CN116883145A

CN116883145A - Loan fund convergence link generation method and device and electronic equipment

Info

Publication number: CN116883145A
Application number: CN202310712976.0A
Authority: CN
Inventors: 季海婧
Original assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Current assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Priority date: 2023-06-15
Filing date: 2023-06-15
Publication date: 2023-10-13

Abstract

The disclosure provides a method and a device for generating a loan fund convergence link and electronic equipment, wherein the method comprises the following steps: acquiring transaction links of a plurality of loan funds in a target period; extracting entity identification from a transaction link of each loan fund in a plurality of loan funds to obtain an entity set corresponding to each loan fund; constructing a graph network according to entity sets corresponding to the loan funds, and determining sub-graphs in the graph network and convergent entity identifiers and group identifiers corresponding to each entity in the sub-graphs through a connected component algorithm; and generating convergent links corresponding to the loan funds according to the convergent entity identifiers and the group identifiers corresponding to each entity in the subgraph. Therefore, for the transaction links of the loan funds, the converging links of the loan funds can be determined by constructing a graph network and a connected component algorithm, so that whether the loan funds flow to the illegal field or not can be focused, and a precise and reliable wind control basis is provided for financial supervision.

Description

Loan fund convergence link generation method and device and electronic equipment

Technical Field

The disclosure relates to the fields of data processing, financial science and technology, information technology industry and the like, and in particular relates to a method and a device for generating a loan fund convergence link and electronic equipment.

Background

With the increase of the national financial support force for small micro enterprises, the consumption and the overall loan interest rate of management are low, some illegal intermediaries are generally in the name of counterfeit banks, and consumers are induced to transact loans in a manner of false propaganda such as mortgage-free, guarantee-free, free-of-low, credit-clearing and the like. In the related art, most of the attention is paid to whether a single loan fund goes to the illegal domain.

Disclosure of Invention

The present disclosure provides a loan funds convergence link method, apparatus, electronic device, and storage medium. The technical scheme of the present disclosure is as follows:

according to a first aspect of an embodiment of the present disclosure, there is provided a method of loan funds convergence link, comprising:

acquiring transaction links of a plurality of loan funds in a target period;

extracting entity identifiers from transaction links of each loan fund in the plurality of loan funds to obtain entity sets corresponding to each loan fund;

constructing a graph network according to the entity sets corresponding to the loan funds, and determining a sub-graph in the graph network and a convergent entity identifier and a group identifier corresponding to each entity in the sub-graph through a connected component algorithm;

and generating an aggregation link corresponding to the loan funds according to the aggregation entity identifier and the group identifier corresponding to each entity in the subgraph.

According to a second aspect of embodiments of the present disclosure, there is provided a loan funds converging link device, comprising:

the acquisition module is used for acquiring transaction links of a plurality of loan funds in a target period;

the extraction module is used for extracting entity identifiers from transaction links of each loan fund in the plurality of loan funds to obtain entity sets corresponding to each loan fund;

the determining module is used for constructing a graph network according to entity sets corresponding to the loan funds, and determining subgraphs in the graph network and convergent entity identifiers and group identifiers corresponding to each entity in the subgraphs through a connected component algorithm;

and the generation module is used for generating convergent links corresponding to the loan funds according to the convergent entity identifiers and the group identifiers corresponding to each entity in the subgraph.

According to a third aspect of embodiments of the present disclosure, there is provided an electronic device, comprising: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method according to the above-described embodiments of the present disclosure.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform a method as described in the above embodiments of the present disclosure.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising: a computer program which, when executed by a processor, implements a method as described in the above embodiments of the present disclosure.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

Fig. 1 is a flow chart illustrating a method of loan funds convergence links according to a first embodiment of the disclosure.

Fig. 2 is a schematic diagram of a transaction link for loan funds provided by the present disclosure.

Fig. 3 is a schematic diagram of knowledge graph modeling provided by the present disclosure.

Fig. 4 is a schematic diagram of a transaction link for loan funds provided by the present disclosure.

Fig. 5 is a schematic diagram three of a transaction link for loan funds provided by the present disclosure.

Fig. 6 is a schematic diagram of an aggregated link for loan funds provided by the present disclosure.

Fig. 7 is a flowchart illustrating a method for generating a loan funds convergence link according to a second embodiment of the disclosure.

Fig. 8 is a flowchart illustrating a method for generating a loan funds convergence link according to a third embodiment of the disclosure.

Fig. 9 is a schematic structural diagram of a generation apparatus of a loan funds convergence link shown in a fourth embodiment of the disclosure.

Fig. 10 is a schematic structural view of an electronic device according to an exemplary embodiment of the present disclosure.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

With the increase of the national financial support force for small micro enterprises, the consumption and the overall loan interest rate of management are low, some illegal intermediaries are generally in the name of counterfeit banks, and consumers are induced to transact loans in a manner of false propaganda such as mortgage-free, guarantee-free, free-of-low, credit-clearing and the like. In the related art, most of the attention is paid to whether a single loan fund goes to the illegal domain. .

Accordingly, in response to at least one of the above-mentioned problems, the present disclosure proposes a method, an apparatus, an electronic device, and a storage medium for generating a loan funds convergence link.

The data acquisition, storage, use, processing and the like in the technical scheme of the present disclosure all conform to the relevant regulations of the national laws and regulations.

The following describes a method, an apparatus, an electronic device, and a storage medium for generating a loan funds convergence link according to embodiments of the disclosure with reference to the accompanying drawings. Fig. 1 is a flow chart illustrating a method of generating a loan funds convergence link according to a first embodiment of the disclosure.

The embodiment of the disclosure is illustrated in the way that the method for generating the loan funds convergence link is configured in the device for generating the loan funds convergence link, and the device for generating the loan funds convergence link can be applied to any electronic device, so that the electronic device can execute the function of generating the loan funds convergence link.

The electronic device may be any device with computing capability, for example, a personal computer, a mobile terminal, a server, etc.

As shown in fig. 1, the method for generating the loan funds convergence link may include:

step 101, acquiring transaction links of a plurality of loan funds in a target period.

The transaction link for loan funds may include, among other things, the identity of the entity making the transaction, the amount of the transaction, the flow of funds, etc.

In the present disclosure, the plurality of loan funds in the target period may refer to a plurality of loans whose loan issuing time is within the target period, and the transaction link of the plurality of loan funds in the target period may refer to a transaction link determined based on transaction data of the loan issued in the target period within the target period.

For example, the transaction links of loans A1 and A2 are shown in fig. 2, in which the funds receiver a in the loan A2 has turned 10 ten thousand and 20 ten thousand to the transaction opponent E and the transaction opponent H, respectively, and it is seen that the loan A2 has two branch links, and the sum of the amounts transferred to the transaction opponent E and the transaction opponent H is equal to the amount of the loan A1 issued to the funds receiver a by the bank from the source, so that the two branch links can be used as one transaction link of the loan A1.

In the present disclosure, the transaction links of the plurality of loan funds in the target time period may be directly acquired, or may be determined according to the acquired transaction data of the loan issued in the target time period, which is not limited in the present disclosure.

When the transaction links are acquired based on the transaction data of the plurality of loan funds in the target time period, as a possible implementation manner, the funds flow direction of each loan funds in the target time period and the transaction amount between entities can be determined according to the transaction time in the transaction data of each loan funds, the entity identification for performing the transaction and the like, and the transaction links of each loan funds can be determined according to the funds flow direction and the transaction amount between entities. Wherein the entity may be a business entity, a personal entity, a banking entity, etc

As another possible implementation manner, entity extraction and relationship extraction may be performed on transaction data of each loan fund in the plurality of loan funds, so as to obtain entity identifiers and relationships between entities of transactions performed by each loan fund, and a knowledge graph is constructed according to the entity identifiers and relationships between entities respectively corresponding to the plurality of loan funds, and then a transaction link corresponding to each loan fund may be found out from the knowledge graph by taking a second target entity corresponding to each loan fund as a starting point and sequentially taking the first target relationship and the second target relationship as a basis. Therefore, by constructing the knowledge graph and acquiring the transaction link of loan funds based on the knowledge graph, the accuracy of the determined transaction link can be improved.

The second target entity may be a bank, the relationship between the entities may include a loan issue and a fund relationship, the first target relationship may be a loan issue, and the second target relationship may be a fund relationship.

For example, in the knowledge graph model shown in fig. 3, a loan issuing relationship is formed between a bank and a personal entity and between a bank and a business entity, a fund relationship may exist between a personal entity and a business entity, and the fund relationship may also include rotation between a personal entity and a personal entity, rotation between a business entity and a business entity, and the arrow on the side of the relationship in fig. 3 indicates the fund flow direction.

When determining a transaction link of loan funds based on a knowledge graph, a bank can be used as an initial node, funds are issued as a basis, a receiver of the loan funds can be found, the receiver of the loan funds can be an enterprise or a person, then the receiver of the loan is used as a starting point, and a transaction opponent of the funds operation is continuously tracked downwards by using the funds transaction as a relationship expansion basis until the funds operation is stopped or the funds go outside the jurisdiction.

In the knowledge graph, the bank is used as a starting point to find that the bank gives a loan A1 to the fund receiver A, the loan amount is 50 ten thousand, the bank gives a loan A2 to the fund receiver A, the loan amount is 30 ten thousand, and the transaction links of the loan A1 and the loan A2 are shown in fig. 4. For the loan A1, the trade opponents, namely entities, of the fund application are continuously tracked downwards by taking the fund receiver A as a starting point and taking the fund relation as a basis, and the corresponding trade links of the loan A1 are obtained as shown in FIG. 5; and for the loan A2, taking the fund receiver A as a starting point, and obtaining a corresponding transaction link of the loan A2 in the same way. The transaction link of loan A1 in FIG. 4 is then combined with the transaction link of loan A1 in FIG. 5, resulting in a complete transaction link of loan A1, as shown in FIG. 2. Likewise, the transaction link of loan A2 of FIG. 4 is combined with the transaction link of loan A2 of FIG. 5, resulting in a complete transaction link of loan A2, as shown in FIG. 2.

In this disclosure, the target period may be determined according to actual needs, for example, from 3 months to 5 months, or from 3 to 6 months, which is not limited in this disclosure.

Step 102, extracting entity identification from the transaction link of each loan fund in the plurality of loan funds to obtain the entity set corresponding to each loan fund.

In the disclosure, the transaction link of each loan fund may include information such as entity identifier, transaction amount, transaction time, etc., and the entity identifier may be extracted from the transaction link of each loan fund, so as to obtain an entity set corresponding to each loan fund. The entity set corresponding to one loan fund may include all entity identifiers on the transaction link of the loan fund.

For example, entity identification extraction is performed on the transaction links of loans A1 and A2 in fig. 2, so as to obtain the entity set of loan A1 as follows: fund receiver a, trade opponent B, trade opponent C, extrajurisdictional opponent D; the set of entities for loan A2 is: [ fund receiver A, trade opponent E, trade opponent F, trade opponent C, trade opponent G, trade opponent H, trade opponent I, trade opponent J, extrajurisdictional opponent D ].

And 103, constructing a graph network according to entity sets corresponding to the loan funds, and determining a sub-graph in the graph network and an aggregation entity identifier and a group identifier corresponding to each entity in the sub-graph through a connected component algorithm.

When the graph network is constructed, each entity identifier in the entity sets corresponding to the loan funds can be used as a node, and if the same entity identifier exists in the entity sets of different loan funds, the same entity identifier can be used as a node.

In the disclosure, through a connected component algorithm, each loan fund can go downwards from a fund receiving party as a starting point, each entity going through is marked with a group identifier, if a plurality of loan funds exist and meet at the same node, the node can be used as a converging entity, the nodes with connected loan funds form a subgraph, and the converging entity identifiers corresponding to the entities with the same group identifier can be determined, namely, the converging entity identifier and the group identifier corresponding to each entity in the subgraph can be determined. Therefore, all sub-graphs in the graph network can be found through the connected component algorithm, and the converged entity identifier and the group identifier corresponding to each entity in the sub-graphs can be returned.

The number of the subgraphs in one graph network can be one or a plurality of subgraphs, and group identifiers corresponding to different subgraphs are different.

And 104, generating convergent links corresponding to the loan funds according to the convergent entity identifiers and the group identifiers corresponding to each entity in the subgraph.

In the disclosure, a transaction link belonging to the same sub-graph can be determined according to entity identifiers in transaction links of multiple loan funds, and an aggregation entity identifier and a group identifier corresponding to each entity in the sub-graph, and the transaction links belonging to the same sub-graph are aggregated according to the aggregation entity identifiers corresponding to the sub-graph, so as to obtain an aggregation link corresponding to the sub-graph. If multiple subgraphs exist, multiple convergent links can be generated, and thus the multiple convergent links are convergent links of multiple loan funds in a target time period.

In order to facilitate understanding of the following description with reference to fig. 6, two convergent links are provided in the transaction link of the loan A1 and the transaction link of the loan A2 shown in fig. 2, and as shown in fig. 6, the loan A1 and the loan A2 have two convergent links, where a convergent entity of one convergent link is an extrajurisdictional opponent D, and a convergent entity of the other convergent link is a transaction opponent C.

In the embodiment of the disclosure, entity sets corresponding to multiple loan funds are obtained by extracting entity identifiers in transaction links of the multiple loan funds, a graph network is constructed according to the entity sets corresponding to the multiple loan funds, a sub graph in the graph network and an aggregation entity identifier and a group identifier corresponding to each entity in the sub graph are determined through a connected component algorithm, and an aggregation link corresponding to the multiple loan funds is generated according to the aggregation entity identifier and the group identifier corresponding to each entity in the sub graph. Therefore, for the transaction links of the loan funds, the converging links of the loan funds can be determined by constructing a graph network and a connected component algorithm, so that whether the loan funds flow to the illegal field or not can be focused, and a precise and reliable wind control basis is provided for financial supervision.

As shown in fig. 7, the method for generating the loan funds convergence link may include:

step 701, obtaining transaction links of a plurality of loan funds in a target period.

Step 702, extracting entity identification from transaction links of each loan fund in the plurality of loan funds, and obtaining an entity set corresponding to each loan fund.

Step 703, constructing a graph network according to the entity sets corresponding to the loan funds, and determining the subgraph in the graph network and the aggregation entity identifier and the group identifier corresponding to each entity in the subgraph through a connected component algorithm.

In the present disclosure, any implementation manner of the embodiments of the present disclosure may be adopted in steps 701 to 703, which is not limited in this disclosure and will not be described in detail.

Step 704, determining a first target transaction link corresponding to the subgraph from the transaction links of the loan funds according to the aggregate entity identifier and the group identifier corresponding to each entity in the subgraph.

Because each entity in the subgraph has a corresponding aggregation entity identifier and a group identifier, the entity identifiers with the same group identifier and aggregation entity identifier in the transaction links of the loan funds can be determined, and the transaction link where the entity identifiers with the same group identifier and aggregation entity identifier are located is used as a first target transaction link. Wherein the first target transaction link is a plurality of target transaction links, and the first target transaction link can be a complete transaction link for loan funds.

Step 705, generating convergent links corresponding to multiple loan funds according to the first target transaction links corresponding to the subgraph and the convergent entity identifiers.

If the first target transaction link is a complete transaction link of loan funds, deleting the entity identifier after the aggregation entity identifier in the first target transaction link corresponding to the subgraph to obtain a second target transaction link corresponding to the subgraph, wherein the second target transaction links are multiple, and the entity at the tail end of the second target transaction link is the aggregation entity. If there are multiple branch links in the first target transaction link, the branch links that do not contain the identity of the sink entity may also be deleted. And then, the convergence entity identifier corresponding to the subgraph can be used as a convergence point, the second target transaction link is connected and converged to obtain convergence links, if the subgraph is a plurality of convergence links, a plurality of convergence links can be obtained, and the convergence links are convergence links corresponding to a plurality of loan funds. Therefore, redundant links in the first target transaction link can be removed to obtain a transaction link for aggregation, and the aggregation link is further obtained through aggregation, so that the visualization effect of the aggregation link is improved.

For example, in the transaction links of the loans A1 and A2 in fig. 2, corresponding to the two sink entity outsourcing opponents D and the transaction opponent C, taking the sink entity transaction opponent C as an example, the branch link behind the transaction opponent H and the transaction opponent G behind the transaction opponent C in the transaction link of the loan A1 may be deleted, so as to obtain the transaction link: bank- > funds receiver a- > trade opponent E- > trade opponent D- > trade opponent C as the second target trade link of loan A1 for generating the aggregated link.

Optionally, a transaction link formed by entity identifiers with the same group identifier and the same aggregation entity identifier in the transaction link of loan funds can be used as a first target transaction link, wherein an entity at the tail end of the first target transaction link is used as an aggregation entity, the aggregation entity identifier can be used as an aggregation point, and the first target transaction link with the same aggregation entity identifier is connected and aggregated, so that the aggregation link can be obtained. If the aggregation entity identifiers are multiple, multiple aggregation links can be obtained, and the multiple aggregation links are aggregation links corresponding to multiple loan funds.

For example, in the transaction links of loans A1 and A2 in fig. 2, corresponding to two sink entity outside-jurisdiction opponents D and transaction opponents C, taking sink entity transaction opponents C as an example, entity identifiers with sink entity transaction opponents C in the transaction links of loans A2 are funds receiver a, transaction opponents E, transaction opponents D and transaction opponents C, and transaction links that can be obtained according to these entity identifiers: the bank- > funds receiver A- > trade opponent E- > trade opponent D- > trade opponent C is used as a second target trade link of the loan A2 and is directly used for converging to generate a converging link.

In practice, some of the convergence entities may be loan funds recipients in the transaction link, and the flow of the loan funds may be considered as not being the offending area. Optionally, it may be determined whether the hierarchy in which the aggregate entity identifier corresponding to the subgraph is located in the first target transaction link is a target hierarchy, if the hierarchy in which the aggregate entity identifier corresponding to any subgraph is located in the first target transaction link is a target hierarchy, any subgraph is screened out, the remaining subgraph is taken as the first target subgraph, and an aggregate link corresponding to a plurality of loan funds is generated according to the first target transaction link and the aggregate entity identifier corresponding to the first target subgraph.

Wherein the target tier may refer to the next tier of the bank. For example, with bank as tier 0, then the target tier may refer to tier 1, and bank as tier 1, then the target tier may refer to tier 2.

It should be noted that, the above values of the target levels are only examples, and specific values of the target levels may be determined according to actual needs, which is not limited in this disclosure.

In the present disclosure, the number of the first target transaction links is multiple, and if the hierarchy where the aggregation entity identifier corresponding to a certain sub-graph is located in any transaction link in the first target transaction links is the target hierarchy, the sub-graph may be screened out.

In the present disclosure, an aggregate link corresponding to a plurality of loan funds is generated according to a first target transaction link and an aggregate entity identifier corresponding to a first target sub-graph, which are similar to the aggregate links corresponding to a plurality of loan funds generated according to the aggregate entity identifier and the group identifier corresponding to each entity in the sub-graph described in the above embodiment, and therefore will not be described herein.

Therefore, whether the level of the aggregation entity identifier corresponding to the sub-graph in the first target transaction link is the target level is judged, the sub-graph is filtered, and the generated aggregation link is generated by utilizing the sub-graph obtained after filtering, so that the accuracy of the generated aggregation link can be improved, and a more accurate and reliable wind control basis is provided for financial supervision.

In the embodiment of the disclosure, the first target transaction link corresponding to the subgraph is determined from the transaction links of the multiple loan funds according to the converged entity identifier and the group identifier corresponding to each entity in the subgraph, and the converged links corresponding to the multiple loan funds are generated according to the first target transaction link and the converged entity identifier corresponding to the subgraph, so that whether the multiple loan funds flow to the illegal field can be focused, and a precise and reliable wind control basis is provided for financial supervision.

As shown in fig. 8, the method for generating the loan funds convergence link may include:

step 801, acquiring transaction links of a plurality of loan funds in a target period.

Step 802, extracting entity identification from transaction links of each loan fund in the plurality of loan funds to obtain an entity set corresponding to each loan fund.

Step 803, a graph network is constructed according to the entity sets corresponding to the loan funds, and the subgraph in the graph network and the aggregation entity identifier and the group identifier corresponding to each entity in the subgraph are determined through a connected component algorithm.

In the present disclosure, any implementation manner of the embodiments of the present disclosure may be adopted in the steps 801 to 803, which is not limited and not repeated herein.

Step 804, determining whether the convergence entity corresponding to the convergence entity identifier corresponding to the subgraph is the first target entity.

In practical application, the convergence entity may not belong to the illegal field, such as banks or enterprises of financial types such as insurance, loan, etc., so in the present disclosure, before the convergence link is generated, it may be determined whether the convergence entity corresponding to the subgraph is the first target entity, so as to screen out the subgraph that does not meet the requirement.

In the present disclosure, the first target entity may be set according to actual needs, for example, may be a bank, or an insurance type enterprise, or a loan type enterprise, or other entities, etc., which is not limited in this disclosure.

If the plurality of first target entities are provided, whether the aggregation entity corresponding to the aggregation entity identifier corresponding to the subgraph is any entity in the plurality of first target entities can be determined.

And step 805, screening out any sub-graph to obtain a second target sub-graph under the condition that the convergence entity corresponding to any sub-graph is the first target entity.

In the disclosure, if the convergence entity corresponding to any sub-graph is the first target entity, any sub-graph may be screened out, and the remaining sub-graph is used as the second target sub-graph. That is, the sub-graph of which the convergence entity is the first target entity in all sub-graphs can be screened out, and the rest of sub-graphs are taken as the second target sub-graph.

Optionally, if the number of the first target entities is plural, when the corresponding aggregate entity of the aggregate entity identifier corresponding to any sub-graph is any entity of the plural first target entities, any sub-graph may be screened out, and the remaining sub-graph is used as the second target sub-graph. That is, the sub-graph of the sink entity for any of the plurality of first target entities may be filtered out, with the remaining sub-graph being the second target sub-graph.

Step 806, generating an aggregate link corresponding to the plurality of loan funds according to the aggregate entity identifier and the group identifier corresponding to each entity in the second target subgraph.

In the present disclosure, the aggregate links corresponding to the multiple loan funds are generated according to the aggregate entity identifier and the group identifier corresponding to each entity in the second target subgraph, which are similar to the aggregate links corresponding to the multiple loan funds generated according to the aggregate entity identifier and the group identifier corresponding to each entity in the subgraph described in the above embodiment, and therefore are not described herein.

In the embodiment of the disclosure, the convergent entity is filtered for the subgraph of the second target entity, and the convergent entity and the group identifier corresponding to the filtered subgraph are utilized to generate the convergent link, so that the accuracy of the generated convergent link can be improved, and a more accurate and reliable wind control basis is provided for financial supervision.

Corresponding to the method for generating the loan funds convergence link provided by the embodiments of fig. 1, fig. 7 and fig. 8, the present disclosure further provides a device for generating the loan funds convergence link, and since the device for generating the loan funds convergence link provided by the embodiments of the present disclosure corresponds to the method for generating the loan funds convergence link provided by the embodiments of fig. 1, fig. 7 and fig. 8, the implementation of the method for generating the loan funds convergence link is also applicable to the device for generating the loan funds convergence link provided by the embodiments of the present disclosure, which will not be described in detail in the embodiments of the present disclosure.

Referring to fig. 9, the generation apparatus 900 of the loan funds convergence link may include:

an obtaining module 910, configured to obtain transaction links of a plurality of loan funds in a target period;

the extracting module 920 is configured to extract an entity identifier from a transaction link of each loan fund in the plurality of loan funds, so as to obtain an entity set corresponding to each loan fund;

a determining module 930, configured to construct a graph network according to the entity sets corresponding to the multiple loan funds, and determine, through a connected component algorithm, a subgraph in the graph network and a convergence entity identifier and a group identifier corresponding to each entity in the subgraph;

And the generating module 940 is configured to generate an aggregate link corresponding to the plurality of loan funds according to the aggregate entity identifier and the group identifier corresponding to each entity in the subgraph.

Optionally, in another embodiment, the generating module 940 is configured to:

determining a first target transaction link corresponding to the subgraph from transaction links of multiple loan funds according to the aggregation entity identifier and the group identifier corresponding to each entity in the subgraph;

and generating convergent links corresponding to the loan funds according to the first target transaction links corresponding to the subgraph and the convergent entity identifiers.

Optionally, in another embodiment, the generating module 940 is configured to:

deleting entity identifiers which are positioned behind the aggregation entity identifiers in the first target transaction links corresponding to the subgraph, and/or deleting branch links which do not contain the aggregation entity identifiers in the first target transaction links to obtain second target transaction links corresponding to the subgraph;

and taking the convergence entity identifier corresponding to the subgraph as a convergence point, and connecting and converging the second target transaction link to obtain convergence links corresponding to the loan funds.

Optionally, in another embodiment, the generating module 940 is configured to:

determining whether a hierarchy in which an aggregation entity identifier corresponding to the subgraph is located in a first target transaction link is a target hierarchy or not;

Screening any sub-graph to obtain a first target sub-graph under the condition that the hierarchy of the aggregation entity identifier corresponding to any sub-graph in the first target transaction link is a target hierarchy;

and generating convergent links corresponding to the loan funds according to the first target transaction links corresponding to the first target subgraph and the convergent entity identifiers.

Optionally, in another embodiment, the generating module 940 is configured to:

determining whether an aggregation entity corresponding to the aggregation entity identifier corresponding to the subgraph is a first target entity;

screening any sub-graph to obtain a second target sub-graph under the condition that the convergence entity corresponding to any sub-graph is the first target entity;

and generating convergent links corresponding to the loan funds according to the convergent entity identifiers and the group identifiers corresponding to each entity in the second target subgraph.

Optionally, in another embodiment, the obtaining module 910 is configured to:

acquiring transaction data of a plurality of loan funds in a target period;

entity extraction and relation extraction are carried out on transaction data of each loan fund in the plurality of loan funds so as to obtain entity identification and relation among entities of each loan fund for transaction;

constructing a knowledge graph according to entity identifiers and relationships among entities corresponding to the loan funds;

And searching a transaction link corresponding to each loan fund from the knowledge graph by taking a second target entity corresponding to each loan fund as a starting point and sequentially taking the first target relationship and the second target relationship as the basis.

In an exemplary embodiment, an electronic device is also presented.

Wherein, electronic equipment includes:

a processor;

a memory for storing processor-executable instructions;

Wherein the processor is configured to execute instructions to implement the method of generating a loan funds convergence link as set forth in any of the preceding embodiments.

As an example, fig. 10 is a schematic structural diagram of an electronic device 1000 according to an exemplary embodiment of the present disclosure, and as shown in fig. 10, the electronic device 1000 may further include:

the memory 1010 and the processor 1020, the bus 1030 connecting the different components (including the memory 1010 and the processor 1020), the memory 1010 stores a computer program, and the processor 1020 executes the program to implement the method for generating the loan funds convergence link according to the embodiments of the disclosure.

Bus 1030 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Electronic device 1000 typically includes many types of electronic device readable media. Such media can be any available media that is accessible by the electronic device 1000 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 1010 may also include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 1040 and/or cache memory 1050. The server 1000 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 1060 may be used to read from or write to a non-removable, non-volatile magnetic media (not shown in FIG. 10, commonly referred to as a "hard disk drive"). Although not shown in fig. 10, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 1030 through one or more data medium interfaces. Memory 1010 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the various embodiments of the disclosure.

A program/utility 1080 having a set (at least one) of program modules 1070 may be stored, for example, in memory 1010, such program modules 1070 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 1070 typically perform the functions and/or methods in the embodiments described in this disclosure.

The electronic device 1000 can also communicate with one or more external devices 1090 (e.g., keyboard, pointing device, display 1091, etc.), with one or more devices that enable a user to interact with the electronic device 1000, and/or with any device (e.g., network card, modem, etc.) that enables the electronic device 1000 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 1092. Also, the electronic device 1000 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through a network adapter 1093. As shown, the network adapter 1093 communicates with other modules of the electronic device 1000 via the bus 1030. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with the electronic device 1000, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

The processor 1020 executes various functional applications and data processing by running programs stored in the memory 1010.

It should be noted that, the implementation process and the technical principle of the electronic device in this embodiment refer to the foregoing explanation of the method for generating the loan funds convergence link in the embodiment of the disclosure, and are not repeated herein.

In an exemplary embodiment, a computer readable storage medium is also provided, e.g. a memory, comprising instructions executable by a processor of an electronic device to perform the method set forth in any of the embodiments described above. Alternatively, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program product is also provided, comprising a computer program/instruction, characterized in that the computer program/instruction, when executed by a processor, implements the method as set forth in any of the above embodiments.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method of generating a loan funds sink link, the method comprising:

acquiring transaction links of a plurality of loan funds in a target period;

2. The method of claim 1, wherein the generating the aggregate links corresponding to the plurality of loan funds according to the aggregate entity identifier and the group identifier corresponding to each entity in the subgraph comprises:

Determining a first target transaction link corresponding to the subgraph from the transaction links of the loan funds according to the aggregation entity identifier and the group identifier corresponding to each entity in the subgraph;

and generating the convergent links corresponding to the loan funds according to the first target transaction links corresponding to the subgraph and the convergent entity identifiers.

3. The method of claim 2, wherein the generating the aggregate links corresponding to the plurality of loan funds according to the first target transaction links and the aggregate entity identifiers corresponding to the subgraphs comprises:

deleting entity identifiers which are positioned behind the aggregation entity identifiers in the first target transaction link corresponding to the subgraph, and/or deleting branch links which do not contain the aggregation entity identifiers in the first target transaction link, so as to obtain a second target transaction link corresponding to the subgraph;

and taking the convergence entity identifier corresponding to the subgraph as a convergence point, and carrying out connection convergence on the second target transaction link to obtain convergence links corresponding to the loan funds.

4. The method of claim 2, wherein the generating the aggregate links corresponding to the plurality of loan funds according to the first target transaction links and the aggregate entity identifiers corresponding to the subgraphs comprises:

Determining whether a hierarchy in which the aggregation entity identifier corresponding to the subgraph is located in the first target transaction link is a target hierarchy or not;

screening any sub-graph to obtain a first target sub-graph under the condition that the hierarchy of the aggregation entity identifier corresponding to the any sub-graph in the first target transaction link is the target hierarchy;

and generating an aggregation link corresponding to the loan funds according to the first target transaction link corresponding to the first target subgraph and the aggregation entity identifier.

5. The method of claim 1, wherein the generating the aggregate links corresponding to the plurality of loan funds according to the aggregate entity identifier and the group identifier corresponding to each entity in the subgraph comprises:

determining whether the convergence entity corresponding to the convergence entity identifier corresponding to the subgraph is a first target entity;

screening any sub-graph to obtain a second target sub-graph under the condition that the convergence entity corresponding to the any sub-graph is the first target entity;

and generating an aggregation link corresponding to the loan funds according to the aggregation entity identifier and the group identifier corresponding to each entity in the second target subgraph.

6. The method of any one of claims 1-5, wherein the acquiring transaction links for a plurality of loans over a target period of time comprises:

Acquiring transaction data of the loan funds in the target period;

constructing a knowledge graph according to entity identifiers and relationships among entities corresponding to the plurality of loan funds respectively;

and sequentially searching a transaction link corresponding to each loan fund from the knowledge graph based on the first target relation and the second target relation by taking the second target entity corresponding to each loan fund as a starting point.

7. A device for generating a loan funds convergence link, the device comprising:

the extraction module is used for extracting entity identifiers from the transaction links of each loan fund in the plurality of loan funds to obtain an entity set corresponding to each loan fund;

the determining module is used for constructing a graph network according to the entity sets corresponding to the loan funds, and determining a sub-graph in the graph network and a convergent entity identifier and a group identifier corresponding to each entity in the sub-graph through a connected component algorithm;

And the generation module is used for generating the convergent links corresponding to the loan funds according to the convergent entity identifiers and the group identifiers corresponding to each entity in the subgraph.

8. The apparatus of claim 7, wherein the generating module is configured to:

9. The apparatus of claim 8, wherein the generating module is configured to:

10. The apparatus of claim 8, wherein the generating module is configured to:

11. The apparatus of claim 7, wherein the generating module is configured to:

12. The apparatus according to any one of claims 7-11, wherein the acquisition module is configured to:

Acquiring transaction data of the loan funds in the target period;

13. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of any one of claims 1 to 6.

14. A computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the method of any one of claims 1 to 6.

15. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-6.