Business processing method and apparatus, electronic device, and storage medium

Abstract

The application discloses a service processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. A specific embodiment of the method comprises: receiving a service processing request of a target user, obtaining scene data of a preset scene corresponding to the target user from a database; in response to the scene data meeting a preset condition, calling a data collection engine to collect target attribute information of the target user; calling a preset feature parameter model to determine a feature parameter value of the target user based on the target attribute information; calling a preset timing parameter model to determine a timing parameter matrix of the target user based on the target attribute information; inputting the timing parameter matrix and the feature parameter value into a preset calculation model to calculate a service quota corresponding to the target user, and performing service processing on the target user. The embodiment can solve the problem that the credit line is determined by expert experience, which is not only low in efficiency but also reduces accuracy.

Description

TECHNICAL FIELD

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

[0002] With the development of financial business, credit business covers more and more extensive, and the credit business processing of small and micro enterprises is also valued, especially for the first loan of small and micro enterprises, how to determine the credit line suitable for it becomes the key of credit business processing. Since the first loan of small and micro enterprises, it usually lacks data to support the determination of credit line, in the prior art, the credit line is usually determined by expert experience based on the data that the first loan enterprise can obtain, but this way depends too much on artificial experience, not only low efficiency, but also reduces accuracy. SUMMARY

[0003] Therefore, the embodiments of the present application provide a business processing method and device, electronic equipment and storage medium, which can solve the problem that the credit line is determined by expert experience, which is not only low efficiency, but also reduces accuracy.

[0004] To achieve the above object, according to one aspect of the embodiments of the present application, a business processing method is provided.

[0005] The business processing method of the embodiments of the present application comprises: receiving a business processing request of a target user, and acquiring scene data corresponding to a preset scene of the target user from a database; in response to the scene data meeting a preset condition, calling a data collection engine to collect target attribute information of the target user; calling a preset feature parameter model to determine a feature parameter value of the target user based on the target attribute information; calling a preset time sequence parameter model to determine a time sequence parameter matrix of the target user based on the target attribute information; inputting the time sequence parameter matrix and the feature parameter value into a preset calculation model to calculate a business limit corresponding to the target user, so as to process the business of the target user.

[0006] In one embodiment, the calculation model comprises a first calculation model and a second calculation model.

[0007] Inputting the time sequence parameter matrix and the feature parameter value into a preset calculation model to calculate the business limit corresponding to the target user comprises:

[0008] Inputting the time sequence parameter matrix into a preset first calculation model to calculate a predicted business limit corresponding to the target user.

[0009] The feature parameter value and the predicted business quota are spliced, and a preset second calculation model is input to obtain a target business quota of the target user.

[0010] In yet another embodiment, before the receiving of the business processing request of the target user, further comprising:

[0011] Screening model training users to obtain training attribute information of the model training users;

[0012] From the training attribute information, the repayment quota of each first preset period of the model training user within a preset time period is counted to determine the training target quota of the training user;

[0013] Based on the training attribute information, the feature parameter value of the model training user is determined, and the time sequence parameter matrix of the model training user is determined based on the training attribute information;

[0014] Based on the training target quota, the time sequence parameter matrix and the feature parameter value of the model training user, the established calculation model is trained to obtain a trained calculation model.

[0015] In yet another embodiment, the established calculation model includes a first calculation model and a second calculation model;

[0016] Based on the training target quota, the time sequence parameter matrix and the feature parameter value of the model training user, the established calculation model is trained, including:

[0017] The time sequence parameter matrix of the model training user is taken as the input of the first calculation model, the output of the first calculation model is spliced with the feature parameter value of the model training user to be taken as the input of the second credit model, and the training target quota is taken as the model training target to train the established calculation model.

[0018] In yet another embodiment, determining the training target quota of the training user includes:

[0019] According to the order of the repayment quota from large to small, the repayment quota of each first preset period is sorted, and the repayment quota located at a target position is determined as the training target quota of the training user.

[0020] In yet another embodiment, determining the feature parameter value of the target user based on the target attribute information includes:

[0021] Based on the target attribute information, the enterprise business parameter corresponding to the target user is obtained to count the first parameter value of the preset feature parameter;

[0022] obtain personal service parameters corresponding to the target user based on the target attribute information, to count a second parameter value of a preset characteristic parameter;

[0023] determine a larger value between the first parameter value and the second parameter value as a characteristic parameter value of the preset characteristic parameter.

[0024] In yet another embodiment, determining a timing parameter matrix of the target user based on the target attribute information comprises:

[0025] counting parameter values of each preset timing parameter in a second preset period from the target attribute information based on time sequence within a preset historical time length, to splice the parameter values and generate a corresponding timing parameter matrix.

[0026] In yet another embodiment, before the response to the scene data satisfying the preset condition, further comprising:

[0027] determining whether the scene data is empty;

[0028] If yes, it is determined that the scene data does not satisfy the preset condition; if no, it is determined that the scene data satisfies the preset condition.

[0029] A service processing device according to an embodiment of the application comprises: a receiving unit configured to receive a service processing request of a target user, and obtain scene data of a preset scene corresponding to the target user from a database; a collection unit configured to, in response to the scene data satisfying a preset condition, invoke a data collection engine to collect target attribute information of the target user; a determination unit configured to invoke a preset characteristic parameter model to determine a characteristic parameter value of the target user based on the target attribute information, and invoke a preset timing parameter model to determine a timing parameter matrix of the target user based on the target attribute information; and a calculation unit configured to input the timing parameter matrix and the characteristic parameter value into a preset calculation model, calculate a service quota corresponding to the target user, and perform service processing on the target user.

[0030] The calculation model comprises a first calculation model and a second calculation model.

[0031] The calculation unit is specifically configured to:

[0032] input the timing parameter matrix into a preset first calculation model to calculate a predicted service quota corresponding to the target user;

[0033] splice the characteristic parameter value and the predicted service quota, and input into a preset second calculation model to obtain a target service quota of the target user.

[0034] In yet another embodiment, the device further comprises:

[0035] a screening unit configured to screen a model training user to obtain training attribute information of the model training user;

[0036] The determination unit is further configured to count a repayment amount of the model training user in each first preset period within a preset time period from the training attribute information, to determine a training target amount of the model training user.

[0037] The determination unit is further configured to determine a feature parameter value of the model training user based on the training attribute information, and determine a time sequence parameter matrix of the model training user based on the training attribute information.

[0038] The apparatus further includes:

[0039] a training unit configured to train the established calculation model based on the training target amount, the time sequence parameter matrix and the feature parameter value of the model training user, to obtain a trained calculation model.

[0040] In yet another embodiment, the established calculation model includes a first calculation model and a second calculation model.

[0041] The training unit is specifically configured to:

[0042] splice the time sequence parameter matrix of the model training user as an input of the first calculation model, splice an output of the first calculation model and the feature parameter value of the model training user as an input of the second calculation model, and train the constructed calculation model with the training target amount as a model training target.

[0043] In yet another embodiment, the determination unit is specifically configured to:

[0044] sort the repayment amount of each first preset period in descending order of the repayment amount, and determine a repayment amount at a target position as the training target amount of the model training user.

[0045] In yet another embodiment, the determination unit is specifically configured to:

[0046] obtain an enterprise business parameter corresponding to the target user based on the target attribute information, to count a first parameter value of a preset feature parameter;

[0047] obtain a personal business parameter corresponding to the target user based on the target attribute information, to count a second parameter value of a preset feature parameter;

[0048] determine a larger value between the first parameter value and the second parameter value as a feature parameter value of a preset feature parameter.

[0049] In yet another embodiment, the determining unit is specifically configured to:

[0050] Based on the time sequence in the preset historical time length, the parameter values of each preset time sequence parameter in a second preset period are counted from the target attribute information to splice the parameter values and generate a corresponding time sequence parameter matrix.

[0051] In yet another embodiment, the determining unit is further configured to:

[0052] determine whether the scene data is empty;

[0053] If yes, it is determined that the scene data does not meet the preset condition; if no, it is determined that the scene data meets the preset condition.

[0054] To achieve the above object, according to a further aspect of embodiments of the present application, an electronic device is provided.

[0055] The electronic device of embodiments of the present application comprises one or more processors; a storage device configured to store 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 service processing method provided by embodiments of the present application.

[0056] To achieve the above object, according to a further aspect of embodiments of the present application, a computer readable medium is provided.

[0057] The computer readable medium of embodiments of the present application has a computer program stored thereon, and the program is executed by a processor to implement the service processing method provided by embodiments of the present application.

[0058] To achieve the above object, according to a further aspect of embodiments of the present application, a computer program product is provided.

[0059] The computer program product of embodiments of the present application comprises a computer program, and the program is executed by a processor to implement the service processing method provided by embodiments of the present application.

[0060] An embodiment of the above application has the following advantages or beneficial effects: in the embodiment of the application, after receiving a service processing request of a target user, whether a preset condition is met can be determined based on scene data of a preset scene corresponding to the target user, after the target user meets the preset condition, target attribute information of the user can be collected to determine a characteristic parameter value and a time sequence parameter matrix of the target user, and then the business quota can be calculated by inputting the calculation model, so as to process the business. In the embodiment of the application, after it is determined that the target user is a small and micro enterprise in the first loan based on the preset condition, the characteristic parameter value and the time sequence parameter matrix of the target user can be determined based on the target attribute information, and then the business quota, i.e., the credit quota, can be calculated. In this way, information is extracted from the target attribute information, and the credit quota is calculated in combination with the characteristic parameter and the time sequence parameter, so as to improve the accuracy of the credit quota calculation, and the credit quota model is constructed in advance to calculate the credit quota by the credit quota model, so as to improve the efficiency of the credit quota calculation.

[0061] Further effects of the above non-conventional optional mode will be described in the following in combination with the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0062] The accompanying drawings are used to better understand the application, and do not constitute undue limitations on the application. Among them:

[0063] Figure 1 is a schematic diagram of a main process of a service processing method according to an embodiment of the application;

[0064] Figure 2 is a schematic diagram of a main process of a calculation model construction method according to an embodiment of the application;

[0065] Figure 3 is a schematic diagram of another main process of a service processing method according to an embodiment of the application;

[0066] Figure 4 is a schematic diagram of main units of a service processing device according to an embodiment of the application;

[0067] Figure 5 is an exemplary system architecture diagram to which an embodiment of the application can be applied;

[0068] Figure 6 is a structural schematic diagram of a computer system suitable for implementing an embodiment of the application. DETAILED DESCRIPTION

[0069] Exemplary embodiments of the present application are described herein with reference to the accompanying drawings, which are cited by way of example only. Thus, it will be apparent to those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the spirit and scope of the application. Also, for the purpose of clarity and the brevity, the description below omits the description of well-known functions and structures.

[0070] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The acquisition, storage, use, processing, etc. of data in the technical solutions of the present application comply with the relevant provisions of national laws and regulations.

[0071] The embodiments of the present application provide a business processing method, which can be executed by a business processing system, as shown in Figure 1 The method comprises the following steps.

[0072] S101: receiving a business processing request of a target user, and acquiring scene data corresponding to a preset scene of the target user from a database.

[0073] The business processing request can be specifically a credit business processing request. The target user can be specifically an enterprise user, for example, a small and medium-sized enterprise. The credit processing request can be sent by the target user when applying for credit. After receiving the credit processing request, the user identifier of the target user can be acquired therefrom, and then the scene data corresponding to the preset scene of the target user can be acquired from the database. The preset scene can be set based on specific requirements and functions, for example, in the embodiments of the present application, the scene data is used to determine whether the target user is a first-credit user, and the first-credit user means that the user has not applied for credit in the industry, that is, there is no credit record in the database of the system, so the preset scene can be set as a credit application scene.

[0074] S102: in response to the scene data meeting a preset condition, calling a data collection engine to collect target attribute information of the target user.

[0075] The preset condition can be set based on requirements, for example, in the embodiments of the present application, the target user is determined to be a first-credit user, so the preset scene can be a credit application scene. In this step, whether the target user is a first-credit user can be determined by whether the acquired scene data is empty, that is, the preset condition is that the scene data is empty. If the acquired scene data is empty, it means that the user has not applied for credit, that is, there is no credit record, so it can be determined that the scene data meets the preset condition. If the acquired scene data is not empty, it means that the user has applied for credit, that is, there is a credit record, so it can be determined that the scene data does not meet the preset condition. Correspondingly, the target attribute can be specifically a credit attribute, so the target attribute information can be specifically credit information.

[0076] After determining that the scene data meets the preset condition, the target attribute information of the target data can be collected to calculate the business quota of the target user. In the embodiment of the application, taking the target attribute as credit investigation as an example, since the target user has no credit record, it is usually necessary to collect credit investigation information from an external system, so a data collection engine can be preset in the embodiment of the application to collect the credit investigation information of the target user from the external system by calling the data collection engine.

[0077] Specifically, the credit investigation information can include various types, for example, it can be a credit investigation report. The target user can be a small and medium-sized micro enterprise. In order to more accurately calculate the credit quota, the credit investigation information can include enterprise credit parameters of the enterprise, such as credit data, loan data, guarantee data, etc., and can also include personal credit parameters of the enterprise legal person, such as credit data, loan data, guarantee data, consumer loan data, credit card data, credit investigation query data, etc.

[0078] S103: calling a preset feature parameter model to determine a feature parameter value of the target user based on the target attribute information; and calling a preset time sequence parameter model to determine a time sequence parameter matrix of the target user based on the target attribute information.

[0079] The feature parameter model and the time sequence parameter model are both pre-constructed and trained, the feature parameter value represents a parameter value of a preset feature parameter, and the time sequence parameter matrix represents a matrix composed of parameter values of preset time sequence parameters.

[0080] In the embodiment of the application, it can be used for processing of credit business, and specifically for calculating the credit quota of the credit business, so in the embodiment of the application, taking the target attribute as credit investigation as an example, the preset feature parameters can include credit history labels (maximum credit amount, earliest credit time length, maximum credit amount, etc.), debt status labels (such as current total credit amount, current total credit balance, current overdue amount, etc., current total guarantee amount), loan behavior labels (such as total amount of newly added loans in the past 1 year, monthly total repayment amount in the past 1 year, etc.). Since the credit investigation information can include both enterprise credit parameters and personal credit parameters, the enterprise credit parameters corresponding to the target user can be obtained to count a first parameter value of the preset feature parameter, and the personal credit parameters corresponding to the target user can be obtained to count a second parameter value of the preset feature parameter, and then the larger value of the first parameter value and the second parameter value is determined as the feature parameter value of the preset feature parameter.

[0081] In the embodiment of the present application, based on the credit information of the target user, the preset timing parameter value counted in each second preset period within the preset historical time length can be obtained, so that the preset timing parameter value can reflect the credit change of the target user with respect to time. Specifically, the preset timing parameter can include: the number of transactions, the amount, the number of overdue transactions and the overdue amount of the loan parameter and the guarantee parameter of the enterprise corresponding to each second period, the number of transactions, the amount, the number of overdue transactions and the overdue amount of the loan parameter and the credit card parameter of the individual corresponding to each second period, the number of credit inquiries of the individual corresponding to each second period, the credit history length, the current loan number, the credit card number, the total amount of credit, the balance and the like of the individual and the enterprise. The second preset time period and the preset historical time length can be set based on the scene, for example, the second time period can be set to one month, and the preset historical time length can be set to 5 years, 2 years, etc.

[0082] In the embodiment of the present application, the corresponding historical time length can also be set based on different preset timing parameters, for example, for the number of transactions, the amount, the number of overdue transactions and the overdue amount of the loan parameter and the guarantee parameter of the enterprise corresponding to each second period, the historical time length can be set to 5 years; for the number of transactions, the amount, the number of overdue transactions and the overdue amount of the loan parameter and the credit card parameter of the individual corresponding to each second period, the historical time length can be set to 5 years; for the number of credit inquiries of the individual corresponding to each second period, the historical time length can be set to 2 years; the credit history length, the current loan number, the credit card number, the total amount of credit, the balance of the individual and the enterprise can not be set. Thus, taking the second time period set to one month as an example, based on the number of transactions, the amount, the number of overdue transactions and the overdue amount of the loan parameter and the guarantee parameter of the enterprise corresponding to each second period, 8 vectors of 1*60 can be obtained; based on the number of transactions, the amount, the number of overdue transactions and the overdue amount of the loan parameter and the guarantee parameter of the individual corresponding to each second period, 8 vectors of 1*60 can be obtained; based on the number of credit inquiries of the individual corresponding to each second period, 2 vectors of 1*20 can be obtained; based on the credit history length, the current loan number, the credit card number, the total amount of credit, the balance of the individual and the enterprise, 1 vector of 1*5 can be obtained. After obtaining the above vectors, that is, the parameter values of each preset timing parameter in the second preset period, the vectors are spliced to generate a timing parameter matrix.

[0083] It should be noted that when generating the timing parameter matrix, if the number of digits is insufficient, 0 can be used to fill in.

[0084] S104: inputting the timing parameter matrix and the feature parameter value into a preset calculation model to calculate the business limit corresponding to the target user, and performing business processing on the target user.

[0085] The business quota can be specifically a credit business credit quota, and the calculation model is pre-set and used to calculate the credit quota of the target user. Specifically, the calculation model in the embodiment of the application includes a first calculation model and a second calculation model. The first calculation model can take a time sequence parameter matrix as input and calculate a predicted business quota, and then splice the predicted business quota and a feature parameter value into an input parameter and input into the second calculation model to calculate a final business quota, i.e., a target credit quota. Thus, the target user's business can be processed based on the business quota.

[0086] In the embodiment of the application, the first calculation model can be an LSTM (Long Short Term Memory) model, which is a special recurrent neural network (RNN) capable of learning long-term rules, which has the form of a neural network repeating module chain and realizes protection and control of information flow vector state through a gate structure. The second credit model can be a TOBIT model, also known as a truncated regression model or a censored regression model, which is a model for the overall target variable to be approximately continuously distributed on the positive side, and contains a part of observation values with a positive probability of 0.

[0087] In the embodiment of the application, after determining that the target user is a small and micro enterprise in the first credit, the feature parameter value and the time sequence parameter matrix of the target user can be determined based on the target attribute information, and then the business quota, i.e., the credit quota, can be calculated. In this way, information is extracted from the target attribute information, and the credit quota is calculated in combination with the feature parameters and the time sequence parameters, thereby improving the accuracy of the credit quota calculation, and the credit quota model is pre-constructed to calculate the credit quota through the credit quota model, thereby improving the efficiency of the credit quota calculation.

[0088] Before step S101 is performed, the construction of the calculation model also needs to be completed. The construction method of the calculation model in the embodiment of the application will be specifically described below in combination with the embodiment shown in Figure 1 Figure 2 The method includes:

[0089] S201: Screening model training users to obtain training attribute information of the model training users.

[0090] The training attribute information represents attribute information used for model training. In the embodiment of the application, the training attribute information can be specifically credit investigation attribute information of the training users. The model training users can be users who have not performed credit, and the credit investigation information of the users is non-credit white household, i.e., users who have credit investigation information, so that the target quota of the business, i.e., the training target quota, can be calculated.

[0091] ​It should be noted that, since model training requires more sample data, multiple model training users can be screened in this step as training samples.

[0092] S202: From the training attribute information, the repayment amount of each first preset period of the model training user in the preset time period is counted to determine the training target amount of the training user.

[0093] The first preset period and the preset time period can be set based on the scene, for example, the preset time period can be the last year, and the first preset period can be one month. In this way, the repayment amount of each first preset period can be counted after the preset time period is divided according to the first preset period. Then the repayment amount of each first preset period can be sorted in order from small to large, so that the repayment amount at the target position can be determined as the training target amount of the training user. The target position can be the 6th position, so that the possibility that the training user can repay on time for 6 months can be improved, so as to reduce credit loss.

[0094] In the embodiment of the application, the repayment amount can be calculated based on the training credit information. Specifically, the loan parameters of the enterprise and / or the business loan parameters of the individual in the preset time period can be extracted from the training credit information in this step to count the repayment amount of each first preset period. If the training credit information does not include the loan parameters of the enterprise and the business loan parameters of the individual in the preset time period, the consumption loan and credit card records of the individual in the preset time period can be obtained to count the repayment amount of each first preset period.

[0095] S203: Determine the feature parameter value of the model training user based on the training attribute information, and determine the time sequence parameter matrix of the model training user based on the training attribute information.

[0096] The data processing principle in this step is the same as the corresponding data principle in step S103, and will not be repeated here. In this way, the feature parameter value and the time sequence parameter matrix of each model training user can be determined in this step.

[0097] S204: Based on the training target amount, the time sequence parameter matrix and the feature parameter value of the model training user, the established calculation model is trained to obtain the trained calculation model.

[0098] The established calculation model can include a first credit model and a second credit model. In this step, the time sequence parameter matrix of the model training user can be used as the input of the first calculation model, the output of the first calculation model can be spliced with the feature parameter value of the model training user to be used as the input of the second calculation model, and the training target amount can be used as the model training target to train the constructed calculation model.

[0099] In the embodiment of the present application, the calculation model is constructed in advance based on the training attribute information of the training user, so as to calculate the business quota of the target user through the calculation model, thereby improving the efficiency of business quota calculation.

[0100] In combination with the embodiment shown in Figure 1 and Figure 2 , the business processing method in the embodiment of the present application is specifically described, as shown in Figure 3 , the method comprises the following steps.

[0101] S301: receiving a business processing request of a target user, and obtaining scene data corresponding to a preset scene of the target user from a database.

[0102] S302: determining whether the scene data is empty; if yes, it is determined that the scene data does not meet the preset condition, and a prompt information is sent; if not, step S303 is executed.

[0103] S303: calling a data collection engine to collect target attribute information of the target user.

[0104] S304: based on the target attribute information, obtaining enterprise business parameters corresponding to the target user to count a first parameter value of a preset characteristic parameter; based on the target attribute information, obtaining personal business parameters corresponding to the target user to count a second parameter value of the preset characteristic parameter; and determining a larger value between the first parameter value and the second parameter value as a characteristic parameter value of the preset characteristic parameter.

[0105] S305: based on the time sequence in a preset historical time length, counting parameter values of each preset time sequence parameter in a second preset period from the target attribute information to splice the parameter values and generate a corresponding time sequence parameter matrix.

[0106] S306: inputting the time sequence parameter matrix into a preset first calculation model to calculate a predicted business quota corresponding to the target user.

[0107] S307: splicing the characteristic parameter value and the predicted business quota, and inputting into a preset second calculation model to obtain a target business quota of the target user, so as to process the target user.

[0108] It should be noted that the data processing principle in the embodiment of the present application is the same as the corresponding data processing principle in the embodiment shown in Figure 1 , which will not be repeated here.

[0109] In the embodiment of the present application, after the target user is determined to be a small and micro enterprise through the preset condition, the characteristic parameter value and the time sequence parameter matrix of the target user can be determined based on the target attribute information, and then the business limit, i.e., the credit limit, can be calculated. In this way, the information is extracted from the target attribute information, and the credit limit is calculated in combination with the characteristic parameter and the time sequence parameter, so as to improve the accuracy of the credit limit calculation. In addition, the credit limit model is constructed in advance, so that the credit limit is calculated through the credit limit model, thereby improving the efficiency of the credit limit calculation.

[0110] To solve the problems in the prior art, the embodiment of the present application provides a service processing device 400, as shown in the figure, which comprises: Figure 4

[0111] A receiving unit 401 is configured to receive a service processing request of a target user, and acquire scene data corresponding to a preset scene of the target user from a database.

[0112] A collecting unit 402 is configured to call a data collection engine to collect target attribute information of the target user in response to the scene data meeting a preset condition.

[0113] A determining unit 403 is configured to call a preset characteristic parameter model to determine a characteristic parameter value of the target user based on the target attribute information, and call a preset time sequence parameter model to determine a time sequence parameter matrix of the target user based on the target attribute information.

[0114] A calculating unit 404 is configured to input the time sequence parameter matrix and the characteristic parameter value into a preset calculation model, calculate a business limit corresponding to the target user, and perform service processing on the target user.

[0115] It should be understood that the manner of implementing the embodiment of the present application is the same as the manner of implementing the embodiment of the prior art, and thus will not be described here. Figure 1

[0116] In one embodiment, the calculation model comprises a first calculation model and a second calculation model.

[0117] The calculating unit 404 is specifically configured to:

[0118] input the time sequence parameter matrix into a preset first calculation model to calculate a predicted business limit corresponding to the target user;

[0119] splicing the characteristic parameter value and the predicted business limit, and inputting into a preset second calculation model to obtain a target business limit of the target user.

[0120] In another embodiment, the device 400 further comprises: ​​

[0121] a screening unit configured to screen a model training user to obtain training attribute information of the model training user;

[0122] The determination unit 403 is further configured to: count, from the training attribute information, a repayment amount of the model training user in each first preset period within a preset time period, to determine a training target amount of the model training user.

[0123] The determination unit 403 is further configured to: determine a feature parameter value of the model training user based on the training attribute information, and determine a time sequence parameter matrix of the model training user based on the training attribute information.

[0124] The apparatus 400 further includes:

[0125] a training unit configured to train the established calculation model based on the training target amount, the time sequence parameter matrix and the feature parameter value of the model training user, to obtain a trained calculation model.

[0126] In yet another embodiment, the established calculation model includes a first calculation model and a second calculation model.

[0127] The training unit is specifically configured to:

[0128] concatenate the time sequence parameter matrix of the model training user as an input of the first calculation model, and concatenate an output of the first calculation model and the feature parameter value of the model training user as an input of the second calculation model, to train the established calculation model with the training target amount as a model training target.

[0129] In yet another embodiment, the determination unit 403 is specifically configured to:

[0130] sort the repayment amount of each first preset period according to a descending order of the repayment amount, to determine a repayment amount located at a target position as the training target amount of the model training user.

[0131] In yet another embodiment, the determination unit 403 is specifically configured to:

[0132] obtain an enterprise business parameter corresponding to the target user based on the target attribute information, to count a first parameter value of a preset feature parameter;

[0133] obtain a personal business parameter corresponding to the target user based on the target attribute information, to count a second parameter value of a preset feature parameter;

[0134] determine a larger value between the first parameter value and the second parameter value as a feature parameter value of the preset feature parameter.

[0135] In yet another embodiment, the determining unit 403 is specifically configured to:

[0136] statistically determine parameter values of each preset timing parameter in a second preset period from the target attribute information based on time sequence in a preset historical time length, to splice the parameter values to generate a corresponding timing parameter matrix.

[0137] In yet another embodiment, the determining unit 403 is further configured to:

[0138] determine whether the scene data is empty;

[0139] if yes, determine that the scene data does not meet the preset condition; and if no, determine that the scene data meets the preset condition.

[0140] It should be understood that the manner of implementing the embodiments of the present application is the same as that of implementing the embodiments shown in Figure 1 、 Figure 2 or Figure 3 , which will not be described here.

[0141] In the embodiments of the present application, after determining that the target user is a small and micro enterprise in the first loan by the preset condition, the feature parameter value and the timing parameter matrix of the target user can be determined based on the credit information, and then the credit limit can be calculated. In this way, information extraction is performed from the credit information, and the credit limit is calculated in combination with the feature parameters and the timing parameters, thereby improving the accuracy of the credit limit calculation. Moreover, the credit limit model is constructed in advance, so that the credit limit is calculated through the credit limit model, thereby improving the efficiency of the credit limit calculation.

[0142] According to the embodiments of the present application, the embodiments of the present application further provide an electronic device and a readable storage medium.

[0143] The electronic device of the embodiments of the present application comprises at least one processor, and a memory communicatively connected with 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 to enable the at least one processor to execute the business processing method provided by the embodiments of the present application.

[0144] Figure 5 An exemplary system architecture 500 is shown, which can apply the business processing method or the business processing device of the embodiments of the present application.

[0145] As Figure 5As shown, the system architecture 500 can include terminal devices 501, 502, 503, a network 504 and a server 505. The network 504 is a medium for providing communication links between the terminal devices 501, 502, 503 and the server 505. The network 504 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0146] The users 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.

[0147] The terminal devices 501, 502, 503 can be, but are not limited to, smart phones, tablet computers, laptop computers and desktop computers, etc.

[0148] The server 505 can be a server providing various services, which can analyze and process received product information query requests, etc., and feed back the processing results (e.g. product information - just an example) to the terminal devices.

[0149] It should be noted that the service processing method provided by the embodiments of the present application is generally executed by the server 505, and correspondingly, the service processing apparatus is generally arranged in the server 505.

[0150] It should be understood that the number of terminal devices, networks and servers in the system architecture 500 is only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers. Figure 5

[0151] Reference will be made to Figure 6 which shows a structural schematic diagram of a computer system 600 suitable for implementing the embodiments of the present application. Figure 6 The computer system shown is only an example and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0152] As shown in Figure 6 , the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or programs loaded from a storage portion 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 through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0153] ​The following components are connected to the I / O interface 605: an input part 606 including a keyboard, a mouse, etc.; an output part 607 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage part 608 including a hard disk, etc.; and a communication part 609 including a network interface card such as a LAN card, a modem, etc. The communication part 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as necessary. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 610 as necessary, so that a computer program read out therefrom is installed in the storage part 608 as necessary.

[0154] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the methods illustrated by the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by 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-described functions defined in the system of the present disclosure are executed.

[0155] It should be noted that the computer-readable medium shown in the present application can 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, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer-readable storage media can 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component. In the present application, the computer-readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or component. The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0156] The flow diagrams and block diagrams in the drawings are schematic illustrations of possible architectures, functions and operations of systems, methods and computer program products in accordance with various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a 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 blocks can 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

[0157] The units described in the embodiments of the present application can be implemented by software, or by hardware. The units described can also be implemented in a processor, for example, a processor can be described as including a receiving unit, a collecting unit, a determining unit and a calculating unit. In some cases, the names of the units do not constitute a limitation on the units themselves, for example, the receiving unit can also be described as a unit with a request receiving function.

[0158] As another aspect, the present application also provides a computer readable medium, which can be included in the device described in the above embodiments, or can exist separately and not be assembled into the device. The computer readable medium carries one or more programs, which, when executed by the device, enable the device to perform the service processing method provided by the present application.

[0159] As another aspect, the present application also provides a computer program product, which includes a computer program, and the program, when executed by a processor, implements the service processing method provided by the embodiments of the present application.

[0160] The specific embodiments described above do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made depending on design requirements and other factors. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A service processing method characterized by, The method comprises: receiving a service processing request of a target user, and obtaining scene data corresponding to a preset scene of the target user from a database; in response to the scene data satisfying a preset condition, calling a data collection engine to collect target attribute information of the target user; and in response to the scene data not satisfying the preset condition, sending a prompt message; calling a preset feature parameter model to determine a feature parameter value of the target user based on the target attribute information, including: obtaining enterprise business parameters corresponding to the target user based on the target attribute information to count a first parameter value of a preset feature parameter; obtaining personal business parameters corresponding to the target user based on the target attribute information to count a second parameter value of the preset feature parameter; and determining a larger value between the first parameter value and the second parameter value as the feature parameter value of the preset feature parameter; calling a preset timing parameter model, setting a corresponding historical time length based on different preset timing parameters, positioning the target attribute information to obtain each preset timing parameter vector, and splicing each preset timing parameter vector to determine a timing parameter matrix of the target user; inputting the timing parameter matrix and the feature parameter value into a preset calculation model to calculate a business limit corresponding to the target user, so as to process the business of the target user.

2. The method of claim 1, wherein, The calculation model comprises a first calculation model and a second calculation model. Inputting the timing parameter matrix and the feature parameter value into a preset calculation model to calculate a business limit corresponding to the target user, including: inputting the timing parameter matrix into a preset first calculation model to calculate a predicted business limit corresponding to the target user; splicing the feature parameter value and the predicted business limit, and inputting them into a preset second calculation model to obtain a target business limit of the target user.

3. The method of claim 1, wherein, Before the receiving of the service processing request of the target user, the method further comprises: screening model training users to obtain training attribute information of the model training users; from the training attribute information, counting a repayment limit of each first preset period within a preset time period of the model training users to determine a training target limit of the training users; determining a feature parameter value of the model training users based on the training attribute information, and determining a timing parameter matrix of the model training users based on the training attribute information; training the established calculation model based on the training target limit, the timing parameter matrix and the feature parameter value of the model training users to obtain a trained calculation model.

4. The method of claim 3, wherein, The established calculation model comprises a first calculation model and a second calculation model. Training the established calculation model based on the training target limit, the timing parameter matrix and the feature parameter value of the model training users, including: inputting the timing parameter matrix of the model training users as an input of the first calculation model, splicing the output of the first calculation model and the feature parameter value of the model training users as an input of the second calculation model, and training the established calculation model with the training target limit as a model training target.

5. The method of claim 3, wherein, Determining the training target limit of the training users, including: The repayment amount of each first preset period is sorted in descending order of the repayment amount, and a repayment amount at a target position is determined as a training target amount of the training user.

6. The method of claim 1, wherein, The time sequence parameter matrix of the target user is determined based on the target attribute information, including: The parameter values of each preset time sequence parameter in a second preset period are counted from the target attribute information based on the time sequence in a preset historical time length, and the parameter values are spliced to generate a corresponding time sequence parameter matrix.

7. The method of claim 1, wherein, Before the step of responding to the scenario data satisfying a preset condition, the method further includes: determining whether the scenario data is empty; if not, determining that the scenario data does not satisfy the preset condition; if yes, determining that the scenario data satisfies the preset condition.

8. A service processing apparatus characterized by comprising: including: a receiving unit configured to receive a service processing request of a target user, and acquire scenario data of a preset scenario corresponding to the target user from a database; a collecting unit configured to, in response to the scenario data satisfying a preset condition, invoke a data collection engine to collect target attribute information of the target user; wherein, in response to the scenario data not satisfying the preset condition, send a prompt information; a determining unit configured to invoke a preset feature parameter model to determine a feature parameter value of the target user based on the target attribute information, including: acquiring enterprise business parameters corresponding to the target user based on the target attribute information to count a first parameter value of a preset feature parameter; acquiring personal business parameters corresponding to the target user based on the target attribute information to count a second parameter value of the preset feature parameter; determining a larger value between the first parameter value and the second parameter value as the feature parameter value of the preset feature parameter; invoking a preset time sequence parameter model, setting a corresponding historical time length based on different preset time sequence parameters, positioning target attribute information to obtain each preset time sequence parameter vector, splicing each preset time sequence parameter vector to determine a time sequence parameter matrix of the target user; a calculating unit configured to input the time sequence parameter matrix and the feature parameter value into a preset calculation model, calculate a business amount corresponding to the target user, and perform service processing on the target user.

9. The apparatus of claim 8, wherein, Further including: a screening unit configured to screen model training users to acquire training attribute information of the model training users; the determining unit is further configured to count repayment amounts of each first preset period of the model training users in a preset time period from the training attribute information to determine training target amounts of the training users; the determining unit is further configured to determine feature parameter values of the model training users based on the training attribute information, and determine time sequence parameter matrices of the model training users based on the training attribute information; the device further includes: a training unit configured to train a built calculation model based on the training target amounts, the time sequence parameter matrices and the feature parameter values of the model training users to obtain a trained calculation model.

10. The apparatus of claim 9, wherein, The built calculation model includes a first calculation model and a second calculation model; the training unit is specifically configured to: The time sequence parameter matrix of the model training user is taken as an input of a first calculation model, and an output of the first calculation model is spliced with a feature parameter value of the model training user to be taken as an input of a second credit model, so as to train the established calculation model with the training target quota as a model training target.

11. An electronic device, comprising: Comprising: 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, so that the one or more processors implement the method as claimed in any one of claims 1-7.

12. A computer readable medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method as claimed in any one of claims 1-7.

13. A computer program product comprising a computer program, characterized in that, The program is executed by the processor to implement the method as claimed in any one of claims 1-7. The program is executed by the processor to implement the method as claimed in any one of claims 1-7.

Images