CN113988718A

CN113988718A - Risk identification method, device and equipment

Info

Publication number: CN113988718A
Application number: CN202111585663.0A
Authority: CN
Inventors: 王宝坤; 张屹綮; 石磊磊
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2021-12-23
Filing date: 2021-12-23
Publication date: 2022-01-28

Abstract

The embodiment of the specification discloses a risk identification method, a risk identification device and risk identification equipment, wherein the method comprises the following steps: obtaining a bipartite graph constructed based on business information of a target business, then carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation condition of nodes in the bipartite graph to obtain at least one sub bipartite graph, and finally identifying risks of other nodes in the bipartite graph based on risk nodes contained in the sub bipartite graph and incidence relation information between the risk nodes in the sub bipartite graph and other nodes except the risk nodes to obtain the degree of the risk of each other node in the sub bipartite graph.

Description

Risk identification method, device and equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a risk identification method, apparatus, and device.

Background

In recent years, telecommunication fraud events are in endless, and besides an account on a certain service platform, many fraud parties also have accounts on other service platforms besides the service platform, so that the fraud parties can not only cheat users through interaction channels provided by the service platform, but also can cheat users through interaction channels provided by other various service platforms, especially among service platforms capable of service interaction, through the service interaction, different types of accounts are connected to form a bipartite graph, meanwhile, due to the difference of the service platforms, transactions among accounts outside a certain service platform system cannot be obtained, namely only one subgraph of a service interaction network can be obtained, and therefore difficulty is brought to risk identification. Therefore, it is necessary to provide a technical solution that can make full use of the bipartite graph information and can perform risk evaluation on each node in the bipartite graph.

Disclosure of Invention

The purpose of the embodiments of the present specification is to provide a technical solution that can make full use of bipartite graph information and can perform risk evaluation on each node in a bipartite graph.

In order to implement the above technical solution, the embodiments of the present specification are implemented as follows:

the embodiment of the specification provides a risk identification method, which comprises the following steps: and acquiring a bipartite graph constructed based on the service information of the target service. And carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. Identifying risks of other nodes in the sub-bipartite graph based on risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, and obtaining the degree of risk of each other node in the sub-bipartite graph.

The risk identification method provided by the embodiment of the specification is applied to a block chain system, and the method comprises the following steps: acquiring risk identification rule information based on a bipartite graph aiming at target business, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into the blockchain system. And calling the first intelligent contract to obtain a bipartite graph constructed based on the service information of the target service. And carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. Identifying risks existing in other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk existing in each other node in the sub-bipartite graph.

The embodiment of the present specification provides a risk identification device, including: and the bipartite graph acquisition module is used for acquiring a bipartite graph constructed based on the service information of the target service. And the community division module is used for carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. And the risk identification module is used for identifying risks existing in other nodes in the sub-bipartite graph based on risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the risk degree of each other node in the sub-bipartite graph.

The embodiment of the present specification provides a risk identification device, where the risk identification device is a device in a blockchain system, and the device includes: and the contract deployment module is used for acquiring risk identification rule information based on a bipartite graph aiming at target services, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into the block chain system. And the bipartite graph acquisition module calls the first intelligent contract to acquire a bipartite graph constructed based on the service information of the target service. And the community division module is used for carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. And the risk identification module is used for identifying risks of other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the risk degree of each other node in the sub-bipartite graph.

The embodiment of the present specification provides a risk identification device, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: and acquiring a bipartite graph constructed based on the service information of the target service. And carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. Identifying risks of other nodes in the sub-bipartite graph based on risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, and obtaining the degree of risk of each other node in the sub-bipartite graph.

The embodiment of the present specification provides a risk identification device, where the device is a device in a blockchain system, and the risk identification device includes: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to: acquiring risk identification rule information based on a bipartite graph aiming at target business, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into the blockchain system. And calling the first intelligent contract to obtain a bipartite graph constructed based on the service information of the target service. And carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. Identifying risks existing in other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk existing in each other node in the sub-bipartite graph.

Embodiments of the present specification also provide a storage medium, where the storage medium is used to store computer-executable instructions, and the executable instructions, when executed, implement the following processes: and acquiring a bipartite graph constructed based on the service information of the target service. And carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. Identifying risks of other nodes in the sub-bipartite graph based on risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, and obtaining the degree of risk of each other node in the sub-bipartite graph.

Embodiments of the present specification also provide a storage medium, where the storage medium is used to store computer-executable instructions, and the executable instructions, when executed, implement the following processes: acquiring risk identification rule information based on a bipartite graph aiming at target business, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into a block chain system. And calling the first intelligent contract to obtain a bipartite graph constructed based on the service information of the target service. And carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph. Identifying risks existing in other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk existing in each other node in the sub-bipartite graph.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the specification, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive exercise:

FIG. 1 illustrates an embodiment of a risk identification method of the present disclosure;

FIG. 2 is a schematic diagram of a risk identification system according to the present disclosure;

FIG. 3 is a schematic structural diagram of a risk identification correlation interface according to the present disclosure;

FIG. 4 is a schematic diagram of a bipartite graph according to the present disclosure;

FIG. 5 is another embodiment of a risk identification method of the present disclosure;

FIG. 6 is a schematic view of a bipartite projection according to the present description;

FIG. 7 is a structural diagram of a node association according to the present disclosure;

FIG. 8A is a flowchart of yet another embodiment of a risk identification method of the present disclosure;

FIG. 8B is a schematic diagram of a risk identification process according to the present disclosure;

FIG. 9 illustrates an embodiment of a risk identification device according to the present disclosure;

FIG. 10 is another risk identification device embodiment of the present disclosure;

fig. 11 illustrates an embodiment of a risk identification device according to the present disclosure.

Detailed Description

The embodiment of the specification provides a risk identification method, a risk identification device and risk identification equipment.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all of the embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments in the present specification without any inventive step should fall within the scope of protection of the present specification.

Example one

As shown in fig. 1, an execution main body of the method may be a terminal device or a server, where the terminal device may be a mobile terminal device such as a mobile phone and a tablet computer, or a device such as a personal computer, the server may be an independent server, or a server cluster formed by a plurality of servers, and the server may be a background server such as a financial service or an online shopping service, or a background server of an application. The method may be applied to a service scenario capable of constructing a bipartite graph, and the server is taken as an execution subject in this embodiment for detailed description, and for the case of the terminal device, the following related contents may be referred to, and are not described herein again. The method may specifically comprise the steps of:

in step S102, a bipartite graph constructed based on service information of a target service is acquired.

The target service may be any service, for example, the target service may be a financial service, an internet shopping service, and the like, which is specifically set according to an actual situation, and this is not limited in this embodiment of the specification. The service information may be information related to the target service, for example, the service information may include information of a purchaser and information of a merchant in the online shopping service, the information of the purchaser may include account information of the purchaser, shopping history information of the purchaser, and the like, the information of the merchant may include account information of the merchant, transaction history information of the merchant, and the like, and the service information may also include information related to both parties of a transaction in the financial service, and the information may be specifically set according to an actual situation, which is not limited in this embodiment of the specification. A bipartite graph may also be referred to as a bipartite graph, and if G = (V, E) is an undirected graph, if a vertex V can be divided into two mutually disjoint subsets (a, B), and two vertices i and j associated with each edge (i, j) in the graph belong to two different vertex sets, i.e., vertex i belongs to subset a and vertex j belongs to subset B, the graph G is referred to as a bipartite graph.

In implementation, in recent years, telecommunication fraud events are endlessly established, and many fraud parties have accounts on a certain service platform and also on other service platforms besides the service platform, so that the fraud parties can not only cheat users through interaction channels provided by the service platform, but also can cheat users through interaction channels provided by other service platforms, especially among service platforms capable of service interaction, through the service interaction, different types of accounts are connected to form a heterogeneous graph (i.e. a graph with more than one node type or relationship type), meanwhile, due to the difference of service platforms, transactions among accounts outside a certain service platform system cannot be obtained, i.e. only one subgraph of a service interaction network can be obtained, thereby bringing difficulty to risk identification.

The data structure formed by the business risks may be defined as a heterogeneous graph relationship, where a business initiator (an account in a certain business platform hierarchy) serves as one type of node, and a target (an account outside the certain business platform hierarchy) serves as another type of node, specifically, for example, a user of a financial service provided by a certain financial organization and a user of a certain bank. How to determine the potential risks from bipartite graphs becomes a current problem that needs to be addressed. In general, a bipartite graph can be treated as a homogeneity graph, and then the bipartite graph is cut by using a Louvain algorithm to obtain a corresponding subgraph. And calculating the occupation ratio of the risk nodes in each subgraph, and acquiring the subgraph with the occupation ratio higher than a preset threshold, wherein the nodes except the risk nodes in the subgraph are potential risk nodes. However, in the above-mentioned method, characteristics of the bipartite graph are not considered when performing subgraph division, if the bipartite graph is simply treated as a homogenous graph, much bipartite graph information will be lost, and in practical applications, people will pay more attention to aggregation of one of the node sets, but the method of the homogenous graph cannot be implemented. The embodiment provides a selectable processing manner, which may specifically include the following:

the service information of the target service may be obtained in a variety of different manners, for example, as shown in fig. 2, an input page of the service information of the target service may be preset, and the input page may include a data input box, a determination key, a cancel key, and the like of the service information of the target service. As shown in fig. 3, a user may input the service information of the target service in the data input box of the input page, and after the input is completed, the user may click a determination key in the input page, and at this time, the server may obtain the service information of the target service, and may obtain a certain amount of service information of the target service by the above manner. Or, the server may record related data of a certain service, when service information of a target service needs to be acquired, data meeting a specified requirement may be acquired from the related data of the service, and the acquired data may be used as service information of the target service, and the like.

After the service information of the target service is obtained in the above manner, a corresponding bipartite graph may be constructed based on the service information of the target service, for example, as shown in fig. 4, the node on the left side is a node set (including nodes a to E) formed by accounts of buyers in the online shopping service, the node on the right side is a node set (including nodes a to E) formed by accounts registered by a merchant in a certain bank, and a connection line between the nodes on the two sides is used to represent that there is a certain association relationship between the two nodes, such as a purchasing relationship, a transaction relationship, and the like, which may be specifically set according to an actual situation, and is not limited in this description.

It should be noted that, as shown in fig. 4, edges in the bipartite graph only exist between the node assembly a and the node assembly B, and there is no connected edge inside the node assembly a and the node assembly B. In fraud identification, a node in a node set A can be used as an account in a certain service platform system, a node in a node set B can be used as an account outside the service platform system, the node set A and the node set B are associated through a transaction relationship, and if an account outside the service platform system and an account in the service platform system perform a money transfer transaction, an edge is connected between the two accounts.

In step S104, based on the aggregation of the nodes in the bipartite graph, performing community partition on the bipartite graph through a bipartite graph community discovery algorithm to obtain at least one sub-bipartite graph.

The bipartite graph community discovery algorithm may include multiple algorithms, for example, an algorithm based on a characteristic value of a laplacian matrix, and the like, and may be specifically set according to an actual situation, which is not limited in this specification. The aggregation condition of the nodes in the bipartite graph may be determined in a variety of different manners, for example, the aggregation condition may be determined by the number or the association complexity of the association relationship between the nodes in the bipartite graph in a specified spatial region, and based on this, if edges connected between nodes in a certain local region in the bipartite graph are denser, the nodes in the local region are more aggregated, and conversely, the nodes in the local region are more sparse, and the like.

In implementation, an algorithm of eigenvalues of the laplacian matrix may be selected as a bipartite graph community discovery algorithm, at this time, the bipartite graph may be analyzed to determine a laplacian matrix corresponding to the bipartite graph, then, a second small eigenvalue of the laplacian matrix and a corresponding matrix thereof may be calculated by combining aggregation conditions of nodes in the bipartite graph, nodes of positive values in a column vector formed by a plurality of nodes may be divided into one group, nodes of negative values therein may be divided into another group, and nodes in each group may be derived from two node sets, so that nodes in each group may also construct one sub-bipartite graph, thereby performing community division on the bipartite graph to obtain at least one sub-bipartite graph.

It should be noted that the community division manner is only one realizable manner, and in practical applications, the community division manner may include multiple realizable community division manners, which may be set according to practical situations, and this is not limited in the embodiment of the present specification.

In step S106, based on the risk nodes included in the sub-bipartite graph and the association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, the risks existing in the other nodes in the sub-bipartite graph are identified, and the degree of risk existing in each other node in the sub-bipartite graph is obtained.

The risk node may be a node that has been predetermined to have a certain risk, for example, an account of a certain merchant is reported or complained by a plurality of users: the account has a fraud risk, the service platform side can determine whether the account of the merchant has the fraud risk by performing risk evaluation on the account of the merchant, if the account of the merchant has the fraud risk, a corresponding mark (such as setting a fraud label) can be set on the account of the merchant to indicate that the account of the merchant is a risk account, and if the account of the merchant does not have the risk, the account can not be processed. The association relationship information may include various types, such as transaction relationships, friend relationships, and the like, and may be specifically set according to actual conditions.

In implementation, after the bipartite graph is divided into one or more different sub bipartite graphs in the manner described above, a risk account included in each sub bipartite graph may be obtained (specifically, according to a label carried by a node in each sub bipartite graph, if a node carries a fraud tag, the node may be determined to be a risk node, and if a node not carrying the fraud tag is a node that does not have a risk, etc.), furthermore, for each sub bipartite graph, a node that does not have a risk may be obtained from the sub bipartite graph, and association relationship information between the node that does not have a risk and the risk nodes may be obtained, that is, which node and which risk node or which risk nodes have a connected edge in the node that does not have a risk, the number of edges between each node that does not have a risk and the risk node may be counted, and a correlation between the node that does not have a risk and a known risk node may be measured by the counted number, the higher the correlation is, the greater the potential risk possibility is, so as to identify the risk existing in other nodes in the bipartite graph, and furthermore, the degree of risk existing in each other node in the bipartite graph can be determined by the number of statistics corresponding to each node without risk, wherein the larger the number of statistics corresponding to the node is, the higher the risk existing degree of the node is, the smaller the number of statistics corresponding to the node is, and the lower the risk existing degree of the node is.

The embodiment of the specification provides a risk identification method, which includes acquiring a bipartite graph constructed based on business information of a target business, performing community division on the bipartite graph through a bipartite graph community discovery algorithm based on an aggregation condition of nodes in the bipartite graph to obtain at least one sub bipartite graph, and finally identifying risks of other nodes in the bipartite graph based on risk nodes contained in the sub bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub bipartite graph to obtain a degree of risk of each other node in the sub bipartite graph, so that a bipartite graph community division mode based on the bipartite graph community discovery algorithm and a risk identification scheme of the nodes are designed based on characteristics of the bipartite graph to measure incidence relations between potential nodes and risk nodes in each sub bipartite graph, therefore, risk detection and identification of the nodes are completed, and the purpose of risk evaluation of each node in the bipartite graph is achieved.

Example two

As shown in fig. 5, an execution main body of the method may be a terminal device or a server, where the terminal device may be a mobile terminal device such as a mobile phone and a tablet computer, or a device such as a personal computer, the server may be an independent server, or a server cluster formed by a plurality of servers, and the server may be a backend server such as a financial service or an online shopping service, or a backend server of an application. The method may be applied to a service scenario capable of constructing a bipartite graph, and the server is taken as an execution subject in this embodiment for detailed description, and for the case of the terminal device, the following related contents may be referred to, and are not described herein again. The method may specifically comprise the steps of:

in step S502, a bipartite graph constructed based on service information of a target service is acquired.

In step S504, based on the aggregation condition of the nodes in the bipartite graph, the bipartite graph is subjected to community partition by using a bilovain algorithm to obtain at least one sub-bipartite graph.

In implementation, a bipartite graph is constructed through the above step S502, the bipartite graph is composed of a node set a and a node set B and an interaction relationship between the two node sets, and if an account in which a node corresponds to is present has been identified as being at risk of fraud, the node is provided with a risk label. The community division (i.e. subgraph cutting) is performed on the bipartite graph in order to find a sub bipartite graph (or called community) in which data interaction (such as transfer, etc.) between the bipartite graph is particularly frequent, and in the sub bipartite graph with dense interaction, many risky accounts (which may include risky bank accounts, etc.) may appear in a concentrated manner. How to determine the risk of an account, a bipartite graph can be regarded as a homogeneous graph, then, a community partition is performed by using a Louvain algorithm, and the Modularity modulation is optimized by the Louvain algorithm. The most primitive Modularity formula is as follows:

wherein E is the total sum of the edge weights in the bipartite graph,

represents the sum of the edge weights of all connections pointing to node i,

represents the sum of the edge weights of all connections pointing to node j,

the probability of the node j being connected to any node can be defined, and the weight of a certain node i except the node j is defined as

Then the expected values of the weighted values of the node i and the node j under random conditions can be obtained

The expectation is defined as a null model.

Representing the edge weights of the connections between nodes i, j,

subtracting from the expected value can characterize the difference between the currently connected edge and the randomly connected edge. c (i) and c (j) represent the numbers of the subpartitions where the nodes i and j are located, and if two nodes are in the same subpartition, the number is delta = 1. According to the modularity formula, the better community division mode is to maximize the modularity Q.

Modulation gives a community partitioning approach for homogenous graphs, but this approach does not take into account the original input bipartite graph relationship. The Bilouvain algorithm modifies the original modulation formula for the characteristics of the bipartite graph. In the Bipartite graph, neither node set a nor node set B have edges connected inside, and therefore, the matrix a in the modularity formula becomes a block matrix, which can be further written as binary Adjacency metric of N × M (i.e., in the following formula)

) I.e. by

The Bi-louvain algorithm optimizes the modulation formula in an iterative calculation mode, when the value reaches the maximum value, a better community partition is obtained from the global view, each sub-community also corresponds to a bipartite graph, and each sub-community corresponds to a bipartite graphIn the sub-bipartite graph, the interaction between node set a and node set B is denser. Wherein,

and carrying out community division by using a Bi-louvain algorithm to obtain a plurality of sub bipartite graphs. The nodes possibly existing in the node set A and the node set B in each sub-bipartite graph are qualified as being at risk, the sub-bipartite graph without risk can be directly ignored, and only the sub-bipartite graph with the risk nodes is reserved, because the scheme is to find whether the potential risk nodes exist in the same sub-bipartite graph. Nodes in each sub-community that do not have a risk can be scored to measure the relevance between the node and nodes known to have a risk, and if the relevance is higher, the potential risk is higher.

In addition to optimizing the modulority formula to classify the bipartite graph into communities in the above manner, the above processing may also classify the bipartite graph into communities in other manners, and an alternative processing manner is provided below, and may specifically include the processing of step C2 and step C4 below.

In step C2, the first node set included in the bipartite graph is projected to obtain a projected node set.

In implementation, a node set may be considered, that is, a bipartite graph is projected, as shown in fig. 6, the bipartite graph includes a node set a and a node set B, and if a projection relationship on the node set B is to be obtained and two nodes in the node set B are simultaneously associated with the same node, in the bipartite graph, the two nodes are connected to one edge, so that a projected graph, that is, a projected node set, is obtained.

In step C4, performing community partition on the projected node set based on a preset community discovery algorithm to obtain at least one sub bipartite graph.

In practice, the following formula may be used

The community division is performed on the projected node set to obtain at least one sub bipartite graph, which may specifically refer to the above related contents, and is not described herein again. Where P represents a projected node set or a matrix corresponding thereto, or the like.

Sequentially executing the following processing for any second node in other nodes except the risk node:

in step S506, a third node different from the second node is sequentially obtained from other nodes, and the number of association relationships existing between the second node and each risk node and the third node are respectively determined.

In step S508, based on the determined number, a degree to which the second node is at risk is determined.

In the implementation of step S506 and step S508, fig. 7 shows a typical heterogeneous graph in an account-bank card (or bank account) scenario, where square nodes represent bank cards (or bank accounts), and circular nodes represent account nodes of a service platform. In an actual scenario, the interaction relationship between accounts (or account nodes) in a general service platform hierarchy is available, so before processing, if the interaction relationship existing between them can be found, the operation of connecting edges can be performed on the interaction relationship. The scheme can be used for processing the condition that the internal relation of the service platform system can be found. The scoring can be performed based on a TrianglerRank formula, and the TrianglerRank can score one node pair to obtain the relationship strength between two nodes. Fig. 7 shows a schematic diagram of the degree of association between a node s and g, t, i, j, k belonging to a node set.

In a data interaction network, a triangular structure is a very firm association relationship, and can better describe the 'intimacy' between nodes. The general definition of the Triangle Rank formula is as follows:

wherein,

a one-degree neighbor node representing the node s,

the two-degree relationship of the node s is represented, and for an intermediate node (i.e., a circular node), if the node and more other two-degree nodes form a triangular relationship, it is indicated that the node is a very active node, and the association relationship between two nodes to be calculated needs to be weighted down in the calculation process, but in a wind control scene, the situation is slightly different. In a found sub-bipartite graph, there may be labels for nodes and account nodes corresponding to a bank card (or a bank account), for example, the bank card (or the bank account) may be a bank card (or a bank account) that is qualified as having a fraud risk, and the account nodes may be account nodes corresponding to a fraudster/fraudster, and the above requirements may not be completely met by directly using the above formula, and based on this, the following assumptions may be set: the more triangles (i, j) in the nodes and the second-degree nodes (the bank cards (or bank accounts) which are already identified as having risks), the higher the possibility that the nodes t corresponding to the currently calculated bank cards (or bank accounts) have the risks is; the more triangles (i, j) in the nodes and the second-degree nodes (the bank cards (or bank accounts) which are not qualified as risky) are formed, the less the possibility that the nodes t corresponding to the bank cards (or bank accounts) which are calculated at present have risks is; if (i, j) in the nodes is already identified as a node with risk, the node t corresponding to the currently calculated bank card (or bank account) has a high possibility of having risk.

In order to make the above formula have more wind control characteristics, the above formula may be modified to satisfy the above assumption, and the modified disclosure may be as follows:

wherein,

a set of risk nodes is represented as a set of risk nodes,

representing a collection of nodes other than risk nodes.

The comparison results of the original Triangle Rank formula and the modified Triangle Rank formula for different sample pairs are shown in Table 1.

From the results of table 1, the following conclusions can be drawn about the modified Triangle Rank formula: for the sample pair sim < s, g >, the result becomes higher compared with the result corresponding to the original Triangle Rank formula, because b belongs to the nodes which are qualified as having risks in the common nodes (b, c) of s and g, the similarity is increased; for the sample pair sim < s, t >, the result corresponding to the original Triangle Rank formula becomes higher, for the reasons stated above; for the sample pair sim < s, i >, the corresponding result varies more, because of the common node (d, e) of s and i, e belongs to the node that is qualified as risky, and the triangle formed by < d, e, j > contains two risky nodes. Intuitively, it is consistent with business understanding, if all nodes in the sub-bipartite graph have no risk, the result obtained by the modified Triangle Rank formula will be degraded to the result corresponding to the original Triangle Rank formula.

In practical applications, the above-mentioned specific processing for identifying risks existing in other nodes in the sub-bipartite graph based on the risk nodes contained in the sub-bipartite graph and the association relationship information between the risk node and other nodes except the risk node in the sub-bipartite graph to obtain the degree of risk existing in each other node in the sub-bipartite graph can be implemented by the processing of the above-mentioned step S506 and step S508, and may also be implemented in a variety of different manners, and an alternative processing manner is provided below, and may specifically include the processing of the following step a2 and step a 4.

In step a2, a first node of the other nodes of the sub-bipartite graph having an association relationship with the risk node included in the sub-bipartite graph is obtained.

In implementation, the first node having an association relationship with the risk node may be obtained based on an association relationship between different nodes in the sub bipartite graph, where the first node may include a plurality of first nodes, or may include one first node, and if the first node includes a plurality of first nodes, the first node may include a first node having an association relationship with only one risk node, or may include a first node having an association relationship with each of a plurality of different risk nodes, or the like.

In step a4, based on the number of association relations with the risk nodes included in the sub-bipartite graph, the risk of the first node is identified, and the degree of risk of the first node in the sub-bipartite graph is obtained.

In implementation, if a certain risk-free node and a plurality of different risk nodes have an interactive relationship (e.g., a resource transfer relationship, etc.), the risk of the node is high, if a certain risk-free node and a risk node do not have an interactive relationship, the risk of the node is low, based on which, the number of association relationships existing between the first node and the risk nodes included in the sub-bipartite graph may be counted, whether the first node has a risk may be determined based on the obtained number, and the risk degree of the first node in the sub-bipartite graph may be determined based on the obtained number, wherein the greater the number corresponding to the first node is, the higher the risk degree of the first node is.

In practical applications, the specific process of identifying the risks existing in other nodes in the bipartite graph based on the risk nodes included in the bipartite graph and the association relationship information between the risk nodes and other nodes in the bipartite graph except the risk nodes to obtain the degree of risk existing in each other node in the bipartite graph may be various, and may be implemented in many different ways besides the above-mentioned ways, and an alternative processing way is provided below, which may specifically include the following processes of steps B2 and B4,

in step B2, based on the risk node included in the sub-bipartite graph and the association relationship information between the risk node and other nodes except the risk node in the sub-bipartite graph, the similarity between other nodes in the sub-bipartite graph and the similarity between other nodes and the risk node are determined through a preset similarity algorithm.

In step B4, the risk of the other nodes in the sub-bipartite graph is identified based on the determined similarity, resulting in a degree to which each of the other nodes in the sub-bipartite graph is at risk.

In the implementation of the above step B2 and step B4, in some scenarios, there is no association between nodes in the node set, so that the child bipartite graph after the community partition is performed cannot be refilled with the edge relationship, and thus, in order to measure the correlation between other nodes and risk nodes, it is necessary to calculate the affinity between the node i and the node j using a preset similarity algorithm, and further identify the risk of other nodes in the child bipartite graph, so as to obtain the risk degree of each other node in the child bipartite graph.

The preset similarity algorithm may include an Adamic/Adar algorithm or a SWING algorithm.

Based on the similarity algorithm, the processing procedure of the above steps may be: in the above specific processing, it is assumed that there are edges (i.e. association relationships) between nodes in one node set, but in some scenarios, there are no association relationships between nodes in the node set, so that the sub bipartite graph after community partition cannot be refilled with edge relationships, and thus, in order to measure the correlation between other nodes and risk nodes, an Adamic/Adar algorithm needs to be used

And (6) performing calculation. Wherein, in the Adamic/Adar algorithm formula:

to represent

The first-degree node of (a) is,

the degree of Z is shown, and obviously after the denominator is removed, the above formula shows the number of common neighbors. Formula of SWING algorithm: wherein i, j represent nodes in the same type of node set (e.g. node set B),

and

one degree nodes representing node i and node j respectively,

，

respectively represent the intersection of the i, j one-degree nodes,

and

respectively representing nodes

Node, node

The first-degree node of (a) is,

is a constant and can be used to control the affinity size of the generated nodes. Assuming that i and j are all nodes in the node set B, the affinity between i and j can be calculated according to the above formula as follows:

(1) if i and j have at least 2 common first degree nodes (in node set A), then s (i, j) is scored;

(2) the more the nodes i and j share one-degree nodes, the higher the intimacy between the nodes is;

(3) in the common nodes (node set a) of the nodes i and j, if the common nodes are simultaneously associated with a plurality of other nodes (node set B), the affinity becomes low.

In step S510, the other nodes in the sub-bipartite graph are sorted based on the degree to which each of the other nodes in the sub-bipartite graph is at risk, and the sorted other nodes are output.

In implementation, each node with risk is used as a query node, similarity between the query node and other nodes is calculated, and a final ranking result of each node can be generated by the following method: the above calculation method is to use the node with risk as the query node and calculate the similarity between the node and other card nodes. However, after the community partition is performed on the bipartite graph, there are multiple nodes with risks (assuming that there are m nodes) and multiple nodes without risks (assuming that there are n nodes) in the same sub bipartite graph, so that m × n times of calculation is required, each node performs m times of score calculation, and the two methods can be adopted to calculate { g, t, i, k } in the original Triangle Rank formula to obtain the result of table 2.

In table 2, the relationship strengths between the node s and the node j and the right node g, the node t, the node i, and the node k are generated, and then the average scores of the node g, the node t, the node i, and the node k can be obtained by averaging the relationship strengths. If the score is higher, the node is indicated to have a higher potential risk. If the TrianglerRank formula before the modification is used, the risk degree of the node t is the highest, but if the modified TrianglerRank formula is used, the risk degree of the node i is the highest. In a wind control application, the above conclusion is intuitively understood because node i has a triangular relationship with more risk nodes.

The embodiment of the present specification provides a risk identification method, which includes obtaining a bipartite graph constructed based on service information of a target service, then performing community partition on the bipartite graph based on a bipartite graph community discovery algorithm to obtain at least one sub bipartite graph, and finally identifying risks existing in other nodes in the bipartite graph based on risk nodes included in the sub bipartite graph and association relationship information between the risk nodes and other nodes except the risk nodes in the sub bipartite graph to obtain a degree of the risk existing in each other node in the sub bipartite graph, so that based on characteristics of the bipartite graph, a bipartite graph community partition method based on the bipartite graph community discovery algorithm and a risk identification scheme of the nodes are designed to measure an association relationship between the potential nodes and the risk nodes in each sub bipartite graph to complete risk detection and identification of the nodes, the purpose of risk evaluation of each node in the bipartite graph is achieved.

EXAMPLE III

As shown in fig. 8A and 8B, an execution main body of the method may be a blockchain system, where the blockchain system may be composed of a terminal device and/or a server, where the terminal device may be a mobile terminal device such as a mobile phone and a tablet computer, or may be a device such as a personal computer, the server may be an independent server, or may be a server cluster composed of a plurality of servers, and the server may be a backend server of a financial service or an online shopping service, or may be a backend server of an application. The method can be applied to relevant scenes provided with model training and the like, and specifically can comprise the following steps:

in step S802, risk identification rule information based on a bipartite graph for a target service is obtained, a corresponding first intelligent contract is generated by using the risk identification rule information based on the bipartite graph, and the first intelligent contract is deployed into a blockchain system.

Wherein the first intelligent contract may be a computer agreement intended to propagate, verify or execute contracts in an informational manner, the intelligent contract allowing trusted interaction without third parties, the process of such interaction being traceable and irreversible, the first intelligent contract including agreements on which contract participants may execute rights and obligations agreed.

In implementation, in order to make the traceability of the bipartite graph-based risk identification process for a target service better, a designated blockchain system may be created or added, so that the bipartite graph-based risk identification for the target service may be performed based on the blockchain system, specifically, a corresponding application may be installed in a blockchain node, an input box and/or a selection box and the like of the bipartite graph-based risk identification rule information for the target service may be set in the application, and corresponding information may be set in the input box and/or the selection box. The blockchain system may then receive bipartite graph-based risk identification rule information for the target business. The blockchain system can generate a corresponding first intelligent contract through the risk identification rule information based on the bipartite graph, and can deploy the first intelligent contract into the blockchain system, so that the risk identification rule information based on the bipartite graph and the corresponding first intelligent contract for the target business are stored in the blockchain system, other users cannot tamper with the risk identification rule information based on the bipartite graph and the corresponding first intelligent contract for the target business, and the blockchain system executes risk identification based on the bipartite graph through the first intelligent contract.

In step S804, a first intelligent contract is called to obtain a bipartite graph constructed based on the service information of the target service.

In implementation, the first intelligent contract may be provided with relevant rule information for obtaining a bipartite graph constructed based on the service information of the target service, so that the corresponding processing may be implemented based on the rule information in the first intelligent contract, which may be referred to specifically for the above relevant content, and is not described herein again.

In step S806, based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph, performing community division on the bipartite graph through a bipartite graph community discovery algorithm to obtain at least one sub-bipartite graph.

In implementation, relevant rule information for performing community division on the bipartite graph through a bipartite graph community discovery algorithm may be set in the first intelligent contract, so that the corresponding processing may be implemented based on the rule information in the first intelligent contract, which may be referred to specifically for the above relevant content, and is not described herein again.

In step S808, based on the first intelligent contract, the risk nodes included in the sub-bipartite graph, and the association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, the risks existing in the other nodes in the sub-bipartite graph are identified, and the degree of risk existing in each other node in the sub-bipartite graph is obtained.

In implementation, the first intelligent contract may be provided with relevant rule information for identifying risks existing in other nodes in the sub-bipartite graph through risk nodes included in the sub-bipartite graph and association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, so that the corresponding processing may be implemented based on the rule information in the first intelligent contract, which may be specifically referred to the above relevant contents, and is not described herein again.

In practical application, the service information of the target service may be stored in the blockchain system, or may be stored in other storage devices, and for the case that the service information of the target service is stored in other storage devices, considering that the service information of the target service is different for different users or different times, since the blockchain system has a characteristic of being not falsifiable, if the service information of the target service is stored in the blockchain system, it is necessary to perform frequent operations such as uploading, deleting, and identity authentication of an uploader on the service information of the target service subsequently, so as to increase the processing pressure of the blockchain system, and to improve the processing efficiency and reduce the processing pressure of the blockchain system, the service information of the target service may be stored in a designated storage address of the storage device in advance, and the storage address (i.e. index information) may be uploaded to the blockchain system, the memory address can be fixed and stored in the blockchain system, so that the tamper resistance of the data in the blockchain system is ensured.

The processing of step S808 may be various, and three optional processing manners are provided below, which may specifically include one to three manners.

The first method is as follows: sequentially executing the following processing for any second node in other nodes: based on the first intelligent contract, sequentially acquiring third nodes different from the second node from other nodes, and respectively determining the number of association relations between the second node and each risk node and between the third nodes; based on the first intelligent contract and the determined quantity, a degree to which the second node is at risk is determined.

The second method comprises the following steps: acquiring a first node in other nodes of the sub-bipartite graph, which has an association relation with risk nodes contained in the sub-bipartite graph, based on a first intelligent contract; based on the first intelligent contract and the number of incidence relations with risk nodes contained in the sub-bipartite graph, identifying risks of the first nodes to obtain the degree of the risks of the first nodes in the sub-bipartite graph.

The third method comprises the following steps: determining the similarity between other nodes in the sub-bipartite graph and the similarity between other nodes and the risk node through a preset similarity algorithm based on the risk node contained in the first intelligent contract and the sub-bipartite graph and the incidence relation information between the risk node and other nodes except the risk node in the sub-bipartite graph; and identifying the risks of other nodes in the sub-bipartite graph based on the first intelligent contract and the determined similarity to obtain the risk degree of each other node in the sub-bipartite graph.

In this way, the corresponding processing can be implemented based on the rule information in the first intelligent contract, which may be referred to as the above-mentioned related content specifically, and is not described herein again.

Wherein, the similarity algorithm is an Adamic/Adar algorithm or a SWING algorithm. The bipartite graph community discovery algorithm is a Bilouvain algorithm.

In addition, after determining the degree of risk of the nodes, the nodes may also be sorted and output, which may be specifically referred to as the following: and ordering other nodes in the sub-bipartite graph based on a second intelligent contract pre-deployed in the blockchain system and the risk degree of each other node in the sub-bipartite graph, and outputting the ordered other nodes.

In the second intelligent contract, rule information setting for ordering other nodes in the sub-bipartite graph may be performed based on the degree of risk of each other node in the sub-bipartite graph, so that the corresponding processing may be implemented based on the rule information in the second intelligent contract, which may be specifically referred to the above-mentioned related contents and is not described herein again.

The processing of step S806 may be various, and an optional processing manner is provided below, and may specifically include the following processing of step D2 and step D4.

In step D2, based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph, the first node set included in the bipartite graph is projected to obtain a projected node set.

In implementation, relevant rule information for projecting the first node set included in the bipartite graph may be set in the first intelligent contract, so that the corresponding processing may be implemented based on the rule information in the first intelligent contract, which may be specifically referred to above, and details are not described here.

In step D4, performing community partition on the projected node set based on the first intelligent contract and a preset community discovery algorithm to obtain at least one sub-bipartite graph.

In implementation, relevant rule information for performing community division on the projected node set through a preset community discovery algorithm may be set in the first intelligent contract, so that the corresponding processing may be implemented based on the rule information in the first intelligent contract, which may be specifically referred to the above relevant content, and is not described herein again.

For the specific processing in the above steps S804 to S808, reference may be made to the relevant contents in the above embodiments one to two, that is, various processing related to the above embodiments one to two may be implemented through the corresponding first smart contracts.

The embodiment of the specification provides a risk identification method, which is applied to a block chain system, acquires risk identification rule information based on a bipartite graph aiming at a target service, generates a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, deploys the first intelligent contract into the block chain system, calls the first intelligent contract, acquires the bipartite graph constructed based on the service information of the target service, performs community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of nodes in the bipartite graph to obtain at least one sub-bipartite graph, and identifies risks existing in other nodes in the bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes in the sub-bipartite graph and other nodes except the risk nodes, and obtaining the risk degree of each other node in the sub bipartite graph, thus designing a bipartite graph community division mode based on a bipartite graph community discovery algorithm and a risk identification scheme of the node based on characteristics of the bipartite graph to measure the incidence relation between the potential node and the risk node in each sub bipartite graph, thereby completing the risk detection and identification of the node and realizing the purpose of performing risk evaluation on each node in the bipartite graph.

Example four

Based on the same idea, the risk identification method provided in the embodiment of the present specification further provides a risk identification device, as shown in fig. 9.

The risk identification device includes: a bipartite graph acquisition module 901, a community division module 902, and a risk identification module 903, wherein:

a bipartite graph acquisition module 901 for acquiring a bipartite graph constructed based on service information of a target service;

the community division module 902 is used for carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph;

the risk identification module 903 identifies risks existing in other nodes in the sub-bipartite graph based on risk nodes included in the sub-bipartite graph and association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, and obtains a degree of risk existing in each other node in the sub-bipartite graph.

In the embodiment of the present specification, the bipartite graph community discovery algorithm is a bilovain algorithm.

In this embodiment of the present specification, the risk identification module 903 includes:

the node acquisition unit is used for acquiring a first node which has an association relation with risk nodes contained in the sub bipartite graph from other nodes of the sub bipartite graph;

and the first risk identification unit is used for identifying the risk of the first node based on the number of incidence relations with the risk nodes contained in the sub-bipartite graph to obtain the risk degree of the first node in the sub-bipartite graph.

sequentially performing the following processing for any second node of the other nodes:

the quantity determining unit is used for sequentially acquiring third nodes different from the second nodes from the other nodes and respectively determining the quantity of association relations between the second nodes and the risk nodes and between the third nodes and the risk nodes;

and a second risk identification unit which determines the degree of risk of the second node based on the determined number.

In an embodiment of this specification, the apparatus further includes:

and the sorting module is used for sorting other nodes in the sub bipartite graph based on the risk degree of each other node in the sub bipartite graph and outputting the sorted other nodes.

In this embodiment of the present specification, the community dividing module 902 includes:

the device comprises a projection unit, a storage unit and a processing unit, wherein the projection unit is used for projecting a first node set included in a bipartite graph based on the aggregation condition of nodes in the bipartite graph to obtain a projected node set;

and the community division unit is used for carrying out community division on the projected node set based on a preset community discovery algorithm to obtain at least one sub bipartite graph.

the similarity determining unit is used for determining the similarity between other nodes in the sub bipartite graph and the similarity between the other nodes and the risk node based on the risk node contained in the sub bipartite graph and the incidence relation information between the risk node and other nodes except the risk node in the sub bipartite graph through a preset similarity algorithm;

and the third risk identification unit is used for identifying the risks of other nodes in the sub bipartite graph based on the determined similarity to obtain the risk degree of each other node in the sub bipartite graph.

In the embodiment of the specification, the similarity algorithm is an Adamic/Adar algorithm or a SWING algorithm.

The embodiment of the present specification provides a risk identification apparatus, which obtains a bipartite graph constructed based on service information of a target service, and then, based on an aggregation condition of nodes in the bipartite graph, performs community partition on the bipartite graph by a bipartite graph community discovery algorithm to obtain at least one sub bipartite graph, and finally, based on risk nodes included in the sub bipartite graph and association relationship information between the risk nodes and other nodes except the risk nodes in the sub bipartite graph, identifies risks existing in other nodes in the bipartite graph to obtain a degree of risk existing in each other node in the sub bipartite graph, so that based on characteristics of the bipartite graph, a bipartite graph community partition method based on the bipartite graph community discovery algorithm and a risk identification scheme of the nodes are designed to measure an association relationship between potential nodes and risk nodes in each sub bipartite graph, therefore, risk detection and identification of the nodes are completed, and the purpose of risk evaluation of each node in the bipartite graph is achieved.

EXAMPLE five

Based on the same idea, the embodiments of the present specification further provide a risk identification device, which is a device in a blockchain system, as shown in fig. 10.

The risk identification device includes: a contract deployment module 1001, a bipartite graph acquisition module 1002, a community partitioning module 1003, and a risk identification module 1004, wherein:

the contract deployment module 1001 is used for acquiring risk identification rule information based on a bipartite graph for a target service, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into the block chain system;

a bipartite graph acquisition module 1002, which calls the first intelligent contract to acquire a bipartite graph constructed based on the service information of the target service;

the community division module 1003 is used for carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph;

the risk identification module 1004 identifies risks of other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes included in the sub-bipartite graph, and association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, so as to obtain a degree of risk of each other node in the sub-bipartite graph.

In an embodiment of this specification, the apparatus further includes:

and the sequencing module is used for sequencing other nodes in the sub-bipartite graph based on a second intelligent contract pre-deployed in the blockchain system and the risk degree of each other node in the sub-bipartite graph, and outputting the other nodes after sequencing.

The embodiment of the specification provides a risk identification device, which acquires risk identification rule information based on a bipartite graph aiming at a target service, generates a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, deploys the first intelligent contract into a block chain system, calls the first intelligent contract, acquires the bipartite graph constructed based on the service information of the target service, performs community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of nodes in the bipartite graph to obtain at least one sub-bipartite graph, identifies risks existing in other nodes in the bipartite graph based on the risk nodes contained in the first intelligent contract and the sub-bipartite graph and incidence relation information between the risk nodes in the sub-bipartite graph and other nodes except the risk nodes, and acquires the degree of risk existing in each other node in the sub-bipartite graph, therefore, based on the characteristics of the bipartite graph, a bipartite graph community division mode based on a bipartite graph community discovery algorithm and a node risk identification scheme are designed to measure the incidence relation between potential nodes and risk nodes in each sub bipartite graph, so that the risk detection and identification of the nodes are completed, and the purpose of performing risk evaluation on each node in the bipartite graph is achieved.

EXAMPLE six

Based on the same idea, the risk identification device provided in the embodiment of the present specification further provides a risk identification device, as shown in fig. 11.

The risk identification device may provide a terminal device, a server, or a device in the blockchain system, etc. for the above embodiments.

Risk identification devices may vary significantly depending on configuration or performance and may include one or more processors 1101 and memory 1102, where the memory 1102 may have one or more stored applications or data stored therein. Wherein memory 1102 may be transient or persistent. The application stored in memory 1102 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for a risk identification device. Still further, processor 1101 may be configured to communicate with memory 1102 to execute a series of computer-executable instructions in memory 1102 on a risk identification device. The risk identification apparatus may also include one or more power supplies 1103, one or more wired or wireless network interfaces 1104, one or more input-output interfaces 1105, one or more keyboards 1106.

In particular, in this embodiment, the risk identification device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the risk identification device, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:

acquiring a bipartite graph constructed based on service information of a target service;

based on the aggregation condition of nodes in the bipartite graph, carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm to obtain at least one sub bipartite graph;

identifying risks of other nodes in the sub-bipartite graph based on risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, and obtaining the degree of risk of each other node in the sub-bipartite graph.

In this embodiment of the present specification, the identifying risks of other nodes in the sub-bipartite graph based on risk nodes included in the sub-bipartite graph and association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain a degree of risk of each other node in the sub-bipartite graph includes:

acquiring a first node in other nodes of the sub bipartite graph, wherein the first node has an association relation with risk nodes contained in the sub bipartite graph;

and identifying the risk of the first node based on the number of incidence relations with the risk nodes contained in the sub-bipartite graph to obtain the degree of the risk of the first node in the sub-bipartite graph.

sequentially acquiring third nodes different from the second node from the other nodes, and respectively determining the number of association relations between the second node and each risk node and between the third nodes;

determining a degree to which the second node is at risk based on the determined number.

In the embodiment of this specification, the method further includes:

and sorting the other nodes in the sub-bipartite graph based on the risk degree of each other node in the sub-bipartite graph, and outputting the sorted other nodes.

In an embodiment of this specification, the performing community division on the bipartite graph based on a bipartite graph community discovery algorithm to obtain at least one sub-bipartite graph includes:

based on the aggregation condition of nodes in a bipartite graph, projecting a first node set included in the bipartite graph to obtain a projected node set;

and carrying out community division on the projected node set based on a preset community discovery algorithm to obtain at least one sub bipartite graph.

determining similarity between other nodes in the sub-bipartite graph and similarity between the other nodes and the risk node through a preset similarity algorithm based on the risk node contained in the sub-bipartite graph and incidence relation information between the risk node and other nodes except the risk node in the sub-bipartite graph;

and identifying the risks of other nodes in the sub-bipartite graph based on the determined similarity to obtain the degree of risk of each other node in the sub-bipartite graph.

In addition, in particular in this embodiment, the risk identification device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the risk identification device, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:

acquiring risk identification rule information based on a bipartite graph for a target service, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into the blockchain system;

calling the first intelligent contract to obtain a bipartite graph constructed based on the service information of the target service;

based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph, carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm to obtain at least one sub bipartite graph;

identifying risks existing in other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk existing in each other node in the sub-bipartite graph.

In the embodiment of this specification, the method further includes:

and sorting other nodes in the sub-bipartite graph based on a second intelligent contract pre-deployed in the blockchain system and the degree of risk of each other node in the sub-bipartite graph, and outputting the sorted other nodes.

The embodiment of the present specification provides a risk identification device, which obtains a bipartite graph constructed based on service information of a target service, and then, may perform community division on the bipartite graph based on a bipartite graph community discovery algorithm to obtain at least one sub bipartite graph, and finally, may identify risks existing in other nodes in the bipartite graph based on risk nodes included in the sub bipartite graph and association relationship information between the risk nodes and other nodes except the risk nodes in the sub bipartite graph to obtain a degree of the risk existing in each other node in the sub bipartite graph, so that, based on characteristics of the bipartite graph, a bipartite graph community division manner based on the bipartite graph community discovery algorithm and a risk identification scheme of the nodes are designed to measure an association relationship between the potential nodes and the risk nodes in each sub bipartite graph, thereby completing risk detection and identification of the nodes, the purpose of risk evaluation of each node in the bipartite graph is achieved.

EXAMPLE seven

Further, based on the methods shown in fig. 1 to fig. 8B, one or more embodiments of the present specification further provide a storage medium for storing computer-executable instruction information, in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, and the like, and when the storage medium stores the computer-executable instruction information, the storage medium implements the following processes:

In the embodiment of this specification, the method further includes:

In addition, in another specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, or the like, and the storage medium stores computer executable instruction information that, when executed by the processor, can implement the following process:

In the embodiment of this specification, the method further includes:

The embodiment of the present specification provides a storage medium, which acquires a bipartite graph constructed based on service information of a target service, and then performs community partition on the bipartite graph based on a bipartite graph community discovery algorithm to obtain at least one sub bipartite graph, and finally identifies risks existing in other nodes in the bipartite graph based on risk nodes included in the sub bipartite graph and association relationship information between the risk nodes and other nodes except the risk nodes in the sub bipartite graph to obtain a degree of the risk existing in each other node in the sub bipartite graph, so that based on characteristics of the bipartite graph, a bipartite graph community partition method based on the bipartite graph community discovery algorithm and a risk identification scheme of the nodes are designed to measure an association relationship between the potential nodes and the risk nodes in each sub bipartite graph, thereby completing risk detection and identification of the nodes, the purpose of risk evaluation of each node in the bipartite graph is achieved.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Embodiments of the present description are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable fraud case serial-parallel apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable fraud case serial-parallel apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable fraud case to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable fraud case serial-parallel apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A method of risk identification, the method comprising:

based on the aggregation condition of the nodes in the bipartite graph, carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm to obtain at least one sub bipartite graph;

identifying risks existing in other nodes in the sub-bipartite graph based on risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, and obtaining the degree of risk existing in each other node in the sub-bipartite graph.

2. The method of claim 1, the bipartite graph community discovery algorithm being a Bilouvain algorithm.

3. The method according to claim 1, wherein the identifying the risks of other nodes in the sub-bipartite graph based on the risk nodes included in the sub-bipartite graph and the association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk of each of the other nodes in the sub-bipartite graph comprises:

4. The method according to claim 1, wherein the identifying the risks of other nodes in the sub-bipartite graph based on the risk nodes included in the sub-bipartite graph and the association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk of each of the other nodes in the sub-bipartite graph comprises:

5. The method of any of claims 1-4, further comprising:

6. The method according to claim 1, wherein the performing community partition on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation of nodes in the bipartite graph to obtain at least one sub-bipartite graph comprises:

based on the aggregation condition of the nodes in the bipartite graph, projecting a first node set included in the bipartite graph to obtain a projected node set;

7. The method according to claim 1, wherein the identifying the risks of other nodes in the sub-bipartite graph based on the risk nodes included in the sub-bipartite graph and the association relationship information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk of each of the other nodes in the sub-bipartite graph comprises:

8. The method of claim 7, wherein the similarity algorithm is an Adamic/Adar algorithm or a SWING algorithm.

9. A risk identification method is applied to a block chain system, and comprises the following steps:

identifying risks existing in other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph, and obtaining the degree of risk existing in each other node in the sub-bipartite graph.

10. The method of claim 9, further comprising:

11. A risk identification device, the device comprising:

the bipartite graph acquisition module is used for acquiring a bipartite graph constructed based on the service information of the target service;

the community division module is used for carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph;

and the risk identification module is used for identifying risks existing in other nodes in the sub-bipartite graph based on risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the risk degree of each other node in the sub-bipartite graph.

12. A risk identification device applied to a blockchain system comprises:

the contract deployment module is used for acquiring risk identification rule information based on a bipartite graph aiming at target services, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into the block chain system;

the bipartite graph acquisition module is used for calling the first intelligent contract to acquire a bipartite graph constructed on the basis of the service information of the target service;

the community division module is used for carrying out community division on the bipartite graph through a bipartite graph community discovery algorithm based on the first intelligent contract and the aggregation condition of the nodes in the bipartite graph to obtain at least one sub bipartite graph;

and the risk identification module is used for identifying risks of other nodes in the sub-bipartite graph based on the first intelligent contract, the risk nodes contained in the sub-bipartite graph and incidence relation information between the risk nodes and other nodes except the risk nodes in the sub-bipartite graph to obtain the degree of risk of each other node in the sub-bipartite graph.

13. A risk identification device, the risk identification device comprising:

a processor; and

a memory arranged to store computer executable instructions that, when executed, cause the processor to:

14. A risk identification device, the device being a device in a blockchain system, the risk identification device comprising:

a processor; and

15. A storage medium for storing computer-executable instructions, which when executed by a processor implement the following:

16. A storage medium for storing computer-executable instructions, which when executed by a processor implement the following:

acquiring risk identification rule information based on a bipartite graph for a target service, generating a corresponding first intelligent contract by adopting the risk identification rule information based on the bipartite graph, and deploying the first intelligent contract into a block chain system;