Method and apparatus for screening data of suspicious money laundering based on cyclic transfer

Abstract

The application provides a suspicious money laundering behavior data screening method and device based on a circulating transfer, the method comprising: obtaining to-be-screened transfer data of a target account; the to-be-screened transfer data comprises transfer data having a direct or indirect transfer relationship with the target account; confirming whether there is circulating transfer data in the to-be-screened transfer data, wherein the circulating transfer data is transfer data constituting a closed loop; in the case that it is determined that there is circulating transfer data in the to-be-screened transfer data, the to-be-screened transfer data of the target account is determined as suspicious money laundering behavior data, and data possibly having money laundering behavior can be screened out from mass transfer record data, so that the target range is reduced, the data characteristics are increased when the method is applied to an existing anti-money laundering model, and the anti-money laundering process is more stable and efficient.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and apparatus for screening suspicious money laundering data based on circular transfers. Background Technology

[0002] Money laundering refers to the act of disguising and cleaning up the source and nature of illicit money through financial institutions such as commercial banks, investment banks, and insurance companies, thereby legitimizing illegal proceeds. Money laundering poses a serious threat to almost all countries, not only because it involves huge sums of money, can severely damage a country's financial system, and fuels other types of crime, but also because its complex structure and rapid development make anti-money laundering monitoring extremely difficult.

[0003] Money laundering is generally characterized by diverse methods, complex processes, specific targets, and international reach. Research into numerous money laundering cases both domestically and internationally has revealed that while money laundering may appear complex on the surface, its purpose is clear: it typically begins by transferring large sums of illicit cash from one or a few accounts, then proceeds through intricate transfers and transactions. Regardless of the complexity of the process, the funds ultimately converge on one or a few target accounts, forming a closed loop. This distinctive characteristic provides crucial clues for identifying suspicious financial transaction paths.

[0004] Currently, there are two main methods for identifying money laundering: rule-based methods and machine learning. Rule-based methods primarily extract suspicious data by defining indicators. Machine learning methods classify data by extracting features. Both methods require defining indicators and features for judgment. Common indicators include: frequent short-term fund inflows and outflows accompanied by sensitive keywords; frequent short-term transfers between offshore and domestic accounts; concentrated and dispersed short-term fund outflows; and short-term fund inflows and outflows with the same individual.

[0005] However, traditional data preprocessing only filters the transfer amount and time, leaving a large number of invalid records after processing, resulting in low screening efficiency. Traditional machine learning models are prone to underfitting due to the large amount of data, with too many invalid records and low resource utilization. Current methods still struggle to identify transactions that are time-consuming, involve small transfer amounts, or have too many transfer nodes.

[0006] Therefore, how to provide a screening scheme for suspicious money laundering data, which can filter out data that may involve money laundering from massive amounts of transfer records, thereby narrowing down the target range, is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0007] This invention provides a method and apparatus for filtering suspicious money laundering data based on circular transfers, which can filter out data that may involve money laundering from massive amounts of transfer record data, thereby narrowing down the target range.

[0008] In a first aspect, embodiments of the present invention provide a method for filtering suspicious money laundering data based on circular transfers, including:

[0009] Obtain the transfer data to be filtered for the target account; the transfer data to be filtered includes transfer data that has a direct or indirect transfer relationship with the target account;

[0010] Confirm whether there is any circular transfer data in the transfer data to be screened, wherein the circular transfer data is transfer data that forms a closed loop;

[0011] If it is determined that there are circular transfer data in the transfer data to be screened, the transfer data of the target account to be screened will be identified as suspicious money laundering data.

[0012] In one embodiment, obtaining the transfer data to be filtered for the target account includes:

[0013] Obtain the original transfer record data;

[0014] Identify a second target account in the original transfer record that has a direct or indirect transfer relationship with the target account;

[0015] The transfer data of the target account and the transfer data of the second target account are determined as the transfer data to be screened.

[0016] In one embodiment, confirming whether circular transfer data exists in the transfer data to be filtered includes:

[0017] The data to be filtered for transfers is stored in a Hive database;

[0018] A directed graph is constructed using an adjacency list for the transfer data to be filtered, and the width of the adjacency list is compressed to make the data more compact.

[0019] In the directed graph, search sequentially for closed loops with transfer lengths from M to N; where M is a positive integer and N is an integer greater than M.

[0020] In one embodiment, the step of sequentially searching the directed graph for closed loops with lengths from M to N includes:

[0021] A1: Start searching from the root node of the directed graph, and set the node root = Graph[id], where the variable id is initially 0;

[0022] A2: Using node Graph[id] as the root node, perform the first DFS search with a step size of (NM) / 2+1, and record the nodes visited;

[0023] A3: The second DFS search is performed with a step size of m. The current node is filtered to find a closed loop of length m, and the circular transfer data is obtained; where the initial value of m is M.

[0024] A4: Increment the current m by 1 to update m, and jump to step A3 until m == N;

[0025] A5: Increment the current id by 1 to update the id, jump to step A2, until the value of id is equal to the size value of the directed graph;

[0026] A6: The obtained circular transfer data is identified as suspicious money laundering data.

[0027] In one embodiment, determining the target account's transfer data as suspicious money laundering data when it is determined that circular transfer data exists in the transfer data to be screened includes:

[0028] If it is determined that there are circular transfer data in the transfer data to be screened, the transfer data of the target account to be screened is added to the database of suspicious money laundering activities.

[0029] Add a flag indicating suspicious money laundering activity to the target account.

[0030] Secondly, embodiments of the present invention provide a data screening device for suspicious money laundering behavior based on circular transfers, comprising:

[0031] The data acquisition module is used to acquire the transfer data to be screened for the target account; the transfer data to be screened includes transfer data that has a direct or indirect transfer relationship with the target account;

[0032] The loop confirmation module is used to confirm whether there is loop transfer data in the transfer data to be screened, wherein the loop transfer data is transfer data that forms a closed loop;

[0033] The suspicious activity determination module is used to determine the transfer data of the target account as suspicious money laundering data when it is determined that there is circular transfer data in the transfer data to be screened.

[0034] In one embodiment, the data acquisition module includes:

[0035] The raw data acquisition unit is used to acquire raw transfer record data;

[0036] An account determination unit is used to determine, from the original transfer record, a second target account that has a direct or indirect transfer relationship with the target account;

[0037] The data determination unit is used to determine the transfer data of the target account and the transfer data of the second target account as the transfer data to be screened.

[0038] In one embodiment, the cyclic confirmation module includes:

[0039] A data storage unit is used to store the transfer data to be filtered into a Hive database;

[0040] A directed graph construction unit is used to construct a directed graph from the transfer data to be filtered using an adjacency list, and to compress the width of the adjacency list to make the data more compact.

[0041] The closed-loop search unit is used to sequentially search the directed graph for closed loops with transfer lengths from M to N; where M is a positive integer and N is an integer greater than M.

[0042] In one embodiment, the closed-loop lookup unit includes:

[0043] The first subunit is used to implement step A1: starting from the root node of the directed graph, set the node root = Graph[id], where the variable id is initially 0;

[0044] The second subunit is used to implement step A2: with node Graph[id] as the root node, perform a first DFS search with a step size of (NM) / 2+1, and record the nodes visited;

[0045] The third subunit is used to implement step A3: the second DFS search is performed with a step size of m, the current node is filtered, and a closed loop of length m is found to obtain the cyclic transfer data; where the initial value of m is M.

[0046] The fourth subunit is used to implement step A4: update m by incrementing the current m by 1, and jump to step A3 until m == N;

[0047] The fifth subunit is used to implement step A5: update the current id by incrementing it by 1, jump to step A2, until the value of id is equal to the size value of the directed graph;

[0048] The sixth subunit is used to implement step A6: identifying the obtained circular transfer data as suspicious money laundering data.

[0049] In one embodiment, the suspicious identification module includes:

[0050] The data adding unit is used to add the target account's transfer data to the suspicious money laundering behavior database when it is determined that there is circular transfer data in the transfer data to be screened.

[0051] An account tagging unit is used to add a suspicious money laundering activity tag to the target account.

[0052] Thirdly, the present invention provides an electronic device, including a memory and a memory storing a computer program, wherein the processor executes the program to implement the steps of the suspicious money laundering behavior data screening method based on circular transfers described in the first aspect.

[0053] Fourthly, the present invention provides a processor-readable storage medium storing a computer program for causing the processor to perform the steps of the data screening method for suspicious money laundering activities based on circular transfers described in the first aspect.

[0054] This invention provides a method and apparatus for screening suspicious money laundering data based on circular transfers. By identifying circular transfer data (transfers forming a closed loop) within the data to be screened, the method identifies the target account's transfer data as suspicious money laundering data. This approach can filter out potentially money laundering data from massive amounts of transfer records, thereby narrowing down the target scope. When applied to existing anti-money laundering models, this method enhances data features and makes the anti-money laundering process more stable and efficient. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0056] Figure 1 A flowchart illustrating a method for screening suspicious money laundering data based on revolving transfers, provided in an embodiment of the present invention;

[0057] Figure 2 This is a second flowchart illustrating a method for screening suspicious money laundering data based on revolving transfers, provided by an embodiment of the present invention.

[0058] Figure 3 This is a schematic diagram of the composition structure of a suspicious money laundering behavior data screening device based on circular transfers provided in an embodiment of the present invention;

[0059] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0061] The following is combined Figures 1-2 This invention describes a data screening method for suspicious money laundering activities based on circular transfers.

[0062] Figure 1 This is one of the flowcharts illustrating a method for screening suspicious money laundering data based on revolving transfers, provided by an embodiment of the present invention. Figure 2 This is the second flowchart illustrating a method for screening suspicious money laundering data based on revolving transfers, provided in an embodiment of the present invention.

[0063] In one specific embodiment of the present invention, an embodiment of the present invention provides a method for filtering suspicious money laundering behavior data based on circular transfers, including:

[0064] Step 110: Obtain the transfer data to be filtered for the target account; the transfer data to be filtered includes transfer data that has a direct or indirect transfer relationship with the target account;

[0065] In one embodiment, the original transfer record data can be obtained first; a second target account with a direct or indirect transfer relationship with the target account can be identified from the original transfer records; and the transfer data of the target account and the transfer data of the second target account can be identified as transfer data to be screened.

[0066] For example, transfer records can be searched within a bank. For transfers within the same bank, the data can be retrieved directly from the bank's server. For transfers between different banks, data can be accessed from each bank, thus achieving a more comprehensive collection of transfer data. Furthermore, the transfer data for the target account is divided into incoming and outgoing data, which can be collected separately.

[0067] Step 120: Confirm whether there is circular transfer data in the transfer data to be screened, wherein the circular transfer data is transfer data that forms a closed loop;

[0068] In one embodiment, the transfer data to be filtered is stored in a Hive database; a directed graph is constructed for the transfer data to be filtered using an adjacency list, and the width of the adjacency list is compressed to make the data compact; the directed graph is searched sequentially for closed loops with transfer lengths from M to N; where M is a positive integer and N is an integer greater than M.

[0069] Specifically, the search is primarily performed using bidirectional Depth-First Search (DFS). Because in transaction flows, the in-degree and out-degree of individual nodes are relatively large (generally exceeding 10 or even more), traditional DFS methods experience an exponential increase in the number of nodes with increasing depth, resulting in significant time consumption. Bidirectional DFS, through upward and downward binary search and concatenation, filters out a large number of invalid nodes, significantly improving search efficiency. It also compresses the adjacency list width, making it more uniform and compact, which optimizes the cache line and accelerates read and write operations. The time to find a closed loop on tens of millions of data points is in the seconds range.

[0070] Step 130: If it is determined that there is circular transfer data in the transfer data to be screened, the transfer data to be screened for the target account is identified as suspicious money laundering data.

[0071] Specifically, in one embodiment, in order to find data that may indicate money laundering activity, the following steps may be performed:

[0072] A1: Start searching from the root node of the directed graph, and set the node root = Graph[id], where the variable id is initially 0;

[0073] A2: Using node Graph[id] as the root node, perform the first DFS search with a step size of (NM) / 2+1, and record the nodes visited;

[0074] A3: The second DFS search is performed with a step size of m. The current node is filtered to find a closed loop of length m, and the circular transfer data is obtained; where the initial value of m is M.

[0075] A4: Increment the current m by 1 to update m, and jump to step A3 until m == N;

[0076] A5: Increment the current id by 1 to update the id, jump to step A2, until the value of id is equal to the size value of the directed graph;

[0077] A6: The obtained circular transfer data is identified as suspicious money laundering data.

[0078] Specifically, first, the transfer records are stored in a Hive database. The length range of a circular transfer is set to [M, N], and the variable m is initialized to M. A directed graph Graph is constructed using an adjacency list, and the adjacency list width is compressed to make the data compact. A search for circular transfer records is performed, with the variable id initialized to 0. Let root = Graph[id], and using root as the root node, perform a DFS upwards with a step size of (NM) / 2 + 1. Record the nodes visited, and set visitPre[node.id] = true. Perform a DFS downwards with a step size of m, filtering the current node based on visitPre[node.id] == true, searching for cycles of length m, i.e., circular transfer records. Then m++, jump to step 7, until m == N. id++, jump to step 5, until id equals Graph.size. The calculated result, i.e., the circular transfer record, is written to the database.

[0079] In this embodiment of the invention, a dual-loop technique is adopted, in which both id and m are gradually incremented by 1 to update the data. This allows for the traversal of any suspicious money laundering behavior data that may constitute circular transfer data, narrowing the target range. When applied to existing anti-money laundering models, this technique adds data features and makes the anti-money laundering process more stable and efficient.

[0080] Hive is a database used in data warehouse tools for data extraction, transformation, and loading. It's a mechanism for storing, querying, and analyzing large-scale data stored in a database. Hive data warehouse tools can map structured data files to a database table and provide query functionality. Hive's advantages include a low learning curve and the ability to perform rapid statistical analysis using SQL-like statements.

[0081] In another embodiment of the present invention, after determining that circular transfer data exists in the transfer data to be screened, the transfer data to be screened for the target account can be added to the suspicious money laundering behavior database; a suspicious money laundering behavior flag is added to the target account. This facilitates subsequent monitoring and further investigation of accounts suspected of money laundering.

[0082] This invention provides a method and apparatus for screening suspicious money laundering data based on circular transfers. By identifying circular transfer data (transfer data forming a closed loop) within the transfer data to be screened, the method identifies the target account's transfer data as suspicious money laundering data. This approach can filter out potentially money laundering data from massive amounts of transfer records, thereby narrowing down the target scope. When applied to existing anti-money laundering models, this method enhances data features and makes the anti-money laundering process more stable and efficient.

[0083] The following describes the suspicious money laundering data screening device based on revolving transfers provided by the present invention. The suspicious money laundering data screening device based on revolving transfers described below can be referred to in correspondence with the suspicious money laundering data screening method based on revolving transfers described above.

[0084] Figure 3 This is a schematic diagram of the composition structure of a suspicious money laundering behavior data screening device based on circular transfers, provided in an embodiment of the present invention.

[0085] In another specific embodiment of the present invention, an embodiment of the present invention provides a data screening device 300 for suspicious money laundering behavior based on circular transfers, comprising:

[0086] The data acquisition module 310 is used to acquire the transfer data to be screened for the target account; the transfer data to be screened includes transfer data that has a direct or indirect transfer relationship with the target account;

[0087] The loop confirmation module 320 is used to confirm whether there is loop transfer data in the transfer data to be screened, wherein the loop transfer data is transfer data that forms a closed loop;

[0088] The suspicious identification module 330 is used to identify the transfer data of the target account as suspicious money laundering data when it is determined that there is circular transfer data in the transfer data to be screened.

[0089] In one embodiment, the data acquisition module includes:

[0090] The raw data acquisition unit is used to acquire raw transfer record data;

[0091] An account determination unit is used to determine, from the original transfer record, a second target account that has a direct or indirect transfer relationship with the target account;

[0092] The data determination unit is used to determine the transfer data of the target account and the transfer data of the second target account as the transfer data to be screened.

[0093] In one embodiment, the cyclic confirmation module includes:

[0094] A data storage unit is used to store the transfer data to be filtered into a Hive database;

[0095] A directed graph construction unit is used to construct a directed graph from the transfer data to be filtered using an adjacency list, and to compress the width of the adjacency list to make the data more compact.

[0096] The closed-loop search unit is used to sequentially search the directed graph for closed loops with transfer lengths from M to N; where M is a positive integer and N is an integer greater than M.

[0097] In one embodiment, the closed-loop lookup unit includes:

[0098] The first subunit is used to implement step A1: starting from the root node of the directed graph, set the node root = Graph[id], where the variable id is initially 0;

[0099] The second subunit is used to implement step A2: with node Graph[id] as the root node, perform a first DFS search with a step size of (NM) / 2+1, and record the nodes visited;

[0100] The third subunit is used to implement step A3: the second DFS search is performed with a step size of m, the current node is filtered, and a closed loop of length m is found to obtain the cyclic transfer data; where the initial value of m is M.

[0101] The fourth subunit is used to implement step A4: update m by incrementing the current m by 1, and jump to step A3 until m == N;

[0102] The fifth subunit is used to implement step A5: update the current id by incrementing it by 1, jump to step A2, until the value of id is equal to the size value of the directed graph;

[0103] The sixth subunit is used to implement step A6: identifying the obtained circular transfer data as suspicious money laundering data.

[0104] In one embodiment, the suspicious identification module includes:

[0105] The data adding unit is used to add the target account's transfer data to the suspicious money laundering behavior database when it is determined that there is circular transfer data in the transfer data to be screened.

[0106] An account tagging unit is used to add a suspicious money laundering activity tag to the target account.

[0107] This invention provides a suspicious money laundering behavior data screening device based on circular transfers. By identifying circular transfer data (transfer data forming a closed loop) in the transfer data to be screened, the device identifies the transfer data of the target account as suspicious money laundering behavior data. This device can filter out potentially money laundering data from massive amounts of transfer records, thereby narrowing down the target range. When applied to existing anti-money laundering models, it adds data features and makes the anti-money laundering process more stable and efficient.

[0108] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 can call a computer program in the memory 430 to execute steps of a data screening method for suspicious money laundering activities based on circular transfers, such as including:

[0109] Obtain the transfer data to be filtered for the target account; the transfer data to be filtered includes transfer data that has a direct or indirect transfer relationship with the target account;

[0110] Confirm whether there is any circular transfer data in the transfer data to be screened, wherein the circular transfer data is transfer data that forms a closed loop;

[0111] If it is determined that there are circular transfer data in the transfer data to be screened, the transfer data of the target account to be screened will be identified as suspicious money laundering data.

[0112] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0113] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the data screening method for suspicious money laundering behavior based on circular transfers provided by the above methods, the method comprising:

[0114] Obtain the transfer data to be filtered for the target account; the transfer data to be filtered includes transfer data that has a direct or indirect transfer relationship with the target account;

[0115] Confirm whether there is any circular transfer data in the transfer data to be screened, wherein the circular transfer data is transfer data that forms a closed loop;

[0116] If it is determined that there are circular transfer data in the transfer data to be screened, the transfer data of the target account to be screened will be identified as suspicious money laundering data.

[0117] On the other hand, embodiments of this application also provide a processor-readable storage medium storing a computer program for causing the processor to execute the suspicious money laundering data screening method based on circular transfers provided in the above embodiments, for example including:

[0118] Obtain the transfer data to be filtered for the target account; the transfer data to be filtered includes transfer data that has a direct or indirect transfer relationship with the target account;

[0119] Confirm whether there is any circular transfer data in the transfer data to be screened, wherein the circular transfer data is transfer data that forms a closed loop;

[0120] If it is determined that there are circular transfer data in the transfer data to be screened, the transfer data of the target account to be screened will be identified as suspicious money laundering data.

[0121] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0122] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0123] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for screening suspicious money laundering data based on circular transfers, characterized in that, include: Obtain the transfer data to be filtered for the target account; The transfer data to be screened includes transfer data that has a direct or indirect transfer relationship with the target account; Confirm whether there is any circular transfer data in the transfer data to be screened, wherein the circular transfer data is transfer data that forms a closed loop; If it is determined that there are circular transfer data in the transfer data to be screened, the transfer data to be screened for the target account will be identified as suspicious money laundering data. The step of confirming whether there is circular transfer data in the transfer data to be filtered includes: The data to be filtered for transfers is stored in a Hive database; A directed graph is constructed using an adjacency list for the transfer data to be filtered, and the width of the adjacency list is compressed to make the data more compact. In the directed graph, search sequentially for closed cycles with transfer lengths from M to N; where M is a positive integer and N is an integer greater than M. The step of sequentially searching the directed graph for closed loops with lengths from M to N includes: A1: Start searching from the root node of the directed graph, and set the node root = Graph[id], where the variable id is initially 0; A2: Using node Graph[id] as the root node, perform the first DFS search with a step size of (NM) / 2+1, and record the nodes visited; A3: The second DFS search is performed with a step size of m. The current node is filtered to find a closed loop of length m, and the circular transfer data is obtained; where the initial value of m is M. A4: Increment the current m by 1 to update m, and jump to step A3 until m == N; A5: Increment the current id by 1 to update the id, jump to step A2, until the value of id is equal to the size value of the directed graph; A6: The obtained circular transfer data is identified as suspicious money laundering data.

2. The method for filtering suspicious money laundering data based on circular transfers according to claim 1, characterized in that, The process of obtaining the transfer data to be filtered for the target account includes: Obtain the original transfer record data; Identify a second target account in the original transfer record that has a direct or indirect transfer relationship with the target account; The transfer data of the target account and the transfer data of the second target account are determined as the transfer data to be screened.

3. The method for filtering suspicious money laundering data based on circular transfers according to claim 1, characterized in that, The step of identifying the target account's transfer data as suspicious money laundering data when it is determined that there is circular transfer data in the transfer data to be screened includes: If it is determined that there are circular transfer data in the transfer data to be screened, the transfer data of the target account to be screened is added to the database of suspicious money laundering activities. Add a flag indicating suspicious money laundering activity to the target account.

4. A data screening device for suspicious money laundering behavior based on circular transfers, characterized in that, include: The data acquisition module is used to acquire the transfer data to be filtered for the target account; The transfer data to be screened includes transfer data that has a direct or indirect transfer relationship with the target account; The loop confirmation module is used to confirm whether there is loop transfer data in the transfer data to be screened, wherein the loop transfer data is transfer data that forms a closed loop; The suspicious activity determination module is used to determine the target account's transfer data as suspicious money laundering data when it is determined that there is circular transfer data in the transfer data to be screened; The cyclic confirmation module includes: A data storage unit is used to store the transfer data to be filtered into a Hive database; A directed graph construction unit is used to construct a directed graph from the transfer data to be filtered using an adjacency list, and to compress the width of the adjacency list to make the data more compact. The closed-loop search unit is used to sequentially search the directed graph for closed loops with transfer lengths from M to N; where M is a positive integer and N is an integer greater than M. The step of sequentially searching the directed graph for closed loops with lengths from M to N includes: A1: Start searching from the root node of the directed graph, and set the node root = Graph[id], where the variable id is initially 0; A2: Using node Graph[id] as the root node, perform the first DFS search with a step size of (NM) / 2+1, and record the nodes visited; A3: The second DFS search is performed with a step size of m. The current node is filtered to find a closed loop of length m, and the circular transfer data is obtained; where the initial value of m is M. A4: Increment the current m by 1 to update m, and jump to step A3 until m == N; A5: Increment the current id by 1 to update the id, jump to step A2, until the value of id is equal to the size value of the directed graph; A6: The obtained circular transfer data is identified as suspicious money laundering data.

5. The suspicious money laundering behavior data screening device based on circular transfers according to claim 4, characterized in that, The data acquisition module includes: The raw data acquisition unit is used to acquire raw transfer record data; An account determination unit is used to determine, from the original transfer record, a second target account that has a direct or indirect transfer relationship with the target account; The data determination unit is used to determine the transfer data of the target account and the transfer data of the second target account as the transfer data to be screened.

6. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the suspicious money laundering data screening method based on circular transfers as described in any one of claims 1 to 3.

7. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program for causing the processor to perform the steps of the suspicious money laundering data screening method based on circular transfers as described in any one of claims 1 to 3.

Images