Data processing method and device, equipment and medium

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a data processing method and device, equipment and a medium. According to the method and the device, the user portrait data and the external data are processed based on the preset neural network model, the initial loan scheme of the user is determined, and the accuracy of the initial loan scheme is improved by integrating multi-dimensional data and a large model technology; the initial loan scheme is adjusted according to the feedback information of the user for the initial loan scheme and the risk information of the user, the adjusted loan scheme is obtained, the initial loan scheme is adjusted within the risk range, the individual requirements of the user are met, the corresponding loan risk is reduced, and therefore the user satisfaction degree is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a data processing method and device, equipment and a medium. BACKGROUND

[0002] With the rapid development of financial technology, loan business gradually develops in the direction of intelligence and individualization. The traditional loan scheme design mainly relies on artificial experience, and has problems such as information dispersion, low efficiency, and inaccurate scheme. Especially when facing massive user data, the traditional loan scheme design cannot take into account all the data, so that the user satisfaction of the designed loan scheme is low. Therefore, how to process massive user data to design a loan scheme with high user satisfaction has become a problem to be solved in the loan scheme design process. SUMMARY

[0003] In view of this, the embodiments of the present application provide a data processing method, device, equipment and medium to solve the problem of low user satisfaction in the loan scheme design process.

[0004] In a first aspect, the embodiments of the present application provide a data processing method, which comprises: obtaining user portrait data of a user and external data, the external data at least including market interest rate data and market economic policy data; processing the user portrait data and the external data based on a preset neural network model to determine an initial loan scheme of the user, the initial loan scheme at least including an initial loan amount, an initial loan interest rate, and an initial repayment period; determining risk information of the user, and determining a loan condition matched with the user according to the risk information; determining feedback information of the user on the initial loan scheme, determining a target condition according to the intersection between the feedback information and the loan condition, and adjusting the initial loan amount, the initial loan interest rate, and the initial repayment period in the initial loan scheme according to the target condition to obtain an adjusted loan scheme.

[0005] In a second aspect, the embodiments of the present application provide a data processing device, which comprises: an obtaining module configured to obtain user portrait data of a user and external data, the external data at least including market interest rate data and market economic policy data; a first determining module configured to process the user portrait data and the external data based on a preset neural network model to determine an initial loan scheme of the user, the initial loan scheme at least including an initial loan amount, an initial loan interest rate, and an initial repayment period; A second determining module is configured to determine risk information of the user, and determine a loan condition matched with the user according to the risk information. An adjusting module is configured to determine feedback information of the user on the initial loan scheme, determine a target condition according to an intersection between the feedback information and the loan condition, and adjust an initial loan amount, an initial loan interest rate and an initial repayment period in the initial loan scheme according to the target condition to obtain an adjusted loan scheme.

[0006] In a third aspect, an embodiment of the present application provides a computer device, which comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the data processing method when executing the computer program.

[0007] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the data processing method.

[0008] Compared with the prior art, the present application has the following beneficial effects: In the present application, the user portrait data and external data are processed based on a preset neural network model to determine an initial loan scheme of the user, the accuracy of the initial loan scheme is improved by integrating multi-dimensional data and large model technology, the initial loan scheme is adjusted according to feedback information of the user on the initial loan scheme and risk information of the user to obtain an adjusted loan scheme, the initial loan scheme is adjusted within a risk range, the individualized needs of the user are met, the corresponding loan risk is reduced, and thus the user satisfaction is improved. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0010] Figure 1 is an application environment schematic diagram of a data processing method provided by an embodiment of the present application; Figure 2 is a flow schematic diagram of a data processing method provided by an embodiment of the present application; Figure 3 is a structure schematic diagram of a data processing device provided by an embodiment of the present application; Figure 4is a structural schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0011] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of the present application.

[0012] In the following description, specific details are set forth in connection with the particular systems, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, persons skilled in the art will appreciate that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0013] It should be understood that the term "comprises" as used in the specification and the appended claims indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0014] It should also be understood that the term "and / or" as used in the specification and the appended claims indicates any combination of the associated listed items, as well as all possible combinations of the items.

[0015] As used in the specification and the appended claims, the term "if" can be interpreted as meaning "when" or "once" or "in response to a determination" or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if detected [the described condition or event]" can be interpreted as meaning "once determined" or "in response to a determination" or "once detected [the described condition or event]" or "in response to detecting [the described condition or event]" depending on the context.

[0016] In addition, in the description of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for differentiation in description, and cannot be understood as indicating or implying relative importance.

[0017] Reference within the specification of this application to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places within specified descriptions are not necessarily all referring to the same embodiment, however, but can refer to one or more but not all embodiments. The terms "including," "comprising," "having" and variations thereof as used herein are meant to be equivalent to the term "consisting of."

[0018] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Wherein, artificial intelligence (AI) is to use digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results.

[0019] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The software technology of artificial intelligence mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0020] It should be understood that the size of the serial number of each step in the following embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0021] In order to illustrate the technical solutions of the present application, the following will be described through specific embodiments.

[0022] The data processing method provided by an embodiment of the present application can be applied to, for example, Figure 1The application environment is a client-server application environment, wherein the client communicates with the server. The client includes, but is not limited to, a palmtop computer, a desktop computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud computer device, a personal digital assistant (PDA), and the like. The server can be a standalone server or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, and the like.

[0023] In order to illustrate the technical solutions of the present application, specific examples are used for illustration.

[0024] Referring to Figure 2 is a flowchart of a data processing method provided by an embodiment of the present application, as Figure 2 shown, the data processing method can include the following steps.

[0025] S201: Obtain user portrait data of a user and external data, wherein the external data at least includes market interest rate data and market economic policy data.

[0026] In step S201, the user portrait data of the user and the external data are obtained, wherein the user portrait data includes the financial data, credit records, behavior data, and the like of the user, and the external data includes market interest rates, market economic policy data, and the like.

[0027] In this embodiment, the user portrait data of the user is obtained, wherein the user can be any person such as a male, married, enterprise manager, undergraduate, and resident of a first-tier city, and the user portrait data includes the financial data, credit records, behavior data, and the like of the user. When the financial data, credit records, and behavior data of the user are obtained, the bank account of the user can be connected through an API interface to collect the financial data, credit records, behavior data, and the like of the user. The financial data can include income, expenditure, assets, liabilities, and the like. The credit records can include credit scores, loan history, repayment records, and the like. The behavior data can include the consumption behavior and investment behavior of the corresponding user. When the external data is obtained, the current market interest rate, economic policy, and the like can be collected through a market data interface.

[0028] In this embodiment, the user portrait data of the user and the external data are obtained, so that the initial loan scheme is predicted based on multi-source data, thereby outputting a more comprehensive initial loan scheme.

[0029] S202: processing the user portrait data and the external data based on a preset neural network model to determine an initial loan scheme of the user.

[0030] In step S202, the neural network model is a large language model. The user portrait data and the external data are processed using the preset neural network model to determine an initial loan scheme of the user. The initial loan scheme at least includes an initial loan amount, an initial loan interest rate, and an initial repayment period.

[0031] In this embodiment, a corresponding large language model is obtained to facilitate analysis and prediction of the user portrait data and the external data using the corresponding large language model to determine an initial loan scheme of the user. The initial loan scheme at least includes an initial loan amount, an initial loan interest rate, and an initial repayment period.

[0032] In this embodiment, the user portrait data and the external data are preprocessed before being processed based on the preset neural network model to obtain preprocessed user portrait data and preprocessed external data. The preprocessed user portrait data and the preprocessed external data are input into the preset neural network model to output a corresponding initial loan scheme. The preset neural network model is a trained neural network model, which can include an input layer, a hidden layer, and an output layer. The input layer is used to receive the preprocessed user portrait data and the preprocessed external data, and the number of neurons is consistent with the feature dimension of the preprocessed user portrait data and the preprocessed external data. The hidden layer is used to set 3-5 layers, and the number of neurons in each layer is 64-128. The ReLU activation function is used for feature extraction and nonlinear mapping. The output layer is used to output the initial loan scheme of the user, such as the loan amount, the loan interest rate, the repayment period, and the repayment method. It should be noted that the training process of the preset neural network model includes: A plurality of sets of training samples are obtained, each set of training samples including sample user portrait data and sample external data, and a loan scheme label corresponding to each set of training samples, wherein the loan scheme label includes a loan amount label, a loan interest rate label, a repayment period label, and a repayment method label, etc. The loan amount in the loan amount label is mapped to the [0, 1] interval by Min-Max standardization, facilitating gradient descent optimization during model training. The loan interest rate label is mapped to the [0, 1] interval by Min-Max standardization to avoid model training bias towards high interest rate samples due to absolute value differences in interest rates (such as 3.85% and 8%). The repayment period label is integer encoded (such as 6 months encoded as 1, 12 months encoded as 2, and so on), ensuring that the label matches the model output dimension. The repayment method label is encoded, such as equal repayment and interest repayment. The initial neural network model is supervised trained according to each set of training samples and the loan scheme label corresponding to each set of training samples, obtaining a trained neural network model, i.e., a preset neural network model. The initial neural network model can be an MLP model, and the output layer includes 4 branches, respectively outputting the loan amount, the loan interest rate, the repayment period, and the repayment method.

[0033] It should be noted that when training the initial neural network model, the loss functions corresponding to different branches can be different, such as the loss function of the output layer outputting the loan amount and the loan interest rate can be a mean square error loss function, and the loss function corresponding to the output layer outputting the repayment period and the repayment method can be a cross-entropy loss function. It can also be other loss functions, which are not limited in the present embodiment.

[0034] In the present embodiment, the user portrait data and the external data are processed based on the preset neural network model to determine the initial loan scheme of the user. The neural network model can mine the user portrait data and the external data, comprehensively analyze the user's repayment ability, and output personalized repayment methods for the user.

[0035] Optionally, the user portrait data and the external data are processed based on the preset neural network model to determine the initial loan scheme of the user, including: The user portrait data and the external data are preprocessed to obtain preprocessed user portrait data and preprocessed external data; The preprocessed user portrait data and the preprocessed external data are data fused based on a multi-source data fusion technology to obtain fused data; The fused data is processed based on the preset neural network model to determine the initial loan scheme of the user.

[0036] In this embodiment, before the user portrait data and the external data are processed based on the preset neural network model, the user portrait data and the external data are preprocessed. The preprocessing can include data cleaning and data standardization processing. The data cleaning can eliminate invalid data with missing key fields or logical contradictions. The data standardization processing can use a Min-Max normalization algorithm to map user portrait data and external data of different magnitudes to the interval [0, 1], eliminate the influence of the dimension on the model operation, and form a unified data format and structure.

[0037] Based on the multi-source data fusion technology, the preprocessed user portrait data and the preprocessed external data are fused to obtain fused data. When the preprocessed user portrait data and the preprocessed external data are fused, data layer fusion can be performed, that is, the preprocessed user portrait data and the preprocessed external data are integrated to obtain the fused data. The preprocessed user portrait data and the preprocessed external data can also be fused at the feature layer, that is, the features of the preprocessed user portrait data and the preprocessed external data are extracted to obtain user portrait data features and external data features, and the user portrait data features and the external data features are fused. Other methods can also be used, and the present embodiment is not limited in this regard.

[0038] Based on the preset neural network model, the fused data are processed to determine an initial loan scheme for the user. That is, the fused data are input into the preset neural network model, and an initial loan scheme for the user is output.

[0039] In this embodiment, preprocessing can effectively eliminate noise and avoid misleading the model. By filling or deleting missing samples, data integrity is ensured. Based on the multi-source data fusion technology, the preprocessed user portrait data and the preprocessed external data are fused. Data from different sources, different formats, and different accuracies are integrated to obtain more accurate, more comprehensive, and more reliable data, reduce the error and uncertainty of single data, and provide more comprehensive support for the output of the initial loan scheme.

[0040] S203: Determine the risk information of the user, and determine the loan condition matched with the user according to the risk information.

[0041] In step S203, the risk information represents the size of the user's loan risk, and the loan condition is a constraint condition for the user.

[0042] In this embodiment, the risk information of the user is determined, and the loan condition matched with the user is determined according to the risk information. According to the risk information, a corresponding risk level is determined. The higher the risk level, the greater the loan risk is considered. The lower the risk level, the smaller the loan risk is considered. For example, the smaller the risk probability value, the lower the risk level, and the greater the risk probability value, the higher the risk level. According to the risk level, the loan condition is determined. For example, the loan condition corresponding to the low risk level can include high loan amount, low loan interest rate, long repayment period, flexible repayment method, etc. The loan condition corresponding to the high risk level can include high loan amount, high loan interest rate, short repayment period, fixed repayment method, etc.

[0043] Optionally, the determination process of the risk information includes: According to the user portrait data, the risk of the user is evaluated, and the risk information of the user is determined.

[0044] In this embodiment, a preset risk assessment model is obtained, and the user portrait data is risk assessed using the corresponding risk assessment model to determine the risk information of the user. The risk assessment model is a Transformer model, which extracts complex feature relationships of the user portrait data based on the Transformer model, determines a weight value corresponding to each feature, and determines the risk information of the user according to the weight value corresponding to each feature. The user portrait data is converted into serialized data and input into the Transformer model to output the risk information. After the serialized data is input into the Transformer model, the attention weight value of the user portrait data is extracted based on the attention mechanism, and the corresponding risk information is determined according to the attention weight value.

[0045] In this embodiment, the user portrait data is mapped to three subspaces through linear transformation: wherein, is the user portrait data, , , is a learnable parameter matrix.

[0046] According to the attention weight matrix generated, , , the formula is as follows: wherein, is the attention weight matrix, is the dimension of X.

[0047] The calculation formula of the risk information is as follows: wherein, is a risk probability, that is, the risk information, and b are model parameters of the model Transformer, is an attention weight matrix. The greater the risk probability is, the higher the corresponding risk is, that is, the greater the loan risk is.

[0048] In this embodiment, the corresponding risk probability value is calculated based on the attention mechanism. The corresponding weight value can be dynamically allocated according to the input user portrait data, and the high-risk features can be automatically identified, so as to improve the accuracy of the risk information.

[0049] S204: determining the feedback information of the user on the initial loan scheme, determining the target condition according to the intersection between the feedback information and the loan condition, and adjusting the initial loan amount, the initial loan interest rate and the initial repayment period in the initial loan scheme according to the target condition to obtain an adjusted loan scheme.

[0050] In step S204, the feedback information represents the adjustment information of the user on the loan amount, the loan interest rate, the repayment period and the repayment method of the initial loan scheme. The target condition is determined according to the intersection between the feedback information and the loan condition, wherein the intersection between the feedback information and the loan condition is the same data contained in the feedback information and the loan condition, and the target condition is the condition for adjusting the initial loan scheme. The initial loan amount, the initial loan interest rate and the initial repayment period in the initial loan scheme are adjusted according to the target condition to obtain an adjusted loan scheme.

[0051] In this embodiment, the feedback information of the user on the initial loan scheme is determined, wherein the feedback information represents the adjustment information of the user on the loan amount, the loan interest rate, the repayment period and the repayment method of the initial loan scheme, for example, when the loan amount of the initial loan scheme is large, the feedback information can be to reduce the loan amount, when the repayment method of the initial loan scheme is equal repayment, the expected repayment method of the user is principal and interest repayment, and the corresponding feedback information can be to change the loan method, and adjust the equal repayment to the principal and interest repayment.

[0052] According to the intersection between the feedback information and the loan condition, the target condition is determined, for example, if there is an intersection between the feedback information and the loan condition, the target condition is the condition contained in the corresponding intersection, such as the loan amount feedback information in the feedback information is 70-100, the loan amount constraint condition of the loan condition is 50-80, and the corresponding intersection is 70-80. According to the corresponding intersection, the loan amount in the initial loan scheme is adjusted so that the adjusted loan amount is between 70-80. If there is no intersection between the feedback information and the loan condition, the target condition is determined between the feedback information and the loan condition, such as if the feedback information is the target condition, the initial loan amount, the initial loan interest rate, and the initial repayment period in the initial loan scheme are adjusted according to the feedback information to obtain the adjusted loan scheme.

[0053] It should be noted that when the target condition is determined between the feedback information and the loan condition, the target condition can be determined according to the difference between the feedback information and the loan condition. When the difference is greater than a preset threshold, the loan condition is determined as the target condition. When the difference is not greater than the preset threshold, the feedback information is determined as the target condition. The target condition can also be determined by other methods, which are not limited in the embodiment. For example, the loan amount feedback information in the feedback information is less than 100,000, and the loan amount constraint condition of the loan condition is less than 80,000. The difference between the feedback information and the loan condition is small, and the feedback information is determined as the target condition. For example, the loan amount feedback information in the feedback information is greater than 200,000, and the loan amount constraint condition of the loan condition is less than 100,000. The difference between the feedback information and the loan condition is large, and the loan condition is determined as the target condition.

[0054] In the embodiment, according to the determination of the target condition, the initial loan amount, the initial loan interest rate, and the initial repayment period in the initial loan scheme are adjusted according to the target condition, so that the adjusted loan scheme meets the corresponding target condition.

[0055] In the embodiment, the initial loan scheme is adjusted according to the feedback information and the risk information, which can reduce the corresponding loan risk while meeting the personalized needs of the user, thereby improving the reliability of the adjusted loan scheme.

[0056] Optionally, the initial loan scheme includes at least an initial loan amount, an initial loan interest rate, and an initial repayment period. The feedback information includes at least loan amount feedback information, loan interest rate feedback information, and repayment period feedback information. The loan condition includes at least a loan amount constraint condition, a loan interest rate constraint condition, and a repayment period constraint condition. According to the intersection between the feedback information and the loan condition, the target condition is determined, including: determining the amount intersection of the loan amount feedback information and the loan amount constraint condition, the interest rate intersection of the loan interest rate feedback information and the loan interest rate constraint condition, and the term intersection of the repayment term feedback information and the repayment term constraint condition; If the amount intersection, the interest rate intersection, and the term intersection are not empty sets, the amount intersection, the interest rate intersection, and the term intersection are determined as the target condition.

[0057] In this embodiment, the initial loan scheme includes at least an initial loan amount, an initial loan interest rate, and an initial repayment term. The corresponding feedback information includes at least loan amount feedback information, loan interest rate feedback information, and repayment term feedback information, and the loan condition includes at least a loan amount constraint condition, a loan interest rate constraint condition, and a repayment term constraint condition. The loan amount feedback information is the demand information of the user for the loan amount, the loan interest rate feedback information is the demand information of the user for the loan interest rate, and the repayment term feedback information is the demand information of the user for the repayment term. The loan amount constraint condition is the condition for constraining the loan amount, the loan interest rate constraint condition is the condition for constraining the loan interest rate, and the repayment term constraint condition is the condition for constraining the repayment term, so as to avoid increasing the loan risk.

[0058] determining the amount intersection of the loan amount feedback information and the loan amount constraint condition, the interest rate intersection of the loan interest rate feedback information and the loan interest rate constraint condition, and the term intersection of the repayment term feedback information and the repayment term constraint condition. The amount intersection is the intersection of the loan amount feedback information and the loan amount constraint condition, for example, the loan amount feedback information is 80-12, and the loan amount constraint condition is 50-100, and the amount intersection is 80-100. The interest rate intersection is the intersection of the loan interest rate feedback information and the loan interest rate constraint condition, and the term intersection is the intersection of the repayment term feedback information and the repayment term constraint condition.

[0059] If the amount intersection, the interest rate intersection, and the term intersection are not empty sets, the amount intersection, the interest rate intersection, and the term intersection are determined as the target condition. That is, a certain loan amount in the amount intersection is used to adjust the initial loan amount, a certain loan interest rate in the interest rate intersection is used to adjust the initial loan interest rate, and a certain repayment term in the term intersection is used to adjust the initial repayment term.

[0060] It should be noted that if the initial loan amount, the initial loan interest rate, and the initial repayment term are in the corresponding amount intersection, the interest rate intersection, and the term intersection, no adjustment is performed.

[0061] In this embodiment, the feedback information and the loan condition are adjusted based on the feedback information and the loan condition, so that the adjusted loan scheme can meet the feedback information and the loan condition at the same time, thereby improving the personalization of the loan scheme while avoiding increasing the corresponding loan risk.

[0062] Optionally, after determining the amount intersection of the loan amount feedback information and the loan amount constraint condition, the interest rate intersection of the loan interest rate feedback information and the loan interest rate constraint condition, and the term intersection of the repayment term feedback information and the repayment term constraint condition, the method further comprises: If there is an empty set in the amount intersection, the interest rate intersection, and the term intersection, determining the number of empty sets; If the number of empty sets is greater than a preset threshold, determining the loan condition as the target condition; If the number of empty sets is not greater than the preset threshold, determining the feedback information as the target condition.

[0063] In this embodiment, if there is an empty set in the amount intersection, the interest rate intersection, and the term intersection, that is, there is feedback information that does not belong to the corresponding loan condition under the corresponding risk level, there may be a corresponding risk. For example, if the loan amount feedback information is greater than the corresponding loan amount of the loan amount constraint condition, there may be a risk that the user cannot repay on time. Therefore, if there is an empty set in the amount intersection, the interest rate intersection, and the term intersection, the number of empty sets is determined. If the number of empty sets is greater than a preset threshold, the loan condition is determined as the target condition, and if the number of empty sets is not greater than the preset threshold, the feedback information is determined as the target condition. That is, when multiple parameters in the feedback information do not meet the loan condition, the loan risk is reduced, the initial loan scheme is adjusted according to the loan condition, and the adjusted loan scheme is obtained. That is, the initial loan amount, the initial loan interest rate, and the initial repayment term are adjusted using the loan amount constraint condition, the loan interest rate constraint condition, and the repayment term constraint condition to obtain the adjusted loan scheme. When a small part of the parameters in the feedback information do not meet the loan condition, the personalized loan scheme of the user is given priority, the initial loan scheme is adjusted according to the feedback information, and the adjusted loan scheme is obtained. That is, the initial loan amount, the initial loan interest rate, and the initial repayment term are adjusted according to the loan amount feedback information, the loan interest rate feedback information, and the repayment term feedback information to obtain the adjusted loan scheme.

[0064] In this embodiment, according to the number of empty sets, that is, according to the difference between the feedback information and the loan condition, it is determined whether to adjust the initial loan scheme according to the feedback information or the loan condition. When the number of empty sets is small, that is, the difference between the feedback information and the loan condition is small, the feedback information is determined as the target condition, and the initial loan scheme is adjusted according to the feedback information. This not only ensures the generation of the personalized loan scheme of the user, but also does not increase the corresponding loan risk. When the number of empty sets is large, the loan condition is determined as the target condition, that is, when the difference between the feedback information and the loan condition is large, the initial loan scheme is adjusted according to the loan condition to ensure that the corresponding loan risk is not increased.

[0065] Optionally, the data processing method further comprises: According to the adjusted loan scheme, the parameters of the neural network model are adjusted to obtain an adjusted neural network model.

[0066] In this embodiment, the adjusted data is processed as the final loan scheme of the user, and the parameters of the neural network are adjusted according to the adjusted loan scheme to obtain an adjusted neural network model. The loan scheme output by the adjusted neural network model based on the user portrait data and external data is similar to the adjusted loan scheme. When adjusting the parameters of the neural network model, the parameters are adjusted in the opposite direction of the gradient based on the gradient descent principle to reduce the loss function. Other methods can also be used for parameter adjustment, which is not limited in this embodiment.

[0067] In this embodiment, the parameters of the neural network model are adjusted according to the adjusted loan scheme to obtain an adjusted neural network model, so that the adjusted neural network model can output the corresponding loan scheme according to the user demand and the corresponding loan risk, and improve the stability of the loan scheme output by the adjusted neural network model.

[0068] In this application, the user portrait data and external data are processed based on the preset neural network model to determine the initial loan scheme of the user. By integrating multi-dimensional data and large model technology, the accuracy of the initial loan scheme is improved. The initial loan scheme is adjusted according to the feedback information of the user and the risk information of the user to obtain an adjusted loan scheme. The initial loan scheme is adjusted within the risk range, which not only meets the individual needs of the user, but also reduces the corresponding loan risk, thereby improving the user satisfaction.

[0069] Please refer to Figure 3 , Figure 3 is a structural schematic diagram of a data processing device provided by an embodiment of the present application. The data processing device corresponds to the data processing method in the above embodiments one by one. For details, please refer to the related description in the embodiments corresponding to Figure 2 and Figure 2 . For the sake of convenience, only the parts related to this embodiment are shown. Please refer to Figure 3 , the data processing device 30 comprises an acquisition module 31, a first determination module 32, a second determination module 33, and an adjustment module 34.

[0070] The acquisition module 31 is configured to acquire user portrait data and external data of a user, wherein the external data at least comprises market interest rate data and market economic policy data.

[0071] The first determination module 32 is configured to process the user portrait data and the external data based on a preset neural network model to determine an initial loan scheme of the user, wherein the initial loan scheme at least comprises an initial loan amount, an initial loan interest rate, and an initial repayment period.

[0072] The second determining module 33 is configured to determine risk information of the user, and determine the loan condition matched with the user according to the risk information.

[0073] The adjusting module 34 is configured to determine feedback information of the user on the initial loan scheme, determine the target condition according to the intersection between the feedback information and the loan condition, and adjust the initial loan amount, the initial loan interest rate and the initial repayment period in the initial loan scheme according to the target condition to obtain the adjusted loan scheme.

[0074] Optionally, the first determining module 32 comprises: The preprocessing unit is configured to preprocess the user portrait data and the external data to obtain preprocessed user portrait data and preprocessed external data.

[0075] The fusion unit is configured to perform data fusion on the preprocessed user portrait data and the preprocessed external data based on a multi-source data fusion technology to obtain fused data.

[0076] The first determining unit is configured to process the fused data based on a preset neural network model to determine the initial loan scheme of the user.

[0077] Optionally, the adjusting module 34 comprises: The second determining unit is configured to determine an amount intersection of the loan amount feedback information and the loan amount constraint condition, an interest rate intersection of the loan interest rate feedback information and the loan interest rate constraint condition, and a period intersection of the repayment period feedback information and the repayment period constraint condition.

[0078] The first obtaining unit is configured to determine the amount intersection, the interest rate intersection and the period intersection as the target condition if the amount intersection, the interest rate intersection and the period intersection are not empty sets.

[0079] Optionally, the adjusting module 34 further comprises: The third determining unit is configured to determine the number of empty sets if there are empty sets in the amount intersection, the interest rate intersection and the period intersection.

[0080] The first judging unit is configured to determine the loan condition as the target condition if the number of empty sets is greater than a preset threshold.

[0081] The second judging unit is configured to determine the feedback information as the target condition if the number of empty sets is not greater than the preset threshold.

[0082] Optionally, the data processing apparatus 30 further comprises: The adjusting module is configured to perform parameter adjustment on the neural network model according to the adjusted loan scheme to obtain an adjusted neural network model.

[0083] It should be noted that the information interaction and execution process between the units are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought by the same can be referred to the method embodiments part. Therefore, no further description is given here.

[0084] Figure 4 is a structural schematic diagram of a computer device provided by an embodiment of the present application. As shown in Figure 4 the computer device of this embodiment includes at least one processor (only one is shown in Figure 4 the memory and a computer program stored in the memory and executable on the at least one processor. The processor implements the steps in any of the above data processing method embodiments when executing the computer program.

[0085] The computer device can include, but is not limited to, the processor, the memory. Those skilled in the art can understand that Figure 4 it is only an example of the computer device and does not constitute a limitation on the computer device. The computer device can include more or fewer components than those shown, or combine certain components, or different components, for example, it can also include a network interface, a display screen and an input device, etc.

[0086] The processor can be a CPU. The processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), ready programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0087] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory can be a memory of the computer device, and the internal memory provides an environment for running of the operating system and the computer-readable instructions in the readable storage medium. The readable storage medium can be a hard disk of the computer device, and in other embodiments, can also be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory can include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a BootLoader, data, and other programs, such as program codes of computer programs, etc. The memory can also be used to temporarily store data that has been output or will be output.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the above device can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here. If the integrated unit is realized in the form of software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium at least includes any entity or device that can carry computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, computer readable medium cannot be electrical carrier signal and telecommunication signal.

[0089] The above embodiment methods can also be completed by a computer program product, which can be run on a computer device to make the computer device execute the steps of the above method embodiments.

[0090] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0091] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0092] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / computer device and method can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely schematic. The division of the modules or units is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0093] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0094] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A data processing method, characterized by, The data processing method comprises: Obtaining user portrait data of a user and external data, wherein the external data at least comprises market interest rate data and market economic policy data; Processing the user portrait data and the external data based on a preset neural network model to determine an initial loan scheme of the user, wherein the initial loan scheme at least comprises an initial loan amount, an initial loan interest rate and an initial repayment period; Determining risk information of the user, and determining a loan condition matched with the user according to the risk information; Determining feedback information of the user on the initial loan scheme, determining a target condition according to an intersection between the feedback information and the loan condition, and adjusting the initial loan amount, the initial loan interest rate and the initial repayment period in the initial loan scheme according to the target condition to obtain an adjusted loan scheme.

2. The data processing method of claim 1, wherein, The processing of the user portrait data and the external data based on the preset neural network model to determine the initial loan scheme of the user comprises: Preprocessing the user portrait data and the external data to obtain preprocessed user portrait data and preprocessed external data; Fusing the preprocessed user portrait data and the preprocessed external data based on a multi-source data fusion technology to obtain fused data; Processing the fused data based on the preset neural network model to determine the initial loan scheme of the user.

3. The data processing method of claim 1, wherein, The determination process of the risk information comprises: Performing risk assessment on the user according to the user portrait data to determine the risk information of the user.

4. The data processing method of claim 1, wherein, The feedback information at least comprises loan amount feedback information, loan interest rate feedback information and repayment period feedback information; The loan condition at least comprises a loan amount constraint condition, a loan interest rate constraint condition and a repayment period constraint condition; The determination of the target condition according to the intersection between the feedback information and the loan condition comprises: Determining an amount intersection of the loan amount feedback information and the loan amount constraint condition, a rate intersection of the loan interest rate feedback information and the loan interest rate constraint condition, and a period intersection of the repayment period feedback information and the repayment period constraint condition; If the amount intersection, the rate intersection and the period intersection are not empty sets, the amount intersection, the rate intersection and the period intersection are determined as the target condition.

5. The data processing method of claim 4, wherein, After determining the amount intersection of the loan amount feedback information and the loan amount constraint condition, the rate intersection of the loan interest rate feedback information and the loan interest rate constraint condition, and the period intersection of the repayment period feedback information and the repayment period constraint condition, the method further comprises: If there is an empty set in the amount intersection, the rate intersection and the period intersection, determining the number of empty sets; If the number of empty sets is greater than a preset threshold, the loan condition is determined as the target condition; If the number of empty sets is not greater than the preset threshold, the feedback information is determined as the target condition.

6. The data processing method of claim 1, wherein, The data processing method further comprises: Adjusting parameters of the neural network model according to the adjusted loan scheme to obtain an adjusted neural network model.

7. A data processing apparatus, characterized by, The data processing apparatus comprises: an acquisition module configured to acquire user portrait data of a user and external data, the external data comprising at least market interest rate data and market economic policy data; a first determination module configured to process the user portrait data and the external data based on a preset neural network model, and determine an initial loan scheme of the user, the initial loan scheme comprising at least an initial loan amount, an initial loan interest rate and an initial repayment period; a second determination module configured to determine risk information of the user, and determine a loan condition matched with the user according to the risk information; an adjustment module configured to determine feedback information of the user on the initial loan scheme, determine a target condition according to an intersection between the feedback information and the loan condition, and adjust the initial loan amount, the initial loan interest rate and the initial repayment period in the initial loan scheme according to the target condition to obtain an adjusted loan scheme.

8. The data processing apparatus of claim 7, wherein, The first determination module comprises: a preprocessing unit configured to preprocess the user portrait data and the external data to obtain preprocessed user portrait data and preprocessed external data; a fusion unit configured to perform data fusion on the preprocessed user portrait data and the preprocessed external data based on a multi-source data fusion technology to obtain fused data; and a determination unit configured to process the fused data based on a preset neural network model to determine the initial loan scheme of the user.

9. A computer device, comprising: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the data processing method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executable on the processor to implement the data processing method according to any one of claims 1 to 6.

Images