CN114723481A

CN114723481A - Data processing method and device, electronic equipment and storage medium

Info

Publication number: CN114723481A
Application number: CN202210315710.8A
Authority: CN
Inventors: 刘垚; 范戈; 许晴
Original assignee: China Construction Bank Corp
Current assignee: China Construction Bank Corp
Priority date: 2022-03-29
Filing date: 2022-03-29
Publication date: 2022-07-08

Abstract

The invention discloses a data processing method and device, electronic equipment and a storage medium, and relates to the technical field of big data intelligent analysis. One embodiment of the method comprises: responding to a data processing request of a target object, and acquiring a user identifier so as to acquire basic information, first attribute information and second attribute information of a corresponding user; querying the type strategy of the target object to determine a corresponding processing model; counting target values of preset first attribute parameters and preset second attribute parameters to determine user types and risk types of users; generating a grading feature vector of the user to input a grading model and determining the grading level of the user; and calling a processing model, and determining the rate level of the user based on the user type, the risk type and the grading level of the user so as to generate the price of the target object. This embodiment can solve the problem that the mode of unified setting product price can't satisfy user's diversity demand.

Description

Data processing method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of big data intelligent analysis, in particular to a data processing method and device, electronic equipment and a storage medium.

Background

In recent years, networked financial enterprises, which represent consumer financing, have been rapidly developed, and the credit business volume of users has been gradually increased, so that it has become an important issue to provide proper credit products for different users and to determine matched prices. In the prior art, generally, a uniform product price is set for issuing credit products, but because users who purchase products can involve different types and change over time, the risks that each user can bear are different, and therefore the mode of uniformly setting the product price cannot meet the requirement of diversity of the users.

Disclosure of Invention

In view of this, embodiments of the present invention provide a data processing method and apparatus, an electronic device, and a storage medium, which can solve the problem that a way of uniformly setting product prices cannot meet the diversity requirements of users.

To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a data processing method.

The data processing method of the embodiment of the invention comprises the following steps:

responding to a data processing request of a target object, acquiring a user identifier in the data processing request to call a preset acquisition engine, and acquiring basic information, first attribute information and second attribute information of a corresponding user; inquiring the type strategy of the target object from a database to match a target type through the basic information and determine a corresponding processing model; counting target values of preset first attribute parameters and preset second attribute parameters from the first attribute information and the second attribute information to determine the user type and the risk type of the user; generating a scoring feature vector of the user based on the first attribute information and the second attribute information so as to input a scoring model and determine a scoring level of the user; and calling the processing model, and determining the rate grade of the user based on the user type, the risk type and the grading grade of the user so as to generate the price of the target object.

In one embodiment, the querying the type policy of the target object from the database to match the target type with the basic information, and determining the corresponding processing model includes:

acquiring an object identifier of the target object so as to query a corresponding type strategy from a database;

and matching the basic information with the type strategy to obtain a successfully matched basic rate so as to determine a processing model corresponding to the basic rate.

In yet another embodiment, generating the price for the target object comprises:

and adjusting the basic rate based on the rate grade to obtain the price of the target object.

In yet another embodiment, before generating the scored feature vector of the user based on the first attribute information and the second attribute information, the method further comprises:

obtaining model training data to perform model training on the scoring model;

obtaining a score numerical interval input by the trained score model, and dividing the score numerical interval corresponding to each score grade based on a preset grade proportion;

calling a preset lifting rate model to calculate the lifting rate corresponding to each evaluation data value interval based on model training data;

and determining a score numerical value interval corresponding to each score grade in response to that the lifting rate corresponding to each score data value interval meets a preset condition.

In another embodiment, before counting target values of a preset first attribute parameter and a preset second attribute parameter from the first attribute information and the second attribute information, the method includes:

acquiring a first parameter value of the preset first attribute parameter from the first attribute information;

updating a preset first target value to a new first parameter value in response to the first parameter value belonging to a first parameter value set;

acquiring a second parameter value of the preset second attribute parameter from the second attribute information;

updating the preset second target value to a new second parameter value in response to the second parameter value belonging to the second set of parameter values.

In another embodiment, counting target values of a preset first attribute parameter and a preset second attribute parameter from the first attribute information and the second attribute information includes:

screening parameter values of preset first attribute parameters and preset second attribute parameters in each preset time window from the first attribute information and the second attribute information to calculate statistical values of the preset first attribute parameters and the preset second attribute parameters;

and determining the statistic value of the preset first attribute parameter as a target value of the preset first attribute parameter, and determining the statistic value of the preset second attribute parameter as a target value of the preset second attribute parameter.

In another embodiment, the querying the type policy of the target object from the database includes:

acquiring a historical user corresponding to the target object to inquire corresponding basic information, first attribute information and second attribute information, calling a similarity model, and calculating the similarity between the historical user and a user corresponding to the user identifier;

responding that the similarity is larger than a preset threshold value, and acquiring the price of a target object corresponding to the historical user to determine the price as the price of the target object;

and responding to the similarity not larger than the preset threshold value, and inquiring the type strategy of the target object from a database.

In another embodiment, querying the corresponding basic information, the first attribute information and the second attribute information to invoke a similarity model, and calculating the similarity between the historical user and the user corresponding to the user identifier comprises:

and querying a user type, a risk type and a rating level corresponding to the historical user, and determining the user type, the risk type and the rating level of the user based on the first attribute information and the second attribute information corresponding to the user identification so as to calculate the similarity between the historical user and the user.

To achieve the above object, according to another aspect of the embodiments of the present invention, there is provided a data processing apparatus.

A data processing apparatus of an embodiment of the present invention includes: the acquisition unit is used for responding to a data processing request of a target object, acquiring a user identifier in the data processing request, calling a preset acquisition engine, and acquiring basic information, first attribute information and second attribute information of a corresponding user; the determining unit is used for inquiring the type strategy of the target object from a database so as to match the target type through the basic information and determine a corresponding processing model; the determining unit is further configured to count target values of preset first attribute parameters and preset second attribute parameters from the first attribute information and the second attribute information to determine a user type and a risk type of the user; the determining unit is further configured to generate a scoring feature vector of the user based on the first attribute information and the second attribute information, so as to input a scoring model and determine a scoring level of the user; and the generating unit is used for calling the processing model, determining the rate level of the user based on the user type, the risk type and the grading level of the user, and generating the price of the target object.

To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic apparatus.

An electronic device of an embodiment of the present invention includes: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the data processing method provided by the embodiment of the invention.

To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided a computer-readable medium.

A computer-readable medium of an embodiment of the present invention stores thereon a computer program, which, when executed by a processor, implements a data processing method provided by an embodiment of the present invention.

To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided a computer program product.

A computer program product according to an embodiment of the present invention includes a computer program, and when the computer program is executed by a processor, the computer program implements the data processing method according to an embodiment of the present invention.

One embodiment of the above invention has the following advantages or benefits: in the embodiment of the invention, in response to a processing request of a target product, a processing engine of a target object can be determined, user information is collected, and further credit and risk analysis of a user can be carried out based on the collected user information to obtain user types, risk types and risk scores, so that adaptive pricing rate grades can be determined for the user based on the processing engine from the aspects, and the price of the target object is generated. In the embodiment of the invention, different processing rules are set for different types of objects, and adaptive object prices are determined for users from different attribute angles, so that different users can purchase target objects through different prices, the purchase requirements of diversified users are met, and meanwhile, adaptive product prices can be determined for users with higher risks, and the accuracy of risk avoidance is improved.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:

FIG. 1 is a schematic diagram of a main flow of a data processing method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of yet another major flow of a data processing method according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of another main flow of a data processing method according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of the main elements of a data processing apparatus according to an embodiment of the present invention;

FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;

FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing embodiments of the present invention.

Detailed Description

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.

An embodiment of the present invention provides a data processing method, which may be executed by a data processing system, as shown in fig. 1, and the method includes:

s101: and responding to a data processing request of the target object, acquiring a user identifier in the data processing request to call a preset acquisition engine, and acquiring basic information, first attribute information and second attribute information of a corresponding user.

The data processing request represents a price processing request for a product such as finance, and the target object may be a product corresponding to the data processing request, such as a credit product. The data processing request may be triggered automatically by the data processing system or by an external system. For example, a data processing request of a target object may be triggered when a user purchases the target object. The data processing request indicates that the purchase price of the target object is determined for the user, so the object identification of the target object and the user identification of the user who purchased the target object may be included in the data processing request. After the user identifier in the data processing request is obtained in this step, information acquisition can be performed based on the user identifier. Since the user information to be collected may need to be collected from multiple systems, in the embodiment of the present invention, a collection engine may be preset to perform data transmission with each system through the collection engine, so as to collect the user information of the user.

Specifically, the user information may include basic information of the user, first attribute information, and second attribute information, where the first attribute information may specifically be loan information, and the second attribute information may specifically be credit investigation information, and in the embodiment of the present invention, the first attribute information is taken as the loan information, and the second attribute information is taken as the credit investigation information. The basic information may include user identity information, used equipment information, address information, etc., the debit and credit information may include information that the user purchases other credit products in the system, credit information from other third party systems, etc., and the credit information may include credit investigation reports of the user, etc.

S102: and inquiring the type strategy of the target object from the database to match the target type through the basic information and determine a corresponding processing model.

Since different types of objects are generally applicable to different types of users and have different pricing rules, corresponding processing models can be configured for different types of users and stored in a database, and a corresponding relationship between object types and processing models is established.

In this step, the type policy of the target object can be queried through the object identifier, so that the corresponding type policy is matched through the basic information of the user, and then the successfully matched target type can be determined, and further the processing model corresponding to the target type can be determined. Specifically, the basic information of the user may include identity information of the user, such as age, income, occupation, and the like, and the identity information may be matched with a preset type policy to obtain a corresponding target type.

It should be noted that, in the embodiment of the present invention, different reference rates may be set for the target object, and then the target object may be adjusted on the basis of the reference rates to determine the price of the target object, so that corresponding rule tables may be configured for the different reference rates, where the rule tables include rate adjustment rules, i.e., processing engines, corresponding to users of different user types, risk types, and rating levels, and therefore in this step, the target type of the target object may be matched through the basic information of the user, i.e., the reference rate is determined, and then the processing engine is obtained, so that the rate adjustment is performed on the basis of the reference rates to obtain the price of the target object.

S103: and counting target values of preset first attribute parameters and preset second attribute parameters from the first attribute information and the second attribute information to determine the user type and the risk type of the user.

In the embodiment of the present invention, the preset first attribute parameter may specifically be a preset credit parameter for determining a user type of the user, and the preset second attribute parameter may specifically be a preset credit investigation parameter for determining a risk type of the user. In this step, the loan information and the credit investigation information include the parameter values of the preset credit parameters and the preset credit investigation parameters corresponding to the user, so that the target values of the preset credit parameters and the target values of the preset credit investigation parameters can be counted from the parameter values, and the user type and the risk type of the user can be determined.

The preset credit parameter and the preset credit investigation parameter can be both based on the scene setting. For example, the preset credit parameters may include characteristics of the property, loan particulars, transaction information, and the like of the user, and may be specifically derived from a transaction flow record of the user, and the preset credit parameters may include the number of times the user is set to a blacklist, and the like. Specifically, in the embodiment of the present invention, a plurality of time windows (for example, within the previous 1 month, and from the previous 1 month to the previous 3 months) may be preset, so as to screen parameter values of the preset credit parameters and the preset credit assessment parameters within each preset time window from the loan information and the credit assessment information, and further calculate statistical values of the parameter values of the preset credit parameters and the preset credit assessment parameters within each preset time window, such as statistical values of a sum, a mean value, a quantile, a minimum value, a maximum value, a standard deviation, and the like, so that the statistical values may be determined as target values of the preset credit parameters and the preset credit assessment parameters.

It should be noted that, in the embodiment of the present invention, before the target values of the preset credit parameter and the preset credit investigation parameter are counted, the loan information and the credit investigation information may be preprocessed. Specifically, the parameter values of some parameters usually have some unusual parameter values, for example, the type of business, and there are usually many parameter values, and the unusual parameter values can be classified into one group and expressed by the same parameter value. Therefore, in this step, a first parameter value of the preset credit parameter may be obtained from the loan information, and then it is determined whether the first parameter value belongs to a first parameter value set, where the first parameter value set is an uncommon parameter value set corresponding to the preset credit parameter; if the first parameter value belongs to the first parameter value set, which indicates that the first parameter value is an uncommon parameter value, the preset first target value can be updated to a new first parameter value; if the first parameter value does not belong to the first set of parameter values, indicating that it is not an uncommon parameter value, then no processing may be performed. Similarly, in this step, a second parameter value of the preset credit investigation parameter may be obtained from the credit investigation information, and it is further determined whether the second parameter value belongs to a second parameter value set, where the second parameter value set is an uncommon parameter value set corresponding to the preset credit investigation parameter; if the second parameter value belongs to the second parameter value set, which indicates that the second parameter value is an uncommon parameter value, the preset second target value can be updated to a new second parameter value; if the second parameter value does not belong to the second set of parameter values, indicating that it is not an uncommon parameter value, then no processing may be performed.

In the embodiment of the invention, the user types can be divided into common users and high-quality credit returning users, and the mapping relation between each user type and the parameter value of the preset credit parameter is further established, so that the corresponding user type can be determined based on the target value of the preset credit parameter in the step.

In the embodiment of the invention, the risk types of the user can be divided, for example, the risk types can be divided into strong rule hit, weak rule hit and irregular hit, and then each risk rule is established so as to determine the risk types based on the risk rules hit by the preset credit investigation parameters. Specifically, for example, the preset credit investigation parameters and the credit investigation times are taken as examples, the strong rule hit represents the hit strong rejection rule of the preset credit investigation parameters of the user, for example, the user is set as a list to represent the hit strong rejection rule, so that the risk type of the user is the strong rule hit; the weak rule hit represents that the user is hit by the weak rejection rule, for example, the number of credit investigation times of the user in the last 3 months exceeds 5, which represents the weak rejection rule hit, so the risk type of the user is the weak rule hit; and if the random hit represents that the user does not hit any risk rule, determining that the risk type of the user is the random hit.

S104: and generating a scoring feature vector of the user based on the first attribute information and the second attribute information so as to input a scoring model and determine a scoring level of the user.

The scoring characteristic can be preset, and in the step, a scoring characteristic value can be determined from the loan information and the credit investigation information based on the preset scoring characteristic, so that a scoring characteristic vector is generated. And inputting the scoring characteristic vector into a scoring model, so that the risk score of the user can be obtained, and further the scoring grade of the user can be determined.

Specifically, taking a numerical value of 0 to 800 as an example of the score output by the scoring model, the scoring levels shown in table 1 may be divided, and then the scoring level of the user may be determined.

TABLE 1

Grade of rating	Section of the score
		A	651-800
B	551-650
		C	451-550
D	351-450
		E	0-350

In the embodiment of the invention, the scoring model is pre-trained and can be a model constructed based on a machine learning algorithm. After the model is built, a user group used by the model can be determined, so that the model is trained based on user information of users in the user group. Specifically, in the embodiment of the present invention, the score features corresponding to each user in the user group are obtained through the view analysis, and further, the feature vector for model training may be generated through measures such as variable binning, WOE conversion, and information value IV calculation. And inputting the obtained feature vectors into the constructed scoring model, and then realizing the training of the scoring model. The scoring characteristics of model training may include minimum credit card available amount of 90 days in the past, average credit card transaction amount of 60 days in the past, number of queries in 1 month of credit investigation, maximum credit investigation amount of credit investigation card, number of financial companies consuming the credit investigation institution of 1800 days in the past, used amount of credit investigation card ratio, average credit investigation residual loan amount of 720 days in the past, average credit investigation credit card transaction amount of 90 days in the past, total credit investigation amount of 60 days in the past, and number of payment of 60 days in the past.

The scoring model may use integrated algorithm LightGBM, and the adjustable parameters include max _ depth, min _ data _ in _ leaf, bagging _ fraction, early _ stopping _ round, and min _ gain _ to _ split. The max _ depth represents the maximum depth of the tree, a leaf-wise splitting strategy can grow a deeper decision tree to generate overfitting, the limit of the max _ depth is increased, overfitting is prevented while high efficiency is guaranteed, and the decision tree can be set to be 8 in the embodiment of the invention; min _ data _ in _ leaf represents the minimum number of records a leaf may have, which is set to 100-1000 in the embodiment of the present invention to prevent overfitting; bagging _ fraction represents the proportion of data used in each iteration and is used for carrying out faster result bagging to accelerate training speed and reduce overfitting; early stopping and stopping iteration when a certain verification index of certain verification data is not lifted in the last current iteration, so that analysis can be accelerated and excessive iteration is reduced; min _ gain _ to _ split represents the minimum gain describing the split, which can control the useful split of the tree.

After the model is trained, the training effect of the model can be evaluated to evaluate the effect of the model, and the accuracy and the stability of the model effect generally meet the preset requirements. Specifically, the accuracy of the model can be evaluated by using the KS value, for example, the preset requirement is that the KS value of the model is not lower than 0.35, and the stability of the model is evaluated by using the PSI value, for example, the preset requirement is that the PSI of the model is not higher than 0.1.

The scoring model outputs the default rate of the result of the common user, which is not the value in the preset scoring interval, and the result obtained by the scoring model can be converted through the formula 1 to obtain the scoring value in the scoring interval. In formula 1, P represents a value obtained by a scoring model (specifically, may represent a default rate of a user), x and y represent calculation coefficients, and Score represents a Score of the user based on a scene setting.

In the embodiment of the present invention, the ratio of the rating grade division may be preset to divide the rating grade, but since the higher the rating grade is, the higher the risk of the corresponding user is, the higher the rating grade needs to be, the higher the corresponding promotion rate is, so that in the embodiment of the present invention, the rating grade division manner may be determined based on the promotion rate. Specifically, the preset grade ratio may be 20%: 25%: 30%: 20%: 5%, the scoring numerical value interval input by the trained scoring model can be obtained, and the scoring numerical value interval corresponding to each scoring grade is divided based on the preset grade proportion; then calling a preset lifting rate model to calculate the lifting rate corresponding to each grading data value interval based on model training data; if the lifting rate corresponding to each grading data value interval meets the preset condition, namely the lifting rate corresponding to each grading data value interval is sequentially increased, then the grading numerical value interval corresponding to each grading grade can be determined; if the lifting rate corresponding to each scoring data value interval does not meet the preset condition, that is, the lifting rate corresponding to each scoring data value interval is not sequentially increased, the preset grade proportion can be adjusted to adjust the scoring value interval corresponding to each scoring grade.

The lift rate model may be constructed based on equation 2.

In equation 2, the parameters may be statistically derived based on the training data, and whether each user is a bad user may be determined before the model training.

S105: and calling a processing model, and determining the rate level of the user based on the user type, the risk type and the grading level of the user so as to generate the price of the target object.

Wherein, after the user type, the risk type and the grade of the user are obtained, the rate grade of the user can be determined based on the processing model.

Specifically, the processing model may include a rule table for pricing, in which rate levels corresponding to the user types, the risk types, and the rating levels are set, and further, based on the reference rate and the pricing rate levels corresponding to the processing model, the price of the target object may be obtained.

For example, taking the user types including credit, premium user, and general user, the risk types including irregular hit, weak regular hit, and strong regular hit, and the rating level including A, B, C, D, E as an example, the rule table may specifically be: the user types are: the method comprises the steps that users with good quality are rewarded, the risk types are hit irregularly, when the rating level is A, the rate level is rate reduction 2; the user types are: and when the risk type of the common user is weak rule hit and the rating level is E, the rate level is rate up-grade 2 and the like.

It should be noted that, in the embodiment of the present invention, when responding to a data processing request, the price of the current target object may also be determined from the target objects already priced in the history record, so that the operation process of price processing is reduced, and the processing efficiency is improved. Specifically, before step S102 is executed, a historical user corresponding to the target object may be further obtained to query corresponding basic information, first attribute information, and second attribute information, and then the user information of the corresponding user and the user information of the historical user may be requested through data processing to calculate the similarity between the users. If a historical user with the similarity larger than a preset threshold exists, determining the price of the target object corresponding to the historical user as the price of the target object; if there is no historical user with a similarity greater than the preset threshold, step S102 may be performed until the price of the target object is determined.

Specifically, calculating the similarity between users may be performed as: and querying the user type, the risk type and the grade corresponding to the historical user, and determining the user type, the risk type and the grade of the user based on the first attribute information and the second attribute information so as to calculate the similarity between the historical user and the user corresponding to the user identification.

Since the historical user has already determined the corresponding object price, the user type, risk type and rating level corresponding to the historical user can be queried from the database. In the embodiment of the present invention, the user type, the risk type and the rating level corresponding to the user identifier may also be obtained through steps S102, S103 and S104, so that the similarity between the users may be calculated through the user type, the risk type and the rating level corresponding to the historical user and the user type, the risk type and the rating level corresponding to the user representation.

In the embodiment of the invention, different processing rules are set for different types of objects, and adaptive object prices are determined for users from different attribute angles, so that different users can purchase target objects through different prices, the purchase requirements of diversified users are met, and meanwhile, adaptive product prices can be determined for users with higher risks, and the accuracy of risk avoidance is improved.

The following describes, in detail, a data processing method in an embodiment of the present invention with reference to the embodiment shown in fig. 1, and as shown in fig. 2, the method includes:

s201: and responding to the data processing request of the target object, and acquiring the user identification in the data processing request.

S202: and calling a preset acquisition engine to acquire the basic information, the first attribute information and the second attribute information of the user.

S203: acquiring a product identifier of a target object so as to query a corresponding type strategy from a database; and matching the basic information with the type strategy to obtain a successfully matched basic rate so as to determine a processing model corresponding to the basic rate.

S204: and screening parameter values of preset first attribute parameters and preset second attribute parameters in each preset time window from the first attribute information and the second attribute information to calculate statistical values of the preset first attribute parameters and the preset second attribute parameters.

S205: and determining the preset statistical value of the first attribute parameter as a preset target value of the first attribute parameter, and determining the preset statistical value of the second attribute parameter as a preset target value of the second attribute parameter.

S206: and determining the user type and the risk type of the user based on the target value of the preset first attribute parameter and the target value of the preset second attribute parameter.

S207: and generating a scoring feature vector of the user based on the first attribute information and the second attribute information so as to input a scoring model and determine a scoring level of the user.

S208: and calling a processing model, and determining the rate level of the user based on the user type, the risk type and the rating level of the user.

S209: and adjusting the basic rate based on the rate grade to obtain the price of the target object.

It should be noted that the data processing principle in the embodiment of the present invention is the same as that in the embodiment shown in fig. 1, and is not described herein again.

Referring to the embodiment shown in fig. 1, a data processing method in the embodiment of the present invention is specifically described below by taking a target object as a target product, first attribute information as loan information, second attribute information as credit information, a preset first attribute parameter as a preset loan parameter, and a preset second attribute parameter as a preset credit parameter, as shown in fig. 3, where the method includes:

s301: and responding to the data processing request of the target object, and acquiring the user identification in the data processing request.

S302: and calling a preset acquisition engine to acquire basic information, loan information and credit investigation information of the user.

S303: acquiring a product identifier of a target product to inquire a corresponding type strategy from a database; and matching the basic information with the type strategy to obtain a successfully matched basic rate so as to determine a processing model corresponding to the basic rate.

S304: and screening the parameter values of the preset credit parameters and the preset credit investigation parameters in each preset time window from the loan information and the credit investigation information to calculate the statistical values of the preset credit parameters and the preset credit investigation parameters.

S305: and determining the statistical value of the preset credit parameters as the target value of the preset credit parameters, and determining the statistical value of the preset credit investigation parameters as the target value of the preset investigation parameters.

S306: and determining the user type and the risk type of the user based on the target value of the preset credit parameter and the target value of the preset credit investigation parameter.

S307: and generating a grading feature vector of the user based on the loan information and the credit investigation information so as to input a grading model and determine the grading level of the user.

S308: and calling a processing model, and determining the rate level of the user based on the user type, the risk type and the rating level of the user.

S309: and adjusting the basic rate based on the rate grade to obtain the price of the target product.

In the embodiment of the invention, different pricing rules are set for different types of products, and the adaptive product price is determined for the user from the perspective of credit and risk, so that different users can purchase the target object through different prices, the purchase demand of diversified users is met, and the adaptive product price can be determined for users with higher risk, thereby improving the accuracy of risk avoidance.

In order to solve the problems in the prior art, an embodiment of the present invention provides an apparatus 400 for data processing, as shown in fig. 4, the apparatus 400 includes:

the acquisition unit 401 is configured to, in response to a data processing request of a target object, acquire a user identifier in the data processing request to call a preset acquisition engine, and acquire basic information, first attribute information, and second attribute information of a corresponding user;

a determining unit 402, configured to query a type policy of the target object from a database, to match a target type with the basic information, and determine a corresponding processing model;

the determining unit 402 is further configured to count target values of preset first attribute parameters and preset second attribute parameters from the first attribute information and the second attribute information to determine a user type and a risk type of the user;

the determining unit 402 is further configured to generate a scoring feature vector of the user based on the first attribute information and the second attribute information, so as to input a scoring model and determine a scoring level of the user;

a generating unit 403, configured to invoke the processing model, and determine a rate level of the user based on the user type, the risk type, and the rating level of the user, so as to generate a price of the target object.

It should be understood that the manner of implementing the embodiment of the present invention is the same as the manner of implementing the embodiment shown in fig. 1, and the description thereof is omitted.

In an embodiment, the determining unit 402 is specifically configured to:

In another embodiment, the generating unit 403 is specifically configured to:

In another embodiment, the determining unit 402 is specifically configured to:

obtaining model training data to perform model training on the scoring model;

acquiring a scoring numerical interval input by the trained scoring model, and dividing the scoring numerical interval corresponding to each scoring grade based on a preset grade proportion;

and determining a score value interval corresponding to each score grade in response to that the promotion rate corresponding to each score data value interval meets a preset condition.

In another embodiment, the determining unit 402 is specifically configured to:

It should be understood that the embodiment of the present invention is implemented in the same manner as the embodiment shown in fig. 2 or fig. 3 of fig. 1, and is not repeated herein.

According to an embodiment of the present invention, an electronic device and a readable storage medium are also provided.

The electronic device of the embodiment of the invention comprises: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the processor, and the instructions are executed by the at least one processor to cause the at least one processor to execute the data processing method provided by the embodiment of the invention.

Fig. 5 shows an exemplary system architecture 500 of a data processing method or data processing apparatus to which embodiments of the present invention may be applied.

As shown in fig. 5, the system architecture 500 may include

terminal devices

501, 502, 503, a network 504, and a server 505. The network 504 is the medium used to provide communication links between

terminal devices

501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

A user may use

terminal devices

501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages, etc. Various client applications may be installed on the

terminal devices

501, 502, 503.

The

terminal devices

501, 502, 503 may be, but are not limited to, smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 505 may be a server providing various services, and the server may analyze and process data such as a received product information query request, and feed back a processing result (for example, product information — just an example) to the terminal device.

It should be noted that the data processing method provided by the embodiment of the present invention is generally executed by the server 505, and accordingly, the data processing apparatus is generally disposed in the server 505.

It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use in implementing embodiments of the present invention is shown. The computer system illustrated in FIG. 6 is only one example and should not impose any limitations on the scope of use or functionality of embodiments of the invention.

As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.

It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a unit, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present invention may be implemented by software or hardware. The described units may also be provided in a processor, which may be described as: a processor includes an acquisition unit, a determination unit, and a generation unit. The names of these units do not in some cases form a limitation on the units themselves, and for example, the acquisition unit may also be described as a "unit of an information acquisition function".

As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to perform the data processing method provided by the present invention.

As another aspect, the present invention further provides a computer program product including a computer program, where the computer program is executed by a processor to implement the data processing method provided by the embodiment of the present invention.

The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A data processing method, comprising:

responding to a data processing request of a target object, acquiring a user identifier in the data processing request to call a preset acquisition engine, and acquiring basic information, first attribute information and second attribute information of a corresponding user;

inquiring the type strategy of the target object from a database to match a target type through the basic information and determine a corresponding processing model;

counting target values of preset first attribute parameters and preset second attribute parameters from the first attribute information and the second attribute information to determine the user type and the risk type of the user;

generating a scoring feature vector of the user based on the first attribute information and the second attribute information so as to input a scoring model and determine a scoring level of the user;

and calling the processing model, and determining the rate grade of the user based on the user type, the risk type and the grading grade of the user so as to generate the price of the target object.

2. The method of claim 1, wherein the querying the type policy of the target object from the database to match the target type with the basic information to determine the corresponding processing model comprises:

3. The method of claim 2, wherein generating the price for the target object comprises:

4. The method of claim 1, further comprising, prior to generating a scored feature vector for the user based on the first attribute information and the second attribute information:

obtaining model training data to perform model training on the scoring model;

5. The method according to claim 1, wherein counting the target values of the preset first attribute parameter and the preset second attribute parameter from the first attribute information and the second attribute information comprises:

6. The method according to claim 1, wherein counting target values of preset first attribute parameters and preset second attribute parameters from the first attribute information and the second attribute information comprises:

7. The method of claim 1, wherein querying the type policy of the target object from the database comprises:

8. The method of claim 7, wherein querying corresponding basic information, first attribute information and second attribute information to invoke a similarity model to calculate similarity between the historical user and the user corresponding to the user identifier comprises:

9. A data processing apparatus, characterized by comprising:

the acquisition unit is used for responding to a data processing request of a target object, acquiring a user identifier in the data processing request, calling a preset acquisition engine, and acquiring basic information, first attribute information and second attribute information of a corresponding user;

the determining unit is used for inquiring the type strategy of the target object from a database so as to match the target type through the basic information and determine a corresponding processing model;

the determining unit is further configured to count target values of preset first attribute parameters and preset second attribute parameters from the first attribute information and the second attribute information to determine a user type and a risk type of the user;

the determining unit is further configured to generate a scoring feature vector of the user based on the first attribute information and the second attribute information, so as to input a scoring model and determine a scoring level of the user;

and the generating unit is used for calling the processing model, determining the rate level of the user based on the user type, the risk type and the grading level of the user, and generating the price of the target object.

10. The apparatus according to claim 9, wherein the determining unit is specifically configured to:

11. The apparatus according to claim 10, wherein the generating unit is specifically configured to:

12. The apparatus according to claim 9, wherein the determining unit is specifically configured to:

obtaining model training data to perform model training on the scoring model;

13. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.

14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-8.

15. A computer program product comprising a computer program, characterized in that the program realizes the method according to any of claims 1-8 when executed by a processor.