Credit risk assessment system and method based on big data

Abstract

The invention relates to the technical field of credit risk assessment, in particular to a credit risk assessment system and method based on big data. The method comprises the steps of receiving a credit application request of a user, obtaining personal basic information of the user based on the credit application request of the user, obtaining a credit qualification value of the user based on the personal basic information of the user, and judging whether the user has credit qualification or not based on the credit qualification value of the user; performing data extraction on the declaration information based on a bag-of-word model to obtain financial information, credit record information and behavior information; analyzing the financial information to obtain a first credit risk index, analyzing the credit record information to obtain a second credit risk index, and analyzing the behavior information to obtain a third credit risk index; and evaluating the credit risk of the user based on the first credit risk index, the second credit risk index and the third credit risk index. According to the invention, comprehensive and accurate evaluation of the credit risk can be realized, and the safety and efficiency of the credit business are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of credit risk assessment, and in particular to a credit risk assessment system and method based on big data. Background Art

[0002] With the continuous integration of global financial markets and the rapid development of technology, the financial industry is facing unprecedented opportunities and challenges. Among them, credit business is the core part of financial services, and the effectiveness and efficiency of its risk management are directly related to the sound operation of financial institutions.

[0003] The rise of big data technology has brought new solutions to credit risk assessment. Big data has the 4V characteristics of volume, velocity, variety and value, which enables financial institutions to process and analyze massive, multi-dimensional data, thereby more comprehensively assessing the credit risk of borrowers and improving credit efficiency and security.

[0004] However, traditional credit risk control methods have many limitations, such as reliance on manual experience, limited data samples, and lack of dynamic updates, which make it difficult to meet the complex needs of modern financial markets.

[0005] Therefore, there is an urgent need for a credit risk assessment system and method based on big data to solve the above problems. Summary of the invention

[0006] The purpose of the present invention is to provide a credit risk assessment system and method based on big data: to solve the technical problem that in the process of assessing user credit risk in existing solutions, credit risk assessment is inaccurate due to reliance on manual experience and limited data samples, and thus credit security is low.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] On the one hand, the credit risk assessment system based on big data includes a credit qualification management module, a declaration information acquisition module, a declaration information analysis module and a credit risk assessment module;

[0009] The credit qualification management module is used to receive a user's credit application request, and obtain the user's basic personal information based on the user's credit application request, wherein the basic personal information includes age, occupation, social security record information and personal tax payment information, and obtain the user's credit qualification value based on the user's basic personal information, and determine whether the user has credit qualifications based on the user's credit qualification value;

[0010] The declaration information acquisition module is used to obtain the declaration information corresponding to the credit-qualified users, and extract the declaration information based on the bag-of-words model to obtain financial information, credit record information and behavioral information;

[0011] The declaration information parsing module is used to parse the financial information to obtain a first credit risk index, parse the credit record information to obtain a second credit risk index, and parse the behavior information to obtain a third credit risk index;

[0012] The credit risk assessment module is used to assess the credit risk of the user based on the first credit risk index, the second credit risk index and the third credit risk index.

[0013] Furthermore, obtaining the user's credit qualification value based on the user's basic personal information includes the following process:

[0014] Get the user's age NJ based on the user's basic personal information;

[0015] Based on the user's personal basic information, the user's occupation is obtained, and it is determined whether the user's occupation is an unqualified occupation. If so, the user's occupation qualification R is 0, and if not, the user's occupation qualification R is 1, wherein the system stores pre-set unqualified occupation types;

[0016] Based on the user's basic personal information, obtain the user's social security record information, and based on the social security record information, obtain the number of consecutive social security payment months S of the user;

[0017] Obtain individual tax payment information based on the user's basic personal information, and obtain the user's total individual tax payment GS for the previous year based on the individual tax payment information;

[0018] Substitute age NJ, professional qualification R, consecutive social security payment months S and total personal tax payment GS into the credit qualification value calculation formula to obtain the user's credit qualification value. The calculation formula is as follows:

[0019]

[0020] Among them, XDZ is the user's credit qualification value, and e is 2.72.

[0021] Further, judging whether the user is credit qualified based on the user's credit qualification value includes the following process:

[0022] A credit qualification value threshold is obtained, wherein the credit qualification value threshold is stored in the system and is set by the system to determine whether the user's credit qualification value exceeds the credit qualification value threshold. If so, the user is credit qualified, and if not, the user is not credit qualified.

[0023] Furthermore, data extraction of the declared information based on the bag-of-words model to obtain financial information, credit record information and behavioral information includes the following process:

[0024] Based on the bag-of-words model, data extraction of the declared information was performed to obtain financial terms corresponding to the financial information, credit record terms corresponding to the credit record information, and behavioral terms corresponding to the behavioral information. Among them, financial terms include real estate, vehicles, deposits, stocks, funds, debts, loans, credit card arrears, wages, bonuses, and investment income; credit record terms include loan amount, repayment record, default amount, and tax arrears; behavioral terms include consumption amount, consumption frequency, and consumption preference;

[0025] Financial terms, credit record terms and behavioral terms are used as branches, and the data corresponding to each term is used as leaves, forming financial information, credit record information and behavioral information in a tree-like form, wherein the data corresponding to each term is a specific amount or number of records.

[0026] Furthermore, parsing the financial information to obtain the first credit risk index includes the following process:

[0027] Based on the financial information, the number of positive asset items and negative asset items of the user is counted, where the positive asset items are the real estate items, vehicle items, deposit items, stock items, fund items, salary items, bonus items, and investment income items owned by the user, and the negative asset items are the debt items, loan items, and credit card outstanding balances owned by the user, and the ratio A of the number of positive asset items to the number of negative asset items is calculated;

[0028] Based on the financial information, calculate the sum B of the number of properties and vehicles of the user, and calculate the total amount C of the stock amount, fund amount, bonus amount, investment income amount and salary amount;

[0029] Calculate the total amount D of the debt amount, loan amount and credit card outstanding amount based on the financial information;

[0030] Substitute the ratios A, B, total amount C and total amount D into the first credit risk index calculation formula to obtain the first credit risk index, which is as follows:

[0031]

[0032] Among them, DYZ is the first credit risk index.

[0033] Furthermore, parsing the credit record information to obtain the second credit risk index includes the following process:

[0034] Obtain the user's loan amount E based on the credit record information;

[0035] Obtain repayment records based on credit record information, count the number of on-time repayments and the number of repayments after the repayment deadline based on the repayment records, and calculate the ratio F of the number of repayments after the repayment deadline to the number of on-time repayments;

[0036] Obtain the total amount G of the user's default amount and tax arrears based on the credit record information;

[0037] Substitute the loan amount E, ratio F, and total amount G into the second credit risk index calculation formula to obtain the second credit risk index, which is as follows:

[0038]

[0039] Among them, DEZ is the second credit risk index.

[0040] Furthermore, parsing the behavior information to obtain the third credit risk index includes the following process:

[0041] Based on the behavior information, obtain the user's average monthly consumption amount H and consumption frequency L;

[0042] Based on the behavior information, the monthly consumption preference of the user is obtained, where the consumption preference includes luxury goods consumption type, daily necessities consumption type, and electronic product consumption type. The monthly consumption preference of the user is determined based on the proportion of the amount of money spent by the user on each consumption type each month. The consumption type corresponding to the largest proportion of the amount of money spent is recorded as the user's monthly consumption preference, and the consumption preference value K is determined based on the user's monthly consumption preference, where each consumption type corresponds to a different consumption preference value, which is set by the system;

[0043] Substitute the average monthly consumption amount H, consumption frequency L and consumption preference value K into the third credit risk index calculation formula to calculate the third credit risk index, which is as follows:

[0044]

[0045] Among them, DSZ is the third credit risk index, k1, k2, and k3 are weight coefficients, and their values ​​are 0.2, 0.4, and 0.4 respectively.

[0046] Further, evaluating the credit risk of the user based on the first credit risk index, the second credit risk index and the third credit risk index includes the following process:

[0047] Calculate the sum of the first credit risk index, the second credit risk index and the third credit risk index, record the sum as the total credit risk value of the user, and determine whether the total credit risk value of the user exceeds a preset total credit risk threshold of the user. If so, the credit risk of the user is high and the risk assessment will not be passed; if not, the credit risk of the user is low and the risk assessment will be allowed to pass, wherein the preset total credit risk threshold of the user is set by the system and stored in the system.

[0048] On the other hand, the credit risk assessment method based on big data includes:

[0049] Receive a credit application request from a user, and obtain basic personal information of the user based on the credit application request, wherein the basic personal information includes age, occupation, social security record information and personal tax payment information, and obtain a credit qualification value of the user based on the basic personal information of the user, and determine whether the user is eligible for credit based on the credit qualification value of the user;

[0050] Obtain the declaration information corresponding to users with credit qualifications, and extract data from the declaration information based on the bag-of-words model to obtain financial information, credit record information, and behavioral information;

[0051] The financial information is parsed to obtain a first credit risk index, the credit record information is parsed to obtain a second credit risk index, and the behavioral information is parsed to obtain a third credit risk index;

[0052] The credit risk of the user is assessed based on the first credit risk index, the second credit risk index, and the third credit risk index.

[0053] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0054] The present invention can comprehensively evaluate the credit risk of users, and the obtained evaluation result is more accurate.

[0055] The present invention can achieve a comprehensive and accurate assessment of credit risks and improve the security and efficiency of credit business by making full use of big data technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0057] Figure 1 It is a system block diagram of a credit risk assessment system based on big data according to an embodiment of the present invention;

[0058] Figure 2 This is a workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention;

[0059] Figure 3 is another workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention;

[0060] Figure 4 is another workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention;

[0061] Figure 5 This is another workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0064] This embodiment provides a credit risk assessment system based on big data. Figure 1 is a system block diagram of a credit risk assessment system based on big data according to an embodiment of the present invention. Figure 1 As shown, the system includes a credit qualification management module, a declaration information acquisition module, a declaration information parsing module and a credit risk assessment module;

[0065] The credit qualification management module is used to receive a user's credit application request, and obtain the user's basic personal information based on the user's credit application request, wherein the basic personal information includes age, occupation, social security record information and personal tax payment information, and obtain the user's credit qualification value based on the user's basic personal information, and determine whether the user has credit qualifications based on the user's credit qualification value;

[0066] The declaration information acquisition module is used to obtain the declaration information corresponding to the credit-qualified users, and extract the declaration information based on the bag-of-words model to obtain financial information, credit record information and behavioral information;

[0067] The declaration information parsing module is used to parse the financial information to obtain a first credit risk index, parse the credit record information to obtain a second credit risk index, and parse the behavior information to obtain a third credit risk index;

[0068] The credit risk assessment module is used to assess the credit risk of the user based on the first credit risk index, the second credit risk index and the third credit risk index.

[0069] In summary, the present invention receives a user's credit application request, obtains the user's personal basic information based on the user's credit application request, obtains the user's credit qualification value based on the user's personal basic information, and determines whether the user has credit qualifications based on the user's credit qualification value; extracts data from the declared information based on the bag-of-words model to obtain financial information, credit record information, and behavioral information; parses the financial information to obtain a first credit risk index, parses the credit record information to obtain a second credit risk index, and parses the behavioral information to obtain a third credit risk index; and evaluates the user's credit risk based on the first credit risk index, the second credit risk index, and the third credit risk index. The present invention can achieve a comprehensive and accurate assessment of credit risk and improve the security and efficiency of credit business.

[0070] In some embodiments, Figure 2 is a workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention. Figure 2 As shown, obtaining the user's credit qualification value based on the user's basic personal information includes the following process:

[0071] Step S201: Acquire the user's age NJ based on the user's basic personal information;

[0072] Step S202: obtaining the user's occupation based on the user's personal basic information, and determining whether the user's occupation is an unqualified occupation. If so, the user's occupation qualification R is 0, and if not, the user's occupation qualification R is 1, wherein the system stores a preset unqualified occupation type;

[0073] Step S203: obtaining the user's social security record information based on the user's personal basic information, and obtaining the number of consecutive social security payment months S of the user based on the social security record information;

[0074] Step S204: obtaining individual tax payment information based on the user's basic personal information, and obtaining the total individual tax payment GS of the user in the previous year based on the individual tax payment information;

[0075] Step S205: Substitute age NJ, occupation qualification R, consecutive social security payment months S and total individual tax payment GS into the credit qualification value calculation formula to obtain the user's credit qualification value, which is as follows:

[0076]

[0077] Among them, XDZ is the user's credit qualification value, and e is 2.72.

[0078] In some embodiments, determining whether a user is credit qualified based on the user's credit qualification value includes the following process:

[0079] A credit qualification value threshold is obtained, wherein the credit qualification value threshold is stored in the system and is set by the system to determine whether the user's credit qualification value exceeds the credit qualification value threshold. If so, the user is credit qualified, and if not, the user is not credit qualified.

[0080] In some embodiments, extracting data from the declared information based on the bag-of-words model to obtain financial information, credit record information, and behavioral information includes the following process:

[0081] Based on the bag-of-words model, data extraction of the declared information was performed to obtain financial terms corresponding to the financial information, credit record terms corresponding to the credit record information, and behavioral terms corresponding to the behavioral information. Among them, financial terms include real estate, vehicles, deposits, stocks, funds, debts, loans, credit card arrears, wages, bonuses, and investment income; credit record terms include loan amount, repayment record, default amount, and tax arrears; behavioral terms include consumption amount, consumption frequency, and consumption preference;

[0082] Financial terms, credit record terms and behavioral terms are used as branches, and the data corresponding to each term is used as leaves, forming financial information, credit record information and behavioral information in a tree-like form. The data corresponding to each term is a specific amount or number of records. It is worth noting that the number of records can be the number of properties, the number of vehicles, the number of defaults, etc.

[0083] In some embodiments, Figure 3 is another workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention. Figure 3 As shown, parsing the financial information to obtain the first credit risk index includes the following steps:

[0084] Step S301: Count the number of positive asset items and negative asset items of the user based on the financial information, wherein the positive asset items are the real estate items, vehicle items, deposit items, stock items, fund items, salary items, bonus items, and investment income items owned by the user, and the negative asset items are the debt items, loan items, and credit card outstanding balances owned by the user, and calculate the ratio A of the number of positive asset items to the number of negative asset items;

[0085] Step S302: Calculate the sum B of the number of properties and the number of vehicles of the user based on the financial information, and calculate the total amount C of the stock amount, fund amount, bonus amount, investment income amount and salary amount;

[0086] Step S303: Calculate the total amount D of the debt amount, loan amount and credit card outstanding amount based on the financial information;

[0087] Step S304: Substitute the ratios A, B, the total amount C and the total amount D into the first credit risk index calculation formula to calculate the first credit risk index. The calculation formula is as follows:

[0088]

[0089] Among them, DYZ is the first credit risk index.

[0090] In some embodiments, Figure 4 is another workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention. Figure 4 As shown, parsing the credit record information to obtain the second credit risk index includes the following process:

[0091] Step S401: Obtaining the user's loan amount E based on the credit record information;

[0092] Step S402: Obtain repayment records based on the credit record information, count the number of on-time repayments and the number of repayments after the repayment deadline based on the repayment records, and calculate the ratio F of the number of repayments after the repayment deadline to the number of on-time repayments;

[0093] Step S403: Obtain the total amount G of the user's default amount and tax arrears amount based on the credit record information;

[0094] Step S404: Substitute the loan amount E, the ratio F, and the total amount G into the second credit risk index calculation formula to calculate the second credit risk index. The calculation formula is as follows:

[0095]

[0096] Among them, DEZ is the second credit risk index.

[0097] In some embodiments, Figure 5 is another workflow diagram of a credit risk assessment system based on big data according to an embodiment of the present invention. Figure 5 As shown, parsing the behavioral information to obtain the third credit risk index includes the following process:

[0098] Step S501: Obtain the user's average monthly consumption amount H and consumption frequency L based on the behavior information;

[0099] Step S502: Obtain the user's monthly consumption preference based on the behavior information, wherein the consumption preference includes luxury consumption type, daily necessities consumption type, and electronic product consumption type. The user's monthly consumption preference is determined based on the proportion of the user's monthly consumption amount on each consumption type. The consumption type corresponding to the largest consumption amount proportion is recorded as the user's monthly consumption preference, and the consumption preference value K is determined based on the user's monthly consumption preference, wherein each consumption type corresponds to a different consumption preference value, which is set by the system;

[0100] Step S503: Substitute the average monthly consumption amount H, consumption frequency L and consumption preference value K into the third credit risk index calculation formula to calculate the third credit risk index. The calculation formula is as follows:

[0101]

[0102] Among them, DSZ is the third credit risk index, k1, k2, and k3 are weight coefficients, and their values ​​are 0.2, 0.4, and 0.4 respectively.

[0103] Further, evaluating the credit risk of the user based on the first credit risk index, the second credit risk index and the third credit risk index includes the following process:

[0104] Calculate the sum of the first credit risk index, the second credit risk index and the third credit risk index, record the sum as the total credit risk value of the user, and determine whether the total credit risk value of the user exceeds a preset total credit risk threshold of the user. If so, the credit risk of the user is high and the risk assessment will not be passed; if not, the credit risk of the user is low and the risk assessment will be allowed to pass, wherein the preset total credit risk threshold of the user is set by the system and stored in the system.

[0105] The present invention also provides a credit risk assessment method based on big data, the method comprising:

[0106] Receive a credit application request from a user, and obtain basic personal information of the user based on the credit application request, wherein the basic personal information includes age, occupation, social security record information and personal tax payment information, and obtain a credit qualification value of the user based on the basic personal information of the user, and determine whether the user is eligible for credit based on the credit qualification value of the user;

[0107] Obtain the declaration information corresponding to users with credit qualifications, and extract data from the declaration information based on the bag-of-words model to obtain financial information, credit record information, and behavioral information;

[0108] The financial information is parsed to obtain a first credit risk index, the credit record information is parsed to obtain a second credit risk index, and the behavioral information is parsed to obtain a third credit risk index;

[0109] The credit risk of the user is assessed based on the first credit risk index, the second credit risk index, and the third credit risk index.

[0110] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0111] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Credit risk assessment system based on big data, characterized by: The system includes a credit qualification management module, a declaration information acquisition module, a declaration information analysis module and a credit risk assessment module; The credit qualification management module is used to receive a user's credit application request, and obtain the user's basic personal information based on the user's credit application request, wherein the basic personal information includes age, occupation, social security record information and personal tax payment information, and obtain the user's credit qualification value based on the user's basic personal information, and determine whether the user has credit qualifications based on the user's credit qualification value; The declaration information acquisition module is used to obtain the declaration information corresponding to the credit-qualified users, and extract the declaration information based on the bag-of-words model to obtain financial information, credit record information and behavioral information; The declaration information parsing module is used to parse the financial information to obtain a first credit risk index, parse the credit record information to obtain a second credit risk index, and parse the behavior information to obtain a third credit risk index; The credit risk assessment module is used to assess the credit risk of the user based on the first credit risk index, the second credit risk index and the third credit risk index.

2. The credit risk assessment system based on big data according to claim 1, characterized in that: The process of obtaining the user's credit qualification value based on the user's basic personal information includes the following: Get the user's age NJ based on the user's basic personal information; Based on the user's personal basic information, the user's occupation is obtained, and it is determined whether the user's occupation is an unqualified occupation. If so, the user's occupation qualification R is 0, and if not, the user's occupation qualification R is 1, wherein the system stores pre-set unqualified occupation types; Based on the user's basic personal information, obtain the user's social security record information, and based on the social security record information, obtain the number of consecutive social security payment months S of the user; Obtain individual tax payment information based on the user's basic personal information, and obtain the user's total individual tax payment GS for the previous year based on the individual tax payment information; Substitute age NJ, professional qualification R, consecutive social security payment months S and total personal tax payment GS into the credit qualification value calculation formula to obtain the user's credit qualification value. The calculation formula is as follows: Among them, XDZ is the user's credit qualification value, and the value of e is 2.

72.

3. The credit risk assessment system based on big data according to claim 1, characterized in that: Judging whether a user is credit qualified based on the user's credit qualification value includes the following process: A credit qualification value threshold is obtained, wherein the credit qualification value threshold is stored in the system and is set by the system to determine whether the user's credit qualification value exceeds the credit qualification value threshold. If so, the user is credit qualified, and if not, the user is not credit qualified.

4. The credit risk assessment system based on big data according to claim 1, characterized in that: The data extraction of declared information based on the bag-of-words model to obtain financial information, credit record information and behavioral information includes the following process: Based on the bag-of-words model, data extraction of the declared information was performed to obtain financial terms corresponding to the financial information, credit record terms corresponding to the credit record information, and behavioral terms corresponding to the behavioral information. Among them, financial terms include real estate, vehicles, deposits, stocks, funds, debts, loans, credit card arrears, wages, bonuses, and investment income; credit record terms include loan amount, repayment record, default amount, and tax arrears; behavioral terms include consumption amount, consumption frequency, and consumption preference; Financial terms, credit record terms and behavioral terms are used as branches, and the data corresponding to each term is used as leaves, forming financial information, credit record information and behavioral information in a tree-like form, wherein the data corresponding to each term is a specific amount or number of records.

5. The credit risk assessment system based on big data according to claim 1, characterized in that: Parsing the financial information to obtain the first credit risk index includes the following process: Based on the financial information, the number of positive asset items and negative asset items of the user is counted, where the positive asset items are the real estate items, vehicle items, deposit items, stock items, fund items, salary items, bonus items, and investment income items owned by the user, and the negative asset items are the debt items, loan items, and credit card outstanding balances owned by the user, and the ratio A of the number of positive asset items to the number of negative asset items is calculated; Based on the financial information, calculate the sum B of the number of properties and vehicles of the user, and calculate the total amount C of the stock amount, fund amount, bonus amount, investment income amount and salary amount; Calculate the total amount D of the debt amount, loan amount and credit card outstanding amount based on the financial information; Substitute the ratios A, B, total amount C and total amount D into the first credit risk index calculation formula to obtain the first credit risk index, which is as follows: Among them, DYZ is the first credit risk index.

6. The credit risk assessment system based on big data according to claim 1, characterized in that: The process of parsing the credit record information to obtain the second credit risk index includes the following steps: Obtain the user's loan amount E based on the credit record information; Obtain repayment records based on credit record information, count the number of on-time repayments and the number of repayments after the repayment deadline based on the repayment records, and calculate the ratio F of the number of repayments after the repayment deadline to the number of on-time repayments; Obtain the total amount G of the user's default amount and tax arrears based on the credit record information; Substitute the loan amount E, ratio F, and total amount G into the second credit risk index calculation formula to calculate the second credit risk index, which is as follows: Among them, DEZ is the second credit risk index.

7. The credit risk assessment system based on big data according to claim 1, characterized in that: The process of parsing the behavioral information to obtain the third credit risk index includes the following steps: Based on the behavior information, obtain the user's average monthly consumption amount H and consumption frequency L; Based on the behavior information, the monthly consumption preference of the user is obtained, where the consumption preference includes luxury goods consumption type, daily necessities consumption type, and electronic product consumption type. The monthly consumption preference of the user is determined based on the proportion of the amount of money spent by the user on each consumption type each month. The consumption type corresponding to the largest proportion of the amount of money spent is recorded as the user's monthly consumption preference, and the consumption preference value K is determined based on the user's monthly consumption preference, where each consumption type corresponds to a different consumption preference value, which is set by the system; Substitute the average monthly consumption amount H, consumption frequency L and consumption preference value K into the third credit risk index calculation formula to calculate the third credit risk index, which is as follows: Among them, DSZ is the third credit risk index, k1, k2, and k3 are weight coefficients, and their values ​​are 0.2, 0.4, and 0.4 respectively.

8. The credit risk assessment system based on big data according to claim 1, characterized in that: Assessing the credit risk of a user based on the first credit risk index, the second credit risk index, and the third credit risk index includes the following process: Calculate the sum of the first credit risk index, the second credit risk index and the third credit risk index, record the sum as the total credit risk value of the user, and determine whether the total credit risk value of the user exceeds a preset total credit risk threshold of the user. If so, the credit risk of the user is high and the risk assessment will not be passed; if not, the credit risk of the user is low and the risk assessment will be allowed to pass, wherein the preset total credit risk threshold of the user is set by the system and stored in the system.

9. A credit risk assessment method based on big data, characterized in that: A credit risk assessment system based on big data applicable to any one of claims 1 to 8, the method comprising: Receive a credit application request from a user, and obtain basic personal information of the user based on the credit application request, wherein the basic personal information includes age, occupation, social security record information and personal tax payment information, and obtain a credit qualification value of the user based on the basic personal information of the user, and determine whether the user is eligible for credit based on the credit qualification value of the user; Obtain the declaration information corresponding to users with credit qualifications, and extract data from the declaration information based on the bag-of-words model to obtain financial information, credit record information, and behavioral information; The financial information is parsed to obtain a first credit risk index, the credit record information is parsed to obtain a second credit risk index, and the behavioral information is parsed to obtain a third credit risk index; The credit risk of the user is assessed based on the first credit risk index, the second credit risk index, and the third credit risk index.

Images