CN110428001A - A kind of community mining method, apparatus, server and storage medium - Google Patents
A kind of community mining method, apparatus, server and storage medium Download PDFInfo
- Publication number
- CN110428001A CN110428001A CN201910702190.4A CN201910702190A CN110428001A CN 110428001 A CN110428001 A CN 110428001A CN 201910702190 A CN201910702190 A CN 201910702190A CN 110428001 A CN110428001 A CN 110428001A
- Authority
- CN
- China
- Prior art keywords
- user
- correlation
- degree
- community
- offline businesses
- 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.)
- Granted
Links
- 238000005065 mining Methods 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000006399 behavior Effects 0.000 claims description 14
- 230000005055 memory storage Effects 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000001419 dependent effect Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 18
- 230000006870 function Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000009412 basement excavation Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a kind of community mining method, apparatus, server and storage medium, determines at least one offline businesses in pre-set geographic range；Determine at least one user, there are incidence relations with any one or more offline businesses at least one offline businesses within the scope of pre-set historical time by user；Calculate the degree of correlation at least one user between every two user；It corrects the degree of correlation between two users and obtains first degree of correlation and second degree of correlation between two users, community mining is carried out at least one user based on first degree of correlation between every two user at least one user and second degree of correlation and obtains community mining result.The application does not need the geographical location information reported dependent on terminal device and realizes community mining, therefore the geographical location information that community mining result is not reported by terminal device is influenced.
Description
Technical field
The present invention relates to community mining technical fields, more specifically to a kind of community mining method, apparatus, service
Device and storage medium.
Background technique
Community mining technology occupies increasingly important role in fields such as below-the-line promotion, advertisement dispensings.Good community
The success rate that Result can effectively improve below-the-line promotion, advertisement is launched.
Existing community mining technology is mainly the geographical location information for receiving the terminal device active reporting that user carries,
Multiple users are clustered according to the geographical location information of terminal device active reporting, to realize the excavation to community.Though
The excavation to community, but the geographical location letter reported dependent on terminal device may be implemented in right existing community mining technology
Breath, the geographical location information for being easy to be reported by terminal device are influenced.
Summary of the invention
In view of this, to solve the above problems, the present invention provides a kind of community mining method, apparatus, server and storage
Medium, to realize the excavation to community on the basis of the geographical location information reported independent of terminal device.Technical solution
It is as follows:
A kind of community mining method, comprising:
Determine at least one offline businesses in pre-set geographic range；
Determine at least one user, the user is within the scope of pre-set historical time and under at least one described line
Any one or more offline businesses in businessman are there are incidence relation, and there are incidence relation instructions with offline businesses by user
There are consumer behaviors in offline businesses by user；
Calculate the degree of correlation at least one described user between every two user, the degree of correlation between described two users
Incidence relation is existed simultaneously with described two users at least one offline businesses described within the scope of the historical time
The quantity of offline businesses is directly proportional；
It corrects the degree of correlation between described two users and obtains first degree of correlation and the second phase between described two users
Guan Du, first degree of correlation are the degree of correlation of first user relative to second user in described two users, second phase
Guan Du is the degree of correlation of the second user relative to first user；
Based on first degree of correlation between every two user at least one described user and second degree of correlation to it is described at least
One user carries out community mining and obtains community mining result.
A kind of community mining device, comprising:
Offline businesses' determination unit, for determining at least one offline businesses in pre-set geographic range；
User's determination unit, for determining at least one user, the user is within the scope of pre-set historical time
There are incidence relation, user and quotient under line with any one or more offline businesses at least one described offline businesses
There are incidence relation instruction user, in offline businesses, there are consumer behaviors for family；
Correlation calculating unit, it is described for calculating the degree of correlation at least one described user between every two user
The degree of correlation between two users and within the scope of the historical time at least one described offline businesses with described two use
The quantity that family exists simultaneously the offline businesses of incidence relation is directly proportional；
Degree of correlation amending unit obtains between described two users for correcting the degree of correlation between described two users
First degree of correlation and second degree of correlation, first degree of correlation are the first user in described two users relative to second user
The degree of correlation, second degree of correlation are the degree of correlation of the second user relative to first user；
Community mining unit, for based on first degree of correlation and second between every two user at least one described user
The degree of correlation carries out community mining at least one described user and obtains community mining result.
A kind of server, comprising: at least one processor and at least one processor；The memory is stored with program,
The processor calls the program of the memory storage, and described program is for realizing the community mining method.
A kind of storage medium is stored with computer executable instructions in the storage medium, and the computer is executable to be referred to
It enables for executing the community mining method.
It is true that the application provides a kind of community mining method, apparatus, server and storage medium, the consumer behavior based on user
Determine the incidence relation between user and offline businesses, and then difference is excavated based on the incidence relation between user and offline businesses
Geographic location association between user carries out community mining finally by each user, determines the user for living in identical community,
Obtain community mining result.The application does not need the geographical location information reported dependent on terminal device during realization,
The geographical location information that community mining result is not reported by terminal device is influenced.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is by a kind of hardware configuration frame for the server that community mining method is suitable for provided by the embodiments of the present application
Figure；
Fig. 2 is a kind of community mining method flow diagram provided by the embodiments of the present application；
Fig. 3 is a kind of user-businessman's Consumption relation schematic diagram provided by the embodiments of the present application；
Fig. 4 is a kind of at least one offline businesses determined in pre-set geographic range provided by the embodiments of the present application
Method flow diagram；
Fig. 5 is a kind of method flow diagram for calculating the degree of correlation between two users provided by the embodiments of the present application；
Fig. 6 is that the degree of correlation between a kind of two users of amendment provided by the embodiments of the present application obtains between two users
The method flow diagram of first degree of correlation and second degree of correlation；
Fig. 7 is provided by the embodiments of the present application a kind of based on first degree of correlation between every two user at least one user
Community mining is carried out at least one user with second degree of correlation and obtains the method flow diagram of community mining result；
Fig. 8 is a kind of degree of correlation that each neighbor user is respectively relative to according to target user provided by the embodiments of the present application
Calculate the method flow diagram of the weight of each community；
Fig. 9 is another community mining method flow diagram provided by the embodiments of the present application；
Figure 10 is a kind of structural schematic diagram of community mining device provided by the embodiments of the present application.
Specific embodiment
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 description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Existing community mining technology is mainly the geographical location information for receiving the terminal device active reporting that user carries,
The geographical location information reported according to the terminal device of multiple users clusters multiple users, obtains community mining result.
The geographical location information that this community mining method depends on terminal device to report, community mining result are reported vulnerable to terminal device
Geographical location information influence.
For example, because the geographical location information of terminal device belongs to the privacy information of user, it is only few under normal conditions
Several terminal device meeting active reporting geographical location information, which results in the geographical location information quantity for being clustered
It is few, the problem of community mining result not comprehensively, inaccurate；Also, because the geographical location information that terminal device reports is accurate
Property be easy influenced by terminal device itself, therefore, also normally result in the problem of community mining result inaccuracy.
The embodiment of the present application provides a kind of community mining method, apparatus, server and storage medium, not depend on terminal
The excavation to community is realized on the basis of the geographical location information that equipment reports.
A kind of community mining method provided by the embodiments of the present application can be applied to server, which can be network side
The service equipment of service is provided for user, may be the server cluster of multiple servers composition, it is also possible to separate unit service
Device.
Optionally, Fig. 1 shows the hardware block diagram of server, and referring to Fig.1, the hardware configuration of server can wrap
It includes: processor 11, communication interface 12, memory 13 and communication bus 14；
In embodiments of the present invention, processor 11, communication interface 12, memory 13, communication bus 14 quantity can be with
For at least one, and processor 11, communication interface 12, memory 13 complete mutual communication by communication bus 14；
Processor 11 may be a central processor CPU or specific integrated circuit ASIC
(Application Specific Integrated Circuit), or be arranged to implement of the invention real
Apply one or more integrated circuits etc. of example；
Memory 13 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-volatile
Memory) etc., a for example, at least magnetic disk storage；
Wherein, memory is stored with program, the program that processor can call memory to store, and program is used for:
Determine at least one offline businesses in pre-set geographic range；
Determine at least one user, user is within the scope of pre-set historical time and at least one offline businesses
There are incidence relation, user and offline businesses, there are incidence relation instruction users to descend quotient online for any one or more offline businesses
There are consumer behaviors for family；
The degree of correlation at least one user between every two user is calculated, the degree of correlation between two users and in history
It is directly proportional to the quantity for the offline businesses that two users exist simultaneously incidence relation at least one offline businesses in time range；
It corrects the degree of correlation between two users and obtains first degree of correlation and second degree of correlation between two users, first
The degree of correlation is the degree of correlation of first user relative to second user in two users, and second degree of correlation is second user relative to the
The degree of correlation of one user；
Based on first degree of correlation and second degree of correlation between every two user at least one user at least one user
It carries out community mining and obtains community mining result.
For the ease of the understanding to the community mining method for being suitable for above-mentioned server, now to provided by the embodiments of the present application
A kind of community mining method describes in detail.
Fig. 2 is a kind of community mining method flow diagram provided by the embodiments of the present application.
As shown in Fig. 2, this method comprises:
S201, at least one offline businesses in pre-set geographic range are determined；
In the embodiment of the present application, pre-set geographic range can be a provincial capital, a city, a city etc.
Deng.It is above only the preferred embodiment of pre-set geographic range provided by the embodiments of the present application, the tool in relation to geographic range
Body set-up mode, inventor can be configured according to their own needs, it is not limited here.
It, can be true after determining pre-set geographic range as a kind of preferred embodiment of the embodiment of the present application
At least one offline businesses being positioned in the geographic range, wherein offline businesses can be using face-to-face gathering functions
Offline businesses.
The service that different offline businesses provide may be different, and some offline businesses are clothes shop, the offline businesses that have are
The offline businesses that the offline businesses that life supermarket, the offline businesses that have be greengrocer's, has are dining room, have are hardware store, the line having
The offline businesses that lower businessman is grocery, has are fresh flower shop etc..
User can generally buy daily necessity near the community lived, therefore can be from positioned at pre-set geography
It is filtered out in each offline businesses in range and the offline businesses of daily necessity is provided, based on quotient under the line for providing daily necessity
Family realizes community mining, improves the accuracy of community mining result.
In the embodiment of the present application, the offline businesses that daily necessity is provided can be service for life class is provided, daily necessities disappear
Take the offline businesses of the daily necessities such as class.For example, life supermarket, greengrocer's, hardware store, grocery, fresh flower shop etc..
Above it is only the preferred content of the offline businesses provided by the embodiments of the present application that daily necessity is provided, specifically will
Which offline businesses can be configured according to their own needs as the offline businesses of life user, inventor is provided, herein not
It limits.
Further, the embodiment of the present application can also filter out monthly average consumption from the offline businesses for providing daily necessity
Number is not less than the offline businesses of pre-set target monthly average consumption number, and then realizes society based on the offline businesses filtered out
Area excavates, to improve a kind for the treatment of effeciency of community mining method provided by the embodiments of the present application.
S202, determine at least one user, user within the scope of pre-set historical time with quotient under at least one line
There are incidence relation, user and offline businesses, there are incidence relation instruction users to exist for any one or more offline businesses in family
There are consumer behaviors for offline businesses；
In the embodiment of the present application, it after determining at least one offline businesses in pre-set geographic range, also needs
To determine that there are the use of incidence relation with the offline businesses within the scope of pre-set historical time for each offline businesses
Family, and then using each user determined as at least one user determined by step S202.Wherein, if a user exists
In an offline businesses, there are consumer behaviors within the scope of historical time, then it is assumed that within the scope of historical time under the user and the line
There are incidence relations by businessman.
In the embodiment of the present application, the incidence relation between at least one identified offline businesses and at least one user
It can be indicated by user-businessman's Consumption relation figure of Fig. 3.Offline businesses' set, offline businesses set are represented referring to Fig. 3, U
In include at least one identified offline businesses, V code user set, include in user set it is identified at least one
User.If there are consumer behaviors in offline businesses by user within the scope of historical time, then it is assumed that the use within the scope of historical time
There are incidence relation, which can be by connecting the line segment of the user He the offline businesses for family and the offline businesses
It indicates, even there are incidence relations between user and offline businesses, then there are a lines between the user and the offline businesses.
In the embodiment of the present application, user as shown in Figure 3-businessman's Consumption relation figure can be determined by point set and line set
Justice:
Point set A={ A1, A2, A3..., An, An+1..., An+m, wherein A1, A2, A3..., AnN offline businesses are characterized,
The n offline businesses are at least one identified offline businesses；An+1..., An+mM user is characterized, the m user is true for institute
At least one fixed user.
Line set E={ eij, wherein eijIndicate user Ai, i=n+1, n+2 ..., n+m and offline businesses Aj, j=1,
Side between 2 ..., n, eij> 0 indicates user AiWith offline businesses AjBetween there are incidence relations, i.e. AiAnd AjBetween there are one
Side.
S203, calculate the degree of correlation at least one user between every two user, the degree of correlation between two users and
Exist simultaneously the quantity of the offline businesses of incidence relation at least one offline businesses with two users within the scope of historical time
It is directly proportional；
In the embodiment of the present application, user two-by-two is carried out to the user at least one user to combine, combination is obtained
Every two user for, calculate the degree of correlation between the two users.For example, at least one user includes 4 users, respectively
For user 1, user 2, user 3 and user 4, the degree of correlation between user 1 and user 2, the phase between user 1 and user 3 are calculated
Guan Du, the degree of correlation between user 1 and user 4, the degree of correlation between user 2 and user 3, the correlation between user 2 and user 4
Degree, the degree of correlation between user 3 and user 4.
For two users, the degree of correlation between the two users and within the scope of historical time under at least one line
It is directly proportional to the quantity that the two users exist simultaneously the offline businesses of incidence relation in businessman.Wherein, if an offline businesses
With each of two users with there is incidence relation per family within the scope of historical time, then it is assumed that this offline businesses is to go through
The offline businesses of incidence relation are existed simultaneously in history time range with the two users.
For example, if at least one offline businesses is respectively offline businesses 1, offline businesses 2, offline businesses 3 and offline businesses
4, at least one user is respectively user 1 and user 2；If user 1 is within the scope of historical time in offline businesses 2 and offline businesses
3 there are consumer behavior, and user 2 has consumption row in offline businesses 2, offline businesses 3 and offline businesses 4 within the scope of historical time
For, then it is assumed that offline businesses 2 exist simultaneously incidence relation with user 1 and user 2 within the scope of historical time, and offline businesses 3 exist
Incidence relation is existed simultaneously with user 1 and user 2 within the scope of historical time；Based on this, determine within the scope of historical time at least
The offline businesses for existing simultaneously incidence relation with user 1 and user 2 in one offline businesses are respectively quotient under offline businesses 2 and line
Family 3, then under the line for existing simultaneously incidence relation at least one offline businesses with user 1 and user 2 within the scope of historical time
The quantity of businessman is 2, based on existing simultaneously pass with user 1 and user 2 at least one offline businesses within the scope of historical time
The quantity 2 of the offline businesses of connection relationship, obtains the degree of correlation between user 1 and user 2, and the degree of correlation is directly proportional to quantity 2.Make
It, can be by quantity 2 as the degree of correlation between user 1 and user 2 for a kind of preferred embodiment of the embodiment of the present application.
In the embodiment of the present application, illustrate if the degree of correlation between two users the high between two users it is practical away from
It is bigger from a possibility that smaller, the two users belong to the same community.
First degree of correlation that the degree of correlation between two S204, amendment users obtains between two users is related to second
Degree, first degree of correlation are the degree of correlation of first user relative to second user in two users, and second degree of correlation is second user
The degree of correlation relative to the first user；
In the embodiment of the present application, after determining the degree of correlation between two users, it is also necessary to be based on historical time model
In enclosing at least one offline businesses with the quantity of the offline businessman of each user-association in two users to the two users it
Between the degree of correlation be modified, with respectively obtain the first user in the two users relative to second user the degree of correlation (for
The degree of correlation is temporarily known as first degree of correlation convenient for distinguishing) and second user relative to first user the degree of correlation (in order to
The degree of correlation is temporarily known as second degree of correlation convenient for distinguishing).Wherein, for the ease of distinguishing, by a use in the two users
Family is known as the first user, another user is known as second user.
S205, based on first degree of correlation and second degree of correlation between every two user at least one user at least one
User carries out community mining and obtains community mining result.
In the embodiment of the present application, it is previously provided with community mining algorithm, for every two user at least one user
For after obtaining first degree of correlation and second degree of correlation between the two users, based on community mining algorithm and obtained
All first degrees of correlation and second degree of correlation carry out community mining at least one user, obtain community mining result.
For example, at least one user includes 4 users, respectively user 1, user 2, user 3 and user 4, used
The degree of correlation of the family 1 relative to user 2, the degree of correlation of the user 2 relative to user 1, the degree of correlation of the user 1 relative to user 3, user
3 degree of correlation relative to user 1, the degree of correlation of the user 1 relative to user 4, the degree of correlation of the user 4 relative to user 1, user 2
Relative to the degree of correlation of user 3, the degree of correlation of the user 3 relative to user 2, the degree of correlation of the user 2 relative to user 4,4 phase of user
For the degree of correlation of user 2, the degree of correlation of the user 3 relative to user 4, after the degree of correlation of the user 4 relative to user 3, based on upper
The degree of correlation stated carries out community mining to user 1, user 2, user 3 and user 4, obtains community mining result.
Fig. 4 is a kind of at least one offline businesses determined in pre-set geographic range provided by the embodiments of the present application
Method flow diagram.
As shown in figure 4, this method comprises:
S401, each first offline businesses in pre-set geographic range are determined；
In the embodiment of the present application, every in the geographic range by being set to after determining pre-set geographic range
A offline businesses using face-to-face gathering functions regard first offline businesses as.
S402, the second offline businesses that offer daily necessity is provided from each first offline businesses；
In the embodiment of the present application, the service that the first offline businesses provide is different, provides the offline businesses of daily necessity more
Therefore the geographical location that the user that there is consumer behavior herein can be embodied filters out from least one first offline businesses and mentions
For the first offline businesses of target for the user that lives, and each the first offline businesses of target are known as second offline businesses.
S403, determine that monthly average consumption number is not less than pre-set target monthly average consumption from each second offline businesses
The third offline businesses of number.
In the embodiment of the present application, after determining each second offline businesses in geographic range, in order to reduce this Shen
Please embodiment provide a kind of community mining method calculation amount, can also further be filtered out from each second offline businesses
Monthly average consumption number is not less than the second offline businesses of target of pre-set target monthly average consumption number, and respectively by each mesh
It marks the second offline businesses and is determined as a third offline businesses.Wherein, identified each third offline businesses may be considered
At least one offline businesses in pre-set geographic range determined in step S201.
For example, if target monthly average consumption number be 100 when, can determine the second offline businesses monthly average consumption number whether
Not less than 100, if the monthly average consumption number of second offline businesses is not less than 100, then it is assumed that second offline businesses are one
Third offline businesses；If the monthly average consumption number of second offline businesses is less than 100, then it is assumed that second offline businesses are not
Three offline businesses.
Fig. 5 is a kind of method flow diagram for calculating the degree of correlation between two users provided by the embodiments of the present application.
As shown in figure 5, this method comprises:
S501, at least one offline businesses is traversed, target offline businesses, target is filtered out from least one offline businesses
Offline businesses are within the scope of historical time with each of two users with there is incidence relation per family；
In the embodiment of the present application, when calculating the degree of correlation of two users, need to be traversed at least one offline businesses, to
Target offline businesses are filtered out in few offline businesses, target offline businesses are within the scope of historical time and in two users
Each of with there are the offline businesses of incidence relation per family.
S502, the degree of correlation between two users is obtained according to the quantity of target offline businesses.
In the embodiment of the present application, when calculating the degree of correlation between two users, at least one offline businesses is traversed, from
After filtering out target offline businesses at least one offline businesses, two users can be generated according to the quantity of target offline businesses
Between the degree of correlation.Wherein, the degree of correlation between the quantity of target offline businesses and the two users of generation is directly proportional.
As a kind of preferred embodiment of the embodiment of the present application, the quantity of the target offline businesses filtered out can be made
For the degree of correlation between two users.
The embodiment of the present application provides a kind of for calculating the formula of the degree of correlation between two users, and the formula is to calculate use
Family AxWith user AyBetween the degree of correlation for be illustrated.Wherein, for calculating the formula packet of the degree of correlation between two users
Formula 1 and formula 2 are included, it is specific as follows.
Formula 1:
Wherein, dxyIndicate user AxWith user AyThe distance between, exj> 0 is indicated
User AxWith offline businesses AjBetween there are a line, eyj> 0 indicates user AyWith offline businesses AjBetween there are a line, I is
Indicative function works as exj> 0 and eyjWhen > 0, I (exj> 0 and eyj> 0)=1.
Formula 1 can be by user AxWith user AyBetween the offline businesses consumed jointly quantity and user AxAnd user
AyCommunity associate, user AxWith user AyBetween the quantity of offline businesses consumed jointly it is more, user AxWith user Ay
The distance between it is closer.
Formula 2:
wxyIndicate user AxWith user AyBetween the degree of correlation.
User AxWith user AyThe distance between closer, user AxWith user AyBetween the degree of correlation it is higher.
It, can be by the quantity of the target offline businesses filtered out as another preferred embodiment of the embodiment of the present application
Product with preset value is as the degree of correlation between two users.
It is above only a kind of relevant preferred embodiment calculated between two users provided by the embodiments of the present application, it is related
The concrete mode of the degree of correlation between two users is calculated, inventor can be configured according to their own needs, not limit herein
It is fixed.
Fig. 6 is that the degree of correlation between a kind of two users of amendment provided by the embodiments of the present application obtains between two users
The method flow diagram of first degree of correlation and second degree of correlation.
As shown in fig. 6, this method comprises:
S601, it determines at least one offline businesses, is deposited within the scope of historical time with the first user in two users
In the first quantity of the offline businesses of incidence relation；
In the embodiment of the present application, the degree of correlation between two users is corrected to obtain the first correlation between two users
When degree and second degree of correlation, for ease of description, a user in the two users is temporarily known as the first user, another
User is known as second user.Wherein, first degree of correlation between two users can be understood as the first user relative to the second use
The degree of correlation at family, second degree of correlation between two users can be understood as the degree of correlation of the second user relative to the first user.
To the degree of correlation between two users of amendment, at least one offline businesses is needed to be traversed for, determines historical time model
In enclosing at least one offline businesses with the first user there are the quantity of the offline businesses of incidence relation (for the ease of distinguishing, temporarily
When the quantity is known as the first quantity)；And it determines within the scope of historical time and is deposited at least one offline businesses with second user
In the quantity (for the ease of distinguishing, the quantity is temporarily known as the second quantity) of the offline businesses of incidence relation.
S602, it determines at least one offline businesses, is deposited within the scope of historical time with the second user in two users
In the second quantity of the offline businesses of incidence relation；
S603, the degree of correlation between two users is corrected according to the first quantity, obtains the first user relative to second user
First degree of correlation；
S604, the degree of correlation between two users is corrected using the second quantity, obtains second user relative to the first user
Second degree of correlation.
For example, if at least one offline businesses is respectively offline businesses 1, offline businesses 2, offline businesses 3 and offline businesses
4, at least one user is respectively user 1 and user 2；If user 1 is within the scope of historical time in offline businesses 2 and offline businesses
3 there are consumer behavior, and user 2 has consumption row in offline businesses 2, offline businesses 3 and offline businesses 4 within the scope of historical time
For, then it is assumed that offline businesses 2 exist simultaneously incidence relation with user 1 and user 2 within the scope of historical time, and offline businesses 3 exist
Incidence relation is existed simultaneously with user 1 and user 2 within the scope of historical time；Thereby determine that within the scope of historical time at least one
The offline businesses for existing simultaneously incidence relation with user 1 and user 2 in offline businesses are respectively offline businesses 2 and offline businesses 3,
Then exist simultaneously the offline businesses of incidence relation at least one offline businesses with user 1 and user 2 within the scope of historical time
Quantity be 2, determine that the degree of correlation of user 1 and user 2 are 2；Correspondingly, determining within the scope of historical time under at least one line
In businessman with user 1 there are the quantity of the offline businesses of incidence relation be 2, at least one offline businesses within the scope of historical time
In with user 2 there are the quantity of the offline businesses of incidence relation be 3, then user 1 relative to user 2 the degree of correlation be 1 He of user
The degree of correlation 2 of user 2 is divided by there are under the line of incidence relation with user 1 at least one offline businesses within the scope of historical time
The obtained result of quantity 2 of businessman；User 2 relative to the degree of correlation 2 that the degree of correlation of user 1 is user 1 and user 2 divided by
There are the quantity 3 of the offline businesses of incidence relation is obtained with user 2 at least one offline businesses within the scope of historical time
As a result.
By taking above-described embodiment as an example, user A is being calculatedxWith user AyBetween the degree of correlation after, user can be calculated
AxRelative to user AyThe degree of correlation, and calculate user AyRelative to user AxThe degree of correlation.
Wherein, user AxRelative to user AyThe calculation of the degree of correlation can pass through formula 3 and formula 4 and realize.
Formula 3: user A is calculatedxConsumption intensityWherein, exj> 0 indicates user AxWith quotient under line
Family AjBetween there are a lines, work as exjWhen > 0, I (exj> 0)=1.
User AxConsumption intensity can be understood as at least one offline businesses within the scope of historical time with user Ax
There are the quantity of the offline businesses of incidence relation.
Formula 4:
Wherein, fxFor user AxRelative to user AyThe degree of correlation.
Wherein, user AyRelative to user AxThe calculation of the degree of correlation can pass through formula 5 and formula 6 and realize.
Formula 5: user A is calculatedyConsumption intensityWherein, eyj> 0 indicates user AyWith quotient under line
Family AjBetween there are a lines, work as eyjWhen > 0, I (eyj> 0)=1.
User AyConsumption intensity can be understood as at least one offline businesses within the scope of historical time with user Ay
There are the quantity of the offline businesses of incidence relation.
Formula 6:
Wherein, fyFor user AyRelative to user AxThe degree of correlation.
Fig. 7 is provided by the embodiments of the present application a kind of based on first degree of correlation between every two user at least one user
Community mining is carried out at least one user with second degree of correlation and obtains the method flow diagram of community mining result.
As shown in fig. 7, this method comprises:
S701, it initializes each user at least one user and belongs to a unique community；
In the embodiment of the present application, based on first degree of correlation and the second phase between every two user at least one user
When Guan Du obtains community mining result at least one user progress community mining, initialize first each at least one user
User belongs to a unique community.
S702, the neighbor user that target user and target user are determined from least one user, in historical time model
At least there are an offline businesses in enclosing, there are incidence relations with target user and neighbor user respectively；
In the embodiment of the present application, at least one user can be traversed, the user currently traversed is determined as target and is used
Family determines the neighbor user of the target user after determining target user from least one user.
As a kind of preferred embodiment of the embodiment of the present application, can determine within the scope of historical time under at least one line
There are the offline businesses of incidence relation with target user in businessman, and use for identified each offline businesses from least one
Determine that there are the users of incidence relation with the offline businesses within the scope of historical time in family, and then will be in identified each user
A neighbor user of each user as the target user in addition to target user.
S703, target user and the current affiliated each community of neighbor user are determined；
In the embodiment of the present application, it determines the current affiliated community of target user and determines each neighbour of the target user
The current affiliated community of user is occupied, using the union of identified each community as the neighbours of the target user and the target user
Community belonging to user is current.
For example, determining mesh if the neighbor user of target user is respectively neighbor user 1, neighbor user 2 and neighbor user 3
Community belonging to mark user is current is community 1, and the current affiliated community of neighbor user 1 is community 2, and neighbor user 2 is current affiliated
Community be community 2, when the community belonging to neighbor user 3 is current is community 1, can determine target user and the target user
Community belonging to neighbor user is current is community 1 and community 2.
S704, each community of relatedness computation that each neighbor user is respectively relative to according to target user weight；
In the embodiment of the present application, it for each community determined in step S703, needs from each of target user
The target base user for currently belonging to the community is determined in a neighbor user, and then adjacent relative to each target based on target user
The degree of correlation for occupying user calculates the total relevance of the community；And then the total relevance based on each community calculates each community
Weight.
It is a kind of phase that each neighbor user is respectively relative to according to target user provided by the embodiments of the present application referring to Fig. 8
Guan Du calculates the method flow diagram of the weight of each community.
As shown in figure 8, this method comprises:
S801, the degree of correlation according to target user relative to each neighbor user for currently belonging to community, calculate community
Total relevance；
In the embodiment of the present application, it for each community determined in step S703, needs from each of target user
The target base user for currently belonging to the community is determined in a neighbor user, determines the target user relative to each target base
The degree of correlation of user, and using the sum of identified each degree of correlation as the total relevance of the community.
For example, determining mesh if the neighbor user of target user is respectively neighbor user 1, neighbor user 2 and neighbor user 3
Community belonging to mark user is current is community 1, and the current affiliated community of neighbor user 1 is community 2, and neighbor user 2 is current affiliated
Community be community 2, when the community belonging to neighbor user 3 is current is community 1, can determine target user and the target user
Community belonging to neighbor user is current is community 1 and community 2.Determine that the neighbor user for currently belonging to community 1 is neighbours' use as a result,
Family 3, the neighbor user for currently belonging to community 2 is neighbor user 1 and neighbor user 2；Then the total relevance of community 1 is target user
Relative to the degree of correlation of neighbor user 3, the total relevance of community 2 is the degree of correlation and mesh of the target user relative to neighbor user 1
Mark sum of the user relative to the degree of correlation of neighbor user 2.
S802, the weight that each community is calculated separately using the total relevance of each community.
In the embodiment of the present application, the sum of the total relevance of each community can be calculated as the target degree of correlation, by community
Weight of the total relevance divided by the result of the target degree of correlation as community.It, can be by the total correlation of community 1 still for above-mentioned
The sum of degree and the total relevance of community 2 is obtained divided by the target degree of correlation by the total relevance of community 1 as the target degree of correlation
As a result the weight as community 1, using the total relevance of community 2 divided by the obtained result of the target degree of correlation as the power of community 2
Weight.
It is above only provided by the embodiments of the present application a kind of each neighbor user to be respectively relative to according to target user
The preferred embodiment of the weight of each community of relatedness computation, the specific implementation of the weight in relation to calculating each community,
Inventor can be configured according to their own needs, it is not limited here.
S705, by Community renewal belonging to target user and neighbor user be each community in the highest community of weight, obtain
To original community mining result；
In the embodiment of the present application, the highest community of weight in community belonging to target user and neighbor user is determined, it will
Community renewal belonging to the neighbor user of target user and target user is the highest community of the weight, obtains original community mining
As a result.It include community belonging to each user at least one user in the original community mining result.
Whether S706, the original community mining result of detection meet preset condition；If original community mining result is unsatisfactory for pre-
If condition returns to step S702；If original community mining result meets preset condition, step S707 is executed；
In the embodiment of the present application, it is preferred that preset condition can be current original community mining result and the nearest n of history
(n is more than or equal to 1 positive integer) secondary obtained original community mining result is identical.
For example, as n=3, if the original community obtained every time in current original community mining result and history nearest 3 times
Result is all the same, then it is assumed that original community mining result meets preset condition (even nearest continuous 4 times obtained original societies
Area's Result is all the same, then it is assumed that original community mining result meets preset condition)；It is on the contrary, then it is assumed that original community mining
As a result it is unsatisfactory for preset condition.
In the embodiment of the present application, if original community mining result be unsatisfactory for preset condition return to step S702 to
The neighbor user of target user and target user are determined in a few user.
As a kind of preferred embodiment of the embodiment of the present application, the mode for traversing at least one user can be with are as follows: judgement
In at least one current user each user be targeted user number it is whether identical；If not identical, continue to traverse
At least one user；If they are the same, then at least one user is traversed again.
For example, at least one user is 3, respectively user 1, user 2 and user 3, if traversing at least one user
The sequence of each user is followed successively by user 1, user 2 and user 3, then as follows to the traversal mode of at least one user: at first time
It goes through to user 1, user 1 is determined as target user；Continue to traverse at least one user, traverse user 2 again, by user 2
It is determined as target user；Continue to traverse at least one user, traverse user 3 again, user 3 is determined as target user；Weight
At least one user is newly traversed, traverses user 1 again, user 1 is determined as target user, continues to traverse at least one use
Family traverses user 2 again, and user 2 is determined as target user, continues to traverse at least one user, traverses user again
3, user 3 is determined as target user；Again at least one user is traversed, traverses user 1 again, user 1 is determined as mesh
Mark user ...
S707, original community mining result is determined as community mining result.
Further, a kind of community discovery method provided by the embodiments of the present application is executing to improve digging efficiency
After completing step S705, it can also determine whether at least one user has had stepped through preset quantity time；If so, can be direct
The original community mining result that history the last time is obtained is as community mining result.Wherein it is determined that at least one user is
If the no mode for having had stepped through preset quantity time includes: time that each user is targeted user at least one user
Number reaches preset quantity, it is determined that at least one user has had stepped through preset quantity time；If existing at least one user
The number for being targeted user is not up to the user of preset quantity, it is determined that at least one user has not traversed preset quantity
Time.
For example, when preset quantity is 100, if each user is targeted the number of user at least one user
Reach 100, it is determined that at least one user, which has stepped through, completes preset quantity time, at this point it is possible to directly by history nearest one
Secondary obtained original community mining result is as community mining result.
It is above only the preferred value of preset quantity provided by the embodiments of the present application, the specific number in relation to preset quantity
Value, inventor can be configured according to their own needs, it is not limited here.
Further, the embodiment of the present application also provides another community mining method flow diagram, specifically refers to Fig. 9.
As shown in figure 9, this method comprises:
S901, at least one offline businesses in pre-set geographic range are determined；
S902, determine at least one user, user within the scope of pre-set historical time with quotient under at least one line
There are incidence relation, user and offline businesses, there are incidence relation instruction users to exist for any one or more offline businesses in family
There are consumer behaviors for offline businesses；
S903, calculate the degree of correlation at least one user between every two user, the degree of correlation between two users and
Exist simultaneously the quantity of the offline businesses of incidence relation at least one offline businesses with two users within the scope of historical time
It is directly proportional；
First degree of correlation that the degree of correlation between two S904, amendment users obtains between two users is related to second
Degree, first degree of correlation are the degree of correlation of first user relative to second user in two users, and second degree of correlation is second user
The degree of correlation relative to the first user；
S905, based on first degree of correlation and second degree of correlation between every two user at least one user at least one
User carries out community mining and obtains community mining as a result, community mining result includes at least one target community；
In the embodiment of the present application, community mining result includes community belonging to each user at least one user, is
Community belonging to user each at least one user is known as at least one target community convenient for distinguishing.
S906, each user for belonging to target community is determined from least one user；
In the embodiment of the present application, for each target community in community mining result, at least one use is determined
The each user for belonging to the target community in family determines whether there is corresponding with the target community from least one offline businesses
Standard offline businesses, if there are incidence relations in an offline businesses and the identified each user for belonging to the target community
The ratio that the quantity of user accounts for the total quantity of the identified each user for belonging to the target community is more than preset ratio, then should
Offline businesses are determined as standard offline businesses；Businessman's basic information based on the standard offline businesses, generates the target community
Label information.
S907, standard offline businesses at least one offline businesses are determined, it is identified to belong to each of target community
The quantity of relevant user accounts for the sum of the identified each user for belonging to target community to standard offline businesses in user
The ratio of amount is more than preset ratio；
S908, businessman's basic information based on standard offline businesses, generate the label information of target community.
In the embodiment of the present application, it is preferred that businessman's basic information may include vendor location information (for example, * * * node
Neighbourhood committee), the information such as Merchant name (for example, lucky branch supermarket * * *).
It, can quotient under each normal line corresponding to target community as a kind of preferred embodiment of the embodiment of the present application
Businessman's basic information of family carries out word cutting, counts word frequency, extracts the forward preset quantity word of word frequency as the target community
Label information.Further, before counting word frequency, may filter out distinguish information without geographical word (for example, street,
Branch etc.).
A kind of community mining method provided by the embodiments of the present application, by generating each target society in community mining result
The label information in area for the user in target community can push away under line in order to user using the label information of target community
Extensively, advertisement is launched, with the success rate for improving below-the-line promotion, advertisement is launched.
Figure 10 is a kind of structural schematic diagram of community mining device provided by the embodiments of the present application.
As shown in Figure 10, which includes:
Offline businesses' determination unit 101, for determining at least one offline businesses in pre-set geographic range；
User's determination unit 102, for determining at least one user, user within the scope of pre-set historical time with
There are incidence relation, user exists with offline businesses to be associated with for any one or more offline businesses at least one offline businesses
Relationship indicates user, and in offline businesses, there are consumer behaviors；
Correlation calculating unit 103, for calculating the degree of correlation at least one user between every two user, two use
The degree of correlation between family and incidence relation is existed simultaneously with two users at least one offline businesses within the scope of historical time
Offline businesses quantity it is directly proportional；
Degree of correlation amending unit 104 obtains first between two users for correcting the degree of correlation between two users
The degree of correlation and second degree of correlation, first degree of correlation are the degree of correlation of first user relative to second user in two users, second
The degree of correlation is the degree of correlation of the second user relative to the first user；
Community mining unit 105, for based on first degree of correlation and second between every two user at least one user
The degree of correlation carries out community mining at least one user and obtains community mining result.
In the embodiment of the present application, it is preferred that offline businesses' determination unit includes:
First offline businesses' determination unit, for determining each first offline businesses in pre-set geographic range；
Second offline businesses' determination unit provides the second of daily necessity for filtering out from each first offline businesses
Offline businesses；
Third offline businesses determination unit, for determining monthly average consumption number not less than pre- from each second offline businesses
The third offline businesses for the target monthly average consumption number being first arranged.
In the embodiment of the present application, it is preferred that correlation calculating unit includes:
Target offline businesses determination unit is sieved from least one offline businesses for traversing at least one offline businesses
Select target offline businesses, target offline businesses are associated with each of two users with existing per family within the scope of historical time
Relationship；
Relatedness computation subelement, for obtaining the degree of correlation between two users according to the quantity of target offline businesses.
In the embodiment of the present application, it is preferred that degree of correlation amending unit includes:
First determination unit, for determining at least one offline businesses, within the scope of historical time and in two users
The first user there are the first quantity of the offline businesses of incidence relation；
Second determination unit, for determining at least one offline businesses, within the scope of historical time and in two users
Second user there are the second quantity of the offline businesses of incidence relation；
First correlation calculating unit obtains first for correcting the degree of correlation between two users according to the first quantity
First degree of correlation of the user relative to second user；
Second correlation calculating unit obtains second for correcting the degree of correlation between two users using the second quantity
Second degree of correlation of the user relative to the first user.
In the embodiment of the present application, it is preferred that community mining unit includes:
First determination unit, for determining the neighbor user of target user and target user from least one user,
At least there are an offline businesses within the scope of historical time, there are incidence relations with target user and neighbor user respectively；
Second determination unit, for determining target user and the current affiliated each community of neighbor user；
Weight calculation unit, each society of relatedness computation for being respectively relative to each neighbor user according to target user
The weight in area；
Original community mining result generation unit, for being each by Community renewal belonging to target user and neighbor user
The highest community of weight in community obtains original community mining result；
Detection unit, for detecting whether original community mining result meets preset condition；
Third determination unit, it is if meeting preset condition for original community mining result, original community mining result is true
It is set to community mining result.
In the embodiment of the present application, it is preferred that weight calculation unit includes:
Total relevance computing unit, for the phase according to target user relative to each neighbor user for currently belonging to community
Guan Du calculates the total relevance of community；
Weight calculation subelement, for calculating separately the weight of each community using the total relevance of each community.
Further, a kind of community mining device provided by the embodiments of the present application further includes label information generation unit, packet
It includes:
4th determination unit, for determining each user for belonging to target community from least one user；
5th determination unit, it is identified to belong to mesh for determining the standard offline businesses at least one offline businesses
Mark community each user in standard offline businesses the quantity of relevant user account for determined by belong to each of target community
The ratio of the total quantity of a user is more than preset ratio；
Label information generates subelement and generates target community for businessman's basic information based on standard offline businesses
Label information.
Further, the embodiment of the present application also provides a kind of computer readable storage medium, the computer-readable storage medium
Computer executable instructions are stored in matter, the computer executable instructions are for executing above-mentioned community mining method.
Optionally, the refinement function of computer executable instructions and extension function can refer to above description.
The application provides a kind of community mining method, apparatus, server and storage medium, determines pre-set geographical model
Enclose at least one interior offline businesses；Determine at least one user, user is within the scope of pre-set historical time and at least
There are incidence relations for any one or more offline businesses in one offline businesses；Every two at least one user is calculated to use
The degree of correlation between family；It is related to second to correct first degree of correlation that the degree of correlation between two users obtains between two users
Degree carries out society at least one user based on first degree of correlation between every two user at least one user and second degree of correlation
It excavates to obtain community mining result in area.The application does not need the geographical location information reported dependent on terminal device and realizes community
It excavates, therefore the geographical location information that community mining result is not reported by terminal device is influenced.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments in the case where not departing from core of the invention thought or scope.Therefore, originally
Invention is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein
Consistent widest scope.
Claims (10)
1. a kind of community mining method characterized by comprising
Determine at least one offline businesses in pre-set geographic range；
Determine at least one user, the user within the scope of pre-set historical time at least one described offline businesses
In any one or more offline businesses there are incidence relation, there are incidence relations to indicate user for user and offline businesses
In offline businesses, there are consumer behaviors；
Calculate the degree of correlation at least one described user between every two user, the degree of correlation between described two users and
Under the line for existing simultaneously incidence relation within the scope of the historical time at least one described offline businesses with described two users
The quantity of businessman is directly proportional；
It corrects the degree of correlation between described two users and obtains first degree of correlation and second degree of correlation between described two users,
First degree of correlation is the degree of correlation of first user relative to second user in described two users, and second degree of correlation is
The degree of correlation of the second user relative to first user；
Based on first degree of correlation between every two user at least one described user and second degree of correlation to it is described at least one
User carries out community mining and obtains community mining result.
2. the method according to claim 1, wherein at least one in the pre-set geographic range of the determination
A offline businesses, comprising:
Determine each first offline businesses in pre-set geographic range；
It is filtered out from each first offline businesses and the second offline businesses of daily necessity is provided；
Determine that monthly average consumption number is not less than pre-set target monthly average consumption number from each second offline businesses
Third offline businesses.
3. the method according to claim 1, wherein calculating the degree of correlation between two users, comprising:
At least one described offline businesses are traversed, target offline businesses are filtered out from least one described offline businesses, it is described
Target offline businesses are within the scope of the historical time with each of two users with there is incidence relation per family；
The degree of correlation between described two users is obtained according to the quantity of the target offline businesses.
4. the method according to claim 1, wherein the degree of correlation between the described two users of amendment obtains
First degree of correlation and second degree of correlation between described two users, comprising:
Determine at least one described offline businesses, within the scope of the historical time with the first user in described two users
There are the first quantity of the offline businesses of incidence relation；
Determine at least one described offline businesses, within the scope of the historical time with the second user in described two users
There are the second quantity of the offline businesses of incidence relation；
The degree of correlation between described two users is corrected according to first quantity, obtains first user relative to described
First degree of correlation of two users；
The degree of correlation between described two users is corrected using second quantity, obtains the second user relative to described
Second degree of correlation of one user.
5. according to the method described in claim 4, it is characterized in that, based between every two user at least one described user
First degree of correlation and second degree of correlation carry out community mining at least one described user and obtain community mining result, comprising:
The neighbor user that target user and the target user are determined from least one user, in the historical time range
Inside at least there are the offline businesses, there are incidence relations with the target user and the neighbor user respectively；
Determine the target user and the current affiliated each community of the neighbor user；
According to the weight for each community of relatedness computation that the target user is respectively relative to each neighbor user；
It is the highest community of weight in each community by Community renewal belonging to the target user and the neighbor user,
Obtain original community mining result；
Detect whether the original community mining result meets preset condition；
If the original community mining result meets preset condition, the original community mining result is determined as community mining knot
Fruit.
6. according to the method described in claim 5, it is characterized in that, described be respectively relative to each institute according to the target user
State the weight of each community of relatedness computation of neighbor user, comprising:
According to the target user relative to the degree of correlation for currently belonging to each of described community neighbor user, described in calculating
The total relevance of community；
The weight of each community is calculated separately using the total relevance of each community.
7. according to the method described in claim 6, it is characterized in that, the community mining result includes at least one target society
Area, this method further include:
The each user for belonging to the target community is determined from least one described user；
Determine the standard offline businesses at least one described offline businesses, the identified each use for belonging to the target community
The identified each user for belonging to the target community is accounted in family to the quantity of the relevant user of the standard offline businesses
Total quantity ratio be more than preset ratio；
Based on businessman's basic information of the standard offline businesses, the label information of the target community is generated.
8. a kind of community mining device characterized by comprising
Offline businesses' determination unit, for determining at least one offline businesses in pre-set geographic range；
User's determination unit, for determining at least one user, the user is within the scope of pre-set historical time and institute
Any one or more offline businesses at least one offline businesses are stated there are incidence relation, user deposits with offline businesses
In incidence relation instruction user, in offline businesses, there are consumer behaviors；
Correlation calculating unit, it is described two for calculating the degree of correlation at least one described user between every two user
The degree of correlation between user and within the scope of the historical time it is same with described two users at least one described offline businesses
When there are the quantity of the offline businesses of incidence relation is directly proportional；
Degree of correlation amending unit obtains first between described two users for correcting the degree of correlation between described two users
The degree of correlation and second degree of correlation, first degree of correlation are correlation of first user relative to second user in described two users
Degree, second degree of correlation are the degree of correlation of the second user relative to first user；
Community mining unit, for related to second based on first degree of correlation between every two user at least one described user
Degree carries out community mining at least one described user and obtains community mining result.
9. a kind of server characterized by comprising at least one processor and at least one processor；The memory is deposited
Program is contained, the processor calls the program of the memory storage, and described program is any for realizing such as claim 1-7
Community mining method described in one.
10. a kind of storage medium, which is characterized in that be stored with computer executable instructions, the calculating in the storage medium
Machine executable instruction requires community mining method described in 1-7 any one for perform claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910702190.4A CN110428001B (en) | 2019-07-31 | 2019-07-31 | Community mining method and device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910702190.4A CN110428001B (en) | 2019-07-31 | 2019-07-31 | Community mining method and device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110428001A true CN110428001A (en) | 2019-11-08 |
| CN110428001B CN110428001B (en) | 2024-04-05 |
Family
ID=68411834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910702190.4A Active CN110428001B (en) | 2019-07-31 | 2019-07-31 | Community mining method and device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110428001B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239127A (en) * | 2021-05-13 | 2021-08-10 | 北方工业大学 | Construction of scientific and technological service association network, identification method of dependency relationship and computer product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130006880A1 (en) * | 2011-06-29 | 2013-01-03 | International Business Machines Corporation | Method for finding actionable communities within social networks |
| CN107093090A (en) * | 2016-10-25 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN107464132A (en) * | 2017-07-04 | 2017-12-12 | 北京三快在线科技有限公司 | A kind of similar users method for digging and device, electronic equipment |
| CN108763359A (en) * | 2018-05-16 | 2018-11-06 | 武汉斗鱼网络科技有限公司 | A kind of usage mining method, apparatus and electronic equipment with incidence relation |
-
2019
- 2019-07-31 CN CN201910702190.4A patent/CN110428001B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130006880A1 (en) * | 2011-06-29 | 2013-01-03 | International Business Machines Corporation | Method for finding actionable communities within social networks |
| CN107093090A (en) * | 2016-10-25 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN107464132A (en) * | 2017-07-04 | 2017-12-12 | 北京三快在线科技有限公司 | A kind of similar users method for digging and device, electronic equipment |
| CN108763359A (en) * | 2018-05-16 | 2018-11-06 | 武汉斗鱼网络科技有限公司 | A kind of usage mining method, apparatus and electronic equipment with incidence relation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239127A (en) * | 2021-05-13 | 2021-08-10 | 北方工业大学 | Construction of scientific and technological service association network, identification method of dependency relationship and computer product |
| CN113239127B (en) * | 2021-05-13 | 2024-02-09 | 北方工业大学 | Construction of science and technology service association network, dependency relationship identification method and computer product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110428001B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110177094A (en) | A kind of user community recognition methods, device, electronic equipment and storage medium | |
| CN104932966B (en) | Detect that application software downloads the method and device of brush amount | |
| CN103580939B (en) | A kind of unexpected message detection method and equipment based on account attribute | |
| CN104199891B (en) | Data processing method and device for thermodynamic chart | |
| WO2012078091A1 (en) | Method and arrangement for ranking users | |
| CN106408353A (en) | Payment method and terminal | |
| WO2001071545A2 (en) | Systems and methods for analyzing network traffic | |
| CN105338540B (en) | A kind of method and terminal of base station data modeling | |
| CN109255632A (en) | A kind of user community recognition methods, device, equipment and medium | |
| CN104965876A (en) | Method and apparatus for carrying out mining on work units of users on basis of position information | |
| CN105447044A (en) | Method and device for determining user relationship | |
| CN110428001A (en) | A kind of community mining method, apparatus, server and storage medium | |
| CN106502607A (en) | A kind of line segment method for deleting and device | |
| CN110019989A (en) | A kind of data processing method and device | |
| CN106227743A (en) | Advertisement target group touches and reaches ratio estimation method and device | |
| CN108304482A (en) | The recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing | |
| CN107145433A (en) | Detect that APP registers the method and system of channel brush list | |
| CN109934590A (en) | A kind of data processing method based on block chain, device, electronic equipment and medium | |
| CN108696457A (en) | Service traffics distribution method based on time window and device, electronic equipment | |
| CN108347355A (en) | A kind of detection method and its equipment of application state | |
| CN110490690A (en) | The marketing strategy optimization method and system of shared bicycle | |
| CN106776993A (en) | Recommend method and system in a kind of path based on temporal constraint activity purpose | |
| CN109523246A (en) | Subscriber payment channel method and device for planning | |
| CN109618323A (en) | Phone call method, device, computer equipment and computer storage medium | |
| CN106887184A (en) | Route update method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |