CN110348978A - The recognition methods of risk clique, device, equipment and the storage medium calculated based on figure - Google Patents
The recognition methods of risk clique, device, equipment and the storage medium calculated based on figure Download PDFInfo
- Publication number
- CN110348978A CN110348978A CN201910654287.2A CN201910654287A CN110348978A CN 110348978 A CN110348978 A CN 110348978A CN 201910654287 A CN201910654287 A CN 201910654287A CN 110348978 A CN110348978 A CN 110348978A
- Authority
- CN
- China
- Prior art keywords
- network
- service request
- service
- type
- risk
- 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
Abstract
This specification embodiment provides a kind of recognition methods of risk clique, device, equipment and storage medium calculated based on figure, this method, comprising: receives service request, the service request includes type of service and customer attribute information；To the type of service, the customer attribute information and history service data corresponding with the service request, social network analysis is carried out, to generate corresponding community network；Go out sub-network corresponding with the service request from the social community finding according to condensation degree；The adjacency matrix of the sub-network is inputted into preset prediction model, obtains the corresponding risk clique recognition result of the service request.The recognition detection to the risk clique in financial business may be implemented in this specification embodiment.
Description
Technical field
This specification is related to field of artificial intelligence, more particularly, to a kind of identification side, risk clique calculated based on figure
Method, device, equipment and storage medium.
Background technique
It is more various for the fraudulent mean of financial product under the background that financial product and the Internet converged are constantly deepened
And high-tech, iteration upgrading, renovation rapidly, the bands such as channel on line, strange land apply for card, trans-regional trans channel is fled about to commit crimes, black intermediary
Carry out new risk of fraud gradually to show, clique's fraud fraud situation is further severe.In view of this, how to identify that risk clique has become
For technical problem urgently to be resolved at present.
Summary of the invention
This specification embodiment be designed to provide it is a kind of based on figure calculate the recognition methods of risk clique, device, set
Standby and storage medium, to identify the risk clique in financial business.
In order to achieve the above objectives, on the one hand, this specification embodiment provides a kind of risk clique knowledge calculated based on figure
Other method, comprising:
Service request is received, the service request includes type of service and customer attribute information；
To the type of service, the customer attribute information and history service data corresponding with the service request, into
Row social network analysis, to generate corresponding community network；
Go out sub-network corresponding with the service request from the social community finding according to condensation degree；
The adjacency matrix of the sub-network is inputted into preset prediction model, obtains the corresponding risk group of the service request
Partner's recognition result.
The risk clique recognition methods of this specification embodiment calculated based on figure, it is described according to condensation degree from the society
Community finding goes out sub-network corresponding with the service request, comprising:
According to preset community discovery algorithm, determine in the community network that its condensation degree reaches condensation degree threshold value, and with
The corresponding sub-network of the service request.
The risk clique recognition methods of this specification embodiment calculated based on figure, the prediction model include:
Wherein, y is risk clique predicted value, xmFor m-th of type of service, αmFor the weight of m-th of type of service, xnFor
N-th of incidence relation type, βnFor the weight of n-th of incidence relation type, xpFor p-th of fraud black list type, γpFor pth
The weight of a fraud black list type, K, J and L are respectively type of service, incidence relation type and the number for cheating black list type
Amount.
The risk clique recognition methods of this specification embodiment calculated based on figure, the node set in the adjacency matrix
Including the service request logo collection in the sub-network, the line set in the adjacency matrix includes the sub-network interior joint
Between incidence relation set.
On the other hand, this specification embodiment additionally provides a kind of risk clique identification device calculated based on figure, comprising:
Service request receiving module, for receiving service request, the service request includes type of service and user property
Information；
Social network analysis module, for the type of service, the customer attribute information and with the service request
Corresponding history service data carry out social network analysis, to generate corresponding community network；
Community network divides module, for being gone out and the service request pair according to condensation degree from the social community finding
The sub-network answered；
Risk clique prediction module obtains institute for the adjacency matrix of the sub-network to be inputted preset prediction model
State the corresponding risk clique recognition result of service request.
The risk clique identification device of this specification embodiment calculated based on figure, it is described according to condensation degree from the society
Community finding goes out sub-network corresponding with the service request, comprising:
According to preset community discovery algorithm, determine in the community network that its condensation degree reaches condensation degree threshold value, and with
The corresponding sub-network of the service request.
The risk clique identification device of this specification embodiment calculated based on figure, the prediction model include:
Wherein, y is risk clique predicted value, xmFor m-th of type of service, αmFor the weight of m-th of type of service, xnFor
N-th of incidence relation type, βnFor the weight of n-th of incidence relation type, xpFor p-th of fraud black list type, γpFor pth
The weight of a fraud black list type, K, J and L are respectively type of service, incidence relation type and the number for cheating black list type
Amount.
The risk clique identification device of this specification embodiment calculated based on figure, the node set in the adjacency matrix
Including the service request logo collection in the sub-network, the line set in the adjacency matrix includes the sub-network interior joint
Between incidence relation set.
On the other hand, this specification embodiment additionally provides a kind of computer equipment, including memory, processor and
It stores when the computer program described in the computer program on the memory is run by the processor and executes following steps:
Service request is received, the service request includes type of service and customer attribute information；
To the type of service, the customer attribute information and history service data corresponding with the service request, into
Row social network analysis, to generate corresponding community network；
Go out sub-network corresponding with the service request from the social community finding according to condensation degree；
The adjacency matrix of the sub-network is inputted into preset prediction model, obtains the corresponding risk group of the service request
Partner's recognition result.
On the other hand, this specification embodiment additionally provides a kind of computer storage medium, is stored thereon with computer journey
Sequence, the computer program perform the steps of when being executed by processor
Service request is received, the service request includes type of service and customer attribute information；
To the type of service, the customer attribute information and history service data corresponding with the service request, into
Row social network analysis, to generate corresponding community network；
Go out sub-network corresponding with the service request from the social community finding according to condensation degree；
The adjacency matrix of the sub-network is inputted into preset prediction model, obtains the corresponding risk group of the service request
Partner's recognition result.
The technical solution provided by above this specification embodiment is as it can be seen that this specification embodiment passes through to service request packet
Containing type of service, customer attribute information and history service data corresponding with service request, social network analysis is carried out, it can be with
Generate corresponding community network；On this basis, it is partitioned into from social sub-network according to condensation degree corresponding with service request
Then the adjacency matrix of the sub-network is inputted preset prediction model, so that it may it is corresponding to obtain the service request by sub-network
Risk clique recognition result, to realize the recognition detection to the risk clique in financial business.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification, for those of ordinary skill in the art, in not making the creative labor property
Under the premise of, it is also possible to obtain other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is the flow chart of the risk clique recognition methods calculated in some embodiments of this specification based on figure；
Fig. 2 is the sub-network schematic diagram gone out in one embodiment of this specification from social community finding；
Fig. 3 is the flow chart of the risk clique identification device calculated in some embodiments of this specification based on figure；
Fig. 4 is the structural block diagram of computer equipment in some embodiments of this specification.
Specific embodiment
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book embodiment is clearly and completely described the technical solution in this specification embodiment, it is clear that described
Embodiment be only this specification a part of the embodiment, instead of all the embodiments.The embodiment of base in this manual,
Every other embodiment obtained by those of ordinary skill in the art without making creative efforts, all should belong to
The range of this specification protection.
Refering to what is shown in Fig. 1, some risk clique recognition methods calculated based on figure of this specification embodiment may include
Following steps:
S101, service request is received, the service request includes type of service and customer attribute information.
S102, to the type of service, the customer attribute information and history service number corresponding with the service request
According to progress social network analysis, to generate corresponding community network.
S103, sub-network corresponding with the service request is gone out from the social community finding according to condensation degree.
S104, the adjacency matrix of the sub-network is inputted into preset prediction model, it is corresponding obtains the service request
Risk clique recognition result.
Due to being needed in service request comprising the customer attribute information as aptitude checking, and for same criminal gang,
Its customer attribute information often relevant property forged.Therefore, based on the social network analysis of artificial intelligence field
(Social Network Analysis, abbreviation SNA) technology, asks history service data corresponding with the service request, business
It asks and carries out social network analysis comprising type of service and customer attribute information, so as to generate corresponding community network；Herein
On the basis of, sub-network corresponding with service request is partitioned into from social sub-network according to condensation degree, then by the sub-network
Adjacency matrix inputs preset prediction model, so that it may the corresponding risk clique recognition result of the service request is obtained, thus real
The recognition detection to the risk clique in financial business is showed.
In one embodiment of this specification, financial production can include but is not limited to comprising type of service in the service request
The application request of product and/or transaction request etc..Wherein, financial product application request for example can be such as credit card application,
Loan application etc.；The transaction request of financial product for example can be payment transaction, money transfer transactions etc..
In one embodiment of this specification, the customer attribute information can include but is not limited to primary applicant, common Shen
It asks someone, the attribute information of supplier, buyer, contact person, guarantor；The attribute letter for example may include phone number, seat
Machine number, E-mail address, identity ID, unit address, home address etc..
In one embodiment of this specification, community network can be indicated with non-directed graph G=(V, E), wherein G is undirected
Scheme the community network indicated, E indicates the set on side in G, E={ e1,e2,···,em, V indicates the set of G interior joint, V=
{v1,v2,···,vn, it is requested using the application of financial product as Sample Scenario, it, can be with during generating community network
A node is applied for by one；If filling in the same or similar information there are two node is correlation (in social network
It shows as having line between two nodes in network, that is, has Bian Xianglian)；It is if there are two node fill message differences or dissmilarity
For uncorrelated (being shown as in community network without line between two nodes, i.e., boundless to be connected).For example two applications fill in
Identical phone number fills in similar home address labeled as the node to there are incidence relations.In addition, for ground
The non-structural data such as location and organization, it may be considered that carry out fuzzy matching processing.For example, " industrial and commercial bank " and " industrial and commercial bank "
It refers to the same entity (view node), but since title describes difference, it is two nodes that computer, which often will mistakenly believe that it,
Therefore it introduces fuzzy matching algorithm (including participle, standardization, distance calculate and etc.) and and provides similarity between address, Ke Yishi
The merging of existing node.
In this specification embodiment, risk clique crime mode can be determined by identification cyberrelationship mode,
Such as when multiple applicants uses the same contact method, it is possible to be accused of financial fraud.Therefore, for a certain industry
Business request for, find out the corporations belonging to it, be identify the corporations whether be risk clique basis.
In one embodiment of this specification, it can be partitioned into from social sub-network according to condensation degree corresponding with service request
Sub-network (be partitioned into and be accused of risk clique).Further, be accused of risk clique network cutting can be it is non-supervisory
Mode, such as can determine that its condensation degree reaches condensation degree threshold in the community network according to preset community discovery algorithm
Value, and sub-network corresponding with the service request.In some exemplary embodiments, the community discovery algorithm for example can be with
For Newman fast algorithm (FN algorithm), CNM algorithm (Finding Local Community Structure in
) or MSG-MV algorithm (Multistep Greedy Algorithm Identifies Community Networks
Structure in Real-World and Computer-Generated Networks) etc..
The application for ease of understanding is below briefly described condensation degree.
In one embodiment of this specification, the adjacency matrix H=[h of Gij] there are n row and n column, element h in HijIs defined as:
In community network, the cohesion degree (hereinafter referred to as condensation degree) of network be dependent firstly in network each node it
Between connection ability, can be measured with the average path length between node, i.e., the calculation of the shortest distance between all nodes pair
Art average value.Secondly, the condensation degree of network additionally depends on nodes quantity.Such as in a community network, node it
Between contact that more convenient, number is fewer, then the condensation degree of the community network is higher.Therefore, the condensation degree of network can be defined
Are as follows:
WhereinIndicate that the condensation degree of G, n indicate the quantity of G interior joint, dijIndicate i-th of node
With the shortest distance between j-th of node.
In one embodiment of this specification, the node set in the adjacency matrix of sub-network may include in the sub-network
Service request logo collection, the line set in the adjacency matrix includes the incidence relation collection between the sub-network interior joint
It closes.Wherein, service request mark such as can as in Fig. 2 request slip 1, (requested here with the application of financial product request slip 2
For Sample Scenario)；Incidence relation between node for example can phone relationship in such as Fig. 2, contact relationship, address relationship.
In this specification embodiment, prediction model is for judging whether sub-network (being accused of risk clique) is risk group
Group.In one embodiment of this specification, can comprehensively consider the corresponding type of service of sub-network interior joint, incidence relation type and
The dimensions such as black list type are cheated to construct prediction model, to promote the predictablity rate of prediction model.Further, it is contemplated that
Different dimensions for determine be accused of risk clique whether be risk clique contribution it is different, every kind can be tieed up according to percentage contribution
Degree assigns different weight, such as in one exemplary embodiment of this specification, and the prediction model can be with are as follows:
Wherein, y is risk clique predicted value, xmFor m-th of type of service, αmFor the weight of m-th of type of service, xnFor
N-th of incidence relation type, βnFor the weight of n-th of incidence relation type, xpFor p-th of fraud black list type, γpFor pth
The weight of a fraud black list type, K, J and L are respectively type of service, incidence relation type and the number for cheating black list type
Amount.
In one embodiment of this specification, after obtaining the corresponding risk clique recognition result of service request, if by
Verify a certain service request of confirmation through investigation is fraud really, (such as can also cheat the relevant information of the fraud
Type, customer attribute information etc.) it is updated to fraud database, and it is applied to the risk clique identification of follow-up business request.Wherein,
Fraud database for example can be the blacklist according to fraud Type division.
Detecting fraud recognition methods emphasis from tradition, individually the application true and false discrimination of part information is different, implements in this specification
In the risk clique recognition methods of example calculated based on figure, it is based on social network analysis technology, is stressed to multiple clients or group
Body carries out global behavior analysis, has the more intuitive ability of seeing clearly to clique's risk of fraud, so as to precisely identify fraud
Risk clique.Further, agglomerating time of risk clique, each time point risk can based on social network, be excavated
Clique's situation of change, the primary association relationship for forming risk clique, clique's degree of risk etc., so as to assess whole fraud
The features such as quantity, composition, area, age, the vocational distribution of clique, the total situation of overall merit clique risk of fraud, and can be into
Tendency Prediction is cheated by row clique.
Refering to what is shown in Fig. 3, this specification some implementations corresponding with the above-mentioned risk clique recognition methods calculated based on figure
Example based on figure calculate risk clique identification device may include:
Service request receiving module 31, can be used for receiving service request, and the service request includes type of service and use
Family attribute information；
Social network analysis module 32, can be used for the type of service, the customer attribute information and with the industry
Corresponding history service data are requested in business, social network analysis are carried out, to generate corresponding community network；
Community network divides module 33, can be used for being gone out and the business according to condensation degree from the social community finding
Request corresponding sub-network；
Risk clique prediction module 34 can be used for the adjacency matrix of the sub-network inputting preset prediction model,
Obtain the corresponding risk clique recognition result of the service request.
Refering to what is shown in Fig. 4, this specification some implementations corresponding with the above-mentioned risk clique recognition methods calculated based on figure
The computer equipment of example may include memory, processor and the computer program being stored on the memory, the meter
Calculation machine program executes following steps when being run by the processor:
Service request is received, the service request includes type of service and customer attribute information；
To the type of service, the customer attribute information and history service data corresponding with the service request, into
Row social network analysis, to generate corresponding community network；
Go out sub-network corresponding with the service request from the social community finding according to condensation degree；
The adjacency matrix of the sub-network is inputted into preset prediction model, obtains the corresponding risk group of the service request
Partner's recognition result.
Although procedures described above process includes the multiple operations occurred with particular order, it should however be appreciated that understand,
These processes may include more or fewer operations, these operations can be executed sequentially or be executed parallel (such as using parallel
Processor or multi-thread environment).
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when specification.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram
The step of function of being specified in one box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disc type storage or other magnetic storage devices are appointed
What his non-transmission medium, can be used for storing and can be accessed by a computing device information.As defined in this article, computer can
Reading medium not includes temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Include, so that process, method or equipment including a series of elements not only include those elements, but also including not having
There is the other element being expressly recited, or further includes for this process, method or the intrinsic element of equipment.Do not having more
In the case where more limitations, the element that is limited by sentence "including a ...", it is not excluded that including process, the side of the element
There is also other identical elements in method or equipment.
It will be understood by those skilled in the art that the embodiment of this specification can provide as the production of method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or implementation combining software and hardware aspects can be used in this specification
The form of example.Moreover, it wherein includes the computer of computer usable program code that this specification, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
This specification can describe in the general context of computer-executable instructions executed by a computer, such as journey
Sequence module.Generally, program module include routines performing specific tasks or implementing specific abstract data types, programs, objects,
Component, data structure etc..This specification can also be practiced in a distributed computing environment, in these distributed computing environment
In, by executing task by the connected remote processing devices of communication network.In a distributed computing environment, program module
It can be located in the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely the embodiments of this specification, are not limited to this specification.For art technology
For personnel, this specification can have various modifications and variations.It is all made any within the spirit and principle of this specification
Modification, equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.
Claims (10)
1. a kind of risk clique recognition methods calculated based on figure characterized by comprising
Service request is received, the service request includes type of service and customer attribute information；
To the type of service, the customer attribute information and history service data corresponding with the service request, society is carried out
Meeting network analysis, to generate corresponding community network；
Go out sub-network corresponding with the service request from the social community finding according to condensation degree；
The adjacency matrix of the sub-network is inputted into preset prediction model, the corresponding risk clique of the service request is obtained and knows
Other result.
2. the risk clique recognition methods calculated as described in claim 1 based on figure, which is characterized in that described according to condensation degree
Go out sub-network corresponding with the service request from the social community finding, comprising:
According to preset community discovery algorithm, determine in the community network that its condensation degree reaches condensation degree threshold value, and with it is described
The corresponding sub-network of service request.
3. the risk clique recognition methods calculated as described in claim 1 based on figure, which is characterized in that the prediction model packet
It includes:
Wherein, y is risk clique predicted value, xmFor m-th of type of service, αmFor the weight of m-th of type of service, xnIt is n-th
Incidence relation type, βnFor the weight of n-th of incidence relation type, xpFor p-th of fraud black list type, γpIt is taken advantage of for p-th
The weight of black list type is cheated, K, J and L are respectively type of service, incidence relation type and the quantity for cheating black list type.
4. the risk clique recognition methods calculated as described in claim 1 based on figure, which is characterized in that in the adjacency matrix
Node set include service request logo collection in the sub-network, the line set in the adjacency matrix includes the son
Incidence relation set between nodes.
5. a kind of risk clique identification device calculated based on figure characterized by comprising
Service request receiving module, for receiving service request, the service request includes type of service and customer attribute information；
Social network analysis module, for the type of service, the customer attribute information and corresponding with the service request
History service data, carry out social network analysis, to generate corresponding community network；
Community network divides module, corresponding with the service request for being gone out according to condensation degree from the social community finding
Sub-network；
Risk clique prediction module obtains the industry for the adjacency matrix of the sub-network to be inputted preset prediction model
Business request corresponding risk clique recognition result.
6. the risk clique identification device calculated as claimed in claim 5 based on figure, which is characterized in that described according to condensation degree
Go out sub-network corresponding with the service request from the social community finding, comprising:
According to preset community discovery algorithm, determine in the community network that its condensation degree reaches condensation degree threshold value, and with it is described
The corresponding sub-network of service request.
7. the risk clique identification device calculated as claimed in claim 5 based on figure, which is characterized in that the prediction model packet
It includes:
Wherein, y is risk clique predicted value, xmFor m-th of type of service, αmFor the weight of m-th of type of service, xnIt is n-th
Incidence relation type, βnFor the weight of n-th of incidence relation type, xpFor p-th of fraud black list type, γpIt is taken advantage of for p-th
The weight of black list type is cheated, K, J and L are respectively type of service, incidence relation type and the quantity for cheating black list type.
8. the risk clique identification device calculated as claimed in claim 5 based on figure, which is characterized in that in the adjacency matrix
Node set include service request logo collection in the sub-network, the line set in the adjacency matrix includes the son
Incidence relation set between nodes.
9. a kind of computer equipment, including memory, processor and the computer program being stored on the memory,
It is characterized in that, the computer program executes following steps when being run by the processor:
Service request is received, the service request includes type of service and customer attribute information；
To the type of service, the customer attribute information and history service data corresponding with the service request, society is carried out
Meeting network analysis, to generate corresponding community network；
Go out sub-network corresponding with the service request from the social community finding according to condensation degree；
The adjacency matrix of the sub-network is inputted into preset prediction model, the corresponding risk clique of the service request is obtained and knows
Other result.
10. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is located
Reason device performs the steps of when executing
Service request is received, the service request includes type of service and customer attribute information；
To the type of service, the customer attribute information and history service data corresponding with the service request, society is carried out
Meeting network analysis, to generate corresponding community network；
Go out sub-network corresponding with the service request from the social community finding according to condensation degree；
The adjacency matrix of the sub-network is inputted into preset prediction model, the corresponding risk clique of the service request is obtained and knows
Other result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910654287.2A CN110348978A (en) | 2019-07-19 | 2019-07-19 | The recognition methods of risk clique, device, equipment and the storage medium calculated based on figure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910654287.2A CN110348978A (en) | 2019-07-19 | 2019-07-19 | The recognition methods of risk clique, device, equipment and the storage medium calculated based on figure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110348978A true CN110348978A (en) | 2019-10-18 |
Family
ID=68179239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910654287.2A Pending CN110348978A (en) | 2019-07-19 | 2019-07-19 | The recognition methods of risk clique, device, equipment and the storage medium calculated based on figure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110348978A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111177150A (en) * | 2019-12-17 | 2020-05-19 | 北京明略软件系统有限公司 | Method and system for identifying group genealogy |
| CN111310780A (en) * | 2019-12-18 | 2020-06-19 | 北京明略软件系统有限公司 | Police service processing method and device |
| CN111340612A (en) * | 2020-02-25 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Account risk identification method and device and electronic equipment |
| CN111711614A (en) * | 2020-05-27 | 2020-09-25 | 平安科技（深圳）有限公司 | Knowledge graph-based suspicious user verification method and device and computer equipment |
| CN112380531A (en) * | 2020-11-11 | 2021-02-19 | 平安科技（深圳）有限公司 | Black product group partner identification method, device, equipment and storage medium |
| CN112926991A (en) * | 2021-03-30 | 2021-06-08 | 顶象科技有限公司 | Cascade group severity grade dividing method and system |
| CN112989374A (en) * | 2021-03-09 | 2021-06-18 | 闪捷信息科技有限公司 | Data security risk identification method and device based on complex network analysis |
| CN113011483A (en) * | 2021-03-11 | 2021-06-22 | 北京三快在线科技有限公司 | Method and device for model training and business processing |
| CN113743954A (en) * | 2021-06-29 | 2021-12-03 | 阳光保险集团股份有限公司 | Vehicle insurance risk network identification method and device, electronic equipment and medium |
| CN114820219A (en) * | 2022-05-23 | 2022-07-29 | 杭银消费金融股份有限公司 | Complex network-based cheating community identification method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780067A (en) * | 2016-12-14 | 2017-05-31 | 南京工业职业技术学院 | It is a kind of to consider the sign prediction method that node locally marks characteristic |
| CN107194623A (en) * | 2017-07-20 | 2017-09-22 | 深圳市分期乐网络科技有限公司 | A kind of discovery method and device of clique's fraud |
| CN108734479A (en) * | 2018-04-12 | 2018-11-02 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
| CN108764917A (en) * | 2018-05-04 | 2018-11-06 | 阿里巴巴集团控股有限公司 | It is a kind of fraud clique recognition methods and device |
| CN109658222A (en) * | 2018-10-16 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Risk analysis method, device, equipment and computer readable storage medium |
| CN109816519A (en) * | 2019-01-25 | 2019-05-28 | 宜人恒业科技发展（北京）有限公司 | A kind of recognition methods of fraud clique, device and equipment |
-
2019
- 2019-07-19 CN CN201910654287.2A patent/CN110348978A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780067A (en) * | 2016-12-14 | 2017-05-31 | 南京工业职业技术学院 | It is a kind of to consider the sign prediction method that node locally marks characteristic |
| CN107194623A (en) * | 2017-07-20 | 2017-09-22 | 深圳市分期乐网络科技有限公司 | A kind of discovery method and device of clique's fraud |
| CN108734479A (en) * | 2018-04-12 | 2018-11-02 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and the server of Insurance Fraud identification |
| CN108764917A (en) * | 2018-05-04 | 2018-11-06 | 阿里巴巴集团控股有限公司 | It is a kind of fraud clique recognition methods and device |
| CN109658222A (en) * | 2018-10-16 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Risk analysis method, device, equipment and computer readable storage medium |
| CN109816519A (en) * | 2019-01-25 | 2019-05-28 | 宜人恒业科技发展（北京）有限公司 | A kind of recognition methods of fraud clique, device and equipment |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111177150A (en) * | 2019-12-17 | 2020-05-19 | 北京明略软件系统有限公司 | Method and system for identifying group genealogy |
| CN111310780A (en) * | 2019-12-18 | 2020-06-19 | 北京明略软件系统有限公司 | Police service processing method and device |
| CN111340612A (en) * | 2020-02-25 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Account risk identification method and device and electronic equipment |
| CN111340612B (en) * | 2020-02-25 | 2022-12-06 | 支付宝(杭州)信息技术有限公司 | Account risk identification method and device and electronic equipment |
| CN111711614A (en) * | 2020-05-27 | 2020-09-25 | 平安科技（深圳）有限公司 | Knowledge graph-based suspicious user verification method and device and computer equipment |
| CN112380531A (en) * | 2020-11-11 | 2021-02-19 | 平安科技（深圳）有限公司 | Black product group partner identification method, device, equipment and storage medium |
| CN112989374A (en) * | 2021-03-09 | 2021-06-18 | 闪捷信息科技有限公司 | Data security risk identification method and device based on complex network analysis |
| CN113011483A (en) * | 2021-03-11 | 2021-06-22 | 北京三快在线科技有限公司 | Method and device for model training and business processing |
| CN113011483B (en) * | 2021-03-11 | 2022-08-05 | 北京三快在线科技有限公司 | Method and device for model training and business processing |
| CN112926991A (en) * | 2021-03-30 | 2021-06-08 | 顶象科技有限公司 | Cascade group severity grade dividing method and system |
| CN113743954A (en) * | 2021-06-29 | 2021-12-03 | 阳光保险集团股份有限公司 | Vehicle insurance risk network identification method and device, electronic equipment and medium |
| CN113743954B (en) * | 2021-06-29 | 2024-04-02 | 阳光保险集团股份有限公司 | Vehicle risk network identification method and device, electronic equipment and medium |
| CN114820219A (en) * | 2022-05-23 | 2022-07-29 | 杭银消费金融股份有限公司 | Complex network-based cheating community identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110348978A (en) | The recognition methods of risk clique, device, equipment and the storage medium calculated based on figure | |
| JP6913241B2 (en) | Systems and methods for issuing loans to consumers who are determined to be creditworthy | |
| Clohessy et al. | Blockchain adoption: Technological, organisational and environmental considerations | |
| CN111476662A (en) | Anti-money laundering identification method and device | |
| CN108416577A (en) | A kind of block chain service system | |
| KR20210116439A (en) | Systems and Methods for Anti-Money Laundering Analysis | |
| Saltos et al. | An exploration of crime prediction using data mining on open data | |
| MacLachlan et al. | Genetic programming hyper-heuristics with vehicle collaboration for uncertain capacitated arc routing problems | |
| TW201802732A (en) | Method and device for controlling data risk | |
| CN111507543A (en) | Model training method and device for predicting business relation between entities | |
| CN110796269B (en) | Method and device for generating model, and method and device for processing information | |
| CN112241549A (en) | Secure privacy calculation method, server, system, and storage medium | |
| CN112132676A (en) | Method and device for determining contribution degree of joint training target model and terminal equipment | |
| Razumnikov et al. | A model of decision support on migration of enterprise IT-applications in the cloud environment | |
| CN110851482B (en) | Method and device for providing data model for multiple data parties | |
| CN116307671A (en) | Risk early warning method, risk early warning device, computer equipment and storage medium | |
| CN112231746B (en) | Joint data analysis method, device, system and computer readable storage medium | |
| CN112750038B (en) | Transaction risk determination method, device and server | |
| CN113436006A (en) | Loan risk prediction method and device based on block chain | |
| CA3069987A1 (en) | System and method for detecting and responding to transaction patterns | |
| CN109492891B (en) | User loss prediction method and device | |
| CN114493850A (en) | Artificial intelligence-based online notarization method, system and storage medium | |
| Viswanatha et al. | Online Fraud Detection Using Machine Learning Approach | |
| US11270230B1 (en) | Self learning machine learning transaction scores adjustment via normalization thereof | |
| CN112053174B (en) | Method, device and equipment for determining relationship between bank clients and teller |
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: 20191018 |