Database keyword-driven processing system and method for loan service

Abstract

The invention discloses a database keyword driving processing system and method for loan service, and belongs to the technical field of data driving. After user authorization, obtaining loan information of the user, and calculating a risk value of the user; presetting a risk value interval, and constructing a risk level allocation rule based on the risk value; obtaining risk levels of all users, and constructing a user risk level data set; constructing a loan service database, and calculating an association weight of the user and the keyword; presetting an association weight threshold value, and analyzing and designing different management schemes for users with different risk levels; and periodically acquiring the loan information, recalculating the risk value and the association weight of the user, and performing dynamic adjustment. According to the method, the loan service is driven through data, accurate division of risk levels and efficient management of personalized services are realized by relying on the loan service database and keyword association weight calculation, and regular dynamic adjustment is performed, so that the safety and flexibility of the loan service are ensured.

Description

Technical Field

[0001] The present invention relates to the field of data driven technology, and in particular to a database keyword driven processing system and method for loan services. Background Art

[0002] In recent years, financial service technologies based on big data analysis and artificial intelligence have been widely used around the world, which not only promoted the personalization and intelligence of loan services, but also provided a scientific basis for risk assessment and management. For example, traditional loan approval mainly relies on manual experience and simple scoring models. With the advancement of technology, more and more financial institutions have begun to adopt big data risk control models to establish dynamic risk assessment systems by analyzing users' credit records, repayment habits, etc. However, the existing technologies still have many shortcomings in practical applications, especially in how to formulate differentiated management and service strategies through correlation analysis of user risk levels and keywords. There is a lack of systematic solutions.

[0003] Most existing risk assessment models are based only on static user data, such as credit scores or the number of overdue payments, ignoring the impact of dynamic changes in risk factors on loan management; on the other hand, although some systems have introduced keyword matching mechanisms, they often remain at the level of simple text matching or rule setting, lacking in-depth exploration of the complex relationship between users and keywords; in addition, service strategies for users of different risk levels are mostly implemented in a one-size-fits-all manner, failing to fully consider individual differences among users, which not only reduces service efficiency but also increases risk control costs. Summary of the invention

[0004] The object of the present invention is to provide a database keyword driven processing system and method for loan services to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A database keyword-driven processing method for loan services, the method comprising the following steps: after authorization by the user, obtaining the user's loan information and calculating the user's risk value; presetting a risk value interval, and constructing a risk level allocation rule based on the risk value; obtaining the risk levels of all users and constructing a user risk level data set; constructing a loan service database, and calculating the association weights between users and keywords; presetting an association weight threshold, analyzing and designing different management plans for users of different risk levels; regularly obtaining the loan information, recalculating the user's risk value and association weight, and making dynamic adjustments.

[0007] As a preferred solution of the database keyword-driven processing method for loan services described in the present invention, after authorization by the user, the user's loan information is obtained, the loan information includes the user's credit score and the user's repayment record, and the user's credit score is scored through the user's credit investigation; based on the user's repayment record, the number of overdue repayments of the user is extracted, and based on the user's credit score and the number of overdue repayments, the user's risk value is calculated, as follows:

[0008] FX i =α1×CS i +α2×OR i ;

[0009] Among them, FX i represents the risk value of the i-th user, α1 represents the preset user credit score weight coefficient, CS i represents the user credit score of the i-th user, α2 represents the preset overdue repayment weight coefficient, and OR i represents the number of overdue repayments of the i-th user, and i∈[1,I], where I represents the total number of users.

[0010] As a preferred solution of the database keyword driven processing method for loan services described in the present invention, the preset risk value interval [FX min FX max ], among which, FX max Indicates the maximum risk value within the risk value range, FX mm Indicates the minimum risk value within the risk value range, based on the risk value range [FX min FX max ], construct the risk level allocation rules, as follows:

[0011] If the risk value of the i-th user FX i >FX max , then the i-th user is recorded as a high-risk user.

[0012] If the risk value of the i-th user FX max >FX i >FX min , then the i-th user is recorded as a medium-risk level user.

[0013] If the risk value of the i-th user FX i <FX min , then the i-th user is recorded as a low-risk user.

[0014] As a preferred solution of the database keyword-driven processing method for loan services described in the present invention, let i=i+1, traverse the users, obtain the risk levels of all users, and construct a user risk level data set, recorded as URL={UFX i，j |j∈[1,J],i∈[1,I]},where UFX i，j indicates that the i-th user is a user of the j-th risk level, and J represents the total number of risk levels (in the present invention, J is 3, that is, there are three risk levels, j=1 represents high risk, j=2 represents medium risk, and j=3 represents low risk; for example, UFX 1，2 It means that the first user is a user of the second risk level, that is, the first user is a user of the medium risk level).

[0015] Construct a loan service database, wherein the loan service database stores keywords based on loan services, and the loan service database is recorded as LSD={kw a |a∈[1,A]}, where kw a represents the ath keyword, and A represents the total number of keywords (the keywords include repayment ability, application purpose, loan amount, overdue reason, etc.).

[0016] Calculate users and keywords kw a The association weight is calculated as follows:

[0017]

[0018] Among them, UFX i，j (a) represents the i-th user with the j-th risk level and the a-th keyword kw a The association weight between j represents the preset weight coefficient of the jth risk level (when j=1, the weight coefficient is high, when j=2, the weight coefficient is medium, and when j=3, the weight coefficient is low), δ a Indicates the preset keyword kw a The weight coefficient, K i，a Indicates the matching degree between the ith user and the ath keyword.

[0019] As a preferred solution of the database keyword driven processing method for loan services described in the present invention, a correlation weight threshold is preset. If the user is associated with the keyword kw a The associated weight of UFX i，j (a) is greater than the associated weight threshold, and the user is a high-risk user, then when the user applies for a loan, a high-risk warning signal is issued (to remind loan approval personnel to conduct more stringent review and risk assessment).

[0020] If the user and the keyword kwa The associated weight of UFX i，j (a) If the loan amount is greater than the associated weight threshold and the user is a medium-risk user, a loan amount adjustment suggestion and a repayment plan optimization plan are provided to the medium-risk user (for example, for users with unstable income but certain repayment potential, the loan amount can be appropriately reduced and the repayment period can be extended to reduce their repayment pressure and default risk).

[0021] If the user and the keyword kw a The associated weight of UFX i，j (a) If the associated weight is greater than the associated weight threshold and the user is a low-risk user, a preferential loan service policy is formulated for the low-risk user (for example, a more attractive loan interest rate and loan amount are provided to encourage them to continue to maintain a good credit and financial status).

[0022] It should be noted that the personalized services provided to users of different risk levels can meet the needs of users under different credit conditions; although high-risk users face stricter review, this is also to ensure the rationality and feasibility of the loan; the loan amount adjustment and repayment plan optimization suggestions received by medium-risk users can help them better manage loans and reduce repayment pressure; the preferential policies enjoyed by low-risk users can enable them to feel the value of their good credit, enhance their trust and satisfaction with lending institutions, thereby improving user loyalty and promoting long-term cooperation.

[0023] The user's credit score and number of overdue repayments are obtained regularly, and the user's risk level and associated weight are recalculated and dynamically adjusted.

[0024] It should be noted that the present invention relies on the loan service database and keyword association weight calculation to drive loan service decisions with data. This is consistent with the concept of "collection, collection and sharing" of inclusive green information data by "Weiluda" with the help of Taizhou Digital Financial Service Platform, using privacy computing, model co-construction and other means; for example, the system in the present invention continuously learns and improves the keyword library to improve matching accuracy, just like the system in "Weiluda" automatically learns different keywords, combines recommendations from multiple parties to build a "green means of production library", and continuously iterates and optimizes the keyword library, all of which use data accumulation and optimization as a means to improve the accuracy and effectiveness of the business, thereby promoting the high-quality development of financial services.

[0025] The present invention provides personalized loan services based on the user's risk level, such as formulating preferential loan policies for users with low risk levels. This echoes the "Micro Green" initiative to give policy preferences to working capital loans that meet green loan standards in terms of credit guarantee fund guarantee fee reductions, financial subsidies, re-loans and re-discounts. Both provide differentiated support and incentives based on the specific circumstances of the objects to achieve specific goals. The present invention aims to encourage users to maintain good credit and financial status, while "Micro Green" aims to assist small and micro entities in their green transformation and promote the development of green finance. Through personalized services and policy guidance, the two encourage users or enterprises to develop in a positive direction, realize the organic integration of financial services and social development goals, and jointly contribute to the healthy development of the financial market and the realization of social goals.

[0026] A database keyword driven processing system for loan services includes: a data acquisition and risk calculation module, a risk level allocation module, a database construction and weight calculation module, and an analysis and dynamic adjustment module.

[0027] The data acquisition and risk calculation module: after authorization by the user, obtains the user's loan information and calculates the user's risk value.

[0028] The risk level allocation module presets a risk value interval and constructs a risk level allocation rule based on the risk value.

[0029] The database construction and weight calculation module: obtains the risk level of all users and constructs a user risk level data set; constructs a loan service database and calculates the association weights between users and keywords.

[0030] The analysis and dynamic adjustment module: presets the associated weight threshold, analyzes and designs different management plans for users with different risk levels; regularly obtains the loan information, recalculates the user's risk value and associated weight, and performs dynamic adjustments.

[0031] Furthermore, the data acquisition and risk calculation module includes a data acquisition unit and a risk calculation unit.

[0032] The data acquisition unit: after authorization by the user, acquires the user's loan information, the loan information includes the user's credit score and the user's repayment record, the user's credit score is scored through user credit investigation; based on the user's repayment record, extracts the number of overdue repayments of the user.

[0033] The risk calculation unit calculates the risk value of the user based on the user's credit score and the number of overdue repayments.

[0034] Furthermore, the risk level allocation module includes a risk level allocation unit.

[0035] The risk level allocation unit: presets a risk value interval, and constructs a risk level allocation rule based on the risk value interval, which is specifically as follows:

[0036] If the user's risk value is greater than the maximum value in the risk value range, the user will be recorded as a high-risk level user.

[0037] If the user's risk value is greater than the minimum value in the risk value range and less than the maximum value in the risk value range, the user is recorded as a medium-risk level user.

[0038] If the user's risk value is less than the minimum value in the risk value range, the user is recorded as a low-risk user.

[0039] Furthermore, the database construction and weight calculation module includes a database construction unit and a weight calculation unit.

[0040] The database construction unit: traverses the users, obtains the risk levels of all users, and constructs a user risk level data set; constructs a loan service database, and the loan service database stores keywords based on loan services.

[0041] The weight calculation unit calculates the association weight between the user and the keyword.

[0042] Furthermore, the analysis and dynamic adjustment module includes an analysis unit and a dynamic adjustment unit.

[0043] The analysis unit: presets an association weight threshold. If the association weight between the user and the keyword is greater than the association weight threshold, and the user is a high-risk user, a high-risk warning signal is issued when the user applies for a loan; if the association weight between the user and the keyword is greater than the association weight threshold, and the user is a medium-risk user, a loan amount adjustment suggestion and a repayment plan optimization plan are provided for the medium-risk user; if the association weight between the user and the keyword is greater than the association weight threshold, and the user is a low-risk user, a preferential loan service policy is formulated for the low-risk user.

[0044] The dynamic adjustment unit periodically obtains the user's credit score and the number of overdue repayments, recalculates the user's risk level and associated weight, and performs dynamic adjustments.

[0045] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in a database keyword-driven processing system and method for loan services provided by the present invention, by obtaining loan information and calculating risk values ​​with user authorization, a quantitative assessment of the user's credit status is achieved, ensuring the accuracy and pertinence of subsequent processing; by presetting risk value intervals and constructing risk level allocation rules, a refined classification of user risks is achieved, providing a basis for differentiated management; by constructing a user risk level data set and a loan service database, and calculating the association weights between users and keywords, a deep matching of user risk characteristics and service needs is achieved, and the accuracy of loan services is improved; by setting an association weight threshold, designing personalized management plans according to different risk levels, and regularly adjusting them dynamically, real-time monitoring of user risk status and service optimization are achieved, ensuring the security and flexibility of loan services; overall, the present invention improves the accuracy and effectiveness of loan services in a data-driven manner, and promotes a two-way improvement in risk control and user service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0047] Figure 1 It is a schematic diagram of the steps of a database keyword driven processing method for loan services of the present invention;

[0048] Figure 2 It is a structural schematic diagram of a database keyword driven processing system for loan services according to the present invention. DETAILED DESCRIPTION

[0049] 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.

[0050] See also Figure 1 In the first embodiment, a database keyword-driven processing method for loan services is provided, the method comprising the following steps:

[0051] Step S1: After authorization by the user, obtain the user's loan information and calculate the user's risk value.

[0052] Specifically, after authorization by the user, the user's loan information is obtained, the loan information includes the user's credit score and the user's repayment record, and the user's credit score is scored through the user's credit investigation; based on the user's repayment record, the number of overdue repayments of the user is extracted, and based on the user's credit score and the number of overdue repayments, the user's risk value is calculated, as follows:

[0053] FX i =α1×CS i +α2×OR i ;

[0054] Among them, FX i represents the risk value of the i-th user, α1 represents the preset user credit score weight coefficient, CS i represents the user credit score of the i-th user, α2 represents the preset overdue repayment weight coefficient, and OR i represents the number of overdue repayments of the i-th user, and i∈[1,I], where I represents the total number of users.

[0055] Step S2: Preset a risk value interval and construct a risk level allocation rule based on the risk value.

[0056] Specifically, the preset risk value range [FX min FX max ], among which, FX max Indicates the maximum risk value within the risk value range, FX mm Indicates the minimum risk value within the risk value range, based on the risk value range [FX min FX max ], construct the risk level allocation rules, as follows:

[0057] If the risk value of the i-th user FX i >FX max , then the i-th user is recorded as a high-risk user.

[0058] If the risk value of the i-th user FX max >FX i >FX min , then the i-th user is recorded as a medium-risk level user.

[0059] If the risk value of the i-th user FX i <FX min , then the i-th user is recorded as a low-risk user.

[0060] Step S3: Obtain the risk levels of all users and construct a user risk level data set; construct a loan service database and calculate the association weights between users and keywords.

[0061] Specifically, let i = i + 1, traverse the users, obtain the risk levels of all users, and construct a user risk level dataset, recorded as URL = {UFX i，j |j∈[1,J],i∈[1,I]},where UFX i，j indicates that the i-th user is a user of the j-th risk level, and J represents the total number of risk levels (in the present invention, J is 3, that is, there are three risk levels, j=1 represents high risk, j=2 represents medium risk, and j=3 represents low risk; for example, UFX 1，2 It means that the first user is a user of the second risk level, that is, the first user is a user of the medium risk level).

[0062] Furthermore, a loan service database is constructed, wherein the loan service database stores keywords based on loan services, and the loan service database is recorded as LSD={kw a |a∈[1,A]}, where kw a represents the ath keyword, and A represents the total number of keywords (the keywords include repayment ability, application purpose, loan amount, overdue reason, etc.).

[0063] Furthermore, we calculate the user and keyword kw a The association weight is calculated as follows:

[0064]

[0065] Among them, UFX i，j (a) represents the i-th user with the j-th risk level and the a-th keyword kw a The association weight between j represents the preset weight coefficient of the jth risk level (when j=1, the weight coefficient is high, when j=2, the weight coefficient is medium, and when j=3, the weight coefficient is low), δ a Indicates the preset keyword kw a The weight coefficient, K i，a Indicates the matching degree between the ith user and the ath keyword.

[0066] Step S4: preset the associated weight threshold, analyze and design different management plans for users with different risk levels; regularly obtain the loan information, recalculate the user's risk value and associated weight, and make dynamic adjustments.

[0067] Preset association weight threshold, if the user is associated with keyword kw a The associated weight of UFX i，j(a) is greater than the associated weight threshold, and the user is a high-risk user, then when the user applies for a loan, a high-risk warning signal is issued (to remind loan approval personnel to conduct more stringent review and risk assessment).

[0068] If the user and the keyword kw a The associated weight of UFX i，j (a) If the loan amount is greater than the associated weight threshold and the user is a medium-risk user, a loan amount adjustment suggestion and a repayment plan optimization plan are provided to the medium-risk user (for example, for users with unstable income but certain repayment potential, the loan amount can be appropriately reduced and the repayment period can be extended to reduce their repayment pressure and default risk).

[0069] If the user and the keyword kw a The associated weight of UFX i，j (a) If the associated weight is greater than the associated weight threshold and the user is a low-risk user, a preferential loan service policy is formulated for the low-risk user (for example, a more attractive loan interest rate and loan amount are provided to encourage them to continue to maintain a good credit and financial status).

[0070] It should be noted that the personalized services provided to users of different risk levels can meet the needs of users under different credit conditions; although high-risk users face stricter review, this is also to ensure the rationality and feasibility of the loan; the loan amount adjustment and repayment plan optimization suggestions received by medium-risk users can help them better manage loans and reduce repayment pressure; the preferential policies enjoyed by low-risk users can enable them to feel the value of their good credit, enhance their trust and satisfaction with lending institutions, thereby improving user loyalty and promoting long-term cooperation.

[0071] The user's credit score and number of overdue repayments are obtained regularly, and the user's risk level and associated weight are recalculated and dynamically adjusted.

[0072] It should be noted that the present invention relies on the loan service database and keyword association weight calculation to drive loan service decision-making with data, which is consistent with the concept of "collection, collection and sharing" of inclusive green information data by "Weiluda" with the help of Taizhou Digital Intelligence Financial Service Platform, using privacy computing, model co-construction and other means. For example, the system in the present invention continuously learns and improves the keyword library to improve the matching accuracy, just like the system in "Weiluda" automatically learns different keywords, combines multi-party recommendations to build a "green production materials library", and continuously iterates and optimizes the keyword library, all of which use data accumulation and optimization as a means to improve the accuracy and effectiveness of the business, thereby promoting the high-quality development of financial services.

[0073] The present invention provides personalized loan services based on the user's risk level, such as formulating preferential loan policies for users with low risk levels. This echoes the "Micro Green" initiative to give policy preferences to working capital loans that meet green loan standards in terms of credit guarantee fund guarantee fee reductions, financial subsidies, re-loans and re-discounts. Both provide differentiated support and incentives based on the specific circumstances of the objects to achieve specific goals. The present invention aims to encourage users to maintain good credit and financial status, while "Micro Green" aims to assist small and micro entities in their green transformation and promote the development of green finance. Through personalized services and policy guidance, the two encourage users or enterprises to develop in a positive direction, realize the organic integration of financial services and social development goals, and jointly contribute to the healthy development of the financial market and the realization of social goals.

[0074] Looking further, the present invention can draw on the ideas of "Micro Green" in data application to expand data sources and application scenarios. For example, when assessing user risks, in addition to existing data such as credit scores and repayment records, you can try to include data related to the green development of small and micro enterprises, such as the company's green production inputs, energy conservation and emission reduction indicators, etc., to enrich the risk assessment dimensions, make risk assessment more comprehensive and accurate, and better serve the field of green finance. At the same time, the personalized service strategy of the present invention can also be combined with green financial policies. For small and micro enterprises that actively participate in green transformation and have lower risks, in addition to providing preferential loan policies, green finance-related rewards or support can also be given, such as priority access to green financial product recommendations, green financial project guidance, etc., to further promote the green development of small and micro enterprises, form a synergistic effect with "Micro Green", and jointly promote the prosperity of the green financial ecology.

[0075] See also Figure 2 In the second embodiment of the present invention, a database keyword driven processing system for loan services is provided, the system comprising: a data acquisition and risk calculation module, a risk level allocation module, a database construction and weight calculation module and an analysis and dynamic adjustment module.

[0076] The data acquisition and risk calculation module: after authorization by the user, obtains the user's loan information and calculates the user's risk value.

[0077] The risk level allocation module presets a risk value interval and constructs a risk level allocation rule based on the risk value.

[0078] The database construction and weight calculation module: obtains the risk level of all users and constructs a user risk level data set; constructs a loan service database and calculates the association weights between users and keywords.

[0079] The analysis and dynamic adjustment module: presets the associated weight threshold, analyzes and designs different management plans for users with different risk levels; regularly obtains the loan information, recalculates the user's risk value and associated weight, and performs dynamic adjustments.

[0080] Furthermore, the data acquisition and risk calculation module includes a data acquisition unit and a risk calculation unit.

[0081] The data acquisition unit: after authorization by the user, acquires the user's loan information, the loan information includes the user's credit score and the user's repayment record, the user's credit score is scored through user credit investigation; based on the user's repayment record, extracts the number of overdue repayments of the user.

[0082] The risk calculation unit calculates the risk value of the user based on the user's credit score and the number of overdue repayments.

[0083] Furthermore, the risk level allocation module includes a risk level allocation unit.

[0084] The risk level allocation unit: presets a risk value interval, and constructs a risk level allocation rule based on the risk value interval, which is specifically as follows:

[0085] If the user's risk value is greater than the maximum value in the risk value range, the user will be recorded as a high-risk level user.

[0086] If the user's risk value is greater than the minimum value in the risk value range and less than the maximum value in the risk value range, the user is recorded as a medium-risk level user.

[0087] If the user's risk value is less than the minimum value in the risk value range, the user is recorded as a low-risk user.

[0088] Furthermore, the database construction and weight calculation module includes a database construction unit and a weight calculation unit.

[0089] The database construction unit: traverses the users, obtains the risk levels of all users, and constructs a user risk level data set; constructs a loan service database, and the loan service database stores keywords based on loan services.

[0090] The weight calculation unit calculates the association weight between the user and the keyword.

[0091] Furthermore, the analysis and dynamic adjustment module includes an analysis unit and a dynamic adjustment unit.

[0092] The analysis unit: presets an association weight threshold. If the association weight between the user and the keyword is greater than the association weight threshold, and the user is a high-risk user, a high-risk warning signal is issued when the user applies for a loan; if the association weight between the user and the keyword is greater than the association weight threshold, and the user is a medium-risk user, a loan amount adjustment suggestion and a repayment plan optimization plan are provided for the medium-risk user; if the association weight between the user and the keyword is greater than the association weight threshold, and the user is a low-risk user, a preferential loan service policy is formulated for the low-risk user.

[0093] The dynamic adjustment unit periodically obtains the user's credit score and the number of overdue repayments, recalculates the user's risk level and associated weight, and performs dynamic adjustments.

[0094] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0095] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A database keyword-driven processing method for loan services, characterized in that: The method comprises the following steps: Step S1: After the user's authorization, obtain the user's loan information and calculate the user's risk value; Step S2: Preset a risk value interval, and construct a risk level allocation rule based on the risk value; Step S3: Obtain the risk level of all users and construct a user risk level data set; construct a loan service database and calculate the association weight between users and keywords; Step S4: preset the associated weight threshold, analyze and design different management plans for users with different risk levels; regularly obtain the loan information, recalculate the user's risk value and associated weight, and make dynamic adjustments.

2. A database keyword driven processing method for loan services according to claim 1, characterized in that: The specific implementation process of step S1 includes: After the user's authorization, the user's loan information is obtained, and the loan information includes the user's credit score and the user's repayment record. The user's credit score is scored through the user's credit investigation; based on the user's repayment record, the number of overdue repayments of the user is extracted, and based on the user's credit score and the number of overdue repayments, the user's risk value is calculated, as follows: FX i =α1×CS i +α2×OR i ; Among them, FX i represents the risk value of the i-th user, α1 represents the preset user credit score weight coefficient, CS i represents the user credit score of the i-th user, α2 represents the preset overdue repayment weight coefficient, and OR i represents the number of overdue repayments of the i-th user, and i∈[1,I], where I represents the total number of users.

3. A database keyword driven processing method for loan services according to claim 2, characterized in that: The specific implementation process of step S2 includes: Preset risk value range [FX min FX max ], among which, FX max Indicates the maximum risk value within the risk value range, FX min Indicates the minimum risk value within the risk value range, based on the risk value range [FX min FX max ], construct the risk level allocation rules, as follows: If the risk value of the i-th user FX i >FX max , then the i-th user is recorded as a high-risk user; If the risk value of the i-th user FX max >FX i >FX min , then the i-th user is recorded as a medium-risk level user; If the risk value of the i-th user FX i <FX min , then the i-th user is recorded as a low-risk user.

4. A database keyword driven processing method for loan services according to claim 3, characterized in that: The specific implementation process of step S3 includes: Let i = i + 1, traverse the users, obtain the risk level of all users, and build a user risk level dataset, recorded as URL = {UFX i，j |j∈[1,J],i∈[1,I]},where UFX i，j Indicates that the i-th user is a user of the j-th risk level, and J represents the total number of risk levels; Construct a loan service database, wherein the loan service database stores keywords based on loan services, and the loan service database is recorded as LSD={kw a |a∈[1,A]}, where kw a represents the ath keyword, and A represents the total number of keywords; Calculate users and keywords kw a The association weight is calculated as follows: Among them, UFX i，j (a) represents the i-th user with the j-th risk level and the a-th keyword kw a The association weight between j represents the weight coefficient of the preset j-th risk level, δ a Indicates the preset keyword kw a The weight coefficient, K i，a Indicates the matching degree between the ith user and the ath keyword.

5. A database keyword driven processing method for loan services according to claim 4, characterized in that: The specific implementation process of step S4 includes: Preset association weight threshold, if the user is associated with keyword kw a The associated weight of UFX i，j (a) if the value of the user's credit risk is greater than the associated weight threshold and the user is a high-risk user, a high-risk warning signal is issued when the user applies for a loan; If the user and the keyword kw a The associated weight of UFX i，j (a) if the amount of the loan is greater than the associated weight threshold and the user is a medium-risk user, a loan amount adjustment suggestion and a repayment plan optimization plan are provided to the medium-risk user; If the user and the keyword kw a The associated weight of UFX i，j (a) if the value of the associated weight is greater than the associated weight threshold, and the user is a low-risk user, a preferential loan service policy is formulated for the low-risk user; The user's credit score and number of overdue repayments are obtained regularly, and the user's risk level and associated weight are recalculated and dynamically adjusted.

6. A database keyword driven processing system for loan services, executing a database keyword driven processing method for loan services as claimed in any one of claims 1 to 5, characterized in that: The system includes: a data acquisition and risk calculation module, a risk level allocation module, a database construction and weight calculation module, and an analysis and dynamic adjustment module; The data acquisition and risk calculation module: after authorization by the user, obtains the user's loan information and calculates the user's risk value; The risk level allocation module: presets a risk value interval and constructs a risk level allocation rule based on the risk value; The database construction and weight calculation module: obtains the risk level of all users and constructs a user risk level data set; constructs a loan service database and calculates the association weight between users and keywords; The analysis and dynamic adjustment module: presets the associated weight threshold, analyzes and designs different management plans for users with different risk levels; regularly obtains the loan information, recalculates the user's risk value and associated weight, and performs dynamic adjustments.

7. A database keyword driven processing system for loan services according to claim 6, characterized in that: The data acquisition and risk calculation module includes a data acquisition unit and a risk calculation unit; The data acquisition unit: after authorization by the user, acquires the user's loan information, the loan information includes the user's credit score and the user's repayment record, the user's credit score is scored through the user's credit investigation; based on the user's repayment record, extracts the number of overdue repayments of the user; The risk calculation unit calculates the risk value of the user based on the user's credit score and the number of overdue repayments.

8. A database keyword driven processing system for loan services according to claim 7, characterized in that: The risk level allocation module includes a risk level allocation unit; The risk level allocation unit: presets a risk value interval, and constructs a risk level allocation rule based on the risk value interval, which is specifically as follows: If the user's risk value is greater than the maximum value in the risk value range, the user will be recorded as a high-risk user; If the user's risk value is greater than the minimum value in the risk value range and less than the maximum value in the risk value range, the user will be recorded as a medium-risk level user; If the user's risk value is less than the minimum value in the risk value range, the user is recorded as a low-risk user.

9. A database keyword driven processing system for loan services according to claim 8, characterized in that: The database construction and weight calculation module includes a database construction unit and a weight calculation unit; The database construction unit: traverses the users, obtains the risk levels of all users, and constructs a user risk level data set; constructs a loan service database, wherein the loan service database stores keywords based on loan services; The weight calculation unit calculates the association weight between the user and the keyword.

10. A database keyword driven processing system for loan services according to claim 9, characterized in that: The analysis and dynamic adjustment module includes an analysis unit and a dynamic adjustment unit; The analysis unit: presets an association weight threshold, and if the association weight between the user and the keyword is greater than the association weight threshold, and the user is a high-risk user, then when the user applies for a loan, a high-risk warning signal is issued; If the association weight between the user and the keyword is greater than the association weight threshold, and the user is a medium-risk user, a loan amount adjustment suggestion and a repayment plan optimization plan are provided for the medium-risk user; if the association weight between the user and the keyword is greater than the association weight threshold, and the user is a low-risk user, a preferential loan service policy is formulated for the low-risk user; The dynamic adjustment unit periodically obtains the user's credit score and the number of overdue repayments, recalculates the user's risk level and associated weight, and performs dynamic adjustments.

Images