CN113159922A - Data flow direction identification method, device, equipment and medium - Google Patents
Data flow direction identification method, device, equipment and medium Download PDFInfo
- Publication number
- CN113159922A CN113159922A CN202110454435.3A CN202110454435A CN113159922A CN 113159922 A CN113159922 A CN 113159922A CN 202110454435 A CN202110454435 A CN 202110454435A CN 113159922 A CN113159922 A CN 113159922A
- Authority
- CN
- China
- Prior art keywords
- account
- data
- financial
- graph
- generate
- 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 57
- 238000004458 analytical method Methods 0.000 claims abstract description 80
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 39
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 238000012546 transfer Methods 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000005206 flow analysis Methods 0.000 claims description 7
- 238000007635 classification algorithm Methods 0.000 claims description 5
- 238000010992 reflux Methods 0.000 claims 2
- 239000000126 substance Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 10
- 238000004900 laundering Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Abstract
The invention discloses a flow direction identification method, a flow direction identification device, flow direction identification equipment and a flow direction identification medium of financial data, wherein the method comprises the following steps: collecting and preprocessing historical transaction data of a plurality of financial account numbers; acquiring account data associated with each financial account in the preprocessed transaction data to generate an account set; constructing a plurality of directed node graphs based on the account set, and generating a target mesh graph after randomly combining the directed node graphs; and performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result, and generating a risk report based on the analysis result. Therefore, according to the embodiment of the application, the network graph is generated from the historical transaction data, and the financial data flow direction relation analysis is performed on the network graph structure through the set algorithm, so that the financial data flow direction situation of each account is accurately and comprehensively identified, and the loan risk coefficient of the financial institution is reduced.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for identifying a flow direction of data.
Background
In recent years, financial operation risk cases are frequently and frequently generated, cases related to operation of financial institutions are frequently generated, and it is common knowledge that flow identification and analysis of financial data of user accounts in the financial institutions are performed. Therefore, how to effectively prevent and control the problems of different scenes in the financial industry becomes a problem which needs to be solved urgently.
In the prior art, the financial institution describes the fund traffic between accounts by the rules processed by the database SQL statements aiming at the financial data flow analysis. In the prior art, the processing flow is long when the rules are processed, the processing logic is complex, and the processed rules cannot accurately depict the characteristics of fund exchange among accounts, so that the identification difficulty of the financial data flow direction is improved, and the risk coefficient of the fund of a financial institution is increased.
Disclosure of Invention
In view of the above, it is desirable to provide a method, an apparatus, a device, and a medium for identifying a flow direction of financial data, which solve the problem of difficulty in identifying a flow direction of financial data.
A flow direction identification method of financial data comprises the following steps: collecting and preprocessing historical transaction data corresponding to a plurality of financial account numbers; acquiring account data associated with each financial account number in the preprocessed transaction data to generate an account set; constructing a plurality of directed node graphs based on the account set, and generating a target mesh graph after randomly combining the directed node graphs; and performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result, and generating a risk report based on the analysis result.
In one embodiment, collecting and preprocessing historical transaction data corresponding to a plurality of financial account numbers comprises: determining a plurality of transaction financial account numbers; inquiring the loan amount data of each transaction financial account in the plurality of transaction financial accounts, and determining a risk-free loan account based on the loan amount data of each transaction financial account; removing the risk-free loan account from the plurality of transaction financial account numbers to generate a target financial account number set; collecting fund access information of each target financial account in the target financial account set within a preset time period from a data center of the target financial institution; and carrying out data cleaning on fund access information of each target financial account in a preset time period to generate preprocessed historical transaction data.
In one embodiment, the data cleaning of the fund access information of each target financial account in a preset time period to generate the preprocessed historical transaction data includes: creating a cache set of incomplete information according to a preset method; inquiring incomplete historical transaction information one by one from fund access information of each target financial account in a preset time period; storing the inquired incomplete history transaction information into an incomplete information cache set to generate cached incomplete history transaction information; and clearing or repairing the cached incomplete historical transaction information to generate processed historical transaction data.
In one embodiment, acquiring account data associated with each of the financial account numbers in the pre-processed transaction data to generate an account set includes: establishing a Bayesian classifier by adopting a Bayesian classification algorithm; inputting the preprocessed historical transaction data into a Bayesian classifier for identification and classification, and outputting account data associated with each financial account; determining the account data associated with each of the financial account numbers as a set of accounts.
In one embodiment, building a plurality of directed node graphs based on account sets includes: converting each account in the account set into a graph node, and generating a graph node set; determining transfer relations among all graph nodes in the graph node set, and determining the transfer relations among all the graph nodes as directed edges connected among all the graph nodes; and connecting the graph nodes in the graph node set according to the directed edges connected among the graph nodes to generate a plurality of directed node graphs.
In one embodiment, the analyzing the flow of financial data for the target mesh graph to generate the analysis result comprises: adopting a depth-first traversal algorithm of the graph to traverse and inquire whether a closed loop is included from the initial graph node of the target mesh graph one by one; determining that a return of funds has occurred when a closed loop is involved; acquiring transaction amount data and transaction time data corresponding to directed edges contained in the closed loop; calculating the fund backflow proportion and fund backflow period of the fund backflow according to the transaction amount data and the transaction time data corresponding to the directed edge; and determining a risk grade according to the fund return proportion and the fund return period, and determining the risk grade as an analysis result.
In one embodiment, the analyzing the flow of financial data for the target mesh graph to generate the analysis result comprises: calculating the edge betweenness of each directed edge in the target mesh graph by adopting a community discovery algorithm of the graph to generate the edge betweenness corresponding to each directed edge; determining a directed edge with the maximum boundary number based on the edge betweenness corresponding to each directed edge; deleting the directed edge with the maximum number of the boundaries to generate a mesh graph after the directed edge is deleted; calculating the corresponding modularity of the mesh graph after the directed edge is deleted; when the modularity is larger than a first threshold and smaller than a second threshold, determining that illegal loan-putting behaviors occur; determining illegal loan-placing behaviors as analysis results; wherein, the first threshold is smaller than the second threshold, and the community discovery algorithm of the graph is GN algorithm.
An apparatus comprising a memory and a processor, the memory having stored therein computer readable instructions, which when executed by the processor, cause the processor to perform the steps of the above-described method for flow direction identification of financial data.
A medium storing computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the above method for flow direction identification of financial data.
The flow direction identification device of the financial data firstly collects and preprocesses historical transaction data of a plurality of financial account numbers, then obtains account data associated with each financial account number in the preprocessed transaction data to generate an account set, secondly constructs a plurality of directed node graphs based on the account set, randomly combines the directed node graphs to generate a target mesh graph, and finally performs financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result and generates a risk report based on the analysis result. Therefore, by adopting the embodiment of the application, the account set is obtained from the historical transaction data of the financial institution loan, the directed node graph is constructed according to the transaction data among the accounts in the account set, the mesh graph is formed based on the directed node graph, and the financial data flow direction relation analysis is performed on the mesh graph structure through the set algorithm, so that the financial data flow direction situation of each account can be accurately and comprehensively identified, and the risk coefficient of the financial institution loan is reduced.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a diagram of an implementation environment of a flow identification method for financial data provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of the internal structure of the apparatus according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a method for flow direction identification of financial data as provided in one embodiment of the present application;
FIG. 4 is a directed node graph as provided in one embodiment of the present application;
FIG. 5 is a schematic diagram of a method for identifying a flow direction of financial data according to another embodiment of the present application;
fig. 6 is a schematic diagram of an apparatus for identifying a flow direction of financial data according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another.
Fig. 1 is a diagram of an implementation environment of a flow identification method of financial data provided in an embodiment, as shown in fig. 1, in which a device 110 and a client 120 are included.
It should be noted that the client 120 may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like. The device 110 and the client 120 may be connected through bluetooth, USB (Universal Serial Bus), or other communication connection methods, which is not limited herein.
Fig. 2 is a schematic diagram of the internal structure of the apparatus in one embodiment. As shown in fig. 2, the device includes a processor, a medium, a memory, and a network interface connected by a system bus. The device comprises a medium, an operating system, a database and computer readable instructions, wherein the database can store control information sequences, and the computer readable instructions can enable a processor to realize a flow direction identification method of financial data when being executed by the processor. The processor of the device is used to provide computing and control capabilities to support the operation of the entire device. The memory of the device may have stored therein computer readable instructions that, when executed by the processor, may cause the processor to perform a method of flow direction identification of financial data. The network interface of the device is used for connecting and communicating with the terminal. 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 on the devices to which the present application applies, and that a particular device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components. Wherein the medium is a readable storage medium.
The flow direction identification method of the financial data provided by the embodiment of the present application will be described in detail below with reference to fig. 3 to 5. The method may be implemented in dependence on a computer program operable on a flow direction identification device based on financial data of the von neumann architecture. The computer program may be integrated into the application or may run as a separate tool-like application.
Referring to fig. 3, a flow chart of a method for identifying a flow direction of financial data is provided according to an embodiment of the present application. As shown in fig. 3, the method of the embodiment of the present application may include the following steps:
s101, collecting and preprocessing historical transaction data corresponding to a plurality of financial accounts;
the plurality of financial account numbers are user account numbers with successful money put by the financial institution, the historical transaction data is the transaction information of fund input and output in the user account numbers, and the transaction information comprises the transaction data between the user account numbers and the payee.
Historical transaction data exists according to a batch of loan-related account numbers, and the transaction data comprises: payee account number, payer account number, transaction amount, transaction time, transaction type (transfer/loan). The account number also has relevant associated information: including the name of the collection, the name of the payment, the card number, the date of the opening of the account, the line of the opening of the account (accurate to the community, such as a certain branch of a certain financial institution in a certain region of a certain city in a certain province), the type of the client (institution/insurance/investment), the sign of the public, etc.
It should be noted that, the historical transaction data is generally derived from transaction data in a row, or is obtained from online clearing, and the collection of the historical transaction data may be determined according to an actual scenario, which is not limited herein.
In an embodiment of the present application, historical transaction data is stored on a blockchain to facilitate preventing tampering with transaction information. In the actual transaction, when the user performs each transaction, the transaction information is sent to the blockchain for storage in a wired or wireless manner.
In general, the preprocessing is to perform data cleansing on historical transaction data in an account, for example, to remove risk-free account data such as a small loan from a plurality of account numbers, or to remove incomplete data in the historical transaction data.
In a possible implementation manner, when financial data flow direction analysis is performed on a batch of loan accounts, a batch of transaction financial account numbers are determined from data derived from an online clearing place or a financial institution, then fund entering and exiting information of the batch of financial account numbers in a time period from a current time to a financial institution depositing time is collected from a financial institution database, risk-free account numbers are determined based on loan lines of the financial account numbers, transaction information of risk-free account numbers and risk-free account numbers is eliminated from data of a plurality of financial account numbers, incomplete historical transaction information is searched from historical transaction information corresponding to the remaining financial account numbers after elimination, and preprocessed historical transaction data are generated based on the inquired incomplete information.
Further, when generating the preprocessed historical transaction data based on the inquired incomplete information, if the preprocessed historical transaction data cannot be inquired, generating final historical transaction information. If the historical transaction information is found out, the incomplete information is removed to generate final historical transaction information, or the incomplete information is repaired, and after the incomplete information is successfully repaired, the preprocessed historical transaction information is generated.
Further, when the incomplete information is repaired, the incomplete record of the incomplete information is firstly obtained, the data at the same position in the transaction information on the incomplete record is inquired, and the final information is estimated and filled according to the data at the upper position and the lower position. For example, the incomplete record is time information, the time for inquiring the previous transaction information is, for example, 16:07:55 at 25/1/2021/25, and the time for inquiring the next transaction information is, for example, 16:07:55 at 27/1/2021, so that the default time for inquiring the incomplete record is, for example, 16:07:55 at 26/2021/1.
Further, when searching for the risk-free account, firstly, calculating the loan lines of the financial accounts, then arranging the loan lines in an ascending order, and finally selecting a preset number of loan line accounts from the ordered loan lines one by one from the initial position to clear the loan line accounts to generate the remaining financial accounts after clearing.
S102, acquiring account data associated with each financial account in the preprocessed transaction data to generate an account set;
wherein, a large number of transaction accounts exist in the preprocessed historical transaction data.
Typically, the pre-processed historical transaction data includes the loan account, and other financial institution accounts that have traded funds with the loan account, and therefore these accounts need to be extracted from the historical transaction data. Because the account field identification in the historical transaction data is unique, all accounts in the historical transaction data can be acquired as long as the data under the account field identification is classified.
It should be noted that, the present application uses a bayesian classifier to perform field identification classification.
In a possible implementation manner, when obtaining the pre-processed historical transaction data, firstly, inputting the pre-processed historical transaction data into a pre-created bayesian classifier, wherein account field identifiers are preset in the bayesian classifier, so that the bayesian classifier can identify and classify all accounts in the historical transaction data, and after performing classification processing, the bayesian classifier outputs the classified accounts.
S103, constructing a plurality of directed node graphs based on the account set, and generating a target mesh graph after randomly combining the directed node graphs;
the directed node graph is a directed graph formed according to the relationship between nodes. A directed node graph is shown, for example, in fig. 4, where each node in the graph is, for example, A, B, C, D, E, F, G, H, I, J.
In a possible implementation manner, when a directed node graph is constructed, firstly, each account in an account set is determined as a node, then a node set is generated, then transfer relations among all nodes in the node set are mapped, the transfer relations among all nodes are converted into directed edges among all nodes, and finally all nodes are connected based on the directed edges to generate a plurality of directed node graphs.
Further, after the directed node graph is obtained, firstly, the card number, the account opening date, the account opening row and the like of each node in the directed node graph are obtained to be used as first attributes of the nodes, the first attributes are bound to each node, secondly, the transaction time, the transaction amount and the like between the nodes in the directed node graph are obtained to be used as second attributes, the second attributes and the corresponding directed edges are bound, and finally, the directed node graphs after the attributes are bound can be combined to obtain the target mesh graph.
For example, each account in the account set is used as a node, and transfers among accounts are used as a relationship (i.e., account a transfers a transfer to account B once, and then node a has a directed edge pointing to B). The information of the account number is as follows: card number, account opening date, account opening row and the like are used as attributes of the nodes, transaction time, transaction amount and the like are used as attributes of the relationship, and finally, data are processed into a network comprising a plurality of subgraphs.
And S104, performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result, and generating a risk report based on the analysis result.
The analysis results can be divided into two types, one is capital return (i.e. money laundering behavior) and the other is illegal loan. The fund flow-back may be that the borrower has money laundering behavior, and the illegal use may be that the borrower holds money from a financial institution to loan high interest.
In a possible implementation manner, when a target mesh graph is generated and analyzed, firstly, a depth-first traversal algorithm of the graph is adopted to traverse and inquire whether a closed loop is included from an initial graph node of the target mesh graph one by one, when the closed loop is included, fund backflow is determined to occur, then transaction amount data and transaction time data corresponding to a directed edge included in the closed loop are obtained, then, a fund backflow proportion and a fund backflow period of the fund backflow are calculated according to the transaction amount data and the transaction time data corresponding to the directed edge, finally, a risk level is determined according to the fund backflow proportion and the fund backflow period, and the risk level is determined as an analysis result.
Further, after the analysis result is generated, the higher the risk level in the analysis result is, the higher the suspicion of money laundering of the borrower is proved, a preset report template is obtained according to the level displayed in the analysis result, the financial institution account and the account related information with the suspicion of money laundering are obtained, the financial institution account and the account related information with the suspicion of money laundering are converted into a text in an xml format, the converted text information is filled into the preset report template, and the filled template report is sent to a computer terminal of a post-loan wind control manager for early warning.
Specifically, when whether a fund backflow behavior exists or not is identified for a target mesh graph, a depth-first traversal algorithm of the graph is adopted to start from a first node of the target mesh graph, whether closed loops exist in the graph or not is searched in a one-by-one traversal mode according to directed edges of the nodes, if the graph comprises the loops, a certain fund backflow is proved, then a fund backflow proportion is calculated according to transaction amount and transaction time in the attributes of the directed edges in the closed loops, a risk grade is determined according to the fund backflow proportion, and the determined risk grade is used as an analysis result.
Wherein, the smaller the period of the return flow of funds is, the larger the proportion of the returned funds is, the higher the risk level is, and the distribution of the proportion of the returned funds, the return period and the risk level is defined as shown in table 1:
TABLE 1
In another possible implementation manner, when the target mesh graph is generated and analyzed, firstly, the community discovery algorithm of the graph is adopted to calculate the edge betweenness of each directed edge in the target mesh graph, the edge betweenness corresponding to each directed edge is generated, then the directed edge with the maximum boundary number is determined based on the edge betweenness corresponding to each directed edge, then the directed edge with the maximum boundary number is deleted, the mesh graph with the directed edge deleted is generated, then the modularity corresponding to the mesh graph with the directed edge deleted is calculated, when the modularity is greater than a first threshold and smaller than a second threshold, an illegal loan-putting behavior is determined to occur, and finally, the illegal loan-putting behavior is determined to be an analysis result; the first threshold is smaller than the second threshold, and the community discovery algorithm of the graph is abbreviated as GN algorithm.
Specifically, the identification is performed by using a community discovery algorithm of the graph. The community discovery algorithm of the graph adopts a GN algorithm which is a type of algorithm based on clustering, because after the graph is formed by our data, the inside of the graph is composed of a plurality of subgraphs. Such algorithms are relatively good at clustering this type of data. In a network, the shortest paths through edges within communities are relatively small, and the number of shortest paths through edges between communities is relatively large. The GN algorithm is an algorithm based on edge deletion, is essentially based on the splitting idea in clustering, and is a measurement method using edge betweenness as similarity in principle. In the GN algorithm, deletion of edges with a high edge betweenness is selected each time, so that the network is gradually divided into sub-graphs, and each sub-graph corresponds to a community. When the degree of the graph reaches the value expected by us, the division of the community is proved to be relatively reasonable.
The steps of the GN algorithm are as follows: (1) calculating the edge betweenness of each edge; (2) deleting the side with the maximum number of boundaries; (3) recalculating the edge orders of the rest edges in the network; (4) calculating the modularity of the diagram (i.e., the value of Q), and repeating steps (3) and (4) if the value of Q does not reach the desired value (typically between 0.3 and 0.7) until the desired value is reached.
Among others, the GN algorithm has the advantages: the time complexity of calculating the number of boundaries is O (m × n), and the total time complexity is O (m2 × n) under a network of m edges and n nodes. The time complexity of the device is better to control in the whole, and the device is better to perform under the condition of relatively less edges.
Through the algorithm, as long as the modularity of a sub-graph in a network formed by the sub-graphs reaches 0.3-0.7, a community sub-graph is considered to be found, and the account number related in the sub-graph has the risk of lending up and benefiting the money of a financial institution. When the fact that the loan is illegally used is found, a preset report template is obtained, the financial institution account and the account related information with the suspicion of money laundering are obtained, the financial institution account with the illegal use funds and the account related information are converted into a text in an xml format, the converted text information is filled into the preset report template, and the filled template report is sent to a computer terminal of a post-loan wind control manager for early warning.
In the embodiment of the application, a flow direction identification device of financial data firstly collects and preprocesses historical transaction data of a plurality of financial account numbers, then obtains account data associated with each financial account number in the preprocessed transaction data to generate an account set, secondly constructs a plurality of directed node graphs based on the account set, randomly combines the directed node graphs to generate a target mesh graph, and finally performs financial data flow direction analysis on the target mesh graph by using a preset method to generate an analysis result and generates a risk report based on the analysis result. Therefore, by adopting the embodiment of the application, the account set is obtained from the historical transaction data of the financial institution loan, the directed node graph is constructed according to the transaction data among the accounts in the account set, the mesh graph is formed based on the directed node graph, and the financial data flow direction relation analysis is performed on the mesh graph structure through the set algorithm, so that the financial data flow direction situation of each account can be accurately and comprehensively identified, and the risk coefficient of the financial institution loan is reduced.
In order to facilitate understanding of the flow direction identification method of the financial data provided in the embodiment of the present application, the following description is made with reference to fig. 5. As shown in fig. 5, a flow direction identification method for financial data includes:
s201, determining a plurality of transaction financial account numbers;
s202, inquiring the loan amount data of each transaction financial account in the plurality of transaction financial accounts, and determining a risk-free loan account based on the loan amount data of each transaction financial account;
s203, removing the risk-free loan accounts from the multiple transaction financial account numbers to generate a target financial account number set;
s204, collecting fund access information of each target financial account in the target financial account set in a preset time period from a data center of the target financial institution;
s205, performing data cleaning on fund access information of each target financial account within a preset time period to generate preprocessed historical transaction data;
s206, establishing a Bayesian classifier by adopting a Bayesian classification algorithm;
s207, inputting the preprocessed historical transaction data into a Bayesian classifier for identification and classification, and outputting account data associated with each financial account;
s208, determining the account data associated with each financial account number as an account set;
s209, converting each account in the account set into a graph node, and generating a graph node set;
s210, determining the transfer relation among the graph nodes in the graph node set, and determining the transfer relation among the graph nodes as directed edges connected among the graph nodes;
s211, connecting graph nodes in a graph node set according to directed edges connected among the graph nodes to generate a plurality of directed node graphs, and randomly combining the directed node graphs to generate a target mesh graph;
s212, performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result, and generating a risk report based on the analysis result.
In the embodiment of the application, a flow direction identification device of financial data firstly collects and preprocesses historical transaction data of a plurality of financial account numbers, then obtains account data associated with each financial account number in the preprocessed transaction data to generate an account set, secondly constructs a plurality of directed node graphs based on the account set, randomly combines the directed node graphs to generate a target mesh graph, and finally performs financial data flow direction analysis on the target mesh graph by using a preset method to generate an analysis result and generates a risk report based on the analysis result. Therefore, by adopting the embodiment of the application, the account set is obtained from the historical transaction data of the financial institution loan, the directed node graph is constructed according to the transaction data among the accounts in the account set, the mesh graph is formed based on the directed node graph, and the financial data flow direction relation analysis is performed on the mesh graph structure through the set algorithm, so that the financial data flow direction situation of each account can be accurately and comprehensively identified, and the risk coefficient of the financial institution loan is reduced.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
Referring to fig. 6, a schematic structural diagram of a flow direction identification apparatus for financial data according to an exemplary embodiment of the present invention is shown, which is applied to a server. The flow identification system for financial data may be implemented as all or part of the device in software, hardware, or a combination of both. The device 1 comprises a historical transaction data preprocessing module 10, an account set generating module 20, a target mesh map generating module 30 and a risk report generating module 40.
The historical transaction data preprocessing module 10 is used for collecting and preprocessing historical transaction data corresponding to a plurality of financial account numbers;
an account set generating module 20, configured to acquire account data associated with each financial account in the preprocessed transaction data to generate an account set;
a target mesh graph generating module 30, configured to construct a plurality of directed node graphs based on the account set, and generate a target mesh graph after arbitrarily combining the plurality of directed node graphs;
and the risk report generating module 40 is configured to perform financial data flow direction analysis on the target mesh graph by using a preset method to generate an analysis result, and generate a risk report based on the analysis result.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
In the embodiment of the application, a flow direction identification device of financial data firstly collects and preprocesses historical transaction data of a plurality of financial account numbers, then obtains account data associated with each financial account number in the preprocessed transaction data to generate an account set, secondly constructs a plurality of directed node graphs based on the account set, randomly combines the directed node graphs to generate a target mesh graph, and finally performs financial data flow direction analysis on the target mesh graph by using a preset method to generate an analysis result and generates a risk report based on the analysis result. Therefore, by adopting the embodiment of the application, the account set is obtained from the historical transaction data of the financial institution loan, the directed node graph is constructed according to the transaction data among the accounts in the account set, the mesh graph is formed based on the directed node graph, and the financial data flow direction relation analysis is performed on the mesh graph structure through the set algorithm, so that the financial data flow direction situation of each account can be accurately and comprehensively identified, and the risk coefficient of the financial institution loan is reduced.
In one embodiment, an apparatus is presented, the apparatus comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: collecting and preprocessing historical transaction data corresponding to a plurality of financial account numbers; acquiring account data associated with each financial account number in the preprocessed transaction data to generate an account set; constructing a plurality of directed node graphs based on the account set, and generating a target mesh graph after randomly combining the directed node graphs; and performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result, and generating a risk report based on the analysis result.
In one embodiment, when the processor collects and preprocesses historical transaction data corresponding to a plurality of financial account numbers, the following operations are specifically performed: determining a plurality of transaction financial account numbers; inquiring the loan amount data of each transaction financial account in the plurality of transaction financial accounts, and determining a risk-free loan account based on the loan amount data of each transaction financial account; removing the risk-free loan account from the plurality of transaction financial account numbers to generate a target financial account number set; collecting fund access information of each target financial account in the target financial account set within a preset time period from a data center of the target financial institution; and carrying out data cleaning on fund access information of each target financial account in a preset time period to generate preprocessed historical transaction data.
In one embodiment, the processor performs data cleaning on fund access information of each target financial account within a preset time period, and specifically performs the following operations when generating the preprocessed historical transaction data: creating a cache set of incomplete information according to a preset method; inquiring incomplete historical transaction information one by one from fund access information of each target financial account in a preset time period; storing the inquired incomplete history transaction information into an incomplete information cache set to generate cached incomplete history transaction information; and clearing or repairing the cached incomplete historical transaction information to generate processed historical transaction data.
In one embodiment, the processor performs the following operation when acquiring the account data associated with each financial account number in the preprocessed transaction data to generate the account set: establishing a Bayesian classifier by adopting a Bayesian classification algorithm; inputting the preprocessed historical transaction data into a Bayesian classifier for identification and classification, and outputting account data associated with each financial account; determining the account data associated with each of the financial account numbers as a set of accounts.
In one embodiment, the processor builds a plurality of directed node graphs based on the set of accounts, and further performs the following: converting each account in the account set into a graph node, and generating a graph node set; determining transfer relations among all graph nodes in the graph node set, and determining the transfer relations among all the graph nodes as directed edges connected among all the graph nodes; and connecting the graph nodes in the graph node set according to the directed edges connected among the graph nodes to generate a plurality of directed node graphs.
In one embodiment, when the processor performs the financial data flow analysis on the target mesh graph to generate the analysis result, the following operations are specifically performed: adopting a depth-first traversal algorithm of the graph to traverse and inquire whether a closed loop is included from the initial graph node of the target mesh graph one by one; determining that a return of funds has occurred when a closed loop is involved; acquiring transaction amount data and transaction time data corresponding to directed edges contained in the closed loop; calculating the fund backflow proportion and fund backflow period of the fund backflow according to the transaction amount data and the transaction time data corresponding to the directed edge; and determining a risk grade according to the fund return proportion and the fund return period, and determining the risk grade as an analysis result.
In one embodiment, when the processor performs the financial data flow analysis on the target mesh graph to generate the analysis result, the following operations are specifically performed: calculating the edge betweenness of each directed edge in the target mesh graph by adopting a community discovery algorithm of the graph to generate the edge betweenness corresponding to each directed edge; determining a directed edge with the maximum boundary number based on the edge betweenness corresponding to each directed edge; deleting the directed edge with the maximum number of the boundaries to generate a mesh graph after the directed edge is deleted; calculating the corresponding modularity of the mesh graph after the directed edge is deleted; when the modularity is larger than a first threshold and smaller than a second threshold, determining that illegal loan-putting behaviors occur; determining illegal loan-placing behaviors as analysis results; wherein, the first threshold is smaller than the second threshold, and the community discovery algorithm of the graph is GN algorithm.
In the embodiment of the application, a flow direction identification device of financial data firstly collects and preprocesses historical transaction data of a plurality of financial account numbers, then obtains account data associated with each financial account number in the preprocessed transaction data to generate an account set, secondly constructs a plurality of directed node graphs based on the account set, randomly combines the directed node graphs to generate a target mesh graph, and finally performs financial data flow direction analysis on the target mesh graph by using a preset method to generate an analysis result and generates a risk report based on the analysis result. Therefore, by adopting the embodiment of the application, the account set is obtained from the historical transaction data of the financial institution loan, the directed node graph is constructed according to the transaction data among the accounts in the account set, the mesh graph is formed based on the directed node graph, and the financial data flow direction relation analysis is performed on the mesh graph structure through the set algorithm, so that the financial data flow direction situation of each account can be accurately and comprehensively identified, and the risk coefficient of the financial institution loan is reduced.
In one embodiment, a medium is presented having computer-readable instructions stored thereon which, when executed by one or more processors, cause the one or more processors to perform the steps of: collecting and preprocessing historical transaction data corresponding to a plurality of financial account numbers; acquiring account data associated with each financial account number in the preprocessed transaction data to generate an account set; constructing a plurality of directed node graphs based on the account set, and generating a target mesh graph after randomly combining the directed node graphs; and performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result, and generating a risk report based on the analysis result.
In one embodiment, when the processor collects and preprocesses historical transaction data corresponding to a plurality of financial account numbers, the following operations are specifically performed: determining a plurality of transaction financial account numbers; inquiring the loan amount data of each transaction financial account in the plurality of transaction financial accounts, and determining a risk-free loan account based on the loan amount data of each transaction financial account; removing the risk-free loan account from the plurality of transaction financial account numbers to generate a target financial account number set; collecting fund access information of each target financial account in the target financial account set within a preset time period from a data center of the target financial institution; and carrying out data cleaning on fund access information of each target financial account in a preset time period to generate preprocessed historical transaction data.
In one embodiment, the processor performs data cleaning on fund access information of each target financial account within a preset time period, and specifically performs the following operations when generating the preprocessed historical transaction data: creating a cache set of incomplete information according to a preset method; inquiring incomplete historical transaction information one by one from fund access information of each target financial account in a preset time period; storing the inquired incomplete history transaction information into an incomplete information cache set to generate cached incomplete history transaction information; and clearing or repairing the cached incomplete historical transaction information to generate processed historical transaction data.
In one embodiment, the processor performs the following operation when acquiring the account data associated with each financial account number in the preprocessed transaction data to generate the account set: establishing a Bayesian classifier by adopting a Bayesian classification algorithm; inputting the preprocessed historical transaction data into a Bayesian classifier for identification and classification, and outputting account data associated with each financial account; determining the account data associated with each of the financial account numbers as a set of accounts.
In one embodiment, the processor builds a plurality of directed node graphs based on the set of accounts, and further performs the following: converting each account in the account set into a graph node, and generating a graph node set; determining transfer relations among all graph nodes in the graph node set, and determining the transfer relations among all the graph nodes as directed edges connected among all the graph nodes; and connecting the graph nodes in the graph node set according to the directed edges connected among the graph nodes to generate a plurality of directed node graphs.
In one embodiment, when the processor performs the financial data flow analysis on the target mesh graph to generate the analysis result, the following operations are specifically performed: adopting a depth-first traversal algorithm of the graph to traverse and inquire whether a closed loop is included from the initial graph node of the target mesh graph one by one; determining that a return of funds has occurred when a closed loop is involved; acquiring transaction amount data and transaction time data corresponding to directed edges contained in the closed loop; calculating the fund backflow proportion and fund backflow period of the fund backflow according to the transaction amount data and the transaction time data corresponding to the directed edge; and determining a risk grade according to the fund return proportion and the fund return period, and determining the risk grade as an analysis result.
In one embodiment, when the processor performs the financial data flow analysis on the target mesh graph to generate the analysis result, the following operations are specifically performed: calculating the edge betweenness of each directed edge in the target mesh graph by adopting a community discovery algorithm of the graph to generate the edge betweenness corresponding to each directed edge; determining a directed edge with the maximum boundary number based on the edge betweenness corresponding to each directed edge; deleting the directed edge with the maximum number of the boundaries to generate a mesh graph after the directed edge is deleted; calculating the corresponding modularity of the mesh graph after the directed edge is deleted; when the modularity is larger than a first threshold and smaller than a second threshold, determining that illegal loan-putting behaviors occur; determining illegal loan-placing behaviors as analysis results; wherein, the first threshold is smaller than the second threshold, and the community discovery algorithm of the graph is GN algorithm.
In the embodiment of the application, a flow direction identification device of financial data firstly collects and preprocesses historical transaction data of a plurality of financial account numbers, then obtains account data associated with each financial account number in the preprocessed transaction data to generate an account set, secondly constructs a plurality of directed node graphs based on the account set, randomly combines the directed node graphs to generate a target mesh graph, and finally performs financial data flow direction analysis on the target mesh graph by using a preset method to generate an analysis result and generates a risk report based on the analysis result. Therefore, by adopting the embodiment of the application, the account set is obtained from the historical transaction data of the financial institution loan, the directed node graph is constructed according to the transaction data among the accounts in the account set, the mesh graph is formed based on the directed node graph, and the financial data flow direction relation analysis is performed on the mesh graph structure through the set algorithm, so that the financial data flow direction situation of each account can be accurately and comprehensively identified, and the risk coefficient of the financial institution loan is reduced.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer readable medium, and when executed, can include the processes of the embodiments of the methods described above. The medium may be a non-volatile medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for identifying a flow direction of data, the method comprising:
collecting and preprocessing historical transaction data corresponding to a plurality of financial account numbers;
acquiring account data associated with each financial account number in the preprocessed transaction data to generate an account set;
constructing a plurality of directed node graphs based on the account set, and generating a target mesh graph after randomly combining the directed node graphs;
and performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result, and generating a risk report based on the analysis result.
2. The method of claim 1, wherein collecting and pre-processing historical transaction data for a plurality of financial account numbers comprises:
determining a plurality of transaction financial account numbers;
inquiring the loan amount data of each transaction financial account in the plurality of transaction financial accounts, and determining a risk-free loan account based on the loan amount data of each transaction financial account;
removing the risk-free loan account from the plurality of transaction financial account numbers, generating a set of target financial account numbers;
collecting fund access information of each target financial account in the target financial account set within a preset time period from a data center of a target financial institution;
and carrying out data cleaning on the fund access information of each target financial account in a preset time period to generate preprocessed historical transaction data.
3. The method of claim 2, wherein the step of performing data cleaning on the fund access information of each target financial account within a preset time period to generate pre-processed historical transaction data comprises:
creating a cache set of incomplete information according to a preset method;
inquiring incomplete historical transaction information one by one from fund access information of each target financial account in a preset time period;
storing the inquired incomplete history transaction information into the incomplete information cache set to generate cached incomplete history transaction information;
and clearing or repairing the cached incomplete historical transaction information to generate processed historical transaction data.
4. The method of claim 1, wherein the obtaining account data associated with each of the financial account numbers in the pre-processed transaction data to generate a set of accounts comprises:
establishing a Bayesian classifier by adopting a Bayesian classification algorithm;
inputting the preprocessed historical transaction data into the Bayesian classifier for identification and classification, and outputting account data associated with each financial account;
determining the account data associated with each of the financial account numbers as a set of accounts.
5. The method of claim 1, wherein constructing a plurality of directed node graphs based on the set of accounts comprises:
converting each account in the account set into a graph node to generate a graph node set;
determining transfer relations among all graph nodes in the graph node set, and determining the transfer relations among all the graph nodes as directed edges connected among all the graph nodes;
and connecting the graph nodes in the graph node set according to the directed edges connected among the graph nodes to generate a plurality of directed node graphs.
6. The method of claim 1, wherein the performing a financial data flow analysis on the target mesh graph generates analysis results, comprising:
adopting a depth-first traversal algorithm of the graph to traverse and inquire whether a closed loop is included from the initial graph node of the target mesh graph one by one;
determining that a return of funds has occurred when a closed loop is involved;
acquiring transaction amount data and transaction time data corresponding to directed edges contained in the closed loop;
calculating the fund backflow proportion and fund backflow period of the fund backflow according to the transaction amount data and the transaction time data corresponding to the directed edge;
and determining a risk grade according to the fund reflux proportion and the fund reflux period, and determining the risk grade as an analysis result.
7. The method of claim 1, wherein the performing a financial data flow analysis on the target mesh graph generates analysis results, comprising:
calculating the edge betweenness of each directed edge in the target mesh graph by adopting a community discovery algorithm of the graph to generate the edge betweenness corresponding to each directed edge;
determining a directed edge with the maximum boundary number based on the edge betweenness corresponding to each directed edge;
deleting the directed edge with the maximum number of the boundaries to generate a mesh graph with the directed edges deleted;
calculating the corresponding modularity of the mesh graph after the directed edge is deleted;
when the modularity is larger than a first threshold and smaller than a second threshold, determining that illegal loan-putting behaviors occur;
determining the illegal loan-placing behavior as an analysis result; wherein the content of the first and second substances,
the first threshold is less than the second threshold, and the community discovery algorithm of the graph is a GN algorithm.
8. An apparatus for identifying a flow direction of financial data, the apparatus comprising:
the historical transaction data preprocessing module is used for collecting and preprocessing historical transaction data corresponding to a plurality of financial account numbers;
an account set generating module, configured to acquire account data associated with each financial account in the preprocessed transaction data to generate an account set;
a target mesh graph generation module, configured to construct a plurality of directed node graphs based on the account set, and generate a target mesh graph after arbitrarily combining the plurality of directed node graphs;
and the risk report generating module is used for performing financial data flow direction analysis on the target mesh graph by adopting a preset method to generate an analysis result and generating a risk report based on the analysis result.
9. An apparatus comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the flow direction identification method of financial data as claimed in any one of claims 1 to 7.
10. A medium having stored thereon computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of flow direction identification of financial data as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110454435.3A CN113159922A (en) | 2021-04-26 | 2021-04-26 | Data flow direction identification method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110454435.3A CN113159922A (en) | 2021-04-26 | 2021-04-26 | Data flow direction identification method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113159922A true CN113159922A (en) | 2021-07-23 |
Family
ID=76871082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110454435.3A Pending CN113159922A (en) | 2021-04-26 | 2021-04-26 | Data flow direction identification method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159922A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114564525A (en) * | 2022-04-28 | 2022-05-31 | 支付宝(杭州)信息技术有限公司 | Method and device for mining user intention based on user transaction data |
| CN114675942A (en) * | 2022-03-23 | 2022-06-28 | 支付宝(杭州)信息技术有限公司 | Group identification method and system based on dynamic graph |
| CN116109414A (en) * | 2023-02-14 | 2023-05-12 | 中国科学院软件研究所 | Visual layout method of fund transaction Sang Ji diagram based on force action |
| CN116596665A (en) * | 2023-07-19 | 2023-08-15 | 建信金融科技有限责任公司 | Data processing method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232524A (en) * | 2019-06-14 | 2019-09-13 | 哈尔滨哈银消费金融有限责任公司 | Social networks cheats the construction method of model, antifraud method and apparatus |
| CN111476662A (en) * | 2020-04-13 | 2020-07-31 | 中国工商银行股份有限公司 | Anti-money laundering identification method and device |
| 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 |
-
2021
- 2021-04-26 CN CN202110454435.3A patent/CN113159922A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232524A (en) * | 2019-06-14 | 2019-09-13 | 哈尔滨哈银消费金融有限责任公司 | Social networks cheats the construction method of model, antifraud method and apparatus |
| CN111476662A (en) * | 2020-04-13 | 2020-07-31 | 中国工商银行股份有限公司 | Anti-money laundering identification method and device |
| 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 |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114675942A (en) * | 2022-03-23 | 2022-06-28 | 支付宝(杭州)信息技术有限公司 | Group identification method and system based on dynamic graph |
| CN114564525A (en) * | 2022-04-28 | 2022-05-31 | 支付宝(杭州)信息技术有限公司 | Method and device for mining user intention based on user transaction data |
| CN116109414A (en) * | 2023-02-14 | 2023-05-12 | 中国科学院软件研究所 | Visual layout method of fund transaction Sang Ji diagram based on force action |
| CN116109414B (en) * | 2023-02-14 | 2023-10-24 | 中国科学院软件研究所 | Visual layout method of fund transaction Sang Ji diagram based on force action |
| CN116596665A (en) * | 2023-07-19 | 2023-08-15 | 建信金融科技有限责任公司 | Data processing method, device, equipment and storage medium |
| CN116596665B (en) * | 2023-07-19 | 2023-10-20 | 建信金融科技有限责任公司 | Data processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220405860A1 (en) | Artificial intelligence transaction risk scoring and anomaly detection | |
| CN110009174B (en) | Risk recognition model training method and device and server | |
| CN113159922A (en) | Data flow direction identification method, device, equipment and medium | |
| WO2018103456A1 (en) | Method and apparatus for grouping communities on the basis of feature matching network, and electronic device | |
| CN109191226B (en) | Risk control method and device | |
| US20160364794A1 (en) | Scoring transactional fraud using features of transaction payment relationship graphs | |
| US20210182859A1 (en) | System And Method For Modifying An Existing Anti-Money Laundering Rule By Reducing False Alerts | |
| CN110020866B (en) | Training method and device for recognition model and electronic equipment | |
| CN111444232A (en) | Method for mining digital currency exchange address and storage medium | |
| CN113689218A (en) | Risk account identification method and device, computer equipment and storage medium | |
| CN116307671A (en) | Risk early warning method, risk early warning device, computer equipment and storage medium | |
| CN113792089B (en) | Illegal behavior detection method, device, equipment and medium based on artificial intelligence | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| US20210397905A1 (en) | Classification system | |
| CN111311420A (en) | Business data pushing method and device | |
| CN113487109B (en) | Group identification method, group identification device, electronic equipment and storage medium | |
| CN108446907B (en) | Safety verification method and device | |
| CN112991079B (en) | Multi-card co-occurrence medical treatment fraud detection method, system, cloud end and medium | |
| CN113537960A (en) | Method, device and equipment for determining abnormal resource transfer link | |
| CN113094595A (en) | Object recognition method, device, computer system and readable storage medium | |
| Caplescu et al. | Will they repay their debt? Identification of borrowers likely to be charged off | |
| CN111652718A (en) | Method, device, equipment and medium for monitoring value flow direction based on relational network diagram | |
| KR100686466B1 (en) | System and method for valuing loan portfolios using fuzzy clustering | |
| Pal et al. | Application of data mining techniques in health fraud detection | |
| CN114978616B (en) | Construction method and device of risk assessment system, and risk assessment method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40051213 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |