CN109670937A - Risk subscribers recognition methods, user equipment, storage medium and device - Google Patents
Risk subscribers recognition methods, user equipment, storage medium and device Download PDFInfo
- Publication number
- CN109670937A CN109670937A CN201811129426.1A CN201811129426A CN109670937A CN 109670937 A CN109670937 A CN 109670937A CN 201811129426 A CN201811129426 A CN 201811129426A CN 109670937 A CN109670937 A CN 109670937A
- Authority
- CN
- China
- Prior art keywords
- user
- risk
- target
- default
- 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.)
- Withdrawn
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
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses risk subscribers recognition methods, user equipment, storage medium and devices.The personal information of target user is obtained in the present invention, and creates destination node corresponding with the personal information of the target user；The destination node is added in preset relation network, and the preset relation network after addition node is set as relationship by objective (RBO) network；Association user corresponding with the target user is determined in the relationship by objective (RBO) network, and inquires association user role corresponding with the association user；Whether the user role based on target user described in the association user Role judgement is risk subscribers.Significantly, it is different from existing identification method, relational network will individually be constructed, and based on the user role for inferring target user in relational network there are the identity of the other users of relevance with target user, showed in the accuracy of recognition result more excellent, solve that existing identification method there is technical issues that cannot accurately identify.
Description
Technical field
The present invention relates to technical field of information processing more particularly to risk subscribers recognition methods, user equipment, storage mediums
And device.
Background technique
With the appearance of loan fraud clique, loan fraud clique causes one to the normal operation of internet financial institution
Fixed negative influence.Because loan fraud clique can maliciously postpone also after handling loan transaction at internet financial institution
Money duration is not refunded, also, its behavior be often dolus malus and caused by loss it is larger.
So needing to identify as soon as possible in loan personnel after releasing loan for internet financial institution
Hiding loan fraud clique, and collection disposition is carried out as early as possible to the personnel that provided a loan, more effectively to retrieve economic losses.
And the mode of traditional identification loan fraud clique is, financial institution can regularly pull the reference of the personnel of loan
Information or third party's data are to be monitored management, to judge whether the personnel that provided a loan may be loan fraud molecule.
But this kind of mode can not identify loan fraud molecule early stage and in hiding state very accurately,
These loan fraud molecules being under hiding state are all the user there are risk for financial institution.So can
Think, existing identification method there is technical issues that accurately to identify.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide risk subscribers recognition methods, user equipment, storage medium and devices, it is intended to
Solve that existing identification method there is technical issues that cannot accurately identify.
To achieve the above object, the present invention provides a kind of risk subscribers recognition methods, the risk subscribers recognition methods packet
Include following steps:
The personal information of target user is obtained, and creates destination node corresponding with the personal information of the target user；
The destination node is added in preset relation network, and the preset relation network after addition node is set as mesh
Mark relational network, the preset relation network by default node corresponding with each user and each default node of connection connection side
It constitutes；
Association user corresponding with the target user is determined in the relationship by objective (RBO) network, and is inquired and the association
The corresponding association user role of user；
Whether the user role based on target user described in the association user Role judgement is risk subscribers.
Preferably, described that the destination node is added in the preset relation network, and will be pre- after addition node
If relational network is set as relationship by objective (RBO) network, comprising:
The personal information of the target user is matched with default personal information；
In successful match, determines default node corresponding with the default personal information of successful match and be set to off interlink
Point；
The destination node is added in the preset relation network, and adds the connection associated nodes and the mesh
Mark the connection side of node；
Preset relation network after change is set as relationship by objective (RBO) network.
Preferably, described that association user corresponding with the target user is determined in the relationship by objective (RBO) network, and look into
Ask association user role corresponding with the association user, comprising:
The default node that there is connection side between the destination node is being searched in the relationship by objective (RBO) network；
User corresponding with there is the connection default node on side is regarded as into association user, and is inquired and the association user
Corresponding association user role；
Whether the user role based on target user described in the association user Role judgement is risk subscribers, packet
It includes:
When the user role of the association user is default fraud molecule, by the user role identification of the target user
For risk subscribers.
Preferably, the personal information of the target user is made of the sub-information of each information type；
The personal information by the target user is matched with default personal information, comprising:
Sub-information in the personal information of the target user is compared with the sub-information in default personal information, and
Count the identical target item number of sub-information；
When the target item number is greater than or equal to preset standard item number, personal information and the institute of the target user are assert
State default personal information successful match.
Preferably, described in successful match, determine default node corresponding with the default personal information of successful match simultaneously
It is set as after associated nodes, the risk subscribers recognition methods further include:
Determine association user corresponding with the associated nodes；
The corresponding relationship between the target item number and the association user is established, and the corresponding relationship is added to pre-
It include the corresponding relationship between item number and user if connecting in the mapping relations of side, in the default connection side mapping relations；
Whether the user role based on target user described in the association user Role judgement is risk subscribers, packet
It includes:
Obtain role's value-at-risk corresponding with the association user role；
Inquire corresponding target item number in the default connection side mapping relations according to the association user, and determine with
The corresponding weight coefficient of the target item number；
Target risk value is calculated according to role's value-at-risk and the weight coefficient；
When the target risk value is greater than or equal to default value-at-risk, the user role of the target user is regarded as
Risk subscribers.
Preferably, it is described target risk value is calculated according to role's value-at-risk and the weight coefficient after, it is described
Risk subscribers recognition methods further include:
When the target risk value is less than default value-at-risk, the reference information of the target user is obtained；
Corresponding reference credit value is generated according to the reference information；
When the reference credit value is less than default credit value, the user role of the target user is regarded as into risk and is used
Family.
Preferably, described when the reference credit value is less than default credit value, by the user role of the target user
After regarding as risk subscribers, the risk subscribers recognition methods further include:
The numerical value of the target risk value is revised as the default value-at-risk.
In addition, to achieve the above object, the present invention also proposes a kind of user equipment, the user equipment include memory,
Processor and it is stored in the risk subscribers recognizer that can be run on the memory and on the processor, the risk is used
Family recognizer is arranged for carrying out the step of risk subscribers recognition methods as described above.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, stored on the storage medium risky
User's recognizer, the risk subscribers recognizer realize risk subscribers identification side as described above when being executed by processor
The step of method.
In addition, to achieve the above object, the present invention also proposes a kind of risk subscribers identification device, the risk subscribers identification
Device includes:
Node creation module for obtaining the personal information of target user, and creates and believes with the personal of the target user
Cease corresponding destination node；
Network struction module, for the destination node to be added in preset relation network, and will be after addition node
Preset relation network is set as relationship by objective (RBO) network, and the preset relation network is by default node corresponding with each user and connection
The connection side of each default node is constituted；
Role determination module, for determining that association corresponding with the target user is used in the relationship by objective (RBO) network
Family, and inquire association user role corresponding with the association user；
Role's determination module, for the user role based on target user described in the association user Role judgement whether be
Risk subscribers.
Relationship by objective (RBO) network will be constructed based on personal information in the present invention, and according to the association in relationship by objective (RBO) network
The user role of user determines the user role of target user, so as to complete the identification for risk subscribers.It is apparent that area
Not in existing identification method, the present invention will individually construct relational network, and be based on existing in relational network with target user
The identity of the other users of relevance infers the user role of target user, this kind of mode just allows for fraud molecule exists
Clique's property crime characteristic, showed in the accuracy of recognition result it is more excellent, so, it is believed that, solve existing identification side
What formula be there is technical issues that cannot accurately identify.
Detailed description of the invention
Fig. 1 is the user device architecture schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is the flow diagram of risk subscribers recognition methods first embodiment of the present invention；
Fig. 3 is the schematic diagram of relationship by objective (RBO) network；
Fig. 4 is the flow diagram of risk subscribers recognition methods second embodiment of the present invention；
Fig. 5 is the flow diagram of risk subscribers recognition methods 3rd embodiment of the present invention；
Fig. 6 is the structural block diagram of risk subscribers identification device first embodiment of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the user device architecture schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
As shown in Figure 1, the user equipment may include: processor 1001, such as CPU, communication bus 1002, user interface
1003, network interface 1004, memory 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen (Display), optional user interface 1003 can also include standard wireline interface,
Wireless interface, the wireline interface for user interface 1003 can be USB interface in the present invention.Network interface 1004 optionally may be used
To include standard wireline interface and wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory, can also
To be stable memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be
Independently of the storage device of aforementioned processor 1001.
It will be understood by those skilled in the art that structure shown in Fig. 1 does not constitute the restriction to user equipment, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe module, Subscriber Interface Module SIM and risk subscribers recognizer.
In user equipment shown in Fig. 1, network interface 1004 is mainly used for connecting background server, takes with the backstage
Business device carries out data communication；User interface 1003 is mainly used for connecting peripheral hardware；The user equipment is called by processor 1001
The risk subscribers recognizer stored in memory 1005, and execute risk subscribers recognition methods provided in an embodiment of the present invention.
Based on above-mentioned hardware configuration, the embodiment of risk subscribers recognition methods of the present invention is proposed.
It is the flow diagram of risk subscribers recognition methods first embodiment of the present invention referring to Fig. 2, Fig. 2.
In the first embodiment, the risk subscribers recognition methods the following steps are included:
Step S10: the personal information of target user is obtained, and creates mesh corresponding with the personal information of the target user
Mark node；
It is understood that the mode in view of traditional identification loan fraud clique is the reference based on the personnel of having provided a loan
Information or third party's data identify operation come the credit risk user completed, still, this kind of mode only by reference information or
Third party's data can not guarantee the accuracy of recognition result as voucher is identified well.In order to more accurately identify
Whether the identity that user is judged based on relational network is risk subscribers by risk subscribers, the present embodiment, this kind of mode will be based on
The identity of other users to judge indirectly the identity of active user, shows in the identification accuracy for identifying loan fraud molecule
It is more excellent.
In the concrete realization, after user A has handled loan transaction, user A can fill in it when due to handling loan transaction
Personal information can construct relational network based on its personal information.Wherein, personal information include cell-phone number, contact person, address,
Mailbox, Business Name and fingerprint etc..
Step S20: the destination node is added in preset relation network, and by add node after preset relation net
Network is set as relationship by objective (RBO) network, and the preset relation network is by default node corresponding with each user and each default node of connection
Connection side constitute；
It should be understood that the building of relational network and extension will consider relational network based on graph theory
Characteristic, the network constructed will be made of the connection side of multiple nodes and each node of connection, wherein node is used to represent not
Same entity, and side is then used to the relationship between presentation-entity.
In the concrete realization, the node in the present embodiment indicates user, and side indicates existing incidence relation between user,
Specifically, the personal information based on user A is constructed relational network by the present embodiment, will include in the relational network constructed
Pre-existing default node and the node A for representing user A.Wherein, presetting node indicates the other users provided a loan.Specifically
It can be found in Fig. 3, Fig. 3 is the schematic diagram of relationship by objective (RBO) network, and node B, node C and node D in figure are default node.
In the concrete realization, in order to successfully construct relationship by objective (RBO) network, preset relation network can first be obtained, wherein
Preset relation network is made of each default node with the connection side for connecting each default node, reference can be made to Fig. 3, preset relation network packet
Between the node D and these three nodes that include the node B for indicating user B, the node C for indicating user C, expression user D
Connect side.
It is understood that egress A can be created after getting preset relation network, and node A is added to default
In relational network, so that relationship by objective (RBO) network as shown in Figure 3 will be obtained.
Step S30: determining corresponding with target user association user in the relationship by objective (RBO) network, and inquire and
The corresponding association user role of the association user；
It should be understood that after constructing relationship by objective (RBO) network as shown in Figure 3, due to node A and other nodes it
Between there is connection side, then it represents that there is juxtapositions between the personal information of node A and the personal information of other nodes
Situation, for example, the Business Name that may be recorded in the personal information of node A may be with the public affairs that record in the personal information of node D
It is identical to take charge of title, it is also possible to which there is social networks etc. between the user that the user and node D that node A is indicated indicate.
It is understood that in view of loan fraud molecule exists mostly in the form of loan fraud clique, so, this implementation
Example exactly carries out the identification of potential fraud molecule using the characteristic that its clique's property is committed a crime, so, it can be based on the identity of association user
To infer indirectly the identity of user A.
Step S40: whether the user role based on target user described in the association user Role judgement is risk subscribers.
It should be understood that node D expression can be obtained after inquiring the node D that there is connection side between node A
The user role of association user.
In the concrete realization, the user role of each user in relational network can be classified, for example, default fraud point
Sub, potential fraud molecule, that is, risk subscribers and normal users etc., wherein default fraud molecule indicates existing loan fraud row
For user, risk subscribers expression do not record loan fraud behavior also but infer its can be carried out the risk of loan fraud use
Family.So if the user role for the user that node D is indicated is to preset fraud molecule or risk subscribers, it can be by target user's
User role also regards as risk subscribers, so as to complete the identification for risk subscribers.
Relationship by objective (RBO) network will be constructed based on personal information in the present embodiment, and according to the pass in relationship by objective (RBO) network
The user role at family is combined to determine the user role of target user, so as to complete the identification for risk subscribers.It is apparent that
It is different from existing identification method, the present embodiment will individually construct relational network, and be based in relational network and target user
The user role of target user is inferred there are the identity of the other users of relevance, this kind of mode is just allowing for fraud molecule
There are clique's property crime characteristic, showed in the accuracy of recognition result it is more excellent, so, it is believed that, solve existing knowledge
What other mode be there is technical issues that cannot accurately identify.
It is the flow diagram of risk subscribers recognition methods second embodiment of the present invention referring to Fig. 4, Fig. 4, is based on above-mentioned Fig. 2
Shown in first embodiment, propose the second embodiment of risk subscribers recognition methods of the present invention.
In second embodiment, the step S20 may include:
Step S201: the personal information of the target user is matched with default personal information；
It is understood that in view of there is connection sides between each node, and connect side will indicate connected node it
Between incidence relation.If the information incidence relation regarded as between the personal information of the user of connected node expression is similar
Property, the matching operation of personal information can be first carried out.Wherein, presetting personal information indicates the personal information of user of having provided a loan.
Step S202: it in successful match, determines default node corresponding with the default personal information of successful match and sets
For associated nodes；
It should be understood that the matching operation of personal information is specifically, can be first by the Business Name of user A with user B's
Business Name is matched, if the Business Name of the two is not identical, the addition connection side not between node A and node B；It can incite somebody to action
The Business Name of user A is matched with the Business Name of user D, if the Business Name of the two is identical, then it is assumed that user A and use
There are certain information similitudes between the D of family.
Step S203: the destination node is added in the preset relation network, and adds the connection association section
The connection side of point and the destination node；
It is understood that connection side can be added between node A and node B if there is incidence relation therebetween.
Step S204: the preset relation network after change is set as relationship by objective (RBO) network.
Further, the association user corresponding with the target user determining in the relationship by objective (RBO) network, and
Inquire association user role corresponding with the association user, comprising:
The default node that there is connection side between the destination node is being searched in the relationship by objective (RBO) network；
User corresponding with there is the connection default node on side is regarded as into association user, and is inquired and the association user
Corresponding association user role；
Whether the user role based on target user described in the association user Role judgement is risk subscribers, packet
It includes:
When the user role of the association user is default fraud molecule, by the user role identification of the target user
For risk subscribers.
In the concrete realization, for assert that the identification of potential fraud molecule operates specifically, by first finding between node A
In the presence of the node D on connection side.
It is understood that after determining node D, if the user role of user D is default fraud molecule, use can be estimated
The user role of family A is risk subscribers.Certainly, if the user role of user D is risk subscribers, the user of user A can also be estimated
Role is risk subscribers.
In the present embodiment will by comparison target user and existing subscriber personal information come establish target user with
There is the connection side between user, so that incidence relation described in relationship by objective (RBO) network has higher confidence level.
It is the flow diagram of risk subscribers recognition methods 3rd embodiment of the present invention referring to Fig. 5, Fig. 5, is based on above-mentioned Fig. 4
Shown in second embodiment, propose the 3rd embodiment of risk subscribers recognition methods of the present invention.
In 3rd embodiment, the personal information of the target user is made of the sub-information of each information type；
The step S201, comprising:
Step S2011: by the sub-information in the sub-information and default personal information in the personal information of the target user
It is compared, and counts the identical target item number of sub-information；
It is understood that the matching operation of personal information is directed to, in addition to judging the Business Name of user A with user D's
Outside the whether identical mode of Business Name, the personal information of all types can be also comprehensively considered, so that the association finally picked out
There is more believable node relevance between node and destination node.
It in the concrete realization, include cell-phone number, contact person, address, postal since there are much information types for personal information
Case, Business Name and fingerprint etc., the personal information of each information type are all a sub-information.Judging user A and its
When incidence relation between his user, the personal information that user A can be calculated sub-information identical with the personal information of other users
Item number, for example, the Business Name of user A, address and cell-phone number are identical with user D, then the target item number counted
It is 3.
Step S2012: when the target item number is greater than or equal to preset standard item number, assert of the target user
People's information and the default personal information successful match.
It should be understood that if setting preset standard item number is 2.Since target item number is greater than preset standard item number, then may be used
Think that there is certain incidence relations between user A and user D, and the connection being successfully established between node A and node D
Side.
Further, described in successful match, determine default node corresponding with the default personal information of successful match
And it is set as after associated nodes, the risk subscribers recognition methods further include:
Determine association user corresponding with the associated nodes；
The corresponding relationship between the target item number and the association user is established, and the corresponding relationship is added to pre-
It include the corresponding relationship between item number and user if connecting in the mapping relations of side, in the default connection side mapping relations；
Whether the user role based on target user described in the association user Role judgement is risk subscribers, packet
It includes:
Obtain role's value-at-risk corresponding with the association user role；
Inquire corresponding target item number in the default connection side mapping relations according to the association user, and determine with
The corresponding weight coefficient of the target item number；
Target risk value is calculated according to role's value-at-risk and the weight coefficient；
When the target risk value is greater than or equal to default value-at-risk, the user role of the target user is regarded as
Risk subscribers.
It is understood that the identical target item number of the sub-information counted is in addition to can be used for judging user A and other
It whether there is outside certain incidence relation between user, it may also be used for determine user role belonging to user A.
In the concrete realization, it when the target item number counted is 3, can accordingly be deposited in default connection side mapping relations
User D and target item number 3 are stored up, to be used for subsequent role's decision.As for subsequent role's decision specifically, can
It first determines the user role of user D, for example, the user role of user D is " default fraud molecule ", and obtains corresponding role's wind
Danger value is 100.Wherein, role's value-at-risk is used to characterize the risk of fraud of user；Also, the user role of each type is deposited
In corresponding role's value-at-risk, with for further evaluation, there are the risk of fraud of associated other users with the user.
It should be understood that the corresponding relationship for being stored with target item number and weight coefficient can be preset, for example, if target
Item number is x=0, and x is integer, then weight coefficient q is 0.5；If target item number is 1≤x≤2, weight coefficient q is 0.7；If mesh
Mark item number is 3≤x≤5, then weight coefficient q is 0.8；If target item number is x >=6, weight coefficient q is 0.9.So working as mesh
When mark item number is 3, corresponding weight coefficient is 0.8.
It is understood that the risk of fraud in order to determine user A, in combination with the risk of fraud and use of user D
Incidence relation between family A and user D determines jointly, so determines that the risk of fraud of user A combines the information of various dimensions
Confidence level with higher.Wherein, role's value-at-risk of user D is for judging its risk of fraud, and weight coefficient is for commenting
Sentence the power of the incidence relation between user A and user D.
In the concrete realization, the target risk value of user A can be calculated based on default value-at-risk calculation formula, wherein
Presetting value-at-risk calculation formula is,
M2=M1*q；
Wherein, M2Indicate target risk value, M1Indicate role's value-at-risk, and q indicates weight coefficient.If role's wind of user D
Danger value M1It is 100, weight coefficient 0.8, then calculated M2It is 80, calculated M2For judging the risk of fraud of user A
Property, M2Numerical value it is bigger, indicate the user carry out loan fraud behavior a possibility that it is bigger.
It is understood that 75 can be set by default value-at-risk, due to M2Greater than 75, then user A can be regarded as wind
Dangerous user.
Further, it is described target risk value is calculated according to role's value-at-risk and the weight coefficient after, institute
State risk subscribers recognition methods further include:
When the target risk value is less than default value-at-risk, the reference information of the target user is obtained；
Corresponding reference credit value is generated according to the reference information；
When the reference credit value is less than default credit value, the user role of the target user is regarded as into risk and is used
Family.
It is understood that judging whether user A is risk subscribers by relational network in addition to the present embodiment description
Judgment mode, the judgement for risk subscribers can be also completed in combination with reference information, can be in combination with two ways
Greatly improve the accuracy of judging result.
In the concrete realization, if calculated M2It is less than default value-at-risk for 70, description individual subscriber credit wind can be called
The reference information of danger, and obtain a reference credit value.For example, if the reference information of user A is assessed as well, it is corresponding
Reference credit value is 85；If the reference information of user A be assessed as it is medium, corresponding reference credit value be 70；If user A's
Reference information be assessed as it is poor, then corresponding reference credit value be 60.
It should be understood that if the reference credit value of user A is 60, and pre-set default credit value is 70, then may be used
User A is defined as risk subscribers, user A is subsequent repay when will in advance in the normal collection date carry out fund urge
It receives, more effectively to retrieve economic losses, and controls economic risk.
Further, described when the reference credit value is less than default credit value, by the user angle of the target user
After color regards as risk subscribers, the risk subscribers recognition methods further include:
The numerical value of the target risk value is revised as the default value-at-risk.
In the concrete realization, it is contemplated that after determining user A based on reference information for risk subscribers, due to before based on closing
Be network determine user A be not risk subscribers, so, will modify relational network in user A value-at-risk 70.Specifically,
Since when value-at-risk is greater than or equal to default value-at-risk, corresponding user role is " risk subscribers ", so, relationship can be modified
The value-at-risk of user A in network is 75, and the user role finally to decide user A is being answered for " risk subscribers " convenient for subsequent
Exist when being assert with the role that relational network carries out other users and assert error.
User role will be judged by value-at-risk in the present embodiment, not only combines the risk of association user,
It is strong and weak with reference to the relevance between association user and this user, so that the judgement for user role is more accurate and comprehensive.
In addition, the embodiment of the present invention also proposes a kind of storage medium, risk subscribers identification is stored on the storage medium
Program, the risk subscribers recognizer realize the step of risk subscribers recognition methods as described above when being executed by processor
Suddenly.
In addition, the embodiment of the present invention also proposes a kind of risk subscribers identification device, the risk subscribers identification referring to Fig. 6
Device includes:
Node creation module 10 for obtaining the personal information of target user, and creates the individual with the target user
The corresponding destination node of information；
It is understood that the mode in view of traditional identification loan fraud clique is the reference based on the personnel of having provided a loan
Information or third party's data identify operation come the credit risk user completed, still, this kind of mode only by reference information or
Third party's data can not guarantee the accuracy of recognition result as voucher is identified well.In order to more accurately identify
Whether the identity that user is judged based on relational network is risk subscribers by risk subscribers, the present embodiment, this kind of mode will be based on
The identity of other users to judge indirectly the identity of active user, shows in the identification accuracy for identifying loan fraud molecule
It is more excellent.
In the concrete realization, after user A has handled loan transaction, user A can fill in it when due to handling loan transaction
Personal information can construct relational network based on its personal information.Wherein, personal information include cell-phone number, contact person, address,
Mailbox, Business Name and fingerprint etc..
Network struction module 20, for the destination node to be added in preset relation network, and will be after addition node
Preset relation network be set as relationship by objective (RBO) network, the preset relation network is by default node corresponding with each user and company
The connection side for connecing each default node is constituted；
It should be understood that the building of relational network and extension will consider relational network based on graph theory
Characteristic, the network constructed will be made of the connection side of multiple nodes and each node of connection, wherein node is used to represent not
Same entity, and side is then used to the relationship between presentation-entity.
In the concrete realization, the node in the present embodiment indicates user, and side indicates existing incidence relation between user,
Specifically, the personal information based on user A is constructed relational network by the present embodiment, will include in the relational network constructed
Pre-existing default node and the node A for representing user A.Wherein, presetting node indicates the other users provided a loan.Specifically
It can be found in Fig. 3, Fig. 3 is the schematic diagram of relationship by objective (RBO) network, and node B, node C and node D in figure are default node.
In the concrete realization, in order to successfully construct relationship by objective (RBO) network, preset relation network can first be obtained, wherein
Preset relation network is made of each default node with the connection side for connecting each default node, reference can be made to Fig. 3, preset relation network packet
Between the node D and these three nodes that include the node B for indicating user B, the node C for indicating user C, expression user D
Connect side.
It is understood that egress A can be created after getting preset relation network, and node A is added to default
In relational network, so that relationship by objective (RBO) network as shown in Figure 3 will be obtained.
Role determination module 30, for determining that association corresponding with the target user is used in the relationship by objective (RBO) network
Family, and inquire association user role corresponding with the association user；
It should be understood that after constructing relationship by objective (RBO) network as shown in Figure 3, due to node A and other nodes it
Between there is connection side, then it represents that there is juxtapositions between the personal information of node A and the personal information of other nodes
Situation, for example, the Business Name that may be recorded in the personal information of node A may be with the public affairs that record in the personal information of node D
It is identical to take charge of title, it is also possible to which there is social networks etc. between the user that the user and node D that node A is indicated indicate.
It is understood that in view of loan fraud molecule exists mostly in the form of loan fraud clique, so, this implementation
Example exactly carries out the identification of potential fraud molecule using the characteristic that its clique's property is committed a crime, so, it can be based on the identity of association user
To infer indirectly the identity of user A.
Role's determination module 40, for the user role based on target user described in the association user Role judgement whether
For risk subscribers.
It should be understood that node D expression can be obtained after inquiring the node D that there is connection side between node A
The user role of association user.
In the concrete realization, the user role of each user in relational network can be classified, for example, default fraud point
Sub, potential fraud molecule, that is, risk subscribers and normal users etc., wherein default fraud molecule indicates existing loan fraud row
For user, risk subscribers expression do not record loan fraud behavior also but infer its can be carried out the risk of loan fraud use
Family.So if the user role for the user that node D is indicated is to preset fraud molecule or risk subscribers, it can be by target user's
User role also regards as risk subscribers, so as to complete the identification for risk subscribers.
Relationship by objective (RBO) network will be constructed based on personal information in the present embodiment, and according to the pass in relationship by objective (RBO) network
The user role at family is combined to determine the user role of target user, so as to complete the identification for risk subscribers.It is apparent that
It is different from existing identification method, the present embodiment will individually construct relational network, and be based in relational network and target user
The user role of target user is inferred there are the identity of the other users of relevance, this kind of mode is just allowing for fraud molecule
There are clique's property crime characteristic, showed in the accuracy of recognition result it is more excellent, so, it is believed that, solve existing knowledge
What other mode be there is technical issues that cannot accurately identify.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.If listing equipment for drying
Unit claim in, several in these devices, which can be, to be embodied by the same item of hardware.Word first,
Second and the use of third etc. do not indicate any sequence, can be title by these word explanations.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, computer, clothes
Business device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of risk subscribers recognition methods, which is characterized in that the risk subscribers recognition methods the following steps are included:
The personal information of target user is obtained, and creates destination node corresponding with the personal information of the target user；
The destination node is added in preset relation network, and the preset relation network after addition node is set as target and is closed
It is network, the preset relation network is by default node corresponding with each user and the connection side structure of each default node of connection
At；
Association user corresponding with the target user is determined in the relationship by objective (RBO) network, and is inquired and the association user
Corresponding association user role；
Whether the user role based on target user described in the association user Role judgement is risk subscribers.
2. risk subscribers recognition methods as described in claim 1, which is characterized in that described that the destination node is added to institute
It states in preset relation network, and the preset relation network after addition node is set as relationship by objective (RBO) network, comprising:
The personal information of the target user is matched with default personal information；
In successful match, determines default node corresponding with the default personal information of successful match and be set as associated nodes；
The destination node is added in the preset relation network, and adds the connection associated nodes and the target section
The connection side of point；
Preset relation network after change is set as relationship by objective (RBO) network.
3. risk subscribers recognition methods as claimed in claim 2, which is characterized in that described true in the relationship by objective (RBO) network
Fixed association user corresponding with the target user, and inquire association user role corresponding with the association user, comprising:
The default node that there is connection side between the destination node is being searched in the relationship by objective (RBO) network；
User corresponding with there is the connection default node on side is regarded as into association user, and is inquired corresponding with the association user
Association user role；
Whether the user role based on target user described in the association user Role judgement is risk subscribers, comprising:
When the user role of the association user is default fraud molecule, the user role of the target user is regarded as into wind
Dangerous user.
4. risk subscribers recognition methods as claimed in claim 2, which is characterized in that the personal information of the target user is by each
The sub-information of information type is constituted；
The personal information by the target user is matched with default personal information, comprising:
Sub-information in the personal information of the target user is compared with the sub-information in default personal information, and is counted
The identical target item number of sub-information；
When the target item number is greater than or equal to preset standard item number, assert the personal information of the target user with it is described pre-
If personal information successful match.
5. risk subscribers recognition methods as claimed in claim 4, which is characterized in that it is described in successful match, determine with
With the successful default corresponding default node of personal information and after being set as associated nodes, the risk subscribers recognition methods is also wrapped
It includes:
Determine association user corresponding with the associated nodes；
The corresponding relationship between the target item number and the association user is established, and the corresponding relationship is added to default company
It include the corresponding relationship between item number and user in edge fit mapping relations, in the default connection side mapping relations；
Whether the user role based on target user described in the association user Role judgement is risk subscribers, comprising:
Obtain role's value-at-risk corresponding with the association user role；
Inquire corresponding target item number in the default connection side mapping relations according to the association user, and it is determining with it is described
The corresponding weight coefficient of target item number；
Target risk value is calculated according to role's value-at-risk and the weight coefficient；
When the target risk value is greater than or equal to default value-at-risk, the user role of the target user is regarded as into risk
User.
6. risk subscribers recognition methods as claimed in claim 5, which is characterized in that described according to role's value-at-risk and institute
State the risk subscribers recognition methods after weight coefficient calculates target risk value further include:
When the target risk value is less than default value-at-risk, the reference information of the target user is obtained；
Corresponding reference credit value is generated according to the reference information；
When the reference credit value is less than default credit value, the user role of the target user is regarded as into risk subscribers.
7. risk subscribers recognition methods as claimed in claim 6, which is characterized in that described to be less than in advance in the reference credit value
If when credit value, after the user role of the target user is regarded as risk subscribers, the risk subscribers recognition methods is also
Include:
The numerical value of the target risk value is revised as the default value-at-risk.
8. a kind of user equipment, which is characterized in that the user equipment includes: memory, processor and is stored in the storage
It operation risk user recognizer, the risk subscribers recognizer can be held on device and by the processor on the processor
The step of risk subscribers recognition methods as described in any one of claims 1 to 7 is realized when row.
9. a kind of storage medium, which is characterized in that be stored with risk subscribers recognizer on the storage medium, the risk is used
The step of the risk subscribers recognition methods as described in any one of claims 1 to 7 is realized when family recognizer is executed by processor
Suddenly.
10. a kind of risk subscribers identification device, which is characterized in that the risk subscribers identification device includes:
Node creation module for obtaining the personal information of target user, and creates the personal information pair with the target user
The destination node answered；
Network struction module, for the destination node to be added in preset relation network, and will be default after addition node
Relational network is set as relationship by objective (RBO) network, and the preset relation network is each pre- by default node corresponding with each user and connection
If the connection side of node is constituted；
Role determination module, for determining association user corresponding with the target user in the relationship by objective (RBO) network, and
Inquire association user role corresponding with the association user；
Whether role's determination module is risk for the user role based on target user described in the association user Role judgement
User.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811129426.1A CN109670937A (en) | 2018-09-26 | 2018-09-26 | Risk subscribers recognition methods, user equipment, storage medium and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811129426.1A CN109670937A (en) | 2018-09-26 | 2018-09-26 | Risk subscribers recognition methods, user equipment, storage medium and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109670937A true CN109670937A (en) | 2019-04-23 |
Family
ID=66142038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811129426.1A Withdrawn CN109670937A (en) | 2018-09-26 | 2018-09-26 | Risk subscribers recognition methods, user equipment, storage medium and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670937A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135978A (en) * | 2019-04-25 | 2019-08-16 | 北京淇瑀信息科技有限公司 | User's financial risks appraisal procedure, device, electronic equipment and readable medium |
| CN110223165A (en) * | 2019-06-14 | 2019-09-10 | 哈尔滨哈银消费金融有限责任公司 | A kind of anti-fraud and credit risk forecast method and system based on related network |
| CN110689426A (en) * | 2019-09-30 | 2020-01-14 | 中诚信征信有限公司 | Risk identification method and device, electronic equipment and storage medium |
| CN110852878A (en) * | 2019-11-26 | 2020-02-28 | 中国建设银行股份有限公司 | Credibility determination method, device, equipment and storage medium |
| CN110956391A (en) * | 2019-11-28 | 2020-04-03 | 中信银行股份有限公司 | Information processing method based on finance and electronic equipment |
| CN111049809A (en) * | 2019-11-27 | 2020-04-21 | 深圳壹账通智能科技有限公司 | Risk user identification method and device, computer equipment and storage medium |
| CN111291234A (en) * | 2020-03-31 | 2020-06-16 | 京东数字科技控股有限公司 | Account risk probability assessment method, device and system and storage medium |
| CN111861281A (en) * | 2020-08-05 | 2020-10-30 | 中国银行股份有限公司 | Knowledge graph-based risk employee discovery method and device |
| CN112053174A (en) * | 2020-09-29 | 2020-12-08 | 中国银行股份有限公司 | Method, device and equipment for determining relation between bank customer and teller |
| CN112102093A (en) * | 2020-08-05 | 2020-12-18 | 中证征信（深圳）有限公司 | Method, device, equipment and medium for identifying subject identity and incidence relation |
| CN112330468A (en) * | 2020-11-03 | 2021-02-05 | 中国平安财产保险股份有限公司 | Method, device, equipment and storage medium for identifying risk client |
| CN113762684A (en) * | 2020-12-14 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | New user risk assessment method and device, electronic equipment and medium |
| CN114003648A (en) * | 2021-10-20 | 2022-02-01 | 支付宝(杭州)信息技术有限公司 | Risk transaction group partner identification method and device, electronic equipment and storage medium |
-
2018
- 2018-09-26 CN CN201811129426.1A patent/CN109670937A/en not_active Withdrawn
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135978B (en) * | 2019-04-25 | 2021-07-30 | 北京淇瑀信息科技有限公司 | User financial risk assessment method and device, electronic equipment and readable medium |
| CN110135978A (en) * | 2019-04-25 | 2019-08-16 | 北京淇瑀信息科技有限公司 | User's financial risks appraisal procedure, device, electronic equipment and readable medium |
| CN110223165A (en) * | 2019-06-14 | 2019-09-10 | 哈尔滨哈银消费金融有限责任公司 | A kind of anti-fraud and credit risk forecast method and system based on related network |
| CN110689426A (en) * | 2019-09-30 | 2020-01-14 | 中诚信征信有限公司 | Risk identification method and device, electronic equipment and storage medium |
| CN110852878A (en) * | 2019-11-26 | 2020-02-28 | 中国建设银行股份有限公司 | Credibility determination method, device, equipment and storage medium |
| CN110852878B (en) * | 2019-11-26 | 2022-08-26 | 中国建设银行股份有限公司 | Credibility determination method, device, equipment and storage medium |
| CN111049809A (en) * | 2019-11-27 | 2020-04-21 | 深圳壹账通智能科技有限公司 | Risk user identification method and device, computer equipment and storage medium |
| CN110956391A (en) * | 2019-11-28 | 2020-04-03 | 中信银行股份有限公司 | Information processing method based on finance and electronic equipment |
| CN111291234A (en) * | 2020-03-31 | 2020-06-16 | 京东数字科技控股有限公司 | Account risk probability assessment method, device and system and storage medium |
| CN111861281A (en) * | 2020-08-05 | 2020-10-30 | 中国银行股份有限公司 | Knowledge graph-based risk employee discovery method and device |
| CN112102093A (en) * | 2020-08-05 | 2020-12-18 | 中证征信（深圳）有限公司 | Method, device, equipment and medium for identifying subject identity and incidence relation |
| CN112053174A (en) * | 2020-09-29 | 2020-12-08 | 中国银行股份有限公司 | Method, device and equipment for determining relation between bank customer and teller |
| CN112053174B (en) * | 2020-09-29 | 2024-03-29 | 中国银行股份有限公司 | Method, device and equipment for determining relationship between bank clients and teller |
| CN112330468A (en) * | 2020-11-03 | 2021-02-05 | 中国平安财产保险股份有限公司 | Method, device, equipment and storage medium for identifying risk client |
| CN112330468B (en) * | 2020-11-03 | 2023-10-27 | 中国平安财产保险股份有限公司 | Method, device, equipment and storage medium for identifying risk clients |
| CN113762684A (en) * | 2020-12-14 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | New user risk assessment method and device, electronic equipment and medium |
| CN114003648A (en) * | 2021-10-20 | 2022-02-01 | 支付宝(杭州)信息技术有限公司 | Risk transaction group partner identification method and device, electronic equipment and storage medium |
| CN114003648B (en) * | 2021-10-20 | 2024-04-26 | 支付宝(杭州)信息技术有限公司 | Identification method and device for risk transaction group partner, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670937A (en) | Risk subscribers recognition methods, user equipment, storage medium and device | |
| WO2019154115A1 (en) | Resource transferring monitoring method and device | |
| CN107563757B (en) | Data risk identification method and device | |
| CN108615119B (en) | Abnormal user identification method and equipment | |
| CN108876600A (en) | Warning information method for pushing, device, computer equipment and medium | |
| CN105824813B (en) | A kind of method and device for excavating core customer | |
| CN107169629A (en) | A kind of telecommunication fraud recognition methods and data processing equipment | |
| CN109949154B (en) | Customer information classification method, apparatus, computer device and storage medium | |
| CN107153847A (en) | Predict method and computing device of the user with the presence or absence of malicious act | |
| CN109670933A (en) | Identify method, user equipment, storage medium and the device of user role | |
| CN110956503B (en) | User identification method and device with lending requirements based on user network behaviors | |
| CN106156151A (en) | The Risk Identification Method of internetwork operation event and device | |
| CN110378575B (en) | Overdue event refund collection method and device and computer readable storage medium | |
| CN109472656B (en) | Virtual article display method and device and storage medium | |
| CN110363644A (en) | Exception information recognition methods, device, computer equipment and storage medium | |
| CN108595579A (en) | Contact person's cohesion evaluation method, device, computer equipment and storage medium | |
| CN109598542A (en) | A kind of put-on method, device and the electronic equipment of equity of marketing | |
| CN110609908A (en) | Case serial-parallel method and device | |
| CN110728301A (en) | Credit scoring method, device, terminal and storage medium for individual user | |
| CN114693192A (en) | Wind control decision method and device, computer equipment and storage medium | |
| CN113641827A (en) | Phishing network identification method and system based on knowledge graph | |
| CN110909129B (en) | Abnormal complaint event identification method and device | |
| CN109636570A (en) | Risk analysis method, device, equipment and the readable storage medium storing program for executing of cell-phone number | |
| CN111105064A (en) | Method and device for determining suspected information of fraud event | |
| CN113538126A (en) | Fraud risk prediction method and device based on GCN |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190423 |
|
| WW01 | Invention patent application withdrawn after publication |