CN109388679A - User population construction method, device, storage medium and equipment in population marketing - Google Patents
User population construction method, device, storage medium and equipment in population marketing Download PDFInfo
- Publication number
- CN109388679A CN109388679A CN201811030057.0A CN201811030057A CN109388679A CN 109388679 A CN109388679 A CN 109388679A CN 201811030057 A CN201811030057 A CN 201811030057A CN 109388679 A CN109388679 A CN 109388679A
- Authority
- CN
- China
- Prior art keywords
- user
- initial seed
- seed object
- group
- target user
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 32
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 25
- 230000006399 behavior Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical group C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013442 quality metrics Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a user ethnic group construction method, a system, a storage medium and equipment in ethnic group marketing, wherein a user object is selected as an initial seed object, and characteristic information of the initial seed object is obtained; traversing the database, and determining a target user in the database, wherein the characteristic information of the target user and the characteristic information of the initial seed object meet a preset relation condition corresponding to the initial seed object; and constructing a user population applied to population marketing according to the determined target users. The user selection is carried out according to the initial seed object information and the corresponding preset relation conditions, so that the selected user relation is relatively close, the accuracy of the user selection in the process of constructing the user population is improved, and the constructed user population applied to the population marketing is more scientific and reasonable.
Description
Technical field
This application involves information technology fields, more particularly to user group construction method, the dress in a kind of marketing of group
It sets, storage medium and equipment.
Background technique
With the development of internet technology, " group's marketing " this word is used more and more widely, wherein group refers to
In certain space-time unique, the group of user's composition with same interest hobby, group's marketing then refers to for this kind of tool
The process for the group expansion precision marketing for thering is same interest to like, wherein building user group is the basis of group's marketing.
The method of traditional building user group, enterprise is by client's letter in analysis corporate client data management system
Breath is to find relationship between client, to construct corresponding user group.
However, relying on the customer information in customer data management system in conventional method merely to divide doing for user group
Method is coarseness, i.e., only considers the classification of user object, do not consider the particular instance of object, constructs user so as to cause enterprise
The method of group has that relationship is weaker between user, user's accuracy of selection is lower.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of battalion, group that can be improved user's accuracy of selection
User group construction method, device, storage medium and equipment in pin.
A kind of user group construction method in group marketing, comprising the following steps:
User object is chosen as initial seed object, and obtains the characteristic information of the initial seed object；
Ergodic data library, determines the target user in the database, the characteristic information of the target user and it is described just
The characteristic information of beginning seed object meets preset relation condition corresponding with the initial seed object；
The user group being applied in group's marketing according to determining target user's building.
A kind of user group construction device in group marketing, comprising:
Seed selection module for choosing user object as initial seed object, and obtains the initial seed object
Characteristic information；
Target determination module is used for ergodic data library, determines the target user in the database, the target user's
The characteristic information of characteristic information and the initial seed object meets preset relation condition corresponding with the initial seed object；
Group constructs module, the user group for being applied in group's marketing according to determining target user's building.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
User object is chosen as initial seed object, and obtains the characteristic information of the initial seed object；
Ergodic data library, determines the target user in the database, the characteristic information of the target user and it is described just
The characteristic information of beginning seed object meets preset relation condition corresponding with the initial seed object；
The user group being applied in group's marketing according to determining target user's building.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
User object is chosen as initial seed object, and obtains the characteristic information of the initial seed object；
Ergodic data library, determines the target user in the database, the characteristic information of the target user and it is described just
The characteristic information of beginning seed object meets preset relation condition corresponding with the initial seed object；
The user group being applied in group's marketing according to determining target user's building.
User group construction method, system, storage medium and equipment in above-mentioned group's marketing, choose user object conduct
Initial seed object, and obtain the characteristic information of initial seed object；Ergodic data library determines the target user in database,
The characteristic information of target user and the characteristic information of initial seed object meet preset relation item corresponding with initial seed object
Part；The user group being applied in group's marketing according to determining target user's building.By according to initial seed object information
And corresponding preset relation condition carries out user's selection, so that relationship is more close between the user of selection, uses to improve building
The accuracy that user selects during the group of family, so that the more scientific conjunction of user group of building being applied in group's marketing
Reason.
Detailed description of the invention
Fig. 1 is the applied environment figure of the user group construction method in one embodiment in group's marketing；
Fig. 2 is the flow diagram of the user group construction method in one embodiment in group's marketing；
Fig. 3 is the process signal for determining the corresponding target user's step of each initial seed object in one embodiment respectively
Figure；
Fig. 4 is the flow diagram of the user group construction method in another embodiment in group's marketing；
Fig. 5 is the process signal for realizing the user group building in group's marketing in one embodiment using crawler technology
Figure；
Fig. 6 is the structural block diagram of the user group construction device in one embodiment in group's marketing；
Fig. 7 is the structural block diagram of the user group construction device in another embodiment in group's marketing；
Fig. 8 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
User group construction method in group's marketing provided by the present application can be applied to application ring as shown in Figure 1
In border.Wherein, terminal 102 is communicated with server 104 by network by network, for executing the user in group's marketing
Group's construction method.Wherein, it is various personal computers that terminal 102, which can be, but not limited to, laptop, smart phone, is put down
Plate computer and portable wearable device, server 104 can use the clothes of the either multiple server compositions of independent server
Device cluster be engaged in realize.
In one embodiment, as shown in Fig. 2, the user group construction method in a kind of marketing of group is provided, with the party
Method be applied to Fig. 1 in terminal for be illustrated, the user group construction method the following steps are included:
Step S110 chooses user object as initial seed object, and obtains the characteristic information of initial seed object.
It can be grabbed from database in one embodiment and meet the user object of certain condition as initial seed object,
The certain condition can be markets the condition for needing and being arranged according to group, for example, gender be male or age for 20 years old with
On, perhaps often browse certain website or commonly using certain application etc..Choosing the conduct initial seed pair for meeting certain condition
After the user object of elephant, the characteristic information of the user object is obtained.
Step S120, ergodic data library determine the target user in database.
This step determines characteristic information and initial seed object by the characteristic information for the user for including in ergodic data library
Characteristic information meet the target user of corresponding with initial seed object preset relation condition.
Step S130, the user group being applied in group's marketing according to determining target user's building.
In this step, determined according to initial seed object the characteristic information of characteristic information and initial seed object meet with
After the target user of the corresponding preset relation condition of initial seed object, group is applied to according to determining target user's building and is sought
User group in pin.
Group's marketing is in certain space-time unique, is enterprise to the group expansion precision marketing for having identical hobby
Marketing sharp weapon and break-through point.In building user group, and analysis adopted compared to the user social contact delineation of social platform maturation, one
As enterprise be limited by data source and can only rely on the customer data in CRM system to find relationship between user, depending on
Adopted group, however rely on the essential attribute of CRM system record user merely come comparatively to divide group be coarse grain
Degree.The present embodiment, which passes through, determines initial seed object information, and according to the initial seed object, characteristic information and corresponding
Preset relation condition determines target user, rather than determines target user according to the essential attribute of user in database merely,
So that relationship is more close between the user of selection, user-association degree is stronger, so that user selects during improving building user group
The accuracy selected, so that the user group of building being applied in group's marketing is more scientific and reasonable.
In one embodiment, characteristic information includes foundation characteristic information and behavior characteristic information.Foundation characteristic information is
Refer to the inherent feature information of user, such as age, gender, address static information；Behavior characteristic information then covers relatively extensively, refers to
Be record client behavioural information, such as menu click, page browsing, application and program service condition action message.
In the step s 120, ergodic data library, the step of determining the target user in database, specifically: ergodic data
The foundation characteristic information and behavior characteristic information of each user in library, determines foundation characteristic information and/or behavior characteristic information
Meet the corresponding preset relation item of initial seed object with the foundation characteristic information and/or behavior characteristic information of initial seed object
The target user of part.
It should be noted that when carrying out target user's confirmation, it is special as the foundation characteristic information of Rule of judgment and behavior
The quantity of reference breath be it is indefinite, can be and target user is carried out really according to single foundation characteristic information or behavior characteristic information
Recognize, is also possible to carry out the confirmation of target user according to multiple foundation characteristic information and/or behavior characteristic information.
Such as: the characteristic information of an initial seed object is as follows: male, and 20 years old, make a phone call every month was 100 points time
It is more than clock.When carrying out user's selection according to above-mentioned initial seed object, it can be and need to select wherein to appoint according to race's marketing
One characteristic information carries out user's selection, such as when carrying out the popularization of call voice set meal, can choose that " time of making a phone call every month is
100 minutes or more " this characteristic information as target user's fixed condition really, finds meet that " every month beats electricity in the database
Talking about the time is 100 minutes or more " target user of this condition, and call voice set meal is carried out to these target users and is pushed away
Extensively.User is carried out according to single features information and selects available a fairly large number of target user, to improve group's marketing
Range.In addition it is also possible to be according to " every month make a phone call time be 100 minutes or more " and " 20 years old " the two characteristic informations
User's selection is carried out, process is consistent with the above process.According to multiple characteristic informations carry out user select available accuracy compared with
High target user, to improve the precision of group's marketing.
The present embodiment by according to user with the foundation characteristic information and row that are left in enterprise product or service interaction
It is characterized information and carries out sufficient data mining, so that user is divided into more fine-grained group, is conducive to group's marketing and lives
Dynamic development.
In one embodiment, when carrying out target user's selection, when determining database according to current initial seed object
In target user after, using determining target user as new initial seed object, and true according to new initial seed object
Fixed new target user.
Such as: include tetra- users of A, B, C, D by the target user that an initial seed object determines, is carrying out second
When secondary target user selects, then new target user is determined as initial seed object using tetra- users of A, B, C, D respectively.?
When two wheel target users determine, obtaining new target user according to party A-subscriber is A1, A2, and new target user is obtained according to party B-subscriber
For B1, obtaining new target user according to C user is C1, C2, C3, according to D user obtain new target user be D1, D2, D3,
D4 carries out new target as initial seed object using the target user that the second wheel is determining then when third round target user determines
The determination of user.It should be noted that every wheel user selects pre- when wheel users selections more for initial seed object progress
If relation condition may be the same or different.
User's selection can be improved when the more wheel target users of progress determine, by replacing initial seed object in the present embodiment
Depth, so as to obtain sufficient amount of target user, when guaranteeing building user group there are enough numbers of users with
Convenient for carrying out group's marketing activity.
In one embodiment, after determining the target user in database according to current initial seed object, with determination
Target user as new initial seed object, and the step of new target user is determined according to new initial seed object,
It is further comprising the steps of:
Obtain the current depth information for carrying out target user's selection operation according to initial seed object in database.Currently
Depth information carries out the wheel number information that target user determines according to the initial seed object in first round user selection, such as fixed
The depth that adopted first round user selects is first layer, and the depth that the second wheel user selects is the second layer, and so on.
When current depth information reaches predetermined depth information, stop carrying out target user's selection according to initial seed object
Operation.User's selection of unlimited number can be carried out by an initial seed object, therefore passes through setting one in this step
The Rule of judgment that a predetermined depth information stops as user's selection operation: when active user's selected depth (when front-wheel number) reaches
When predetermined depth (default wheel number), stop the operation for carrying out user's selection.
The present embodiment is on the basis of upper one embodiment, to the depth (i.e. the determining wheel number of target user) of user's selection
It is defined, one stop condition on the one hand is set for user's selection operation, on the other hand, due to selecting the increasing of wheel number with user
More, newly the degree of association of determining target user and initial seed object also gradually reduces, and therefore, the restriction of user's selected depth also can
Guarantee that determining target user and initial seed object still have certain degree of association, building and race in order to user group
The development of group's marketing activity.
In one embodiment, when the quantity of the initial seed object of selection is multiple, ergodic data library determines respectively
The corresponding target user of each initial seed object.
In the present embodiment, before carrying out user's selection, the quantity of the initial seed object of selection can be one or
Be it is multiple, when only one initial seed object, according to the initial seed object carry out target user determine, until user select
It selects until depth reaches predetermined depth.When being multiple initial seed objects, target use is carried out according to each initial seed object
Family determines, until user's selected depth of each initial seed object reaches predetermined depth.According to multiple initial seeds
Object, which carries out target user's selection, can be improved the range of user's selection, guarantee the quantity of target user.
In one embodiment, when the quantity of initial seed object is multiple, each initial seed object is corresponding default
Relation condition is identical or different.
Such as: choosing as the user of initial seed object includes tetra- users of A, B, C, D, in the target for carrying out first time
When user selects, new target user is determined as initial seed object using tetra- users of A, B, C, D respectively.A, at the beginning of B, C, D tetra-
The corresponding preset relation condition of beginning seed object may be the same or different.
As shown in figure 3, ergodic data library in the present embodiment, determines that the corresponding target of each initial seed object is used respectively
The step of family, including step S122 to step S126.
Step S122 chooses an initial seed object as current initial seed object from each initial seed object.
Step S124, ergodic data library determine the target user for corresponding to current initial seed object in database, corresponding
Meet in the characteristic information of the target user of current initial seed object and the characteristic information of current initial seed object current first
The corresponding preset relation condition of beginning seed object.
Step S126 is returned and is chosen an initial seed object from each initial seed object as current initial seed pair
As the step of, until each initial seed object was used as current initial seed object.
Specifically, equally to divide by taking tetra- initial seed objects of A, B, C, D as an example according to this four initial seed objects
Not carry out target user's selection when, can according to ABCD sequence respectively as current initial seed object carry out target user's choosing
It selects, multiple initial seed objects carry out the sequence of target user's selection as current initial seed object and are not fixed.This implementation
In example, when the quantity of initial seed object is multiple, user's selection is carried out according to an initial seed object every time, when one
When user's selected depth of initial seed object reaches predetermined depth, the user for carrying out next initial seed object selects behaviour
Make, so as to preferably manage initial seed object and corresponding user's selected depth.
In one embodiment, as shown in figure 4, in the use being applied in group's marketing according to determining target user's building
After family group step, which further includes step S140, is carried out to the target user in user group special
Levy classification processing.
Specifically, it is assumed that have N number of user object in the user group of building, each user object has characteristic information m a, pre-
Surveying characteristic information (characteristic information of application and race's marketing) has n.To excavate expected marketing model, under necessary, by user
Part multivalue, the further discretization of continuous characteristic information of object, make each characteristic information be used as independent Relation Element.Phase
The basic step of closing property method is as follows:
1) N number of sample object is selected from user group, is assigned Boolean for its characteristic information having, is established N number of m+n long
Binary string, Boolean is one in "true" True or "false" False.
2) binary string based on m+n long, establishes the incidence relation of characteristic information Yu single predicted characteristics information, and mode is total
Number is such as formulaTo the probability value from N number of each mode of sample centralized calculation.
3) sample number with relationship for true value of characteristic information and single predicted characteristics information in N number of sample number is counted, such as
Formula:
Whereinj∈[1,n],R∈[0,1]
To acquire the R value of each pattern dependency.
Feature correlation analysis traverses n times for each mode and seeks R value, and the overall consuming time is mode sum and sample
The product of sum, correlation method time complexity are shown in formula T (n)=O (n2), but not each mode is effectively, in vain
Mode needs clean up.
4) invalid mode is cleared up by characteristic information set inclusion relation and the sequence of R value, such as formulaMode A can be cleared up, to retain interesting mode for business opportunity digging；
Mode B is Mode A from attribute set from attribute in formula, but the R value of Mode B is greater than Mode A, then shows mould
Formula A is invalid.
5) the remaining interesting mode after mode cleaning, it is practical in combination with production, the empirical value of R is defined, feature letter is extracted
The mode for ceasing strong incidence relation finds the client with characteristic information assemblage characteristic from the data warehouse based on user group,
Derive a possibility that potential predicted characteristics information occurs.
Further evaluation profile is such as wanted, then obtains the characteristic information attribute value of sample object, determining certainly by regression analysis,
Because of the relevance function relationship between attribute；Mode is cleared up, can also further defining mode quality metric be restrained.In view of race
The close relationship of group's data warehouse meets the sociability of real customers, and the client of close relationship has similar product consumption
Tendency, by correlation analysis, excavates interesting Attribute Association mode, and mode is directly applied to pair in warehouse
As.
The present embodiment is after establishing the user group that application is marketed with group, further according to the characteristic information of user object
Tagsort processing is carried out to the target user in user group, so that targetedly pattern classification is carried out to user object, into
And carry out a variety of different group's marketing activities.
In one embodiment, as shown in figure 5, realizing the battalion, group provided in above-mentioned multiple embodiments using crawler technology
User group construction method in pin.Web crawlers be it is a kind of according to certain rules, automatically grab the journey of web message
Sequence or script.Traditional crawler technology multi-user grasping information of web site, and crawler technology is applied to crawl in the present embodiment and is used
Family object.
A kind of method that close relative crawler is proposed in the present embodiment, the essential characteristic and behavioural characteristic of synthetic user construct particulate
The user group of degree, the close relative crawler method is using user as research object, the characteristic attribute based on known object, defines close relative
Relationship grabs unknown object from enterprise's Production database, make known object and institute crawler to unknown object have therebetween
Close relationship, as crawler recycles incessantly, it is established that the user group with close relationship finds to carry out data mining
Mode between attribute, and then support is provided for marketing.Such as party A-subscriber often browses the page of a certain theme, if party B-subscriber
It is that the two is it can be assumed that there is close relationship, on the basis of this, if A hobby uses some function of product, it is possible to determine that
B also can preference this attribute, can be to this function of B personalized recommendation.
Specifically, it is primarily based on marketing scene and defines close relative's crawler rule, comprising: the selection of crawler initial seed object,
The Attributions selection of close relationship, the setting of crawler depth.Select some or multiple characteristic attributes of crawler initial seed object fixed
Adopted close relationship, so that the segment data warehouse for going out crawler has specific subject, as special time period browsing store is a kind of
The user of commodity has close relationship.
When executing close relative's crawler operation, in one embodiment, close relative's crawler algorithm is described as follows with pseudocode:
Algorithm: close relative's crawler algorithm in segment data warehouse is established.
Input: the user behavior information of each channel record of enterprises customer basis and product consumption database and enterprise.
Definition:
1) object Ob (S1, S2 ..., Sn, P1, P2 ..., Pn), S indicate essential characteristic, and P indicates behavioural characteristic；
2) close relationship attribute Sc；
3) crawler depth depth；
4) seed object queue Q, length length；
5) queue nodes QNode (Ob, depth), storage object and its crawler depth；
6) input data source DB records sum rows；
7) output data warehouse DW.
Output: setting up the object set with close relationship, and data warehouse storage relationship such as the following table 1 close relative is closed
It is shown in table.
1 close relationship table of table
| Feature | S1 | Sc | … | Sn | P1 | … | Pn |
| Ob1 | Char[] | ||||||
| Ob2 | Char[] | ||||||
| … | Char[] | ||||||
| Obn | Char[] |
Method:
GetObFromDB(&Ob)；// initial seed object is selected from data source DB
Q←QNode(Ob,0)；// initialization queue, and it is inserted into initial seed Object node, object is under the jurisdiction of crawler depth
0
Depth==1；// first round crawler
Sc←Ob.Sc；// the crawler attribute value of initial seed object is assigned to Sc, as close relationship judgment basis
{ // queue is not sky to while (Q.length), and the length of Q is not zero
GetFirstNodeFromQ(&QNode)；// queue enemy's element is fallen out
SaveObToDW(QNode.Ob)；// seed object, which is fallen out, is saved in data warehouse DW
If QNode.depth==9then continue；// terminate this circulation, reach crawler depth 10
For (int i=0；i<DB.rows；I++) // traverse all objects in DB
GetObFromDB(&Ob[i])；// object is extracted from DB
If Ob [i] .Sc==Sc then
Q←QNode(Ob[i],depth)；// close relative's object with Sc attribute is fallen in lines
}
depth++；// epicycle crawler terminates, and crawler depth increases by 1 layer
}
Close relative's crawler algorithm used in the present embodiment depends on the data acquisition breadth and depth in enterprise's Various types of data source,
Abundant object information, can sufficiently crawler to close relative's object, also provide adequate sample for the mode excavation in correlation analysis
Collection.
It should be understood that although each step in the flow chart of Fig. 2-5 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-5
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in fig. 6, providing the user group construction device in a kind of marketing of group, the device
Module 130 is constructed including seed selection module 110, target determination module 120 and group.
Seed selection module 110 obtains initial seed object for choosing user object as initial seed object
Characteristic information, characteristic information include foundation characteristic information and behavior characteristic information.
Target determination module 120 is used for ergodic data library, determines the target user in database, the feature letter of target user
The characteristic information of breath and initial seed object meets preset relation condition corresponding with initial seed object.Target determination module
120 by the foundation characteristic information and behavior characteristic information of each user in ergodic data library, determine foundation characteristic information and/
Or the foundation characteristic information and/or behavior characteristic information of behavior characteristic information and initial seed object meet initial seed object pair
The target user for the preset relation condition answered.
Group constructs the user group that module 130 is used to be applied to according to determining target user's building in group's marketing.
After the target object that target determination module 120 determines each initial seed object, group constructs module 130 and is determined according to target
Target user's building that module 120 determines is applied to the user group in group's marketing.
In one embodiment, as shown in fig. 7, the user group construction device further includes user's categorization module 140.User
Categorization module 140 is used to carry out tagsort processing to the target user in user group.Establishing what application was marketed with group
After user group, further the target user in user group is carried out at tagsort according to the characteristic information of user object
Reason to carry out targetedly pattern classification to user object, and then carries out a variety of different group's marketing activities.
Specific restriction about the user group construction device in group's marketing may refer to market above for group
In user group construction method restriction, details are not described herein.In user group construction device in above-mentioned group's marketing
Modules can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware
Or independently of in the processor in computer equipment, can also be stored in a software form in the memory in computer equipment,
The corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 8.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the user group building data in group's marketing.The network interface of the computer equipment is used for
It is communicated with external terminal by network connection.To realize in a kind of marketing of group when the computer program is executed by processor
User group construction method.
It will be understood by those skilled in the art that structure shown in Fig. 8, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
User object is chosen as initial seed object, and obtains the characteristic information of initial seed object；
Ergodic data library determines the target user in database；
The user group being applied in group's marketing according to determining target user's building.
In one embodiment, it is also performed the steps of when processor executes computer program
After determining the target user in the database according to current initial seed object, made with determining target user
For new initial seed object, and new target user is determined according to the new initial seed object.
In one embodiment, it is also performed the steps of when processor executes computer program
Obtain the current depth information for carrying out target user's selection operation according to initial seed object in the database；
When the current depth information reaches predetermined depth information, stop carrying out target according to the initial seed object
The operation of user's selection.
In one embodiment, it is also performed the steps of when processor executes computer program
An initial seed object is chosen from each initial seed object as current initial seed object；
Ergodic data library determines the target user for corresponding to the current initial seed object in the database, corresponding
It is full in the characteristic information of the target user of the current initial seed object and the characteristic information of the current initial seed object
The corresponding preset relation condition of the current initial seed object enough；
It returns and chooses a step of initial seed object is as current initial seed object from each initial seed object,
Until each initial seed object was used as current initial seed object.
In one embodiment, it is also performed the steps of when processor executes computer program
Tagsort processing is carried out to the target user in the user group.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
User object is chosen as initial seed object, and obtains the characteristic information of initial seed object；
Ergodic data library determines the target user in database；
The user group being applied in group's marketing according to determining target user's building.
In one embodiment, it is also performed the steps of when computer program is executed by processor
After determining the target user in the database according to current initial seed object, made with determining target user
For new initial seed object, and new target user is determined according to the new initial seed object.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Obtain the current depth information for carrying out target user's selection operation according to initial seed object in the database；
When the current depth information reaches predetermined depth information, stop carrying out target according to the initial seed object
The operation of user's selection.
In one embodiment, it is also performed the steps of when computer program is executed by processor
An initial seed object is chosen from each initial seed object as current initial seed object；
Ergodic data library determines the target user for corresponding to the current initial seed object in the database, corresponding
It is full in the characteristic information of the target user of the current initial seed object and the characteristic information of the current initial seed object
The corresponding preset relation condition of the current initial seed object enough；
It returns and chooses a step of initial seed object is as current initial seed object from each initial seed object,
Until each initial seed object was used as current initial seed object.
In one embodiment, it is also performed the steps of when computer program is executed by processor
Tagsort processing is carried out to the target user in the user group.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. the user group construction method in a kind of group's marketing, which comprises the following steps:
User object is chosen as initial seed object, and obtains the characteristic information of the initial seed object；
Ergodic data library, determines the target user in the database, the characteristic information of the target user with described initial kind
The characteristic information of subobject meets preset relation condition corresponding with the initial seed object；
The user group being applied in group's marketing according to determining target user's building.
2. the user group construction method in group's marketing according to claim 1, which is characterized in that the characteristic information
It include: foundation characteristic information and behavior characteristic information.
3. the user group construction method in group's marketing according to claim 1, which is characterized in that when according to current first
After beginning seed object determines the target user in the database, using determining target user as new initial seed object,
And new target user is determined according to the new initial seed object.
4. the user group construction method in group's marketing according to claim 3, which is characterized in that described when basis is worked as
After preceding initial seed object determines the target user in the database, using determining target user as new initial seed pair
As, and the step of new target user is determined according to the new initial seed object, further includes:
Obtain the current depth information for carrying out target user's selection operation according to initial seed object in the database；
When the current depth information reaches predetermined depth information, stop carrying out target user according to the initial seed object
The operation of selection.
5. the user group construction method in group according to claim 1 marketing, which is characterized in that initial when selection
When the quantity of seed object is multiple, ergodic data library determines the corresponding target user of each initial seed object respectively.
6. the user group construction method in group's marketing according to claim 5, which is characterized in that when described initial kind
When the quantity of subobject is multiple, the corresponding preset relation condition of each initial seed object is identical or different；
The ergodic data library, the step of determining the corresponding target user of each initial seed object respectively, comprising:
An initial seed object is chosen from each initial seed object as current initial seed object；
Ergodic data library determines the target user for corresponding to the current initial seed object in the database, corresponds to institute
The characteristic information of the characteristic information and the current initial seed object of stating the target user of current initial seed object meets institute
State the corresponding preset relation condition of current initial seed object；
It returns and chooses a step of initial seed object is as current initial seed object from each initial seed object, until
Each initial seed object was used as current initial seed object.
7. the user group construction method in group's marketing according to claim 1, which is characterized in that described according to determination
Target user building be applied to group marketing in user group step after, further includes: to the mesh in the user group
It marks user and carries out tagsort processing.
8. the user group construction device in a kind of group's marketing characterized by comprising
Seed selection module for choosing user object as initial seed object, and obtains the spy of the initial seed object
Reference breath；
Target determination module is used for ergodic data library, determines the target user in the database, the feature of the target user
The characteristic information of information and the initial seed object meets preset relation condition corresponding with the initial seed object；
Group constructs module, the user group for being applied in group's marketing according to determining target user's building.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811030057.0A CN109388679A (en) | 2018-09-05 | 2018-09-05 | User population construction method, device, storage medium and equipment in population marketing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811030057.0A CN109388679A (en) | 2018-09-05 | 2018-09-05 | User population construction method, device, storage medium and equipment in population marketing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109388679A true CN109388679A (en) | 2019-02-26 |
Family
ID=65417572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811030057.0A Pending CN109388679A (en) | 2018-09-05 | 2018-09-05 | User population construction method, device, storage medium and equipment in population marketing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109388679A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538051A (en) * | 2021-07-16 | 2021-10-22 | 广州电力交易中心有限责任公司 | Electric power transaction platform safety early warning method based on user behaviors |
| CN114385700A (en) * | 2022-01-10 | 2022-04-22 | 腾讯科技（深圳）有限公司 | Method, device and equipment for determining seed object and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104428805A (en) * | 2012-07-13 | 2015-03-18 | 脸谱公司 | Search-powered connection targeting |
| WO2017090539A1 (en) * | 2015-11-26 | 2017-06-01 | 株式会社博報堂 | Information processing system and method |
| CN106951436A (en) * | 2017-02-09 | 2017-07-14 | 华南理工大学 | A kind of extensive online recommendation method based on mobile contextual |
| CN107346496A (en) * | 2016-05-05 | 2017-11-14 | 腾讯科技（北京）有限公司 | Targeted customer's orientation method and device |
| CN107515915A (en) * | 2017-08-18 | 2017-12-26 | 晶赞广告（上海）有限公司 | User based on user behavior data identifies correlating method |
-
2018
- 2018-09-05 CN CN201811030057.0A patent/CN109388679A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104428805A (en) * | 2012-07-13 | 2015-03-18 | 脸谱公司 | Search-powered connection targeting |
| WO2017090539A1 (en) * | 2015-11-26 | 2017-06-01 | 株式会社博報堂 | Information processing system and method |
| CN107346496A (en) * | 2016-05-05 | 2017-11-14 | 腾讯科技（北京）有限公司 | Targeted customer's orientation method and device |
| CN106951436A (en) * | 2017-02-09 | 2017-07-14 | 华南理工大学 | A kind of extensive online recommendation method based on mobile contextual |
| CN107515915A (en) * | 2017-08-18 | 2017-12-26 | 晶赞广告（上海）有限公司 | User based on user behavior data identifies correlating method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538051A (en) * | 2021-07-16 | 2021-10-22 | 广州电力交易中心有限责任公司 | Electric power transaction platform safety early warning method based on user behaviors |
| CN114385700A (en) * | 2022-01-10 | 2022-04-22 | 腾讯科技（深圳）有限公司 | Method, device and equipment for determining seed object and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11715132B2 (en) | Adaptive and recursive system and method | |
| US7526458B2 (en) | Adaptive recommendations systems | |
| US7539652B2 (en) | Adaptive self-modifying and recombinant systems | |
| US7526459B2 (en) | Adaptive social and process network systems | |
| US7493294B2 (en) | Mutually adaptive systems | |
| US8194830B2 (en) | Method for predicting churners in a telecommunications network | |
| USRE44559E1 (en) | Adaptive social computing methods | |
| CN109271420A (en) | Information-pushing method, device, computer equipment and storage medium | |
| CN108763502A (en) | Information recommendation method and system | |
| CN109408724A (en) | Multimedia resource estimates the determination method, apparatus and server of clicking rate | |
| CN112287015B (en) | Image generation system, image generation method, electronic device, and storage medium | |
| CN110377851A (en) | Implementation method, device and the computer equipment of multistage linking combobox | |
| CN108874926A (en) | Mass data inquiry method, device, computer equipment and storage medium | |
| US20090190729A1 (en) | System and computer program product for predicting churners in a telecommunications network | |
| CN107526807A (en) | Information recommendation method and device | |
| CN107066476A (en) | A kind of real-time recommendation method based on article similarity | |
| CN102279851A (en) | Intelligent navigation method, device and system | |
| CN109388679A (en) | User population construction method, device, storage medium and equipment in population marketing | |
| CN112380433B (en) | Recommendation element learning method for cold start user | |
| CN105224532A (en) | Data processing method and device | |
| WO2005054982A2 (en) | Adaptive recombinant systems | |
| CN106203631A (en) | The parallel Frequent Episodes Mining of description type various dimensions sequence of events and system | |
| US12093983B2 (en) | Adaptive and recursive system and method | |
| CN108512948A (en) | Address book updating method, device, computer equipment and storage medium | |
| Bugajev et al. | The impact of churn labelling rules on churn prediction in telecommunications |
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: 20190226 |