Data processing method, device, electronic device and storage medium

Abstract

The present invention discloses a data processing method, device, electronic device and storage medium, and relates to the technical field of big data intelligent analysis. A specific implementation of the method includes: in response to a data processing request of a target object, obtaining a user identifier to collect basic information, first attribute information and second attribute information of the corresponding user; querying the type policy of the target object to determine the corresponding processing model; statistically calculating the target values ​​of the preset first attribute parameter and the preset second attribute parameter to determine the user type and risk type of the user; generating a scoring feature vector of the user to input into the scoring model to determine the user's scoring level; calling the processing model to determine the user's rate level based on the user's user type, risk type and scoring level to generate the price of the target object. This implementation can solve the problem that the method of uniformly setting product prices cannot meet the diverse needs of users.

Description

Technical Field

[0001] The present invention relates to the technical field of big data intelligent analysis, and in particular to a data processing method, device, electronic device and storage medium. Background Art

[0002] In recent years, Internet financial enterprises represented by consumer finance have developed rapidly, and the amount of user credit business has gradually increased. Providing appropriate credit products for different users and determining matching prices have become important issues. In the prior art, credit product releases usually set a unified product price, but since the users who purchase products may involve different types and change over time, and the risks that each user can bear are also different, the method of setting a unified product price cannot meet the diverse needs of users. Summary of the invention

[0003] In view of this, embodiments of the present invention provide a data processing method, device, electronic device and storage medium, which can solve the problem that a unified way of setting product prices cannot meet the diverse needs of users.

[0004] To achieve the above objective, according to one aspect of an embodiment of the present invention, a data processing method is provided.

[0005] A data processing method according to an embodiment of the present invention includes:

[0006] In response to a data processing request of a target object, a user identifier in the data processing request is obtained to call a preset collection engine to collect basic information, first attribute information and second attribute information of the corresponding user; the type policy of the target object is queried from a database to match the target type through the basic information and determine the corresponding processing model; from the first attribute information and the second attribute information, target values ​​of the preset first attribute parameter and the preset second attribute parameter are statistically calculated to determine the user type and risk type of the user; based on the first attribute information and the second attribute information, a scoring feature vector of the user is generated to input into a scoring model to determine the scoring level of the user; the processing model is called to determine the rate level of the user based on the user type, risk type and scoring level of the user to generate a price for the target object.

[0007] In one embodiment, querying the type strategy of the target object from the database to match the target type through the basic information and determine the corresponding processing model includes:

[0008] Obtaining an object identifier of the target object to query a corresponding type strategy from a database;

[0009] The basic information is matched with the type strategy to obtain a basic rate that matches successfully, so as to determine a processing model corresponding to the basic rate.

[0010] In yet another embodiment, generating a price for the target object includes:

[0011] The basic rate is adjusted based on the rate level to obtain a price for the target object.

[0012] In yet another embodiment, before generating the scoring feature vector of the user based on the first attribute information and the second attribute information, the method further includes:

[0013] Acquiring model training data to perform model training on the scoring model;

[0014] Obtain the score value range of the trained score model input, and divide the score value range corresponding to each score level based on the preset level ratio;

[0015] Calling a preset lift rate model to calculate the lift rates corresponding to each of the score data value intervals based on the model training data;

[0016] In response to the improvement rate corresponding to each of the score data value intervals satisfying a preset condition, the score value interval corresponding to each score level is determined.

[0017] In yet another embodiment, before calculating 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, the method includes:

[0018] Acquire a first parameter value of the preset first attribute parameter from the first attribute information;

[0019] In response to the first parameter value belonging to the first parameter value set, updating the preset first target value to a new first parameter value;

[0020] Acquire a second parameter value of the preset second attribute parameter from the second attribute information;

[0021] In response to the second parameter value belonging to a second parameter value set, the preset second target value is updated to a new second parameter value.

[0022] In yet another embodiment, calculating 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:

[0023] Filtering parameter values ​​of a preset first attribute parameter and a preset second attribute parameter in each preset time window from the first attribute information and the second attribute information to calculate statistical values ​​of the preset first attribute parameter and the preset second attribute parameter;

[0024] The statistical value of the preset first attribute parameter is determined as the target value of the preset first attribute parameter, and the statistical value of the preset second attribute parameter is determined as the target value of the preset second attribute parameter.

[0025] In yet another embodiment, querying the type strategy of the target object from a database includes:

[0026] Acquire a historical user corresponding to the target object to query the corresponding basic information, first attribute information, and second attribute information to call a similarity model to calculate the similarity between the historical user and the user corresponding to the user identifier;

[0027] In response to the similarity being greater than a preset threshold, obtaining a price of the target object corresponding to the historical user to determine the price of the target object;

[0028] In response to the similarity being not greater than the preset threshold, querying the type strategy of the target object from a database.

[0029] In yet another embodiment, querying the corresponding basic information, the first attribute information, and the second attribute information to call a similarity model and calculate the similarity between the historical user and the user corresponding to the user identifier includes:

[0030] The user type, risk type and score level corresponding to the historical user are queried, and the user type, risk type and score level of the user are determined based on the first attribute information and the second attribute information corresponding to the user identifier, so as to calculate the similarity between the historical user and the user.

[0031] To achieve the above objective, according to another aspect of an embodiment of the present invention, a data processing device is provided.

[0032] A data processing device according to an embodiment of the present invention includes: a collection unit, which is used to respond to a data processing request of a target object, obtain a user identifier in the data processing request, so as to call a preset collection engine to collect basic information, first attribute information and second attribute information of the corresponding user; a determination unit, which is used to query the type policy of the target object from a database, so as to match the target type through the basic information and determine the corresponding processing model; the determination unit is also used to statistically calculate 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 to determine the user type and risk type of the user; the determination unit is also used to generate a scoring feature vector of the user based on the first attribute information and the second attribute information, so as to input the scoring model and determine the scoring level of the user; a generation unit is used to call the processing model to determine the rate level of the user based on the user type, risk type and scoring level of the user, so as to generate the price of the target object.

[0033] To achieve the above objective, according to another aspect of an embodiment of the present invention, an electronic device is provided.

[0034] An electronic device according to an embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method provided by the embodiment of the present invention.

[0035] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer readable medium is provided.

[0036] A computer-readable medium according to an embodiment of the present invention stores a computer program, and when the program is executed by a processor, the data processing method provided by the embodiment of the present invention is implemented.

[0037] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer program product is provided.

[0038] A computer program product according to an embodiment of the present invention includes a computer program, and when the program is executed by a processor, the data processing method provided by the embodiment of the present invention is implemented.

[0039] An embodiment of the above invention has the following advantages or beneficial effects: In the embodiment of the present invention, in response to the processing request of the target product, the processing engine of the target object can be determined, and the user information can be collected, and then the user's credit and risk can be analyzed based on the collected user information to obtain the user type, risk type and risk score level, so that the appropriate pricing rate level can be determined for the user based on the processing engine from these aspects, thereby generating the price of the target object. In the embodiment of the present invention, different processing rules are set for different types of objects, and appropriate object prices are determined for users from different attribute perspectives, so that different users can purchase the target object at different prices to meet the purchase needs of diverse users. At the same time, appropriate product prices can be determined for users with higher risks to improve the accuracy of risk avoidance.

[0040] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0042] Figure 1 is a schematic diagram of a main process of a data processing method according to an embodiment of the present invention;

[0043] Figure 2 is a schematic diagram of another main flow of a data processing method according to an embodiment of the present invention;

[0044] Figure 3 is a schematic diagram of another main flow of a data processing method according to an embodiment of the present invention;

[0045] Figure 4 is a schematic diagram of main units of a data processing device according to an embodiment of the present invention;

[0046] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0047] Figure 6 It is a schematic diagram of the structure of a computer system suitable for implementing the embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0049] It should be noted that the embodiments and features of the embodiments of the present invention can be combined with each other without conflict. The acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.

[0050] The embodiment of the present invention provides a data processing method, which can be executed by a data processing system. Figure 1 As shown, the method includes:

[0051] S101: In response to a data processing request of a target object, a user identifier in the data processing request is obtained to call a preset collection engine to collect basic information, first attribute information, and second attribute information of a corresponding user.

[0052] Among them, the data processing request represents a price processing request for financial products, etc., and the target object can be specifically the product corresponding to the data processing request, such as a credit product. The data processing request can be automatically triggered by the data processing system, or it can be triggered by an external system. For example, the data processing request for the target object can be triggered when the user purchases the target object. The data processing request represents the purchase price of the target object determined by the user, so the data processing request may include the object identifier of the target object and the user identifier of the user who purchases the target object. After obtaining the user identifier in the data processing request in this step, information collection can be performed based on the user identifier. Since the user information that needs to be collected may need to be collected from multiple systems, a collection engine can be pre-set in an embodiment of the present invention to transmit data with each system through the collection engine to collect the user's user information.

[0053] Specifically, user information may include basic information, first attribute information, and second attribute information of the user, wherein the first attribute information may be specifically loan information, and the second attribute information may be specifically credit information. In the embodiment of the present invention, the first attribute information is loan information, and the second attribute information is credit information. Basic information may include user identity information, device information used, address information, etc., loan information may include information about other credit products purchased by the user in this system, credit information from other third-party systems, etc., and credit information may include the user's credit report, etc.

[0054] S102: Query the type strategy of the target object from the database to match the target type through basic information and determine the corresponding processing model.

[0055] Among them, since different types of objects are usually suitable for different types of users, they also have different pricing rules. Therefore, in an embodiment of the present invention, corresponding processing models can be configured for different types of users and stored in a database to establish a corresponding relationship between object types and processing models.

[0056] In this step, the type strategy of the target object can be queried through the object identification product, and the corresponding type strategy can be matched with the basic information of the user, and then the target type that is successfully matched can be determined, and then the processing model corresponding to the target type can be determined. Specifically, the basic information of the user may include the user's age, income, occupation and other identity information, and these identity information can be matched with the preset type strategy to obtain the corresponding target type.

[0057] It should be noted that in the embodiment of the present invention, different base rates can be set for the target object, and then adjustments can be made on the basis of the base rates to determine the price of the target object. Therefore, corresponding rule tables can be configured for different base rates, and the rule tables include rate adjustment rules corresponding to users of different user types, risk types and scoring levels, that is, the processing engine. Therefore, in this step, the target type of the target object can be matched through the basic information of the user, that is, the base rate is determined, and then the processing engine is obtained to adjust the rate based on the base rate to obtain the price of the target object.

[0058] S103: Counting target values ​​of the preset first attribute parameter and the preset second attribute parameter from the first attribute information and the second attribute information to determine the user type and risk type of the user.

[0059] The preset first attribute parameter may be a preset credit parameter for determining the user type of the user, and the preset second attribute parameter may be a preset credit parameter for determining the risk type of the user. In the embodiment of the present invention, the preset first attribute parameter is a preset credit parameter, and the preset second attribute parameter is a preset credit parameter. In this step, the loan information and credit information include the parameter values ​​of the preset credit parameter and the preset credit parameter of the user, so that the target value of the preset credit parameter and the target value of the preset credit parameter can be statistically calculated, and then the user type and risk type of the user can be determined.

[0060] Both the preset credit parameters and the preset credit parameters can be set based on scenarios. For example, the preset credit parameters may include the user's assets, loan details, transaction information and other characteristics, which can be specifically obtained from the user's transaction flow records, and the preset credit parameters may include the number of times the user has been set on the blacklist, etc. Specifically, in an embodiment of the present invention, multiple time windows (such as within the previous month, from the previous month to the previous three months) can be preset to filter the parameter values ​​of the preset credit parameters and the preset credit parameters in each preset time window from the loan information and credit information, and then calculate the statistical values ​​of the parameter values ​​of the preset credit parameters and the preset credit parameters in each preset time window, such as the sum, mean, quantile, minimum value, maximum value, standard deviation and other statistical values, so that they can be determined as the target values ​​of the preset credit parameters and the preset credit parameters.

[0061] It should be noted that, in the embodiment of the present invention, before the target values ​​of the preset credit parameters and the preset credit parameters are calculated, the loan information and the credit information may be preprocessed. Specifically, some parameter values ​​usually have some uncommon parameter values. For example, the enterprise type usually has multiple parameter values, and the uncommon parameter values ​​can be classified into one category and represented by the same parameter value. Therefore, in this step, the first parameter value of the preset credit parameter can be obtained from the loan information, and then it can be determined whether the first parameter value belongs to the first parameter value set, and the first parameter value set is the uncommon parameter value set corresponding to the preset credit parameter; if the first parameter value belongs to the first parameter value set, it means that it is an uncommon parameter value, and 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 parameter value set, it means that it is not an uncommon parameter value, and no processing is required. Similarly, in this step, the second parameter value of the preset credit parameter can be obtained from the credit information, and then it can be determined whether the second parameter value belongs to a second parameter value set, where the second parameter value set is a set of uncommon parameter values ​​corresponding to the preset credit parameter; if the second parameter value belongs to the second parameter value set, it means that it is an uncommon parameter value, and 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 parameter value set, it means that it is not an uncommon parameter value, and no processing is required.

[0062] In an embodiment of the present invention, user types can be divided, for example, into ordinary users and high-quality loan users, and then a mapping relationship between each user type and the parameter value of the preset credit parameter is established. Therefore, in this step, the corresponding user type can be determined based on the target value of the preset credit parameter.

[0063] In the embodiment of the present invention, the risk type of the user can also be divided, for example, it can be divided into strong rule hits, weak rule hits, and no rule hits, and then various risk rules are established to determine the risk type based on the risk rule hit by the preset credit parameter. Specifically, taking the preset credit parameter and the number of credit inquiries as an example, a strong rule hit means that the preset credit parameter of the user hits the strong rejection rule. For example, the user is set to a list, which means that the strong rejection rule is hit, so the risk type of the user is a strong rule hit; a weak rule hit means that the user is hit by a weak rejection rule. For example, the number of credit inquiries of the user in the past three months exceeds 5 times, which means that the weak rejection rule is hit, so the risk type of the user is a weak rule hit; no rule hit means that the user does not hit any risk rule, and the risk type of the user is determined to be no rule hit.

[0064] S104: Based on the first attribute information and the second attribute information, a rating feature vector of the user is generated to input into a rating model to determine the rating level of the user.

[0065] The scoring feature may be pre-set. In this step, the scoring feature value may be determined from the loan information and credit information based on the preset scoring feature, thereby generating a scoring feature vector. The scoring feature vector is input into the scoring model to obtain the user's risk score, thereby determining the user's score level.

[0066] Specifically, taking the score output by the scoring model as a value between 0 and 800 as an example, the scoring levels can be divided as shown in Table 1, and then the user's scoring level can be determined.

[0067] Table 1

[0068] Rating scale Rating range A 651-800 B 551-650 C 451-550 D 351-450 E 0-350

[0069] In an embodiment of the present invention, the scoring model is pre-trained and can be a model built based on a machine learning algorithm. After the model is built, the user group used by the model can be determined to train the model based on the user information of the users in the user group. Specifically, in an embodiment of the present invention, the scoring features corresponding to each user in the user group are obtained by vintage analysis, and then the feature vector for model training can be generated by variable binning, WOE conversion, information value IV calculation and other measures. After the feature vector obtained above is input into the constructed scoring model, the training of the scoring model is realized. The scoring features of the model training may include the minimum available credit limit of the credit card in the past 90 days of the bank, the average credit card transaction amount of the credit card in the past 60 days of the bank, the number of inquiries in the past month of credit investigation, the maximum credit amount of the credit card, the number of credit institutions in the past 1800 days of credit investigation for consumer finance companies, the proportion of the amount used by the credit card, the average remaining loan amount of consumer loans in the past 720 days of credit investigation, the average credit card transaction amount in the past 90 days of credit investigation, the sum of the loan amount of the bank's multiple mutual gold institutions in the past 60 days, and the number of repayments of the bank's multiple mutual gold institutions in the past 60 days.

[0070] The scoring model can use the integrated algorithm LightGBM, and the adjustable parameters include max_depth, min_data_in_leaf, bagging_fraction, early_stopping_round, and min_gain_to_split. Among them, max_depth represents the maximum depth of the tree. The leaf-wise splitting strategy will grow a relatively deep decision tree and produce overfitting. The max_depth limit is increased to prevent overfitting while ensuring high efficiency. In the embodiment of the present invention, it can be set to 8; min_data_in_leaf represents the minimum number of records that a leaf may have. In the embodiment of the present invention, it is set to between 100-1000 to prevent overfitting; bagging_fraction represents the data ratio used in each iteration, which is used to perform faster result bagging to speed up training and reduce overfitting; early_stopping_round means early stopping, which stops iteration when a certain verification indicator of a certain verification data has not been improved in the current last round of iteration, which can speed up analysis and reduce excessive iterations; min_gain_to_split represents the minimum gain describing the split, which can control the useful split of the tree.

[0071] After the model is trained, the training effect of the model can be evaluated to evaluate the effectiveness of the model. The model effect generally requires accuracy and stability to meet preset requirements. Specifically, the accuracy of the model can be evaluated by the KS value, for example, the preset requirement is that the model KS value is not less than 0.35, and the model stability is evaluated by PSI, for example, the preset requirement is that the model PSI is not higher than 0.1.

[0072] The output of the scoring model is usually the user's default rate. If it is not a value within the preset scoring range, the result obtained by the scoring model can also be converted through Formula 1 to obtain a scoring value within the scoring range. In Formula 1, P represents the value obtained by the scoring model (specifically, it can represent the user's default rate), x and y represent calculation coefficients, which can be set based on the scenario, and Score represents the user's score.

[0073]

[0074] In the embodiment of the present invention, the ratio of the scoring division level can be preset to divide the scoring level. However, since the higher the scoring level, the higher the risk of the corresponding user, the higher the scoring level, the higher the corresponding improvement rate. Therefore, in the embodiment of the present invention, the scoring level division method can be determined based on the improvement rate. Specifically, the preset level ratio can be 20%: 25%: 30%: 20%: 5%, so that the scoring value interval input by the trained scoring model can be obtained to divide the scoring value interval corresponding to each scoring level based on the preset level ratio; and then call the preset improvement rate model to calculate the improvement rate corresponding to each scoring data value interval based on the model training data; if the improvement rate corresponding to each scoring data value interval meets the preset conditions, that is, the improvement rate corresponding to each scoring data value interval increases in sequence, then the scoring value interval corresponding to each scoring level can be determined; if the improvement rate corresponding to each scoring data value interval does not meet the preset conditions, that is, the improvement rate corresponding to each scoring data value interval does not increase in sequence, then the preset level ratio can be adjusted to adjust the scoring value interval corresponding to each scoring level.

[0075] The improvement rate model may be constructed based on Formula 2.

[0076]

[0077] In Formula 2, each parameter can be obtained based on training data statistics, and whether each user is a bad user can be determined before model training.

[0078] S105: calling a processing model to determine the user's rate level based on the user's user type, risk type and scoring level to generate a price for the target object.

[0079] After obtaining the user type, risk type and score level of the user, the user's rate level can be determined based on the processing model.

[0080] Specifically, the processing model may include a rule table for pricing, in which rate levels corresponding to each user type, risk type and scoring level are set, and then the price of the target object can be obtained based on the base rate and pricing rate level corresponding to the processing model.

[0081] For example, taking the user types including re-loan, high-quality users and ordinary users, the risk types including no rule hits, weak rule hits and strong rule hits, and the scoring levels including A, B, C, D, and E as an example, the rule table can be specific as follows: the user type is: re-loan, high-quality user, the risk type is no rule hits, when the scoring level is A, the rate level is a reduction of 2 levels; the user type is: ordinary user, the risk type is a weak rule hit, when the scoring level is E, the rate level is an increase of 2 levels, and so on.

[0082] It should be noted that, in an embodiment of the present invention, when responding to a data processing request, the price of the target object can also be determined from the target object that has been priced in the historical records, thereby reducing the operational process of price processing and improving processing efficiency. Specifically, before executing step S102, the historical user corresponding to the target object can also be obtained to query the corresponding basic information, first attribute information, and second attribute information, and then the similarity between users can be calculated through the user information of the user corresponding to the data processing request and the user information of the historical user. If there is a historical user whose similarity is greater than a preset threshold, the price of the target object corresponding to this historical user can be determined as the price of the target object; if there is no historical user whose similarity is greater than the preset threshold, step S102 can be executed until the price of the target object is determined.

[0083] Specifically, calculating the similarity between users can be performed as follows: querying the user type, risk type and score level corresponding to the historical user, and determining the user type, risk type and score level of the user based on the first attribute information and the second attribute information to calculate the similarity between the historical user and the user corresponding to the user identifier.

[0084] Since the historical user has determined the corresponding object price, the user type, risk type and score level corresponding to the historical user can be queried from the database. In the embodiment of the present invention, the user type, risk type and score level corresponding to the user identifier can also be obtained through steps S102, S103 and S104, so that the similarity between users can be calculated by the user type, risk type and score level corresponding to the historical user and the user type, risk type and score level corresponding to the user representation.

[0085] In an embodiment of the present invention, different processing rules are set for different types of objects, and appropriate object prices are determined for users from different attribute perspectives, so that different users can purchase target objects at different prices to meet the purchasing needs of diverse users. At the same time, appropriate product prices can also be determined for users with higher risks to improve the accuracy of risk avoidance.

[0086] Combine the following Figure 1 The embodiment shown in the figure specifically describes the data processing method in the embodiment of the present invention. Figure 2 As shown, the method includes:

[0087] S201: In response to a data processing request of a target object, obtain a user identifier in the data processing request.

[0088] S202: Calling a preset collection engine to collect basic information, first attribute information, and second attribute information of the user.

[0089] S203: Obtain the product identification of the target object to query the corresponding type strategy from the database; match the basic information with the type strategy to obtain the basic rate of successful matching to determine the processing model corresponding to the basic rate.

[0090] S204: Filter parameter values ​​of the preset first attribute parameter and the preset second attribute parameter in each preset time window from the first attribute information and the second attribute information to calculate statistical values ​​of the preset first attribute parameter and the preset second attribute parameter.

[0091] S205: Determine the statistical value of the preset first attribute parameter as the target value of the preset first attribute parameter, and determine the statistical value of the preset second attribute parameter as the target value of the preset second attribute parameter.

[0092] S206: Determine the user type and risk type of the user based on the preset target value of the first attribute parameter and the preset target value of the second attribute parameter.

[0093] S207: Based on the first attribute information and the second attribute information, a rating feature vector of the user is generated to input into a rating model to determine a rating level of the user.

[0094] S208: Calling a processing model to determine the user's rate level based on the user's user type, risk type and score level.

[0095] S209: Adjust the basic rate based on the rate level to obtain the price of the target object.

[0096] It should be noted that the data processing principle in the embodiment of the present invention is the same as Figure 1 The data processing principles of the illustrated embodiments are the same and will not be described in detail here.

[0097] In an embodiment of the present invention, different processing rules are set for different types of objects, and appropriate object prices are determined for users from different attribute perspectives, so that different users can purchase target objects at different prices to meet the purchasing needs of diverse users. At the same time, appropriate product prices can also be determined for users with higher risks to improve the accuracy of risk avoidance.

[0098] Combine the following Figure 1 In the embodiment shown, the target object is the target product, the first attribute information is the loan information, the second attribute information is the credit information, the first attribute parameter is preset as the preset loan parameter, and the second attribute parameter is preset as the preset credit parameter. As an example, the data processing method in the embodiment of the present invention is specifically described. Figure 3 As shown, the method includes:

[0099] S301: In response to a data processing request from a target object, obtain a user identifier in the data processing request.

[0100] S302: Calling a preset collection engine to collect the user's basic information, loan information and credit information.

[0101] S303: Obtain the product identification of the target product to query the corresponding type strategy from the database; match the basic information with the type strategy to obtain the basic rate of the successful match to determine the processing model corresponding to the basic rate.

[0102] S304: Filtering the parameter values ​​of the preset credit parameters and the preset credit parameters in each preset time window from the loan information and the credit information to calculate the statistical values ​​of the preset credit parameters and the preset credit parameters.

[0103] S305: Determine the statistical value of the preset credit parameter as the target value of the preset credit parameter, and determine the statistical value of the preset credit reference parameter as the target value of the preset credit reference parameter.

[0104] S306: Determine the user type and 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.

[0105] S307: Based on the loan information and credit information, generate a user's scoring feature vector to input into a scoring model to determine the user's scoring level.

[0106] S308: Calling a processing model to determine the user's rate level based on the user's user type, risk type and score level.

[0107] S309: Adjust the basic rate based on the rate level to obtain the price of the target product.

[0108] It should be noted that the data processing principle in the embodiment of the present invention is the same as Figure 1 The data processing principles of the illustrated embodiments are the same and will not be described in detail here.

[0109] In an embodiment of the present invention, different pricing rules are set for different types of products, and appropriate product prices are determined for users from the perspective of credit and risk, so that different users can purchase target objects at different prices to meet the purchasing needs of diverse users. At the same time, appropriate product prices can also be determined for users with higher risks to improve the accuracy of risk avoidance.

[0110] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a data processing device 400, such as Figure 4 As shown, the device 400 includes:

[0111] The collection unit 401 is used to respond to the data processing request of the target object, obtain the user identifier in the data processing request, call the preset collection engine, and collect the basic information, the first attribute information and the second attribute information of the corresponding user;

[0112] A determination unit 402 is used to query the type strategy of the target object from the database to match the target type through the basic information and determine the corresponding processing model;

[0113] The determining unit 402 is further configured to collect target values ​​of a preset first attribute parameter and a preset second attribute parameter from the first attribute information and the second attribute information to determine a user type and a risk type of the user;

[0114] 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 the scoring model and determine the scoring level of the user;

[0115] The generating unit 403 is used to call the processing model, determine the rate level of the user based on the user type, risk type and scoring level of the user, so as to generate the price of the target object.

[0116] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1 The method of the illustrated embodiment is the same and will not be repeated here.

[0117] In one embodiment, the determining unit 402 is specifically configured to:

[0118] Obtaining an object identifier of the target object to query a corresponding type strategy from a database;

[0119] The basic information is matched with the type strategy to obtain a basic rate that matches successfully, so as to determine a processing model corresponding to the basic rate.

[0120] In yet another embodiment, the generating unit 403 is specifically configured to:

[0121] The basic rate is adjusted based on the rate level to obtain a price for the target object.

[0122] In yet another embodiment, the determining unit 402 is specifically configured to:

[0123] Acquiring model training data to perform model training on the scoring model;

[0124] Obtain the score value range of the trained score model input, and divide the score value range corresponding to each score level based on the preset level ratio;

[0125] Calling a preset lift rate model to calculate the lift rates corresponding to each of the score data value intervals based on the model training data;

[0126] In response to the improvement rate corresponding to each of the score data value intervals satisfying a preset condition, the score value interval corresponding to each score level is determined.

[0127] In yet another embodiment, the determining unit 402 is specifically configured to:

[0128] Acquire a first parameter value of the preset first attribute parameter from the first attribute information;

[0129] In response to the first parameter value belonging to the first parameter value set, updating the preset first target value to a new first parameter value;

[0130] Acquire a second parameter value of the preset second attribute parameter from the second attribute information;

[0131] In response to the second parameter value belonging to a second parameter value set, the preset second target value is updated to a new second parameter value.

[0132] In yet another embodiment, the determining unit 402 is specifically configured to:

[0133] Filtering parameter values ​​of a preset first attribute parameter and a preset second attribute parameter in each preset time window from the first attribute information and the second attribute information to calculate statistical values ​​of the preset first attribute parameter and the preset second attribute parameter;

[0134] The statistical value of the preset first attribute parameter is determined as the target value of the preset first attribute parameter, and the statistical value of the preset second attribute parameter is determined as the target value of the preset second attribute parameter.

[0135] In yet another embodiment, the determining unit 402 is specifically configured to:

[0136] Acquire a historical user corresponding to the target object to query the corresponding basic information, first attribute information, and second attribute information to call a similarity model to calculate the similarity between the historical user and the user corresponding to the user identifier;

[0137] In response to the similarity being greater than a preset threshold, obtaining a price of the target object corresponding to the historical user to determine the price of the target object;

[0138] In response to the similarity being not greater than the preset threshold, querying the type strategy of the target object from a database.

[0139] In yet another embodiment, the determining unit 402 is specifically configured to:

[0140] The user type, risk type and score level corresponding to the historical user are queried, and the user type, risk type and score level of the user are determined based on the first attribute information and the second attribute information corresponding to the user identifier, so as to calculate the similarity between the historical user and the user.

[0141] It should be understood that the manner of implementing the embodiments of the present invention is different from the Figure 1 Figure 2 or Figure 3 The method of the illustrated embodiment is the same and will not be repeated here.

[0142] In an embodiment of the present invention, different processing rules are set for different types of objects, and appropriate object prices are determined for users from different attribute perspectives, so that different users can purchase target objects at different prices to meet the purchasing needs of diverse users. At the same time, appropriate product prices can also be determined for users with higher risks to improve the accuracy of risk avoidance.

[0143] According to an embodiment of the present invention, the embodiment of the present invention further provides an electronic device and a readable storage medium.

[0144] The electronic device of an embodiment of the present invention comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the data processing method provided by the embodiment of the present invention.

[0145] Figure 5 An exemplary system architecture 500 is shown to which the data processing method or data processing device according to the embodiment of the present invention can be applied.

[0146] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0147] The user can use the terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages, etc. Various client applications can be installed on the terminal devices 501, 502, 503.

[0148] The terminal devices 501 , 502 , and 503 may be, but are not limited to, smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0149] The server 505 may be a server that provides various services. The server may analyze and process the received data such as the product information query request, and feed back the processing result (such as product information - just an example) to the terminal device.

[0150] It should be noted that the data processing method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the data processing device is generally disposed in the server 505 .

[0151] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0152] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 suitable for implementing an embodiment of the present invention. Figure 6 The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0153] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which 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 part 608 to a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0154] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 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, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0155] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0156] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0157] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a unit, a program segment, or a part of a code, and the above-mentioned unit, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0158] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a collection unit, a determination unit, and a generation unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the collection unit may also be described as a "unit of information collection function".

[0159] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device executes the data processing method provided by the present invention.

[0160] As another aspect, the present invention further provides a computer program product, including a computer program, which implements the data processing method provided by an embodiment of the present invention when the program is executed by a processor.

[0161] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data processing method, characterized in that: include: In response to a data processing request of a target object, a user identifier in the data processing request is obtained to call a preset collection engine to collect basic information, first attribute information, and second attribute information of the corresponding user; Querying the type policy of the target object from a database to match the target type through the basic information and determine the corresponding processing model, including: obtaining the object identifier of the target object to query the corresponding type policy from a database; matching the basic information with the type policy to obtain a basic rate that matches successfully, so as to determine the processing model corresponding to the basic rate; The method comprises: calculating 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, comprising: selecting the parameter values ​​of the preset first attribute parameter and the preset second attribute parameter in each preset time window from the first attribute information and the second attribute information to calculate the statistical values ​​of the preset first attribute parameter and the preset second attribute parameter; determining the statistical value of the preset first attribute parameter as the target value of the preset first attribute parameter, and determining the statistical value of the preset second attribute parameter as the target value of the preset second attribute parameter; determining a user type and a risk type of the user; Based on the first attribute information and the second attribute information, generating a rating feature vector of the user to input into a rating model to determine a rating level of the user; The processing model is called to determine the rate level of the user based on the user type, risk type and score level of the user to generate a price for the target object.

2. The method according to claim 1, characterized in that Generate a price for the target object, including: The basic rate is adjusted based on the rate level to obtain a price for the target object.

3. The method according to claim 1, characterized in that Before generating the scoring feature vector of the user based on the first attribute information and the second attribute information, the method further includes: Acquiring model training data to perform model training on the scoring model; Obtain the score value range of the trained score model input, and divide the score value range corresponding to each score level based on the preset level ratio; Calling a preset lift rate model to calculate the lift rates corresponding to each of the score data value intervals based on the model training data; In response to the improvement rate corresponding to each of the score data value intervals satisfying a preset condition, the score value interval corresponding to each score level is determined.

4. The method according to claim 1, characterized in that Before calculating target values ​​of the preset first attribute parameter and the preset second attribute parameter from the first attribute information and the second attribute information, the method includes: Acquire a first parameter value of the preset first attribute parameter from the first attribute information; In response to the first parameter value belonging to the first parameter value set, updating the preset first target value to a new first parameter value; Acquire a second parameter value of the preset second attribute parameter from the second attribute information; In response to the second parameter value belonging to a second parameter value set, the preset second target value is updated to a new second parameter value.

5. The method according to claim 1, characterized in that The step of querying the type strategy of the target object from the database includes: Acquire a historical user corresponding to the target object to query the corresponding basic information, first attribute information, and second attribute information to call a similarity model to calculate the similarity between the historical user and the user corresponding to the user identifier; In response to the similarity being greater than a preset threshold, obtaining a price of the target object corresponding to the historical user to determine the price of the target object; In response to the similarity being not greater than the preset threshold, querying the type strategy of the target object from a database.

6. The method according to claim 5, characterized in that Querying the corresponding basic information, the first attribute information, and the second attribute information to call a similarity model and calculate the similarity between the historical user and the user corresponding to the user identifier, including: The user type, risk type and score level corresponding to the historical user are queried, and the user type, risk type and score level of the user are determined based on the first attribute information and the second attribute information corresponding to the user identifier, so as to calculate the similarity between the historical user and the user.

7. A data processing device, characterized in that: include: A collection unit, used to respond to a data processing request of a target object, obtain a user identifier in the data processing request, call a preset collection engine, and collect basic information, first attribute information, and second attribute information of a corresponding user; A determination unit is used to query the type policy of the target object from a database to match the target type through the basic information and determine the corresponding processing model, including: obtaining the object identifier of the target object to query the corresponding type policy from the database; matching the basic information with the type policy to obtain a basic rate that matches successfully, so as to determine the processing model corresponding to the basic rate; The determination unit is further used to calculate the target values ​​of the preset first attribute parameter and the preset second attribute parameter in the first attribute information and the second attribute information, including: screening the parameter values ​​of the preset first attribute parameter and the preset second attribute parameter in each preset time window from the first attribute information and the second attribute information to calculate the statistical values ​​of the preset first attribute parameter and the preset second attribute parameter; determining the statistical value of the preset first attribute parameter as the target value of the preset first attribute parameter, and determining the statistical value of the preset second attribute parameter as the target value of the preset second attribute parameter; and determining the user type and 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 the scoring feature vector into a scoring model and determine the scoring level of the user; A generating unit is used to call the processing model, determine the rate level of the user based on the user type, risk type and scoring level of the user, so as to generate the price of the target object.

8. The device according to claim 7, characterized in that The generating unit is specifically used for: The basic rate is adjusted based on the rate level to obtain a price for the target object.

9. The device according to claim 7, characterized in that The determining unit is specifically configured to: Acquiring model training data to perform model training on the scoring model; Obtain the score value range of the trained score model input, and divide the score value range corresponding to each score level based on the preset level ratio; Calling a preset lift rate model to calculate the lift rates corresponding to each of the score data value intervals based on the model training data; In response to the improvement rate corresponding to each of the score data value intervals satisfying a preset condition, the score value interval corresponding to each score level is determined.

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

11. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images