Method and system for identifying special benefit transmission link
By combining corporate registration and judicial information, extracting key characteristics of counterparties and constructing transaction curves, and using a mean square error calculation model to identify potential special interest transfer links, this technology overcomes the limitations of existing technologies in identifying interest transfers between companies without business or equity relationships, and achieves a wider range of identification effects.
Patent Information
- Application Number
- CN202411113881.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-22
AI Technical Summary
Existing technologies have limitations in identifying potential indirect relationships between enterprises and cannot effectively identify the transfer of benefits between enterprises that have no industrial or commercial equity relationship.
By combining corporate registration and legal information, key characteristics of counterparties are extracted, and transaction curves are constructed. A mean square error calculation model is used to identify potential channels for the transfer of special benefits.
It expands the scope of identification of special interest transfers and can effectively identify interest transfers between enterprises that have no industrial or commercial equity relationship.
Smart Images

Figure CN119006162A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of information identification, and relates to a method and system for identifying a special benefit delivery link. Background Art
[0002] In recent years, enterprises have focused on risk prevention and control of cooperative merchants and strictly investigated all kinds of false trade behaviors. For special interests, the current risk control models on the market evaluate the credit of enterprises and identify whether there are industrial and commercial equity relations between enterprises to identify and avoid the occurrence of related transactions.
[0003] The existing special interest transfer identification method based on whether there is an industrial and commercial equity relationship between enterprises has identification limitations. For enterprises that are not related in terms of industrial and commercial information, the industrial and commercial equity model cannot discover the potential indirect relationship between merchants. Through the method proposed in the present invention, the industrial and commercial information and judicial information of enterprises are combined with enterprise transaction information, which can effectively solve the problem of identifying the interest transfer between member units and enterprises that have no industrial and commercial equity relationship. Summary of the invention
[0004] In response to the above problems, the present invention discloses a method for identifying special interest transfer links, which can combine corporate industrial and commercial, judicial information and corporate transaction information, thereby effectively solving the problem of interest transfer between companies without industrial and commercial equity relations.
[0005] To achieve the above-mentioned object of the invention, the technical solution of the present invention includes the following contents.
[0006] A method for identifying a special interest delivery link, the method comprising:
[0007] Obtaining the counterparties of the member units and extracting the key enterprise characteristics of the counterparties; wherein the counterparties include: suppliers and customers;
[0008] Select key companies from the counterparties based on key features;
[0009] Constructing a transaction curve chart of all transaction counterparties, wherein the enterprise transaction curve chart is used to display all transactions between the transaction counterparty and the member unit within a set time range;
[0010] Based on the transaction curve of key focus companies, identify suppliers and customers with special interest delivery links.
[0011] Furthermore, the key characteristics of the enterprise include: registration time, registered capital, paid-in capital, number of social security payers, industrial and commercial business status, industrial and commercial equity status, business affiliation status, transaction amount Y with member units, first cooperation time n with member units, whether it is currently included in the abnormal catalogue, and whether there are any disputes with member units; among them, the abnormal catalogue includes: restrictions on high consumption, dishonest debtors, military procurement dishonest list, government procurement dishonest list and bill exchange overdue list.
[0012] Furthermore, the screening of key enterprises from counterparties based on key features includes:
[0013] If a trading counterparty is included in the abnormal catalogue, the trading counterparty shall be identified as a key concern enterprise;
[0014] and,
[0015] When the difference rate between the registered capital of the transaction counterparty and the transaction amount Y is greater than the first set threshold, the transaction counterparty is determined to be a key focus enterprise;
[0016] and,
[0017] When the difference between the registration time of the transaction counterparty and the first cooperation time n is less than the second set threshold, the transaction counterparty is determined to be a key focus enterprise;
[0018] and,
[0019] When the difference between the number of social security payers of the counterparty and the transaction amount Y is greater than the third set threshold, the counterparty is determined to be a key focus enterprise;
[0020] and,
[0021] If the business operation status of the counterparty is deregistered, the counterparty shall be deemed as a key focus enterprise;
[0022] and,
[0023] If the industrial and commercial equity status of the counterparty is related to a member unit, but the business affiliation status is that of an external enterprise that is not a subsidiary of a member unit and there is suspected business affiliation, the counterparty will be determined as a key focus enterprise;
[0024] and,
[0025] In the event of a dispute between a counterparty and a member unit, the counterparty will be identified as a key focus enterprise.
[0026] Furthermore, in the case where the key focus enterprise is a supplier, obtaining suppliers and customers with special benefit delivery links based on the transaction curve graph of the key focus enterprise includes:
[0027] Get the enterprise transaction curve P of the focused enterprise i i The enterprise transaction curve P with customer j j , i and j are natural numbers;
[0028] Based on the transaction nodes in the enterprise transaction curve graph, calculate the enterprise transaction curve graph P i The mean square error and enterprise transaction curve P j The mean square error
[0029] In the mean square error With the mean square error When the difference is less than the fourth set threshold, it is determined that there is a special interest transfer link between the focused enterprise i and the customer j.
[0030] Furthermore, in the case where the key focus enterprise is a customer, obtaining suppliers and customers with special interest delivery links based on the transaction curve graph of the key focus enterprise includes:
[0031] Get the enterprise transaction curve P of the focused enterprise u u The enterprise transaction curve P with supplier v v , u and v are natural numbers;
[0032] Based on the transaction nodes in the enterprise transaction curve graph, calculate the enterprise transaction curve graph P u The mean square error and enterprise transaction curve P v The mean square error
[0033] In the mean square error With the mean square error When the difference is less than the fifth set threshold, it is determined that there is a special interest transfer link between the focused enterprise u and the supplier v.
[0034] A system for identifying a special interest delivery link, the system comprising:
[0035] A feature extraction module is used to obtain the counterparties of the member units and extract the key enterprise features of the counterparties; wherein the counterparties include: suppliers and customers;
[0036] Enterprise screening module, used to select key enterprises from counterparties based on key features;
[0037] A graph construction module, used to construct a transaction curve graph of all transaction counterparties, wherein the enterprise transaction curve graph is used to display all transactions between the transaction counterparty and the member unit within a set time range;
[0038] The anomaly identification module is used to identify suppliers and customers with special interest delivery links based on the transaction curve chart of key focus enterprises.
[0039] An electronic device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for identifying a special benefit delivery link as described in any one of the above items is implemented.
[0040] A computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement any of the above-mentioned methods for identifying a special benefit delivery link.
[0041] Compared with the prior art, the present invention combines corporate industrial and commercial, judicial information and corporate transaction information, which can effectively solve the problem of identifying interest transfer behavior between companies without industrial and commercial equity relations, and expand the identification scope of special interest links. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 Flowchart of a method for identifying special interest delivery links. DETAILED DESCRIPTION
[0043] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0044] The present invention integrates multi-dimensional data, including internal financial capital flow data of enterprises, as well as external industrial and commercial and judicial data. For internal and external big data, the model classifies trading counterparties according to key features, and then combines transaction data to identify and screen out upstream and downstream enterprises with matching transaction rhythms.
[0045] like Figure 1 As shown, the method for identifying a special interest delivery link of the present invention includes the following contents.
[0046] Step 1: Obtain the counterparties of the member units and extract the key corporate characteristics of the counterparties.
[0047] The present invention extracts key features of enterprises from industrial and commercial, judicial and other data of enterprises, including: registration time, registered capital, paid-in capital, number of social security payers, industrial and commercial operation status, industrial and commercial equity status, business affiliation status, transaction amount Y with member units, first cooperation time n with member units, whether it is currently included in the abnormal catalogue, and whether there are any disputes with member units; wherein the abnormal catalogue includes: restrictions on high consumption, dishonest persons subject to execution, military procurement dishonest list, government procurement dishonest list and bill exchange overdue list.
[0048] Step 2: Select key companies from among the counterparties based on key features.
[0049] The present invention is based on key features and the key focus enterprises can include the following categories:
[0050] 1) The model classifies enterprises according to their key characteristics. Enterprises that are included in the list of restricted high consumption, dishonest persons subject to enforcement, the list of dishonest persons in military procurement, the list of dishonest persons in government procurement, and the list of overdue bills of the Bill Exchange will be classified as key focus enterprises due to their credit anomalies.
[0051] 2) Enterprises with a difference rate of registered capital X and member unit transaction amount Y greater than m% will be classified as key focus enterprises due to industrial and commercial anomalies.
[0052] 3) Enterprises whose registration time m and the first cooperation time n of member units differ by less than Q days are classified as key focus enterprises due to industrial and commercial anomalies.
[0053] 4) Enterprises with a difference of p, the number of social security contributors and Y, which is greater than t, will be classified as key focus enterprises due to industrial and commercial anomalies.
[0054] 5) Enterprises whose industrial and commercial business status is cancelled are classified as key focus enterprises due to industrial and commercial abnormalities.
[0055] 6) External enterprises that have industrial and commercial equity linked to member units but are not subsidiaries of member units are classified as key focus enterprises due to their business affiliation.
[0056] 7) Merchants who have disputes with member units will be classified as key focus enterprises due to the disputes.
[0057] Step 3: Construct a trading curve graph for all counterparties.
[0058] In one embodiment, the present invention extracts the transaction flow of all transaction counterparties for one year to construct a transaction curve chart, wherein the transaction curve chart uses time as the horizontal axis and the transaction amount as the vertical axis.
[0059] Step 4: Based on the transaction curve of the key companies, identify suppliers and customers with special benefit transmission links.
[0060] Since the focused enterprise may be a supplier or a customer, the present invention considers two aspects.
[0061] When the focused enterprise is a supplier, the transaction curve of the supplier is compared with the customers of the member units in the same time range. By comparing the nodes of the curve, the mean square error t is calculated. If the mean square error of the two enterprises is less than X, it proves that the transaction rhythm of the two enterprises is consistent within a year, and there is a risk of special interest transfer.
[0062] When the focused enterprise is a customer, the transaction curve of the customer is compared with the supplier of the member unit in the same time range. By comparing the nodes of the curve, the mean square error t is calculated. If the mean square error of the two enterprises is less than X, it proves that the transaction rhythm of the two enterprises is consistent within a year, and there is a risk of special interest transfer.
[0063] In summary, the identification method provided by the present invention refines and analyzes key companies through seven dimensions, extracts key characteristics of customers, and then identifies companies that have the potential to transfer benefits and artificially increase unnecessary transaction links.
[0064] The present invention uses a mean square error calculation model to determine the degree of coincidence of the current transaction curve fitting. The closer the mean square error value is to 0, the higher the degree of fit. The fitting threshold can be adjusted by user, and if it is less than or equal to the fitting threshold, an early warning transaction rhythm is consistent.
[0065] The above implementation is only used to illustrate the technical solution of the present invention rather than to limit it. Ordinary technicians in this field can modify or replace the technical solution of the present invention with equivalents without departing from the scope of the present invention. The protection scope of the present invention shall be based on the claims.
Claims
1. A method for identifying a special interest transmission link, characterized in that: The method comprises: Obtaining the counterparties of the member units and extracting the key enterprise characteristics of the counterparties; wherein the counterparties include: suppliers and customers; Select key companies from the counterparties based on key features; Constructing a transaction curve chart of all transaction counterparties, wherein the enterprise transaction curve chart is used to display all transactions between the transaction counterparty and the member unit within a set time range; Based on the transaction curve of key focus companies, identify suppliers and customers with special interest delivery links.
2. The method according to claim 1, characterized in that The key characteristics of the enterprise include: registration time, registered capital, paid-in capital, number of social security payers, industrial and commercial business status, industrial and commercial equity status, business affiliation status, transaction amount Y with member units, first cooperation time n with member units, whether it is currently included in the abnormal catalogue, and whether there are disputes with member units; among them, the abnormal catalogue includes: restrictions on high consumption, dishonest debtors, military procurement dishonest list, government procurement dishonest list and bill exchange overdue list.
3. The method according to claim 2, characterized in that The above mentioned companies of focus are selected from the counterparties based on key features, including: If a trading counterparty is included in the abnormal catalogue, the trading counterparty shall be identified as a key concern enterprise; and, When the difference rate between the registered capital of the transaction counterparty and the transaction amount Y is greater than the first set threshold, the transaction counterparty is determined to be a key focus enterprise; and, When the difference between the registration time of the transaction counterparty and the first cooperation time n is less than the second set threshold, the transaction counterparty is determined to be a key focus enterprise; and, When the difference between the number of social security payers of the counterparty and the transaction amount Y is greater than the third set threshold, the counterparty is determined to be a key focus enterprise; and, If the business operation status of the counterparty is deregistered, the counterparty shall be deemed as a key focus enterprise; and, If the industrial and commercial equity status of the counterparty is associated with a member unit, but an external enterprise that is not a subsidiary of the member unit is suspected of operating under affiliation, the counterparty is determined to be a key focus enterprise; and, In the event of a dispute between a counterparty and a member unit, the counterparty will be identified as a key focus enterprise.
4. The method according to claim 1, characterized in that: In the case where the key focus enterprise is a supplier, obtaining suppliers and customers with special interest delivery links based on the transaction curve graph of the key focus enterprise includes: Get the enterprise transaction curve P of the focused enterprise i i The enterprise transaction curve P with customer j j , i and j are natural numbers; Based on the transaction nodes in the enterprise transaction curve graph, calculate the enterprise transaction curve graph P i The mean square error and enterprise transaction curve P j The mean square error In the mean square error With the mean square error When the difference is less than the fourth set threshold, it is determined that there is a special interest transfer link between the focused enterprise i and the customer j.
5. The method according to claim 1, characterized in that In the case where the key focus enterprise is a customer, obtaining suppliers and customers with special interest delivery links based on the transaction curve graph of the key focus enterprise includes: Get the enterprise transaction curve P of the focused enterprise u u The enterprise transaction curve P with supplier v v , u and v are natural numbers; Based on the transaction nodes in the enterprise transaction curve graph, calculate the enterprise transaction curve graph P u The mean square error and enterprise transaction curve P v The mean square error In the mean square error With the mean square error When the difference is less than the fifth set threshold, it is determined that there is a special interest transfer link between the focused enterprise u and the supplier v.
6. A system for identifying special interest transmission links, characterized in that: The system comprises: A feature extraction module is used to obtain the counterparties of the member units and extract the key enterprise features of the counterparties; wherein the counterparties include: suppliers and customers; Enterprise screening module, used to select key enterprises from counterparties based on key features; A graph construction module, used to construct a transaction curve graph of all transaction counterparties, wherein the enterprise transaction curve graph is used to display all transactions between the transaction counterparty and the member unit within a set time range; The anomaly identification module is used to identify suppliers and customers with special interest delivery links based on the transaction curve chart of key focus enterprises.
7. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the method for identifying the special benefit delivery link as described in any one of claims 1-5 is implemented.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for identifying a special benefit delivery link as described in any one of claims 1 to 5 is implemented.
