, properer target is obtained and recommends prize.
S40：Recommend prize based on target, generate and send the second recommendation information, wherein the second recommendation information includes and mesh
Mark recommends the corresponding second recommendation activity of prize.
Wherein, the second recommendation information carries out specific aim recommendation i.e. according to user's portrait and existing movable prize for user
Information.Second recommendation information includes the second recommendation activity corresponding with target recommendation prize, that is, passes through and participate in the second recommendation
Activity can obtain target and recommend prize.In the present embodiment, recommends prize to generate corresponding second according to the target of acquisition and push away
Information is recommended, and second recommendation information is sent to the client of user, allows users to receive and user's portrait and user
The second closely related recommendation information of demand, enables to user to get the second recommendation activity in time, improves user's participation
Movable participation.
In a specific embodiment, as shown in fig. 6, after the step s 40, i.e., recommending prize based on target, generating
And after the step of sending the second recommendation information, user marketing recommendation method further includes following steps：
S41：Recommend movable feedback information if not receiving user in preset time and participating in any second, based on use
Family is drawn a portrait and existing activity carries out relevant matches, obtains goal activities.
In the present embodiment, if not receiving the feedback information of the second recommendation information in preset time, then it is assumed that for portion
The user point not fed back the characteristics of can't embody user well in user demand this dimension, in movable selection also
It is not reasonable, therefore, user's portrait can be based on and existing activity carries out relevant matches, obtain goal activities.The correlation
Matching is similar to step S321 steps, please refers to step S321, details are not described herein.It is carried out by user's portrait and existing activity
Relevant matches obtain goal activities, and embodied user's feature of drawing a portrait in conjunction with user is formulated for different users and more sticked on
It cuts, rational activity recommendation.
S42：Recommend prize based on goal activities and target, generates and sends third recommendation information.
In the present embodiment, after step S41 obtains goal activities, it is to draw a portrait to obtain based on user to recommend prize due to target
, it is to have important reference value, therefore when selecting prize type (i.e. the dimension of user demand), combining target is answered to recommend
Prize generates third recommendation information together, which is drawn a portrait according to user and existing activity, and combining target
Recommend prize, the action message of specific aim recommendation is carried out for user.The visitor of user will be sent to after generation third recommendation information
Family end allows users to receive the third recommendation information closely related with user's portrait and user demand.It is drawn a portrait by user
Relevant matches are carried out with existing activity, goal activities is obtained and combining target recommends prize to be represented in user demand dimension
Important references, user can be reduced because existing activity is chosen improper, lead to be reluctant the situation for participating in third recommendation activity
Occur, user can be made energetically to participate in third recommendation activity, and obtains and prize is recommended according to the target that user's feature obtains.
It should be noted that the user markets, recommendation method is suitble to be used for the scene recommended of marketing with all, is such as reading
The favorite reading matter of platform recommended user, the commodity liked in shopping platform recommended user and relevant various recommendation activities.This reality
It applies example and has only lifted one such user and marketed and recommend situation, should not market the user reality for recommending situation as this method
Apply range.
The user that the present embodiment is provided markets in recommendation method, and the activity for obtaining user participates in information, based on activity ginseng
Generate and send the first recommendation information with information, movable this dimension of history information participated in from user, generate with
User participates in the first closely related recommendation information of activity condition, which can reflect that user participates in movable happiness
Good and user can be according to this from movable dimension to the receiving degree of activity description, manner and movable prize
Reliable user is provided and is marketed with the closely related dimension of user and recommends to use for reference and reference, help to realize preferably, more have needle
It markets and recommends to the user of property.Recommend movable feedback information if not receiving user in preset time and participating in any first,
User's portrait is then obtained, user draws a portrait can reflect the behavioural habits and hobby of user on the whole, draw a portrait based on user
More reliable decision references are capable of providing, the user for the more fitting user's feature of making that can draw a portrait by user, which markets, to be recommended.Base
Relevant matches are carried out in user's portrait and existing movable prize, target is obtained and recommends prize, prize is recommended based on target, is generated
And the second recommendation information is sent, using user's portrait as reference basis, by creating target user's label and existing movable prize
Feature vector is calculated and is obtained based on cosine similarity the correlation of target user's label and existing movable prize, is follow-up base
Obtaining target in the correlation recommends prize to provide effective decision judgement, is advantageously implemented efficient, accurate user's marketing
Recommend.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment 2
Fig. 7 shows the principle frame with the one-to-one user's marketing recommendation apparatus of user's marketing recommendation method in embodiment 1
Figure.As shown in fig. 7, the user markets, recommendation apparatus includes the first generation sending module 10, user's portrait acquisition module 20, target
Prize acquisition module 30 and second is recommended to generate sending module 40.Wherein, first sending module 10, user's portrait acquisition mould are generated
User markets in block 20, the realization function of target recommendation prize acquisition module 30 and the second generation sending module 40 and embodiment 1
The corresponding step of recommendation method corresponds, and to avoid repeating, the present embodiment is not described in detail one by one.
First generates sending module 10, and the activity for obtaining user participates in information, and participating in information based on activity generates simultaneously
Send the first recommendation information, wherein the first recommendation information includes the first recommendation activity.
User's portrait acquisition module 20, if participating in any first recommendation activity for not receiving user in preset time
Feedback information, then obtain user portrait.
Target recommends prize acquisition module 30, for carrying out relevant matches based on user's portrait and existing movable prize,
It obtains target and recommends prize.
Second generates sending module 40, for recommending prize based on target, generates and sends the second recommendation information, wherein
Second recommendation information includes the second recommendation activity corresponding with target recommendation prize.
Preferably, the first generation sending module 10 includes Activity Type acquiring unit 11, the first recommendation activity acquiring unit
12 and first generate transmission unit 13.
Activity Type acquiring unit 11, the activity for obtaining user participate in information, acquisition of information pair are participated in based on activity
The Activity Type answered.
First recommendation activity acquiring unit 12 recommends to live for selecting activity corresponding with Activity Type as first
It is dynamic.
First generates transmission unit 13, for generating the first recommendation information based on the first recommendation activity, and sends first and pushes away
Recommend information.
Preferably, it includes that target user's label acquiring unit 31 and target recommend prize that target, which recommends prize acquisition module 30,
Unit 32.
Target user's label acquiring unit 31, the weight accounting for obtaining user tag in user's portrait, weight selection
The top n user tag that accounting sorts from high to low, as target user's label.
Target recommends prize unit 32, for carrying out relevant matches based on target user's label and existing movable prize,
The highest existing movable prize of correlation is obtained, recommends prize as target.
Preferably, target user's label acquiring unit 31 includes that target labels list obtains subelement 311 and target user
Label obtains subelement 312.
Target labels list obtains subelement 311, for the user tag in drawing a portrait based on user, obtains target labels row
Table.
Target user's label obtains subelement 312, for the user tag from acquisition user portrait in target labels list
Weight accounting, the top n user tag that weight selection accounting sorts from high to low, as target user's label.
Preferably, it includes that correlation calculations subelement 321 and target recommend prize to obtain son that target, which recommends prize unit 32,
Unit 322.
Correlation calculations subelement 321, for calculating target user's label and existing movable prize based on cosine similarity
Correlation, cosine similarity calculation formula isWherein, U indicates target user's label
Feature vector, I indicate the feature vector of existing movable prize.
Target recommends prize to obtain subelement 322, for obtaining the highest existing movable prize of correlation, is pushed away as target
Recommend prize.
Preferably, user marketing recommendation apparatus further includes that third generates sending module 50, which generates sending module
50 include that goal activities acquiring unit 51 and third generate transmission unit 52.
Goal activities acquiring unit 51, if participating in any second recommendation activity for not receiving user in preset time
Feedback information, then be based on user portrait and it is existing activity carry out relevant matches, obtain goal activities.
Third generates transmission unit 52, for recommending prize based on goal activities and target, generates and sends third recommendation
Information.
Embodiment 3
The present embodiment provides a computer readable storage medium, computer journey is stored on the computer readable storage medium
Sequence realizes user's marketing recommendation method in embodiment 1, to avoid repeating, here not when the computer program is executed by processor
It repeats again.Alternatively, when the computer program is executed by processor realize embodiment 2 in user market recommendation apparatus in each module/
The function of unit, to avoid repeating, which is not described herein again.
Embodiment 4
Fig. 8 is the schematic diagram of terminal device in the present embodiment.As shown in figure 8, terminal device 60 includes processor 61, storage
Device 62 and it is stored in the computer program 63 that can be run in memory 62 and on processor 61.Processor 61 executes computer
Each step of user's marketing recommendation method in embodiment 1, such as step S10, S20, S30 shown in FIG. 1 are realized when program 63
And S40.Alternatively, processor 61 realizes in embodiment 2 that user markets recommendation apparatus each module/mono- when executing computer program 63
The function of member, as shown in Figure 7 first, which generates sending module 10, user's portrait acquisition module 20, target, recommends prize acquisition module
30 and second generate sending module 40 function.
Illustratively, computer program 63 can be divided into one or more module/units, one or more mould
Block/unit is stored in memory 62, and is executed by processor 61, to complete the present invention.One or more module/units can
To be the series of computation machine program instruction section that can complete specific function, the instruction segment is for describing computer program 63 at end
Implementation procedure in end equipment 60.For example, computer program 63 can be divided into the first generation sending module in embodiment 2
10, draw a portrait acquisition module 20, target of user recommends prize acquisition module 30 and second to generate sending module 40, each module it is specific
Function is as described in Example 2, to avoid repeating, does not repeat one by one herein.
Terminal device 60 can be the computing devices such as desktop PC, notebook, palm PC and cloud server.Eventually
End equipment may include, but be not limited only to, processor 61, memory 62.It will be understood by those skilled in the art that Fig. 8 is only eventually
The example of end equipment 60 does not constitute the restriction to terminal device 60, may include components more more or fewer than diagram, or
Combine certain components or different components, for example, terminal device can also include input-output equipment, network access equipment,
Bus etc..
Alleged processor 61 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
Memory 62 can be the internal storage unit of terminal device 60, such as the hard disk or memory of terminal device 60.It deposits
Reservoir 62 can also be the plug-in type hard disk being equipped on the External memory equipment of terminal device 60, such as terminal device 60, intelligence
Storage card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card)
Deng.Further, memory 62 can also both include terminal device 60 internal storage unit and also including External memory equipment.It deposits
Reservoir 62 is used to store other programs and the data needed for computer program and terminal device.Memory 62 can be also used for temporarily
When store the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work(
Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion
The all or part of function of description.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can be stored in a computer read/write memory medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
May include：Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic of the computer program code can be carried
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to legislation in jurisdiction and the requirement of patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electric carrier signal and
Telecommunication signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to aforementioned reality
Applying example, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each
Technical solution recorded in embodiment is modified or equivalent replacement of some of the technical features；And these are changed
Or replace, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
- A kind of recommendation method 1. user markets, which is characterized in that including：The activity for obtaining user participates in information, and participating in information based on the activity generates and sends the first recommendation information, wherein institute It includes the first recommendation activity to state the first recommendation information；Recommend movable feedback information if not receiving user in preset time and participating in any described first, obtains user's picture Picture；Relevant matches are carried out based on user portrait and existing movable prize, target is obtained and recommends prize；Recommend prize based on the target, generates and sends the second recommendation information, wherein second recommendation information includes and institute It states target and recommends the corresponding second recommendation activity of prize.
- The recommendation method 2. user according to claim 1 markets, which is characterized in that the activity for obtaining user participates in letter Breath participates in information based on the activity and generates and sends the first recommendation information, including：The activity for obtaining user participates in information, and the corresponding Activity Type of acquisition of information is participated in based on the activity；Selection activity corresponding with the Activity Type, as the first recommendation activity；The first recommendation information is generated based on the first recommendation activity, and sends first recommendation information.
- The recommendation method 3. user according to claim 1 markets, which is characterized in that described based on user portrait and existing There is movable prize to carry out relevant matches, obtains target and recommend prize, including：Obtain the weight accounting of user tag in user's portrait, the top n user that weight selection accounting sorts from high to low Label, as target user's label；Relevant matches are carried out based on target user's label and existing movable prize, obtain the highest existing activity of correlation Prize recommends prize as target.
- The recommendation method 4. user according to claim 3 markets, which is characterized in that user marks in the acquisition user portrait The weight accounting of label, the top n user tag that weight selection accounting sorts from high to low, as target user's label, including：User tag in being drawn a portrait based on the user obtains target labels list；From the weight accounting for obtaining user tag in user portrait in the target labels list, weight selection accounting is from height User tag described in top n to low sequence, as target user's label.
- The recommendation method 5. user according to claim 3 markets, which is characterized in that described to be based on target user's label Relevant matches are carried out with existing movable prize, the highest existing movable prize of correlation is obtained, recommends prize, packet as target It includes：The correlation of target user's label and the existing movable prize is calculated based on cosine similarity, the cosine is similar Spending calculation formula isWherein, U indicates the feature vector of target user's label, I tables Show the feature vector of the existing movable prize；The highest existing movable prize of correlation is obtained, recommends prize as target.
- The recommendation method 6. user according to claim 1 markets, which is characterized in that prize is recommended based on the target described Product, after the step of generating and sending the second recommendation information, user recommendation method of marketing further includes：Recommend movable feedback information if not receiving user in preset time and participating in any described second, is based on the use Family is drawn a portrait and existing activity carries out relevant matches, obtains goal activities；Recommend prize based on the goal activities and the target, generates and sends third recommendation information.
- The recommendation apparatus 7. a kind of user markets, which is characterized in that including：First generates sending module, and the activity participation information for obtaining user participates in information based on the activity and generates concurrently Send the first recommendation information, wherein first recommendation information includes the first recommendation activity；User's portrait acquisition module, if movable for not receiving any first recommendation of user's participation in preset time Feedback information then obtains user's portrait；Target recommends prize acquisition module, for carrying out relevant matches based on user portrait and existing movable prize, obtains Target is taken to recommend prize；Second generates sending module, for recommending prize based on the target, generates and sends the second recommendation information, wherein institute It includes the second recommendation activity corresponding with target recommendation prize to state the second recommendation information.
- The recommendation apparatus 8. user according to claim 7 markets, which is characterized in that it includes activity that the activity, which participates in information, Information is participated in, the first generation sending module includes：Activity Type acquiring unit, the activity for obtaining user participate in information, and participating in acquisition of information based on the activity corresponds to Activity Type；First recommendation activity acquiring unit, for selecting activity corresponding with the Activity Type, as the first recommendation activity；First generates transmission unit, for generating the first recommendation information based on the first recommendation activity, and sends described first Recommendation information.
- 9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 6 when executing the computer program Any one user market recommendation method the step of.
- 10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist In realizing user's marketing recommendation method as described in any one of claim 1 to 6 when the computer program is executed by processor Step.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810138039.8A CN108460629A (en) | 2018-02-10 | 2018-02-10 | User, which markets, recommends method, apparatus, terminal device and storage medium |
| PCT/CN2018/096220 WO2019153655A1 (en) | 2018-02-10 | 2018-07-19 | User marketing recommendation method and apparatus, and terminal device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810138039.8A CN108460629A (en) | 2018-02-10 | 2018-02-10 | User, which markets, recommends method, apparatus, terminal device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108460629A true CN108460629A (en) | 2018-08-28 |
Family
ID=63240057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810138039.8A Pending CN108460629A (en) | 2018-02-10 | 2018-02-10 | User, which markets, recommends method, apparatus, terminal device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN108460629A (en) |
| WO (1) | WO2019153655A1 (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829752A (en) * | 2018-05-25 | 2018-11-16 | 南京邮电大学 | Based on personalized tutor's proposed algorithm |
| CN109245996A (en) * | 2018-09-18 | 2019-01-18 | 平安科技（深圳）有限公司 | Mail push method, device, computer equipment and storage medium |
| CN109785045A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | A kind of method for pushing and device based on user behavior data |
| CN109919650A (en) * | 2019-01-16 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Multi-stage service promotes management method, device and storage medium, computer equipment |
| CN110335079A (en) * | 2019-07-02 | 2019-10-15 | 上海上湖信息技术有限公司 | A kind of intelligent task dispatching method and device collected based on instruction |
| CN110443639A (en) * | 2019-07-16 | 2019-11-12 | 深圳市数位汇聚科技有限公司 | A kind of marketing strategy recommended method and device based on position positioning under line |
| CN110738416A (en) * | 2019-10-15 | 2020-01-31 | 珠海格力电器股份有限公司 | Distribution recommendation system, method, medium, and computing device |
| CN111127077A (en) * | 2019-11-29 | 2020-05-08 | 中国建设银行股份有限公司 | Recommendation method and device based on stream computing |
| CN111159534A (en) * | 2019-12-03 | 2020-05-15 | 泰康保险集团股份有限公司 | User portrait based aid decision making method and device, equipment and medium |
| CN112215664A (en) * | 2020-10-29 | 2021-01-12 | 支付宝(杭州)信息技术有限公司 | Information recommendation method and device |
| CN112650913A (en) * | 2020-12-30 | 2021-04-13 | 福建福诺移动通信技术有限公司 | Counting method and system for coping with big data high concurrency counting scene |
| CN112685598A (en) * | 2019-10-18 | 2021-04-20 | 腾讯科技（深圳）有限公司 | Gift package pushing method and device in live broadcast |
| CN113034241A (en) * | 2021-04-23 | 2021-06-25 | 中国平安人寿保险股份有限公司 | Product information recommendation method and computer equipment |
| CN113065888A (en) * | 2021-03-09 | 2021-07-02 | 北京安锐卓越信息技术股份有限公司 | Method, device and storage medium for recommending business opportunity based on action behavior |
| CN115033798A (en) * | 2022-07-04 | 2022-09-09 | 贵州电网有限责任公司 | Activity recommendation method and system based on big data |
| CN115086701A (en) * | 2022-06-23 | 2022-09-20 | 咪咕动漫有限公司 | Lottery drawing processing method, device and equipment in live broadcast and readable storage medium |
| CN116205679A (en) * | 2023-02-27 | 2023-06-02 | 深圳市秦丝科技有限公司 | Physical store marketing recommendation method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104731830A (en) * | 2013-12-24 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Recommendation method, recommendation device and server |
| CN105049526A (en) * | 2015-08-19 | 2015-11-11 | 网易（杭州）网络有限公司 | Push method, device and system of game gift bag |
| CN105245577A (en) * | 2015-09-11 | 2016-01-13 | 腾讯科技（深圳）有限公司 | Information push method, device and system |
| CN105631538A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | User activity prediction method and device, and application method and system thereof |
| CN106327032A (en) * | 2015-06-15 | 2017-01-11 | 阿里巴巴集团控股有限公司 | Data analysis method used for customer loss early warning and data analysis device thereof |
| CN106815738A (en) * | 2015-12-01 | 2017-06-09 | 中国电信股份有限公司 | A kind of method and apparatus for obtaining user's portrait |
| CN107230136A (en) * | 2017-05-31 | 2017-10-03 | 合肥亿迈杰软件有限公司 | A kind of shopping sequence method for pushing based on big data |
| AU2016347232A1 (en) * | 2015-10-27 | 2018-02-08 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for delivering a message |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107040863B (en) * | 2015-07-30 | 2021-01-15 | 中国移动通信集团内蒙古有限公司 | Real-time service recommendation method and system |
| CN107391603B (en) * | 2017-06-30 | 2020-12-18 | 北京奇虎科技有限公司 | User portrait establishing method and device for mobile terminal |
-
2018
- 2018-02-10 CN CN201810138039.8A patent/CN108460629A/en active Pending
- 2018-07-19 WO PCT/CN2018/096220 patent/WO2019153655A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104731830A (en) * | 2013-12-24 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Recommendation method, recommendation device and server |
| CN106327032A (en) * | 2015-06-15 | 2017-01-11 | 阿里巴巴集团控股有限公司 | Data analysis method used for customer loss early warning and data analysis device thereof |
| CN105049526A (en) * | 2015-08-19 | 2015-11-11 | 网易（杭州）网络有限公司 | Push method, device and system of game gift bag |
| CN105245577A (en) * | 2015-09-11 | 2016-01-13 | 腾讯科技（深圳）有限公司 | Information push method, device and system |
| AU2016347232A1 (en) * | 2015-10-27 | 2018-02-08 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for delivering a message |
| CN106815738A (en) * | 2015-12-01 | 2017-06-09 | 中国电信股份有限公司 | A kind of method and apparatus for obtaining user's portrait |
| CN105631538A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | User activity prediction method and device, and application method and system thereof |
| CN107230136A (en) * | 2017-05-31 | 2017-10-03 | 合肥亿迈杰软件有限公司 | A kind of shopping sequence method for pushing based on big data |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829752A (en) * | 2018-05-25 | 2018-11-16 | 南京邮电大学 | Based on personalized tutor's proposed algorithm |
| CN109245996A (en) * | 2018-09-18 | 2019-01-18 | 平安科技（深圳）有限公司 | Mail push method, device, computer equipment and storage medium |
| CN109785045A (en) * | 2018-12-14 | 2019-05-21 | 深圳壹账通智能科技有限公司 | A kind of method for pushing and device based on user behavior data |
| CN109919650A (en) * | 2019-01-16 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Multi-stage service promotes management method, device and storage medium, computer equipment |
| CN110335079A (en) * | 2019-07-02 | 2019-10-15 | 上海上湖信息技术有限公司 | A kind of intelligent task dispatching method and device collected based on instruction |
| CN110335079B (en) * | 2019-07-02 | 2022-02-25 | 上海上湖信息技术有限公司 | Intelligent task scheduling method and device based on instruction set |
| CN110443639A (en) * | 2019-07-16 | 2019-11-12 | 深圳市数位汇聚科技有限公司 | A kind of marketing strategy recommended method and device based on position positioning under line |
| CN110738416A (en) * | 2019-10-15 | 2020-01-31 | 珠海格力电器股份有限公司 | Distribution recommendation system, method, medium, and computing device |
| CN112685598A (en) * | 2019-10-18 | 2021-04-20 | 腾讯科技（深圳）有限公司 | Gift package pushing method and device in live broadcast |
| CN112685598B (en) * | 2019-10-18 | 2024-04-26 | 腾讯科技（深圳）有限公司 | Gift package pushing method and device in live broadcast |
| CN111127077A (en) * | 2019-11-29 | 2020-05-08 | 中国建设银行股份有限公司 | Recommendation method and device based on stream computing |
| CN111159534A (en) * | 2019-12-03 | 2020-05-15 | 泰康保险集团股份有限公司 | User portrait based aid decision making method and device, equipment and medium |
| CN112215664A (en) * | 2020-10-29 | 2021-01-12 | 支付宝(杭州)信息技术有限公司 | Information recommendation method and device |
| CN112650913A (en) * | 2020-12-30 | 2021-04-13 | 福建福诺移动通信技术有限公司 | Counting method and system for coping with big data high concurrency counting scene |
| CN113065888A (en) * | 2021-03-09 | 2021-07-02 | 北京安锐卓越信息技术股份有限公司 | Method, device and storage medium for recommending business opportunity based on action behavior |
| CN113065888B (en) * | 2021-03-09 | 2023-04-18 | 北京安锐卓越信息技术股份有限公司 | Method, device and storage medium for recommending business opportunity based on action behavior |
| CN113034241A (en) * | 2021-04-23 | 2021-06-25 | 中国平安人寿保险股份有限公司 | Product information recommendation method and computer equipment |
| CN115086701A (en) * | 2022-06-23 | 2022-09-20 | 咪咕动漫有限公司 | Lottery drawing processing method, device and equipment in live broadcast and readable storage medium |
| CN115033798A (en) * | 2022-07-04 | 2022-09-09 | 贵州电网有限责任公司 | Activity recommendation method and system based on big data |
| CN116205679A (en) * | 2023-02-27 | 2023-06-02 | 深圳市秦丝科技有限公司 | Physical store marketing recommendation method and device, electronic equipment and storage medium |
| CN116205679B (en) * | 2023-02-27 | 2023-10-31 | 深圳市秦丝科技有限公司 | Physical store marketing recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019153655A1 (en) | 2019-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108460629A (en) | User, which markets, recommends method, apparatus, terminal device and storage medium | |
| US11769182B2 (en) | Purchase information utilization system, purchase information utilization method, and program | |
| US10936986B2 (en) | Generation of engagement and support recommendations for content creators | |
| CN108242016B (en) | Product recommendation method and device | |
| KR101324909B1 (en) | Touchpoint customization system | |
| CN108776907A (en) | Advertisement intelligent recommends method, server and storage medium | |
| CN107679946A (en) | Fund Products Show method, apparatus, terminal device and storage medium | |
| CN108460627A (en) | Marketing activity scheme method for pushing, device, computer equipment and storage medium | |
| CN104035926B (en) | A kind of dispensing of internet information and system | |
| CN105608125B (en) | Information processing method and server | |
| CN110428276B (en) | Method, device and storage medium for selecting offline advertisement delivery area | |
| CN109711866B (en) | Bank advertisement putting method, device and system | |
| Burelli | Predicting customer lifetime value in free-to-play games | |
| CN109544209A (en) | Virtual interests bonusing method, device and computer equipment and storage medium | |
| CN109727055A (en) | Network Questionnaire Survey method, apparatus, equipment and computer readable storage medium | |
| CN103092348A (en) | Mobile terminal advertisement playing method based on user behavior | |
| CN111861605A (en) | Business object recommendation method | |
| CN110362751B (en) | Service recommendation method, device, computer equipment and storage medium | |
| CN108492135A (en) | The tracking optimization method and tracking optimization system of channel port cost | |
| CN112269933A (en) | Potential customer identification method based on effective connection | |
| CN111738754A (en) | Object recommendation method and device, storage medium and computer equipment | |
| CN116934372A (en) | Store operation customer data management method and system | |
| CN116757715A (en) | Ranking list generation method and device, storage medium and computer equipment | |
| CN107844874A (en) | Enterprise operation problem analysis system and its method | |
| US20100250363A1 (en) | Exchange based on traders buying and selling fictitious shares of content types based upon anticipated returns of such content |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1256425 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180828 |