Financial product intelligent matching method of digital financial service platform

Abstract

The invention discloses a financial product intelligent matching method of a digital financial service platform, and relates to the technical field of artificial intelligence and data analysis. Comprising the following steps: step 1, based on a digital financial service platform, according to enterprise data and financial product data, processing and generating enterprise labels, carrying out label marking on warehousing enterprises, and sorting enterprise admission rules according to the enterprise labels, step 2, judging whether the enterprises actively fill the label data or not, and if the enterprises do not actively fill the label data, executing step 3; if the label data is actively filled, only verifying the enterprise access rules, matching with the financial products on the digital financial service platform according to the enterprise access rules, and obtaining all the financial products meeting the conditions, and if the label data is actively filled, firstly verifying the enterprise access rules, matching with the financial products on the digital financial service platform according to the enterprise access rules, and obtaining all the financial products meeting the conditions. The method comprises the following steps: step 1, obtaining all financial products meeting conditions, checking enterprise scoring rules, and obtaining financial products meeting the conditions, and step 2, carrying out list sorting on all financial products meeting the conditions according to sorting rules, recommending financial products for enterprises according to a list, and recommending more enterprises for financial institutions.

Description

Technical Field

[0001] The present invention discloses a financial product intelligent matching method for a digital financial service platform, and relates to the technical fields of artificial intelligence and data analysis. Background Art

[0002] After the digital financial service platform is built, the platform will support corporate user registration and financing application functions, and support financial product release and financing acceptance functions for financial institution users.

[0003] Usually, when corporate users actively apply for products, more manual participation is needed to determine whether the financial products meet the company's expectations. However, this method mainly relies on personal experience and cannot accurately recommend suitable financial products to companies, nor can it recommend more suitable companies to financial institutions. Summary of the invention

[0004] In view of the problems of the prior art, the present invention provides a financial product intelligent matching method for a digital financial service platform, which has the characteristics of strong versatility and simple implementation, and has broad application prospects.

[0005] The specific scheme proposed by the present invention is:

[0006] The present invention provides a financial product intelligent matching method for a digital financial service platform, comprising:

[0007] Step 1: Based on the digital financial service platform, process the enterprise data and financial product data, generate enterprise labels, label the enterprises in the database, and sort out the enterprise access rules based on the enterprise labels.

[0008] Step 2: Determine whether the enterprise has actively reported the label data. If not, only check the enterprise access rules, match the financial products on the digital financial service platform according to the enterprise access rules, and obtain all financial products that meet the conditions. Check the enterprise access rule matching result sequence of each financial product according to the enterprise access rules. If the matching result is a hit, the corresponding mark in the result sequence is 1, if not, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. Financial products with a non-0 score are financial products that meet the conditions.

[0009] If you actively fill in the label data, first check the enterprise access rules, match the financial products on the digital financial service platform according to the enterprise access rules, obtain all the financial products that meet the conditions, and then check the enterprise scoring rules. Check the enterprise access rule matching result sequence of each financial product according to the enterprise access rules. If the matching result hits, the corresponding mark in the result sequence is 1, and if it does not hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. If the score is not 0, the matching score of the financial product is calculated according to the enterprise scoring rules. Financial products with a score not 0 are financial products that meet the conditions.

[0010] Step 3: Sort all the financial products that meet the conditions into a list according to the sorting rules, recommend financial products to enterprises based on the list, and recommend more enterprises to financial institutions.

[0011] Furthermore, the enterprise labels generated in step 1 of the financial product intelligent matching method of a digital financial service platform include: age of the corporate legal person, years of establishment of the enterprise, registered address of the enterprise, type of enterprise, industry to which the enterprise belongs, business status of the enterprise, tax scale of the enterprise, annual tax credit rating of the enterprise, financing amount, financing term, loan method, payment time, purpose of financing, expected interest rate range, type of financial institution, business income of the enterprise, invoicing income, and short-term debt limit.

[0012] Further, in step 2 of the financial product intelligent matching method of a digital financial service platform, enterprise access rules are formulated according to enterprise labels, including: formulating access rules for verifying the age of legal persons, formulating access rules for verifying the years of establishment of enterprises, formulating access rules for verifying the place of registration of enterprises, formulating access rules for verifying the types of customers facing products, formulating access rules for verifying the industries prohibited for enterprises, formulating access rules for the operating status of enterprises, formulating access rules for the scale of tax payment of enterprises, and formulating access rules for the credit rating of tax payment of enterprises;

[0013] Enterprise scoring rules are formulated based on enterprise labels, including: formulating entry rules for verifying financing amount, formulating entry rules for verifying financing period, formulating entry rules for verifying loan method, formulating entry rules for verifying financing purpose, formulating entry rules for verifying expected interest rate range, formulating entry rules for verifying institution type, and formulating entry rules for verifying payment time.

[0014] Furthermore, the sorting rules in step 3 of the financial product intelligent matching method of a digital financial service platform are:

[0015] Bank products take precedence over guarantee products and financial leasing products.

[0016] Or sort by popularity product table,

[0017] Or sort in reverse order of product creation time.

[0018] The present invention also provides a financial product intelligent matching device for a digital financial service platform, including a tag management module, a matching analysis module and a recommendation module.

[0019] The label management module is based on the digital financial service platform. It processes enterprise data and financial product data, generates enterprise labels, and labels the enterprises in the database. It also sorts out enterprise access rules based on enterprise labels.

[0020] The matching analysis module determines whether the enterprise actively reports the label data. If the label data is not actively reported, only the enterprise access rules are verified, and the financial products on the digital financial service platform are matched according to the enterprise access rules to obtain all financial products that meet the conditions. The enterprise access rule matching result sequence of each financial product is checked according to the enterprise access rules. If the matching result is a hit, the corresponding mark in the result sequence is 1, and if it is not a hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. Financial products with a score not equal to 0 are financial products that meet the conditions.

[0021] If you actively fill in the label data, first check the enterprise access rules, match the financial products on the digital financial service platform according to the enterprise access rules, obtain all the financial products that meet the conditions, and then check the enterprise scoring rules. Check the enterprise access rule matching result sequence of each financial product according to the enterprise access rules. If the matching result hits, the corresponding mark in the result sequence is 1, and if it does not hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. If the score is not 0, the matching score of the financial product is calculated according to the enterprise scoring rules. Financial products with a score not 0 are financial products that meet the conditions.

[0022] The recommendation module lists all the financial products that meet the conditions according to the sorting rules, recommends financial products to enterprises based on the list, and recommends more enterprises to financial institutions.

[0023] Furthermore, the enterprise labels generated by the label management module of the financial product intelligent matching device of the digital financial service platform include: the age of the corporate legal person, the years of establishment of the enterprise, the registered address of the enterprise, the type of enterprise, the industry to which the enterprise belongs, the business status of the enterprise, the tax scale of the enterprise, the annual tax credit rating of the enterprise, the financing amount, the financing period, the loan method, the time of payment, the purpose of financing, the expected interest rate range, the type of financial institution, the business income of the enterprise, the invoicing income, and the short-term debt limit.

[0024] Further, the matching analysis module of the financial product intelligent matching device of the digital financial service platform formulates enterprise access rules according to enterprise labels, including: formulating access rules for verifying the age of legal persons, formulating access rules for verifying the years of establishment of enterprises, formulating access rules for verifying the place of registration of enterprises, formulating access rules for verifying the types of products facing customers, formulating access rules for verifying the industries prohibited for enterprises, formulating access rules for the operating status of enterprises, formulating access rules for the scale of tax payment of enterprises, and formulating access rules for the credit rating of tax payment of enterprises;

[0025] Enterprise scoring rules are formulated based on enterprise labels, including: formulating entry rules for verifying financing amount, formulating entry rules for verifying financing period, formulating entry rules for verifying loan method, formulating entry rules for verifying financing purpose, formulating entry rules for verifying expected interest rate range, formulating entry rules for verifying institution type, and formulating entry rules for verifying payment time.

[0026] Furthermore, the sorting rule executed by the recommendation module of the financial product intelligent matching device of the digital financial service platform is:

[0027] Bank products take precedence over guarantee products and financial leasing products.

[0028] Or sort by popularity product table,

[0029] Or sort in reverse order of product creation time.

[0030] The benefits of the present invention are:

[0031] It improves the success rate of corporate financing matchmaking, better recommends suitable financial products to enterprises, and recommends more suitable enterprises to financial institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0033] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0034] Example 1

[0035] The present invention provides a financial product intelligent matching method for a digital financial service platform, comprising:

[0036] Step 1: Based on the digital financial service platform, process the enterprise data and financial product data, generate enterprise tags, label the stored enterprises, and sort out the enterprise access rules based on the enterprise tags. The generated enterprise tags include: age of the corporate legal person, years of establishment of the enterprise, registered address of the enterprise, type of enterprise, industry to which the enterprise belongs, business status of the enterprise, scale of enterprise tax payment, annual tax credit rating of the enterprise, financing amount, financing period, loan method, time of payment, purpose of financing, expected interest rate range, type of financial institution, business income of the enterprise, invoicing income, and short-term debt limit. Please refer to Table 1.

[0037] In step 2, it is determined whether the enterprise actively fills in the label data. If the label data is not actively filled in, only the enterprise access rules are verified, and the financial products on the digital financial service platform are matched according to the enterprise access rules to obtain all financial products that meet the conditions. According to the enterprise access rules, the enterprise access rule matching result sequence of each financial product is checked. If the matching result hits, the corresponding mark in the result sequence is 1, and if it does not hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0, and the financial products with a score not equal to 0 are the financial products that meet the conditions.

[0038] For example, if there is no active reporting of data, please refer to the following process:

[0039] I. Obtain the values ​​of the corresponding labels of the enterprise according to the information in the enterprise label table 1, such as the age of the legal person of the enterprise, the years of establishment of the enterprise, the registered address of the enterprise, the type of enterprise, the industry to which the enterprise belongs, the business status of the enterprise, the scale of the enterprise's tax payment, and the credit rating of the enterprise's tax payment. Assume that the values ​​of these eight labels of a certain enterprise are 38, 5, XX, innovative small and medium-sized enterprises, C, in operation (opened), general taxpayer, and A level;

[0040] II. Obtain the access rule hits for all products in the financial product library. Assuming that the product library has five financial products A, B, C, D, and E, calculate the criterion matching result sequence for each product based on rule table 2 and enterprise tag information. For example, for financial product A, the matching result sequence is (1, 0, 1, 1, 0, 0, 1, 1);

[0041] III. If there is a 0 value in the result, the score of product A is 0, and a product sequence without 0 is returned. Other judgment conditions can also be added, such as increasing the differentiation of products, increasing the calculation of product heat values ​​and enterprise list libraries, giving priority to the calculation of enterprise list libraries, and establishing a mapping table of more mainstream enterprise list libraries, enterprise industries and corresponding main matching products. If the enterprise is not in the enterprise list library, the matching products are sorted according to the product heat value. If the enterprise is in the enterprise list library, the corresponding products are matched first.

[0042] If you actively fill in the label data, the enterprise access rules will be checked first, and then the enterprise scoring rules will be checked. The enterprise access rule matching result sequence of each financial product will be checked according to the enterprise access rules. If the matching result is a hit, the corresponding mark in the result sequence is 1, and if it is not a hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. If the score is not 0, the matching score of the financial product is calculated according to the enterprise scoring rules. Financial products with a score not 0 are financial products that meet the conditions.

[0043] For example, if there is a match for actively reported data, first check the admission rules, then check the scoring rules. The process is as follows:

[0044] I. Obtain the values ​​of the corresponding labels of the enterprise based on the information in the enterprise label table, such as the age of the legal person of the enterprise, the years of establishment of the enterprise, the registered address of the enterprise, the type of enterprise, the industry to which the enterprise belongs, the business status of the enterprise, the tax scale of the enterprise, the tax credit rating of the enterprise, and other fields that the enterprise actively fills in: financing amount, expected interest rate range, expected loan time, expected financing period, etc. Assume that the values ​​of these 12 labels of a certain enterprise are 38, 5, XX, innovative small and medium-sized enterprises, C, in operation (opened), general taxpayer, A level, 100000, 3-5, 3, 12;

[0045] II. Obtain the access rule hit status of all products in the financial product library.

[0046] Assume that the product library has five financial products, A, B, C, D, and E. According to the rules in the following table and the company's tag information, calculate the criterion matching result sequence of each product. For example, for financial product A, the matching result sequence is (1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1);

[0047] III. If there is a 0 value in the access rule, the score of financial product A is 0. Otherwise, the matching score of product A is calculated. Each scoring rule is 5 points. If there are 4 scoring rules in total, the matching score of financial product A is 5*4 / 20*100=100 points. In this way, the matching score sequence of five products is obtained, which is assumed to be (100, 50, 75, 75, 100);

[0048] Other judgment conditions can also be added to increase the differentiation of products with the same score, give priority to calculating the enterprise list library, establish a more mainstream enterprise list library, enterprise industry and corresponding main matching product mapping table, if the enterprise is not in the enterprise list library, sort the matching products according to the product heat value, if the enterprise is in the enterprise list library, give priority to matching the corresponding products, so that financial products with the same score can be easily distinguished.

[0049] Step 3: Sort all the financial products that meet the conditions into a list according to the sorting rules, recommend financial products to enterprises based on the list, and recommend more enterprises to financial institutions.

[0050] The sorting rules may be:

[0051] Bank products take precedence over guarantee products and financial leasing products.

[0052] Or sort by popularity product table,

[0053] Or sort in reverse order of product creation time.

[0054] For enterprise access rules and enterprise scoring rules, please refer to Table 2. For the logic of access rules and scoring rules, please refer to Table 3.

[0055] Example 2

[0056] The present invention also provides a financial product intelligent matching device for a digital financial service platform, including a tag management module, a matching analysis module and a recommendation module.

[0057] The label management module is based on the digital financial service platform. It processes enterprise data and financial product data, generates enterprise labels, and labels the enterprises in the database. It also sorts out enterprise access rules based on enterprise labels.

[0058] The matching analysis module determines whether the enterprise actively reports the label data. If the label data is not actively reported, only the enterprise access rules are verified, and the financial products on the digital financial service platform are matched according to the enterprise access rules to obtain all financial products that meet the conditions. The enterprise access rule matching result sequence of each financial product is checked according to the enterprise access rules. If the matching result is a hit, the corresponding mark in the result sequence is 1, and if it is not a hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. Financial products with a score not equal to 0 are financial products that meet the conditions.

[0059] If you actively fill in the label data, you will first check the enterprise access rules, and then check the enterprise scoring rules. According to the enterprise access rules, check the enterprise access rule matching result sequence of each financial product. If the matching result is a hit, the corresponding mark in the result sequence is 1, and if it is not a hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. If the score is not 0, the matching score of the financial product is calculated according to the enterprise scoring rules. Financial products with a score not 0 are financial products that meet the conditions.

[0060] The recommendation module lists all the financial products that meet the conditions according to the sorting rules, recommends financial products to enterprises based on the list, and recommends more enterprises to financial institutions.

[0061] As the information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the embodiment of the method of the present invention, the specific contents can be found in the description of the embodiment of the method of the present invention and will not be repeated here.

[0062] Likewise, the device of the present invention improves the success rate of corporate financing matchmaking, better recommends suitable financial products to enterprises, and recommends more suitable enterprises to financial institutions.

[0063] It should be noted that not all steps and modules in the above-mentioned processes and device structures are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The system structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by multiple physical entities, or some components in multiple independent devices may be implemented together.

[0064] The above-described embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art based on the present invention are within the protection scope of the present invention. The protection scope of the present invention shall be subject to the claims.

[0065] Table 1

[0066]

[0067]

[0068]

[0069] Table 2

[0070] Access rule number Access rule type Access rule name GZ01 Enterprise access rules Legal person age verification GZ02 Enterprise access rules Verification of the company's establishment years GZ03 Enterprise access rules Company registration location verification GZ04 Enterprise access rules Product type verification for customers GZ05 Enterprise access rules Enterprise banned from industry verification GZ06 Enterprise access rules Business status verification GZ07 Enterprise access rules Enterprise tax scale verification GZ08 Enterprise access rules Corporate tax credit rating verification GZ09 Enterprise access rules Enterprise sales-loan ratio GZ10 Enterprise access rules Is there a winning project? GZ11 Enterprise Rating Rules Financing amount verification GZ12 Enterprise Rating Rules Financing term verification GZ13 Enterprise Rating Rules Loan method verification GZ14 Enterprise Rating Rules Payment time verification GZ15 Enterprise Rating Rules Financing purpose verification GZ16 Enterprise Rating Rules Expected interest rate range verification GZ17 Enterprise Rating Rules Organization type verification

[0071] Table 3

[0072]

[0073]

[0074]

[0075]

Claims

1. A financial product intelligent matching method for a digital financial service platform, characterized by: include: Step 1: Based on the digital financial service platform, process the enterprise data and financial product data, generate enterprise labels, label the enterprises in the database, and sort out the enterprise access rules based on the enterprise labels. Step 2: Determine whether the enterprise has actively reported the label data. If not, only check the enterprise access rules, match the financial products on the digital financial service platform according to the enterprise access rules, and obtain all financial products that meet the conditions. Check the enterprise access rule matching result sequence of each financial product according to the enterprise access rules. If the matching result is a hit, the corresponding mark in the result sequence is 1, if not, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. Financial products with a non-0 score are financial products that meet the conditions. If you actively fill in the label data, first check the enterprise access rules, match the financial products on the digital financial service platform according to the enterprise access rules, obtain all the financial products that meet the conditions, and then check the enterprise scoring rules. Check the enterprise access rule matching result sequence of each financial product according to the enterprise access rules. If the matching result hits, the corresponding mark in the result sequence is 1, and if it does not hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. If the score is not 0, the matching score of the financial product is calculated according to the enterprise scoring rules. Financial products with a score not 0 are financial products that meet the conditions. Step 3: Sort all the financial products that meet the conditions into a list according to the sorting rules, recommend financial products to enterprises based on the list, and recommend more enterprises to financial institutions.

2. According to claim 1, a financial product intelligent matching method for a digital financial service platform is characterized by: The enterprise tags generated in step 1 include: age of the legal person of the enterprise, years of establishment of the enterprise, registered address of the enterprise, type of enterprise, industry to which the enterprise belongs, business status of the enterprise, tax payment scale of the enterprise, annual tax credit rating of the enterprise, financing amount, financing term, loan method, payment time, financing purpose, expected interest rate range, type of financial institution, business income of the enterprise, invoicing income, and short-term debt limit.

3. The financial product intelligent matching method of a digital financial service platform according to claim 1 is characterized by: In step 2, enterprise access rules are formulated according to enterprise tags, including: formulating access rules for verifying the age of legal persons, formulating access rules for verifying the years of establishment of enterprises, formulating access rules for verifying the place of registration of enterprises, formulating access rules for verifying the types of customers facing products, formulating access rules for verifying the industries prohibited for enterprises, formulating access rules for the operating status of enterprises, formulating access rules for the scale of tax payments made by enterprises, and formulating access rules for the credit rating of tax payments made by enterprises; Enterprise scoring rules are formulated based on enterprise labels, including: formulating entry rules for verifying financing amount, formulating entry rules for verifying financing period, formulating entry rules for verifying loan method, formulating entry rules for verifying financing purpose, formulating entry rules for verifying expected interest rate range, formulating entry rules for verifying institution type, and formulating entry rules for verifying payment time.

4. According to the financial product intelligent matching method of a digital financial service platform according to claim 1, it is characterized in that the sorting rule in step 3 is: Bank products take precedence over guarantee products and financial leasing products. Or sort by popularity product table, Or sort in reverse order of product creation time.

5. A financial product intelligent matching device for a digital financial service platform, characterized in that Including tag management module, matching analysis module and recommendation module, The label management module is based on the digital financial service platform. It processes enterprise data and financial product data, generates enterprise labels, and labels the enterprises in the database. It also sorts out enterprise access rules based on enterprise labels. The matching analysis module determines whether the enterprise actively reports the label data. If the label data is not actively reported, only the enterprise access rules are verified, and the financial products on the digital financial service platform are matched according to the enterprise access rules to obtain all financial products that meet the conditions. The enterprise access rule matching result sequence of each financial product is checked according to the enterprise access rules. If the matching result is a hit, the corresponding mark in the result sequence is 1, and if it is not a hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. Financial products with a score not equal to 0 are financial products that meet the conditions. If you actively fill in the label data, first check the enterprise access rules, match the financial products on the digital financial service platform according to the enterprise access rules, obtain all the financial products that meet the conditions, and then check the enterprise scoring rules. Check the enterprise access rule matching result sequence of each financial product according to the enterprise access rules. If the matching result hits, the corresponding mark in the result sequence is 1, and if it does not hit, the corresponding mark in the result sequence is 0. If there is a 0 value in the matching result, the corresponding financial product score is 0. If the score is not 0, the matching score of the financial product is calculated according to the enterprise scoring rules. Financial products with a score not 0 are financial products that meet the conditions. The recommendation module lists all the financial products that meet the conditions according to the sorting rules, recommends financial products to enterprises based on the list, and recommends more enterprises to financial institutions.

6. The financial product intelligent matching device of a digital financial service platform according to claim 5, characterized in that the tag The enterprise labels generated by the management module include: age of the legal person of the enterprise, years of establishment of the enterprise, registered address of the enterprise, type of enterprise, industry to which the enterprise belongs, business status of the enterprise, tax scale of the enterprise, annual tax credit rating of the enterprise, financing amount, financing period, loan method, payment time, purpose of financing, expected interest rate range, type of financial institution, business income of the enterprise, invoicing income, and short-term debt limit.

7. The financial product intelligent matching device of a digital financial service platform according to claim 5, characterized in that The matching analysis module formulates enterprise access rules based on enterprise tags, including: formulating access rules for verifying the age of legal persons, formulating access rules for verifying the years of establishment of enterprises, formulating access rules for verifying the place of registration of enterprises, formulating access rules for verifying the types of customers facing products, formulating access rules for prohibiting enterprises from entering industries, formulating access rules for enterprise operating status, formulating access rules for enterprise tax scale, and formulating access rules for enterprise tax credit rating; Enterprise scoring rules are formulated based on enterprise labels, including: formulating entry rules for verifying financing amount, formulating entry rules for verifying financing period, formulating entry rules for verifying loan method, formulating entry rules for verifying financing purpose, formulating entry rules for verifying expected interest rate range, formulating entry rules for verifying institution type, and formulating entry rules for verifying payment time.

8. According to claim 5, a financial product intelligent matching device for a digital financial service platform is characterized in that The sorting rules implemented by the recommendation module are: Bank products take precedence over guarantee products and financial leasing products. Or sort by popularity product table, Or sort in reverse order of product creation time.

Images