CN109410035A - A kind of method and tool for assisting anti-fraud analysis cluster structure - Google Patents
A kind of method and tool for assisting anti-fraud analysis cluster structure Download PDFInfo
- Publication number
- CN109410035A CN109410035A CN201811153021.1A CN201811153021A CN109410035A CN 109410035 A CN109410035 A CN 109410035A CN 201811153021 A CN201811153021 A CN 201811153021A CN 109410035 A CN109410035 A CN 109410035A
- Authority
- CN
- China
- Prior art keywords
- group
- user
- association
- cluster structure
- point value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Technology Law (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of methods and tool for assisting anti-fraud analysis cluster structure, belong to data mining technology field.Described method includes following steps: S1: obtaining the information and its affiliated person's information of user；S2: judging the degree of association between each user and calculates the strength of association of each association medium；S3: according to the calculated result of the step S2, group is built；S4: to each user in the group and it is associated with media definitions label；S5: enumerating generation tables of data for all information, then carry out group's operation to new user, judges that the group of new user is sorted out.Similarity, strength of association and the bridge point value that the embodiment of the present invention passes through calculating new user and existing group, the group for quickly positioning new user is sorted out, fraud judgement is carried out to new user, improve the working efficiency of anti-fraud personnel, to help business high-speed decision, real-time response risk of fraud, inherently stops loss.
Description
Technical field
The present invention relates to data mining technology field, in particular to a kind of method for assisting anti-fraud analysis cluster structure and
Tool.
Background technique
With the high speed development of internet finance, client is only needed to fill in by web terminal upload towards personal loan process
Simple data can be made loans by approval process.Due to the weakness of part company air control means and being somebody's turn to do in the present case
It calling to account also in improving in middle situation to the law of promise breaking user, some crowds obtain loan limit by various illegal means,
It is no longer given back using after amount, becomes the permanent overdue user in company, bring huge economic loss to company.And this
A little crowds often show the property of organized clique, i.e., all there is certain incidence relations between this groups of people.
Therefore it is necessary to be analyzed and processed to the relevant information of these people and affiliated person, group is built, it is quickly quasi-
Risk subscribers that may be present are really locked, corresponding air control strategy are carried out for the risk subscribers identified, thus effectively
Reduce companies losses.
However exist in the prior art be accused of fraud personnel and affiliated person data be scattered, cluster structure builds speed
Slowly, the problems such as data analysis efficiency is low, these defects tend to that fraud is caused to stop loss not in time.
Summary of the invention
In order to solve problems in the prior art, anti-fraud analysis cluster structure is assisted the embodiment of the invention provides a kind of
Method, to overcome, the data for being accused of fraud personnel and affiliated person present in existing and technology are scattered, cluster structure builds speed
The problems such as degree is slow, data analysis efficiency is low.
In order to solve the above technical problems, the technical solution adopted by the present invention is that:
On the one hand, a kind of method for assisting anti-fraud analysis cluster structure is provided, described method includes following steps:
S1: the information and its affiliated person's information of user are obtained；
S2: judging the degree of association between each user and calculates the strength of association of each association medium；
S3: according to the calculated result of the step S2, group is built；
S4: to each user in the group and it is associated with media definitions label；
S5: all information is enumerated into generation tables of data, then group's operation is carried out to new user, judges the group of new user
Sort out.
Further, the step S2 is specifically included:
The degree of association between each user is judged by calculating similarity between each user and bridge point value, it is similar
Degree and/or bridge point value are bigger, and the degree of association between user is bigger.
Further, the step S3 is specifically included:
According to the calculated result of the step S2, the user of relevant degree is linked together, forms cluster structure.
Further, the step S3 further include:
Judge user whether in a group according to the size of bridge point value.
Further, the size according to bridge point value judges whether user specifically includes in a group:
The bridge point value is standardized calculating, if calculated result is 0, then user corresponding to the bridge point value is not
In the group, otherwise, user corresponding to the bridge point value is in the group.
Further, the step S3 further include:
The group is numbered, and corresponding user is referred under the group with medium is associated with.
Further, the step S4 is specifically included:
If the corresponding label of the group, then the user in the group has this label, if the group
The corresponding multiple labels of group, then determine the label of user in group according to strength of association and the degree of association
Further, described that new user progress group's operation is specifically included:
Calculate similarity, strength of association and the bridge point value between new user and the group.
Further, the group of the new user of judgement, which is sorted out, specifically includes:
If the similarity, strength of association and bridge point value between new user and the group are bigger, then illustrate described new
The degree of association between user and group is bigger
On the other hand, a kind of tool for assisting anti-fraud analysis cluster structure is provided, the tool includes:
Data acquisition module, for obtaining the information and its affiliated person's information of user；
Computing module, for calculating the degree of association between each user, the strength of association of each association medium and to new
User carries out group's operation；
Module is built by group, for the strength of association according to the degree of association and each association medium between each user
Calculated result builds group；
Tag definition module, for in the group each user and association media definitions label；
Generation module, for all information to be enumerated generation tables of data.
Further, the group builds module and includes:
Judging unit, for judging the calculated result of similarity and bridge point value between each user, similarity and/or
Bridge point value is bigger, then judges that the degree of association between user is bigger；
The judgment module be also used to according to by the bridge point value be standardized calculate after as a result, whether judging user
In a group, if calculated result is 0, then user corresponding to the bridge point value is not in the group, otherwise, the bridge
User corresponding to point value is in the group.
Further, module is built by the group further include:
Numbered cell, for the group to be numbered.
Technical solution provided in an embodiment of the present invention has the benefit that
1, the method and tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, Data Integration is transported
It calculates, puts up group, anti-fraud system is built by help company, and can effectively solve the problem that data are scattered, cluster structure is built
Slowly, the problems such as data analysis efficiency is low.
2, the method and tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, by calculating new user
With the similarity, strength of association and bridge point value of existing group, the group for quickly positioning new user is sorted out, and carries out to new user
Fraud judgement, improves the working efficiency of anti-fraud personnel, so that business high-speed decision is helped, real-time response risk of fraud, from this
It is stopped loss in matter.
3, the method and tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, the design reason of similarity
It reads and uses asymmetric similarity, and only realize value matching completely, to solve cluster structure mistake caused by error hiding, improve group
The accuracy rate that group structure is built.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the flow chart of the method provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure；
Fig. 2 is the node bridge point value sample calculation schematic diagram that the embodiment of the present invention 1 provides；
Fig. 3 is the structural schematic diagram of the tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure；
Fig. 4 is the interface schematic diagram of the tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure；
Fig. 5 is that toolbar shows in the interface of the tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure
It is intended to.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Embodiment 1
Fig. 1 is the flow chart of the method provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, referring to Fig.1 institute
Show, described method includes following steps:
S1: the information and its affiliated person's information of user are obtained.
Specifically, the information and its affiliated person's information that obtain user as data sample, as shown in table 1, are included at least and are used
Family name, user identity demonstrate,prove number, subscriber phone number, user and are associated with relationship, affiliated person's name, affiliated person's phone number
Deng.Wherein, the information of user and its affiliated person's information include historical data and online real time data.
S2: judging the degree of association between each user and calculates the strength of association of each association medium.
Further, the pass between each user is judged by calculating similarity between each user and bridge point value
Connection degree, similarity and/or bridge point value are bigger, and the degree of association between user is bigger, wherein association medium include phone number,
Location, mailbox, bank's card number etc..
Specifically, the similarity in the embodiment of the present invention is using asymmetric similarity, each node (referring to user)
Weight be 1, weighted average is assigned in each attribute, and the asymmetric similarity value of two nodes is by association medium and its institute
It is determined in weight, calculation is as follows:
Such as there are two node (i.e. users): A:{ address:a1, a2, a3 } { phone:p1, p2, p3 }, B:
{ address:a1 }, in example, A-B is by association medium a1 association, then when calculating the asymmetric similarity between A and B:
Sim (A, B)=1/2*1/3*1/2
Sim (B, A)=1*1*1/2
What needs to be explained here is that each user in embodiments of the present invention is a node, in addition, in the present invention
Value matching completely is only realized in embodiment, it in this way can be to avoid cluster structure mistake caused by error hiding.
Node bridge point value be the shortest path of the non-node of any two by the ratio of the node and, this operation can be helped
Help the collection of the strength of association and this cluster structure of a certain user and central node (and central user) in identification cluster structure
Moderate.The calculating of bridge point value is as follows:
As shown in Fig. 2, shortest path between the non-A node of any two and have to pass through A shortest path number it is as follows:
1, B, C:1,1
2, B, D:1,1
3, B, E:1,0
4, C, D:1,1
5, C, E:1,1
6, D, E:1,1
The bridge point value of so A is (1/1) * 5+ (0/1),
It is standardized as [(1/1) * 5+ (0/1)] * 2/ (5-1) * (5-2).
Strength of association is the number of public association medium between two nodes.Such as there are two nodes: A:{ address:
A1, a2, a3 } { phone:p1, p2, p3 }, B:{ address:a1 }, then the strength of association of A and B is 1 in example.
S3: according to the calculated result of the step S2, group is built.
Further, according to the calculated result of the step S2, the user of relevant degree is linked together, forms group
Whether structure judges user in a group according to the size of bridge point value, wherein the node on behalf user in cluster structure,
Side between node and node, which represents, is associated with medium.
Specific judgement, is standardized calculating for the bridge point value, if calculated result is 0, then the bridge point value institute is right
The user answered is not in the group, and otherwise, user corresponding to the bridge point value is in the group.For example, as shown in Figure 2 shows
In example, the bridge point value of node A is standardized as [(1/1) * 5+ (0/1)] * 2/ (5-1) * (5-2)=5/6, calculated result 5/
6, it is not 0, then shows node A in the group that present node (including node B, C, D, E) is constituted.
Further, after group puts up, also need that the group is numbered, and corresponding user be associated be situated between
Matter is referred under the group.
S4: to each user in the group and it is associated with media definitions label.
Specifically, user in application product process, will do it Analysis of Policy Making, reference verification and related blacklist school
It tests, if the relevant strategy of hit or blacklist, user can generate some labels, these labels can equally be attached to the user
All Media, including equipment, cell-phone number and IP, thus each user in group and association medium are just defined label.
If the corresponding label of the group, then the user in the group has this label, if group correspondence is more
A label then determines the label of user in group, for example, having a, tri- use of b, c in group A according to strength of association and the degree of association
The strength of association that the strength of association of family, a and b are 0.8, a and c is that 0.1, a user has bull debt-credit and two labels of malicious overdue,
Because the degree of association of a and b is closer, then b can also be transmitted the two labels, but the degree of association of c and a is weaker, then c is not
The two labels can be defined.Referring to shown in following table, following table is some examples of cluster label:
S5: all information is enumerated into generation tables of data, then group's operation is carried out to new user, judges the group of new user
Sort out.
Specifically, all information is enumerated generation tables of data, cheat that personnel are subsequent to inquire it for counter.Then
Group's operation is carried out to new user, judges that the group of new user is sorted out, specifically includes:
Similarity, strength of association and the bridge point between new user and existing group are calculated according to above-mentioned calculation method
Value then illustrates the new user if the similarity, strength of association and bridge point value between new user and existing group are bigger
The degree of association between existing group is bigger, that is to say, that the relationship between new user and existing group is closer.For example,
User G is new user, and to apply for certain product, the personal information of G is logged；Then these information be used to carry out with other users
Association calculates (calculation is shown in step S2), obtains association medium and bridge point value, similarity is equivalent, so that new group construction is complete
At being the group comprising user G；Further according to the label for being associated with tightness and group of user G and this group, use is obtained
The label of family G, so that the fraud of user G defines to be formed.
Embodiment 2
Fig. 3 is the structural schematic diagram of the tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, reference
Shown in Fig. 3, the tool includes:
Data acquisition module, for obtaining the information and its affiliated person's information of user.
Specifically, the information and its affiliated person's information of user include at least address name, user identity demonstrate,proves number, user hand
Machine number, user and it is associated with relationship, affiliated person's name, affiliated person's phone number etc..Wherein, the information of user and its affiliated person
Information includes historical data and online real time data.
Computing module, for calculating the degree of association between each user, the strength of association of each association medium and to new
User carries out group's operation.
Module is built by group, for the strength of association according to the degree of association and each association medium between each user
Calculated result builds group.
Specifically, module is built by group includes:
Judging unit, for judging the calculated result of similarity and bridge point value between each user, similarity and/or
Bridge point value is bigger, then judges that the degree of association between user is bigger；
The judgment module be also used to according to by the bridge point value be standardized calculate after as a result, whether judging user
In a group, if calculated result is 0, then user corresponding to the bridge point value is not in the group, otherwise, the bridge
User corresponding to point value is in the group.
Numbered cell, for the group put up to be numbered.
Tag definition module, for in the group each user and association media definitions label.
Specifically, the group put up may correspond to a label, it is also possible to corresponding multiple labels.
Generation module cheats that personnel are subsequent to look into it for all information to be enumerated generation tables of data for counter
It askes.
Further, the tool further include:
Enquiry module inquires associated group's record, the querying condition packet for the querying condition according to input
Include telephone number, ID card No., mailbox and bank's card number etc..
Display module, the relevant cluster structure figure of querying condition for showing to inputting.
Referring to shown in Fig. 4, Fig. 4 is the interface of the tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure
Schematic diagram, interface are divided into four parts:
Toolbar 1, for searching for cluster structure and control Drawing zone；
Drawing zone 2 reproduces fraud clique and its association for showing the network of cluster structure.It clicks " inquiry ", right
After talking about the corresponding condition of frame input, system can be according to the corresponding group of conditional search of input, then by whole points in group
" Drawing zone " is shown to side；
User information 3, for showing the essential information of user, including name, identity card, household register address, marital status and
Education background etc..People's icon in " Drawing zone " figure is clicked, " user information " can accordingly update；
Historical record 4, be according to the associated related application of group information, can clique be inter-product attacks across the time to fraud
A comprehensive understanding is hit.
Referring to Figure 5, Fig. 5 is the interface of the tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure
The schematic diagram of middle toolbar includes: in toolbar
Global search button, after input inquiry condition clicks " inquiry " in dialog box, background query is associated
Group's record, the structure chart of group can show Drawing zone below for further detecting corresponding content.Supporting telephone number at present
Four kinds of modes such as code, identification card number, mailbox and bank's card number inquire group.
All erasing buttonsClick all the elements that can be removed except current page " toolbar ".
Local frame selects buttonClick can select corresponding node, and shift position using left mouse button frame in Drawing zone.
Image actuating buttonClick can be dragged the full content of Drawing zone with left mouse button is pinned together, be first
Default behavior when secondary displaying cluster structure.
Expert's the view buttonAll nodes and the side that can show group network are clicked, is rollout cluster structure
When default view.
Simplification view buttonIt clicks and can simplify the structure for showing group, between the node and these nodes that only retain people
Relationship.
Search button in scheming, input phone numbers associated, identification card number, mailbox or bank's card number, clicking magnifying glass can
To search corresponding node in current figure, a dotted line frame can be done in node outer layer after finding.
It can show various types of icons in Drawing zone 2, the type of the kernel representation node of icon, for example,It represents
People,Mailbox is represented,Address is represented,Phone is represented,Bank card is represented,Represent equipment.Click Drawing zone
These nodes, can be yellow by corresponding information mark in " historical record ", wherein if what is clicked is people's node, " can use simultaneously
The essential information of the people is shown in family information ".
There are three types of colors for the core of icon: grey, red, orange, this is illustrated for sentencing user node, grey kernel representation
Bridge point value < 0.5, orange 0.5≤bridge of kernel representation point value < 0.7, red kernel representation bridge point value >=0.7.Bridge point value, which refers to, appoints
Anticipate two non-nodes shortest path by the ratio of the node and, be the important indicator for identifying intermediary between 0~1,
Zhi Yuegao intermediary risk is higher.
There are three types of the border colors of icon: grey, red, orange, grey frame indicates my devoid of risk feature, and red frame indicates
Risky feature in person, orange frame indicate the risky feature of affiliated person；The border thickness of icon has 3 grades: from carefully to rough segmentation
Not Biao Shi: low risk, moderate risk and high risk.
Name, identity card, household register address, marital status and education background etc. can be shown in user information 3, specific as follows:
Name: default black, red indicate that the people had not passed through public security real name or the same identity card and once corresponded to two surnames
Name.
Real name situation: non-real name label is " non-real name ", can be appeared dimmed；It is by public security real-name authentication meeting label
" real name ", male can be shown as blue, and women can be shown in red.
Household register address: the household register returned for public security, relevant information is not checked in for empty expression.
Marital status: the marital status parsed according to public security data or collage-credit data does not check in relevant information for empty expression.
Education background: the educational background parsed according to public security returned data or collage-credit data is horizontal, does not check in correlation for empty expression
Information.
Historical record 4 is to include at least following information: product number, product according to the associated related application of group information
It name, application number, application time, name, identity card, phone, bank's card number, device number, mailbox, contact person, applicant and contacts
The information such as relationship, contact phone.
In conclusion technical solution provided in an embodiment of the present invention has the benefit that
1, the method and tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, Data Integration is transported
It calculates, puts up group, anti-fraud system is built by help company, and can effectively solve the problem that data are scattered, cluster structure is built
Slowly, the problems such as data analysis efficiency is low.
2, the method and tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, by calculating new user
With the similarity, strength of association and bridge point value of existing group, the group for quickly positioning new user is sorted out, and carries out to new user
Fraud judgement, improves the working efficiency of anti-fraud personnel, so that business high-speed decision is helped, real-time response risk of fraud, from this
It is stopped loss in matter.
3, the method and tool provided in an embodiment of the present invention for assisting anti-fraud analysis cluster structure, the design reason of similarity
It reads and uses asymmetric similarity, and only realize value matching completely, to solve cluster structure mistake caused by error hiding, improve group
The accuracy rate that group structure is built
It should be understood that the tool provided by the above embodiment for assisting anti-fraud analysis cluster structure analyzes group in triggering
Group structured walk-through when, only the example of the division of the above functional modules, in practical application, can according to need and incite somebody to action
Above-mentioned function distribution is completed by different functional modules, i.e., the internal structure of tool is divided into different functional modules, with complete
At all or part of function described above.In addition, the work provided by the above embodiment for assisting anti-fraud analysis cluster structure
Tool belongs to same design with the embodiment of the method for assisting anti-fraud analysis cluster structure, and specific implementation process is detailed in method implementation
Example, which is not described herein again.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of method for assisting anti-fraud analysis cluster structure, which is characterized in that described method includes following steps:
S1: the information and its affiliated person's information of user are obtained；
S2: judging the degree of association between each user and calculates the strength of association of each association medium；
S3: according to the calculated result of the step S2, group is built；
S4: to each user in the group and it is associated with media definitions label；
S5: all information is enumerated into generation tables of data, then group's operation is carried out to new user, judges that the group of new user is returned
Class.
2. the method according to claim 1 for assisting anti-fraud analysis cluster structure, which is characterized in that the step S2 tool
Body includes:
The degree of association between each user, similarity are judged by calculating similarity between each user and bridge point value
And/or bridge point value is bigger, the degree of association between user is bigger.
3. the method according to any one of claims 1 or 2 for assisting anti-fraud analysis cluster structure, which is characterized in that
The step S3 is specifically included:
According to the calculated result of the step S2, the user of relevant degree is linked together, forms cluster structure.
4. the method according to claim 2 for assisting anti-fraud analysis cluster structure, which is characterized in that the step S3 is also
Include:
Judge user whether in a group according to the size of bridge point value.
5. the method according to claim 4 for assisting anti-fraud analysis cluster structure, which is characterized in that described according to bridge point
The size of value judges whether user specifically includes in a group:
The bridge point value is standardized calculating, if calculated result is 0, then user corresponding to the bridge point value is not at this
In group, otherwise, user corresponding to the bridge point value is in the group.
6. the method according to any one of claims 1 or 2 for assisting anti-fraud analysis cluster structure, which is characterized in that
The step S3 further include:
The group is numbered, and corresponding user is referred under the group with medium is associated with.
7. the method according to any one of claims 1 or 2 for assisting anti-fraud analysis cluster structure, which is characterized in that
The step S4 is specifically included:
If the corresponding label of the group, then the user in the group has this label, if the group pair
Multiple labels are answered, then determine the label of user in group according to strength of association and the degree of association.
8. the method according to any one of claims 1 or 2 for assisting anti-fraud analysis cluster structure, which is characterized in that
It is described that new user progress group's operation is specifically included:
Calculate similarity, strength of association and the bridge point value between new user and the group.
9. the method according to claim 8 for assisting anti-fraud analysis cluster structure, which is characterized in that the judgement is new to be used
The group at family, which is sorted out, to be specifically included:
If the similarity, strength of association and bridge point value between new user and the group are bigger, then illustrate the new user
The degree of association between group is bigger.
10. a kind of assistance based on the method for the anti-fraud analysis cluster structure of assistance described in claim 1 to 9 any one is anti-
The tool of fraud analysis cluster structure, which is characterized in that the tool includes:
Data acquisition module, for obtaining the information and its affiliated person's information of user；
Computing module, for calculating the degree of association between each user, the strength of association of each association medium and to new user
Carry out group's operation；
Module is built by group, for the calculating according to the degree of association and each strength of association for being associated with medium between each user
As a result, building group；
Tag definition module, for in the group each user and association media definitions label；
Generation module, for all information to be enumerated generation tables of data.
11. the tool according to claim 10 for assisting anti-fraud analysis cluster structure, which is characterized in that the group takes
Modeling block includes:
Judging unit, for judging the calculated result of similarity and bridge point value between each user, similarity and/or bridge point
Value is bigger, then judges that the degree of association between user is bigger；
The judgment module be also used to according to by the bridge point value be standardized calculate after as a result, judging user whether one
In a group, if calculated result is 0, then user corresponding to the bridge point value is not in the group, otherwise, the bridge point value
Corresponding user is in the group.
12. the tool of the anti-fraud analysis cluster structure of assistance described in 0 or 11 any one, feature exist according to claim 1
In module is built by the group further include:
Numbered cell, for the group to be numbered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811153021.1A CN109410035B (en) | 2018-09-29 | 2018-09-29 | Method and tool for assisting anti-fraud analysis of group structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811153021.1A CN109410035B (en) | 2018-09-29 | 2018-09-29 | Method and tool for assisting anti-fraud analysis of group structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109410035A true CN109410035A (en) | 2019-03-01 |
| CN109410035B CN109410035B (en) | 2021-03-16 |
Family
ID=65465704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811153021.1A Active CN109410035B (en) | 2018-09-29 | 2018-09-29 | Method and tool for assisting anti-fraud analysis of group structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109410035B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110069923A (en) * | 2019-03-13 | 2019-07-30 | 咪咕文化科技有限公司 | A kind of method and relevant apparatus identifying risk subscribers |
| CN112785423A (en) * | 2021-02-07 | 2021-05-11 | 撼地数智(重庆)科技有限公司 | Method, device, equipment and storage medium for mining fraud risk node |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169864A (en) * | 2017-05-31 | 2017-09-15 | 天云融创数据科技（北京）有限公司 | A kind of card holder's risk of fraud feature extracting method based on complex network |
| 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 |
| CN108009915A (en) * | 2017-12-21 | 2018-05-08 | 连连银通电子支付有限公司 | A kind of labeling method and relevant apparatus of fraudulent user community |
| CN108038778A (en) * | 2017-12-05 | 2018-05-15 | 深圳信用宝金融服务有限公司 | Clique's fraud recognition methods of the small micro- loan of internet finance and device |
-
2018
- 2018-09-29 CN CN201811153021.1A patent/CN109410035B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169864A (en) * | 2017-05-31 | 2017-09-15 | 天云融创数据科技（北京）有限公司 | A kind of card holder's risk of fraud feature extracting method based on complex network |
| 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 |
| CN108038778A (en) * | 2017-12-05 | 2018-05-15 | 深圳信用宝金融服务有限公司 | Clique's fraud recognition methods of the small micro- loan of internet finance and device |
| CN108009915A (en) * | 2017-12-21 | 2018-05-08 | 连连银通电子支付有限公司 | A kind of labeling method and relevant apparatus of fraudulent user community |
Non-Patent Citations (2)
| Title |
|---|
| 闵志锋: "中国证券市场的复杂网络特性研究", 《中国优秀硕士学位论文全文数据库》 * |
| 高学东 等: "基于共享最近邻探测社团结构的算法", 《系统工程理论与实践》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110069923A (en) * | 2019-03-13 | 2019-07-30 | 咪咕文化科技有限公司 | A kind of method and relevant apparatus identifying risk subscribers |
| CN112785423A (en) * | 2021-02-07 | 2021-05-11 | 撼地数智(重庆)科技有限公司 | Method, device, equipment and storage medium for mining fraud risk node |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109410035B (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110413707A (en) | The excavation of clique's relationship is cheated in internet and checks method and its system | |
| US5966650A (en) | Detecting mobile telephone misuse | |
| US6535728B1 (en) | Event manager for use in fraud detection | |
| Ainin et al. | Applying Importance-Performance Analysis to Information Systems: An Exploratory Case Study. | |
| CN112053221A (en) | Knowledge graph-based internet financial group fraud detection method | |
| CN107943879A (en) | Fraud group detection method and system based on social networks | |
| CN109816397A (en) | A kind of fraud method of discrimination, device and storage medium | |
| EP2146298A1 (en) | Systems and methods for e-commerce fraud detection | |
| CN109918452A (en) | A kind of method, apparatus of data processing, computer storage medium and terminal | |
| Kaur et al. | A comparative analysis of structural graph metrics to identify anomalies in online social networks | |
| CN106447490A (en) | Credit investigation application method based on user figures | |
| CN112053222A (en) | Knowledge graph-based internet financial group fraud detection method | |
| CN110795574A (en) | Knowledge graph construction method based on finance anti-fraud | |
| CN109376182A (en) | The method for realizing affiliated company's identifying processing based on computer software | |
| CN109410035A (en) | A kind of method and tool for assisting anti-fraud analysis cluster structure | |
| CN109636570A (en) | Risk analysis method, device, equipment and the readable storage medium storing program for executing of cell-phone number | |
| CN112750038B (en) | Transaction risk determination method, device and server | |
| CN108563706A (en) | A kind of collection big data intelligent service system and its operation method | |
| CN116385137A (en) | Enterprise anti-fraud risk assessment method and system based on power information data | |
| Khan et al. | Transaction mining for fraud detection in ERP Systems | |
| CN115496130A (en) | Training and approving method, device and storage medium for new card issuing real-time approving model | |
| CN109359808A (en) | A kind of appraisal procedure and its management system suitable for potential customers' value | |
| CN112862594A (en) | Financial risk control method, system, device and computer readable medium | |
| Shortland et al. | Data mining applications in BT | |
| CN109447455A (en) | A kind of enterprises air control engine building method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |