CN113537960A - Method, device and equipment for determining abnormal resource transfer link - Google Patents
Method, device and equipment for determining abnormal resource transfer link Download PDFInfo
- Publication number
- CN113537960A CN113537960A CN202110811722.5A CN202110811722A CN113537960A CN 113537960 A CN113537960 A CN 113537960A CN 202110811722 A CN202110811722 A CN 202110811722A CN 113537960 A CN113537960 A CN 113537960A
- Authority
- CN
- China
- Prior art keywords
- account
- resource transfer
- network
- node
- sub
- 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
- 238000012546 transfer Methods 0.000 title claims abstract description 185
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000007781 pre-processing Methods 0.000 claims abstract description 27
- 238000010845 search algorithm Methods 0.000 claims abstract description 26
- 238000013138 pruning Methods 0.000 claims abstract description 23
- 238000005520 cutting process Methods 0.000 claims abstract description 16
- 238000003860 storage Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 7
- 230000000977 initiatory effect Effects 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 239000000047 product Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000003999 initiator Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000007704 transition 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/085—Payment architectures involving remote charge determination or related payment systems
- G06Q20/0855—Payment architectures involving remote charge determination or related payment systems involving a third party
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the specification provides a method, a device and equipment for determining an abnormal resource transfer link, and relates to the technical field of big data, wherein the method comprises the following steps: acquiring a resource transfer information set in a target time period; constructing an account relation network based on the resource transfer information set; the account relation network is used for representing the resource transfer relation among the accounts; preprocessing the account relation network to obtain a plurality of sub-networks; the pretreatment comprises the following steps: network pruning and network cutting; searching each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; the initial account of the abnormal resource transfer link is a credit account, and the final account is a forbidden account. In the embodiment of the description, the resource transfer link can be efficiently tracked and analyzed by using the account relation network in combination with the network pruning, the preprocessing and the heuristic search algorithm, so that the abnormal resource transfer link can be accurately determined.
Description
Technical Field
The embodiment of the specification relates to the technical field of big data, in particular to a method, a device and equipment for determining an abnormal resource transfer link.
Background
With the rapid development of internet finance, various online financing products are released by banks in disputes so as to promote the economic development of small, medium and small and individual entities. The product has the characteristics of 'no need of mortgage, convenience, high efficiency, flexible use' and the like, so that the loan is more convenient. But the method brings new risks, and a small and tiny individual household does not use the money which is credited for production and management, but uses the money which is credited for the forbidden fields of investment, financing, securities, real estate, P2P and the like, and needs to be supervised. Usually, the borrower avoids bank monitoring, and can flow to the forbidden field after being associated with friends, relatives and the like for multiple circulation, so that the transaction link is too long and tracking difficulty is high.
In the prior art, the transaction link is usually analyzed by using an SQL (structured query language) analysis technology through multiple associations, but a cartesian product is generated in the operation by using an SQL direct association method, which increases the amount of calculation data in a square form and has low calculation efficiency. Iterative computation of hundreds of millions or even billions of transaction details can result in memory overflow and failure to execute. Therefore, the abnormal transaction link cannot be efficiently identified by adopting the technical scheme in the prior art.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the specification provides a method, a device and equipment for determining an abnormal resource transfer link, so as to solve the problem that an abnormal transaction link cannot be efficiently identified in the prior art.
An embodiment of the present specification provides a method for determining an abnormal resource transfer link, including: acquiring a resource transfer information set in a target time period; constructing an account relation network based on the resource transfer information set; wherein, the account relation network is used for characterizing the resource transfer relation between accounts; preprocessing the account relation network to obtain a plurality of sub-networks; wherein the pre-processing comprises: network pruning and network cutting; searching each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; and the starting account of the abnormal resource transfer link is a credit account, and the terminating account is a forbidden account.
An embodiment of the present specification further provides a device for determining an abnormal resource transfer link, including: the acquisition module is used for acquiring a resource transfer information set in a target time period; the construction module is used for constructing an account relation network based on the resource transfer information set; wherein, the account relation network is used for characterizing the resource transfer relation between accounts; the preprocessing module is used for preprocessing the account relation network to obtain a plurality of sub-networks; wherein the pre-processing comprises: network pruning and network cutting; the processing module is used for searching each sub-network by utilizing a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; and the starting account of the abnormal resource transfer link is a credit account, and the terminating account is a forbidden account.
The embodiment of the present specification further provides an apparatus for determining an abnormal resource transfer link, including a processor and a memory for storing processor-executable instructions, where the processor executes the instructions to implement the steps of any one of the method embodiments in the embodiments of the present specification.
The present specification embodiments also provide a computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of any one of the method embodiments of the specification embodiments.
The embodiment of the specification provides a method for determining an abnormal resource transfer link, which can construct an account relation network based on an acquired resource transfer information set in a target time period, wherein the account relation network is used for representing a resource transfer relation between accounts. Since the account relationship network may be complex and may have redundant information, the account relationship network may be preprocessed to obtain a plurality of sub-networks, where the preprocessing may include: and network pruning and network cutting are performed, so that an effective sub-network can be extracted from the initial account relation network under the condition of large data scale, and the data processing amount is effectively reduced. Furthermore, each sub-network can be searched by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network, wherein an initial account of the abnormal resource transfer link is a credited account, and a terminating account of the abnormal resource transfer link is an prohibited account. The heuristic search algorithm is utilized to search each sub-network, the starting point of the sub-network is taken as the center, the vertex with the shortest sum of the distance starting point and the forbidden account node path is preferentially selected to be searched and traversed, blind search is not carried out, unnecessary search can be effectively avoided, and the calculation efficiency is improved. Therefore, the resource transfer link can be efficiently tracked and analyzed by using the account relation network in combination with the network pruning, preprocessing and heuristic search algorithm, and the abnormal resource transfer link can be accurately determined.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the disclosure, are incorporated in and constitute a part of this specification, and are not intended to limit the embodiments of the disclosure. In the drawings:
fig. 1 is a schematic diagram illustrating steps of a method for determining an abnormal resource transfer link according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of an account relationship network provided in accordance with an embodiment of the present description;
FIG. 3 is a schematic diagram illustrating comparison of pre-and post-effects of pruning, cutting and sub-network screening on an account relationship network according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram illustrating comparison of the effects of a breadth-first traversal strategy and a heuristic search algorithm provided in accordance with an embodiment of the present description;
fig. 5 is a schematic structural diagram of an apparatus for determining an abnormal resource transfer link according to an embodiment of the present specification;
fig. 6 is a schematic structural diagram of a determination device for an abnormal resource transfer link according to an embodiment of the present specification.
Detailed Description
The principles and spirit of the embodiments of the present specification will be described with reference to a number of exemplary embodiments. It should be understood that these embodiments are presented merely to enable those skilled in the art to better understand and to implement the embodiments of the present description, and are not intended to limit the scope of the embodiments of the present description in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As will be appreciated by one skilled in the art, implementations of the embodiments of the present description may be embodied as a system, an apparatus, a method, or a computer program product. Therefore, the disclosure of the embodiments of the present specification can be embodied in the following forms: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or a combination of hardware and software.
Although the flow described below includes operations that occur in a particular order, it should be appreciated that the processes may include more or less operations that are performed sequentially or in parallel (e.g., using parallel processors or a multi-threaded environment).
Referring to fig. 1, the present embodiment may provide a method for determining an abnormal resource transfer link. The method for determining the abnormal resource transfer link can be used for efficiently tracking and analyzing the resource transfer link by using an account relation network in combination with network pruning, preprocessing and a heuristic search algorithm. The method for determining the abnormal resource transfer link may include the following steps.
S101: and acquiring a resource transfer information set in the target time period.
In this embodiment, the resource transfer information of all users recorded by the target mechanism in the target time period may be acquired, so as to obtain the resource transfer information set in the target time period. The resource transfer information set may include a plurality of pieces of resource transfer information, and each piece of resource transfer information may include information on an account of a resource transfer initiator, information on an account of a resource transfer receiver, a resource transfer amount, resource transfer information, and the like. It is understood that the resource transfer information may also include other information, such as: the attribute of the transferred resource, the attribute of the account, the remark information, and the like may be determined according to the actual situation, and this is not limited in the embodiments of the present specification.
In this embodiment, the resources may include: virtual currency, account funds, gold, real estate and other fixed assets, and the like. The resource transfer information may be used to represent resource transfer conditions between users, between a user and a third-party user, or between third-party users, and in some embodiments, the resource transfer may include: transfer accounts, borrow, repay, purchase financing products, etc. The specific situation can be determined according to actual situations, and the embodiment of the present specification does not limit the specific situation.
In this embodiment, the resource migration information set may be recorded in the form of a text, a table, or the like. Of course, the manner of recording the resource transfer information set is not limited to the above example, and other modifications may be made by those skilled in the art within the spirit of the embodiments of the present disclosure, but the function and effect achieved by the embodiments of the present disclosure are all covered by the scope of the embodiments of the present disclosure.
In this embodiment, the target time period may be the last month, the last year, or a specified time period, which may be determined as needed, and is not limited in this embodiment of the present disclosure.
S102: constructing an account relation network based on the resource transfer information set; the account relation network is used for representing the resource transfer relation between the accounts.
In this embodiment, a plurality of groups of data may be extracted from the resource transfer information set to obtain a point-edge file, where each group of data may include: the point-edge file can be used for constructing a mesh relationship network formed by an entity-relationship-entity triple, and converting the independent data into a structured knowledge association database so as to construct and obtain the account relationship network. The account relation network is used for representing the resource transfer relation between the accounts.
In this embodiment, the account relationship network may include a plurality of nodes (entities), each node corresponds to one account, the accounts having the resource transfer relationship are connected by directed edges, each node may have a node attribute, each edge also has an edge attribute, and a complete drawing of the relationship between the entities and the entities may be formed by the attributes.
In one embodiment, the account relationship network described above may be as shown in FIG. 2. Each account in fig. 2 corresponds to a node, and accounts having a resource transfer relationship are connected by directed edges, where "loan balance, owned balance, creation date" and the like may be node attributes, and "3-1 hhmmss … 01 roll-out 5 k" may be edge attributes. The above-mentioned 3-1hhmmss may be a specific time (month/day/hour/minute/second), and hhmmss is a time format, such as: 12:18:09(12 points 18 min 9 sec). It is understood that fig. 2 is only an example, the account relationship network may further include more or fewer nodes in an actual application, and other different information may be recorded in the account relationship network, which may be determined according to an actual situation, and the embodiment of the present specification does not limit this.
In this embodiment, the loan may be classified into a general account and an illegal account in advance, so that whether the loan flows to the illegal account can be visually shown. Other accounts outside the prohibited account are common accounts, and the common accounts can be further divided into accounts with credit and accounts without credit. The forbidden account can be an account in a forbidden field such as investment, financing, securities, real estate, P2P (peer-to-peer network borrowing), and the type of the account can be recorded in a database of a target institution as an account attribute and can be directly obtained when needed.
S103: preprocessing an account relation network to obtain a plurality of sub-networks; wherein the pretreatment comprises: network pruning and network cutting.
In this embodiment, because redundant information may exist in the account relationship network and the account relationship network generated from a large amount of resource transfer information may be complex, the account relationship network may be preprocessed to obtain a plurality of sub-networks. Wherein, the pretreatment may include: network pruning and network cutting.
In the embodiment, invalid nodes and edges in the account relationship network can be removed through network pruning, so that the responsibility of the network is reduced, and the data volume of subsequent calculation is effectively reduced.
In this embodiment, since a plurality of subnetworks which do not have a resource transfer relationship may appear after network pruning is performed, it is possible to cut the account relationship network obtained after pruning. And the plurality of sub-networks obtained by cutting do not have resource transfer relationship.
S104: searching each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; the initial account of the abnormal resource transfer link is a credit account, and the termination account is a forbidden account.
In this embodiment, a heuristic search algorithm may be used to search each sub-network to obtain an abnormal resource transfer link in each sub-network; the initial account of the abnormal resource transfer link is a credit account, and the termination account is a forbidden account.
In the embodiment, the heuristic search is also called information search, the heuristic search can guide the search by using the initiation information owned by the problem, so as to achieve the purposes of reducing the search range and reducing the complexity of the problem, and the heuristic strategy can advance to the most promising direction by guiding the search, thereby reducing the complexity.
In this embodiment, the heuristic search algorithm is used to search each sub-network, so that the starting point of the sub-network is used as the center, and the vertex with the shortest sum of the distance from the starting point and the forbidden account node path is preferentially selected to perform search traversal, instead of performing blind search, so that the calculation efficiency is improved by reducing unnecessary searches.
In the present embodiment, a plurality of sub-networks NET { NET ═ NET may be provided1，NETmIn the method, a sub-network NET is selectedi. And creates two sets Q, R, set Q, R representing the set of nodes to be traversed and the set of nodes traversed, respectively. The set Q, R may be initialized, where Q ═ NETiStarting point in (1), R { }, setting each starting point priority weight to 0.
In the present embodiment, the point V having the smallest priority weight may be selected from the set QiAs a starting point, if ViNot the target vertex (with a credit account), then: (1) will ViDeleting the data from the set Q and adding the data into the set R; (2) traversing its one-degree neighbor node if the neighbor node VjNot in the set R, then V is calculatedjAnd V is givenjAdding the obtained mixture into a set Q; if the neighbor node VjIn set R, skip. The priority weight is calculated according to a priority function f (x) ═ h (x) + g (x), where h (x) represents the shortest distance from the node to the target node (the forbidden account node), g (x) represents the shortest distance from the node to the starting node, and the priority weight is higher when the value of the priority weight is smaller. Further, the above steps may be sequentially cycled until the set Q is empty.
From the above description, it can be seen that the embodiments of the present specification achieve the following technical effects: an account relationship network may be constructed based on the acquired resource transfer information set within the target time period, and the account relationship network is used to characterize the resource transfer relationship between accounts. Since the account relationship network may be complex and redundant information may exist, the account relationship network may be preprocessed to obtain a plurality of sub-networks, where the preprocessing may include: and network pruning and network cutting are performed, so that an effective sub-network can be extracted from the initial account relation network under the condition of large data scale, and the data processing amount is effectively reduced. Furthermore, each sub-network can be searched by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network, wherein an initial account of the abnormal resource transfer link is a credited account, and a terminating account of the abnormal resource transfer link is an prohibited account. The heuristic search algorithm is utilized to search each sub-network, the starting point of the sub-network is taken as the center, the vertex with the shortest sum of the distance starting point and the forbidden account node path is preferentially selected to be searched and traversed, blind search is not carried out, unnecessary search can be effectively avoided, and the calculation efficiency is improved. Therefore, the resource transfer link can be efficiently tracked and analyzed by using the account relation network in combination with the network pruning, preprocessing and heuristic search algorithm, and the abnormal resource transfer link can be accurately determined.
In one embodiment, constructing an account relationship network based on a resource transfer information set may include: identifying account resource attributes corresponding to all resource transfer information in the resource transfer information set to obtain a first resource transfer information set; the first resource transfer information set comprises a plurality of pieces of resource transfer information, and each piece of resource transfer information comprises a resource transfer initiating account, a resource transfer receiving account, an account entity attribute, an account resource attribute and an attribute of a resource transfer relationship. Determining remark information corresponding to target resource transfer information related to a third party account in the first resource transfer information set, and converting the third party account into a plurality of virtual sub-accounts according to the remark information corresponding to the target resource transfer information to obtain a second resource transfer information set; wherein, a virtual sub-account corresponds to a type of remark information. Further, a point-side file can be generated based on the second resource transfer information set, and an account relation network is constructed according to the point-side file; the account relationship network comprises a plurality of nodes, the nodes are connected through directed edges, each node corresponds to an account, the attributes of the nodes comprise account entity attributes and account resource attributes, and the edge attributes are the attributes of the resource transfer relationship.
In this embodiment, attributes of account resources may be identified in order to clearly specify the flow of resources. The specified resource may be a resource that is expected to be tracked, in some specific examples, the specified resource may be a loan balance, and the obtaining of the account resource attribute may include: account loan balance and account owned balance. The concrete can be determined according to actual conditions, and the comparison of the examples in the specification is not limited.
In this embodiment, each piece of resource transfer information may include a resource transfer initiating account, a resource transfer receiving account, an account entity attribute, an account resource attribute, an attribute of a resource transfer relationship, and the like. The resource transfer initiating account and the resource transfer receiving account may be unique identifiers of the accounts, for example: account number, corresponding user's identification number, etc.; the above-mentioned account entity attributes may be used to characterize the type of account, for example: general accounts (credit account, no credit account), illicit accounts, etc.; the attributes of the resource transfer relationship may be used to characterize resource transfer between accounts, and may include: resource transfer amount, resource transfer time, remark information of resource transfer, and the like. Of course, the attributes of the account entity and the resource transfer relationship are not limited to the above examples, and other modifications may be made by those skilled in the art within the spirit of the embodiments of the present disclosure, but the functions and effects achieved by the attributes are the same as or similar to those of the embodiments of the present disclosure, and all the attributes are included in the scope of the embodiments of the present disclosure.
In this embodiment, the user may perform resource transfer through the third-party payment account, for example: the user transfers resources through third-party accounts such as payment treasures, WeChat and the like, so that the third-party accounts are associated with a plurality of accounts, and points with the number of associated edges of the third-party accounts being more than 50 ten thousand can be ultra-large points. At the moment, the third-party payment type super-large account can be virtualized into a plurality of sub-accounts, so that the data volume of subsequent searching is reduced, and the calculation efficiency is improved.
In this embodiment, some abbreviated remark information is usually recorded due to the resource transfer with the third party account, for example: transfer accounts, red envelope, refunds, etc. Therefore, the remark information corresponding to the target resource transfer information related to the third party account in the first resource transfer information set can be determined, and the third party account is converted into a plurality of virtual sub-accounts by the remark information corresponding to the target resource transfer information. And the resource transfer information corresponding to the same type of remark information belongs to the same specific virtual sub-account.
In this embodiment, the third party account may be virtualized in a rule batch manner, or may be virtualized in a natural language processing machine learning modeling manner, which is specifically determined according to the actual situation, and the examples in this specification are not limited to this.
In this embodiment, the point-edge file may be loaded into a graph database or a graph calculation engine to generate an account relationship network. It is understood, of course, that in some embodiments, the account relationship network may be constructed in other manners, which may be determined according to actual situations, and the embodiments of this specification are not limited thereto.
In one embodiment, account entity attributes may include: a credit account, a non-credit account, and a default account; account resource attributes may include: account loan balance and account owned balance; attributes of the resource transfer relationship may include: the amount of resource transfer and the resource transfer time.
In one embodiment, preprocessing the account relationship network to obtain a plurality of sub-networks may include: screening nodes according to account entity attributes in the account relationship network to obtain a target candidate node set; and the target candidate node set does not contain the credit-free account nodes only with the outgoing edges or the incoming edges. A set of target candidate edges may be determined based on the set of target candidate nodes and the account relationship network. Furthermore, the account relationship network corresponding to the target candidate node set and the target candidate edge set can be used as the pruned account relationship network, and the pruned account relationship network is segmented by using the weak link algorithm to obtain a plurality of sub-networks.
In the embodiment, connectivity and directed reachability characteristics can be analyzed for the resource transfer links in the account relationship network, so that the global network is pruned and cut to generate a plurality of sub-networks, and subsequent distributed processing is facilitated to search each sub-network.
In this embodiment, the tracking target of the abnormal resource transfer link is to find a path that a credit account flows to an illegal account, and the ordinary non-credit account can only serve as a transition node (intermediate node), which indicates that the ordinary non-credit account must include at least one outgoing edge and one incoming edge. Therefore, the out-and-in degree analysis can be carried out on the no-credit account, and if one no-credit account node has no out-edge or no in-edge, the no-credit account node can be eliminated. And traversing the credit-free account nodes in the account relationship network according to the mode to finally obtain a target candidate node set.
In this embodiment, the edge associated with the node in the target acquisition node set may be determined based on the account relationship network, so that the target candidate edge set may be obtained correspondingly, and the account relationship network corresponding to the target candidate node set and the target candidate edge set may be used as the pruned account relationship network.
In this embodiment, in order to facilitate distributed computation and further improve the computation efficiency, the pruned account relationship network may be segmented by using a weak link algorithm to obtain a plurality of sub-networks. The weak connectivity algorithm is a partitioning algorithm for partitioning nodes in a sub-network.
In one embodiment, screening nodes according to attributes of account entities in an account relationship network to obtain a target candidate node set may include: and taking the node with the account entity attribute of the account relationship network as an initial node set, taking the node with the account entity attribute of the account relationship network as a forbidden account as a termination node set, and taking the initial node set and the termination node set as initial candidate node sets. Further, other nodes except for the nodes in the initial candidate node set in the account relationship network may be used as a node set to be screened, and when an edge exists in a target node in the node set to be screened at the same time, the target node is removed from the node set to be screened and added to the initial candidate node set. And under the condition that the target nodes in the node set to be screened do not have the outgoing edges and the incoming edges at the same time, removing the target nodes from the node set to be screened until the node set to be screened is traversed to obtain a target candidate node set.
In the bookIn this embodiment, the node in the account relationship network whose account entity attribute is credit account may be set as the starting node set S ═ Vs1,Vs2,...,VsmAnd taking a node with the account entity attribute of the forbidden account in the account relationship network as a termination node set T ═ Vt1,Vt2,...,VtkAnd the SV of the two can be used as an initial candidate node set.
In this embodiment, sets UV and SE may be introduced in the process of performing the ingress and egress analysis, where SV is used to record candidate nodes after reservation, UV is used to record nodes that have not been investigated yet, UV may be a set of nodes to be screened, and SE is used to record edge relations after reservation, and may include:
step 1: initialization, SV ═ Vs1,Vs2,...,Vsm,Vt1,Vt2,...,VtkAnd UV comprises other nodes except the node in the SV in the account relationship network.
Step 2: randomly selecting a target node V from UVjJudging whether the edge exists simultaneously with the edge, if so, then changing VjAdding to SV and removing the node in UV; instead, only this spot was removed from the UV and not added to the SV;
and step 3: repeating the step 2 until no node exists in the UV, wherein the SV is a target candidate node set;
and 4, step 4: selecting top V from SViPoint, according to the structure of the account relationship network, if ViIf the node belongs to the starting node set or the ending node set, adding the entry relationship into the SE; if ViIf the node does not belong to the starting node set or the ending node set, adding the edge exit and edge entry relationship into the SE;
and 5: repeating the step 4 until all nodes in the SV are traversed to obtain a target candidate edge set SE;
step 6: the target candidate node set and the target candidate edge set form a pruned account relationship network.
In an embodiment, after the dividing the pruned account relationship network by using the weak link algorithm to obtain a plurality of sub-networks, the method may further include: and determining whether a node with a credit account attribute and a node with a default account attribute exist in a target sub-network in the plurality of sub-networks, and deleting the target sub-network under the condition that the node with the credit account attribute or the node with the default account attribute does not exist in the target sub-network. In the case of existence determination, it may be further determined whether a node whose account entity attribute is a credit account or a node whose account entity attribute is a contraband account exists in a sub-network next to the target sub-network until a plurality of sub-networks are traversed.
In this embodiment, it may be further determined whether each sub-network includes a credit account node and an illegal account node, and if the target sub-network does not include a credit account node and an illegal account node, it may be determined that an abnormal resource transfer link that is desired to be tracked does not exist in the target sub-network. If the target sub-network contains the credit account node and the forbidden account node, it indicates that the target sub-network has the abnormal resource transfer link which is expected to be tracked, and can reserve the abnormal resource transfer link and further determine whether the next sub-network of the target sub-network has a node with the account entity attribute being a credit account or a node with the account entity attribute being a forbidden account, until all sub-networks are traversed.
In this embodiment, a schematic diagram of comparing before and after effects of pruning, cutting and sub-network screening on an account relationship network may be as shown in fig. 3, where the left side of fig. 3 is an original account relationship network, the right side of fig. 3 is a plurality of sub-networks after pruning, cutting and sub-network screening, Vn in fig. 3 is used to identify different accounts, and a specific value may be determined according to an actual situation, and the diagram is merely an example. In fig. 3, the general account is not fully subdivided, and the details may be determined according to actual situations. Of course, the account relationship network and the sub-network are not limited to the above examples, and other modifications may be made by those skilled in the art within the spirit of the embodiments of the present disclosure, but the functions and effects achieved by the invention are all covered by the scope of the embodiments of the present disclosure.
In an embodiment, after searching each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network, the method may further include: acquiring a service rule; wherein the business rules are determined according to the monitoring requirements. Furthermore, the nodes which do not conform to the service rule in the abnormal resource transfer link can be removed, and the target abnormal resource transfer link is obtained.
In this embodiment, since the initially identified abnormal resource transfer link can only indicate that resources flow to an illegal account due to a loan account, an order form may also exist in which own funds flow to the illegal account instead of the loan funds flow to the illegal account, and thus, the business rule may be determined according to the monitoring requirement. In some embodiments, generally, a lender needs to use some illegal funds against a contract, if the fund amount is too small, it is meaningless, and it may be determined that the business rule is that the flow of the forbidden amount is larger than the balance of own funds, if the transferred resource is smaller than the own funds, it can only indicate that the borrower has the action of making stock investment, etc., and it cannot indicate that the borrower uses the loan funds illegally. Of course, the manner of determining the business rules is not limited to the above examples, and other modifications may be made by those skilled in the art within the spirit of the embodiments of the present disclosure, but the functions and effects achieved by the embodiments of the present disclosure are all covered by the scope of the embodiments of the present disclosure.
In this embodiment, the business rule may include: the limited resource transfer amount is larger than a certain threshold, the next-hand transferred-out resource amount is larger than the previous-hand transferred-out resource amount by a certain threshold, the resource amount flowing to the prohibited account is larger than the own resource amount, and the like. It is understood that the foregoing business rule is only an example, and may be determined according to practical situations, and the embodiment of the present specification does not limit this.
In an embodiment, the effect comparison diagram of the breadth-first traversal strategy and the heuristic search algorithm may be as shown in fig. 4, where the upper side of fig. 4 may be the effect of using the breadth-first traversal strategy, the dotted node is a starting point, the node of the gray background color is a termination node, and the other nodes are traversed nodes. The lower side of fig. 4 may be an effect of using a heuristic search algorithm, where a dotted node is a starting point, a node of a gray background color is an end node, a node of a coarse outline is an unretraversed node, and the rest are traversed nodes. Therefore, nodes traversed by the heuristic search algorithm are far less than nodes traversed by the breadth-first traversal strategy.
In the present embodiment, breadth-first traversal is a traversal strategy for a connected graph, and the idea is to start from one vertex and preferentially traverse a wide area around the vertex in a radial manner. As can be seen from fig. 4, the heuristic search algorithm may search for the tracking target by traversing fewer nodes, instead of performing blind search, so that the calculation efficiency may be improved by reducing unnecessary searches.
Based on the same inventive concept, an embodiment of the present specification further provides a device for determining an abnormal resource transfer link, as described in the following embodiments. Because the principle of solving the problem of the determination device for the abnormal resource transfer link is similar to the determination method for the abnormal resource transfer link, the implementation of the determination device for the abnormal resource transfer link can refer to the implementation of the determination method for the abnormal resource transfer link, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Fig. 5 is a block diagram of a structure of an apparatus for determining an abnormal resource transfer link according to an embodiment of the present disclosure, and as shown in fig. 5, the apparatus may include: an obtaining module 501, a constructing module 502, a preprocessing module 503, and a processing module 504, and the structure will be described below.
An obtaining module 501, configured to obtain a resource transfer information set in a target time period;
a building module 502, which may be configured to build an account relationship network based on the set of resource transfer information; wherein, the account relation network is used for characterizing the resource transfer relation between accounts;
a preprocessing module 503, configured to preprocess the account relationship network to obtain a plurality of subnetworks; wherein the pre-processing comprises: network pruning and network cutting;
the processing module 504 may be configured to search each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; and the starting account of the abnormal resource transfer link is a credit account, and the terminating account is a forbidden account.
An embodiment of the present specification further provides an electronic device, which may specifically refer to a schematic structural diagram of the electronic device shown in fig. 6 based on the method for determining an abnormal resource transfer link provided by the embodiment of the present specification, where the electronic device may specifically include an input device 61, a processor 62, and a memory 63. The input device 61 may be specifically configured to input a resource transfer information set in a target time period. The processor 62 may specifically be configured to obtain a resource transfer information set in a target time period; constructing an account relation network based on the resource transfer information set; wherein, the account relation network is used for characterizing the resource transfer relation between accounts; preprocessing the account relation network to obtain a plurality of sub-networks; wherein the pre-processing comprises: network pruning and network cutting; searching each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; and the starting account of the abnormal resource transfer link is a credit account, and the terminating account is a forbidden account. The memory 63 may be specifically configured to store data of a plurality of sub-networks, abnormal resource transfer links, and the like.
In this embodiment, the input device may be one of the main apparatuses for information exchange between a user and a computer system. The input device may include a keyboard, a mouse, a camera, a scanner, a light pen, a handwriting input board, a voice input device, etc.; the input device is used to input raw data and a program for processing the data into the computer. The input device can also acquire and receive data transmitted by other modules, units and devices. The processor may be implemented in any suitable way. For example, the processor may take the form of, for example, a microprocessor or processor and a computer-readable medium that stores computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, an embedded microcontroller, and so forth. The memory may in particular be a memory device used in modern information technology for storing information. The memory may include multiple levels, and in a digital system, the memory may be any memory as long as it can store binary data; in an integrated circuit, a circuit without a physical form and with a storage function is also called a memory, such as a RAM, a FIFO and the like; in the system, the storage device in physical form is also called a memory, such as a memory bank, a TF card and the like.
In this embodiment, the functions and effects specifically realized by the electronic device can be explained by comparing with other embodiments, and are not described herein again.
Embodiments of the present specification further provide a computer storage medium based on a determination method of an abnormal resource transfer link, where the computer storage medium stores computer program instructions, and when the computer program instructions are executed, the computer storage medium may implement: acquiring a resource transfer information set in a target time period; constructing an account relation network based on the resource transfer information set; wherein, the account relation network is used for characterizing the resource transfer relation between accounts; preprocessing the account relation network to obtain a plurality of sub-networks; wherein the pre-processing comprises: network pruning and network cutting; searching each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; and the starting account of the abnormal resource transfer link is a credit account, and the terminating account is a forbidden account.
In this embodiment, the storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache (Cache), a Hard Disk Drive (HDD), or a Memory Card (Memory Card). The memory may be used to store computer program instructions. The network communication unit may be an interface for performing network connection communication, which is set in accordance with a standard prescribed by a communication protocol.
In this embodiment, the functions and effects specifically realized by the program instructions stored in the computer storage medium can be explained by comparing with other embodiments, and are not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the present specification described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed over a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different from that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the present description are not limited to any specific combination of hardware and software.
Although the embodiments herein provide the method steps as described in the above embodiments or flowcharts, more or fewer steps may be included in the method based on conventional or non-inventive efforts. In the case of steps where no causal relationship is logically necessary, the order of execution of the steps is not limited to that provided by the embodiments of the present description. When the method is executed in an actual device or end product, the method can be executed sequentially or in parallel according to the embodiment or the method shown in the figure (for example, in the environment of a parallel processor or a multi-thread processing).
It is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and many applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of embodiments of the present specification should, therefore, be determined not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above description is only a preferred embodiment of the embodiments of the present disclosure, and is not intended to limit the embodiments of the present disclosure, and it will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present disclosure. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the embodiments of the present disclosure should be included in the protection scope of the embodiments of the present disclosure.
Claims (10)
1. A method for determining an abnormal resource transfer link, comprising:
acquiring a resource transfer information set in a target time period;
constructing an account relation network based on the resource transfer information set; wherein, the account relation network is used for characterizing the resource transfer relation between accounts;
preprocessing the account relation network to obtain a plurality of sub-networks; wherein the pre-processing comprises: network pruning and network cutting;
searching each sub-network by using a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; and the starting account of the abnormal resource transfer link is a credit account, and the terminating account is a forbidden account.
2. The method of claim 1, wherein building an account relationship network based on the set of resource transfer information comprises:
identifying account resource attributes corresponding to the resource transfer information in the resource transfer information set to obtain a first resource transfer information set; the first resource transfer information set comprises a plurality of pieces of resource transfer information, and each piece of resource transfer information comprises a resource transfer initiating account, a resource transfer receiving account, an account entity attribute, an account resource attribute and an attribute of a resource transfer relationship;
determining remark information corresponding to target resource transfer information related to a third party account in the first resource transfer information set;
converting the third party account into a plurality of virtual sub-accounts according to the remark information corresponding to the target resource transfer information to obtain a second resource transfer information set; one virtual sub-account corresponds to one type of remark information;
generating a point-edge file based on the second resource transfer information set;
establishing an account relation network according to the point edge file; the account relationship network comprises a plurality of nodes, the nodes are connected through directed edges, each node corresponds to an account, the attributes of the nodes comprise account entity attributes and account resource attributes, and the edge attributes are the attributes of the resource transfer relationship.
3. The method of claim 2, wherein the account entity attributes comprise: a credit account, a non-credit account, and a default account; the account resource attributes include: account loan balance and account owned balance; the attributes of the resource transfer relationship include: the amount of resource transfer and the resource transfer time.
4. The method of claim 1, wherein pre-processing the account relationship network to obtain a plurality of sub-networks comprises:
screening nodes according to the account entity attributes in the account relationship network to obtain a target candidate node set; wherein, the target candidate node set does not contain the credit-free account nodes only having an outgoing edge or an incoming edge;
determining a target candidate edge set based on the target candidate node set and the account relationship network;
taking the account relation network corresponding to the target candidate node set and the target candidate edge set as the pruned account relation network;
and segmenting the account relation network after pruning by using a weak link algorithm to obtain the plurality of sub-networks.
5. The method of claim 4, wherein screening nodes according to attributes of account entities in the account relationship network to obtain a target candidate node set comprises:
taking the node with the account entity attribute of the account with the credit account in the account relation network as an initial node set;
taking the node with the account entity attribute of the forbidden account in the account relationship network as a termination node set;
taking the starting node set and the terminating node set as initial candidate node sets;
taking other nodes except the nodes in the initial candidate node set in the account relationship network as a node set to be screened;
under the condition that an edge exists in a target node in the node set to be screened and an edge enters in the target node, removing the target node from the node set to be screened and adding the target node into the initial candidate node set;
and under the condition that the target node in the node set to be screened does not have an outgoing edge and an incoming edge at the same time, removing the target node from the node set to be screened until the node set to be screened is traversed to obtain the target candidate node set.
6. The method of claim 4, wherein after the splitting the pruned account relationship network using the weak link algorithm to obtain the plurality of subnetworks, further comprising:
determining whether a node with a credit account attribute and a node with a default account attribute exist in a target sub-network in the plurality of sub-networks;
deleting the target sub-network under the condition that the node with the account entity attribute being a credit account and the node with the account entity attribute being a forbidden account do not exist in the target sub-network;
and under the condition of existence, determining whether a node with a credit account entity attribute or a node with a default account entity attribute exists in the next sub-network of the target sub-network or not, and traversing the sub-networks.
7. The method of claim 1, wherein after searching each sub-network by using a heuristic search algorithm to obtain the abnormal resource transfer link in each sub-network, the method further comprises:
acquiring a service rule; wherein the business rule is determined according to monitoring requirements;
and removing the nodes which do not accord with the business rule in the abnormal resource transfer link to obtain a target abnormal resource transfer link.
8. An apparatus for determining an abnormal resource transfer link, comprising:
the acquisition module is used for acquiring a resource transfer information set in a target time period;
the construction module is used for constructing an account relation network based on the resource transfer information set; wherein, the account relation network is used for characterizing the resource transfer relation between accounts;
the preprocessing module is used for preprocessing the account relation network to obtain a plurality of sub-networks; wherein the pre-processing comprises: network pruning and network cutting;
the processing module is used for searching each sub-network by utilizing a heuristic search algorithm to obtain an abnormal resource transfer link in each sub-network; and the starting account of the abnormal resource transfer link is a credit account, and the terminating account is a forbidden account.
9. An apparatus for determining an abnormal resource transfer link, comprising a processor and a memory for storing processor-executable instructions, which when executed by the processor implement the steps of the method of any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110811722.5A CN113537960A (en) | 2021-07-19 | 2021-07-19 | Method, device and equipment for determining abnormal resource transfer link |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110811722.5A CN113537960A (en) | 2021-07-19 | 2021-07-19 | Method, device and equipment for determining abnormal resource transfer link |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113537960A true CN113537960A (en) | 2021-10-22 |
Family
ID=78100100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110811722.5A Pending CN113537960A (en) | 2021-07-19 | 2021-07-19 | Method, device and equipment for determining abnormal resource transfer link |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113537960A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218447A (en) * | 2021-12-13 | 2022-03-22 | 支付宝(杭州)信息技术有限公司 | Graph processing method and system |
| CN115049493A (en) * | 2022-06-29 | 2022-09-13 | 北京知帆科技有限公司 | Block chain data tracking method and device and electronic equipment |
| WO2023087931A1 (en) * | 2021-11-22 | 2023-05-25 | 腾讯科技（深圳）有限公司 | Data processing method and apparatus, device, readable storage medium and program product |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170243214A1 (en) * | 2016-02-22 | 2017-08-24 | Bank Of America Corporation | System for tracking transfer of resources in a process data network |
| CN108492104A (en) * | 2018-02-12 | 2018-09-04 | 阿里巴巴集团控股有限公司 | A kind of resource transfer monitoring method and device |
| CN109766323A (en) * | 2018-12-17 | 2019-05-17 | 深圳壹账通智能科技有限公司 | The full link monitoring method, apparatus of loan transaction, computer equipment and storage medium |
| CN110490730A (en) * | 2019-08-21 | 2019-11-22 | 北京顶象技术有限公司 | Abnormal fund Assembling Behavior detection method, device, equipment and storage medium |
| CN111127024A (en) * | 2019-11-19 | 2020-05-08 | 支付宝(杭州)信息技术有限公司 | Suspicious fund link detection method and device |
| CN111126828A (en) * | 2019-12-19 | 2020-05-08 | 浙江邦盛科技有限公司 | Knowledge graph-based multilayer fund abnormal flow direction monitoring method |
| CN111429258A (en) * | 2020-03-19 | 2020-07-17 | 中国建设银行股份有限公司 | Method and device for monitoring loan fund flow direction |
| US20200272959A1 (en) * | 2019-02-22 | 2020-08-27 | Northeastern University | Tracking Movement of Resources in a Financial Transaction Network |
| CN111770022A (en) * | 2020-06-28 | 2020-10-13 | 中国平安财产保险股份有限公司 | Link monitoring-based capacity expansion method, system, equipment and computer storage medium |
| CN112491900A (en) * | 2020-11-30 | 2021-03-12 | ***股份有限公司 | Abnormal node identification method, device, equipment and medium |
| CN112733995A (en) * | 2021-01-07 | 2021-04-30 | 中国工商银行股份有限公司 | Method for training neural network, behavior detection method and behavior detection device |
| CN112767127A (en) * | 2021-01-21 | 2021-05-07 | 中信银行股份有限公司 | Loan fund monitoring method and device |
-
2021
- 2021-07-19 CN CN202110811722.5A patent/CN113537960A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170243214A1 (en) * | 2016-02-22 | 2017-08-24 | Bank Of America Corporation | System for tracking transfer of resources in a process data network |
| CN108492104A (en) * | 2018-02-12 | 2018-09-04 | 阿里巴巴集团控股有限公司 | A kind of resource transfer monitoring method and device |
| CN109766323A (en) * | 2018-12-17 | 2019-05-17 | 深圳壹账通智能科技有限公司 | The full link monitoring method, apparatus of loan transaction, computer equipment and storage medium |
| US20200272959A1 (en) * | 2019-02-22 | 2020-08-27 | Northeastern University | Tracking Movement of Resources in a Financial Transaction Network |
| CN110490730A (en) * | 2019-08-21 | 2019-11-22 | 北京顶象技术有限公司 | Abnormal fund Assembling Behavior detection method, device, equipment and storage medium |
| CN111127024A (en) * | 2019-11-19 | 2020-05-08 | 支付宝(杭州)信息技术有限公司 | Suspicious fund link detection method and device |
| CN111126828A (en) * | 2019-12-19 | 2020-05-08 | 浙江邦盛科技有限公司 | Knowledge graph-based multilayer fund abnormal flow direction monitoring method |
| CN111429258A (en) * | 2020-03-19 | 2020-07-17 | 中国建设银行股份有限公司 | Method and device for monitoring loan fund flow direction |
| CN111770022A (en) * | 2020-06-28 | 2020-10-13 | 中国平安财产保险股份有限公司 | Link monitoring-based capacity expansion method, system, equipment and computer storage medium |
| CN112491900A (en) * | 2020-11-30 | 2021-03-12 | ***股份有限公司 | Abnormal node identification method, device, equipment and medium |
| CN112733995A (en) * | 2021-01-07 | 2021-04-30 | 中国工商银行股份有限公司 | Method for training neural network, behavior detection method and behavior detection device |
| CN112767127A (en) * | 2021-01-21 | 2021-05-07 | 中信银行股份有限公司 | Loan fund monitoring method and device |
Non-Patent Citations (1)
| Title |
|---|
| 马青青等: "银行交易网络的链路预测", 《电子科技》, 15 May 2019 (2019-05-15), pages 55 - 61 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023087931A1 (en) * | 2021-11-22 | 2023-05-25 | 腾讯科技（深圳）有限公司 | Data processing method and apparatus, device, readable storage medium and program product |
| CN114218447A (en) * | 2021-12-13 | 2022-03-22 | 支付宝(杭州)信息技术有限公司 | Graph processing method and system |
| CN115049493A (en) * | 2022-06-29 | 2022-09-13 | 北京知帆科技有限公司 | Block chain data tracking method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Matsunaga et al. | Exploring graph neural networks for stock market predictions with rolling window analysis | |
| WO2021174966A1 (en) | Risk identification model training method and apparatus | |
| WO2021164382A1 (en) | Method and apparatus for performing feature processing for user classification model | |
| EP4236197A2 (en) | Micro-loan system | |
| CN113537960A (en) | Method, device and equipment for determining abnormal resource transfer link | |
| JP2018538587A (en) | Risk assessment method and system | |
| Zhan et al. | A loan application fraud detection method based on knowledge graph and neural network | |
| CN111325619A (en) | Credit card fraud detection model updating method and device based on joint learning | |
| CN108492001A (en) | A method of being used for guaranteed loan network risk management | |
| CN111444232A (en) | Method for mining digital currency exchange address and storage medium | |
| CN110930038A (en) | Loan demand identification method, loan demand identification device, loan demand identification terminal and loan demand identification storage medium | |
| CN112199510A (en) | Fraud probability determination method and device, electronic equipment and storage medium | |
| Ozdagoglu et al. | The application of data mining techniques in manipulated financial statement classification: The case of Turkey | |
| CN113361963A (en) | Method and device for identifying risk of enterprise | |
| Eddy et al. | Credit scoring models: Techniques and issues | |
| CN111798304A (en) | Risk loan determination method and device, electronic equipment and storage medium | |
| Haryono et al. | Aspect-based sentiment analysis of financial headlines and microblogs using semantic similarity and bidirectional long short-term memory | |
| Wu et al. | An uncertainty-oriented cost-sensitive credit scoring framework with multi-objective feature selection | |
| CN117291722A (en) | Object management method, related device and computer readable medium | |
| Huang et al. | Domain adaptation approach for credit risk analysis | |
| CN115994331A (en) | Message sorting method and device based on decision tree | |
| Zang | Construction of Mobile Internet Financial Risk Cautioning Framework Based on BP Neural Network | |
| Morales et al. | Credit risk analysis model in microfinance institutions in Peru through the use of Bayesian networks | |
| Feng et al. | Blockchain-oriented approach for detecting cyber-attack transactions | |
| Salehi et al. | Islamic banking ranking efficiency based on a decision tree in Iran |
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 |