CN109816535A - Cheat recognition methods, device, computer equipment and storage medium - Google Patents
Cheat recognition methods, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109816535A CN109816535A CN201811527396.XA CN201811527396A CN109816535A CN 109816535 A CN109816535 A CN 109816535A CN 201811527396 A CN201811527396 A CN 201811527396A CN 109816535 A CN109816535 A CN 109816535A
- Authority
- CN
- China
- Prior art keywords
- corporations
- clustering
- matrix
- network
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 230000003595 spectral effect Effects 0.000 claims abstract description 27
- 239000011159 matrix material Substances 0.000 claims description 99
- 238000010586 diagram Methods 0.000 claims description 34
- 238000001514 detection method Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 14
- 230000017105 transposition Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 241000209202 Bromus secalinus Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000032258 transport Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses fraud recognition methods, device, computer equipment and storage mediums.This method comprises: obtaining the corresponding node of Claims Resolution data, the corresponding nodal parallel of the Claims Resolution data is divided by multiple subgraphs by spectral clustering；Multiple subgraphs are clustered respectively, obtain network community；The network associate data obtained according to historical data are obtained, if being retrieved in network community in the presence of clustering corporations identical with network associate data point, obtain the clustering corporations point；If corresponding score of the clustering corporations point exceeds preset scoring threshold value, the clustering corporations point is placed in doubtful fraud corporations grouping.The method achieve the full dose data to Claims Resolution data to carry out efficient real-time knitmesh, and is based on community discovery algorithm, finds the doubtful fraud data in Claims Resolution data quickly to be verified.
Description
Technical field
The present invention relates to fraud identification technology field more particularly to a kind of fraud recognition methods, device, computer equipment and
Storage medium.
Background technique
Currently, there are many common figure knitmesh algorithms, but it is substantially and knitmesh is carried out based on small scale network, does not support simultaneously
Row cuts net, fixed-focus operation.For example, there is the product of partial insurance company, it is rule match when being settled a claim, does not support figure
Algorithm, community discovery algorithm function.And corporations' algorithm that existing figure knitmesh algorithm is supported is limited, transports in ultra-large data
There is disadvantage in calculation (when more than one hundred million nodes, knitmesh speed surpasses 24 hours), and can not support real-time knitmesh operation.
Summary of the invention
The embodiment of the invention provides a kind of fraud recognition methods, device, computer equipment and storage mediums, it is intended to solve
Corporations' algorithm that figure knitmesh algorithm is supported in the prior art is limited, the knitmesh inefficiency in ultra-large data operation, and not
The problem of supporting real-time knitmesh operation.
In a first aspect, the embodiment of the invention provides a kind of fraud recognition methods comprising:
The corresponding node of Claims Resolution data is obtained, is divided into the corresponding nodal parallel of the Claims Resolution data by spectral clustering more
A subgraph；
Multiple subgraphs are clustered respectively, obtain network community；
The network associate data obtained according to historical data are obtained, are existed and the network if being retrieved in network community
The identical clustering corporations point of associated data, obtains the clustering corporations point；
If corresponding score of the clustering corporations point exceeds preset scoring threshold value, the clustering corporations point is placed in doubtful
It cheats in corporations' grouping.
Second aspect, the embodiment of the invention provides a kind of fraud identification devices comprising:
Subgraph division unit, it is by spectral clustering that the Claims Resolution data are corresponding for obtaining the corresponding node of Claims Resolution data
Nodal parallel be divided into multiple subgraphs；
Network community acquiring unit obtains network community for clustering multiple subgraphs respectively；
Clustering corporations point retrieval unit, for obtaining the network associate data obtained according to historical data, if in network society
It is retrieved in group in the presence of clustering corporations identical with network associate data point, obtains the clustering corporations point；
Corporations' judging unit is cheated, it, will if exceeding preset scoring threshold value for the corresponding scoring of the clustering corporations point
The clustering corporations point is placed in doubtful fraud corporations grouping.
The third aspect, the embodiment of the present invention provide a kind of computer equipment again comprising memory, processor and storage
On the memory and the computer program that can run on the processor, the processor execute the computer program
Fraud recognition methods described in the above-mentioned first aspect of Shi Shixian.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, wherein the computer can
It reads storage medium and is stored with computer program, it is above-mentioned that the computer program when being executed by a processor executes the processor
Fraud recognition methods described in first aspect.
The embodiment of the invention provides a kind of fraud recognition methods, device, computer equipment and storage mediums.This method packet
The corresponding node of acquisition Claims Resolution data is included, the corresponding nodal parallel of the Claims Resolution data is divided by multiple sons by spectral clustering
Figure；Multiple subgraphs are clustered respectively, obtain network community；The network associate data obtained according to historical data are obtained, if
It is retrieved in network community in the presence of clustering corporations identical with network associate data point, obtains the clustering corporations point；
If corresponding score of the clustering corporations point exceeds preset scoring threshold value, the clustering corporations point is placed in doubtful fraud corporations
In grouping.The method achieve the full dose data to Claims Resolution data to carry out efficient real-time knitmesh, and is based on community discovery algorithm,
Find the doubtful fraud data in Claims Resolution data quickly to be verified.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of fraud recognition methods provided in an embodiment of the present invention；
Fig. 2 is the sub-process schematic diagram of fraud recognition methods provided in an embodiment of the present invention；
Fig. 3 is another sub-process schematic diagram of fraud recognition methods provided in an embodiment of the present invention；
Fig. 4 is another sub-process schematic diagram of fraud recognition methods provided in an embodiment of the present invention；
Fig. 5 is the schematic block diagram of fraud identification device provided in an embodiment of the present invention；
Fig. 6 is the subelement schematic block diagram of fraud identification device provided in an embodiment of the present invention；
Fig. 7 is another subelement schematic block diagram of fraud identification device provided in an embodiment of the present invention；
Fig. 8 is another subelement schematic block diagram of fraud identification device provided in an embodiment of the present invention；
Fig. 9 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Referring to Fig. 1, Fig. 1 is the flow diagram of fraud recognition methods provided in an embodiment of the present invention, fraud identification
Method is applied in intelligent terminal, and this method is executed by the application software being installed in intelligent terminal.
As shown in Figure 1, the method comprising the steps of S110~S140.
S110, the corresponding node of Claims Resolution data is obtained, is drawn the corresponding nodal parallel of the Claims Resolution data by spectral clustering
It is divided into multiple subgraphs.
It in the present embodiment, is that fraud identification is carried out to Claims Resolution data in the management server.When management server receives
The case data of magnanimity (such as the case data under vehicle insurance Claims Resolution scene include driver, reporter, beneficiary and the wounded, with
And the data such as repair shop, phone number, maintenance place, GPS information), according to prior art medium or small scale network knitmesh, can lead
Cause knitmesh inefficiency.At this point it is possible to the division for carrying out region to the node of magnanimity by spectral clustering be selected, so that different
The connection weight between node in subgraph (subgraph can be considered as one piece of region, include multiple nodes in the region) is smaller (i.e.
It is less than preset connection weight threshold), and the connection weight between the node in same subgraph is larger (i.e. more than preset
It is weight threshold).The corresponding nodal parallel of the Claims Resolution data quickly can be divided into multiple subgraphs by spectral clustering.
In one embodiment, as shown in Fig. 2, step S110 includes:
S111, inputted similarity matrix and target clusters number are obtained；
S112, the corresponding similar matrix of corresponding with Claims Resolution data node is constructed according to the similarity matrix；
S113, adjacency matrix and diagonal matrix are constructed according to the similar matrix, by the diagonal matrix and the adjoining
The difference of matrix obtains Laplacian Matrix；
S114, the feature that ranking in multiple characteristic values of the Laplacian Matrix is located at before default rank threshold is obtained
The corresponding feature vector of value, to obtain target feature vector set；
S115, it is column vector by feature vector transposition each in target feature vector set and successively combines, obtains mesh
Mark vector matrix；
S116, row vector each in object vector matrix is clustered by k-means algorithm, is obtained poly- with the target
The same number of sub- group of class.
In the present embodiment, spectral clustering is a kind of clustering method based on graph theory, passes through the Laplce to sample data
The feature vector of matrix is clustered, to achieve the purpose that cluster sample data.Spectral clustering can be understood as higher-dimension sky
Between data be mapped to low-dimensional, then clustered in lower dimensional space with other clustering algorithms (such as k-means).
It, need to be by the corresponding node of the Claims Resolution data in order to realize that the Claims Resolution data to higher dimensional space are mapped to lower dimensional space
The building of similar matrix is first carried out according to formula (1):
Wherein, n is to pay for the corresponding node number of data, xiAnd xjAny one node is respectively indicated, σ indicates the mark of node
Poor, the s of standardijThen constitute similar matrix.
The corresponding similar matrix of corresponding with Claims Resolution data node is constructed by the similarity matrix inputted ∈-
Neighbouring method, K is adjacent to method and full connection method.For example, the calculation formula such as formula 1 of full connection method.
Diagonal matrix is calculated according to formula 2 later, formula 2 is specific as follows:
Wherein, diThe sum of the element for indicating every a line in similar matrix, by diForm diagonal matrix wijThen indicate similar square
The element of i-th row jth column in battle array.
After the difference by the diagonal matrix and the adjacency matrix obtains Laplacian Matrix, it can Laplce's square
Corresponding each feature vector transposition is column vector in battle array, to form object vector matrix.It will finally by k-means algorithm
Each row vector is clustered in object vector matrix, obtains sub- group identical with the target clusters number, passes through spectral clustering reality
Show the quick discovery that the full dose data being made of Claims Resolution data are carried out to corporations, and realizes real-time knitmesh.
S120, multiple subgraphs are clustered respectively, obtains network community.
In the present embodiment, multiple subgraphs are clustered respectively again, is a kind of parallel knitmesh, effectively raises big rule
The knitmesh efficiency of modulus evidence.After initial node division is formed multiple subgraphs for multiple regions by spectral clustering, form more
A lesser figure of scale needs each subgraph carrying out knitmesh at this time.Knitmesh will exactly be connected between node and node with side, side
The connection weight between node is represented, the connection weighted value between the more big then node of the incidence relation before two nodes is bigger,
Network community can be obtained after carrying out knitmesh to subgraph.
In one embodiment, as shown in figure 3, step S120 includes:
S121, multiple subgraphs are subjected to knitmesh respectively, obtain social networks topological diagram of initially settling a claim；
S122, initial Claims Resolution social networks topological diagram is clustered by corporations' detection, obtains network community.
It in the present embodiment, is after multiple regions form multiple subgraphs, to be formed by initial node division by spectral clustering
The lesser figures of multiple scales need each subgraph carrying out knitmesh at this time, obtain social networks topological diagram of initially settling a claim.Later
By corporations' detection algorithm, initial Claims Resolution social networks topological diagram can be clustered, obtain network community.
Corporations' detection seeks to (open up comprising the initial Claims Resolution social networks in vertex and side, such as step 1 in a figure
Flutter figure) on find community structure, that is, the node in figure is clustered, constitutes corporations one by one.About corporations
(community), there is presently no exact definition, it is considered that and the connection between point inside corporations is relatively dense, without
It is relatively sparse with the connection between the point of corporations.
For example, a kind of society can be exported after handling by corporations' detection algorithm after the initial Claims Resolution social networks topological diagram of input
Group divides, namely cuts the network after figure.
In one embodiment, as shown in figure 4, after step S122 further include:
S123, the corresponding modularity of included each corporations in the network community is obtained；
If S124, the corresponding modularity of each corporations are respectively less than 1, identify the network community and tested by community network division
Card；
If S125, thering is the corresponding modularity of corporations to be greater than or equal to 1, identifies the network community and do not drawn by community network
Divide verifying, the corporations by corporations' detection to modularity more than or equal to 1 cluster, and obtain updated corporations' network.
In the present embodiment, the modularity (Modularity) of the network after cutting figure is that one community network of assessment divides
Bad measure, it is meant that company's number of edges of community's interior nodes and the difference of the number of edges under random case, the value of modularity
Range is (0,1).
In corporations' detection algorithm, modularity algorithm mainly assesses the compact concentration of node, can help faster into
Row fixed-focus, and in practice, often there is many noises, the image excavation of corporations, therefore can optimize in terms of following three:
A) high-frequency anomaly point is rejected.For the abnormal point of hyperfrequency, often due to typing is abnormal, mistake record phenomenon, lead to height
Frequency point is in danger, for such issues that, after we can reject high frequency points, cut net.
B) time shaft is handled, and, by stretching time axis, the case that limit occurs that will can exceed the time limit in the past is filtered for we, from
And reduce the complexity of network.
C) business rule combination network module degree is combined and excavates high risk network.
The network associate data that S130, acquisition are obtained according to historical data, exist and institute if retrieving in network community
The identical clustering corporations point of network associate data is stated, the clustering corporations point is obtained.
In the present embodiment, it after by the node division of magnanimity for multiple network communities, needs to detect in network community
With the presence or absence of clustering identical with network associate data corporations point.Such as according to historical data, corporations' section in the presence of fraud is obtained
The structure such as node 1- node 3- node 2- node 4- node 5- node 1 of point (manage by the data that node connection relationship can be formed
Solution be network associate data), if that is, there are above-mentioned node connection relationships for node in a certain subgraph, then it represents that in the subgraph
In the presence of fraud corporations.It is that whether there is in network community included in each subgraph in the multiple subgraphs of traversal and network associate
The identical clustering corporations point of data, if being retrieved in network community in the presence of clustering corporations identical with the network associate data
Point obtains the clustering corporations point.
If the corresponding scoring of S140, the clustering corporations point exceeds preset scoring threshold value, the clustering corporations point is set
In the grouping of doubtful fraud corporations.
In one embodiment, before step S140 further include:
The connection weight in clustering corporations point between each node is obtained, and the connection weight between each node is carried out
Summation, obtains the corresponding scoring of clustering corporations point.
In the present embodiment, when calculating the corresponding scoring of clustering corporations point, preset Weight algorithm can be used, such as count
The weight for calculating the clustering corporations point is summed, such as the node structure of clustering corporations point is as follows: node 1- node 3- node 2- section
Point 4- node 5- node 1.The weight that contacts between node 1 and node 3 is 0.4, and the weight that contacts between node 3 and node 2 is
0.3, the weight that contacts between node 2 and node 4 is 0.2, and the weight that contacts between node 4 and node 5 is 0.1, node 5 and section
Connection weight between point 1 is 0.2, then the sum of above-mentioned connection weight is 1.2, if preset scoring threshold value is 1, the clustering
The corresponding scoring of corporations' point exceeds preset scoring threshold value, by the clustering corporations point as in the grouping of doubtful fraud corporations.It is logical
It crosses network associate data and is quickly detected fraud corporations as history flag case, and with all the points in clustering corporations
Weight is summed to be scored, and more objective be used as further can verify the corporations with the presence or absence of fraud.
The method achieve the full dose data to Claims Resolution data to carry out efficient real-time knitmesh, and is calculated based on community discovery
Method finds the doubtful fraud data in Claims Resolution data quickly to be verified.
The embodiment of the present invention also provides a kind of fraud identification device, and the fraud identification device is for executing aforementioned fraud identification
Any embodiment of method.Specifically, referring to Fig. 5, Fig. 5 is the schematic of fraud identification device provided in an embodiment of the present invention
Block diagram.The fraud identification device 100 can be configured in intelligent terminal.
As shown in figure 5, fraud identification device 100 includes subgraph division unit 110, network community acquiring unit 120, clustering
Corporations' point retrieval unit 130, fraud corporations' judging unit 140.
Subgraph division unit 110, for obtaining the corresponding node of Claims Resolution data, by spectral clustering by the Claims Resolution data pair
The nodal parallel answered is divided into multiple subgraphs.
It in the present embodiment, is that fraud identification is carried out to Claims Resolution data in the management server.When management server receives
The case data of magnanimity (such as the case data under vehicle insurance Claims Resolution scene include driver, reporter, beneficiary and the wounded, with
And the data such as repair shop, phone number, maintenance place, GPS information), according to prior art medium or small scale network knitmesh, can lead
Cause knitmesh inefficiency.At this point it is possible to the division for carrying out region to the node of magnanimity by spectral clustering be selected, so that different
The connection weight between node in subgraph (subgraph can be considered as one piece of region, include multiple nodes in the region) is smaller (i.e.
It is less than preset connection weight threshold), and the connection weight between the node in same subgraph is larger (i.e. more than preset
It is weight threshold).The corresponding nodal parallel of the Claims Resolution data quickly can be divided into multiple subgraphs by spectral clustering.
In one embodiment, as shown in fig. 6, the subgraph division unit 110 includes:
Initial typing unit 111, for obtaining inputted similarity matrix and target clusters number；
Similar matrix construction unit 112, for constructing section corresponding with the Claims Resolution data according to the similarity matrix
The corresponding similar matrix of point；
Laplacian Matrix construction unit 113, for constructing adjacency matrix and diagonal matrix according to the similar matrix, by
The difference of the diagonal matrix and the adjacency matrix obtains Laplacian Matrix；
Target feature vector set acquiring unit 114 is arranged in multiple characteristic values for obtaining the Laplacian Matrix
Name is located at feature vector corresponding to the characteristic value before presetting rank threshold, to obtain target feature vector set；
Object vector matrix acquiring unit 115, for being column by feature vector transposition each in target feature vector set
Vector simultaneously successively combines, to obtain object vector matrix；
Matrix Cluster unit 116, for row vector each in object vector matrix to be clustered by k-means algorithm,
Obtain sub- group identical with the target clusters number.
In the present embodiment, spectral clustering is a kind of clustering method based on graph theory, passes through the Laplce to sample data
The feature vector of matrix is clustered, to achieve the purpose that cluster sample data.Spectral clustering can be understood as higher-dimension sky
Between data be mapped to low-dimensional, then clustered in lower dimensional space with other clustering algorithms (such as k-means).
It, need to be by the corresponding node of the Claims Resolution data in order to realize that the Claims Resolution data to higher dimensional space are mapped to lower dimensional space
The building of similar matrix is first carried out according to formula (1):
The corresponding similar matrix of corresponding with Claims Resolution data node is constructed by the similarity matrix inputted ∈-
Neighbouring method, K is adjacent to method and full connection method.For example, the calculation formula such as formula 1 of full connection method.
After the difference by the diagonal matrix and the adjacency matrix obtains Laplacian Matrix, it can Laplce's square
Corresponding each feature vector transposition is column vector in battle array, to form object vector matrix.It will finally by k-means algorithm
Each row vector is clustered in object vector matrix, obtains sub- group identical with the target clusters number, passes through spectral clustering reality
Show the quick discovery that the full dose data being made of Claims Resolution data are carried out to corporations, and realizes real-time knitmesh.
Network community acquiring unit 120 obtains network community for clustering multiple subgraphs respectively.
In the present embodiment, multiple subgraphs are clustered respectively again, is a kind of parallel knitmesh, effectively raises big rule
The knitmesh efficiency of modulus evidence.After initial node division is formed multiple subgraphs for multiple regions by spectral clustering, form more
A lesser figure of scale needs each subgraph carrying out knitmesh at this time.Knitmesh will exactly be connected between node and node with side, side
The connection weight between node is represented, the connection weighted value between the more big then node of the incidence relation before two nodes is bigger,
Network community can be obtained after carrying out knitmesh to subgraph.
In one embodiment, as shown in fig. 7, the network community acquiring unit 120, comprising:
Initial knitmesh unit 121 obtains social networks topology of initially settling a claim for multiple subgraphs to be carried out knitmesh respectively
Figure；
Corporations' detection unit 122 is obtained for being clustered by corporations' detection to initial Claims Resolution social networks topological diagram
Network community.
It in the present embodiment, is after multiple regions form multiple subgraphs, to be formed by initial node division by spectral clustering
The lesser figures of multiple scales need each subgraph carrying out knitmesh at this time, obtain social networks topological diagram of initially settling a claim.Later
By corporations' detection algorithm, initial Claims Resolution social networks topological diagram can be clustered, obtain network community.
Corporations' detection seeks to (open up comprising the initial Claims Resolution social networks in vertex and side, such as step 1 in a figure
Flutter figure) on find community structure, that is, the node in figure is clustered, constitutes corporations one by one.About corporations
(community), there is presently no exact definition, it is considered that and the connection between point inside corporations is relatively dense, without
It is relatively sparse with the connection between the point of corporations.
For example, a kind of society can be exported after handling by corporations' detection algorithm after the initial Claims Resolution social networks topological diagram of input
Group divides, namely cuts the network after figure.
In one embodiment, as shown in fig. 7, the network community acquiring unit 120, further includes:
Modularity acquiring unit 123, for obtaining the corresponding modularity of included each corporations in the network community；
It is logical to identify the network community if being respectively less than 1 for the corresponding modularity of each corporations for first identifier unit 124
It crosses community network and divides verifying；
Second identifier unit 125, if identifying the network community for there is the corresponding modularity of corporations to be greater than or equal to 1
It is not divided and is verified by community network, the corporations by corporations' detection to modularity more than or equal to 1 cluster, and are updated
Corporations' network afterwards.
In the present embodiment, the modularity (Modularity) of the network after cutting figure is that one community network of assessment divides
Bad measure, it is meant that company's number of edges of community's interior nodes and the difference of the number of edges under random case, the value of modularity
Range is (0,1).
In corporations' detection algorithm, modularity algorithm mainly assesses the compact concentration of node, can help faster into
Row fixed-focus, and in practice, often there is many noises, the image excavation of corporations, therefore can optimize in terms of following three:
A) high-frequency anomaly point is rejected.For the abnormal point of hyperfrequency, often due to typing is abnormal, mistake record phenomenon, lead to height
Frequency point is in danger, for such issues that, after we can reject high frequency points, cut net.
B) time shaft is handled, and, by stretching time axis, the case that limit occurs that will can exceed the time limit in the past is filtered for we, from
And reduce the complexity of network.
C) business rule combination network module degree is combined and excavates high risk network.
Clustering corporations point retrieval unit 130, for obtaining the network associate data obtained according to historical data, if in network
It is retrieved in corporations in the presence of clustering corporations identical with network associate data point, obtains the clustering corporations point.
In the present embodiment, it after by the node division of magnanimity for multiple network communities, needs to detect in network community
With the presence or absence of clustering identical with network associate data corporations point.Such as according to historical data, corporations' section in the presence of fraud is obtained
The structure such as node 1- node 3- node 2- node 4- node 5- node 1 of point (manage by the data that node connection relationship can be formed
Solution be network associate data), if that is, there are above-mentioned node connection relationships for node in a certain subgraph, then it represents that in the subgraph
In the presence of fraud corporations.It is that whether there is in network community included in each subgraph in the multiple subgraphs of traversal and network associate
The identical clustering corporations point of data, if being retrieved in network community in the presence of clustering corporations identical with the network associate data
Point obtains the clustering corporations point.
Corporations' judging unit 140 is cheated, if exceeding preset scoring threshold value for the corresponding scoring of the clustering corporations point,
The clustering corporations point is placed in doubtful fraud corporations grouping.
In one embodiment, identification device 100 is cheated further include:
Score computing unit, for obtaining the connection weight in clustering corporations point between each node, and to each node
Between connection weight sum, obtain the corresponding scoring of clustering corporations point.
In the present embodiment, when calculating the corresponding scoring of clustering corporations point, preset Weight algorithm can be used, such as count
The weight for calculating the clustering corporations point is summed, such as the node structure of clustering corporations point is as follows: node 1- node 3- node 2- section
Point 4- node 5- node 1.The weight that contacts between node 1 and node 3 is 0.4, and the weight that contacts between node 3 and node 2 is
0.3, the weight that contacts between node 2 and node 4 is 0.2, and the weight that contacts between node 4 and node 5 is 0.1, node 5 and section
Connection weight between point 1 is 0.2, then the sum of above-mentioned connection weight is 1.2, if preset scoring threshold value is 1, the clustering
The corresponding scoring of corporations' point exceeds preset scoring threshold value, by the clustering corporations point as in the grouping of doubtful fraud corporations.It is logical
It crosses network associate data and is quickly detected fraud corporations as history flag case, and with all the points in clustering corporations
Weight is summed to be scored, and more objective be used as further can verify the corporations with the presence or absence of fraud.
The arrangement achieves the full dose data to Claims Resolution data to carry out efficient real-time knitmesh, and is calculated based on community discovery
Method finds the doubtful fraud data in Claims Resolution data quickly to be verified.
Above-mentioned fraud identification device can be implemented as the form of computer program, which can be in such as Fig. 9 institute
It is run in the computer equipment shown.
Referring to Fig. 9, Fig. 9 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Refering to Fig. 9, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 are performed, and processor 502 may make to execute fraud recognition methods.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute fraud recognition methods.
The network interface 505 is for carrying out network communication, such as the transmission of offer data information.Those skilled in the art can
To understand, structure shown in Fig. 9, only the block diagram of part-structure relevant to the present invention program, is not constituted to this hair
The restriction for the computer equipment 500 that bright scheme is applied thereon, specific computer equipment 500 may include than as shown in the figure
More or fewer components perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following function
Can: the corresponding node of Claims Resolution data is obtained, the corresponding nodal parallel of the Claims Resolution data is divided by multiple sons by spectral clustering
Figure；Multiple subgraphs are clustered respectively, obtain network community；The network associate data obtained according to historical data are obtained, if
It is retrieved in network community in the presence of clustering corporations identical with network associate data point, obtains the clustering corporations point；
If corresponding score of the clustering corporations point exceeds preset scoring threshold value, the clustering corporations point is placed in doubtful fraud corporations
In grouping.
In one embodiment, processor 502 execute it is described by spectral clustering by the corresponding node of the Claims Resolution data simultaneously
It when row is divided into the step of multiple subgraphs, performs the following operations: obtaining inputted similarity matrix and target clusters number；Root
The corresponding similar matrix of corresponding with Claims Resolution data node is constructed according to the similarity matrix；According to the similar matrix structure
Adjacency matrix and diagonal matrix are built, Laplacian Matrix is obtained by the difference of the diagonal matrix and the adjacency matrix；Obtain institute
Feature vector corresponding to the characteristic value before ranking in multiple characteristic values of Laplacian Matrix is located at default rank threshold is stated,
To obtain target feature vector set；It is column vector and successively group by feature vector transposition each in target feature vector set
It closes, to obtain object vector matrix；Row vector each in object vector matrix is clustered by k-means algorithm, obtain with
The identical sub- group of the target clusters number.
In one embodiment, processor 502 execute it is described multiple subgraphs are clustered respectively, obtain network community
It when step, performs the following operations: multiple subgraphs is subjected to knitmesh respectively, obtain social networks topological diagram of initially settling a claim；Pass through society
Group's detection clusters initial Claims Resolution social networks topological diagram, obtains network community.
In one embodiment, processor 502 execute it is described by corporations' detection to social networks topological diagram of initially settling a claim
It after the step of being clustered, obtaining network community, performs the following operations: obtaining included each corporations in the network community
Corresponding modularity；If the corresponding modularity of each corporations is respectively less than 1, identifies the network community and tested by community network division
Card；If there is the corresponding modularity of corporations to be greater than or equal to 1, identifies the network community and verifying is not divided by community network, lead to
It crosses corporations of corporations' detection to modularity more than or equal to 1 to cluster, obtains updated corporations' network.
In one embodiment, if processor 502 is executing the corresponding scoring of clustering corporations point beyond preset
Score threshold value, and the clustering corporations point is placed in front of the step in the grouping of doubtful fraud corporations, also performs the following operations: obtaining
Connection weight in clustering corporations point between each node, and sum to the connection weight between each node, obtain group
The corresponding scoring of poly- corporations' point.
It will be understood by those skilled in the art that the embodiment of computer equipment shown in Fig. 9 is not constituted to computer
The restriction of equipment specific composition, in other embodiments, computer equipment may include components more more or fewer than diagram, or
Person combines certain components or different component layouts.For example, in some embodiments, computer equipment can only include depositing
Reservoir and processor, in such embodiments, the structure and function of memory and processor are consistent with embodiment illustrated in fig. 9,
Details are not described herein.
It should be appreciated that in embodiments of the present invention, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable GateArray, FPGA) or other programmable logic devices
Part, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
The processor is also possible to any conventional processor etc..
Computer readable storage medium is provided in another embodiment of the invention.The computer readable storage medium can be with
For non-volatile computer readable storage medium.The computer-readable recording medium storage has computer program, wherein calculating
Machine program performs the steps of acquisition Claims Resolution data corresponding node when being executed by processor, by spectral clustering by the Claims Resolution
The corresponding nodal parallel of data is divided into multiple subgraphs；Multiple subgraphs are clustered respectively, obtain network community；Obtain basis
The network associate data that historical data obtains, if being retrieved in network community in the presence of group identical with the network associate data
Poly- corporations' point obtains the clustering corporations point；If corresponding score of the clustering corporations point exceeds preset scoring threshold value, by institute
Clustering corporations point is stated to be placed in doubtful fraud corporations grouping.
In one embodiment, described that the corresponding nodal parallel of the Claims Resolution data is divided by multiple sons by spectral clustering
Figure, comprising: obtain inputted similarity matrix and target clusters number；According to similarity matrix building and the Claims Resolution
The corresponding similar matrix of the corresponding node of data；Adjacency matrix and diagonal matrix are constructed according to the similar matrix, by described right
Angular moment battle array and the difference of the adjacency matrix obtain Laplacian Matrix；It obtains and is arranged in multiple characteristic values of the Laplacian Matrix
Name is located at feature vector corresponding to the characteristic value before presetting rank threshold, to obtain target feature vector set；By target
Each feature vector transposition is column vector and successively combines in feature vector set, to obtain object vector matrix；Pass through k-
Means algorithm clusters row vector each in object vector matrix, obtains sub- group identical with the target clusters number.
In one embodiment, described to cluster multiple subgraphs respectively, obtain network community, comprising: by multiple subgraphs
Knitmesh is carried out respectively, obtains social networks topological diagram of initially settling a claim；By corporations' detection to initial Claims Resolution social networks topological diagram
It is clustered, obtains network community.
In one embodiment, described that initial Claims Resolution social networks topological diagram is clustered by corporations' detection, obtain net
Network corporations, further includes: obtain the corresponding modularity of included each corporations in the network community；If the corresponding mould of each corporations
Lumpiness is respectively less than 1, identifies the network community by community network and divides verifying；If there is the corresponding modularity of corporations to be greater than or wait
It in 1, identifies the network community and verifying is not divided by community network, 1 is greater than or equal to modularity by corporations' detection
Corporations are clustered, and updated corporations' network is obtained.
It in one embodiment, will be described if the corresponding scoring of clustering corporations point exceeds preset scoring threshold value
Before clustering corporations point is placed in doubtful fraud corporations grouping, further includes: obtain the connection in clustering corporations point between each node
It is weight, and sums to the connection weight between each node, obtains the corresponding scoring of clustering corporations point.
It is apparent to those skilled in the art that for convenience of description and succinctly, foregoing description is set
The specific work process of standby, device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Those of ordinary skill in the art may be aware that unit described in conjunction with the examples disclosed in the embodiments of the present disclosure and algorithm
Step can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and software
Interchangeability generally describes each exemplary composition and step according to function in the above description.These functions are studied carefully
Unexpectedly the specific application and design constraint depending on technical solution are implemented in hardware or software.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided by the present invention, it should be understood that disclosed unit and method, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only logical function partition, there may be another division manner in actual implementation, can also will be with the same function
Unit set is at a unit, such as multiple units or components can be combined or can be integrated into another system or some
Feature can be ignored, or not execute.In addition, shown or discussed mutual coupling, direct-coupling or communication connection can
Be through some interfaces, the indirect coupling or communication connection of device or unit, be also possible to electricity, mechanical or other shapes
Formula connection.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing
The all or part of part or the technical solution that technology contributes can be embodied in the form of software products, should
Computer software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
Personal computer, server or network equipment etc.) execute all or part of step of each embodiment the method for the present invention
Suddenly.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic disk or
The various media that can store program code such as person's CD.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of fraud recognition methods characterized by comprising
The corresponding node of Claims Resolution data is obtained, the corresponding nodal parallel of the Claims Resolution data is divided by multiple sons by spectral clustering
Figure；
Multiple subgraphs are clustered respectively, obtain network community；
The network associate data obtained according to historical data are obtained, are existed and the network associate if being retrieved in network community
The identical clustering corporations point of data, obtains the clustering corporations point；
If corresponding score of the clustering corporations point exceeds preset scoring threshold value, the clustering corporations point is placed in doubtful fraud
In corporations' grouping.
2. fraud recognition methods according to claim 1, which is characterized in that it is described by spectral clustering by the Claims Resolution data
Corresponding nodal parallel is divided into multiple subgraphs, comprising:
Obtain inputted similarity matrix and target clusters number；
The corresponding similar matrix of corresponding with Claims Resolution data node is constructed according to the similarity matrix；
Adjacency matrix and diagonal matrix are constructed according to the similar matrix, is obtained by the difference of the diagonal matrix and the adjacency matrix
To Laplacian Matrix；
It obtains corresponding to the characteristic value before ranking in multiple characteristic values of the Laplacian Matrix is located at default rank threshold
Feature vector, to obtain target feature vector set；
It is column vector by feature vector transposition each in target feature vector set and successively combines, obtains object vector square
Battle array；
Row vector each in object vector matrix is clustered by k-means algorithm, is obtained and the target clusters number phase
Same son group.
3. fraud recognition methods according to claim 1, which is characterized in that it is described to cluster multiple subgraphs respectively,
Obtain network community, comprising:
Multiple subgraphs are subjected to knitmesh respectively, obtain social networks topological diagram of initially settling a claim；
Initial Claims Resolution social networks topological diagram is clustered by corporations' detection, obtains network community.
4. fraud recognition methods according to claim 3, which is characterized in that described to be detected by corporations to initial Claims Resolution society
It hands over network topological diagram to be clustered, obtains network community, further includes:
Obtain the corresponding modularity of included each corporations in the network community；
If the corresponding modularity of each corporations is respectively less than 1, identifies the network community and pass through community network and divide verifying；
If there is the corresponding modularity of corporations to be greater than or equal to 1, identifies the network community and verifying is not divided by community network, lead to
It crosses corporations of corporations' detection to modularity more than or equal to 1 to cluster, obtains updated corporations' network.
5. fraud recognition methods according to claim 1, which is characterized in that commented if clustering corporations point is corresponding
Divide and exceed preset scoring threshold value, before the clustering corporations point is placed in doubtful fraud corporations grouping, further includes:
The connection weight in clustering corporations point between each node is obtained, and the connection weight between each node is asked
With obtain the corresponding scoring of clustering corporations point.
6. a kind of fraud identification device characterized by comprising
Subgraph division unit, for obtaining the corresponding node of Claims Resolution data, by spectral clustering by the corresponding section of the Claims Resolution data
Point parallel patition is multiple subgraphs；
Network community acquiring unit obtains network community for clustering multiple subgraphs respectively；
Clustering corporations point retrieval unit, for obtaining the network associate data obtained according to historical data, if in network community
It retrieves in the presence of clustering corporations identical with network associate data point, obtains the clustering corporations point；
Corporations' judging unit is cheated, it, will be described if exceeding preset scoring threshold value for the corresponding scoring of the clustering corporations point
Clustering corporations point is placed in doubtful fraud corporations grouping.
7. fraud identification device according to claim 6, which is characterized in that the subgraph division unit, comprising:
Initial typing unit, for obtaining inputted similarity matrix and target clusters number；
Similar matrix construction unit, it is corresponding for constructing node corresponding with the Claims Resolution data according to the similarity matrix
Similar matrix；
Laplacian Matrix construction unit, for constructing adjacency matrix and diagonal matrix according to the similar matrix, by described right
Angular moment battle array and the difference of the adjacency matrix obtain Laplacian Matrix；
Target feature vector set acquiring unit, ranking is located at pre- in multiple characteristic values for obtaining the Laplacian Matrix
If feature vector corresponding to the characteristic value before rank threshold, to obtain target feature vector set；
Object vector matrix acquiring unit, for by feature vector transposition each in target feature vector set be column vector and according to
Secondary combination, to obtain object vector matrix；
Matrix Cluster unit obtains and institute for being clustered row vector each in object vector matrix by k-means algorithm
State the identical sub- group of target clusters number.
8. fraud identification device according to claim 6, which is characterized in that the network community acquiring unit, comprising:
Initial knitmesh unit obtains social networks topological diagram of initially settling a claim for multiple subgraphs to be carried out knitmesh respectively；
Corporations' detection unit obtains network society for clustering by corporations' detection to initial Claims Resolution social networks topological diagram
Group.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
Any one of described in fraud recognition methods.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer journey
Sequence, the computer program make the processor execute such as described in any one of claim 1 to 5 take advantage of when being executed by a processor
Cheat recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811527396.XA CN109816535A (en) | 2018-12-13 | 2018-12-13 | Cheat recognition methods, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811527396.XA CN109816535A (en) | 2018-12-13 | 2018-12-13 | Cheat recognition methods, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109816535A true CN109816535A (en) | 2019-05-28 |
Family
ID=66601587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811527396.XA Pending CN109816535A (en) | 2018-12-13 | 2018-12-13 | Cheat recognition methods, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816535A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209660A (en) * | 2019-06-10 | 2019-09-06 | 北京阿尔山金融科技有限公司 | Cheat clique's method for digging, device and electronic equipment |
| CN110348516A (en) * | 2019-07-11 | 2019-10-18 | 同盾控股有限公司 | Data processing method, device, storage medium and electronic equipment |
| CN110598128A (en) * | 2019-09-11 | 2019-12-20 | 西安电子科技大学 | Community detection method for large-scale network for resisting Sybil attack |
| CN110705585A (en) * | 2019-08-22 | 2020-01-17 | 深圳壹账通智能科技有限公司 | Network fraud identification method and device, computer device and storage medium |
| CN111091287A (en) * | 2019-12-13 | 2020-05-01 | 南京三百云信息科技有限公司 | Risk object identification method and device and computer equipment |
| CN111259952A (en) * | 2020-01-14 | 2020-06-09 | 中国平安财产保险股份有限公司 | Abnormal user identification method and device, computer equipment and storage medium |
| CN111612039A (en) * | 2020-04-24 | 2020-09-01 | 平安直通咨询有限公司上海分公司 | Abnormal user identification method and device, storage medium and electronic equipment |
| CN111641518A (en) * | 2020-04-29 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Heterogeneous network-based community division method and device, computer equipment and medium |
| 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 |
| CN111931023A (en) * | 2020-07-01 | 2020-11-13 | 西北工业大学 | Community structure identification method and device based on network embedding |
| CN112396160A (en) * | 2020-11-02 | 2021-02-23 | 北京大学 | Transaction fraud detection method and system based on graph neural network |
| WO2021189730A1 (en) * | 2020-03-27 | 2021-09-30 | 深圳壹账通智能科技有限公司 | Method, apparatus and device for detecting abnormal dense subgraph, and storage medium |
| CN113487109A (en) * | 2021-07-27 | 2021-10-08 | 中国平安财产保险股份有限公司 | Group identification method and device, electronic equipment and storage medium |
| CN115293919A (en) * | 2022-07-22 | 2022-11-04 | 浙江大学 | Graph neural network prediction method and system oriented to social network distribution generalization |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469315A (en) * | 2015-08-04 | 2016-04-06 | 电子科技大学 | Dynamic social network community structure evolution method based on incremental clustering |
| WO2018103456A1 (en) * | 2016-12-06 | 2018-06-14 | 中国银联股份有限公司 | Method and apparatus for grouping communities on the basis of feature matching network, and electronic device |
| CN108681936A (en) * | 2018-04-26 | 2018-10-19 | 浙江邦盛科技有限公司 | A kind of fraud clique recognition methods propagated based on modularity and balance label |
| CN108960335A (en) * | 2018-07-13 | 2018-12-07 | 大连理工大学 | One kind carrying out efficient clustering method based on large scale network |
-
2018
- 2018-12-13 CN CN201811527396.XA patent/CN109816535A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469315A (en) * | 2015-08-04 | 2016-04-06 | 电子科技大学 | Dynamic social network community structure evolution method based on incremental clustering |
| WO2018103456A1 (en) * | 2016-12-06 | 2018-06-14 | 中国银联股份有限公司 | Method and apparatus for grouping communities on the basis of feature matching network, and electronic device |
| CN108681936A (en) * | 2018-04-26 | 2018-10-19 | 浙江邦盛科技有限公司 | A kind of fraud clique recognition methods propagated based on modularity and balance label |
| CN108960335A (en) * | 2018-07-13 | 2018-12-07 | 大连理工大学 | One kind carrying out efficient clustering method based on large scale network |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209660A (en) * | 2019-06-10 | 2019-09-06 | 北京阿尔山金融科技有限公司 | Cheat clique's method for digging, device and electronic equipment |
| CN110209660B (en) * | 2019-06-10 | 2021-12-24 | 北京阿尔山金融科技有限公司 | Cheating group mining method and device and electronic equipment |
| CN110348516B (en) * | 2019-07-11 | 2021-05-11 | 同盾控股有限公司 | Data processing method, data processing device, storage medium and electronic equipment |
| CN110348516A (en) * | 2019-07-11 | 2019-10-18 | 同盾控股有限公司 | Data processing method, device, storage medium and electronic equipment |
| CN110705585A (en) * | 2019-08-22 | 2020-01-17 | 深圳壹账通智能科技有限公司 | Network fraud identification method and device, computer device and storage medium |
| CN110598128A (en) * | 2019-09-11 | 2019-12-20 | 西安电子科技大学 | Community detection method for large-scale network for resisting Sybil attack |
| CN110598128B (en) * | 2019-09-11 | 2022-08-09 | 西安电子科技大学 | Community detection method for large-scale network for resisting Sybil attack |
| CN111091287A (en) * | 2019-12-13 | 2020-05-01 | 南京三百云信息科技有限公司 | Risk object identification method and device and computer equipment |
| CN111259952A (en) * | 2020-01-14 | 2020-06-09 | 中国平安财产保险股份有限公司 | Abnormal user identification method and device, computer equipment and storage medium |
| WO2021189730A1 (en) * | 2020-03-27 | 2021-09-30 | 深圳壹账通智能科技有限公司 | Method, apparatus and device for detecting abnormal dense subgraph, and storage medium |
| CN111612039A (en) * | 2020-04-24 | 2020-09-01 | 平安直通咨询有限公司上海分公司 | Abnormal user identification method and device, storage medium and electronic equipment |
| CN111612039B (en) * | 2020-04-24 | 2023-09-29 | 平安直通咨询有限公司上海分公司 | Abnormal user identification method and device, storage medium and electronic equipment |
| CN111641518A (en) * | 2020-04-29 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Heterogeneous network-based community division method and device, computer equipment and medium |
| 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 |
| CN111931023A (en) * | 2020-07-01 | 2020-11-13 | 西北工业大学 | Community structure identification method and device based on network embedding |
| CN112396160A (en) * | 2020-11-02 | 2021-02-23 | 北京大学 | Transaction fraud detection method and system based on graph neural network |
| CN113487109A (en) * | 2021-07-27 | 2021-10-08 | 中国平安财产保险股份有限公司 | Group identification method and device, electronic equipment and storage medium |
| CN113487109B (en) * | 2021-07-27 | 2023-11-24 | 中国平安财产保险股份有限公司 | Group identification method, group identification device, electronic equipment and storage medium |
| CN115293919A (en) * | 2022-07-22 | 2022-11-04 | 浙江大学 | Graph neural network prediction method and system oriented to social network distribution generalization |
| CN115293919B (en) * | 2022-07-22 | 2023-08-04 | 浙江大学 | Social network distribution outward generalization-oriented graph neural network prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816535A (en) | Cheat recognition methods, device, computer equipment and storage medium | |
| CN109784636A (en) | Fraudulent user recognition methods, device, computer equipment and storage medium | |
| CN109859054A (en) | Network community method for digging, device, computer equipment and storage medium | |
| CN109598509A (en) | The recognition methods of risk clique and device | |
| CN108874927A (en) | Intrusion detection method based on hypergraph and random forest | |
| CN106469276B (en) | Type identification method and device of data sample | |
| CN108809745A (en) | A kind of user's anomaly detection method, apparatus and system | |
| CN111612038B (en) | Abnormal user detection method and device, storage medium and electronic equipment | |
| CN110443120A (en) | A kind of face identification method and equipment | |
| CN108510396B (en) | Method and device for insurance verification, computer equipment and storage medium | |
| CN111596924B (en) | Micro-service dividing method and device | |
| CN104517052B (en) | Invasion detection method and device | |
| CN106960153B (en) | Virus type identification method and device | |
| CN111931047B (en) | Artificial intelligence-based black product account detection method and related device | |
| US9529935B2 (en) | Efficient link management for graph clustering | |
| CN111460315B (en) | Community portrait construction method, device, equipment and storage medium | |
| CN113807940B (en) | Information processing and fraud recognition method, device, equipment and storage medium | |
| CN109960839B (en) | Service link discovery method and system of service support system based on machine learning | |
| CN114265740A (en) | Error information processing method, device, equipment and storage medium | |
| CN109325814A (en) | A method of for finding suspicious trade network | |
| CN112241820A (en) | Risk identification method and device for key nodes in fund flow and computing equipment | |
| CN108429632B (en) | Service monitoring method and device | |
| CN109670976B (en) | Feature factor determination method and device | |
| CN109949070A (en) | Usage rate of the user appraisal procedure, device, computer equipment and storage medium | |
| CN110427558A (en) | The method for pushing and device of Energy Resources Service's director's part |
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 |