CN108304482A - The recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing - Google Patents
The recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN108304482A CN108304482A CN201711478995.2A CN201711478995A CN108304482A CN 108304482 A CN108304482 A CN 108304482A CN 201711478995 A CN201711478995 A CN 201711478995A CN 108304482 A CN108304482 A CN 108304482A
- Authority
- CN
- China
- Prior art keywords
- community
- user
- customer relationship
- broker
- vertex
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004590 computer program Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 239000004744 fabric Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
- G06F16/2237—Vectors, bitmaps or matrices
-
- 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)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present invention provides a kind of recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing.This method includes:User in preset time is obtained to post the entity information of daily record and each daily record, customer relationship network is built according to the entity information of all daily records, customer relationship network is made of vertex table and Bian Biao, vertex table is the set on vertex, set when table is, each entity information is a vertex, incidence relation of the side between user identifier and other entity informations;Customer relationship network is divided using community discovery algorithm, obtains community discovery as a result, community discovery result is community's mark on each vertex in customer relationship network;The broker in the publication user of all daily records is identified according to preset rules and community discovery result.To improve recognition accuracy and recognition efficiency.
Description
Technical field
The present embodiments relate to the recognition methods of field of communication technology more particularly to a kind of broker and device, electronics
Equipment and readable storage medium storing program for executing.
Background technology
Nowadays, house to let information, second-hand house information and used car information etc. are published in all kinds of webpages or related answer
With in program (APP), house to let information or second-hand house information etc. can be private publications, can also be broker (in i.e.
It is situated between) publication.
By taking house to let information as an example, the hair of the house to let information how is identified from the house to let information of publication
Cloth user is broker, and a kind of existing recognition methods of broker is:If a user, which issues source of houses quantity, is more than predetermined threshold value
And the user is issuing house to let information more than N number of region, N is preset value, then judges that the user is broker.However,
User needs user to fill in user identity when issuing house to let information, and some private user and filling in identity at random causes
Information is inaccurate, and also some broker's active concealment broker identity is to attract flow.
Therefore, broker of the part using multiple accounts publication source of houses can be missed according to above-mentioned recognition methods, meanwhile, by
Setting value N in source of houses distributed areas is difficult to reasonable set so that not high for the identification accuracy of broker.
Invention content
The embodiment of the present invention provides a kind of recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing, with
Improve the accuracy of broker's identification.
In a first aspect, the embodiment of the present invention provides a kind of recognition methods of broker, including:
User in preset time is obtained to post the entity information of daily record and each daily record;
Customer relationship network is built according to the entity information of all daily records, the customer relationship network is by vertex table and Bian Biao
It constitutes, vertex table is the set on vertex, and the set when table is, each entity information is a vertex, and side is user identifier and its
Incidence relation between its entity information;
Customer relationship network is divided using community discovery algorithm, obtains community discovery as a result, community discovery result
For community's mark on each vertex in the customer relationship network;
The broker in the publication user of all daily records is identified according to preset rules and community discovery result.
Optionally, described that customer relationship network is built according to the entity information of all daily records, including:
Vertex table and Bian Biao are determined according to the entity information of all daily records, and vertex table and Bian Biao are stored in HDFS;
Using vertex table and Bian Biao as input, customer relationship network is built by Spark GraphX, and customer relationship
Network is loaded into memory in graph form.
Optionally, described that customer relationship network is divided using community discovery algorithm, community discovery is obtained as a result, packet
It includes:
Using the customer relationship network as input, community discovery algorithm is run on Spark GraphX, obtains community
It was found that result.
Optionally, the manager in the publication user that all daily records are identified according to preset rules and community discovery result
People, including:
The target community for determining to meet preset condition according to community discovery result;
If the number of users for issuing house property information in the target community is more than N, judge to issue in the target community
The user of house property information is broker, and N is default positive integer.
Optionally, the target community for determining to meet preset condition, including:
Statistics belongs to the number of users of same community, and there are one communities to identify by each user, and community identifies identical use
Family belongs to same community;
Determine that the community that the number of users for belonging to same community is more than the first predetermined threshold value is the target community;
Alternatively,
Statistics belongs to the source of houses number summation that all users of same community are issued;
The source of houses number summation that the determining all users for belonging to same community are issued is more than the community of the second predetermined threshold value
For the target community.
Second aspect, the embodiment of the present invention provide a kind of identification device of broker, including:
Acquisition module is posted the entity information of daily record and each daily record for obtaining the user in preset time;
Module is built, for building customer relationship network, the customer relationship network according to the entity information of all daily records
It is made of vertex table and Bian Biao, vertex table is the set on vertex, and the set when table is, each entity information is a vertex, side
For the incidence relation between user identifier and other entity informations;
Division module, for being divided to customer relationship network using community discovery algorithm, obtain community discovery as a result,
Community discovery result is community's mark on each vertex in the customer relationship network;
Identification module, the warp in publication user for identifying all daily records according to preset rules and community discovery result
Discipline people.
Optionally, the structure module is used for:
Vertex table and Bian Biao are determined according to the entity information of all daily records, and vertex table and Bian Biao are stored in HDFS;
Using vertex table and Bian Biao as input, customer relationship network is built by Spark GraphX, and customer relationship
Network is loaded into memory in graph form.
Optionally, the division module is used for:
Using the customer relationship network as input, community discovery algorithm is run on Spark GraphX, obtains community
It was found that result.
Optionally, the identification module includes:
Determination unit, the target community for determining to meet preset condition according to community discovery result;
Judging unit judges the mesh when number of users for issuing house property information in the target community is more than N
The user for marking publication house property information in community is broker, and N is default positive integer.
Optionally, the determination unit is used for:
Statistics belongs to the number of users of same community, and there are one communities to identify by each user, and community identifies identical use
Family belongs to same community;
Determine that the community that the number of users for belonging to same community is more than the first predetermined threshold value is the target community;
Alternatively,
Statistics belongs to the source of houses number summation that all users of same community are issued;
The source of houses number summation that the determining all users for belonging to same community are issued is more than the community of the second predetermined threshold value
For the target community.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, including:
Memory, for storing program instruction;
Processor, for calling and execute the program instruction in the memory, to realize the broker of first aspect
Recognition methods.
Fourth aspect, the embodiment of the present invention provide a kind of readable storage medium storing program for executing, computer are stored in readable storage medium storing program for executing
Program, when at least one processor of the identification device of broker executes the computer program, the identification device of broker is held
The recognition methods of the broker of row first aspect.
5th aspect, the embodiment of the present invention provide a kind of program product, which includes computer program, the calculating
Machine program is stored in readable storage medium storing program for executing.At least one processor of the identification device of broker can be from readable storage medium storing program for executing
The computer program is read, at least one processor executes the computer program and the identification device of broker is made to implement first party
The recognition methods of the broker in face.
The recognition methods and device of broker provided in an embodiment of the present invention, electronic equipment and readable storage medium storing program for executing, pass through
It obtains user in preset time to post the entity information of daily record and each daily record, to user identifier, telephone number and hair
The user subject information of multiple dimensions such as electronic equipment used in daily record is integrated, and using entity information (vertex table) and is used
The incidence relation (side table) that family identifies between entity information models customer relationship network, can utilize multiple dimensions
Data are analyzed, and are finally divided to customer relationship network using community discovery algorithm, obtain community discovery as a result, in turn
The broker in the publication user of all daily records is identified according to preset rules and community discovery result, can accurately find one
The broker of the more account publication sources of houses of people, improves recognition accuracy and recognition efficiency.
Description of the drawings
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 technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some embodiments of bright embodiment, for those of ordinary skill in the art, without having to pay creative labor,
Other drawings may also be obtained based on these drawings.
Fig. 1 is a kind of flow chart of the recognition methods of broker provided in an embodiment of the present invention;
Fig. 2 is the flow chart of the recognition methods of another broker provided in an embodiment of the present invention;
Fig. 3 is the flow chart of the recognition methods of another broker provided in an embodiment of the present invention;
Fig. 4 is a kind of structural schematic diagram of the identification device of broker provided in an embodiment of the present invention;
Fig. 5 is the structural schematic diagram of the identification device of another broker provided in an embodiment of the present invention;
Fig. 6 is the structural schematic diagram of the identification device of another broker provided in an embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the embodiment of the present invention, instead of all the embodiments.Based on the embodiment in the embodiment of the present invention, this field
The every other embodiment that those of ordinary skill is obtained without making creative work, belongs to implementation of the present invention
The range of example protection.
The recognition methods of existing broker is by judging that user's publication source of houses quantity is more than predetermined threshold value and user exists
House to let information is issued more than N number of region, then judges that the user is broker, but above-mentioned recognition methods can miss a part
The broker of the source of houses is issued using multiple accounts, while the setting value N of source of houses distributed areas is difficult to reasonable set, identification it is accurate
Property is not high.To improve the accuracy of broker's identification, in the application by obtain the user in preset time period post daily record and
The entity information of each daily record builds customer relationship network according to the entity information of each daily record, utilizes Spark
GraphX and community discovery algorithm divide customer relationship network, obtain community discovery as a result, in turn according to preset rules
The broker in the publication user of all daily records is identified with community discovery result, accurately finds the more account publication sources of houses of a people
Broker, improve recognition accuracy and recognition efficiency.The technical solution of the application is described in detail below in conjunction with the accompanying drawings.
First, the part term in the embodiment of the present invention is explained below, in order to those skilled in the art
Understand.
1, community discovery:What community was reflected is locality characteristic and its mutual pass of the individual behavior in network
Connection relationship is studied the community in network to understanding that it is vital that the structure and function of whole network plays the role of, and can be helped
It helps analysis and predicts the interactive relation between whole network each element.
2, Fast-unfolding algorithms:It is a kind of community discovery algorithm, based on the theory of modularity optimization, will inputs
Diagram data be divided into a large amount of community, the mutual close association of user in the same community, community discovery algorithm to figure
In each node assign a mark (ID), identical ID shows it in the same community.
3、Spark GraphX:Spark GraphX are a distributed figure processing frames, and Spark GraphX are based on
Spark platforms, which provide, to calculate figure and schemes to excavate succinct easy-to-use and colourful interface, greatly facilitates to distribution
Scheme the demand of processing.It is well known that have many relation chains in social networks between men, such as Twitter, Facebook,
Microblogging, wechat, these are all the places that big data generates, and figure is required for calculate, and the processing of present figure is substantially distributed
Figure processing, and not single machine is handled, Spark GraphX are since bottom is handled based on Spark, so being exactly naturally one
A distributed figure processing system.The distribution of figure or parallel processing are this figure to be split into many subgraphs in fact, so
These subgraphs are calculated respectively afterwards, calculating when can distinguish iteration and carry out calculating stage by stage, i.e., carried out simultaneously to figure
Row calculates.
Fig. 1 is a kind of flow chart of the recognition methods of broker provided in an embodiment of the present invention, the execution master of the present embodiment
Body can be the equipment of any recognition methods execute with broker, and optionally, which can be processor, such as
Shown in Fig. 1, the method for the present embodiment may include:
S101, it obtains user in preset time and posts daily record and the entity information of each daily record.
Specifically, preset time is, for example, one month, three months or half a year etc..Entity information is for example marked including user
Know, electronic device identification used in telephone number and hair daily record, electronics used in user identifier, telephone number and hair daily record
Device identification is an entity information, and entity information can also be other information related to user, such as payment information, payment
Information is using wechat payment, Alipay payment or bank card payment etc..User identifier therein is sent out for indicating user identity
Electronic equipment used in daily record includes the electronic equipments such as mobile phone, computer, handheld computer.
S102, customer relationship network is built according to the entity information of all daily records, customer relationship network is by vertex table and side
Table constitute, vertex table be vertex set, while table be while set, each entity information be a vertex, side be user identifier with
Incidence relation between other entity informations.
Specifically, each daily record is corresponding with user identifier, telephone number and sends out the entities such as electronic equipment used in daily record
Information, each entity information are a vertex, and the incidence relation between user identifier and other entity informations is side, according to all days
The entity information of will obtain while set (i.e. table while) and vertex set (i.e. vertex table), built according to vertex table and Bian Biao
Customer relationship network.
S103, customer relationship network is divided using community discovery algorithm, obtains community discovery as a result, community discovery
As a result it is community's mark on each vertex in customer relationship network.
Wherein, community discovery algorithm is Fast-unfolding algorithms, and Fast-unfolding algorithms are by the figure of input
Data are divided into a large amount of community, and in the present embodiment, customer relationship network is the diagram data inputted, more after exporting as division
A community and community discovery are as a result, the mutual close association of user in the same community, Fast-unfolding algorithms pair
Each vertex in customer relationship network assigns community's mark (ID), and community discovery result is every in customer relationship network
Community's mark on one vertex, the user of identical ID is in the same community.
Optionally, after obtaining community discovery result, by community discovery result deposit distributed file system (Hadoop
Distributed File System, HDFS), can be by community discovery result persistence by being stored in HDFS, convenient follow-up point
Analysis is handled.
S104, the broker issued in user that all daily records are identified according to preset rules and community discovery result.
Specifically, preset rules can be set according to actual needs, and in the present embodiment, S104 can specifically include:
S1041, the target community for determining to meet preset condition according to community discovery result.
Wherein, optionally, determining to meet the target community of preset condition according to community discovery result, there are two types of can implement
Mode:
As a kind of enforceable mode, statistics belongs to the number of users of same community, and there are one communities by each user
Mark, community identify identical user and belong to same community, determine that the number of users for belonging to same community is more than the first default threshold
The community of value is the target community.For example, the first predetermined threshold value is 5, the number of users for belonging to same community of statistics is 7,
Then the community is target community.
As another enforceable mode, it is total that statistics belongs to the source of houses number that all users of same community are issued
With determine that it is described to belong to the source of houses number summation that all users of same community are issued to be more than the community of the second predetermined threshold value
Target community.For example, user A, user B and user C belong to same community, the source of houses that user A is issued is 3 sets, and user B is sent out
The source of houses of cloth is 5 sets, and the source of houses that user C is issued is 5 sets, and the source of houses number summation of user A, user B and user C are 3+5+5
=13 sets, the second predetermined threshold value is 10, then the community is target community.
If the number of users for issuing house property information in S1042, the target community is more than N, the target community is judged
The user of middle publication house property information is broker, and N is default positive integer.
The recognition methods of broker provided in this embodiment is posted daily record and every by obtaining user in preset time
The entity information of one daily record builds customer relationship network, customer relationship network therein according to the entity information of all daily records
It is made of vertex table and Bian Biao, each entity information is a vertex, side being associated between user identifier and other entity informations
Relationship divides customer relationship network using community discovery algorithm, obtains community discovery as a result, finally according to preset rules
The broker in the publication user of all daily records is identified with community discovery result.By to user identifier, telephone number and hair
The user subject information of multiple dimensions such as electronic equipment used in daily record is integrated, and using entity information (vertex table) and is used
The incidence relation (side table) that family identifies between entity information models customer relationship network, can utilize multiple dimensions
Data are analyzed, and are finally divided to customer relationship network using community discovery algorithm, obtain community discovery as a result, in turn
The broker in the publication user of all daily records is identified according to preset rules and community discovery result, can accurately find one
The broker of the more account publication sources of houses of people, improves recognition accuracy and recognition efficiency.
Fig. 2 is the flow chart of the recognition methods of another broker provided in an embodiment of the present invention, as shown in Fig. 2, this reality
The method for applying example may include:
S201, it obtains user in preset time and posts daily record and the entity information of each daily record.
Specifically, preset time is, for example, one month, three months or half a year etc..User identifier, telephone number and Fa
Electronic device identification used in will is an entity information, and entity information can also be other information related to user,
In user identifier for indicating user identity, it includes the electricity such as mobile phone, computer, handheld computer to generate electronic equipment used in daily record
Sub- equipment.
S202, vertex table and Bian Biao are determined according to the entity information of all daily records, vertex table and Bian Biao is stored in HDFS.
Wherein, vertex table is the set on vertex, and the set when table is, each entity information is a vertex, while being user
Incidence relation between mark and other entity informations.Memory is larger shared by vertex table and Bian Biao, and vertex table and Bian Biao are stored in
HDFS, subsequently to be handled.
S203, using vertex table and Bian Biao as input, customer relationship network is built by Spark GraphX, and user
Relational network is loaded into memory in graph form.
S204, using customer relationship network as input, on Spark GraphX run community discovery algorithm, obtain community
It was found that as a result, community discovery result is community's mark on each vertex in customer relationship network.
S205, the target community for determining to meet preset condition according to community discovery result.
Specifically, there are two types of enforceable modes:
One, statistics belongs to the number of users of same community, and there are one communities to identify by each user, and community's mark is identical
User belongs to same community, determines that the community that the number of users for belonging to same community is more than the first predetermined threshold value is target community.
Two, statistics belongs to the source of houses number summation that all users of same community are issued, and determination belongs to same community
The community that the source of houses number summation that all users are issued is more than the second predetermined threshold value is target community.
If the number of users for issuing house property information in S206, target community is more than N, judge to issue house property in target community
The user of information is broker, and N is default positive integer.
The recognition methods of broker provided in this embodiment is posted daily record and every by obtaining user in preset time
The entity information of one daily record determines vertex table and Bian Biao according to the entity information of all daily records, is made with vertex table and Bian Biao
Customer relationship network is built by Spark GraphX for input, community discovery algorithm is run on Spark GraphX to user
Relational network is divided, and obtains community discovery as a result, finally the target community for meeting preset condition is determined, if target community
The number of users of middle publication house property information is more than N, then judges that it is broker that the user of house property information is issued in target community.Pass through
The user subject information of multiple dimensions such as electronic equipment used in user identifier, telephone number and hair daily record is integrated,
Customer relationship network is modeled using vertex table and Bian Biao, can be analyzed using the data of multiple dimensions, finally be made
Customer relationship network is divided with community discovery algorithm, obtains community discovery as a result, true according to community discovery result in turn
The target community for meeting preset condition is made, broker user is identified from target community, can accurately find that a people is more
Account issues the broker of the source of houses, improves recognition accuracy and recognition efficiency.
A specific embodiment is used below, and the technical solution of embodiment of the method shown in Fig. 1 and Fig. 2 is carried out specifically
It is bright.
Fig. 3 is the flow chart of the recognition methods of another broker provided in an embodiment of the present invention, as shown in figure 3, this reality
The method for applying example may include:
S301, it obtains user in preset time and posts daily record and the entity information of each daily record, entity information packet
It includes user identifier, telephone number and sends out electronic device identification used in daily record.
S302, vertex table and Bian Biao are determined according to the entity information of all daily records.
S303, vertex table and Bian Biao are stored in HDFS.
S304, using vertex table and Bian Biao as input, customer relationship network is built by Spark GraphX, and user
Relational network is loaded into memory in graph form.
S305, using customer relationship network as input, on Spark GraphX run community discovery algorithm, obtain community
It was found that as a result, community discovery result is community's mark on each vertex in customer relationship network.
S306, community discovery result is stored in HDFS.
S307, the target community for determining to meet preset condition according to community discovery result.
Specifically, there are two types of enforceable modes:
One, statistics belongs to the number of users of same community, and there are one communities to identify by each user, and community's mark is identical
User belongs to same community, determines that the community that the number of users for belonging to same community is more than the first predetermined threshold value is target community.
Two, statistics belongs to the source of houses number summation that all users of same community are issued, and determination belongs to same community
The community that the source of houses number summation that all users are issued is more than the second predetermined threshold value is target community.
The number of users that house property information is issued in S308, target community is more than N, then judges to issue house property letter in target community
The user of breath is broker, and N is default positive integer.
Fig. 4 is a kind of structural schematic diagram of the identification device of broker provided in an embodiment of the present invention, as shown in figure 4, this
The device of embodiment may include:Acquisition module 11, structure module 12, division module 13 and identification module 14, wherein
The user that acquisition module 11 is used to obtain in preset time posts the entity information of daily record and each daily record.
It builds module 12 to be used to build customer relationship network according to the entity information of all daily records, customer relationship network is by pushing up
Point table and Bian Biao are constituted, and vertex table is the set on vertex, and the set when table is, each entity information is a vertex, Bian Weiyong
Family identifies the incidence relation between other entity informations.
Division module 13 obtains community discovery knot for being divided to customer relationship network using community discovery algorithm
Fruit, community discovery result are community's mark on each vertex in customer relationship network.
Identification module 14 is used to be identified according to preset rules and community discovery result in the publication user of all daily records
Broker.
Optionally, structure module 12 is used for:Vertex table and Bian Biao are determined according to the entity information of all daily records, by vertex
Table and Bian Biao are stored in HDFS;Using vertex table and Bian Biao as input, customer relationship network, and handle are built by Spark GraphX
Customer relationship network is loaded into memory in graph form.
Optionally, division module 13 is used for:Using customer relationship network as input, community is run on Spark GraphX
It was found that algorithm, obtains community discovery result.
The device of the present embodiment can be used for executing the technical solution of embodiment of the method shown in Fig. 1 or Fig. 2, realize former
Manage similar, details are not described herein again.
The identification device of broker provided in this embodiment is posted daily record and every by obtaining user in preset time
The entity information of one daily record, to the use of multiple dimensions such as electronic equipment used in user identifier, telephone number and hair daily record
Family entity information is integrated, and incidence relation (side of the entity information (vertex table) between user identifier and entity information is used
Table) customer relationship network is modeled, it can be analyzed using the data of multiple dimensions, finally use community discovery algorithm
Customer relationship network is divided, obtains community discovery as a result, being identified in turn according to preset rules and community discovery result
Broker in the publication user of all daily records can accurately have found the broker of the more account publication sources of houses of a people, improve
Recognition accuracy and recognition efficiency.
Fig. 5 is the structural schematic diagram of the identification device of another broker provided in an embodiment of the present invention, as shown in figure 5,
On the basis of the device device shown in Fig. 4 of the present embodiment, further, identification module 14 includes:Determination unit 141 and judgement
Unit 142, determination unit 141 are used to determine the target community for meeting preset condition according to community discovery result;Judging unit
When 142 number of users for being used to issue house property information in target community are more than N, publication house property information in target community is judged
User is broker, and N is default positive integer.
Further, it is determined that unit 141 is used for:Statistics belongs to the number of users of same community, and there are one each users
Community identifies, and community identifies identical user and belongs to same community, and it is pre- to determine that the number of users for belonging to same community is more than first
If the community of threshold value is target community.
Alternatively, statistics belongs to the source of houses number summation that all users of same community are issued, determination belongs to same community
The source of houses number summation issued of all users to be more than the community of the second predetermined threshold value be target community.
The device of the present embodiment can be used for executing the technical solution of embodiment of the method shown in Fig. 1 or Fig. 2, realize former
Manage similar, details are not described herein again.
The identification device of broker provided in this embodiment is posted daily record and every by obtaining user in preset time
The entity information of one daily record determines vertex table and Bian Biao according to the entity information of all daily records, is made with vertex table and Bian Biao
Customer relationship network is built by Spark GraphX for input, community discovery algorithm is run on Spark GraphX to user
Relational network is divided, and obtains community discovery as a result, finally the target community for meeting preset condition is determined, if target community
The number of users of middle publication house property information is more than N, then judges that it is broker that the user of house property information is issued in target community.Pass through
The user subject information of multiple dimensions such as electronic equipment used in user identifier, telephone number and hair daily record is integrated,
Customer relationship network is modeled using vertex table and Bian Biao, can be analyzed using the data of multiple dimensions, finally be made
Customer relationship network is divided with community discovery algorithm, obtains community discovery as a result, true according to community discovery result in turn
The target community for meeting preset condition is made, broker user is identified from target community, can accurately find that a people is more
Account issues the broker of the source of houses, improves recognition accuracy and recognition efficiency.
Drawing for function module can be carried out to the identification device of broker according to above method example in the embodiment of the present invention
Point, for example, can correspond to each function divides each function module, two or more functions can also be integrated in one
In a processing module.The form that hardware had both may be used in above-mentioned integrated module is realized, software function module can also be used
Form is realized.It should be noted that be to the division of module in each embodiment of the embodiment of the present invention it is schematical, it is only a kind of
Division of logic function, formula that in actual implementation, there may be another division manner.
Fig. 6 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention, as shown in fig. 6, the present embodiment
Electronic equipment may include:Memory 21 and processor 22,
Memory 21, for storing program instruction, which can be flash (flash memory).
Processor 22, for calling and executing the program instruction in memory, to realize broker shown in fig. 1 or fig. 2
Recognition methods in each step.The specific associated description that may refer in previous methods embodiment.
Optionally, memory 21 can also be that memory 21 is integrated with processor 22 either independent.
The embodiment of the present invention also provides a kind of readable storage medium storing program for executing, and computer program is stored in readable storage medium storing program for executing, when
When at least one processor of the identification device of broker executes the computer program, the identification device of broker executes above-mentioned side
The recognition methods of broker in method embodiment.
The embodiment of the present invention also provides a kind of program product, which includes computer program, the computer program
It is stored in readable storage medium storing program for executing.At least one processor of the identification device of broker can be read from readable storage medium storing program for executing should
Computer program, at least one processor execute the computer program and the identification device of broker are made to implement above method implementation
The recognition methods of broker in example.
One of ordinary skill in the art will appreciate that:Realize that all or part of step of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer read/write memory medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned includes:ROM, RAM, magnetic disc or
The various media that can store program code such as person's CD.
Finally it should be noted that:The above various embodiments is only to illustrate the technical solution of the embodiment of the present invention, rather than to it
Limitation;Although the embodiment of the present invention is described in detail with reference to foregoing embodiments, those skilled in the art
It should be understood that:Its still can with technical scheme described in the above embodiments is modified, either to which part or
All technical features carries out equivalent replacement;And these modifications or replacements, it does not separate the essence of the corresponding technical solution this hair
The range of bright each embodiment technical solution of embodiment.
Claims (12)
1. a kind of recognition methods of broker, which is characterized in that including:
User in preset time is obtained to post the entity information of daily record and each daily record;
Customer relationship network is built according to the entity information of all daily records, the customer relationship network is by vertex table and Bian Biao structures
At the set that, vertex table is vertex, the set when table is, each entity information is a vertex, side be user identifier with it is other
Incidence relation between entity information;
Customer relationship network is divided using community discovery algorithm, obtains community discovery as a result, community discovery result is institute
State community's mark on each vertex in customer relationship network;
The broker in the publication user of all daily records is identified according to preset rules and community discovery result.
2. according to the method described in claim 1, it is characterized in that, described build user pass according to the entity information of all daily records
It is network, including:
Vertex table and Bian Biao are determined according to the entity information of all daily records, and vertex table and Bian Biao are stored in HDFS;
Using vertex table and Bian Biao as input, customer relationship network is built by Spark GraphX, and customer relationship network
It is loaded into memory in graph form.
3. method according to claim 1 or 2, which is characterized in that described to use community discovery algorithm to customer relationship net
Network is divided, and obtains community discovery as a result, including:
Using the customer relationship network as input, community discovery algorithm is run on Spark GraphX, obtains community discovery
As a result.
4. method according to claim 1 or 2, which is characterized in that described to be known according to preset rules and community discovery result
Do not go out the broker in the publication user of all daily records, including:
The target community for determining to meet preset condition according to community discovery result;
If the number of users for issuing house property information in the target community is more than N, judge to issue house property in the target community
The user of information is broker, and N is default positive integer.
5. according to the method described in claim 4, it is characterized in that, described determine to meet default item according to community discovery result
The target community of part, including:
Statistics belongs to the number of users of same community, and there are one communities to identify by each user, and community identifies identical user and belongs to
In same community;
Determine that the community that the number of users for belonging to same community is more than the first predetermined threshold value is the target community;
Alternatively,
Statistics belongs to the source of houses number summation that all users of same community are issued;
It is institute that the source of houses number summation that the determining all users for belonging to same community are issued, which is more than the community of the second predetermined threshold value,
State target community.
6. a kind of identification device of broker, which is characterized in that including:
Acquisition module is posted the entity information of daily record and each daily record for obtaining the user in preset time;
Module is built, for building customer relationship network according to the entity information of all daily records, the customer relationship network is by pushing up
Point table and Bian Biao are constituted, and vertex table is the set on vertex, and the set when table is, each entity information is a vertex, Bian Weiyong
Family identifies the incidence relation between other entity informations;
Division module obtains community discovery as a result, community for being divided to customer relationship network using community discovery algorithm
It was found that result is community's mark on each vertex in the customer relationship network;
Identification module, the manager in publication user for identifying all daily records according to preset rules and community discovery result
People.
7. device according to claim 6, which is characterized in that the structure module is used for:
Vertex table and Bian Biao are determined according to the entity information of all daily records, and vertex table and Bian Biao are stored in HDFS;
Using vertex table and Bian Biao as input, customer relationship network is built by Spark GraphX, and customer relationship network
It is loaded into memory in graph form.
8. the device described according to claim 6 or 7, which is characterized in that the division module is used for:
Using the customer relationship network as input, community discovery algorithm is run on Spark GraphX, obtains community discovery
As a result.
9. the device described according to claim 6 or 7, which is characterized in that the identification module includes:
Determination unit, the target community for determining to meet preset condition according to community discovery result;
Judging unit judges the target society when number of users for issuing house property information in the target community is more than N
The user that house property information is issued in area is broker, and N is default positive integer.
10. device according to claim 9, which is characterized in that the determination unit is used for:
Statistics belongs to the number of users of same community, and there are one communities to identify by each user, and community identifies identical user and belongs to
In same community;
Determine that the community that the number of users for belonging to same community is more than the first predetermined threshold value is the target community;
Alternatively,
Statistics belongs to the source of houses number summation that all users of same community are issued;
It is institute that the source of houses number summation that the determining all users for belonging to same community are issued, which is more than the community of the second predetermined threshold value,
State target community.
11. a kind of electronic equipment, which is characterized in that including:
Memory, for storing program instruction;
Processor, for calling and executing the program instruction in the memory, to realize described in any one of Claims 1 to 5
Broker recognition methods.
12. a kind of readable storage medium storing program for executing, which is characterized in that be stored with computer program in the readable storage medium storing program for executing, work as manager
When at least one processor of the identification device of people executes the computer program, the identification device perform claim requirement of broker
The recognition methods of 1~5 any one of them broker.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711478995.2A CN108304482A (en) | 2017-12-29 | 2017-12-29 | The recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711478995.2A CN108304482A (en) | 2017-12-29 | 2017-12-29 | The recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108304482A true CN108304482A (en) | 2018-07-20 |
Family
ID=62868233
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711478995.2A Pending CN108304482A (en) | 2017-12-29 | 2017-12-29 | The recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108304482A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110222484A (en) * | 2019-04-28 | 2019-09-10 | 五八有限公司 | A kind of method for identifying ID, device, electronic equipment and storage medium |
CN110633381A (en) * | 2018-12-25 | 2019-12-31 | 北京时光荏苒科技有限公司 | Method and device for identifying false house source, storage medium and electronic equipment |
CN110990727A (en) * | 2019-11-01 | 2020-04-10 | 贝壳技术有限公司 | Broker information display method, device, storage medium and equipment |
CN111209512A (en) * | 2020-01-03 | 2020-05-29 | 北京同邦卓益科技有限公司 | User identification method, device and equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103731284A (en) * | 2012-10-11 | 2014-04-16 | 腾讯科技(深圳)有限公司 | Method and system for correlating a plurality of network accounts |
CN106874931A (en) * | 2016-12-30 | 2017-06-20 | 东软集团股份有限公司 | User portrait grouping method and device |
CN106960143A (en) * | 2017-03-23 | 2017-07-18 | 网易(杭州)网络有限公司 | The recognition methods of user account and device, storage medium, electronic equipment |
CN107404408A (en) * | 2017-08-30 | 2017-11-28 | 北京邮电大学 | A kind of virtual identity association recognition methods and device |
CN107438050A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Identify the method and system of the potential malicious user of website |
-
2017
- 2017-12-29 CN CN201711478995.2A patent/CN108304482A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103731284A (en) * | 2012-10-11 | 2014-04-16 | 腾讯科技(深圳)有限公司 | Method and system for correlating a plurality of network accounts |
CN107438050A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Identify the method and system of the potential malicious user of website |
CN106874931A (en) * | 2016-12-30 | 2017-06-20 | 东软集团股份有限公司 | User portrait grouping method and device |
CN106960143A (en) * | 2017-03-23 | 2017-07-18 | 网易(杭州)网络有限公司 | The recognition methods of user account and device, storage medium, electronic equipment |
CN107404408A (en) * | 2017-08-30 | 2017-11-28 | 北京邮电大学 | A kind of virtual identity association recognition methods and device |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110633381A (en) * | 2018-12-25 | 2019-12-31 | 北京时光荏苒科技有限公司 | Method and device for identifying false house source, storage medium and electronic equipment |
CN110633381B (en) * | 2018-12-25 | 2023-04-07 | 北京时光荏苒科技有限公司 | Method and device for identifying false house source, storage medium and electronic equipment |
CN110222484A (en) * | 2019-04-28 | 2019-09-10 | 五八有限公司 | A kind of method for identifying ID, device, electronic equipment and storage medium |
CN110222484B (en) * | 2019-04-28 | 2023-05-23 | 五八有限公司 | User identity recognition method and device, electronic equipment and storage medium |
CN110990727A (en) * | 2019-11-01 | 2020-04-10 | 贝壳技术有限公司 | Broker information display method, device, storage medium and equipment |
CN110990727B (en) * | 2019-11-01 | 2024-05-10 | 贝壳技术有限公司 | Broker information display method, device, storage medium and equipment |
CN111209512A (en) * | 2020-01-03 | 2020-05-29 | 北京同邦卓益科技有限公司 | User identification method, device and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108304482A (en) | The recognition methods and device of broker, electronic equipment and readable storage medium storing program for executing | |
JP6362602B2 (en) | System and method for processing digital traffic metrics | |
CN107515890A (en) | A kind of method and terminal for identifying resident point | |
CN109388674A (en) | Data processing method, device, equipment and readable storage medium storing program for executing | |
CN106570014A (en) | Method and device for determining home attribute information of user | |
CN111148018B (en) | Method and device for identifying and positioning regional value based on communication data | |
CN106033510A (en) | Method and system for identifying user equipment | |
CN109669995A (en) | Data storage, quality calculation method, device, storage medium and server | |
CN109690571A (en) | Group echo system and method based on study | |
CN108648093A (en) | Data processing method, device and equipment | |
CN108875048A (en) | Report form generation method, device, electronic equipment and readable storage medium storing program for executing | |
US20160042374A1 (en) | Methods and Systems for Identifying Merchant and ATM Demand | |
CN106227743A (en) | Advertisement target group touches and reaches ratio estimation method and device | |
CN109858735A (en) | Consumer's risk scoring assessment method, device, computer equipment and storage medium | |
CN110309496B (en) | Data summarizing method, electronic device and computer readable storage medium | |
Spichkova et al. | Easy mobile meter reading for non-smart meters: Comparison of aws rekognition and google cloud vision approaches | |
CN109344173B (en) | Data management method and device and data structure | |
CN106257507A (en) | The methods of risk assessment of user behavior and device | |
CN107067276A (en) | Determine the method and device of object influences power | |
CN110516713A (en) | A kind of target group's recognition methods, device and equipment | |
CN106815062A (en) | A kind of business pipelined data processing method and processing device | |
CN110348983B (en) | Transaction information management method and device, electronic equipment and non-transitory storage medium | |
CN110059097A (en) | Data processing method and device | |
CN113743791A (en) | Business evaluation method and device for business work order, electronic equipment and medium | |
CN112418654B (en) | Resource allocation method and device, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180720 |
|
RJ01 | Rejection of invention patent application after publication |