CN108446988A - User identification method based on relational network and system - Google Patents
User identification method based on relational network and system Download PDFInfo
- Publication number
- CN108446988A CN108446988A CN201710717662.4A CN201710717662A CN108446988A CN 108446988 A CN108446988 A CN 108446988A CN 201710717662 A CN201710717662 A CN 201710717662A CN 108446988 A CN108446988 A CN 108446988A
- Authority
- CN
- China
- Prior art keywords
- user
- relational network
- vertex
- abnormal point
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The invention discloses a kind of user identification method and system based on relational network, very big support is provided for internet credit approval, is especially had outstanding performance in the case fraud of group of identification intermediary.Its technical solution is:It is identified based on existing subscriber and carries out relational network figure initialization, wherein vertex includes normal point and abnormal point, and normal point corresponds to trusted user mark, and abnormal point corresponds to not trusted user identifier;The mark that new user provides is subjected to relational network figure after the completion of new user's registration and enters graphic operation, wherein the mark based on new user carries out the addition on the vertex and side of relational network figure;It is added to the relational network figure on vertex and side based on graphic operation is entered through new user, updates the state on vertex in relational network figure, that is, be normal point or abnormal point;Relational network figure is inquired when carrying out user's identification, the abnormal point and user identifier based on relational network figure are associated with identification user with abnormal point.
Description
Technical field
The present invention relates to identification of the relational network model to user type based on big data, more particularly to applied to interconnection
The recognition methods of the financial credit approval field agency user of net.
Background technology
Credit risk and risk of fraud management are the most important parts of loan transaction risk management on line.For credit risk
Assessment, traditional method focuses on the audit of borrower's credit history and human quality, and in internet especially social network
Today of network great development, the assessment to the social networks of creditor (including the qualification of affiliated person be associated with tightness degree),
Gradually become the important module of consumer finance credit evaluation on line.
For risk of fraud, the case fraud of group of intermediary is guard key object therein.From social networks theory and disappear
From the point of view of taking financial business practice, the case fraud of group of intermediary has its distinctive form, such as a large amount of sections on social networks topological structure
Point is assembled, and has common attribute dimensions etc. between node.In these features anti-fraud rule that loan system designs on line, all
There is different degrees of embodiment.
The credit card reference business of conventional banking facilities, due to being typically to pass through to audit under line, and Review Cycle is longer, in
The taking precautions against for application fraud that be situated between can carry out screening by the anti-fraud logic of every day operation batch.And it is completely upper real-time for being based on
The reference business of air control system, to ensure under the premise of data volume and ever-increasing data dimension run timeliness, be one urgently
Problem to be solved.
Invention content
A brief summary of one or more aspects is given below to provide to the basic comprehension in terms of these.This general introduction is not
The extensive overview of all aspects contemplated, and be both not intended to identify critical or decisive element in all aspects also non-
Attempt to define the range in terms of any or all.Its unique purpose is to provide the one of one or more aspects in simplified form
A little concepts are with the sequence for more detailed description given later.
It is an object of the invention to solve the above problems, provides a kind of user identification method based on relational network and be
System, great support is provided for internet credit approval, is especially had outstanding performance in terms of the case fraud of group of identification intermediary.
The technical scheme is that:Present invention is disclosed a kind of user identification methods based on relational network, including:
The initialization for carrying out relational network figure is identified based on existing subscriber in system, wherein using each user identifier as pass
It is the vertex in network, existing be associated with will connect into a line between corresponding vertex between being identified based on two users,
Middle vertex includes normal point and abnormal point, and normal point corresponds to trusted user identifier, and abnormal point corresponds to not trusted user
Mark, user identifier are related to the social relationship information of user;
The mark that new user provides is subjected to relational network figure after the completion of new user's registration and enters graphic operation, including
Mark based on new user carries out the addition on the vertex and side of relational network figure;
It is added to the relational network figure on vertex and side based on graphic operation is entered through new user, updates vertex in relational network figure
State, that is, be normal point or abnormal point;
Inquire relational network figure when carrying out user's identification, abnormal point and user identifier based on relational network figure with it is different
The association identification user often put.
One embodiment of the user identification method according to the present invention based on relational network, user's identification are used for reference,
Middle normal point corresponds to the client for obtaining credit, and abnormal point corresponds to intermediary or the client that breaks one's promise, and user is additionally operable to the knowledge of marketing user
Not, wherein normal point corresponds to normal users, and abnormal point corresponds to marketing user.
One embodiment of the user identification method according to the present invention based on relational network, between vertex connection form side
According to including but not limited to:The relationship between social networks, company between natural person, the correspondence between equipment, difference
The common owner's relationship of equipment room.
One embodiment of the user identification method according to the present invention based on relational network, the relational network of new user identifier
Figure is variable or can be updated, and is divided into real-time update according to update timeliness difference, regularly updates, irregularly updates.
One embodiment of the user identification method according to the present invention based on relational network, method further include relational network figure
The update operation of vertex state, the vertex state update operation includes group one of in following two modes or both
It closes:
Abnormal point information is manually imported from external data source, based on the abnormal point information update relational network manually imported
The state on the vertex being associated in figure;
Timing is according to access rule batch updating abnormal point information, the abnormal point information update network of personal connections based on batch updating
The state on the vertex being associated in network figure.
One embodiment of the user identification method according to the present invention based on relational network, the exception based on relational network figure
Point and user identifier and abnormal point include automatic identification mode the step of being associated with identification user, and automatic identification mode is:
Subgraph is extracted from relational network figure, subgraph is therefrom to collect out and be intended to identify using relational network figure as total figure
The related vertex of user and side and constitute;
The abnormal point and the distance between user identifier and these abnormal points in subgraph are counted, whether is based on statistical result
Meet preset strategy and carries out automatic identification.
One embodiment of the user identification method according to the present invention based on relational network, the exception based on relational network figure
Point and user identifier and abnormal point include manual identified mode the step of being associated with identification user, the identification of manual identified mode
Basis includes the arbitrary combination in following three kinds:
The first, first extracts subgraph from relational network figure, and wherein subgraph is using relational network figure as total figure and therefrom
Collect out and the related vertex of user to be identified and side and constitute, then the information on the vertex in subgraph is inquired, and shows
Show vertex information query result;
Second, subgraph is first extracted from relational network figure, then counts the abnormal point information in subgraph according to level, and
Show abnormal point information;
The third, first subgraph is extracted from relational network figure, then according to a certain parameter to the user identifier in subgraph into
Row sequencing statistical, and show sequencing statistical result.
User's identifying system based on relational network that present invention further teaches a kind of, including processor, memory and calculating
Machine program, has computer program on memory, and processor runs computer program to execute following step:
The initialization for carrying out relational network figure is identified based on existing subscriber in system, wherein using each user identifier as pass
It is the vertex in network, existing be associated with will connect into a line between corresponding vertex between being identified based on two users,
Middle vertex includes normal point and abnormal point, and normal point corresponds to trusted user identifier, and abnormal point corresponds to not trusted user
Mark, user identifier are related to the social relationship information of user;
The mark that new user provides is subjected to relational network figure after the completion of new user's registration and enters graphic operation, including
Mark based on new user carries out the addition on the vertex and side of relational network figure;
It is added to the relational network figure on vertex and side based on graphic operation is entered through new user, updates vertex in relational network figure
State, that is, be normal point or abnormal point;
Inquire relational network figure when carrying out user's identification, abnormal point and user identifier based on relational network figure with it is different
The association identification user often put.
One embodiment of user's identifying system according to the present invention based on relational network, user's identification are used for reference,
Middle normal point corresponds to the client for obtaining credit, and abnormal point corresponds to intermediary or the client that breaks one's promise, and user is additionally operable to the knowledge of marketing user
Not, wherein normal point corresponds to normal users, and abnormal point corresponds to marketing user.
One embodiment of user's identifying system according to the present invention based on relational network, between vertex connection form side
According to including but not limited to:The relationship between social networks, company between natural person, the correspondence between equipment, difference
The common owner's relationship of equipment room.
One embodiment of user's identifying system according to the present invention based on relational network, the relational network of new user identifier
Figure is variable or can be updated, and is divided into real-time update according to update timeliness difference, regularly updates, irregularly updates.
One embodiment of user's identifying system according to the present invention based on relational network, computer program is in operational process
In also execute the vertex state update operation of relational network figure, the vertex state update operation includes in following two modes
One of them or both combination:
Abnormal point information is manually imported from external data source, based on the abnormal point information update relational network manually imported
The state on the vertex being associated in figure;
Timing is according to access rule batch updating abnormal point information, the abnormal point information update network of personal connections based on batch updating
The state on the vertex being associated in network figure.
One embodiment of user's identifying system according to the present invention based on relational network, the exception based on relational network figure
Point and user identifier and abnormal point include automatic identification mode the step of being associated with identification user, and automatic identification mode is:
Subgraph is extracted from relational network figure, subgraph is therefrom to collect out and be intended to identify using relational network figure as total figure
The related vertex of user and side and constitute;
The abnormal point and the distance between user identifier and these abnormal points in subgraph are counted, whether is based on statistical result
Meet preset strategy and carries out automatic identification.
One embodiment of user's identifying system according to the present invention based on relational network, the exception based on relational network figure
Point and user identifier and abnormal point include manual identified mode the step of being associated with identification user, the identification of manual identified mode
Basis includes the arbitrary combination in following three kinds:
The first, first extracts subgraph from relational network figure, and wherein subgraph is using relational network figure as total figure and therefrom
Collect out and the related vertex of user to be identified and side and constitute, then the information on the vertex in subgraph is inquired, and shows
Show vertex information query result;
Second, subgraph is first extracted from relational network figure, then counts the abnormal point information in subgraph according to level, and
Show abnormal point information;
The third, first subgraph is extracted from relational network figure, then according to a certain parameter to the user identifier in subgraph into
Row sequencing statistical, and show sequencing statistical result.
The present invention, which compares the prior art, following advantageous effect:The present invention is based on relational network models, by storage
Collection of illustrative plates modeling is carried out between user and intermediary, calculates the various statistical informations in magnanimity social networks in real time, it is follow-up to support
The automatic or manual audit of credit prevents group of intermediary case from cheating.It can be based on real-time computing engines in specific implementation technology and divide
Cloth chart database realizes, including general real-time computing engines (the general-purpose computations frame of distributed treatment stream data), point
Cloth chart database system (Database Systems of distributed treatment graph model), NoSQL databases be (the non-relational data of processing
Database Systems), message system (effect include asynchronous process, avoiding the peak hour decouples between flow control, system), data warehouse (support to answer
The history full dose database of miscellaneous analysis operation), concurrency programming model, distributed service framework (high-performance and transparence it is long-range
Service call scheme) etc..Since internet credit approval is very high to requirement of real-time, it is in particular in real-time update and inquiry
Two aspects, therefore the general real-time computing engines of seamless integration of the present invention and distribution chart database and the big data ecosphere
A series of Open Frameworks.
The present invention using with the relevant user identifier of social networks as the vertex in relational network figure, will be between user identifier
In the presence of association as the side between vertex, according to the addition of the user of system new registration and timing or manual update vertex state
(normal point or abnormal point) is finally made according to the quantity of the relevant abnormal point of user identifier and with the distance between abnormal point
For considering for policing parameter, user's identification is carried out to complete credit approval.The present invention in addition to be applied to internet credit approval it
Outside, it can be also used for the identification etc. of internet marketing account.The present invention is not limited with specific application scenario, as long as having used this
The principle idea of invention, both falls among protection scope of the present invention.
Description of the drawings
After reading the detailed description of embodiment of the disclosure in conjunction with the following drawings, it better understood when the present invention's
Features described above and advantage.In the accompanying drawings, each component is not necessarily drawn to scale, and has similar correlation properties or feature
Component may have same or similar reference numeral.
Fig. 1 shows the flow chart of an embodiment of the user identification method based on relational network of the present invention.
Fig. 2 shows the flow charts that new user enters graphic operation.
Fig. 3 shows inquiry collection of illustrative plates to carry out the flow chart of credit approval.
Specific implementation mode
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.Note that below in conjunction with attached drawing and specifically real
The aspects for applying example description is merely exemplary, and is understood not to carry out any restrictions to protection scope of the present invention.
Fig. 1 shows the flow of an embodiment of the user identification method based on relational network of the present invention.Refer to figure
1, here is the detailed description to the implementation steps of the method for the present embodiment.Below this reality is carried out for applying in reference field
The explanation for applying example may additionally serve for the fields such as the identification of marketing user similar therewith.
Step S1:The initialization for carrying out relational network figure is identified based on existing subscriber in system.
User refer in the present invention natural person, equipment, company or other can be by the entity of relational network.Initialization is closed
Be network can referring also to Fig. 2 initialization complete before initialization step.
Here existing subscriber is the user of storage in system, and user identifier is referred to as user property, user object
Deng, actually user social contact relationship it is relevant one amount, and social networks can be divided into communication contact, address, identity information,
Working condition etc..So a user can have multiple user identifiers.
Each user identifier is based on two as the vertex (i.e. full dose vertex information in Fig. 2 enters figure) in relational network figure
Existing association will connect into a line (i.e. full dose side information in Fig. 2 enters figure) between user identifier between corresponding vertex.
Connection forms the foundation on side and includes but not limited between vertex:Social networks (such as Peer Relationships, Tong Xueguan between natural person
System, call relationship, mutual powder relationship of microblogging etc.), relationship between company (such as company's cooperative relationship, transaction relationship, ownership and membership relations
Deng), the correspondence between equipment, common owner's relationship etc. between distinct device.According to different users, there may be different
Connection.
Vertex includes normal point and abnormal point, and normal point corresponds to trusted user identifier, and (being in the present embodiment can be with
Obtain the client of credit), it (is, for example, in the present embodiment intermediary, break one's promise user that abnormal point, which corresponds to not trusted user identifier,
Deng).And the identification for other field such as account of marketing, then normal point corresponds to the user of normal use, abnormal point
Then corresponding marketing user.In some other application scenarios, vertex can also be divided into general point and focus.Either one
As put or the name of normal point or the name of focus or abnormal point, carried both for the difference of different business scene
Method, the effect played in respective technical solution are identical.
Step S2:The mark that new user provides is subjected to relational network figure after the completion of new user's registration and enters graphic operation,
The addition on the vertex and side of relational network figure is carried out including the mark based on new user.
New user enters figure and can refer to the right flow after the completion of initialization in Fig. 2.
The relational network figure of new user identifier is variable or can be updated, and is divided into real time more according to update timeliness difference
Newly, it regularly updates, irregularly update.Can be to receive vertex information by remote service to enter figure, and pass through in specific implementation
Message system receives side information and enters figure.
Step S3:It is added to the relational network figure on vertex and side based on graphic operation is entered through new user, updates relational network
The state on vertex in figure.
Since the variation on vertex and side has occurred in relational network figure, with the relevant original top in the vertex being newly added or side
The state (i.e. normal point or abnormal point) of point is it can also happen that variation, it is therefore desirable to pair with it is new enter vertex or side generation it is associated
Original vertex carries out state update.That is, it is shown in Fig. 2 enter in real time it is adjacent according to social networks related updates after graphic operation step
Occupy the intermediary message of node.That is, when it is abnormal point to have vertex, with its other intimate associated normal point also converted into exception
Point.
Step S4:Relational network figure, the abnormal point based on relational network figure and user are inquired when carrying out user's identification
It identifies and identifies user with being associated with for abnormal point.
Above three step is all to carry out the building of relational network figure, (regular) updating maintenance etc. in real time, this step is
Inquiry when user to be identified and then credit approval to relational network figure.This identification can be that automatic identification also may be used
To be manual identified.
Referring specifically to Fig. 3, for automatic identification (credit) mode, including:Subgraph, neutron are extracted from relational network figure
Figure be using relational network figure as total figure, therefrom collect out and the related vertex of user to be identified and side and constitute.Count subgraph
In abnormal point and user identifier vertex and the distance between these abnormal points, whether default plan is met based on statistical result
Slightly carry out automatic identification (credit).
In the present embodiment, the distance between vertex refer between vertex most it is short be several sides connection, the shorter table of distance
Show that vertex association is more intimate.And the preset strategy of automatic credit mainly considers the quantity and reference user and abnormal point of abnormal point
Intimate degree, for example, consider inner ring associated abnormal point quantity at associated abnormal point quantity, outer ring, while consider with
Connection abnormal point quantity and the distance between abnormal point and reference user.
For manual identified (credit) mode, the identification basis of manual identified includes the arbitrary combination in following three kinds.
The first:Subgraph is first extracted from relational network figure, and then the information on the vertex in subgraph is inquired, and leads to
Cross web displaying vertex information query result.These vertex informations include whether for the good user of reference, whether be intermediary, be
No is the client etc. that breaks one's promise.
Second:Subgraph is first extracted from relational network figure, then counts the abnormal point information in subgraph according to level, and
Pass through web displaying abnormal point information.These abnormal point information carry out quantity system according to the distance between reference user grade
Meter.
The third:First subgraph is extracted from relational network figure, then according to a certain parameter to the user identifier in subgraph into
Row sequencing statistical, and show sequencing statistical result.For example, the side between vertex carries attribute, for side of conversing, attribute may
There are talk times, voice frequency or duration of call etc., carries out the vertex in subgraph according to the side attribute of the wherein duration of call
Sequencing statistical simultaneously visualizes display on webpage.
Staff can be shown based on above visualization as a result, credit approval is manually identified.
Can also include the vertex state update operation of relational network figure for the above embodiments.Can have two
Kind of update mode of operation, with reference to Fig. 2, wherein this update mode of operation of several process descriptions on the left side.
The first is that abnormal point information is manually imported from external data source, based on the abnormal point information update manually imported
The state on the vertex being associated in relational network figure.This operation mainly carries out more the information on existing vertex and side
Newly, while if there is the information except relational network figure, new vertex or side can also be increased.It is former such as through manually importing
Some vertex change having may also can become abnormal point for abnormal point, then other normal points adjacent thereto.
Second is periodically according to access rule batch updating abnormal point information, and the abnormal point information based on batch updating is more
The state on the vertex being associated in new relation network.Access rule is, for example,:One voice frequency of setting is then higher than threshold value
More than threshold value it is doubtful intermediary etc. rule for the rule of doubtful intermediary or same address, based on the rule set batch
Amount update relational network figure.Such as when many people use same phone, then corresponding vertex is changed into abnormal point from normal point,
And its neighbours vertex can also update therewith.
It is operated by above-mentioned update, the present invention relies the basis (relational network figure) of realization can more comprehensively, more in real time
The case where reacting doubtful intermediary.
In addition, the present invention also discloses a kind of user's identifying system based on relational network, system includes processor, memory
With the computer program being stored on memory, various information is usually acquired by client and is transferred to server, is then being taken
Function is realized on business device.
Processor runs computer program to execute step shown in FIG. 1 as the aforementioned, that is, comprising based on existing in system
User identifier carries out the initialization of relational network figure, and the mark for providing new user after the completion of new user's registration carries out network of personal connections
Network figure enters graphic operation, is added to the relational network figure on vertex and side based on graphic operation is entered through new user, updates relational network
The state on vertex in figure, finally inquires relational network figure when carrying out user's identification, abnormal point based on relational network figure and
User identifier is associated with identification user with abnormal point.
It is wherein based ultimately upon relational network figure and credit approval is identified as shown in figure 3, being divided into automatic identification and artificial knowledge
Not.Wherein the step of automatic identification includes that subgraph is extracted from relational network figure, subgraph be using relational network figure as total figure, from
In collect out and the related vertex of user to be identified and side and constitute;Count subgraph in abnormal point and user identifier and these
The distance between abnormal point carries out automatic identification based on whether statistical result meets preset strategy.
And the basis of manual identified includes then three kinds, is respectively:The first, first extracts subgraph from relational network figure,
Middle subgraph be using relational network figure as total figure and therefrom collect out and the related vertex of user to be identified and side and constituted, then
The information on the vertex in subgraph is inquired, and shows vertex information query result;It second, is first taken out from relational network figure
Subgraph is taken, then counts the abnormal point information in subgraph according to level, and show abnormal point information;The third, first from network of personal connections
Subgraph is extracted in network figure, statistics is then ranked up to the user identifier in subgraph according to a certain parameter, and show sequencing statistical
As a result.
In order to make relational network figure more accurate, the relational network figure of new user identifier is variable or can be updated,
It is divided into real-time update according to update timeliness difference, regularly updates, irregularly update, therefore the computer program in system is being run
The vertex state update operation of relational network figure is also executed in the process, including one of in following two modes or both
Combination:
Abnormal point information is manually imported from external data source, based on the abnormal point information update relational network manually imported
The state on the vertex being associated in figure;
Timing is according to access rule batch updating abnormal point information, the abnormal point information update network of personal connections based on batch updating
The state on the vertex being associated in network figure.
Although to simplify explanation to illustrate the above method and being described as a series of actions, it should be understood that and understand,
The order that these methods are not acted is limited, because according to one or more embodiments, some actions can occur in different order
And/or with from it is depicted and described herein or herein it is not shown and describe but it will be appreciated by those skilled in the art that other
Action concomitantly occurs.
Those skilled in the art will further appreciate that, the various illustratives described in conjunction with the embodiments described herein
Logic plate, module, circuit and algorithm steps can be realized as electronic hardware, computer software or combination of the two.It is clear
Explain to Chu this interchangeability of hardware and software, various illustrative components, frame, module, circuit and step be above with
Its functional form makees generalization description.Such functionality be implemented as hardware or software depend on concrete application and
It is applied to the design constraint of total system.Technical staff can realize each specific application described with different modes
Functionality, but such realization decision should not be interpreted to cause departing from the scope of the present invention.
General place can be used in conjunction with various illustrative logic plates, module and the circuit that presently disclosed embodiment describes
Reason device, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) other are compiled
Journey logical device, discrete door or transistor logic, discrete hardware component or its be designed to carry out function described herein
Any combinations are realized or are executed.General processor can be microprocessor, but in alternative, which can appoint
What conventional processor, controller, microcontroller or state machine.Processor is also implemented as the combination of computing device, example
As DSP and the combination of microprocessor, multi-microprocessor, the one or more microprocessors to cooperate with DSP core or it is any its
His such configuration.
It can be embodied directly in hardware, in by processor in conjunction with the step of method or algorithm that embodiment disclosed herein describes
It is embodied in the software module of execution or in combination of the two.Software module can reside in RAM memory, flash memory, ROM and deposit
Reservoir, eprom memory, eeprom memory, register, hard disk, removable disk, CD-ROM or known in the art appoint
In the storage medium of what other forms.Exemplary storage medium is coupled to processor so that the processor can be from/to the storage
Medium reads and writees information.In alternative, storage medium can be integrated into processor.Pocessor and storage media can
It resides in ASIC.ASIC can reside in user terminal.In alternative, pocessor and storage media can be used as discrete sets
Part is resident in the user terminal.
In one or more exemplary embodiments, described function can be in hardware, software, firmware, or any combination thereof
Middle realization.If being embodied as computer program product in software, each function can be used as the instruction of one or more items or generation
Code may be stored on the computer-readable medium or is transmitted by it.Computer-readable medium includes computer storage media and communication
Both media comprising any medium for facilitating computer program to shift from one place to another.Storage medium can be can quilt
Any usable medium that computer accesses.It is non-limiting as example, such computer-readable medium may include RAM, ROM,
EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage apparatus can be used to carrying or store instruction
Or data structure form desirable program code and any other medium that can be accessed by a computer.Any connection is also by by rights
Referred to as computer-readable medium.For example, if software is using coaxial cable, fiber optic cables, twisted-pair feeder, digital subscriber line
(DSL) or the wireless technology of such as infrared, radio and microwave etc is passed from web site, server or other remote sources
It send, then the coaxial cable, fiber optic cables, twisted-pair feeder, DSL or such as infrared, radio and microwave etc is wireless
Technology is just included among the definition of medium.Disk (disk) and dish (disc) as used herein include compression dish
(CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and blu-ray disc, which disk (disk) are often reproduced in a manner of magnetic
Data, and dish (disc) with laser reproduce data optically.Combinations of the above should also be included in computer-readable medium
In the range of.
Offer is that can make or use this public affairs to make any person skilled in the art all to the previous description of the disclosure
It opens.The various modifications of the disclosure all will be apparent for a person skilled in the art, and as defined herein general
Suitable principle can be applied to spirit or scope of other variants without departing from the disclosure.The disclosure is not intended to be limited as a result,
Due to example described herein and design, but should be awarded and principle disclosed herein and novel features phase one
The widest scope of cause.
Claims (14)
1. a kind of user identification method based on relational network, which is characterized in that including:
The initialization for carrying out relational network figure is identified based on existing subscriber in system, wherein using each user identifier as network of personal connections
Vertex in network figure, existing be associated with will connect into a line between corresponding vertex between being identified based on two users, wherein pushing up
Point includes normal point and abnormal point, and normal point corresponds to trusted user identifier, and abnormal point corresponds to not trusted user identifier,
User identifier is related to the social relationship information of user;
The mark that new user provides is subjected to relational network figure after the completion of new user's registration and enters graphic operation, including based on
The mark of new user carries out the addition on the vertex and side of relational network figure;
It is added to the relational network figure on vertex and side based on graphic operation is entered through new user, updates the shape on vertex in relational network figure
State, that is, be normal point or abnormal point;
Relational network figure, the abnormal point and user identifier based on relational network figure and abnormal point are inquired when carrying out user's identification
Association identify user.
2. the user identification method according to claim 1 based on relational network, which is characterized in that user identifies for levying
Letter, wherein normal point correspond to the client for obtaining credit, and abnormal point corresponds to intermediary or the client that breaks one's promise, and user is additionally operable to marketing user
Identification, wherein normal point corresponds to normal users, and abnormal point corresponds to marketing user.
3. the user identification method according to claim 1 based on relational network, which is characterized in that connect shape between vertex
Include but not limited at the foundation on side:The relationship between social networks, company between natural person, the communication between equipment are closed
Common owner's relationship between system, distinct device.
4. the user identification method according to claim 1 based on relational network, which is characterized in that the pass of new user identifier
Be network to be variable or can be updated, according to update timeliness difference be divided into real-time update, regularly update, irregularly more
Newly.
5. the user identification method according to claim 1 based on relational network, which is characterized in that method further includes relationship
The vertex state update operation of network, the vertex state update operation include one of in following two modes or
The two combines:
Abnormal point information is manually imported from external data source, based in the abnormal point information update relational network figure manually imported
The state on the vertex being associated;
Timing is according to access rule batch updating abnormal point information, the abnormal point information update relational network figure based on batch updating
In the state on vertex that is associated.
6. the user identification method based on relational network according to claim 1 or 5, which is characterized in that be based on network of personal connections
The abnormal point and user identifier of network figure include automatic identification mode, automatic identification the step of being associated with identification user with abnormal point
Mode is:
Extract subgraph from relational network figure, subgraph is therefrom collected out and user to be identified using relational network figure as total figure
Related vertex and side and constitute;
The abnormal point and the distance between user identifier and these abnormal points in subgraph are counted, whether is met based on statistical result
Preset strategy carries out automatic identification.
7. the user identification method based on relational network according to claim 1 or 5, which is characterized in that be based on network of personal connections
The abnormal point and user identifier of network figure include manual identified mode, manual identified the step of being associated with identification user with abnormal point
The identification basis of mode includes the arbitrary combination in following three kinds:
The first first extracts subgraph from relational network figure, and wherein subgraph is to collect using relational network figure as total figure and therefrom
Go out vertex related with user to be identified and side and constitute, then the information on the vertex in subgraph is inquired, and show top
Point information inquiry result;
Second, subgraph is first extracted from relational network figure, then counts the abnormal point information in subgraph according to level, and show
Abnormal point information;
The third, first extracts subgraph from relational network figure, is then arranged the user identifier in subgraph according to a certain parameter
Sequence counts, and shows sequencing statistical result.
8. a kind of user's identifying system based on relational network, which is characterized in that including processor, memory and computer journey
Sequence, has computer program on memory, and processor runs computer program to execute following step:
The initialization for carrying out relational network figure is identified based on existing subscriber in system, wherein using each user identifier as network of personal connections
Vertex in network figure, existing be associated with will connect into a line between corresponding vertex between being identified based on two users, wherein pushing up
Point includes normal point and abnormal point, and normal point corresponds to trusted user identifier, and abnormal point corresponds to not trusted user identifier,
User identifier is related to the social relationship information of user;
The mark that new user provides is subjected to relational network figure after the completion of new user's registration and enters graphic operation, including based on
The mark of new user carries out the addition on the vertex and side of relational network figure;
It is added to the relational network figure on vertex and side based on graphic operation is entered through new user, updates the shape on vertex in relational network figure
State, that is, be normal point or abnormal point;
Relational network figure, the abnormal point and user identifier based on relational network figure and abnormal point are inquired when carrying out user's identification
Association identify user.
9. user's identifying system according to claim 8 based on relational network, which is characterized in that user identifies for levying
Letter, wherein normal point correspond to the client for obtaining credit, and abnormal point corresponds to intermediary or the client that breaks one's promise, and user is additionally operable to marketing user
Identification, wherein normal point corresponds to normal users, and abnormal point corresponds to marketing user.
10. user's identifying system according to claim 8 based on relational network, which is characterized in that connected between vertex
Formed side foundation include but not limited to:The relationship between social networks, company between natural person, the communication between equipment are closed
Common owner's relationship between system, distinct device.
11. user's identifying system according to claim 8 based on relational network, which is characterized in that new user identifier
Relational network figure is variable or can be updated, and is divided into real-time update according to update timeliness difference, regularly updates, irregularly more
Newly.
12. user's identifying system according to claim 8 based on relational network, which is characterized in that computer program exists
The vertex state update operation of relational network figure is also executed in operational process, the vertex state update operation includes following two
It is combined one of in mode or both:
Abnormal point information is manually imported from external data source, based in the abnormal point information update relational network figure manually imported
The state on the vertex being associated;
Timing is according to access rule batch updating abnormal point information, the abnormal point information update relational network figure based on batch updating
In the state on vertex that is associated.
13. user's identifying system based on relational network according to claim 8 or 12, which is characterized in that be based on relationship
The abnormal point and user identifier of network include automatic identification mode the step of being associated with identification user with abnormal point, automatic to know
Other mode is:
Extract subgraph from relational network figure, subgraph is therefrom collected out and user to be identified using relational network figure as total figure
Related vertex and side and constitute;
The abnormal point and the distance between user identifier and these abnormal points in subgraph are counted, whether is met based on statistical result
Preset strategy carries out automatic identification.
14. user's identifying system based on relational network according to claim 8 or 12, which is characterized in that be based on relationship
The abnormal point and user identifier of network include manual identified mode the step of being associated with identification user with abnormal point, artificial to know
The identification basis of other mode includes the arbitrary combination in following three kinds:
The first first extracts subgraph from relational network figure, and wherein subgraph is to collect using relational network figure as total figure and therefrom
Go out vertex related with user to be identified and side and constitute, then the information on the vertex in subgraph is inquired, and show top
Point information inquiry result;
Second, subgraph is first extracted from relational network figure, then counts the abnormal point information in subgraph according to level, and show
Abnormal point information;
The third, first extracts subgraph from relational network figure, is then arranged the user identifier in subgraph according to a certain parameter
Sequence counts, and shows sequencing statistical result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710717662.4A CN108446988A (en) | 2017-08-21 | 2017-08-21 | User identification method based on relational network and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710717662.4A CN108446988A (en) | 2017-08-21 | 2017-08-21 | User identification method based on relational network and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108446988A true CN108446988A (en) | 2018-08-24 |
Family
ID=63190921
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710717662.4A Pending CN108446988A (en) | 2017-08-21 | 2017-08-21 | User identification method based on relational network and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108446988A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109582808A (en) * | 2018-11-22 | 2019-04-05 | 北京锐安科技有限公司 | A kind of user information querying method, device, terminal device and storage medium |
CN110110954A (en) * | 2019-03-08 | 2019-08-09 | 阿里巴巴集团控股有限公司 | Risk vertex recognition method and apparatus |
CN110597871A (en) * | 2019-08-07 | 2019-12-20 | 成都华为技术有限公司 | Data processing method, data processing device, computer equipment and computer readable storage medium |
CN110766547A (en) * | 2019-10-29 | 2020-02-07 | 中国建设银行股份有限公司 | Method, device, equipment and storage medium for determining credibility grade |
CN111553786A (en) * | 2020-04-24 | 2020-08-18 | 中金汇安(北京)科技有限公司 | Bank shareholder loan association transaction mining method and system based on graphic database |
CN113297436A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | User policy distribution method and device based on relational graph network and electronic equipment |
CN116542685A (en) * | 2023-07-06 | 2023-08-04 | 凯泰铭科技(北京)有限公司 | Vehicle insurance data processing method and device based on graph network |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102710755A (en) * | 2012-05-18 | 2012-10-03 | 华为技术有限公司 | Data mining method of terminal user social network, correlation method, device and system |
CN106327209A (en) * | 2016-08-24 | 2017-01-11 | 上海师范大学 | Multi-standard collaborative fraud detection method based on credit accumulation |
-
2017
- 2017-08-21 CN CN201710717662.4A patent/CN108446988A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102710755A (en) * | 2012-05-18 | 2012-10-03 | 华为技术有限公司 | Data mining method of terminal user social network, correlation method, device and system |
CN106327209A (en) * | 2016-08-24 | 2017-01-11 | 上海师范大学 | Multi-standard collaborative fraud detection method based on credit accumulation |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109582808A (en) * | 2018-11-22 | 2019-04-05 | 北京锐安科技有限公司 | A kind of user information querying method, device, terminal device and storage medium |
CN110110954A (en) * | 2019-03-08 | 2019-08-09 | 阿里巴巴集团控股有限公司 | Risk vertex recognition method and apparatus |
WO2020181909A1 (en) * | 2019-03-08 | 2020-09-17 | 阿里巴巴集团控股有限公司 | Risk vertex identification method and apparatus |
US11348115B2 (en) | 2019-03-08 | 2022-05-31 | Advanced New Technologies Co., Ltd. | Method and apparatus for identifying risky vertices |
CN110597871A (en) * | 2019-08-07 | 2019-12-20 | 成都华为技术有限公司 | Data processing method, data processing device, computer equipment and computer readable storage medium |
CN110597871B (en) * | 2019-08-07 | 2021-12-21 | 成都华为技术有限公司 | Data processing method, data processing device, computer equipment and computer readable storage medium |
CN110766547A (en) * | 2019-10-29 | 2020-02-07 | 中国建设银行股份有限公司 | Method, device, equipment and storage medium for determining credibility grade |
CN111553786A (en) * | 2020-04-24 | 2020-08-18 | 中金汇安(北京)科技有限公司 | Bank shareholder loan association transaction mining method and system based on graphic database |
CN113297436A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | User policy distribution method and device based on relational graph network and electronic equipment |
CN113297436B (en) * | 2021-04-28 | 2023-09-05 | 上海淇玥信息技术有限公司 | User policy distribution method and device based on relational graph network and electronic equipment |
CN116542685A (en) * | 2023-07-06 | 2023-08-04 | 凯泰铭科技(北京)有限公司 | Vehicle insurance data processing method and device based on graph network |
CN116542685B (en) * | 2023-07-06 | 2023-09-15 | 凯泰铭科技(北京)有限公司 | Vehicle insurance data processing method and device based on graph network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108446988A (en) | User identification method based on relational network and system | |
CN108492173A (en) | A kind of anti-Fraud Prediction method of credit card based on dual-mode network figure mining algorithm | |
Cappiello et al. | Time-related factors of data quality in multichannel information systems | |
Luo et al. | Guanxi and organizational performance: A meta-analysis | |
Adedokun et al. | Financial inclusion: A pathway to economic growth in Sub‐Saharan African economies | |
CN104732154A (en) | Method And System For Anonymizing Data | |
CN104376492B (en) | A kind of credits processing system | |
CN104867055A (en) | Financial network doubtable money tracking and identifying method | |
CN108921686A (en) | A kind of credit-graded approach and device of personal user | |
KR102204070B1 (en) | Method and system for compensating for block-chain network participants | |
Whalley | Liberalization in China's key service sectors following WTO accession: Some scenarios and issues of measurement | |
CN110264221A (en) | A kind of full link safety business federal solution for service provider's industry | |
CN109472683A (en) | Customer lending qualification generation method, server and readable storage medium storing program for executing | |
CN105376223A (en) | Network identity relationship reliability calculation method | |
CN114398669A (en) | Joint credit scoring method and device based on privacy protection calculation and cross-organization | |
CN111090780A (en) | Method and device for determining suspicious transaction information, storage medium and electronic equipment | |
CN108305163A (en) | The credit method for early warning and system in feature based library | |
CN110209729A (en) | The method and device of data transfer object identification | |
CN108932635A (en) | A kind of integration managing method and system based on block chain | |
Bhattacharya et al. | Local institutional structure and clientelistic access to employment: the case of MGNREGS in three states of India | |
Zhai et al. | Big data analysis of accounting forecasting based on machine learning | |
CN114677217B (en) | Ethernet room-oriented abnormal transaction behavior detection method based on subgraph matching | |
CN107808339A (en) | A kind of data acquisition and analysis system | |
CN108320133A (en) | Assembled architecture worker management's system based on mobile client | |
CN108335084A (en) | A kind of Intelligent operation system of variable power of organization |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180824 |