Methods, devices, equipment and storage media for identifying bill intermediaries

Abstract

This invention provides a method, apparatus, equipment, and storage medium for identifying bill intermediaries, relating to the field of data processing technology. The method acquires bill data and behavioral characteristics of bill intermediaries, and based on this data and characteristics, generates a knowledge graph of the bill intermediaries. This graph can uncover typical behavioral characteristics of the bill intermediaries, establishing a behavioral network. Using this knowledge graph and the PageRank algorithm, the method can obtain the bill discounting institutions and their PageRank values. Target bill discounting institutions with PageRank values ​​greater than a preset threshold are identified as suspicious bill intermediaries. This allows business personnel to further audit these suspicious institutions, improving the accuracy of the judgment and significantly reducing labor and time costs.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method, apparatus, equipment, and storage medium for identifying bill intermediary institutions. Background Technology

[0002] Currently, bill intermediaries refer to specialized institutions that handle bill discounting, transfer, trading, and agency services, such as bill acceptance offices, bill discounting offices, and bill exchanges. Bill intermediaries provide information on bill buying and selling, charging handling fees and commissions. This practice, which does not involve the intermediary's own funds, plays a connecting and lubricating role in the bill market, and is legal and encouraged. However, some bill intermediaries directly participate in bill transactions, often by registering multiple affiliated companies, packaging non-compliant bills for circulation, and profiting from the price difference through buying low and selling high, leading to significant tax and financial risks.

[0003] In the current technology, the risk screening of bills by bank audit departments mainly relies on manual review by business personnel based on their past screening experience, which makes it impossible to objectively and effectively identify illegal bill intermediary institutions. Summary of the Invention

[0004] In view of the problems existing in the prior art, the present invention provides a method, apparatus, equipment and storage medium for identifying bill intermediary institutions, which can objectively and accurately identify suspicious bill intermediary institutions.

[0005] In a first aspect, embodiments of the present invention provide a method for identifying bill intermediary institutions, the method comprising:

[0006] Obtain bill data and behavioral characteristics from bill intermediaries;

[0007] Based on bill data and behavioral characteristics, a knowledge graph of bill intermediary institutions is generated;

[0008] Based on the knowledge graph and the PageRank algorithm, we obtain the bill discounting institutions and their PR values ​​among the bill intermediary institutions.

[0009] Target bill discounting institutions with PR values ​​greater than a preset threshold are identified as suspicious bill intermediary institutions.

[0010] This method for identifying bill intermediaries acquires their bill data and behavioral characteristics. Based on this data and characteristics, a knowledge graph of the bill intermediaries is generated. This graph can uncover typical behavioral features of the intermediaries and establish a behavioral network. Using this knowledge graph and the PageRank algorithm, the method can then determine the bill discounting institutions and their PageRank values. Target bill discounting institutions with PageRank values ​​exceeding a preset threshold are identified as suspicious bill intermediaries. This allows business personnel to conduct further audits based on the list of suspicious intermediaries, thereby improving the accuracy of the judgment and significantly reducing labor and time costs.

[0011] Optionally, based on bill data and behavioral characteristics, a knowledge graph of bill intermediaries is generated, including: obtaining the relationships between bill intermediaries and other institutions in the bill data, constructing network nodes of the knowledge graph and node attributes of the network nodes, wherein the network nodes include bill intermediaries and other institutions, the node attributes are used to characterize the attribute information of the network nodes, and the other institutions are institutions that have bill transfer and fund transaction behaviors with the bill intermediaries.

[0012] The behavioral characteristics of bill circulation and fund transaction are obtained from the behavioral features, and behavioral attributes between network nodes are constructed. The behavioral attributes are used to characterize the attribute information of the network nodes' bill circulation and fund transaction behaviors through preset banking institutions.

[0013] Optionally, based on the knowledge graph and the PageRank algorithm, the PR values ​​of bill discounting institutions and bill discounting institutions within the bill intermediary institutions are obtained, including:

[0014] Based on the knowledge graph, we can obtain the bill discounting institutions and their behavioral characteristics among bill intermediary institutions.

[0015] For each bill discounting institution, the PR value is calculated using the following formula:

[0016] PR = π k+1 =απ k A+(1-α)π0

[0017]

[0018]

[0019]

[0020] Where, π k+1 N represents the PR value of a bill discounting institution. ijN represents the number of bills transferred from bill intermediary institution i to bill discounting institution. i N represents the total amount of bills transferred from bill intermediary institution i. ij and N i The number of bill discounting institutions is determined by their behavioral characteristics, where n is the total number of bill intermediaries in the knowledge graph, α is the damping coefficient, and k is the number of times the PR value converges.

[0021] Optionally, after generating a knowledge graph of bill intermediaries based on bill data and behavioral characteristics, the method for identifying bill intermediaries further includes:

[0022] Based on the knowledge graph and the preset fund return matching rules, the fund return information of the bill discounting institution and the bill discounting institution in the bill intermediary institution is obtained.

[0023] Optionally, target bill discounting institutions with PR values ​​greater than a preset threshold may be identified as suspicious bill intermediaries, including:

[0024] Target bill discounting institutions whose fund return information meets the preset requirements are identified as suspicious bill intermediary institutions.

[0025] The preset requirements include that the amount of funds returned is greater than a preset amount or that the similarity between the amount of funds returned and the value of the bill is greater than a preset similarity.

[0026] Secondly, embodiments of the present invention provide an apparatus for identifying a bill intermediary institution, the apparatus comprising:

[0027] The acquisition module is configured to acquire bill data and behavioral characteristics of bill intermediaries;

[0028] The generation module is configured to generate a knowledge graph of bill intermediaries based on the bill data and behavioral characteristics. The knowledge graph is used to represent the bill transfer relationship and fund transaction relationship among multiple bill intermediaries.

[0029] The processing module is configured to perform operations based on the knowledge graph and the PageRank algorithm to obtain the bill discounting institutions and their PR values ​​among the bill intermediary institutions. The PR value is used to characterize the suspicion level of the bill discounting institution.

[0030] The identification module is configured to identify target bill discounting institutions with PR values ​​greater than a preset threshold as suspicious bill intermediaries.

[0031] Thirdly, embodiments of the present invention provide an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the method described in the first aspect.

[0032] Fourthly, embodiments of the present invention provide a storage medium storing a computer program, which, when executed by a processor, performs the steps of the method described in the first aspect.

[0033] The beneficial effects described in the second to fourth aspects above can be referred to in the first aspect, and will not be repeated here. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating the method for identifying bill intermediary institutions provided in an embodiment of the present invention is shown;

[0036] Figure 2 Another flowchart illustrating the method for identifying bill intermediary agencies provided in an embodiment of the present invention is shown;

[0037] Figure 3 This diagram illustrates the circulation of negotiable instruments using a method for identifying negotiable instrument intermediaries provided in an embodiment of the present invention.

[0038] Figure 4 This diagram illustrates the fund return process of the method for identifying bill intermediary institutions provided in an embodiment of the present invention.

[0039] Figure 5 Another flowchart illustrating the method for identifying bill intermediary agencies provided in an embodiment of the present invention is shown;

[0040] Figure 6 This invention illustrates the structure of a method for identifying intermediary agencies in bill trading, as provided in an embodiment of the present invention. Figure 1 ;

[0041] Figure 7 This invention provides a schematic diagram of the structure of a device for identifying intermediary institutions for negotiable instruments. Figure 2 ;

[0042] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in the present invention are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of the present invention. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this invention illustrate operations implemented according to some embodiments of the present invention. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this invention, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0044] Furthermore, the embodiments described herein are merely some, not all, of the embodiments of the invention. The components of the embodiments of the invention described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0045] It should be noted that the terms "comprising," "including," or any other variations thereof will be used in the embodiments of the present invention to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. It should also be noted that similar reference numerals and letters in the following figures denote similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In the description of the present invention, it should also be noted that the terms "first," "second," "third," etc., are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0046] First, let me explain some of the terms and techniques used in this application:

[0047] Bill intermediaries refer to specialized institutions that handle bill discounting, transfer, trading, and agency services, such as bill acceptance offices, bill discounting offices, and bill exchanges. In practice, bill intermediaries include not only bill acceptance and discounting institutions, but also brokers who facilitate transactions between buyers and sellers of bills. In markets with well-developed financing bills, they may even include professional rating agencies that rate commercial paper issuances and credit guarantee institutions.

[0048] A bill discounting institution refers to a place where a borrower requests cash from a bank or discounting company for a bank acceptance bill that has not yet matured. The bank or discounting company (financing company) accepts these bills that have not yet matured, deducts interest from the face value after the discount date, and pays the cash. The bank or discounting company (financing company) then collects the cash from the issuer when the bill matures.

[0049] PageRank, also known as the PageRank algorithm, is a technique that uses hyperlinks between web pages to measure the importance of a particular web page relative to other web pages in a search engine's index.

[0050] Currently, there are two main operating models for bill brokerage agencies: The first model involves providing bill trading information and charging handling fees and commissions. This model primarily involves collecting and publishing transaction information, then facilitating bill trading and charging a service fee. The second model involves directly participating in bill trading and profiting from the price difference. The specific process is as follows:

[0051] a. The bill brokerage agency first registers a shell company and opens an account at a bank;

[0052] b. Bill intermediary institutions use shell companies under their control to endorse bills purchased from enterprises to their shell companies.

[0053] c. Bill intermediary agencies forge false commodity transaction contracts and value-added tax invoices, and use shell companies to apply for discounting at banks;

[0054] d. After obtaining the discounted funds, the bill intermediary deducts the interest spread or handling fee and transfers the remaining amount to the account of the bill holder.

[0055] In the second operating model, the bill intermediary institutions that directly participate in the buying and selling of bills are the targets of bill market supervision. In order to evade supervision, some bill intermediary institutions often register multiple affiliated companies to circulate bills in an attempt to cover up their illegal activities, which can easily lead to huge tax risks and financial policy risks.

[0056] In the above circumstances, the identification of suspicious bill intermediaries is mainly done through manual screening. Suspicious bill intermediaries are screened by analyzing the characteristics of typical bill intermediaries, such as the concentration of the number of bills handled and the number of downstream bills. The transaction flow of suspicious bill intermediaries is also reviewed one by one to see if there is a clear process of discount fund return or other suspicious behavior to determine whether they are suspicious bill intermediaries.

[0057] However, the above identification process mainly relies on the experience of business personnel, which is highly subjective. This means that a lot of manpower and time are needed to judge the characteristics and transaction flow of suspicious bill intermediaries. If the characteristics judged by subjective experience do not match the behavioral characteristics of bill intermediaries well, this leads to low efficiency in identifying suspicious bill intermediaries.

[0058] Based on this, the present application provides a method for identifying bill intermediary institutions, wherein the executing entity is an apparatus for identifying bill intermediary institutions.

[0059] In one scenario, the device for identifying a bill intermediary can be an electronic device, which can be a server or a terminal device.

[0060] In some embodiments, the server can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center. This application does not limit the specific form of the server in its embodiments.

[0061] In some embodiments, the terminal device may be: a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, Internet of Things (IoT) device, etc. This application does not limit the specific form of the terminal device.

[0062] Figure 1The following is a flowchart illustrating the method for identifying bill intermediary institutions provided in an embodiment of the present invention, as shown in the figure. Figure 1 As shown, the method may include:

[0063] In step S101, the bill data and behavioral characteristics of the bill intermediary are obtained.

[0064] Generally, bill data refers to the bill data related to the bill intermediary's involvement in bill transactions, such as the endorsement and transfer data of the intermediary's accepted bills and directly discounted bills. Behavioral characteristics refer to the actions of the bill intermediary in executing bill transactions, such as data on bill circulation and fund transactions.

[0065] Optionally, bill data and behavioral characteristics of bill intermediaries within a preset time period of a preset bank can be extracted. For example, data on the endorsement and transfer of accepted bills and directly discounted bills, as well as current account transaction data of the branch over the past two years, can be extracted.

[0066] In step S102, a knowledge graph of the bill intermediary is generated based on bill data and behavioral characteristics.

[0067] By processing the acquired invoice data, the network nodes and node attributes of the knowledge graph are extracted, and feature analysis is performed on the behavioral characteristics to extract the behavioral attributes between the network nodes of the knowledge graph.

[0068] In step S103, based on the knowledge graph and the PageRank algorithm, the bill discounting institution and its PR value are obtained among the bill intermediary institutions.

[0069] The PR value is used to characterize the suspicion level of a bill discounting institution. Based on the bill circulation network and fund transaction network of bill intermediaries in the knowledge graph, the bill discounting institutions within the bill intermediaries are identified. If a bill intermediary has a large collection of bills, and these collected bills circulate among its affiliated discounting institutions, it will result in a high PR value for both the bill intermediary and its affiliated bill discounting institutions.

[0070] In step S104, target bill discounting institutions with PR values ​​greater than a preset threshold are identified as suspicious bill intermediary institutions.

[0071] You can select target bill discounting institutions with PR values ​​greater than a preset threshold, or you can select the top 20 target bill discounting institutions with the highest PR values. The higher the PR value of these target bill discounting institutions, the higher their level of suspicion.

[0072] It should be noted that, in this embodiment of the application, the process of generating the knowledge graph of the aforementioned bill intermediary institution is not limited here.

[0073] This method for identifying bill intermediaries acquires their bill data and behavioral characteristics. Based on this data and characteristics, a knowledge graph of the bill intermediaries is generated. This graph can uncover typical behavioral features of the intermediaries and establish a behavioral network. Using this knowledge graph and the PageRank algorithm, the method can then determine the bill discounting institutions and their PageRank values. Target bill discounting institutions with PageRank values ​​exceeding a preset threshold are identified as suspicious bill intermediaries. This allows business personnel to conduct further audits based on the list of suspicious intermediaries, thereby improving the accuracy of the judgment and significantly reducing labor and time costs.

[0074] Optionally, Figure 2 Another flowchart illustrating the method for identifying bill intermediaries provided in an embodiment of the present invention is shown. Figure 2 As shown, based on bill data and behavioral characteristics, a knowledge graph of bill intermediaries is generated, including:

[0075] In step S201, the relationships between bill intermediaries and other institutions in the bill data are obtained, and the network nodes of the knowledge graph and the node attributes of the network nodes are constructed.

[0076] Among them, network nodes include bill intermediaries and other institutions. Node attributes are used to characterize the attribute information of network nodes. Other institutions are those that have bill transfer and fund transaction activities with bill intermediaries.

[0077] For example, the node attributes of a bill intermediary may include the number of endorsed bills, the number of upstream companies, the start time of endorsement transfer, and the end time of endorsement transfer.

[0078] In step S202, the bill circulation behavior characteristics and fund transaction behavior characteristics in the behavioral characteristics are obtained to construct the behavioral attributes between network nodes.

[0079] Among them, behavioral attributes are used to characterize the attribute information of network nodes’ bill circulation and fund transaction behaviors through preset banking institutions.

[0080] For example, characteristics of negotiable instrument circulation may include the number of negotiable instruments circulated, the amount of negotiable instruments circulated, the start time of endorsement transfer, and the end time of endorsement transfer. Characteristics of fund transaction behavior may include the transaction amount, the start time of the transaction, and the end time of the transaction.

[0081] For example, such as Figure 3 , Figure 4 As shown, all network nodes and attribute information can be imported into the Neo4j graph database to generate a knowledge graph of bill circulation and fund transactions. The tables and their structures imported into the Neo4j graph database can be as follows:

[0082] a) Network node list of bill intermediary institutions:

[0083] Node attributes: number of endorsed notes, number of upstream companies, start time of endorsement transfer, end time of endorsement transfer.

[0084] b) Network node list of bill discounting institutions:

[0085] Node attribute: Number of discounted bills.

[0086] c) Table of bill transfers between bill intermediaries and other institutions:

[0087] Behavioral attributes: number of circulating bills, amount of circulating bills, start time of endorsement transfer, and end time of endorsement transfer.

[0088] d) Statement of fund transfers between bill intermediaries and other institutions:

[0089] Behavioral attributes: transaction amount, transaction start time, and transaction end time.

[0090] It should be noted that there are no restrictions on the process of generating tables and structures for the knowledge graph, as long as it can generate a knowledge graph of the circulation of bills and the fund transactions of bill intermediaries.

[0091] By generating a knowledge graph of bill intermediaries based on bill data and behavioral characteristics, the graph database can express the relationships between network nodes and uncover the degree relationships between network nodes, making the analysis of the behavioral characteristics of bill intermediaries simpler and more intuitive.

[0092] In one embodiment, the knowledge graph of the bill brokerage firm fits well with two assumptions of the PageRank algorithm:

[0093] A. Quantitative Assumption: The greater the in-degree (number of bills circulated) of a network node, the higher the probability that the network node is identified as a suspicious bill intermediary.

[0094] B. Quality Assumption: The higher the source of an in-degree of a network node (i.e., the rate at which upstream entities are identified as suspicious bill intermediaries), the higher the probability that the network node will be identified as a suspicious bill intermediary.

[0095] Optional, such as Figure 5 As shown, based on the knowledge graph and the PageRank algorithm, the PR values ​​of bill discounting institutions and bill discounting institutions among bill intermediaries are obtained, including:

[0096] In step S501, based on the knowledge graph, the bill discounting institution and its behavioral characteristics are obtained among the bill intermediary institutions.

[0097] By using the knowledge graph of the aforementioned bill intermediaries, it is possible to identify bill intermediaries with multiple upstream bill inflow activities and concentrated bill outflow activities. For example, as described above... Figure 3 As shown, Company A is a bill intermediary. Continuing with the knowledge graph of the aforementioned bill intermediaries, the fund transaction activities of this intermediary can be identified. This allows us to identify bill discounting institutions among the bill intermediaries with fund transaction activities. The behavioral characteristics of these bill discounting institutions include multiple upstream bill inflow activities and fund outflow activities similar to those of the bills in question. For example, as described above... Figure 4 As shown, Company A is a bill discounting institution.

[0098] In step S502, for each bill discounting institution, the PR value of the bill discounting institution is calculated using the following formula:

[0099] PR = π k+1 =απ k A+(1-α)π0

[0100]

[0101]

[0102]

[0103] Where, π k+1 N represents the PR value of a bill discounting institution. ij N represents the number of bills transferred from bill intermediary institution i to bill discounting institution. i N represents the total amount of bills transferred from bill intermediary institution i. ij and N i The number of bill discounting institutions is determined by their behavioral characteristics, where n is the total number of bill intermediaries in the knowledge graph, α is the damping coefficient, and k is the number of times the PR value converges.

[0104] It should be noted that the presence of termination points (nodes with no outgoing links) and traps (nodes with only links pointing to themselves) in the knowledge graph network diagram can lead to extreme results in the final PageRank (PR) value. Therefore, a damping factor of 0.85 can be set. The damping factor represents the probability that the user will continue to click the next link in the network diagram, and 1 - 0.85 = 0.15 represents the probability that the user will randomly access any network node. In this way, the problem is solved.

[0105] Based on the knowledge graph, we obtain the bill discounting institutions and their behavioral characteristics among the bill intermediaries, calculate and output the PR value of the bill discounting institutions. Since bill intermediaries collect a large number of bills from enterprises and then circulate them among their affiliated companies, the bill receiving companies and their affiliated companies will all receive high PR values, thus being identified as suspicious bill intermediaries.

[0106] Optionally, after generating a knowledge graph of bill intermediaries based on bill data and behavioral characteristics, the method for identifying bill intermediaries further includes:

[0107] Based on the knowledge graph and the preset fund return matching rules, the fund return information of the bill discounting institution and the bill discounting institution in the bill intermediary institution is obtained.

[0108] Target bill discounting institutions with PR values ​​greater than a preset threshold are identified as suspicious bill intermediaries, including:

[0109] Target bill discounting institutions whose fund return information meets the preset requirements are identified as suspicious bill intermediary institutions.

[0110] The preset requirements include that the amount of funds returned is greater than a preset amount or that the similarity between the amount of funds returned and the value of the bill is greater than a preset similarity.

[0111] Based on the fund transaction relationships in the generated knowledge graph, preset fund return matching rules can be used to statistically analyze the fund return information of bill discounting institutions and output the results. The preset fund return matching rules can be set according to the fund return behavior characteristics of bill intermediaries and bill discounting institutions, and are not restricted here.

[0112] For example, in the case of primary fund repatriation, Company A (a bill intermediary) transfers bills to Company B, and Company B (a bill discounting institution) transfers funds back to Company A. When the amount of fund repatriation is huge, or when the amount of fund repatriation is close to the value of the bills, the behavior between the two companies becomes highly suspicious, and Company B will be identified as a suspicious bill intermediary.

[0113] Optionally, methods for identifying bill intermediaries also include: obtaining business transaction information, discounting information, and related downstream information of suspicious bill intermediaries from a knowledge graph.

[0114] By combining the PR value and primary fund return information of bill discounting institutions, suspicious bill intermediaries can be more accurately identified. Furthermore, business dealings, discounting information, and related downstream information of these suspicious intermediaries can be obtained from a knowledge graph to construct their social network diagram, discounting social network diagram, and downstream network diagram. Specifically, the social network diagram shows all relationships between the suspicious bill intermediary and its upstream and downstream companies, including bill transactions and fund transactions; the discounting social network diagram shows all relationships between the suspicious bill intermediary and its upstream and downstream discounting companies; and the downstream network diagram shows all relationships between the suspicious bill intermediary and its downstream companies.

[0115] By drawing such a network diagram, business personnel can easily and intuitively identify bill intermediary groups, understand the role of the bill intermediary in the network, and determine whether the company is a suspicious bill intermediary.

[0116] Based on the method for identifying bill intermediaries described in the foregoing embodiments, this invention also provides an apparatus for identifying bill intermediaries. Figure 6 A schematic diagram of the structure of the device for identifying intermediary institutions for negotiable instruments provided in an embodiment of the present invention is shown.

[0117] like Figure 6 As shown, the device for identifying bill intermediaries includes: an acquisition module 601, configured to acquire bill data and behavioral characteristics of the bill intermediary;

[0118] The generation module 602 is configured to generate a knowledge graph of bill intermediaries based on the bill data and behavioral characteristics. The knowledge graph is used to represent the bill transfer relationship and fund transaction relationship among multiple bill intermediaries.

[0119] Processing module 603 is configured to perform operations based on knowledge graphs and PageRank algorithms to obtain bill discounting institutions and their PR values ​​among bill intermediary institutions. The PR value is used to characterize the suspicion level of the bill discounting institution.

[0120] The identification module 604 is configured to identify target bill discounting institutions with PR values ​​greater than a preset threshold as suspicious bill intermediary institutions.

[0121] Optionally, such as Figure 7 As shown, the above-mentioned generation module 602 also includes:

[0122] The node construction module 6021 is configured to perform operations such as acquiring the relationship between bill intermediaries and other institutions in the bill data, constructing network nodes of the knowledge graph and node attributes of the network nodes. The network nodes include the bill intermediaries and other institutions, and the node attributes are used to characterize the attribute information of the network nodes. Other institutions are institutions that have bill transfer and fund transaction behaviors with the bill intermediaries.

[0123] The behavior attribute construction module 6022 is configured to acquire the bill circulation behavior feature and fund transaction behavior feature in the behavior features, and construct the behavior attributes between network nodes. The behavior attributes are used to characterize the attribute information of the network nodes' bill circulation behavior and fund transaction behavior through preset banking institutions.

[0124] Processing module 603 is configured to perform operations based on the knowledge graph and PageRank algorithm to obtain the bill discounting institution and its PR value among the bill intermediary institutions, specifically including:

[0125] Based on the knowledge graph, we can obtain the bill discounting institutions and their behavioral characteristics among bill intermediary institutions.

[0126] For each bill discounting institution, the PR value is calculated using the following formula:

[0127] PR = π k+1 =απ k A+(1-α)π0

[0128]

[0129]

[0130]

[0131] Where, π k+1 N represents the PR value of a bill discounting institution. ij N represents the number of bills transferred from bill intermediary institution i to bill discounting institution. i N represents the total amount of bills transferred from bill intermediary institution i. ij and N i The number of bill discounting institutions is determined by their behavioral characteristics, where n is the total number of bill intermediaries in the knowledge graph, α is the damping coefficient, and k is the number of times the PR value converges.

[0132] Optionally, the processing module 603 is also configured to perform operations based on the knowledge graph and preset fund return matching rules to obtain the bill discounting institution and the fund return information of the bill discounting institution among the bill intermediary institutions.

[0133] Optionally, the identification module 604 is configured to identify target bill discounting institutions with PR values ​​greater than a preset threshold as suspicious bill intermediaries, specifically including:

[0134] Target bill discounting institutions whose fund return information meets the preset requirements are identified as suspicious bill intermediary institutions.

[0135] Optionally, the preset requirements include that the amount of funds returned is greater than a preset amount or that the similarity between the amount of funds returned and the value of the bill is greater than a preset similarity.

[0136] Optionally, the generation module 602 is further configured to retrieve business transaction information, discounting information, and related downstream information of the suspected bill intermediary from the knowledge graph.

[0137] The aforementioned device can be integrated into servers, computers, and other devices, and this invention does not impose any limitations thereon. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of this device for identifying bill intermediaries can be referred to the corresponding process of the method for identifying bill intermediaries described in the foregoing method embodiments, and its effect corresponds to the effect of the method for identifying bill intermediaries described in the foregoing method embodiments. Therefore, it will not be described again in this invention.

[0138] It should be understood that the device embodiments described above are merely illustrative, and the devices and methods disclosed in the embodiments of the present invention can also be implemented in other ways. For example, the division of modules is only a logical functional division, and there may be other division methods in actual implementation. For another example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or modules may be electrical, mechanical, or other forms. Additionally, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause the processor to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0140] That is, those skilled in the art should understand that the embodiments of the present invention can be implemented in any of the following forms: a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0141] Based on this, embodiments of the present invention also provide a program product, which can be a storage medium such as a USB flash drive, portable hard drive, ROM, RAM, magnetic disk, or optical disk. The storage medium can store a computer program, which, when run by a processor, executes the steps of the method for identifying bill intermediary institutions as described in the foregoing method embodiments. The specific implementation and technical effects are similar and will not be repeated here.

[0142] Optionally, embodiments of the present invention also provide an electronic device, which may be a server, computer, or other similar device. Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention is shown.

[0143] like Figure 8 As shown, the electronic device may include a processor 801, a storage medium 802, and a bus 803. The storage medium 802 stores machine-readable instructions executable by the processor 801. When the electronic device is running, the processor 801 communicates with the storage medium 802 via the bus 803. The processor 801 executes the machine-readable instructions to perform the steps of the method for identifying a bill intermediary institution as described in the foregoing embodiments. The specific implementation and technical effects are similar and will not be repeated here.

[0144] For ease of explanation, only one processor is described in the above-described electronic device. However, it should be noted that in some embodiments, the electronic device of the present invention may also include multiple processors. Therefore, the steps performed by one processor as described in the present invention may also be performed jointly or individually by multiple processors. For example, if the processor of the electronic device performs steps A and B, it should be understood that steps A and B may also be performed jointly by two different processors or individually by one processor. For example, a first processor performs step A, a second processor performs step B, or a first processor and a second processor jointly perform steps A and B, etc.

[0145] In some embodiments, the processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). By way of example only, the processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction-set Processor (ASIP), a Graphics Processing Unit (GPU), a Physics Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computing (RISC) computer, or a microprocessor, or any combination thereof.

[0146] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for identifying bill intermediaries, characterized in that, The method includes: Obtain bill data and behavioral characteristics of bill intermediary institutions, wherein the behavioral characteristics are used to characterize the bill circulation behavior and fund transaction behavior of the bill intermediary institutions; Based on the bill data and behavioral characteristics, a knowledge graph of the bill intermediary institution is generated; Based on the knowledge graph and the PageRank algorithm, the bill discounting institutions among the bill intermediary institutions and their PR values ​​are obtained. The PR values ​​are used to characterize the suspicion level of the bill discounting institutions. Target bill discounting institutions whose PR value is greater than a preset threshold are identified as suspicious bill intermediary institutions; The process of generating a knowledge graph of the bill intermediary institution based on the bill data and behavioral characteristics includes: The relationships between bill intermediaries and other institutions in the bill data are obtained, and the network nodes and node attributes of the knowledge graph are constructed. The network nodes include the bill intermediaries and the other institutions. The node attributes are used to characterize the attribute information of the network nodes. The other institutions are those that have bill transfer and fund transaction activities with the bill intermediaries. The node attributes of the bill intermediaries include the number of endorsed bills, the number of upstream companies, the start time of endorsement transfer, and the end time of endorsement transfer. The behavioral characteristics of bill circulation and fund transaction are obtained. The bill circulation behavior characteristics include the number of bills circulated, the amount of bills circulated, the start time of endorsement transfer, and the end time of endorsement transfer. The fund transaction behavior characteristics include the transaction amount, the start time of the transaction, and the end time of the transaction. Behavioral attributes between the network nodes are constructed. The behavioral attributes are used to characterize the attribute information of the network nodes' bill circulation and fund transaction behaviors through preset banking institutions.

2. The method according to claim 1, characterized in that, Based on the knowledge graph and the PageRank algorithm, the bill discounting institutions among the bill intermediary institutions and their PageRank values ​​are obtained, including: Based on the knowledge graph, obtain the bill discounting institutions among the bill intermediary institutions and the behavioral characteristics of the bill discounting institutions; For each of the aforementioned bill discounting institutions, the PR value of the bill discounting institution is calculated using the following formula: PR=π k+1 =from k A+(1-α)π0 Where, π k+1 N represents the PR value of the bill discounting institution. ij N represents the number of bills transferred from the bill intermediary institution i to the bill discounting institution. i N represents the total amount of bills transferred from the bill intermediary institution i. ij and the N i The number of bill discounting institutions is determined by the behavioral characteristics of the bill discounting institutions, where n is the total number of bill intermediary institutions in the knowledge graph, α is the damping coefficient, and k is the number of times the PR value converges.

3. The method according to claim 1, characterized in that, After the step of generating the knowledge graph of the bill intermediary institution based on the bill data and behavioral characteristics, the method further includes: Based on the knowledge graph and the preset fund return matching rules, the bill discounting institutions among the bill intermediary institutions and the fund return information of the bill discounting institutions are obtained.

4. The method according to claim 3, characterized in that, The target bill discounting institution with a PR value greater than a preset threshold is identified as a suspicious bill intermediary institution, including: The target bill discounting institutions whose fund return information meets the preset requirements are identified as suspicious bill intermediary institutions.

5. The method according to claim 4, characterized in that, The preset requirements include that the amount of funds returned is greater than a preset amount or that the similarity between the amount of funds returned and the value of the bill is greater than a preset similarity.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: The business dealings, discounting information, and related downstream information of the suspicious bill intermediary are obtained from the knowledge graph.

7. A device for identifying a bill intermediary, characterized in that, The device includes: The acquisition module is configured to acquire bill data and behavioral characteristics of bill intermediaries; The generation module is configured to generate a knowledge graph of the bill intermediary based on the bill data and behavioral characteristics. The knowledge graph is used to represent the bill transfer relationship and fund transaction relationship among multiple bill intermediaries. The processing module is configured to perform operations based on the knowledge graph and the PageRank algorithm to obtain the bill discounting institution among the bill intermediary institutions and the PR value of the bill discounting institution, wherein the PR value is used to characterize the suspicion level of the bill discounting institution; The identification module is configured to identify target bill discounting institutions with PR values ​​greater than a preset threshold as suspicious bill intermediary institutions. The generation module further includes: The node construction module is configured to retrieve the relationships between bill intermediaries and other institutions in the bill data, construct the network nodes of the knowledge graph, and define the node attributes of the network nodes. The network nodes include the bill intermediaries and the other institutions. The node attributes characterize the attribute information of the network nodes. The other institutions are those that have bill transfer and fund transaction activities with the bill intermediaries. The node attributes of the bill intermediaries include the number of endorsed bills, the number of upstream companies, the start time of endorsement transfer, and the end time of endorsement transfer. The behavioral attribute construction module is configured to acquire the bill circulation behavioral characteristics and fund transaction behavioral characteristics from the behavioral features. The bill circulation behavioral characteristics include the number of bills in circulation, the amount of bills in circulation, the start time of endorsement transfer, and the end time of endorsement transfer. The fund transaction behavioral characteristics include the transaction amount, the start time of the transaction, and the end time of the transaction. The module constructs behavioral attributes between the network nodes, which are used to characterize the attribute information of the network nodes' bill circulation behavior and fund transaction behavior through preset banking institutions.

8. The apparatus according to claim 7, characterized in that, The processing module is configured to perform operations based on the knowledge graph and the PageRank algorithm to obtain the bill discounting institutions among the bill intermediary institutions and their PR values, specifically including: Based on the knowledge graph, obtain the bill discounting institutions among the bill intermediary institutions and the behavioral characteristics of the bill discounting institutions; For each of the aforementioned bill discounting institutions, the PR value of the bill discounting institution is calculated using the following formula: PR=π k+1 =from k A+(1-α)π0 Where, π k+1 N represents the PR value of the bill discounting institution. ij N represents the number of bills transferred from the bill intermediary institution i to the bill discounting institution. i N represents the total amount of bills transferred from the bill intermediary institution i. ij and the N i The number of bill discounting institutions is determined by the behavioral characteristics of the bill discounting institutions, where n is the total number of bill intermediary institutions in the knowledge graph, α is the damping coefficient, and k is the number of times the PR value converges.

9. The apparatus according to claim 7, characterized in that, The processing module is also configured to execute, based on the knowledge graph and preset fund return matching rules, to obtain the bill discounting institution among the bill intermediary institutions and the fund return information of the bill discounting institution.

10. The apparatus according to claim 9, characterized in that, The identification module is configured to identify target bill discounting institutions with PR values ​​greater than a preset threshold as suspicious bill intermediaries, specifically including: The target bill discounting institutions whose fund return information meets the preset requirements are identified as suspicious bill intermediary institutions.

11. The apparatus according to claim 10, characterized in that, The preset requirements include that the amount of funds returned is greater than a preset amount or that the similarity between the amount of funds returned and the value of the bill is greater than a preset similarity.

12. The apparatus according to any one of claims 7-11, characterized in that, The generation module is also configured to retrieve business transaction information, discounting information, and related downstream information of the suspicious bill intermediary from the knowledge graph.

13. An electronic device, characterized in that, include: The electronic device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the method as described in any one of claims 1 to 6.

14. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, performs the steps of the method as described in any one of claims 1 to 6.

Images