CN110930246A - Credit anti-fraud identification method and device, computer equipment and computer-readable storage medium - Google Patents
Credit anti-fraud identification method and device, computer equipment and computer-readable storage medium Download PDFInfo
- Publication number
- CN110930246A CN110930246A CN201911227933.3A CN201911227933A CN110930246A CN 110930246 A CN110930246 A CN 110930246A CN 201911227933 A CN201911227933 A CN 201911227933A CN 110930246 A CN110930246 A CN 110930246A
- Authority
- CN
- China
- Prior art keywords
- user
- nodes
- node
- credit
- fraud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 239000013598 vector Substances 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 24
- 230000002265 prevention Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000010276 construction Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
Abstract
The invention discloses a credit anti-fraud identification method, a credit anti-fraud identification device, computer equipment and a storage medium. The method comprises the following steps: constructing a credit knowledge map according to user loan application data of a financial institution; identifying suspicious group fraud groups according to the credit knowledge graph; and extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph, so that the group fraud risk and the individual fraud risk in the existing financial loan application can be accurately identified, and the loss of a financial institution is greatly reduced.
Description
Technical Field
The invention relates to the technical field of knowledge maps, in particular to a credit anti-fraud identification method, a credit anti-fraud identification device, computer equipment and a computer-readable storage medium.
Background
The billions of RMB lost by credit fraud each year by banks and financial institutions, traditional anti-fraud technology plays a very important role in identifying and reducing losses. However, an increasing number of fraudsters have devised a variety of methods of fraud to avoid being identified by conventional methods. The main methods are group fraud and construction of false identities by various methods. The traditional anti-fraud technology carries out an anti-fraud mode through the characteristics of a single data point, and the identification rate of the traditional anti-fraud technology to the current novel fraud mode is low.
Disclosure of Invention
The embodiment of the invention provides a credit anti-fraud identification method, a credit anti-fraud identification device, computer equipment and a computer readable storage medium, and aims to solve the problem that the fraud identification rate of financial application in the prior art is low.
In a first aspect, an embodiment of the present invention provides a credit anti-fraud identification method, which includes:
constructing a credit knowledge map according to user loan application data of a financial institution;
identifying suspicious group fraud groups according to the credit knowledge graph;
and extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph.
The further technical scheme is that the method for constructing the credit knowledge map according to the user loan application data of the financial institution comprises the following steps:
extracting entities from user loan application data of a financial institution, wherein the entities comprise a user entity, an address entity, a mobile phone number entity, an identification card number entity, a bank card number entity and a financial institution entity;
giving corresponding attributes to the user entity, wherein the attributes comprise age, gender, ID card attribution, mutual fund inquiry times, whether the group partner is suspected to be cheating, financial application times in the last month, financial application times in the last three months and financial application times in the last six months;
and establishing an association relationship between nodes according to the relationship between the user loan application data to obtain the credit knowledge map, wherein the relationship between the user loan application data comprises the relationship between a user and an address, the relationship between the user and a mobile phone number, the relationship between the user and an identification number, the relationship between the user and a bank card number and the relationship between the user and a financial institution, and each node corresponds to an entity.
The further technical scheme is that the identification of the suspicious group-partner cheating group according to the credit knowledge graph comprises the following steps:
acquiring a characteristic path in the credit knowledge graph, wherein a starting node of the characteristic path is a user node, and an end node of the characteristic path is a financial institution node;
acquiring characteristic paths passing through the same application information nodes as target characteristic paths, and establishing subgraphs according to the nodes in the target characteristic paths, wherein the application information nodes comprise mobile phone nodes, identity card nodes and address nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
The further technical scheme is that the identification of the suspicious group-partner cheating group according to the credit knowledge graph comprises the following steps:
acquiring node vectors of all nodes of the credit knowledge graph;
acquiring nodes with the distance of the node vectors smaller than a preset threshold value as target nodes, and establishing subgraphs according to the target nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
The further technical scheme is that the obtaining of the node vector of each node of the credit knowledge graph comprises:
and calculating the node vectors of the credit knowledge graph through a preset TransD model.
The further technical scheme is that the identifying suspicious fraud nodes according to the user knowledge graph comprises the following steps:
allocating labels to the cheating individual nodes in the user knowledge graph according to a preset cheating individual name list, and randomly allocating different labels to user nodes except the cheating individual nodes in the user knowledge graph;
acquiring adjacent user nodes of the user knowledge graph, and determining labels of the user nodes according to the labels of the adjacent user nodes of the user nodes;
judging whether the label of the user node of the user knowledge graph changes or not;
if the label of the user node of the user knowledge graph changes, returning to the adjacent user node of the user node which acquires the user knowledge graph, and determining the label of the user node according to the label of the adjacent user node of the user node;
and if the label of the user node of the user knowledge graph is not changed, marking the user node with the same label as the fraud individual node as a suspicious fraud node.
A further technical solution is that the determining the label of the user node according to the label of the user node adjacent to the user node includes:
and determining the label of the user node according to the attribution factor between the user node and the adjacent user node, wherein the attribution factor is determined according to the number of the relations between the user node and the adjacent user node and the similarity of the attributes between the user node and the adjacent user node.
In a second aspect, embodiments of the present invention also provide a credit anti-fraud identification apparatus, which includes means for performing the above method.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the above method when executing the computer program.
In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores a computer program, and the computer program can implement the above method when being executed by a processor.
By applying the technical scheme of the embodiment of the invention, a credit knowledge map is constructed according to the user loan application data of the financial institution; identifying suspicious group fraud groups according to the credit knowledge graph; and extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph, so that the group fraud risk and the individual fraud risk in the existing financial loan application can be accurately identified, and the loss of a financial institution is greatly reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a credit fraud prevention identification method according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
Referring to fig. 1, fig. 1 is a flow chart illustrating a credit fraud prevention identification method according to an embodiment of the present invention. As shown, the method includes the following steps S1-S4.
And S1, constructing a credit knowledge map according to the user loan application data of the financial institution.
In a specific implementation, a credit knowledge map is constructed according to user loan application data of a financial institution. The relationship of which specific application data is used by the user to apply for a loan to the financial institution can be represented by the credit knowledge map.
A knowledge graph is a structured semantic knowledge base used to quickly describe concepts and their interrelationships in the physical world. The knowledge map is converted into simple and clear triples of entities, relations and entities by effectively processing, processing and integrating the data of the complicated documents (the data applied for the user loan in the invention), and finally a great deal of knowledge is aggregated, thereby realizing the quick response and reasoning of the knowledge.
The knowledge graph has two construction modes of top-down and bottom-up. The top-down construction is to extract ontology and mode information from high-quality data by means of structured data sources such as encyclopedic websites and the like, and add the ontology and mode information into a knowledge base. And (4) constructing from bottom to top, namely extracting resource modes from the publicly collected data, selecting a new mode with higher confidence coefficient, and adding the new mode into a knowledge base after manual examination.
In one embodiment, the above step S1 specifically includes the following steps S11-S13.
And S11, extracting entities of the user loan application data of the financial institution, wherein the entities comprise a user entity, an address entity, a mobile phone number entity, an identification card number entity, a bank card number entity and a financial institution entity.
In the concrete implementation, the entity extraction is carried out on the user loan application data of the financial institution, wherein the entities needing to be extracted comprise a user entity, an address entity, a mobile phone number entity, an identification card number entity, a bank card number entity and a financial institution entity.
And S12, giving corresponding attributes to the user entity, wherein the attributes comprise age, gender, ID attribution, mutual fund inquiry times, whether the user entity is suspected to be group fraud, the financial application times in the last month, the financial application times in the last three months and the financial application times in the last six months.
In the specific implementation, after the user entity is extracted, corresponding attributes are further given to the user entity, wherein the corresponding attributes comprise age, gender, ID attribution, mutual fund inquiry times, suspected group fraud, financial application times in a last month, financial application times in a last three months and financial application times in a last six months. It is to be noted that the attribute of the user entity may be set by a person skilled in the art according to experience, and the embodiment of the present invention is not limited to this.
And S13, establishing an association relationship between nodes according to the relationship between the user loan application data to obtain the credit knowledge map, wherein the relationship between the user loan application data comprises the relationship between a user and an address, the relationship between the user and a mobile phone number, the relationship between the user and an identification number, the relationship between the user and a bank card number and the relationship between the user and a financial institution, and each node corresponds to an entity.
In specific implementation, according to the relationship between user loan application data, the association relationship between nodes is established to obtain the credit knowledge graph. The relationship between the user loan application data comprises the relationship between the user and the address, the relationship between the user and the mobile phone number, the relationship between the user and the identification number, the relationship between the user and the bank card number and the relationship between the user and the financial institution. And, each node corresponds to an entity. An edge exists between any two nodes as long as there is an association between the two nodes.
And S2, identifying suspicious group fraud groups according to the credit knowledge graph.
In a specific implementation, after the credit knowledge graph is established, a path analysis and knowledge representation algorithm method is used for finding potential group fraud risks, namely the credit knowledge graph is identified to identify suspicious group fraud groups.
In one embodiment, the above step S2 includes the following steps S21-S24.
And S21, acquiring a characteristic path in the credit knowledge graph, wherein the starting node of the characteristic path is a user node, and the destination node of the characteristic path is a financial institution node.
In specific implementation, a feature path in the credit knowledge graph is obtained, wherein a starting node of the feature path is a user node, and an end node of the feature path is a financial institution node.
S22, obtaining the characteristic path passing through the same application information node as the target characteristic path, and establishing a sub-graph according to the node in the target characteristic path, wherein the application information node comprises a mobile phone node, an identity card node and an address node.
In specific implementation, in all the characteristic paths, the characteristic paths passing through the same application information node are obtained as target characteristic paths, and subgraphs are established according to the nodes in the target characteristic paths. The subgraph includes all nodes of the target feature path. The information application node comprises a mobile phone node, an identity card node and an address node.
And S23, judging whether the number of the nodes in the subgraph is larger than a preset number threshold.
In specific implementation, whether the number of the nodes in the created subgraph is larger than a preset number threshold is judged.
The number threshold may be set empirically by one skilled in the art, and is not particularly limited in this embodiment, for example, in one embodiment, the number threshold is set to 3.
S24, if the number of the nodes in the sub-graph is larger than a preset number threshold, it is determined that the sub-graph contains a suspicious group-partner cheating group.
In specific implementation, if the number of the nodes in the sub-graph is greater than a preset number threshold, it is determined that the sub-graph contains a suspected group fraud group. The suspicious group fraud community is a community formed by users related to all nodes in the subgraph.
In one embodiment, the above step S2 includes the following steps S201-S204.
S201, obtaining node vectors of all nodes of the credit knowledge graph.
In a specific implementation, a node vector of each node of the credit knowledge graph is obtained.
In one embodiment, the node vectors of the credit knowledge graph are calculated by a preset TransD model. The node vector obtained in step S201 includes the structure information of the knowledge-graph. Two nodes with similar association relationship have a closer distance between the node vectors.
S202, obtaining nodes with the distance of the node vectors smaller than a preset threshold value as target nodes, and establishing subgraphs according to the target nodes.
In specific implementation, a node with a distance of a node vector smaller than a preset threshold is obtained as a target node, and a subgraph is established according to the target node. The subgraph includes all target nodes.
S203, judging whether the number of the nodes in the subgraph is larger than a preset number threshold.
In specific implementation, whether the number of the nodes in the created subgraph is larger than a preset number threshold is judged.
The number threshold may be set empirically by one skilled in the art, and is not particularly limited in this embodiment, for example, in one embodiment, the number threshold is set to 3.
S204, if the number of the nodes in the sub-graph is larger than a preset number threshold, the sub-graph is judged to contain a suspicious group partner fraud group.
In specific implementation, if the number of the nodes in the sub-graph is greater than a preset number threshold, it is determined that the sub-graph contains a suspected group fraud group. The suspicious group fraud community is a community formed by users related to all nodes in the subgraph.
S3, extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph.
In specific implementation, all user nodes in the credit knowledge graph are extracted to obtain a user knowledge graph, and suspicious fraud nodes are identified according to the user knowledge graph. Specifically, through a label propagation algorithm (semi-supervised learning) algorithm, nodes (individuals) with fraud risks in a user knowledge graph are discovered.
In one embodiment, the above step S3 specifically includes the following steps S31-S35.
And S31, allocating labels to the cheating individual nodes in the user knowledge graph according to a preset cheating individual name list, and randomly allocating different labels to user nodes except the cheating individual nodes in the user knowledge graph.
In specific implementation, labels are distributed to fraudulent individual nodes in the user knowledge graph according to a preset fraudulent individual name list, and different labels are randomly distributed to user nodes except the fraudulent individual nodes in the user knowledge graph. The list of fraudulent individuals is a list of known fraudulent individuals.
S32, obtaining the adjacent user node of the user knowledge graph, and determining the label of the user node according to the label of the adjacent user node of the user node.
In specific implementation, the adjacent user node of the user knowledge graph is obtained, and the label of the user node is determined according to the label of the adjacent user node of the user node.
In an embodiment, the step S32 specifically includes: and determining the label of the user node according to the attribution factor between the user node and the adjacent user node, wherein the attribution factor is determined according to the number of the relations between the user node and the adjacent user node and the similarity of the attributes between the user node and the adjacent user node.
The specific way to calculate the attribution factor is as follows:
wherein p is(root,i)Is the i-th attribute, p, of the user node(target,i)Is the ith attribute of the neighboring node. n is the total number of attributes that the node has.
Is the total number of relationships between the user node and the neighbor nodes, rmaxThe maximum value of the relationship sum of the user node and the neighbor nodes. The attribution factor calculation formula is as follows:
wherein f (x) there are different calculation methods according to the type of the node attribute value, for example, the age will be the difference between two nodes and normalized, if it is suspected to be a group fraud, it will be determined whether the two node attribute values are equal, if they are equal, it is 1, otherwise it is 0, etc.
In the embodiment of the invention, the user data in the knowledge graph data is labeled by adopting an improved LPA (Label Propagation Algorithm) label Propagation algorithm.
The conventional LPA label propagation algorithm includes the following steps:
the first step is as follows: firstly, distributing a corresponding label to each node, namely, the node 1 corresponds to the label 1, and the node i corresponds to the label i (if any, the label i is directly used, and if not, the label i is generated);
the second step is that: traversing N nodes (for i is 1: N), finding out neighbors of corresponding nodes, obtaining neighbor labels of the nodes, finding out labels with the maximum occurrence frequency, and randomly selecting one label to replace the label with the node label if more than one label with the maximum occurrence frequency is found;
the third step: if the node label is not changed any more, the iteration is stopped, otherwise the second step is repeated.
The improvement point of the invention is that in the second step, the traditional LPA label propagation algorithm updates the label of the LPA according to the maximum labels in the labels of the neighbor nodes. In the invention, the label of the node is determined by adding the calculation of the attribution factor. And calculating the attribution factor according to the quantity of the relationships among the user nodes and the similarity of the attributes among the user nodes.
And S33, judging whether the label of the user node of the user knowledge graph changes.
In specific implementation, whether the label of the user node of the user knowledge graph changes is judged.
S34, if the label of the user node of the user knowledge graph changes, returning to the step of obtaining the adjacent user node of the user knowledge graph and determining the label of the user node according to the label of the adjacent user node of the user node.
In a specific implementation, if the label of the user node of the user knowledge graph changes, returning to the step of obtaining the adjacent user node of the user knowledge graph, and determining the label of the user node according to the label of the adjacent user node of the user node.
S35, if the label of the user node of the user knowledge graph is not changed, the user node with the same label as the fraud individual node is marked as a suspicious fraud node.
In specific implementation, if the label of the user node of the user knowledge graph is not changed, the user node with the same label as the fraud individual node is marked as a suspicious fraud node. And the user corresponding to the suspicious fraud node is the suspicious risk user.
By applying the technical scheme of the embodiment of the invention, a credit knowledge map is constructed according to the user loan application data of the financial institution; identifying suspicious group fraud groups according to the credit knowledge graph; and extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph, so that the group fraud risk and the individual fraud risk in the existing financial loan application can be accurately identified, and the loss of a financial institution is greatly reduced.
The invention also provides a credit anti-fraud recognition device corresponding to the credit anti-fraud recognition method. The credit anti-fraud recognition apparatus includes a unit for executing the credit anti-fraud recognition method, and the apparatus may be configured in a desktop computer, a tablet computer, a laptop computer, or the like. Specifically, the credit anti-fraud recognition apparatus includes a construction unit, a first recognition unit, and a second recognition unit.
The construction unit is used for constructing a credit knowledge map according to the user loan application data of the financial institution;
the first identification unit is used for identifying a suspicious group fraud group according to the credit knowledge graph;
and the second identification unit is used for extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph and identifying suspicious fraud nodes according to the user knowledge graph.
In an embodiment, the construction unit includes an entity extraction unit, an assignment unit, and a creation unit.
The entity extraction unit is used for extracting entities from the user loan application data of the financial institution, wherein the entities comprise a user entity, an address entity, a mobile phone number entity, an identification card number entity, a bank card number entity and a financial institution entity;
the giving unit is used for giving corresponding attributes to the user entity, wherein the attributes comprise age, gender, ID card attribution, mutual fund inquiry times, suspected group fraud, financial application times in the last month, financial application times in the last three months and financial application times in the last six months;
and the establishing unit is used for establishing an association relationship between nodes according to the relationship between the user loan application data to obtain the credit knowledge map, wherein the relationship between the user loan application data comprises the relationship between a user and an address, the relationship between the user and a mobile phone number, the relationship between the user and an identification number, the relationship between the user and a bank card number and the relationship between the user and a financial institution, and each node corresponds to an entity.
In an embodiment, the first identification unit includes a first acquisition unit, a second acquisition unit, a first judgment unit, and a first judgment unit.
The first acquisition unit is used for acquiring a characteristic path in the credit knowledge graph, wherein a starting node of the characteristic path is a user node, and an end node of the characteristic path is a financial institution node;
the second acquisition unit is used for acquiring a characteristic path passing through the same application information node as a target characteristic path and establishing a subgraph according to the node in the target characteristic path, wherein the application information node comprises a mobile phone node, an identity card node and an address node;
the first judging unit is used for judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and the first judging unit is used for judging that the sub-graph contains a suspicious group-partner cheating group if the number of the nodes in the sub-graph is greater than a preset number threshold.
In an embodiment, the first identification unit includes a third acquisition unit, a fourth acquisition unit, a second judgment unit, and a second judgment unit.
A third obtaining unit, configured to obtain a node vector of each node of the credit knowledge graph;
the fourth acquisition unit is used for acquiring nodes with the distance of the node vectors smaller than a preset threshold value as target nodes and establishing subgraphs according to the target nodes;
the second judging unit is used for judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and the second judging unit is used for judging that the sub-graph contains a suspicious group-partner cheating group if the number of the nodes in the sub-graph is greater than a preset number threshold.
In an embodiment, the third obtaining unit comprises a calculating unit.
And the calculating unit is used for calculating the node vectors of the credit knowledge graph through a preset TransD model.
In one embodiment, the second identification unit includes a label assignment unit, a first label determination unit, a third judgment unit, a return unit, and a marking unit.
The label distribution unit is used for distributing labels to the cheating individual nodes in the user knowledge graph according to a preset cheating individual name list and randomly distributing different labels to user nodes except the cheating individual nodes in the user knowledge graph;
a first label determining unit, configured to obtain a user node adjacent to the user node of the user knowledge graph, and determine a label of the user node according to the label of the user node adjacent to the user node;
a third judging unit, configured to judge whether a tag of a user node of the user knowledge graph changes;
a returning unit, configured to return to the neighboring user node of the user node that acquires the user knowledge graph if the label of the user node of the user knowledge graph changes, and determine the label of the user node according to the label of the neighboring user node of the user node;
and the marking unit is used for marking the user node with the same label as the fraud individual node as a suspicious fraud node if the label of the user node of the user knowledge graph is not changed.
In an embodiment, the first tag determination unit comprises a second tag determination unit.
And the second label determining unit is used for determining the label of the user node according to the attribution factor between the user node and the adjacent user node, wherein the attribution factor is determined according to the number of the relations between the user node and the adjacent user node and the similarity of the attributes between the user node and the adjacent user node.
It should be noted that, as can be clearly understood by those skilled in the art, the specific implementation processes of the credit fraud prevention apparatus and each unit may refer to the corresponding descriptions in the foregoing method embodiments, and for convenience and brevity of description, no further description is provided herein.
The credit anti-fraud identification means described above may be implemented in the form of a computer program which may be run on a computer device as shown in figure 2.
Referring to fig. 2, fig. 2 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a terminal or a server, where the terminal may be an electronic device with a communication function, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of a plurality of servers.
Referring to fig. 2, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032, when executed, causes the processor 502 to perform a credit anti-fraud identification method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503, and when the computer program 5032 is executed by the processor 502, the processor 502 may be caused to perform a credit fraud identification method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the configuration shown in fig. 2 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation of the computer device 500 to which the present application may be applied, and that a particular computer device 500 may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is configured to run the computer program 5032 stored in the memory to implement the following steps:
constructing a credit knowledge map according to user loan application data of a financial institution;
identifying suspicious group fraud groups according to the credit knowledge graph;
and extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph.
In one embodiment, the processor 502, in implementing the step of constructing a credit knowledge map from the financial institution's user loan application data, implements the following steps:
extracting entities from user loan application data of a financial institution, wherein the entities comprise a user entity, an address entity, a mobile phone number entity, an identification card number entity, a bank card number entity and a financial institution entity;
giving corresponding attributes to the user entity, wherein the attributes comprise age, gender, ID card attribution, mutual fund inquiry times, whether the group partner is suspected to be cheating, financial application times in the last month, financial application times in the last three months and financial application times in the last six months;
and establishing an association relationship between nodes according to the relationship between the user loan application data to obtain the credit knowledge map, wherein the relationship between the user loan application data comprises the relationship between a user and an address, the relationship between the user and a mobile phone number, the relationship between the user and an identification number, the relationship between the user and a bank card number and the relationship between the user and a financial institution, and each node corresponds to an entity.
In an embodiment, when implementing the step of identifying a suspected group fraud group according to the credit knowledge graph, the processor 502 specifically implements the following steps:
acquiring a characteristic path in the credit knowledge graph, wherein a starting node of the characteristic path is a user node, and an end node of the characteristic path is a financial institution node;
acquiring characteristic paths passing through the same application information nodes as target characteristic paths, and establishing subgraphs according to the nodes in the target characteristic paths, wherein the application information nodes comprise mobile phone nodes, identity card nodes and address nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
In an embodiment, when implementing the step of identifying a suspected group fraud group according to the credit knowledge graph, the processor 502 specifically implements the following steps:
acquiring node vectors of all nodes of the credit knowledge graph;
acquiring nodes with the distance of the node vectors smaller than a preset threshold value as target nodes, and establishing subgraphs according to the target nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
In an embodiment, when the processor 502 implements the step of obtaining node vectors of nodes of the credit knowledge graph, the following steps are specifically implemented:
and calculating the node vectors of the credit knowledge graph through a preset TransD model.
In an embodiment, when the processor 502 implements the step of identifying a suspected fraud node according to the user knowledge graph, the following steps are specifically implemented:
allocating labels to the cheating individual nodes in the user knowledge graph according to a preset cheating individual name list, and randomly allocating different labels to user nodes except the cheating individual nodes in the user knowledge graph;
acquiring adjacent user nodes of the user knowledge graph, and determining labels of the user nodes according to the labels of the adjacent user nodes of the user nodes;
judging whether the label of the user node of the user knowledge graph changes or not;
if the label of the user node of the user knowledge graph changes, returning to the adjacent user node of the user node which acquires the user knowledge graph, and determining the label of the user node according to the label of the adjacent user node of the user node;
and if the label of the user node of the user knowledge graph is not changed, marking the user node with the same label as the fraud individual node as a suspicious fraud node.
In an embodiment, when the processor 502 implements the step of determining the label of the user node according to the labels of the neighboring user nodes of the user node, the following steps are specifically implemented:
and determining the label of the user node according to the attribution factor between the user node and the adjacent user node, wherein the attribution factor is determined according to the number of the relations between the user node and the adjacent user node and the similarity of the attributes between the user node and the adjacent user node.
It should be understood that, in the embodiment of the present Application, the Processor 502 may be a Central Processing Unit (CPU), and the Processor 502 may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It will be understood by those skilled in the art that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program instructing associated hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program. The computer program, when executed by a processor, causes the processor to perform the steps of:
constructing a credit knowledge map according to user loan application data of a financial institution;
identifying suspicious group fraud groups according to the credit knowledge graph;
and extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph.
In one embodiment, when the computer program is executed by the processor to implement the step of constructing a credit knowledge map from user loan application data of a financial institution, the processor implements the following steps:
extracting entities from user loan application data of a financial institution, wherein the entities comprise a user entity, an address entity, a mobile phone number entity, an identification card number entity, a bank card number entity and a financial institution entity;
giving corresponding attributes to the user entity, wherein the attributes comprise age, gender, ID card attribution, mutual fund inquiry times, whether the group partner is suspected to be cheating, financial application times in the last month, financial application times in the last three months and financial application times in the last six months;
and establishing an association relationship between nodes according to the relationship between the user loan application data to obtain the credit knowledge map, wherein the relationship between the user loan application data comprises the relationship between a user and an address, the relationship between the user and a mobile phone number, the relationship between the user and an identification number, the relationship between the user and a bank card number and the relationship between the user and a financial institution, and each node corresponds to an entity.
In an embodiment, when the computer program is executed by the processor to implement the step of identifying a suspected group fraud group according to the credit knowledge map, the processor is further implemented with the following steps:
acquiring a characteristic path in the credit knowledge graph, wherein a starting node of the characteristic path is a user node, and an end node of the characteristic path is a financial institution node;
acquiring characteristic paths passing through the same application information nodes as target characteristic paths, and establishing subgraphs according to the nodes in the target characteristic paths, wherein the application information nodes comprise mobile phone nodes, identity card nodes and address nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
In an embodiment, when the computer program is executed by the processor to implement the step of identifying a suspected group fraud group according to the credit knowledge map, the processor is further implemented with the following steps:
acquiring node vectors of all nodes of the credit knowledge graph;
acquiring nodes with the distance of the node vectors smaller than a preset threshold value as target nodes, and establishing subgraphs according to the target nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
In an embodiment, when the computer program is executed to implement the step of obtaining node vectors of nodes of the credit knowledge graph, the processor specifically implements the following steps:
and calculating the node vectors of the credit knowledge graph through a preset TransD model.
In an embodiment, when the step of identifying a suspected fraud node according to the user knowledge-graph is implemented by the processor executing the computer program, the following steps are specifically implemented:
allocating labels to the cheating individual nodes in the user knowledge graph according to a preset cheating individual name list, and randomly allocating different labels to user nodes except the cheating individual nodes in the user knowledge graph;
acquiring adjacent user nodes of the user knowledge graph, and determining labels of the user nodes according to the labels of the adjacent user nodes of the user nodes;
judging whether the label of the user node of the user knowledge graph changes or not;
if the label of the user node of the user knowledge graph changes, returning to the adjacent user node of the user node which acquires the user knowledge graph, and determining the label of the user node according to the label of the adjacent user node of the user node;
and if the label of the user node of the user knowledge graph is not changed, marking the user node with the same label as the fraud individual node as a suspicious fraud node.
In an embodiment, when the processor executes the computer program to implement the step of determining the label of the user node according to the labels of the neighboring user nodes of the user node, the following steps are specifically implemented:
and determining the label of the user node according to the attribution factor between the user node and the adjacent user node, wherein the attribution factor is determined according to the number of the relations between the user node and the adjacent user node and the similarity of the attributes between the user node and the adjacent user node.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, which can store various computer readable storage media.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, various elements or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, while the invention has been described with respect to the above-described embodiments, it will be understood that the invention is not limited thereto but may be embodied with various modifications and changes.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A credit fraud identification method, comprising:
constructing a credit knowledge map according to user loan application data of a financial institution;
identifying suspicious group fraud groups according to the credit knowledge graph;
and extracting all user nodes in the credit knowledge graph to obtain a user knowledge graph, and identifying suspicious fraud nodes according to the user knowledge graph.
2. The credit fraud prevention identification method of claim 1, wherein said building a credit knowledge map from user loan application data of a financial institution comprises:
extracting entities from user loan application data of a financial institution, wherein the entities comprise a user entity, an address entity, a mobile phone number entity, an identification card number entity, a bank card number entity and a financial institution entity;
giving corresponding attributes to the user entity, wherein the attributes comprise age, gender, ID card attribution, mutual fund inquiry times, whether the group partner is suspected to be cheating, financial application times in the last month, financial application times in the last three months and financial application times in the last six months;
and establishing an association relationship between nodes according to the relationship between the user loan application data to obtain the credit knowledge map, wherein the relationship between the user loan application data comprises the relationship between a user and an address, the relationship between the user and a mobile phone number, the relationship between the user and an identification number, the relationship between the user and a bank card number and the relationship between the user and a financial institution, and each node corresponds to an entity.
3. The credit anti-fraud identification method according to claim 1, characterized in that said identifying suspicious group-partner fraud parties from said credit knowledge map comprises:
acquiring a characteristic path in the credit knowledge graph, wherein a starting node of the characteristic path is a user node, and an end node of the characteristic path is a financial institution node;
acquiring characteristic paths passing through the same application information nodes as target characteristic paths, and establishing subgraphs according to the nodes in the target characteristic paths, wherein the application information nodes comprise mobile phone nodes, identity card nodes and address nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
4. The credit anti-fraud identification method according to claim 1, characterized in that said identifying suspicious group-partner fraud parties from said credit knowledge map comprises:
acquiring node vectors of all nodes of the credit knowledge graph;
acquiring nodes with the distance of the node vectors smaller than a preset threshold value as target nodes, and establishing subgraphs according to the target nodes;
judging whether the number of the nodes in the subgraph is larger than a preset number threshold value or not;
and if the number of the nodes in the sub-graph is larger than a preset number threshold, determining that the sub-graph contains a suspicious group fraud group.
5. The credit anti-fraud identification method according to claim 4, wherein said obtaining node vectors for nodes of said credit knowledge-graph comprises:
and calculating the node vectors of the credit knowledge graph through a preset TransD model.
6. The credit anti-fraud identification method according to claim 1, characterized in that said identifying suspected fraud nodes according to said user knowledge-graph comprises:
allocating labels to the cheating individual nodes in the user knowledge graph according to a preset cheating individual name list, and randomly allocating different labels to user nodes except the cheating individual nodes in the user knowledge graph;
acquiring adjacent user nodes of the user knowledge graph, and determining labels of the user nodes according to the labels of the adjacent user nodes of the user nodes;
judging whether the label of the user node of the user knowledge graph changes or not;
if the label of the user node of the user knowledge graph changes, returning to the adjacent user node of the user node which acquires the user knowledge graph, and determining the label of the user node according to the label of the adjacent user node of the user node;
and if the label of the user node of the user knowledge graph is not changed, marking the user node with the same label as the fraud individual node as a suspicious fraud node.
7. The credit fraud identification method of claim 6, wherein said determining the label of the user node based on the labels of the user nodes adjacent to the user node comprises:
and determining the label of the user node according to the attribution factor between the user node and the adjacent user node, wherein the attribution factor is determined according to the number of the relations between the user node and the adjacent user node and the similarity of the attributes between the user node and the adjacent user node.
8. Credit anti-fraud identification means, characterized in that it comprises means for carrying out the method according to any one of claims 1 to 7.
9. A computer arrangement, characterized in that the computer arrangement comprises a memory having stored thereon a computer program and a processor implementing the method according to any of claims 1-7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911227933.3A CN110930246A (en) | 2019-12-04 | 2019-12-04 | Credit anti-fraud identification method and device, computer equipment and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911227933.3A CN110930246A (en) | 2019-12-04 | 2019-12-04 | Credit anti-fraud identification method and device, computer equipment and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110930246A true CN110930246A (en) | 2020-03-27 |
Family
ID=69856678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911227933.3A Pending CN110930246A (en) | 2019-12-04 | 2019-12-04 | Credit anti-fraud identification method and device, computer equipment and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110930246A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640005A (en) * | 2020-05-28 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Data analysis method and device, computer equipment and storage medium |
| CN112053221A (en) * | 2020-08-14 | 2020-12-08 | 百维金科(上海)信息科技有限公司 | Knowledge graph-based internet financial group fraud detection method |
| CN112200655A (en) * | 2020-09-17 | 2021-01-08 | 中国建设银行股份有限公司 | Application auditing method and device, electronic equipment and storage medium |
| CN112231486A (en) * | 2020-09-04 | 2021-01-15 | 苏宁金融科技(南京)有限公司 | Target database construction method, target applicant identification method, device and system |
| CN112308565A (en) * | 2020-08-14 | 2021-02-02 | 中国工商银行股份有限公司 | Many-to-many cross-border fund wind control method and system based on knowledge graph |
| CN112308694A (en) * | 2020-11-24 | 2021-02-02 | 拉卡拉支付股份有限公司 | Method and device for discovering cheating group |
| CN112561684A (en) * | 2020-12-15 | 2021-03-26 | 平安科技（深圳）有限公司 | Financial fraud risk identification method and device, computer equipment and storage medium |
| CN112598489A (en) * | 2020-12-14 | 2021-04-02 | 深圳市快付通金融网络科技服务有限公司 | Risk monitoring method and system based on financial application |
| CN113094506A (en) * | 2021-04-14 | 2021-07-09 | 每日互动股份有限公司 | Early warning method based on relation map, computer equipment and storage medium |
| CN113553446A (en) * | 2021-07-28 | 2021-10-26 | 厦门国际银行股份有限公司 | Financial anti-fraud method and device based on heteromorphic graph deconstruction |
| CN113657902A (en) * | 2021-08-03 | 2021-11-16 | 浙江创邻科技有限公司 | Financial security management method, system and storage medium based on graph database |
| CN113869904A (en) * | 2021-08-16 | 2021-12-31 | 工银科技有限公司 | Suspicious data identification method, device, electronic equipment, medium and computer program |
| CN114596097A (en) * | 2022-05-10 | 2022-06-07 | 富算科技(上海)有限公司 | User identification method, device, electronic equipment and computer readable storage medium |
| CN115345727A (en) * | 2022-08-19 | 2022-11-15 | 中电金信软件有限公司 | Method and device for identifying fraud loan application |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038778A (en) * | 2017-12-05 | 2018-05-15 | 深圳信用宝金融服务有限公司 | Clique's fraud recognition methods of the small micro- loan of internet finance and device |
| CN109816519A (en) * | 2019-01-25 | 2019-05-28 | 宜人恒业科技发展（北京）有限公司 | A kind of recognition methods of fraud clique, device and equipment |
| CN110297912A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Cheat recognition methods, device, equipment and computer readable storage medium |
-
2019
- 2019-12-04 CN CN201911227933.3A patent/CN110930246A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038778A (en) * | 2017-12-05 | 2018-05-15 | 深圳信用宝金融服务有限公司 | Clique's fraud recognition methods of the small micro- loan of internet finance and device |
| CN109816519A (en) * | 2019-01-25 | 2019-05-28 | 宜人恒业科技发展（北京）有限公司 | A kind of recognition methods of fraud clique, device and equipment |
| CN110297912A (en) * | 2019-05-20 | 2019-10-01 | 平安科技（深圳）有限公司 | Cheat recognition methods, device, equipment and computer readable storage medium |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640005A (en) * | 2020-05-28 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Data analysis method and device, computer equipment and storage medium |
| CN112053221A (en) * | 2020-08-14 | 2020-12-08 | 百维金科(上海)信息科技有限公司 | Knowledge graph-based internet financial group fraud detection method |
| CN112308565A (en) * | 2020-08-14 | 2021-02-02 | 中国工商银行股份有限公司 | Many-to-many cross-border fund wind control method and system based on knowledge graph |
| CN112231486A (en) * | 2020-09-04 | 2021-01-15 | 苏宁金融科技(南京)有限公司 | Target database construction method, target applicant identification method, device and system |
| CN112200655A (en) * | 2020-09-17 | 2021-01-08 | 中国建设银行股份有限公司 | Application auditing method and device, electronic equipment and storage medium |
| CN112308694A (en) * | 2020-11-24 | 2021-02-02 | 拉卡拉支付股份有限公司 | Method and device for discovering cheating group |
| CN112598489B (en) * | 2020-12-14 | 2023-12-26 | 深圳市快付通金融网络科技服务有限公司 | Risk monitoring method and system based on financial application |
| CN112598489A (en) * | 2020-12-14 | 2021-04-02 | 深圳市快付通金融网络科技服务有限公司 | Risk monitoring method and system based on financial application |
| CN112561684A (en) * | 2020-12-15 | 2021-03-26 | 平安科技（深圳）有限公司 | Financial fraud risk identification method and device, computer equipment and storage medium |
| CN112561684B (en) * | 2020-12-15 | 2024-03-19 | 平安科技（深圳）有限公司 | Financial fraud risk identification method, apparatus, computer device and storage medium |
| CN113094506A (en) * | 2021-04-14 | 2021-07-09 | 每日互动股份有限公司 | Early warning method based on relation map, computer equipment and storage medium |
| CN113094506B (en) * | 2021-04-14 | 2023-08-18 | 每日互动股份有限公司 | Early warning method based on relational graph, computer equipment and storage medium |
| CN113553446A (en) * | 2021-07-28 | 2021-10-26 | 厦门国际银行股份有限公司 | Financial anti-fraud method and device based on heteromorphic graph deconstruction |
| CN113553446B (en) * | 2021-07-28 | 2022-05-24 | 厦门国际银行股份有限公司 | Financial anti-fraud method and device based on heterograph deconstruction |
| CN113657902A (en) * | 2021-08-03 | 2021-11-16 | 浙江创邻科技有限公司 | Financial security management method, system and storage medium based on graph database |
| CN113657902B (en) * | 2021-08-03 | 2024-03-22 | 浙江创邻科技有限公司 | Financial security management method, system and storage medium based on graph database |
| CN113869904A (en) * | 2021-08-16 | 2021-12-31 | 工银科技有限公司 | Suspicious data identification method, device, electronic equipment, medium and computer program |
| CN114596097B (en) * | 2022-05-10 | 2022-08-26 | 富算科技(上海)有限公司 | User identification method, device, electronic equipment and computer readable storage medium |
| CN114596097A (en) * | 2022-05-10 | 2022-06-07 | 富算科技(上海)有限公司 | User identification method, device, electronic equipment and computer readable storage medium |
| CN115345727A (en) * | 2022-08-19 | 2022-11-15 | 中电金信软件有限公司 | Method and device for identifying fraud loan application |
| CN115345727B (en) * | 2022-08-19 | 2023-04-28 | 中电金信软件有限公司 | Method and device for identifying fraudulent loan application |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110930246A (en) | Credit anti-fraud identification method and device, computer equipment and computer-readable storage medium | |
| CN107730262B (en) | Fraud identification method and device | |
| CN112600810B (en) | Ether house phishing fraud detection method and device based on graph classification | |
| CN109583468B (en) | Training sample acquisition method, sample prediction method and corresponding device | |
| CN111222976B (en) | Risk prediction method and device based on network map data of two parties and electronic equipment | |
| US20200364719A1 (en) | System and method for determining a decision-making strategy | |
| CN112148987A (en) | Message pushing method based on target object activity and related equipment | |
| CN111199474A (en) | Risk prediction method and device based on network diagram data of two parties and electronic equipment | |
| CN112435137A (en) | Cheating information detection method and system based on community mining | |
| CN111666346A (en) | Information merging method, transaction query method, device, computer and storage medium | |
| CN114187112A (en) | Training method of account risk model and determination method of risk user group | |
| CN111062808B (en) | Credit card limit evaluation method, credit card limit evaluation device, computer equipment and storage medium | |
| CN113807940A (en) | Information processing and fraud identification method, device, equipment and storage medium | |
| CN113472860A (en) | Service resource allocation method and server under big data and digital environment | |
| CN110363534B (en) | Method and device for identifying abnormal transaction | |
| CN112750038A (en) | Transaction risk determination method and device and server | |
| CN115632874A (en) | Method, device, equipment and storage medium for detecting threat of entity object | |
| CN113222609B (en) | Risk identification method and device | |
| CN112200644B (en) | Method and device for identifying fraudulent user, computer equipment and storage medium | |
| CN110472680B (en) | Object classification method, device and computer-readable storage medium | |
| CN113159937A (en) | Method and device for identifying risks and electronic equipment | |
| CN114547448B (en) | Data processing method, model training method, device, equipment, storage medium and program | |
| CN116843432B (en) | Anti-fraud method and device based on address text information | |
| Xue et al. | Bitcoin transaction pattern recognition based on semi-supervised learning | |
| CN113723522B (en) | Abnormal user identification method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200327 |