Financial risk strategy generation method, device and electronic equipment

Abstract

The present disclosure relates to a method, device, electronic device and computer-readable medium for generating a financial risk strategy. The method comprises: obtaining at least one updated parameter of a credit user from a third-party database; obtaining at least one characteristic parameter of the credit user; arbitrarily combining the at least one updated parameter and the parameters in the at least one characteristic parameter to generate multiple combined parameter sets; inputting each combined parameter set in the multiple combined parameter sets into a machine learning model to obtain a financial risk parameter value; and when the financial risk parameter value meets the threshold rule, generating a financial risk strategy based on the combined parameter set corresponding to the risk parameter. The method, device, electronic device and computer-readable medium for generating a financial risk strategy involved in the present disclosure can automatically analyze the user data introduced by the third-party database, and combine it with the existing parameters to generate an updated financial risk strategy set.

Description

Technical Field

[0001] The present disclosure relates to the field of computer information processing, and in particular, to a financial risk strategy generation method, device, electronic device and computer-readable medium. Background Art

[0002] Credit refers to a form of value movement with repayment and interest payment as conditions, usually including bank deposits, loans and other credit activities. Credit is an important form of mobilizing and allocating funds in a paid manner and is a powerful lever for economic development. The generation of loans is inevitably accompanied by risks. Before the repayment period expires, major adverse changes in the borrower's financial and business conditions are likely to affect its ability to perform, thereby causing risks such as bad debts and bad debts. Therefore, in order to reduce the probability of such risks, it is necessary to limit the borrower's financial behavior through various financial risk strategies.

[0003] In terms of strategy formulation, the existing technology formulates financial risk strategies based on the personal characteristics, personal behaviors, or behavioral analysis of the user's associated users input by the user. In order to monitor the real-time situation of users and prevent risks, financial service institutions often need to obtain relevant data of users from a third party, and then conduct a joint analysis of the user input data and the relevant data of the third party to determine the final user financial risk strategy. In the third-party data, since each user has a large amount of input data (that is, a large amount of data of different dimensions corresponding to the same customer, hundreds or thousands of dimensions) for strategy formulation and iteration, especially the dimensions of user data given by different third-party data are not consistent, some dimensions have more items, and some dimensions are missing. At present, for third-party data, the only way is to screen the data through manual analysis, and manually combine the third-party data with the original financial risk strategy. This processing method is very inefficient.

[0004] Therefore, a new financial risk strategy generation method, device, electronic device and computer-readable medium are needed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] In view of this, the present disclosure provides a financial risk strategy generation method, device, electronic device and computer-readable medium, which can automatically analyze user data introduced by a third-party database and combine it with existing parameters to generate an updated financial risk strategy set.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a method for generating a financial risk strategy is proposed, the method comprising: obtaining at least one updated parameter of a credit user from a third-party database; obtaining at least one characteristic parameter of the credit user; arbitrarily combining the at least one updated parameter and parameters in the at least one characteristic parameter to generate a plurality of combined parameter sets; inputting each of the plurality of combined parameter sets into a machine learning model to obtain a financial risk parameter value; and generating a financial risk strategy based on the combined parameter set corresponding to the risk parameter when the financial risk parameter value meets a threshold rule.

[0009] Optionally, the method further includes: performing an update impact analysis based on the financial risk strategy and the user data of the credit user.

[0010] Optionally, obtaining at least one updated parameter of the credit user from a third-party database includes: obtaining user data of the credit user from the third-party database; and performing data cleaning processing on the user data to obtain the at least one updated parameter.

[0011] Optionally, performing data cleansing on the user data to obtain the at least one updated parameter includes: performing data cleansing on the user data to obtain multiple user parameters; and eliminating parameters that are not related to financial risks from the multiple user parameters to obtain the at least one updated parameter.

[0012] Optionally, each of the multiple combined parameter sets is input into a machine learning model, and obtaining the financial risk parameter value also includes: generating the machine learning model through user data of historical credit users and the at least one characteristic parameter.

[0013] Optionally, each of the multiple combination parameter sets is input into a machine learning model, and obtaining a financial risk parameter value includes: inputting each of the multiple combination parameter sets into a machine learning model; the machine learning model performs iterative calculations based on multiple parameters in the combination parameter set; and when the iterative calculations meet preset conditions, generating a financial risk parameter value for the combination parameter set.

[0014] Optionally, when the financial risk parameter value meets the threshold rule, generating a financial risk strategy based on the combined parameter set corresponding to the risk parameter includes: when the financial risk parameter value meets the threshold rule, determining multiple financial risk sub-strategies corresponding to multiple parameters in the combined parameter set corresponding to the risk parameter; and generating the financial risk strategy through the intersection of the multiple financial risk sub-strategies.

[0015] Optionally, performing an update impact analysis based on the financial risk strategy and the user data of the credit user includes: generating a financial risk value through the user data of the credit user and a financial risk model; generating a verification risk value through the user data of the credit user and a verification risk model; and performing the update impact analysis through the verification risk value and the financial risk value.

[0016] Optionally, performing update impact analysis based on the financial risk strategy and the user data of the credit user further includes: updating the financial risk model based on parameters in the financial risk strategy to generate the verification model.

[0017] Optionally, the financial risk model includes at least one of the following: a user pass rate model, a risk prediction model, and a credit limit model.

[0018] According to one aspect of the present disclosure, a financial risk strategy generating device is proposed, which includes: an update data module, used to obtain at least one update parameter of a credit user from a third-party database; a feature parameter module, used to obtain at least one feature parameter of a credit user; a combination parameter module, used to arbitrarily combine the at least one update parameter and the parameters in the at least one feature parameter to generate a plurality of combination parameter sets; a model calculation module, used to input each combination parameter set in the plurality of combination parameter sets into a machine learning model to obtain a financial risk parameter value; and a risk strategy module, used to generate a financial risk strategy based on the combination parameter set corresponding to the risk parameter when the financial risk parameter value meets a threshold rule.

[0019] Optionally, it also includes: an update analysis module, used to perform update impact analysis based on the financial risk strategy and the user data of the credit user.

[0020] Optionally, the data update module includes: a data acquisition unit, used to acquire user data of credit users from a third-party database; and a data cleaning unit, used to perform data cleaning processing on the user data to obtain the at least one update parameter.

[0021] Optionally, the data cleaning unit includes: a cleaning subunit, used to perform data cleaning processing on the user data to obtain multiple user parameters; and a elimination subunit, used to eliminate parameters unrelated to financial risks from the multiple user parameters to obtain the at least one updated parameter.

[0022] Optionally, the model calculation module also includes: a model generation unit, used to generate the machine learning model through user data of historical credit users and the at least one characteristic parameter.

[0023] Optionally, the model calculation module includes: an input unit, used to input each of the multiple combination parameter sets into the machine learning model; an iteration unit, used for the machine learning model to perform iterative calculation based on multiple parameters in the combination parameter set; and a model unit, used to generate a financial risk parameter value of the combination parameter set when the iterative calculation meets preset conditions.

[0024] Optionally, the risk strategy module includes: a sub-strategy unit, used to determine multiple financial risk sub-strategies corresponding to multiple parameters in a combination parameter set corresponding to the risk parameter when the financial risk parameter value meets a threshold rule; and a collection unit, used to generate the financial risk strategy through the intersection of the multiple financial risk sub-strategies.

[0025] Optionally, the update analysis module includes: a financial risk unit, used to generate a financial risk value through the user data of the credit user and a financial risk model; a verification risk unit, used to generate a verification risk value through the user data of the credit user and a verification risk model; and an update analysis unit, used to perform the update impact analysis through the verification risk value and the financial risk value.

[0026] Optionally, the update analysis module further includes: a verification model unit, configured to update the financial risk model based on parameters in the financial risk strategy and generate the verification model.

[0027] Optionally, the financial risk model includes at least one of the following: a user pass rate model, a risk prediction model, and a credit limit model.

[0028] According to one aspect of the present disclosure, an electronic device is proposed, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0029] According to one aspect of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.

[0030] According to the financial risk strategy generation method, device, electronic device and computer-readable medium disclosed in the present invention, the updated parameters of the credit user and the parameters in the characteristic parameters of the credit user obtained from the third-party database are arbitrarily combined to generate multiple combination parameter sets; each combination parameter set in the multiple combination parameter sets is input into the machine learning model to obtain the financial risk parameter value; and when the financial risk parameter value meets the threshold rule, the financial risk strategy is generated based on the combination parameter set corresponding to the risk parameter. This method can automatically analyze the user data introduced by the third-party database, and combine it with the existing parameters to generate an updated financial risk strategy set.

[0031] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail its exemplary embodiments with reference to the accompanying drawings. The accompanying drawings described below are only some embodiments of the present disclosure, and it is clear to a person skilled in the art that other accompanying drawings can be obtained from these accompanying drawings without creative work.

[0033] Figure 1 It is a system block diagram of a method and device for generating a financial risk strategy according to an exemplary embodiment.

[0034] Figure 2 The present invention is a flowchart of a method for generating a financial risk strategy according to an exemplary embodiment.

[0035] Figure 3 The present invention is a flowchart of a method for generating a financial risk strategy according to another exemplary embodiment.

[0036] Figure 4 is a schematic diagram of a method for generating a financial risk strategy according to another exemplary embodiment.

[0037] Figure 5 The present invention is a flowchart of a method for generating a financial risk strategy according to another exemplary embodiment.

[0038] Figure 6 It is a block diagram of a financial risk strategy generating device according to an exemplary embodiment.

[0039] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment.

[0040] Figure 8 It is a block diagram of a computer-readable medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0041] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0042] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0043] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0044] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0045] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the disclosed concepts. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0046] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present disclosure, and therefore cannot be used to limit the protection scope of the present disclosure.

[0047] Figure 1 It is a system block diagram of a method and device for generating a financial risk strategy according to an exemplary embodiment.

[0048] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, a financial network server 105, and a third-party server 106. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the financial network server 105; the network 104 is also used to provide a medium for a communication link between the financial network server 105 and the third-party server 106; the network 104 is also used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the third-party server 106; the network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0049] The user can use the terminal devices 101, 102, 103 to interact with the financial network server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 can be installed with a financial service platform application.

[0050] Users can use terminal devices 101, 102, 103 to interact with third-party server 106 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be installed with various communication client applications, email applications, shopping website applications, instant messaging software, etc.

[0051] The financial network server 105 may be a server that provides various services, such as a background management server that provides support for the financial service platform browsed by the user using the terminal devices 101, 102, 103. The financial network server 105 may analyze the user information obtained by the terminal devices 101, 102, 103 and the user information obtained by the third-party server 106, and feed back the processing results (such as updated financial risk parameters) to the administrator of the financial network platform.

[0052] Server 105 may, for example, obtain at least one updated parameter of the credit user from a third-party database (third-party server 106); server 105 may, for example, obtain at least one characteristic parameter of the credit user; server 105 may, for example, arbitrarily combine the at least one updated parameter and the parameters in the at least one characteristic parameter to generate multiple combined parameter sets; server 105 may, for example, input each combined parameter set in the multiple combined parameter sets into a machine learning model to obtain a financial risk parameter value; server 105 may, for example, generate a financial risk strategy based on the combined parameter set corresponding to the risk parameter when the financial risk parameter value meets the threshold rule.

[0053] The server 105 may be a physical server, or may be composed of multiple servers. It should be noted that the financial risk strategy generation method provided in the embodiment of the present disclosure may be executed by the server 105 , and accordingly, the financial risk strategy generation device may be arranged in the server 105 .

[0054] When formulating financial strategies for users, since each customer has a large amount of input data (i.e. a large amount of data of different dimensions corresponding to the same customer) for strategy formulation and iteration, when a new credit party (third-party data) is newly connected, millions of new access data may be generated every day. The dimensions of user data provided by different third-party data are not consistent. Some dimensions have a few more items, while others lack certain dimensions. Therefore, when formulating new strategies, each piece of data needs to be manually analyzed, which is very inefficient.

[0055] In the financial risk strategy generation method disclosed in the present invention, an automated data analysis system is established to automatically match useful variables (X and Y variables) of the model. For example, the label of the Y variable can be manually defined according to different business needs. The label can be a bad customer / good customer. Then the X variable can be various dimensions (X1, X2, X3...Xn, corresponding to various existing and newly added dimensions) of the customer input data given by the newly connected credit party, and they are combined. Through automatic iteration of the model, variable combinations are automatically formulated according to thresholds that can be manually defined, which can effectively improve the efficiency of formulating strategies.

[0056] Figure 2 The flowchart of a method for generating a financial risk strategy according to an exemplary embodiment is shown. The method 20 for generating a financial risk strategy includes at least steps S202 to S210.

[0057] like Figure 2 As shown, in S202, obtaining at least one update parameter of the credit user from a third-party database may include: obtaining user data of the credit user from a third-party database; and performing data cleaning on the user data to obtain the at least one update parameter.

[0058] In one embodiment, performing data cleansing on the user data to obtain the at least one updated parameter includes: performing data cleansing on the user data to obtain multiple user parameters; and eliminating parameters that are not related to financial risks from the multiple user parameters to obtain the at least one updated parameter.

[0059] Among them, data cleaning is the process of re-examining and verifying data, with the aim of deleting duplicate information, correcting existing errors, and providing data consistency.

[0060] In the embodiments of the present disclosure, data cleaning may include: casewise deletion is used to remove user information with missing values ​​in the third-party database. Since many questionnaires may have missing values, this approach may result in a significant reduction in the effective sample size and inability to fully utilize the collected data. Therefore, it is only suitable for situations where key variables are missing or the proportion of samples containing invalid or missing values ​​is very small.

[0061] In the embodiments of the present disclosure, data cleaning may also include variable deletion. If a variable has many invalid values ​​and missing values, and the variable is not particularly important for the problem being studied, then the variable may be deleted. This approach reduces the number of variables available for analysis, but does not change the sample size.

[0062] After data cleaning, the correlation between user parameters from third parties and existing risk-related parameters can be calculated. For example, the correlation between dozens of columns of return values ​​and risks can be calculated, and user parameters with low risk relevance can be automatically eliminated.

[0063] In S204, at least one characteristic parameter of the credit user is obtained. The characteristic parameter may be a verified parameter capable of analyzing the financial risk of the user.

[0064] In S206, the at least one update parameter and the at least one characteristic parameter are arbitrarily combined to generate a plurality of combination parameter sets. For example, if the update parameters are A, B, C, and the characteristic parameters are D and E, the parameters can be arbitrarily combined to generate a combination parameter set. The combination parameter set can be in any form such as {A, B, D}; {A, C, E}; {A, C, D, E}, etc.

[0065] In S208, each of the multiple combined parameter sets is input into a machine learning model to obtain a financial risk parameter value.

[0066] In one embodiment, each of the multiple combined parameter sets is input into a machine learning model, and obtaining the financial risk parameter value also includes: generating the machine learning model through user data of historical credit users and the at least one characteristic parameter.

[0067] The machine learning models include: linear analysis method, association analysis method, logistic regression method, threshold judgment method, decision tree judgment method, factor analysis method, etc. By defining the Y threshold, effective analysis / modeling methods can be found, and key parameters that can generate user strategies can be automatically extracted.

[0068] In one embodiment, each of the plurality of combined parameter sets is input into the machine learning model, and obtaining the financial risk parameter value includes: inputting each of the plurality of combined parameter sets into the machine learning model; the machine learning model performs iterative calculation based on the plurality of parameters in the combined parameter set; and when the iterative calculation satisfies the preset conditions, generates the financial risk parameter value of the combined parameter set. That is, the newly identified update parameters and the old characteristic parameters in the third-party database are combined, and the suggestion of iterative update strategy of the user's financial risk is generated by using statistical analysis or modeling methods.

[0069] In S210, when the financial risk parameter value meets the threshold rule, a financial risk strategy is generated based on the combined parameter set corresponding to the risk parameter. This includes: when the financial risk parameter value meets the threshold rule, determining multiple financial risk sub-strategies corresponding to multiple parameters in the combined parameter set corresponding to the risk parameter; and generating the financial risk strategy through the intersection of the multiple financial risk sub-strategies.

[0070] When the expected model Y variable (i.e., what is a good user and what is a bad user) is known, the machine learning model outputs various combination strategies of new X variables and old X variables. Furthermore, for example, a new third party has access to 10 million new users. Based on business needs, we hope that the pass rate does not exceed 40%. In this way, we need to define 40% of the 10 million users as good users and 60% as bad users. In this way, the results of automatically combining X variables to fit the Y variables can be used to obtain new financial risk strategies.

[0071] According to the financial risk strategy generation method disclosed in the present invention, the updated parameters of the credit user obtained from the third-party database and the parameters in the characteristic parameters of the credit user are arbitrarily combined to generate multiple combination parameter sets; each combination parameter set in the multiple combination parameter sets is input into the machine learning model to obtain the financial risk parameter value; and when the financial risk parameter value meets the threshold rule, the financial risk strategy is generated based on the combination parameter set corresponding to the risk parameter. This method can automatically analyze the user data introduced by the third-party database, and combine it with the existing parameters to generate an updated financial risk strategy set.

[0072] It should be clearly understood that the present disclosure describes how to form and use specific examples, but the principles of the present disclosure are not limited to any details of these examples. On the contrary, based on the teachings of the contents disclosed in the present disclosure, these principles can be applied to many other embodiments.

[0073] Figure 3 The present invention is a flowchart of a method for generating a financial risk strategy according to another exemplary embodiment. Figure 3 The process shown is Figure 2 The process shown is a detailed description of S208 "generating a financial risk strategy based on a combination parameter set corresponding to the risk parameter when the financial risk parameter value meets the threshold rule."

[0074] like Figure 3 As shown, in S302, multiple combination parameter sets are generated.

[0075] In S304, multiple combination parameter sets are input into the machine learning model to obtain financial risk parameter values.

[0076] In S306, it is determined whether each parameter in the combined parameter set meets the threshold rule.

[0077] In S308, when all parameters in the combination satisfy the threshold rule, multiple financial risk sub-strategies corresponding to multiple parameters in the combination parameter set corresponding to the risk parameter are determined.

[0078] In S310, the financial risk strategy is generated through the intersection of the multiple financial risk sub-strategies.

[0079] Figure 4 is a schematic diagram of a method for generating a financial risk strategy according to another exemplary embodiment. Figure 4 , filter the user data obtained through third-party data, remove risk-irrelevant data, and obtain update parameters (the update parameters can be multiple parameters, AA, BB, CC);

[0080] The updated parameters are combined with the existing user parameters (EE, FF) arbitrarily to generate different combination parameter sets, such as (AA, EE), (AA, BB, FF), (CC, EE, FF), etc. Each set in the above combination parameter sets is input into the machine learning model to generate risk parameter values;

[0081] When the risk parameters meet the threshold rules, for example, when the calculation results of each parameter in the combined risk parameters (AA, BB, FF) meet the threshold rules, the risk strategy is generated by the three parameters (AA, BB, FF).

[0082] More specifically: For example, the original risk strategy is FF: number of arrears;

[0083] After the update, AA stands for: sensitive area; BB stands for: sensitive age;

[0084] The updated financial risk strategy may be: user risk assessment based on sensitive areas + sensitive years + number of arrears.

[0085] Figure 5The present invention is a flowchart of a method for generating a financial risk strategy according to another exemplary embodiment. Figure 5 The process shown is a detailed description of "updating impact analysis based on the financial risk strategy and the user data of the credit user".

[0086] like Figure 5 As shown, in S502, a financial risk value is generated through the user data of the credit user and a financial risk model, wherein the financial risk model includes at least one of the following: a user pass rate model, a risk prediction model, and a credit limit model.

[0087] In S504, a verification risk value is generated by using the user data of the credit user and the verification risk model. The method further includes: updating the financial risk model based on the parameters in the financial risk strategy to generate the verification model. The verification model is generated by using the updated parameters.

[0088] In S506, the update impact analysis is performed using the verification risk value and the financial risk value. The verification risk value calculated after the updated parameters is compared with the financial risk value calculated using the original parameters to obtain the update impact analysis.

[0089] By comparison, the subsequent impact of the updated parameters (including pass rate, risk situation, and credit limit) is predicted. A strategy iteration recommendation report is generated, and business analysts determine whether it is necessary to iterate the strategy based on the report. The system supports multiple calculation methods for return value and risk correlation.

[0090] In the financial risk strategy generation method disclosed in the present invention, a large number of newly introduced variables can be processed. By setting the acceptable risk parameter threshold at the time of model output, the variables can be automatically arranged and combined to generate a financial risk model, and then a recommendation on whether to update the user strategy can be given. In this way, a strategy set of variable combinations is automatically generated through a machine learning model and output to business analysts.

[0091] Those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present disclosure are performed. The program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0092] In addition, it should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0093] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0094] Figure 6 The block diagram of a financial risk strategy generating device according to an exemplary embodiment is shown in FIG. The financial risk strategy generating device 60 comprises: an updating data module 602 , a characteristic parameter module 604 , a combination parameter module 606 , a model calculation module 608 , and a risk strategy module 610 .

[0095] The update data module 602 is used to obtain at least one update parameter of the credit user from a third-party database; specifically, it may include: a data acquisition unit, used to obtain user data of the credit user from a third-party database; and a data cleaning unit, used to perform data cleaning on the user data to obtain the at least one update parameter.

[0096] The data cleaning unit includes: a cleaning subunit, used to perform data cleaning processing on the user data to obtain multiple user parameters; and a elimination subunit, used to eliminate parameters unrelated to financial risks from the multiple user parameters to obtain the at least one updated parameter.

[0097] The characteristic parameter module 604 is used to obtain at least one characteristic parameter of the credit user;

[0098] The combined parameter module 606 is used to arbitrarily combine the at least one update parameter and the parameters in the at least one feature parameter to generate multiple combined parameter sets;

[0099] The model calculation module 608 is used to input each of the multiple combination parameter sets into the machine learning model to obtain the financial risk parameter value; the model calculation module 608 also includes: a model generation unit, used to generate the machine learning model through the user data of historical credit users and the at least one characteristic parameter.

[0100] The model calculation module 608 includes: an input unit, used to input each of the multiple combination parameter sets into the machine learning model; an iteration unit, used for the machine learning model to perform iterative calculation based on multiple parameters in the combination parameter set; and a model unit, used to generate a financial risk parameter value of the combination parameter set when the iterative calculation meets preset conditions.

[0101] The risk strategy module 610 is used to generate a financial risk strategy based on the combination parameter set corresponding to the risk parameter when the financial risk parameter value meets the threshold rule. The risk strategy module 610 includes: a sub-strategy unit, which is used to determine multiple financial risk sub-strategies corresponding to multiple parameters in the combination parameter set corresponding to the risk parameter when the financial risk parameter value meets the threshold rule; and a collection unit, which is used to generate the financial risk strategy through the intersection of the multiple financial risk sub-strategies.

[0102] The financial risk strategy generation device may further include: an update analysis module, which is used to perform update impact analysis based on the financial risk strategy and the user data of the credit user. The update analysis module includes: a financial risk unit, which is used to generate a financial risk value through the user data of the credit user and the financial risk model; a verification risk unit, which is used to generate a verification risk value through the user data of the credit user and the verification risk model; and an update analysis unit, which is used to perform the update impact analysis through the verification risk value and the financial risk value.

[0103] The update analysis module also includes: a verification model unit, which is used to update the financial risk model based on the parameters in the financial risk strategy and generate the verification model.

[0104] According to the financial risk strategy generation device disclosed in the present invention, the updated parameters of the credit user obtained from the third-party database and the parameters in the characteristic parameters of the credit user are arbitrarily combined to generate multiple combination parameter sets; each combination parameter set in the multiple combination parameter sets is input into the machine learning model to obtain the financial risk parameter value; and when the financial risk parameter value meets the threshold rule, the financial risk strategy is generated based on the combination parameter set corresponding to the risk parameter. This method can automatically analyze the user data introduced by the third-party database, and combine it with the existing parameters to generate an updated financial risk strategy set.

[0105] Figure 7 It is a block diagram of an electronic device according to an exemplary embodiment.

[0106] Refer to the following Figure 7 An electronic device 700 according to this embodiment of the present disclosure is described. Figure 7 The electronic device 700 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0107] like Figure 7As shown, the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 may include, but are not limited to: at least one processing unit 710, at least one storage unit 720, a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710), a display unit 740, etc.

[0108] The storage unit stores program codes, which can be executed by the processing unit 710, so that the processing unit 710 executes the steps according to various exemplary embodiments of the present disclosure described in the electronic prescription circulation processing method section of this specification. For example, the processing unit 210 can execute the following steps: Figure 2 , Figure 3 , Figure 5 Follow the steps shown in .

[0109] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 7201 and / or a cache memory unit 7202 , and may further include a read-only memory unit (ROM) 7203 .

[0110] The storage unit 720 may also include a program / utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0111] Bus 730 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0112] The electronic device 700 may also communicate with one or more external devices 700' (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 700, and / or communicate with any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 750. Furthermore, the electronic device 700 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 760. The network adapter 760 may communicate with other modules of the electronic device 700 via a bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0113] Through the above description of the implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by combining software with necessary hardware. Figure 8 As shown, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiment of the present disclosure.

[0114] The software product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0115] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0116] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0117] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by a device, the computer-readable medium realizes the following functions: obtaining at least one updated parameter of the credit user from a third-party database; obtaining at least one characteristic parameter of the credit user; arbitrarily combining the at least one updated parameter and the parameters in the at least one characteristic parameter to generate multiple combined parameter sets; inputting each combined parameter set in the multiple combined parameter sets into the machine learning model to obtain a financial risk parameter value; and when the financial risk parameter value meets the threshold rule, generating a financial risk strategy based on the combined parameter set corresponding to the risk parameter.

[0118] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0119] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0120] The exemplary embodiments of the present disclosure are specifically shown and described above. It should be understood that the present disclosure is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A method for generating a financial risk strategy based on a combination parameter, characterized in that: include: Acquiring at least one updated parameter of the credit user from a third-party database, wherein the updated parameter is a characteristic parameter to be added to the financial risk strategy; Acquire at least one characteristic parameter of the credit user, where the characteristic parameter is an original characteristic parameter; Combining the at least one update parameter and the at least one characteristic parameter arbitrarily to generate a plurality of combination parameter sets; inputting each of the plurality of combined parameter sets into a machine learning model; The machine learning model performs iterative calculation based on multiple parameters in the combined parameter set; When the iterative calculation meets the preset conditions, generating the financial risk parameter value of the combined parameter set; Based on the financial risk parameter value, determine whether each parameter in the combined parameter set meets the threshold rule; When each parameter value in the combined parameter set satisfies the threshold rule, obtaining multiple financial risk sub-strategies corresponding to multiple parameters in the combined parameter set; determining an intersection of the plurality of financial risk sub-strategies; Generating the financial risk strategy through the financial risk sub-strategies in the intersection; Generate a financial risk value through the user data of the credit user and the financial risk model; Generate a verification risk value through the user data of the credit user and the verification risk model; Performing update impact analysis by using the verification risk value and the financial risk value; Determine whether to update the financial risk strategy based on the update impact analysis.

2. The method according to claim 1, characterized in that Acquiring at least one updated parameter of the credit user from the third-party database includes: Obtaining user data of credit users from third-party databases; and The user data is cleansed to obtain the at least one update parameter.

3. The method according to claim 2, characterized in that Performing data cleaning on the user data to obtain the at least one update parameter includes: Performing data cleaning on the user data to obtain multiple user parameters; and Parameters irrelevant to financial risk are eliminated from the plurality of user parameters to obtain the at least one updated parameter.

4. The method according to claim 1, characterized in that Inputting each of the plurality of combined parameter sets into the machine learning model to obtain the financial risk parameter value further comprises: The machine learning model is generated by using user data of historical credit users and the at least one characteristic parameter.

5. A financial risk strategy generation device based on combined parameters, characterized in that: include: An update data module, used to obtain at least one update parameter of a credit user from a third-party database, wherein the update parameter is a characteristic parameter to be added to the financial risk strategy; A characteristic parameter module, used to obtain at least one characteristic parameter of a credit user, wherein the characteristic parameter is an original characteristic parameter; A combination parameter module, used for arbitrarily combining the at least one update parameter and the parameters in the at least one feature parameter to generate a plurality of combination parameter sets; A model calculation module, used for inputting each of the plurality of combined parameter sets into a machine learning model; The machine learning model performs iterative calculation based on multiple parameters in the combined parameter set; When the iterative calculation meets the preset conditions, generating the financial risk parameter value of the combined parameter set; A risk strategy module, used to determine whether each parameter in the combined parameter set meets the threshold rule based on the financial risk parameter value; when each parameter value in the combined parameter set meets the threshold rule, obtain multiple financial risk sub-strategies corresponding to multiple parameters in the combined parameter set; and determine the intersection of the multiple financial risk sub-strategies; Generating the financial risk strategy through the financial risk sub-strategies in the intersection; Generate a financial risk value through the user data of the credit user and the financial risk model; Generate a verification risk value through the user data of the credit user and the verification risk model; Performing update impact analysis by using the verification risk value and the financial risk value; Determine whether to update the financial risk strategy based on the update impact analysis.

6. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.

7. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images