A method, device and system for determining resource transfer limit

Abstract

The embodiments of this specification disclose a method, device and system for determining a resource transfer limit, the method comprising receiving a resource transfer processing request, the resource transfer processing request comprising an account identifier; obtaining first basic resource data and first evaluation data of an enterprise user identifier corresponding to the account identifier and second basic resource data and second evaluation data of an associated user identifier corresponding to the enterprise user identifier based on the account identifier; calculating a basic transfer quota based on the first basic resource data and the second basic resource data; determining a first adjustment coefficient based on the first evaluation data and the second evaluation data; and determining a second adjustment coefficient based on the loyalty of the enterprise user to the financial institution, etc. Then, the resource transfer limit of the resource transfer processing request can be determined based on the basic transfer quota, the first adjustment coefficient and the second adjustment coefficient, so as to reduce the risk of resource loss while improving business processing efficiency and customer satisfaction.

Description

Technical Field

[0001] The present specification relates to the field of computer data processing technology, and in particular, to a method, device and system for determining a resource transfer limit. Background Art

[0002] With the vigorous development of small and micro enterprises, the small and micro enterprise loan business is also growing rapidly. However, because the information of small and micro enterprises owned by financial institutions may be relatively limited, it is difficult for them to accurately assess the repayment ability of some small and micro enterprises. At present, manual comprehensive analysis of various data of users is mostly used to assess the risk of default, and then determine the upper limit of resource transfer for loan business processing to avoid the risk of resource loss of financial institutions. However, it is difficult to control the personal experience and quality requirements during manual evaluation, and the labor cost is high, and the efficiency of business processing is also low. Therefore, how to improve the efficiency of business processing and user satisfaction and reduce human resource costs while avoiding resource losses of financial institutions has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The purpose of the embodiments of this specification is to provide a method, device and system for determining a resource transfer limit, which can reduce the risk of resource loss while improving business processing efficiency and customer satisfaction.

[0004] This specification provides a method, device and system for determining a resource transfer limit, which are implemented in the following ways:

[0005] A method for determining a resource transfer limit, applied to a server, comprises: receiving a resource transfer processing request sent by a terminal device, wherein the resource transfer processing request comprises an account identifier; the account identifier is used to identify a resource receiving account corresponding to the resource transfer processing request. Based on the account identifier, first basic resource data and first evaluation data of an enterprise user identifier corresponding to the account identifier and second basic resource data and second evaluation data of an associated user identifier corresponding to the enterprise user identifier are obtained from a business system; wherein the associated user identifier is used to identify an associated user of the enterprise user identified by the enterprise user identifier; the associated user comprises a user whose influence on whether the enterprise user can repay the resource corresponding to the resource transfer processing request within a preset time meets preset requirements; the basic resource data comprises data for representing the amount of resources owned by the corresponding user; the evaluation data comprises data for representing the probability that the corresponding user can repay the resource corresponding to the resource transfer processing request within a preset time. The basic transfer quota corresponding to the resource transfer processing request is calculated based on the first basic resource data and the second basic resource data; the basic transfer quota refers to the upper limit value of the resource transfer amount used to represent the current repayment ability of the user. The first adjustment coefficient corresponding to the resource transfer processing request is evaluated according to the first evaluation data and the second evaluation data. The resource transfer limit of the resource transfer processing request is determined according to the basic transfer amount and the first adjustment coefficient.

[0006] In some other embodiments of the method provided in this specification, the first adjustment coefficient corresponding to the resource transfer processing request is evaluated according to the first evaluation data and the second evaluation data, including: judging whether there is preset type data under the enterprise user identifier; the preset type data includes data used to characterize the user's historical default probability. If it exists, the first evaluation data and the second evaluation data are input into the first risk identification model to obtain the default probability corresponding to the resource transfer processing request; wherein the first risk identification model is constructed based on the evaluation data of the enterprise user with preset type data and the associated user corresponding to the corresponding enterprise user as sample data. If it does not exist, the first evaluation data and the second evaluation data are input into the second risk identification model to obtain the default probability corresponding to the resource transfer processing request; wherein the first risk identification model is constructed based on the evaluation data of the enterprise user without preset type data and the associated user corresponding to the corresponding enterprise user as sample data. Determine the first adjustment coefficient of the resource transfer processing request according to the default probability.

[0007] In some other embodiments of the method provided in this specification, the first adjustment coefficient of the resource transfer processing request is determined according to the default probability, including: determining the risk level corresponding to the resource transfer processing request based on the default probability; the risk level is divided according to the default probability, bad debt rate, sample proportion and improvement rate; the sample proportion includes the proportion of the number of samples of the corresponding risk level to the total number of samples; the improvement rate is used to characterize the changing characteristics of the number of bad samples with the risk level; the bad sample refers to the resource transfer processing that has not been completed within the preset time. Taking the minimum total bad debt rate as the optimization goal, the first weight coefficient of the bad debt rate corresponding to each risk level is determined; wherein the bad debt rate is the ratio of the bad debt amount of the corresponding risk level to the total amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total amount is the sum of the basic transfer amounts of all samples under the corresponding risk level; the total bad debt rate is the sum of the bad debt rate corresponding to each risk level multiplied by the corresponding first weight coefficient. The determined first weight coefficient is used as the first adjustment coefficient corresponding to the resource transfer processing request.

[0008] In some other embodiments of the method provided in this specification, the method further includes: determining whether the enterprise user identifier has a specified type of historical resource transfer record in the business system. If it exists, the risk level corresponding to the resource transfer processing request is determined according to the first-level identification model; wherein the first-level identification model is constructed based on the first-level data corresponding to the enterprise user without the specified type of historical resource transfer record as sample data. If it does not exist, the risk level corresponding to the resource transfer processing request is determined according to the second-level identification model; wherein the second-level identification model is constructed based on the second-level data corresponding to the enterprise user with the specified type of historical resource transfer record as sample data. Taking the minimum total amount bad rate as the optimization goal, determine the second weight coefficient of the bad rate of the credit corresponding to each risk level; wherein the bad rate of the credit is the ratio of the bad debt amount of the corresponding risk level to the total amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total amount is the sum of the basic transfer amounts of the samples under the corresponding risk level; the total amount bad rate is the sum of the credit bad rate corresponding to each risk level multiplied by the corresponding second weight coefficient. The determined second weight coefficient is used as the second adjustment coefficient corresponding to the resource transfer processing request. The resource transfer limit of the resource transfer processing request is determined according to the basic transfer amount, the first adjustment coefficient and the second adjustment coefficient.

[0009] In some other embodiments of the method provided in this specification, the method further includes: obtaining a product resource transfer quota of a resource transfer product corresponding to the resource transfer processing request, comparing the product resource transfer quota with the resource transfer quota, and processing the resource transfer processing request according to the comparison result.

[0010] On the other hand, the embodiment of the specification also provides a resource transfer limit determination device, which is applied to a server, and includes: a data receiving module, which is used to receive a resource transfer processing request sent by a terminal device, wherein the resource transfer processing request includes an account identifier; the account identifier is used to identify the resource receiving account corresponding to the resource transfer processing request. A data acquisition module, which is used to acquire, from a business system based on the account identifier, first basic resource data and first evaluation data of the enterprise user identifier corresponding to the account identifier, and second basic resource data and second evaluation data of the associated user identifier corresponding to the enterprise user identifier; wherein the associated user identifier is used to identify the associated user of the enterprise user identified by the enterprise user identifier; the associated user includes a user whose influence on whether the enterprise user can repay the resource corresponding to the resource transfer processing request within a preset time meets the preset requirements; the basic resource data includes data used to characterize the amount of resources owned by the corresponding user; the evaluation data includes data used to characterize the probability that the corresponding user can repay the resource corresponding to the resource transfer processing request within a preset time. A basic quota determination module is used to calculate the basic transfer quota corresponding to the resource transfer processing request based on the first basic resource data and the second basic resource data; the basic transfer quota refers to the upper limit of the resource transfer amount used to characterize the current repayment ability of the user. A first coefficient determination module is used to evaluate the first adjustment coefficient corresponding to the resource transfer processing request based on the first evaluation data and the second evaluation data. A transfer quota determination module is used to determine the resource transfer limit of the resource transfer processing request based on the basic transfer quota and the first adjustment coefficient.

[0011] In some other embodiments of the method provided in this specification, the first coefficient determination module includes: a first judgment unit, which is used to judge whether there is preset type data under the enterprise user identifier; the preset type data includes data used to characterize the user's historical default probability. A first identification unit, which is used to input the first evaluation data and the second evaluation data into a first risk identification model if it exists, to obtain the default probability corresponding to the resource transfer processing request; wherein the first risk identification model is constructed based on the evaluation data of the enterprise user with preset type data and the associated user corresponding to the corresponding enterprise user as sample data. A second identification unit, which is used to input the first evaluation data and the second evaluation data into a second risk identification model if it does not exist, to obtain the default probability corresponding to the resource transfer processing request; wherein the first risk identification model is constructed based on the evaluation data of the enterprise user without preset type data and the associated user corresponding to the corresponding enterprise user as sample data. A first coefficient determination unit, which is used to determine the first adjustment coefficient of the resource transfer processing request according to the default probability.

[0012] In some other embodiments of the method provided in this specification, the first coefficient determination module further includes: a level determination unit, which is used to determine the risk level corresponding to the resource transfer processing request based on the default probability; the risk level is divided according to the default probability, bad debt rate, sample proportion and improvement rate; the sample proportion includes the proportion of the number of samples of the corresponding risk level to the total number of samples; the improvement rate is used to characterize the changing characteristics of the number of bad samples with the risk level; the bad sample refers to the resource transfer processing that has not been completed within the preset time. The first optimization unit is used to determine the first weight coefficient of the bad credit rate corresponding to each risk level with the minimum total credit rate as the optimization target; wherein the credit rate is the ratio of the bad debt amount of the corresponding risk level to the total credit under the corresponding risk level; the bad debt amount is the sum of the basic transfer credits of all bad samples under the corresponding risk level; the total credit is the sum of the basic transfer credits of all samples under the corresponding risk level; the total credit rate is the sum of the credit rate corresponding to each risk level multiplied by the corresponding first weight coefficient. The second coefficient determination unit is used to use the determined first weight coefficient as the first adjustment coefficient corresponding to the resource transfer processing request.

[0013] In some other embodiments of the method provided in this specification, the device also includes a second coefficient determination module, and the second coefficient determination module includes: a second judgment unit, used to judge whether there is a historical resource transfer record of a specified type for the enterprise user identifier in the business system. A third identification unit, used to determine the risk level corresponding to the resource transfer processing request according to the first-level identification model if it exists; wherein the first-level identification model is constructed based on the first-level data corresponding to the enterprise user for which there is no historical resource transfer record of the specified type as sample data. A fourth identification unit, used to determine the risk level corresponding to the resource transfer processing request according to the second-level identification model if it does not exist; wherein the second-level identification model is constructed based on the second-level data corresponding to the enterprise user for which there is a historical resource transfer record of the specified type as sample data. The second optimization unit is used to determine the second weight coefficient of the bad credit rate corresponding to each risk level with the minimum bad credit rate of the total credit limit as the optimization target; wherein the bad credit rate is the ratio of the bad debt amount of the corresponding risk level to the total credit limit under the corresponding risk level; the bad debt amount is the sum of the basic transfer credit limits of all bad samples under the corresponding risk level; the total credit limit is the sum of the basic transfer credit limits of the samples under the corresponding risk level; the total bad credit rate is the sum of the bad credit rates corresponding to each risk level multiplied by the corresponding second weight coefficient. The third coefficient determination unit is used to use the determined second weight coefficient as the second adjustment coefficient corresponding to the resource transfer processing request. The transfer credit determination module is also used to determine the resource transfer limit of the resource transfer processing request based on the basic transfer credit limit, the first adjustment coefficient and the second adjustment coefficient.

[0014] On the other hand, an embodiment of the present specification also provides a resource transfer limit determination system, the system comprising at least one processor and a memory for storing processor executable instructions, the instructions when executed by the processor implement the steps of the method described in any one or more of the above embodiments.

[0015] The resource transfer limit determination method, device and system provided in one or more embodiments of this specification preliminarily determine the basic transfer amount available to the enterprise user by further considering the amount of resources owned by the enterprise user itself and the amount of resources owned by the associated users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, the default probability of the enterprise user is determined based on the default probability assessment data of the above-mentioned enterprise users and users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, based on the default probability, an adjustment coefficient is quantitatively determined to adjust the basic upper limit, determine the final transfer limit of the enterprise user, and process the resource transfer processing request of the enterprise user based on the limit. Ensure that the enterprise user obtains a reasonable amount of resource transfer, while improving business processing efficiency and customer satisfaction, and effectively reduce the risk of resource loss of financial institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0017] Figure 1 A flowchart of an embodiment of a method for determining a resource transfer limit provided in this specification;

[0018] Figure 2 A flowchart of another resource transfer quota determination method embodiment provided in this specification;

[0019] Figure 3 This is an example schematic diagram of data used in risk level classification provided in some embodiments of this specification;

[0020] Figure 4 A schematic diagram of the module structure of a resource transfer limit determination device provided in this specification;

[0021] Figure 5 A schematic structural diagram of a server according to an exemplary embodiment of the present specification. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of the specification, not all of the embodiments. Based on one or more embodiments of the specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the embodiments of this specification.

[0023] In the embodiments of this specification, the resource may refer to currency, circulated and exchangeable articles, etc. Some resource transfer types may have certain risks when transferring, such as borrowing. Therefore, the lender (such as a financial institution) usually needs to evaluate the repayment ability of the borrower, determine the upper limit of the resources transferred to the borrower, and transfer resources to the lender within this limit to reduce the risk of resource loss caused by resource transfer. However, usually because the information of the borrower owned by the lender may be relatively limited, it is difficult to accurately evaluate the repayment ability of some borrowers, and thus it is difficult to accurately determine the upper limit of the resources transferred to the borrower. Especially for small business users who are currently developing rapidly, the resources they have are also relatively limited. If the upper limit of resources is determined only according to the amount of resources they have when borrowing, most of these users may not be able to borrow more resources, thereby affecting the development of such users. And the transaction volume of such users may also be less, making it difficult to accurately determine the risk of such users. If the upper limit is set too high, it may cause a greater risk of resource loss to the lender.

[0024] In order to avoid the risk of resource loss of financial institutions, currently, manual comprehensive analysis of various data of users is mostly used to assess the risk of default, and then determine the upper limit of resource transfer for loan business processing. However, manual evaluation requires personal experience and quality, which is difficult to control, and the labor cost is high, and the efficiency of business processing is also low. Therefore, how to improve the efficiency of business processing and user satisfaction and reduce human resource costs while avoiding the loss of financial institutions' resources has become a technical problem that needs to be solved urgently.

[0025] The embodiments of this specification preliminarily determine the basic transfer amount available to the enterprise user by considering the amount of resources owned by the enterprise user itself, and further considering the amount of resources owned by the associated users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, the default probability of the enterprise user is determined based on the default probability assessment data of the above-mentioned enterprise users and users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, based on the default probability, the adjustment coefficient is quantitatively determined to adjust the basic upper limit, determine the final transfer limit of the enterprise user, and process the resource transfer processing request of the enterprise user based on this limit. Ensure that the enterprise user obtains a reasonable amount of resource transfer, while improving business processing efficiency and customer satisfaction, and effectively reduce the risk of resource loss of financial institutions.

[0026] In an application scenario example of this specification, after receiving a resource transfer processing request sent by a terminal device, the server executing the resource transfer processing can obtain the basic resource data, transaction data, and basic enterprise information of the enterprise user corresponding to the account identifier from the business system of the financial institution based on the account identifier of the resource receiving account in the resource transfer processing request. At the same time, the basic resource data, transaction data, and basic enterprise information of the associated users of the enterprise user can also be obtained. After obtaining the above data, the server can evaluate the basic transfer amount and the risk of the enterprise user based on the above data to determine the resource transfer limit corresponding to this resource transfer processing request. Alternatively, the server can also determine whether the enterprise user belongs to an existing user, and further set a weight coefficient based on the judgment result to determine the resource transfer limit obtained by the enterprise user. The server can perform subsequent processing of this resource transfer processing request based on the determined resource transfer limit.

[0027] The business system may refer to a server cluster of a financial institution that performs deposit, withdrawal, and loan business processing and a database responsible for data storage, etc., or may also include a collaborative processing device between the server cluster and / or the database, etc. The server that performs resource transfer processing may be one or more servers in the server cluster of the business system.

[0028] The terminal device may include a business terminal of a financial institution or a client of a user. A business person of a financial institution may initiate a resource transfer processing request through a business terminal, or a user may also initiate a resource transfer processing request through a business terminal of a financial institution. Alternatively, a user may also initiate a resource transfer processing request through a resource transfer processing request access port in his / her terminal device (client), for example, through an application, a browser interface, or a small program, etc.

[0029] Figure 1It is a flow chart of an embodiment of the method for determining the resource transfer limit provided in this specification. Although this specification provides the method operation steps or device structure shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial merger based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments or drawings of this specification. When the method or module structure is applied in an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or drawings (for example, in an environment of parallel processors or multi-threaded processing, or even including distributed processing, server cluster implementation environment). A specific implementation example is Figure 1 As shown, in one embodiment of the resource transfer quota determination method provided in this specification, the method can be applied to the server that performs resource transfer processing, and the method can include the following steps:

[0030] S20: Receive a resource transfer processing request sent by a terminal device, wherein the resource transfer processing request includes an account identifier; the account identifier is used to identify a resource receiving account corresponding to the resource transfer processing request.

[0031] The server may receive a resource transfer processing request sent by a terminal device. The resource transfer type corresponding to the resource transfer processing request may be a resource transfer processing in which a target organization transfers resources to a resource receiving account and the resource receiving account repays the resource within a preset time. The resource transfer processing request may include an account identifier. The account identifier may be used to identify the resource receiving account.

[0032] S22: Based on the account identifier, first basic resource data and first evaluation data of the enterprise user identifier corresponding to the account identifier and second basic resource data and second evaluation data of the associated user identifier corresponding to the enterprise user identifier are obtained from the business system.

[0033] The association relationship between the account identifier and the user identifier may be preconfigured in the server. The user identifier may refer to information for identifying the user corresponding to each account. Accordingly, the server may obtain the enterprise user identifier corresponding to the account identifier from the business system, and then further obtain the data corresponding to the enterprise user identifier.

[0034] The enterprise user identifier may also be pre-associated with an associated user identifier. The associated user identifier may be used to identify the associated users of the enterprise user identified by the enterprise user identifier. The associated users may include users whose influence on whether the enterprise user can repay the resources corresponding to the resource transfer processing request within a preset time meets preset requirements. The associated users may be partners, shareholders or actual managers of the enterprise user, etc. The specific type of the associated user may be determined by the type of the enterprise user and the basic information of the enterprise user collected in advance by the business system. The associated user may be an enterprise-type user or an individual user. For small enterprises, the associated user in actual application scenarios is usually the actual controller of the enterprise user.

[0035] The business system or server may be pre-configured with the association relationship between the enterprise user identifier and the associated user identifier, and the association relationship may be described. Accordingly, if the business system is pre-configured with the association relationship between the enterprise user identifier and the associated user identifier, when the server sends a data acquisition request to the business system, it may simultaneously send a data request description of the associated user identifier corresponding to the enterprise user identifier. If the server is pre-configured with the association relationship between the enterprise user identifier and the associated user identifier, the server may directly send the enterprise user identifier and the corresponding associated user identifier to the business system.

[0036] The data requested by the server may include basic resource data, transaction data, basic user information, and user credit information of the user pre-stored in the business system. The business system may store user data generated or acquired by the financial institution itself. The acquired user data may include data collected from the user, or may include user data obtained from a third-party institution or an open source database.

[0037] In some embodiments, the data requested by the server may include basic resource data. The basic resource data may include data used to characterize the amount of resources owned by the corresponding user, so as to preliminarily evaluate the user's repayment ability. The basic resource data may include, for example, the user's asset data, income data, and liability data.

[0038] In some other embodiments, the data requested by the server may also include evaluation data. The evaluation data may include data used to characterize the probability that the enterprise user can repay the resources corresponding to the resource transfer processing request within a preset time. The evaluation data may include user basic data, transaction data, overdue data, external guarantees, enterprise credit information, enterprise provident fund, taxation and other information. The type of data used for risk assessment can be determined after optimization analysis of a large number of samples.

[0039] Correspondingly, the server may receive the first basic resource data and first evaluation data of the enterprise user corresponding to the account identifier and the second basic resource data and second evaluation data of the associated users of the enterprise user fed back by the business system.

[0040] S24: Calculate the basic transfer amount corresponding to the resource transfer processing request according to the first basic resource data and the second basic resource data; the basic transfer amount refers to the upper limit value of the resource transfer amount used to characterize the user's current repayment ability.

[0041] The server may calculate the basic transfer amount corresponding to the resource transfer processing request according to the first basic resource data and the second basic resource data. The basic transfer amount may refer to an upper limit value of the resource transfer amount used to characterize the current repayment ability of the user.

[0042] The server can obtain basic resource data of enterprise users and associated users corresponding to enterprise users from multiple dimensions. For example, annual income, average annual salary payment, average annual upstream loan, average annual electricity bill, average annual settlement amount, average annual agricultural subsidy amount, average annual accounts receivable, etc. can be obtained. Then, different weights can be assigned according to the importance of different dimensions to estimate the income, assets, and liabilities of enterprise users. In some embodiments, the following calculation model can be used to preliminarily determine the basic transfer amount of enterprise users: basic transfer amount = income + assets - liabilities.

[0043] In some implementations, the income amount can be estimated in the following manner:

[0044] Income = MAX{annual income, average annual wage payment (including housing provident fund), average annual upstream loan, average annual electricity bill, average annual medical insurance card payment, average annual government procurement contract amount, average annual settlement amount, average annual agricultural subsidy, average annual accounts receivable, lower limit of income}. That is, the income is equal to the maximum value of the above indicators. Of course, the above indicators are only examples for preferred explanations and do not constitute direct limitations. In actual applications, they can be flexibly configured according to the actual situation of corporate users.

[0045] Among them, the amount of agricultural subsidies can be calculated based on the corresponding subsidy amount for the planting varieties in the Nongxin Cloud Loan product, which is applicable to enterprises closely related to agricultural products. The annual average value of upstream loans is the loan amount paid to upstream suppliers, which is calculated from the amount of payment to upstream suppliers, and is applicable to supply chain-related enterprises. For enterprises that have a procurement and supply relationship with the government, the government procurement contract amount can be calculated based on the government procurement loan data. The specific calculation process of the government procurement contract amount is as follows: government procurement contract amount = procurement contract amount - corresponding advance payment - warranty deposit - other payments.

[0046] In some other implementations, each indicator may be assigned a corresponding weight coefficient to adjust the degree of influence of different indicators on the risk of resource transfer. The weight coefficient may be determined by analyzing sample data.

[0047] When determining the final transfer limit, the income amount is the main source of repayment for corporate users, so accurate assessment of the income amount is very important. By considering multi-dimensional indicators and the corresponding weights of each indicator, the characteristics of different corporate users and different scenarios can be fully considered, and the accuracy of corporate user income estimation can be further improved, thereby improving the accuracy of the final transfer limit determination.

[0048] In some other implementations, a lower limit of income may be further set to initialize the income when the above-mentioned type of data of a certain enterprise user is missing. The lower limit of income may be configured according to different enterprise user types. The specific value of the lower limit of income may be determined after analyzing a large number of samples.

[0049] In some embodiments, the asset amount may be determined by:

[0050] Asset amount = average daily deposit amount of corporate users within one year × A + average AUM of associated users within one year × B + total monthly mortgage payments of this bank within one year × C + total monthly mortgage payments of other banks within one year

[0051] Among them, A, B, and C are weight coefficients, and AUM is financial assets, which are used to adjust the importance of different indicators to resource transfer risks, which can be determined after a large number of sample analyses. Through the above method, financial assets, intangible assets, and fixed assets can all be included in the accounting scope, and the customer's asset situation can be examined more comprehensively.

[0052] In other embodiments, the debt amount may be determined in the following manner:

[0053] Liabilities = the total monthly mortgage payments of enterprise users in other financial institutions within one year + the total monthly loans of related users in other financial institutions other than mortgages within one year + the average monthly credit card usage of related users within one year. Liabilities accounting helps to further examine the current liabilities of enterprise users and can further accurately assess the risk of resource transfer.

[0054] By estimating the basic transfer amount based on the above three aspects, the estimated basic transfer amount can more accurately represent the actual repayment ability of corporate users, further improving the accuracy of resource transfer risk assessment.

[0055] S26: Determine a first adjustment coefficient corresponding to the resource transfer processing request according to the first evaluation data and the second evaluation data.

[0056] The server can determine the first adjustment coefficient corresponding to the resource transfer processing request based on the first evaluation data and the second evaluation data. The risk of this resource transfer is determined by further combining the evaluation data of the enterprise user and the preset associated user, and on this basis, the basic transfer amount is adjusted to ensure that the enterprise user obtains a transfer amount that matches its risk, and at the same time, the risk of resource loss of the financial institution can be effectively reduced.

[0057] In some implementations, the first adjustment coefficient can be determined by, for example, constructing a risk identification model. For example, the resource transfer processing that has not been completed within the preset time can be regarded as a bad sample, and the resource transfer processing that has been completed within the preset time can be regarded as a good sample. The first evaluation data and the second evaluation data of each sample are used as input data, and whether each sample is a good sample or a bad sample is used as output, that is, the result of whether the resource transfer processing finally defaults is used as the target output. The risk identification model is trained using a large amount of sample data to obtain a risk identification model. Then, the first evaluation data of the enterprise user corresponding to this resource transfer processing request and the second evaluation data of the associated user can be input into the trained risk identification model to obtain the default probability that the enterprise user of this resource transfer processing request may default. Then, the first adjustment coefficient of this resource transfer processing request can be determined based on the default probability. Among them, the algorithm corresponding to the risk identification model can adopt a variety of supervised learning algorithms. Of course, in actual application scenarios, the first adjustment coefficient corresponding to the resource transfer processing request can also be further evaluated in combination with the expert experience library, which is not limited here.

[0058] In actual application scenarios, small business users usually lack historical credit records, corporate credit data, and other preset types of data that intuitively represent the historical default probability of corporate users. It is difficult to accurately assess the default risk of such corporate users only through basic information of corporate users. In some embodiments, different risk identification models can be constructed based on whether corporate users have preset types of data, and then the risk identification of corresponding corporate users can be performed using the separately constructed risk identification models, thereby further improving the accuracy of corporate users' default risk identification.

[0059] In some embodiments, the risk level corresponding to the resource transfer processing request can be determined based on the default probability; the risk level is divided according to the default probability, bad debt rate, sample ratio and improvement rate; the sample ratio includes the proportion of the number of samples of the corresponding risk level to the total number of samples; the improvement rate is used to characterize the changing characteristics of the number of bad samples with the risk level; the bad sample refers to the resource transfer processing that has not been completed within the preset time. Taking the minimum total bad debt rate as the optimization goal, the first weight coefficient of the bad debt rate corresponding to each risk level is determined; wherein the bad debt rate is the ratio of the bad debt amount of the corresponding risk level to the total amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total amount is the sum of the basic transfer amounts of all samples under the corresponding risk level; the total bad debt rate is the sum of the bad debt rate corresponding to each risk level multiplied by the corresponding first weight coefficient. The determined first weight coefficient is used as the first adjustment coefficient corresponding to the resource transfer processing request.

[0060] In some implementations, the process of constructing a risk identification model is described by taking a logistic regression algorithm as an example. The quantitative formula for constructing a model using logistic regression can be expressed as:

[0061]

[0062] Where P represents the probability of default, x1, x2, ..., x n The input characteristic variables of the risk identification model with preset data types may include: the balance of normal corporate credit loans, total tax payment, number of personal credit inquiry agencies, average credit card usage in the past six months, etc. The input characteristic variables of the risk identification model without preset data types include: average daily balance of corporate deposits, customer level, credit limit of personal credit cards of associated users, etc. w1,w2,…,w n is the weight coefficient of each input feature variable. The model can be trained and tested through sample data to optimize w1, w2, ..., w n The value of .

[0063] In some implementations, after obtaining the default probability P, the risk score Score may be determined according to the following formula:

[0064]

[0065] Among them, the A and B values ​​are corresponding conversion coefficients, which are determined according to the required score span. The A and B values ​​can be determined in advance based on sample data.

[0066] Then, each risk score can be divided into risk levels. The risk levels can be divided according to the risk score, bad debt rate, sample ratio and improvement rate. The sample ratio includes the ratio of the number of samples of the corresponding risk level to the total number of samples. The bad debt rate represents the ratio of the number of bad samples to the total number of samples. The bad samples refer to overdue resource transfer processing requests. The improvement rate can be used to characterize the changing characteristics of the number of bad samples with the risk level. In some embodiments, the improvement rate corresponding to each risk level can be quantitatively determined in the following manner:

[0067]

[0068] In some implementations, the risk levels may be divided into the following five risk levels using the following classification criteria:

[0069] (1) The upper and lower limits of the score range for each risk level are multiples of 5;

[0070] (2) The number of samples of the five risk levels follows a normal distribution, that is, the number of samples of level C is the largest, followed by the number of samples of levels B and D, and the number of samples of levels A and E is the smallest;

[0071] (3) The score gap between the upper and lower limits of grades B, C, and D remains consistent;

[0072] (4) The promotion rates of the five levels A, B, C, D, and E increase in sequence.

[0073] Finally, they can be classified into risk levels as shown in Table 1. Table 1 shows an example table of risk levels.

[0074] Table 1

[0075] Risk Level Risk Scoring Bad debt rate Sample number ratio Improvement rate A (210,280] 0.152％ 0.2487 1.00 B (185,210] 0.223％ 0.2615 1.18 C (160,185] 0.385％ 0.3349 1.61 D (135,160] 0.611％ 0.1112 2.25 E (85,135] 1.040％ 0.0435 3.19

[0076] Then, the adjustment coefficient can be determined according to the risk level. Taking the minimum bad debt rate of the total amount as the optimization goal, determine the first weight coefficient of the bad debt rate of the amount corresponding to each risk level; wherein the bad debt rate is the ratio of the bad debt amount of each risk level to the total amount; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total amount is the sum of the basic transfer amounts of the samples under the corresponding risk level; the total bad debt rate is the sum of the bad debt rate of the amount corresponding to each risk level multiplied by the corresponding first weight coefficient. In some implementations, the above optimization goal can be processed using methods such as linear programming to obtain the adjustment coefficient corresponding to each risk level.

[0077] In some other embodiments, the above optimization objectives can be optimized by further limiting the constraints. Assume that the risk levels X1, X2, X3, X4, and X5, the total amount under each risk level, and the bad debt amount under each risk level are known. The optimization is performed according to the following constraints:

[0078] (1) The coefficients X1 to X5 decrease gradually;

[0079] (2) The difference between coefficients X1 to X5 is greater than or equal to 0.1;

[0080] (3) Coefficients X1 and X2 are greater than 1, and coefficients X3, X4, and X5 are less than 1;

[0081] (4) The sum of the quota ratios is 100%.

[0082] Among them, the proportion of the amount of risk level i is:

[0083]

[0084] In a specific scenario example, the final adjustment coefficients of different risk levels are shown in Table 2. Table 2 shows an example table of adjustment coefficients corresponding to each risk level.

[0085] Table 2

[0086] Risk Level The first adjustment factor A 1.2 B 1.1 C 1 D 0.9 E 0.8

[0087] In another specific scenario example, the risk level, adjustment coefficient, bad credit rate, and credit ratio finally calculated are shown in Table 3. Table 3 shows an example table of risk level, adjustment coefficient, bad credit rate, and credit ratio.

[0088] Table 3

[0089]

[0090]

[0091] S28: Determine the resource transfer limit of the resource transfer processing request according to the basic transfer quota and the first adjustment coefficient.

[0092] The server can determine the transfer limit of the resource transfer processing request based on the basic transfer quota and the first adjustment coefficient. For example, the basic transfer quota can be appropriately adjusted with reference to the first adjustment coefficient to obtain the resource transfer limit of the resource transfer processing request. Alternatively, the product of the first adjustment coefficient and the basic transfer quota can be used as the transfer limit of the resource transfer processing request. By quantifying the first adjustment coefficient in the above manner and using the first adjustment coefficient to constrain the basic transfer quota, the transfer limit obtained by corporate users with a lower probability of default can be increased, and the transfer limit of corporate users with a high probability of default can be reduced. At the same time, the overall bad credit rate is guaranteed to be the lowest, and the overall resource transfer loss risk of financial institutions is controlled.

[0093] The above embodiment preliminarily determines the basic transfer amount available to the enterprise user by further considering the amount of resources owned by the above enterprise user, based on the amount of resources owned by the associated users who have a certain impact on the repayment ability and risk of the enterprise user. Then, the risk of the enterprise user is determined based on the evaluation data of the above enterprise user and the evaluation data of the users who have a certain impact on the repayment ability and risk of the enterprise user. Then, the first adjustment system of the comprehensive assessment is used as a weight coefficient to adjust the basic transfer amount, determine the final transfer limit of the enterprise user, and process the enterprise user's resource transfer processing request within the limit, while ensuring that the enterprise user obtains a reasonable amount of resource transfer, effectively reducing the risk of resource loss of financial institutions.

[0094] Figure 2 Schematic diagram of the method for determining resource transfer quota provided in other embodiments of this specification. Figure 2 As shown, in some other embodiments, the method may further include:

[0095] S280: Determine whether the enterprise user identifier has a historical resource transfer record of a specified type in the business system;

[0096] S282: If yes, determine the risk level corresponding to the resource transfer processing request according to a first-level identification model; wherein the first-level identification model is constructed based on first-level data corresponding to enterprise users that do not have a historical resource transfer record of a specified type as sample data;

[0097] S284: If not, determining the risk level corresponding to the resource transfer processing request according to a second-level identification model; wherein the second-level identification model is constructed according to the second-level data corresponding to the enterprise user having a historical resource transfer record of a specified type as sample data;

[0098] S286: Taking the minimum bad debt rate of the total amount as the optimization goal, determine the second weight coefficient of the bad debt rate of the amount corresponding to each risk level; wherein the bad debt rate of the amount is the ratio of the bad debt amount of the corresponding risk level to the total amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total amount is the sum of the basic transfer amounts of the samples under the corresponding risk level; the total bad debt rate is the sum of the bad debt rates of the amount corresponding to each risk level multiplied by the corresponding second weight coefficient, and the determined second weight coefficient is used as the second adjustment coefficient corresponding to the resource transfer processing request.

[0099] S288: Determine the resource transfer limit of the resource transfer processing request according to the basic transfer amount, the first adjustment coefficient and the second adjustment coefficient.

[0100] In some embodiments, the second adjustment coefficient corresponding to the resource transfer processing request can be determined based on whether the user has a historical resource transfer record of a specified type in the business system, so as to further adjust and correct the basic transfer amount. The historical resource transfer record of the specified type may include a resource transfer record in which an enterprise user borrows resources from a current financial institution in the form of lending or financing. The first adjustment coefficient is obtained based on the quantification of the user's historical default probability, but for new users, due to the short cooperation time with the financial institution and the small amount of accumulated data, it is difficult to obtain comprehensive data, and the final transfer limit obtained through the above steps may be lower. For existing users, although there may be some overdue data, in view of their close cooperation with financial institutions and other reasons, it is also necessary to appropriately adjust the transfer resource limit to ensure the customer stickiness of the financial institution.

[0101] It is assumed that users with historical resource transfer records of the specified type are existing users, and users without historical resource transfer records of the specified type are new users.

[0102] New users can be divided into different levels in the following ways:

[0103] Enterprise size: The size of an enterprise can be measured by revenue, and the enterprise size of new users can be divided into three levels: large-scale, medium-scale, and small-scale. The specific classification criteria can be determined based on the analysis of a large amount of sample data;

[0104] Industry: The industry to which the enterprise user belongs can be divided. For example, it can be divided into four categories: trade industry, manufacturing industry, service industry and other industries. The first three industries can basically cover the industry types of most small enterprises at present;

[0105] Region: The regions of enterprise users can be divided into six categories: North China (Beijing, Tianjin, Hebei, Shanxi, Inner Mongolia), Central China (Hubei, Hunan, Henan, Jiangxi), East China (Shandong, Jiangsu, Anhui, Zhejiang, Fujian, Shanghai), South China (Guangdong, Guangxi, Hainan), Southwest China (Sichuan, Yunnan, Guizhou, Tibet, Chongqing), Northwest China (Ningxia, Xinjiang, Qinghai, Shaanxi, Gansu), Northeast China (Liaoning, Jilin, Heilongjiang);

[0106] Years of operation: Corporate users can be divided into three categories based on their years of operation: short operating years, medium operating years, and long operating years.

[0107] The existing users can be divided into different levels in the following ways:

[0108] Contribution: The contribution of enterprise users is divided according to their average monthly financial assets in the current financial institution. It can be divided into 5 levels. According to the order of the average monthly assets of the enterprise, it is divided into 5 levels from low to high, namely, A level with extremely low contribution, B level with relatively low contribution, C level with medium contribution, D level with relatively high contribution and E level with extremely high contribution;

[0109] Loyalty: According to the number of years of cooperation between the enterprise user and the current financial institution, it can be divided into five levels in order from low to high, namely, Level A with extremely low loyalty, Level B with relatively low loyalty, Level C with medium loyalty, Level D with relatively high loyalty, and Level E with extremely high loyalty;

[0110] Credit history length: The credit history length of a user can be obtained by subtracting the date of the first loan application from the date of the most recent loan application of the enterprise user at the current financial institution. The credit history length is divided into five levels in order of time length from low to high, namely, extremely short credit history length (level A), short credit history length (level B), medium credit history length (level C), long credit history length (level D), and extremely long credit history length (level E).

[0111] The second-level identification model can be constructed based on the second-level data corresponding to the new user as sample data. The first-level identification model can be constructed using the first-level data corresponding to the existing users as sample data. Then, it can be determined whether the enterprise user identifier has a historical resource transfer record of a specified type in the business system. If so, the risk level corresponding to the resource transfer processing request is determined based on the first-level identification model. If not, the risk level corresponding to the resource transfer processing request is determined based on the second-level identification model.

[0112] In some implementation scenario examples, the above stratification indicators can be divided into six levels, with the risk levels decreasing in order, namely high risk 1, high risk 2, medium risk 3, medium risk 4, low risk 5, and low risk 6. The specific stratification method can be as follows: Figure 3 Of course, the above-mentioned hierarchical division method is only a preferred example and does not constitute a direct limitation on the embodiments of this specification.

[0113] Then, the second weight coefficient of the non-performing rate of the credit line corresponding to each risk level can be determined with the minimum non-performing rate of the total credit line as the optimization goal; wherein the non-performing rate of the credit line is the ratio of the bad debt amount of the corresponding risk level to the total credit line under the corresponding risk level; the bad debt amount is the sum of the basic transfer credit lines of all bad samples under the corresponding risk level; the total credit line is the sum of the basic transfer credit lines of the samples under the corresponding risk level; the total credit line non-performing rate is the sum of the non-performing rate of the credit line corresponding to each risk level multiplied by the corresponding second weight coefficient. The determined second weight coefficient is used as the second adjustment coefficient corresponding to the resource transfer processing request. After the adjustment of the second adjustment coefficient, users of the low-risk level can obtain a higher transfer limit after the adjustment of the second adjustment coefficient, and users of the high-risk level can appropriately reduce the transfer limit after the adjustment of the second adjustment coefficient. Thus, while ensuring that the overall loss of the financial institution is small, different types of users can finally obtain a more reasonable resource transfer limit.

[0114] In a scenario example, the second adjustment coefficients corresponding to different strata are shown in Table 4. Table 4 shows an example table of adjustment coefficients corresponding to each risk level.

[0115] Table 4

[0116] Risk Level Second adjustment factor Low risk 6 1.4 Low Risk 5 1.3 Medium risk 4 1.2 Medium risk 3 1.1 High Risk 2 0.95 High Risk 1 0.9

[0117] The server may determine the resource transfer limit of the resource transfer processing request according to the resource basic amount, the first adjustment coefficient, and the second adjustment coefficient.

[0118] In some embodiments, the transfer limit may be determined using the following model:

[0119] S=S0×M1×M2

[0120] Among them, S is the resource transfer quota, S0 is the basic transfer quota, M1 is the first adjustment coefficient, and M2 is the second adjustment coefficient.

[0121] The above embodiment further refines the risks based on the characteristics of different types of users, and then further adjusts the basic upper limit to determine the final transfer limit of the corporate user, which can effectively reduce the risk of resource loss of financial institutions while further ensuring the satisfaction of corporate users.

[0122] In some other embodiments, it is possible to determine whether the amount of resources requested to be transferred by the resource transfer processing request is greater than the determined resource transfer limit; if the determination result is negative, continue the resource transfer data processing corresponding to the resource transfer processing request; if the determination result is positive, feedback the determination result to the terminal device so that the terminal device can perform a display.

[0123] In some other embodiments, it is also possible to obtain the product resource transfer limit of the resource transfer product corresponding to the resource transfer processing request. The product resource transfer limit of each resource transfer product can be determined in advance by the server according to the resource transfer limit determination model of each resource product and stored in the business system. The server can obtain the product identifier of the resource transfer product corresponding to the resource transfer processing request, and obtain the corresponding product resource transfer limit from the business system according to the product identifier. Then, the server can compare the product resource transfer limit with the resource transfer limit, and process the resource transfer processing request according to the comparison result. Comparing the product resource transfer limit X and the resource transfer limit Y, if X < Y, then use X as the final resource transfer upper limit, and process the resource transfer processing request based on X; if X > Y, then use Y as the final resource transfer upper limit, and process the resource transfer processing request based on Y. By further combining the resource transfer limits of each product to determine the final resource transfer upper limit, the risk of resource loss of financial institutions can be further reduced.

[0124] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. Specifically, reference can be made to the description of the relevant processing-related embodiments above, and details will not be repeated here.

[0125] The specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0126] The resource transfer limit determination method provided in one or more embodiments of this specification preliminarily determines the basic transfer amount available to the enterprise user by further considering the amount of resources owned by the enterprise user itself and the amount of resources owned by the associated users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, the default probability of the enterprise user is determined based on the default probability assessment data of the above-mentioned enterprise users and users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, based on the default probability, an adjustment coefficient is quantitatively determined to adjust the basic upper limit, determine the final transfer limit of the enterprise user, and process the resource transfer processing request of the enterprise user based on the limit. Ensure that the enterprise user obtains a reasonable amount of resource transfer, while improving business processing efficiency and customer satisfaction, and effectively reduce the risk of resource loss of financial institutions.

[0127] Based on the resource transfer limit determination method described above, one or more embodiments of this specification also provide a resource transfer limit determination device. The device may include a system, software (application), module, component, server, etc. that uses the method described in the embodiments of this specification and is combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiments of this specification is as described in the following embodiments. Since the implementation scheme of the device to solve the problem is similar to the method, the implementation of the specific device in the embodiments of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceived. Specifically, Figure 4 A schematic diagram of the module structure of an embodiment of a resource transfer limit determination device provided in the specification is applied to a server, such as Figure 4 As shown, the device may include:

[0128] The data receiving module 102 may be used to receive a resource transfer processing request sent by a terminal device, wherein the resource transfer processing request includes an account identifier; the account identifier is used to identify a resource receiving account corresponding to the resource transfer processing request;

[0129] The data acquisition module 104 can be used to acquire, based on the account identifier, first basic resource data and first evaluation data of the enterprise user identifier corresponding to the account identifier and second basic resource data and second evaluation data of the associated user identifier corresponding to the enterprise user identifier from the business system; wherein the associated user identifier is used to identify the associated user of the enterprise user identified by the enterprise user identifier; the associated user includes a user whose influence on whether the enterprise user can repay the resources corresponding to the resource transfer processing request within a preset time meets the preset requirements; the basic resource data includes data used to characterize the amount of resources owned by the corresponding user; the evaluation data includes data used to characterize the risk of the corresponding user being able to repay the resources corresponding to the resource transfer processing request within the preset time;

[0130] The basic quota determination module 106 may be used to calculate the basic transfer quota corresponding to the resource transfer processing request according to the first basic resource data and the second basic resource data; the basic transfer quota refers to the upper limit value of the resource transfer amount used to characterize the current repayment ability of the user;

[0131] A first coefficient determination module 108, which may be used to determine a first adjustment coefficient corresponding to the resource transfer processing request according to the first evaluation data and the second evaluation data;

[0132] The transfer quota determination module 110 may be configured to determine the resource transfer quota of the resource transfer processing request according to the basic transfer quota and the first adjustment coefficient.

[0133] In some other embodiments, the first coefficient determination module 108 may include:

[0134] The first judgment unit may be used to judge whether there is preset type data under the enterprise user identifier; the preset type data refers to data used to characterize the user's historical default probability;

[0135] A first identification unit may be configured to input the first evaluation data and the second evaluation data into a first risk identification model, if any, to obtain a default probability corresponding to the resource transfer processing request; wherein the first risk identification model is constructed based on the evaluation data of the enterprise user having preset type data and the associated user corresponding to the corresponding enterprise user as sample data;

[0136] The second identification unit may be configured to input the first evaluation data and the second evaluation data into a second risk identification model to obtain a default probability corresponding to the resource transfer processing request if the first evaluation data and the second evaluation data do not exist; wherein the first risk identification model is constructed based on the evaluation data of the enterprise user for which the preset type of data does not exist and the associated user corresponding to the corresponding enterprise user as sample data;

[0137] The first coefficient determination unit may be configured to determine a first adjustment coefficient of the resource transfer processing request according to the default probability.

[0138] In some other embodiments, the first coefficient determination module 108 may further include:

[0139] The level determination unit may be used to determine the risk level corresponding to the resource transfer processing request based on the default probability; the risk level is divided according to the default probability, bad debt rate, sample ratio and improvement rate; the sample ratio includes the proportion of the number of samples of the corresponding risk level to the total number of samples; the improvement rate is used to characterize the variation characteristics of the number of bad samples with the risk level; the bad sample refers to the resource transfer processing that has not been completed within a preset time;

[0140] The first optimization unit can be used to determine the first weight coefficient of the credit bad rate corresponding to each risk level with the minimum total credit bad rate as the optimization target; wherein the credit bad rate is the ratio of the bad debt amount of the corresponding risk level to the total credit amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total credit amount is the sum of the basic transfer amounts of all samples under the corresponding risk level; the total credit bad rate is the sum of the credit bad rates corresponding to each risk level multiplied by the corresponding first weight coefficient;

[0141] The second coefficient determination unit may be configured to use the determined first weight coefficient as the first adjustment coefficient corresponding to the resource transfer processing request.

[0142] In some other embodiments, the apparatus may further include a second coefficient determination module, and the second coefficient determination module may include:

[0143] The second judgment unit may be used to judge whether the enterprise user identifier has a historical resource transfer record of a specified type in the business system;

[0144] A third identification unit may be configured to determine, if present, a risk level corresponding to the resource transfer processing request according to a first-level identification model; wherein the first-level identification model is constructed using first-level data corresponding to enterprise users for which no historical resource transfer records of a specified type exist as sample data;

[0145] The fourth identification unit may be used to determine the risk level corresponding to the resource transfer processing request according to the second-level identification model if it does not exist; wherein the second-level identification model is constructed according to the second-level data corresponding to the enterprise user having the historical resource transfer record of the specified type as the sample data;

[0146] The second optimization unit can be used to determine the second weight coefficient of the credit bad rate corresponding to each risk level with the minimum total credit bad rate as the optimization target; wherein the credit bad rate is the ratio of the bad debt amount of the corresponding risk level to the total credit amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total credit amount is the sum of the basic transfer amounts of the samples under the corresponding risk level; the total credit bad rate is the sum of the credit bad rates corresponding to each risk level multiplied by the corresponding second weight coefficient;

[0147] A third coefficient determination unit may be configured to use the determined second weight coefficient as a second adjustment coefficient corresponding to the resource transfer processing request;

[0148] The transfer quota determination module may also be configured to determine a resource transfer limit of the resource transfer processing request according to the basic transfer quota, a first adjustment coefficient, and a second adjustment coefficient.

[0149] It should be noted that the above-mentioned device may also include other implementations according to the description of the method embodiment. The specific implementation methods can refer to the description of the relevant method embodiment, and will not be described one by one here.

[0150] The resource transfer limit determination device provided in one or more embodiments of this specification preliminarily determines the basic transfer amount available to the enterprise user by further considering the amount of resources owned by the enterprise user itself and the amount of resources owned by the associated users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, the default probability of the enterprise user is determined based on the default probability assessment data of the above-mentioned enterprise users and users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, based on the default probability, an adjustment coefficient is quantitatively determined to adjust the basic upper limit, determine the final transfer limit of the enterprise user, and process the resource transfer processing request of the enterprise user based on the limit. Ensure that the enterprise user obtains a reasonable amount of resource transfer, while improving business processing efficiency and customer satisfaction, and effectively reduce the risk of resource loss of financial institutions.

[0151] The methods or devices described in the above embodiments provided in this specification can implement business logic through computer programs and record them on storage media, and the storage media can be read and executed by computers to achieve the effects of the solutions described in the embodiments of this specification. Therefore, this specification also provides a resource transfer limit determination device, including a processor and a memory storing processor executable instructions, and when the instructions are executed by the processor, the steps of the method described in any of the above embodiments are implemented.

[0152] The identity authentication device provided in the embodiments of this specification can be a computer terminal, a server or a similar computing device. Taking the server as an example, Figure 5 is a hardware structure block diagram of a server to which the embodiments of this specification are applied. Figure 5 As shown, the server 100 may include one or more (only one is shown in the figure) processors 200 (the processor 200 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 300 for storing data, and a transmission module 400 for communication functions. A person skilled in the art can understand that Figure 5 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 5 More or fewer components shown in the figure may also include other processing hardware, such as a database or multi-level cache, GPU, or other hardware with Figure 5 Show different configurations.

[0153] The memory 300 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the search method in the embodiment of the present invention. The processor 200 executes various functional applications and data processing by running the software programs and modules stored in the memory 300. The memory 300 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 300 may further include a memory remotely arranged relative to the processor 200, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0154] The transmission module 400 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission module 400 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 400 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0155] The storage medium may include a physical device for storing information, which is usually a medium that digitizes the information and then stores it in an electrical, magnetic or optical manner. The storage medium may include: a device that stores information in an electrical energy manner, such as various memories, such as RAM, ROM, etc.; a device that stores information in a magnetic energy manner, such as a hard disk, a floppy disk, a magnetic tape, a magnetic core memory, a magnetic bubble memory, a USB flash drive; a device that stores information in an optical manner, such as a CD or a DVD. Of course, there are other readable storage media, such as quantum memory, graphene memory, etc.

[0156] It should be noted that the above-mentioned device may also include other implementations according to the description of the method embodiment. The specific implementation methods can refer to the description of the relevant method embodiment, and will not be described one by one here.

[0157] The resource transfer limit determination device described in the above embodiment preliminarily determines the basic transfer amount available to the enterprise user by further considering the amount of resources owned by the enterprise user itself and the amount of resources owned by the associated users that have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, the default probability of the enterprise user is determined based on the default probability assessment data of the above-mentioned enterprise users and users that have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, based on the default probability, an adjustment coefficient is quantitatively determined to adjust the basic upper limit, determine the final transfer limit of the enterprise user, and process the resource transfer processing request of the enterprise user based on the limit. Ensure that the enterprise user obtains a reasonable amount of resource transfer, while improving business processing efficiency and customer satisfaction, and effectively reduce the risk of resource loss of financial institutions.

[0158] This specification also provides a resource transfer limit determination system, which can be a separate resource transfer limit determination system, and can also be applied in a variety of computer data processing systems. The system can be a separate server, or it can include a server cluster, system (including distributed system), software (application), actual operation device, logic gate circuit device, quantum computer, etc. that use one or more methods or one or more embodiments of this specification, and a terminal device combined with necessary implementation hardware. The resource transfer limit determination system can include a resource management system and a server, and the resource management system includes one or more business subsystems, wherein the resource management system can be used to send resource transfer data to the server; the server can include at least one processor and a memory storing computer executable instructions, and the processor implements the steps of the method described in one or more embodiments when executing the instructions; one or more business subsystems of the resource management system can be used to receive identification results, and manage and control accounts of the target monitoring account type.

[0159] It should be noted that the above-mentioned system may also include other implementation methods according to the description of the method or device embodiment. The specific implementation method can refer to the description of the relevant method embodiment, which will not be described one by one here.

[0160] The resource transfer limit determination system described in the above embodiment preliminarily determines the basic transfer amount available to the enterprise user by further considering the amount of resources owned by the enterprise user itself and the amount of resources owned by the associated users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, the default probability of the enterprise user is determined based on the default probability assessment data of the above-mentioned enterprise users and users who have a certain impact on the repayment ability and repayment probability of the enterprise user. Then, based on the default probability, an adjustment coefficient is quantitatively determined to adjust the basic upper limit, determine the final transfer limit of the enterprise user, and process the enterprise user's resource transfer processing request based on this limit. Ensure that the enterprise user obtains a reasonable amount of resource transfer, while improving business processing efficiency and customer satisfaction, and effectively reduce the risk of resource loss of financial institutions.

[0161] The embodiments of this specification are not limited to situations that must comply with standard data models / templates or the embodiments of this specification. Certain industry standards or slightly modified implementation plans based on the implementation described in the custom methods or embodiments can also achieve the same, equivalent or similar, or predictable implementation effects after deformation of the above-mentioned embodiments. The embodiments obtained by using these modified or deformed data acquisition, storage, judgment, processing methods, etc. can still fall within the scope of the optional implementation plans of this specification.

[0162] The systems, devices, modules or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions divided into various modules. Of course, when implementing one or more of the present specification, the functions of each module can be implemented in the same or more software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0163] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0164] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0165] One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0166] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, in the absence of contradiction, a person skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0167] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for determining a resource transfer limit, characterized in that: Applicable to servers, including: Receiving a resource transfer processing request sent by a terminal device, wherein the resource transfer processing request includes an account identifier; the account identifier is used to identify a resource receiving account corresponding to the resource transfer processing request; Based on the account identifier, first basic resource data and first evaluation data of the enterprise user identifier corresponding to the account identifier and second basic resource data and second evaluation data of the associated user identifier corresponding to the enterprise user identifier are obtained from the business system; wherein the associated user identifier is used to identify the associated users of the enterprise user identified by the enterprise user identifier; the associated users include users whose influence on whether the enterprise user can repay the resources corresponding to the resource transfer processing request within a preset time meets preset requirements; the basic resource data include data used to characterize the amount of resources owned by the corresponding user; the evaluation data include data used to characterize the probability that the corresponding user can repay the resources corresponding to the resource transfer processing request within a preset time; Calculating a basic transfer amount corresponding to the resource transfer processing request according to the first basic resource data and the second basic resource data; the basic transfer amount refers to an upper limit value of a resource transfer amount used to characterize the current repayment ability of the user; Determine a first adjustment coefficient corresponding to the resource transfer processing request according to the first evaluation data and the second evaluation data; Determining a resource transfer limit of the resource transfer processing request according to the basic transfer amount and a first adjustment coefficient; The determining, according to the first evaluation data and the second evaluation data, a first adjustment coefficient corresponding to the resource transfer processing request includes: Determine whether there is preset type data under the enterprise user identifier; the preset type data includes data used to characterize the user's historical default probability; If so, the first evaluation data and the second evaluation data are input into a first risk identification model to obtain the default probability corresponding to the resource transfer processing request; wherein the first risk identification model is trained based on the evaluation data of the enterprise user with preset type data and the associated user corresponding to the corresponding enterprise user as input data, and whether the enterprise user with preset type data and the associated user corresponding to the corresponding enterprise user complete the resource transfer processing of repayment within a preset time as output; If not, the first evaluation data and the second evaluation data are input into a second risk identification model to obtain the default probability corresponding to the resource transfer processing request; wherein the first risk identification model is trained based on the evaluation data of the enterprise user for which the preset type of data does not exist and the associated users corresponding to the corresponding enterprise user as input data, and whether the enterprise user for which the preset type of data does not exist and the associated users corresponding to the corresponding enterprise user complete the resource transfer processing of repayment within the preset time as output; The risk score Score of the resource transfer processing request is determined according to the default probability and the following formula: Among them, the A and B values ​​are the corresponding conversion coefficients; Determining a risk level of the resource transfer processing request according to the risk score, and determining a first adjustment coefficient of the resource transfer processing request based on the determined risk level; The first risk identification model and the second risk identification model are constructed by using logistic regression. The quantitative expression of the model constructed by using logistic regression is as follows: Where P represents the probability of default, x1, x2, ..., x n are the input feature variables, w1, w2, ..., w n is the weight coefficient of each input feature variable. The model is trained and tested through sample data to optimize w1, w2, ..., w n The value of .

2. The method according to claim 1, characterized in that The determining, according to the default probability, a first adjustment coefficient of the resource transfer processing request comprises: Determine the risk level corresponding to the resource transfer processing request based on the default probability; the risk level is divided according to the default probability, bad debt rate, sample ratio and improvement rate; the sample ratio includes the proportion of the number of samples of the corresponding risk level to the total number of samples; the improvement rate is used to characterize the variation characteristics of the number of bad samples with the risk level; the bad sample refers to the resource transfer processing that has not been completed within the preset time; Taking the minimum total credit bad rate as the optimization goal, determine the first weight coefficient of the credit bad rate corresponding to each risk level; wherein the credit bad rate is the ratio of the bad debt amount of the corresponding risk level to the total credit amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total credit amount is the sum of the basic transfer amounts of all samples under the corresponding risk level; the total credit bad rate is the sum of the credit bad rates corresponding to each risk level multiplied by the corresponding first weight coefficient; The determined first weight coefficient is used as a first adjustment coefficient corresponding to the resource transfer processing request.

3. The method according to claim 1, characterized in that The method further comprises: Determine whether the enterprise user identifier has a historical resource transfer record of a specified type in the business system; If so, determining the risk level corresponding to the resource transfer processing request according to a first-level identification model; wherein the first-level identification model is constructed using first-level data corresponding to enterprise users that do not have a historical resource transfer record of a specified type as sample data; If not, determining the risk level corresponding to the resource transfer processing request according to a second-level identification model; wherein the second-level identification model is constructed based on the second-level data corresponding to the enterprise users with historical resource transfer records of the specified type as sample data; Taking the minimum total credit bad rate as the optimization goal, determine the second weight coefficient of the credit bad rate corresponding to each risk level; wherein the credit bad rate is the ratio of the bad debt amount of the corresponding risk level to the total credit amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total credit amount is the sum of the basic transfer amounts of the samples under the corresponding risk level; the total credit bad rate is the sum of the credit bad rates corresponding to each risk level multiplied by the corresponding second weight coefficient; Using the determined second weight coefficient as a second adjustment coefficient corresponding to the resource transfer processing request; The resource transfer limit of the resource transfer processing request is determined according to the basic transfer amount, the first adjustment coefficient and the second adjustment coefficient.

4. The method according to claim 1, characterized in that: The method further comprises: Obtaining a product resource transfer quota of a resource transfer product corresponding to the resource transfer processing request; The product resource transfer limit is compared with the resource transfer limit, and the resource transfer processing request is processed according to the comparison result.

5. A resource transfer limit determination device, characterized in that: Applicable to servers, including: A data receiving module, configured to receive a resource transfer processing request sent by a terminal device, wherein the resource transfer processing request includes an account identifier; the account identifier is used to identify a resource receiving account corresponding to the resource transfer processing request; A data acquisition module, for acquiring, based on the account identifier, first basic resource data and first evaluation data of the enterprise user identifier corresponding to the account identifier and second basic resource data and second evaluation data of the associated user identifier corresponding to the enterprise user identifier from the business system; wherein the associated user identifier is used to identify the associated user of the enterprise user identified by the enterprise user identifier; the associated user includes a user whose influence on whether the enterprise user can repay the resources corresponding to the resource transfer processing request within a preset time meets preset requirements; the basic resource data includes data for characterizing the amount of resources owned by the corresponding user; the evaluation data includes data for characterizing the probability that the corresponding user can repay the resources corresponding to the resource transfer processing request within a preset time; A basic quota determination module, used to calculate the basic transfer quota corresponding to the resource transfer processing request according to the first basic resource data and the second basic resource data; the basic transfer quota refers to the upper limit value of the resource transfer amount used to characterize the current repayment ability of the user; A first coefficient determination module, configured to determine a first adjustment coefficient corresponding to the resource transfer processing request according to the first evaluation data and the second evaluation data; A transfer quota determination module, configured to determine a resource transfer quota of the resource transfer processing request according to the basic transfer quota and a first adjustment coefficient; The first coefficient determination module includes: A first judgment unit is used to judge whether there is preset type data under the enterprise user identification; the preset type data includes data used to characterize the user's historical default probability; a first identification unit, for inputting the first evaluation data and the second evaluation data into a first risk identification model, if any, to obtain a default probability corresponding to the resource transfer processing request; wherein the first risk identification model is trained based on the evaluation data of the enterprise user with preset type data and the associated user corresponding to the corresponding enterprise user as input data, and based on whether the enterprise user with preset type data and the associated user corresponding to the corresponding enterprise user complete the resource transfer processing of repayment within a preset time as output; A second identification unit is used for inputting the first evaluation data and the second evaluation data into a second risk identification model to obtain the default probability corresponding to the resource transfer processing request if the first evaluation data and the second evaluation data do not exist; wherein the first risk identification model is trained based on the evaluation data of the enterprise user for which the preset type of data does not exist and the associated users corresponding to the corresponding enterprise user as input data, and whether the enterprise user for which the preset type of data does not exist and the associated users corresponding to the corresponding enterprise user complete the resource transfer processing of repayment within a preset time as output; The first coefficient determination unit is used to determine the risk score Score of the resource transfer processing request according to the default probability and the following formula: Among them, the A and B values ​​are the corresponding conversion coefficients; Determining a risk level of the resource transfer processing request according to the risk score, and determining a first adjustment coefficient of the resource transfer processing request based on the determined risk level; The first risk identification model and the second risk identification model are constructed by using logistic regression. The quantitative expression of the model constructed by using logistic regression is as follows: Where P represents the probability of default, x1, x2, ..., x n are the input feature variables, w1, w2, ..., w n is the weight coefficient of each input feature variable. The model is trained and tested through sample data to optimize w1, w2, ..., w n The value of .

6. The device according to claim 5, characterized in that The first coefficient determination module also includes: A level determination unit, for determining the risk level corresponding to the resource transfer processing request based on the default probability; the risk level is divided according to the default probability, bad debt rate, sample ratio and improvement rate; the sample ratio includes the proportion of the number of samples of the corresponding risk level to the total number of samples; the improvement rate is used to characterize the variation characteristics of the number of bad samples with the risk level; the bad sample refers to the resource transfer processing that has not been completed within a preset time; The first optimization unit is used to determine the first weight coefficient of the credit bad rate corresponding to each risk level with the minimum total credit bad rate as the optimization target; wherein the credit bad rate is the ratio of the bad debt amount of the corresponding risk level to the total credit amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total credit amount is the sum of the basic transfer amounts of all samples under the corresponding risk level; the total credit bad rate is the sum of the credit bad rates corresponding to each risk level multiplied by the corresponding first weight coefficient; The second coefficient determination unit is used to use the determined first weight coefficient as the first adjustment coefficient corresponding to the resource transfer processing request.

7. The device according to claim 5, characterized in that The device also includes a second coefficient determination module, and the second coefficient determination module includes: A second judgment unit is used to judge whether the enterprise user identifier has a historical resource transfer record of a specified type in the business system; A third identification unit is used to determine the risk level corresponding to the resource transfer processing request according to a first-level identification model, if any; wherein the first-level identification model is constructed based on first-level data corresponding to enterprise users for which there is no historical resource transfer record of a specified type as sample data; a fourth identification unit, configured to determine the risk level corresponding to the resource transfer processing request according to a second-level identification model if it does not exist; wherein the second-level identification model is constructed according to the second-level data corresponding to the enterprise user having a historical resource transfer record of a specified type as sample data; The second optimization unit is used to determine the second weight coefficient of the credit bad rate corresponding to each risk level with the minimum total credit bad rate as the optimization target; wherein the credit bad rate is the ratio of the bad debt amount of the corresponding risk level to the total credit amount under the corresponding risk level; the bad debt amount is the sum of the basic transfer amounts of all bad samples under the corresponding risk level; the total credit amount is the sum of the basic transfer amounts of the samples under the corresponding risk level; the total credit bad rate is the sum of the credit bad rates corresponding to each risk level multiplied by the corresponding second weight coefficient; a third coefficient determination unit, configured to use the determined second weight coefficient as a second adjustment coefficient corresponding to the resource transfer processing request; The transfer quota determination module is further configured to determine a resource transfer limit of the resource transfer processing request according to the basic transfer quota, a first adjustment coefficient, and a second adjustment coefficient.

8. A resource transfer limit determination system, characterized in that: The system comprises at least one processor and a memory for storing processor-executable instructions, wherein the instructions implement the steps of the method according to any one of claims 1 to 4 when executed by the processor.

Images