Data processing method and device, equipment and storage medium

Abstract

The invention provides a data processing method and device, equipment and a storage medium, and can be applied to the technical field of data processing or the field of financial science and technology. The method comprises the following steps: in response to a request for acquiring credit quota data of a user, exporting an initial index set of the user from a database according to an identifier of the user; based on the relevance value between each index in the initial index set and a credit extension index, a credit extension characteristic index set is screened out from the initial index set, the credit extension index comprises a development potential index and a risk index, and the credit extension characteristic index set comprises a development potential index subset and a risk index subset; determining a development potential coefficient value and a risk coefficient value of the user based on the development potential index subset and the risk index subset; and generating credit granting quota data of the user based on the initial index set, the development potential coefficient value and the risk coefficient value.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology or financial technology, and in particular to a data processing method, device, equipment, storage medium and program product. Background Art

[0002] When banks use the credit system to process corporate users' credit business requests, the credit system is generally required to collect the corporate users' business data, assess the corporate users' credit risks based on their business data, and generate credit limit data based on the credit risk assessment results.

[0003] In the process of realizing the inventive concept of the present disclosure, the inventors found that the following problems generally exist in the related technologies: when the credit system processes credit business requests from various types of corporate users, although the business data of the corporate users is collected, the asset data in the business data is still the main factor in actually generating the credit limit data, which not only reduces the utilization rate of data resources, but also may lead to an increase in the risks of the credit business and reduce the security of the credit business. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a data processing method, apparatus, device, storage medium and program product.

[0005] According to one aspect of the present disclosure, a data processing method is provided, comprising: in response to a request for obtaining a user's credit limit data, exporting the user's initial indicator set from a database according to the user's identification; screening out a credit characteristic indicator set from the initial indicator set based on the correlation value between each indicator in the initial indicator set and the credit indicator, wherein the credit indicator includes a development potential indicator and a risk indicator, and the credit characteristic indicator set includes a development potential indicator subset and a risk indicator subset; determining the user's development potential coefficient value and risk coefficient value based on the development potential indicator subset and the risk indicator subset; generating the user's credit limit data based on the initial indicator set, the development potential coefficient value and the risk coefficient value.

[0006] According to an embodiment of the present disclosure, the above-mentioned initial indicator set includes a business indicator subset and a capital flow indicator subset; the above-mentioned generation of the credit limit data of the above-mentioned user based on the above-mentioned initial indicator set, the above-mentioned development potential coefficient value and the above-mentioned risk coefficient value includes: determining the credit limit base value of the above-mentioned user according to the above-mentioned business indicator subset, the above-mentioned development potential coefficient value and the above-mentioned risk coefficient value; determining the credit limit verification value of the above-mentioned user according to the above-mentioned capital flow indicator subset; when the above-mentioned development potential coefficient value of the above-mentioned user is greater than or equal to a preset threshold value, inputting the above-mentioned credit limit base value and the above-mentioned credit limit verification value into the credit limit function, and outputting the credit limit data of the above-mentioned user; when the above-mentioned development potential coefficient value of the above-mentioned user is less than the above-mentioned preset threshold value, setting the above-mentioned credit limit base value as the credit limit data of the above-mentioned user.

[0007] According to an embodiment of the present disclosure, the above-mentioned determination of the credit limit benchmark value of the above-mentioned user based on the above-mentioned business indicator subset, the above-mentioned development potential coefficient value and the above-mentioned risk coefficient value includes: extracting a first indicator queue characterizing the order revenue characteristics of the above-mentioned user and a second indicator queue characterizing the financial characteristic indicators of the above-mentioned user from the above-mentioned business indicator subset; inputting a first data queue corresponding to the above-mentioned first indicator queue into an order revenue function, and outputting the order revenue amount of the above-mentioned user within a first preset time period; inputting a second data queue corresponding to the above-mentioned second indicator queue into a financial characteristic function, and outputting the financial characteristic indicator value of the above-mentioned user; generating the credit limit benchmark value of the above-mentioned user based on the order revenue amount of the above-mentioned user within the above-mentioned first preset time period, the above-mentioned characteristic financial indicator value, the above-mentioned development potential coefficient value and the above-mentioned risk coefficient value.

[0008] According to an embodiment of the present disclosure, the order revenue function includes a first order revenue function and a second order revenue function. The first order revenue function is constructed based on the current order revenue amount of the user and the order revenue conversion rate of the user within the first preset time period. The second order revenue function is constructed based on the order revenue amount of the user within the second preset time period and the expected revenue growth rate of the user. The second preset time period is earlier than the first preset time period. The first data queue corresponding to the first indicator queue is input into the order revenue function, and outputting the order revenue amount of the user within the first preset time period includes: when the current order revenue amount and the order revenue conversion rate can both be received, the first data queue is input into the first order revenue function, and the order revenue amount of the user within the first preset time period is output; when at least one of the current order revenue amount and the order revenue conversion rate cannot be received, the first data queue is input into the second order revenue function, and the order revenue amount of the user within the first preset time period is output.

[0009] According to an embodiment of the present disclosure, the expected income growth rate of the above-mentioned user is constructed in the following manner: extracting the actual income growth rate of the above-mentioned user in the above-mentioned second preset time period, the industry average income growth rate of the above-mentioned user's industry, the income growth index type evaluation value of the above-mentioned user and the development stage indicator type evaluation value of the above-mentioned user from the above-mentioned first data queue; determining the life cycle coefficient value of the above-mentioned user based on the above-mentioned income growth indicator type evaluation value and the above-mentioned development stage indicator type evaluation value; calling the expected income growth rate function from the above-mentioned database; inputting the life cycle coefficient value of the above-mentioned user, the above-mentioned actual income growth rate and the above-mentioned industry average income growth rate into the above-mentioned expected income growth rate function, and outputting the expected income growth rate of the above-mentioned user.

[0010] According to an embodiment of the present disclosure, the above-mentioned financial characteristic function includes a first financial characteristic function and a second financial characteristic function, the above-mentioned first financial characteristic function is constructed based on the cost asset amount of the above-mentioned user, and the above-mentioned second financial characteristic function is constructed based on the total asset amount of the above-mentioned user; the above-mentioned second data queue corresponding to the above-mentioned second indicator queue is input into the financial characteristic function, and outputting the financial characteristic indicator value of the above-mentioned user includes: retrieving the sub-liability asset amount of the above-mentioned user within a third preset time period and the total liability asset amount of the above-mentioned user from the above-mentioned business class indicator subset; when the ratio of the above-mentioned sub-liability asset amount to the above-mentioned total liability asset amount is less than or equal to the preset ratio, the above-mentioned second data queue is input into the above-mentioned first financial characteristic function, and the financial characteristic indicator value of the above-mentioned user is output; when the ratio of the above-mentioned sub-liability asset amount to the above-mentioned total liability asset amount is greater than the preset ratio, the above-mentioned second data queue is input into the above-mentioned second financial characteristic function, and the financial characteristic indicator value of the above-mentioned user is output.

[0011] According to an embodiment of the present disclosure, the above-mentioned generation of the credit limit benchmark value of the above-mentioned user based on the order revenue amount of the above-mentioned user in the above-mentioned first preset time period, the above-mentioned characteristic financial indicator value, the above-mentioned development potential coefficient value and the above-mentioned risk coefficient value includes: reading the credit limit benchmark function from the above-mentioned database, wherein the above-mentioned credit limit benchmark function includes the first credit limit benchmark function; in the case where the above-mentioned user's initial indicator set represents that the above-mentioned user's income year is greater than or equal to n full years, performing the following operations, wherein n is an integer greater than 1; executing the first preset script to obtain the user's annual average value between the characteristic financial indicator value and the annual income amount of each year of the above-mentioned user; executing the second preset script to obtain the first industry average value between the sub-liability value and the characteristic financial indicator value of the industry where the above-mentioned user is located; inputting the order revenue amount in the above-mentioned first preset time period, the user's annual average value, the above-mentioned first industry average value, the above-mentioned development potential coefficient value and the above-mentioned risk coefficient value into the above-mentioned first credit limit benchmark function, and outputting the credit limit benchmark value of the above-mentioned user.

[0012] According to an embodiment of the present disclosure, the credit limit benchmark function also includes a second credit limit benchmark function; the generation of the credit limit benchmark value of the user according to the order revenue amount of the user within the first preset time period, the characteristic financial indicator value, the development potential coefficient value and the risk coefficient value also includes: when the initial indicator set of the user represents that the income year of the user is less than n full years, perform the following operations, wherein n is an integer greater than 1; extract the total assets of the user from the business indicator subset; execute a third preset script to obtain the second industry average value between the sub-liability value of the industry where the user is located and the total assets associated with the industry; input the total assets of the user, the second industry average value, the development potential coefficient value and the risk coefficient value into the second credit limit benchmark function, and output the credit limit benchmark value of the user.

[0013] According to an embodiment of the present disclosure, the above-mentioned determination of the development potential coefficient value and the risk coefficient value of the above-mentioned user based on the above-mentioned development potential indicator subset and the above-mentioned risk indicator subset includes: for the above-mentioned development potential coefficient value: calling the first weight function from the above-mentioned database; inputting the development potential data subset obtained after digitizing the above-mentioned development potential indicator subset into the above-mentioned first weight function to obtain a plurality of first initial weight values ​​corresponding to each of the plurality of development potential indicators in the above-mentioned development potential indicator subset; normalizing the plurality of the above-mentioned first initial weight values ​​to obtain a plurality of first target weight values; and obtaining the development potential coefficient value of the above-mentioned user based on the evaluation value of each of the above-mentioned development potential indicators and the above-mentioned first target weight value.

[0014] According to an embodiment of the present disclosure, the above-mentioned determination of the development potential coefficient value and the risk coefficient value of the above-mentioned user based on the above-mentioned development potential indicator subset and the above-mentioned risk indicator subset also includes: for the above-mentioned risk coefficient value: calling a second weight function from the above-mentioned database; inputting the risk data subset obtained after digitizing the above-mentioned risk indicator subset into the above-mentioned second weight function to obtain a plurality of second initial weight values ​​corresponding to each of the plurality of risk indicators in the above-mentioned risk indicator subset; normalizing the plurality of the above-mentioned second initial weight values ​​to obtain a plurality of second target weight values; and obtaining the risk coefficient value of the above-mentioned user based on the evaluation value of each of the above-mentioned risk indicators and the above-mentioned second target weight value.

[0015] According to an embodiment of the present disclosure, the above-mentioned subset of capital flow indicators includes the book value of the user, the preset business asset flow amount of the user, and the non-preset business asset flow amount of the user; the above-mentioned determination of the credit limit verification value of the user based on the above-mentioned subset of capital flow indicators includes: calling a limit verification function from the above-mentioned database; inputting the book value of the user, the preset business asset flow amount and the non-preset business asset flow amount of the user into the above-mentioned called limit verification function, and outputting the credit limit verification value of the user.

[0016] According to an embodiment of the present disclosure, multiple historical indicators are collected from the above-mentioned initial indicator set to obtain an initial historical indicator subset, wherein the above-mentioned historical indicators represent the historical business processing status of the above-mentioned user; data cleaning is performed on the above-mentioned multiple historical indicators in the above-mentioned initial historical indicator subset to obtain a target historical indicator subset; encoding processing is performed on the above-mentioned multiple historical indicators in the above-mentioned target historical indicator subset to obtain a numerical historical indicator subset; the above-mentioned numerical historical indicator subset and the numerical credit indicator are input into the information gain function, and a correlation value representing the correlation between each historical indicator and the credit indicator is output; a decision tree model is constructed according to the above-mentioned correlation value; and the above-mentioned credit feature indicator set is screened out from the above-mentioned target historical indicator subset according to the number of segmentations and the segmentation depth of the above-mentioned decision tree model. Another aspect of the present disclosure also provides a data processing device, including: an export module, used to respond to a request for obtaining a user's credit limit data, and export the initial indicator set of the user from a database according to the identifier of the user; a screening module, used to screen out a credit characteristic indicator set from the initial indicator set based on the correlation value between each indicator in the initial indicator set and the credit indicator, wherein the credit indicator includes a development potential indicator and a risk indicator, and the credit characteristic indicator set includes a development potential indicator subset and a risk indicator subset; a first determination module, used to determine the development potential coefficient value and the risk coefficient value of the user based on the development potential indicator subset and the risk indicator subset; a generation module, used to generate the credit limit data of the user based on the initial indicator set, the development potential coefficient value and the risk coefficient value.

[0017] Another aspect of the present disclosure also provides an electronic device, including: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned data processing method.

[0018] Another aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to execute the above-mentioned data processing method.

[0019] According to the data processing method, device, equipment, storage medium and program product provided by the embodiment of the present disclosure, the initial indicator set of the user is derived by responding to the request for obtaining the credit limit data; the development potential indicator subset and the risk indicator subset are screened out from the initial indicator set according to the correlation value between each indicator and the credit indicator; the development potential coefficient value and the risk coefficient value of the user are determined based on the above two subsets; and the credit limit data of the user is generated according to the initial indicator set, the development potential coefficient value and the risk coefficient value. Since in the process of generating the user limit data, the development potential indicator subset and the risk indicator subset are determined according to the initial indicator set of the user, and the development potential coefficient and the risk coefficient are determined. Since the development potential coefficient and the risk coefficient of the user are taken into account, the credit limit data of the user is no longer generated only according to the asset data of the user, and the utilization rate of the collected data resources is improved; and the credit limit data generated by the above method can provide a more comprehensive reference for the credit business, improve the security of the credit business, at least partially overcome the problems of low utilization rate of data resources and high risk of credit business in related technologies, and thus achieve the technical effect of improving the utilization rate of data resources and the security of credit business. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0021] Figure 1 The application scenario diagram of the data processing method, apparatus, device, storage medium and program product according to the embodiments of the present disclosure is schematically shown;

[0022] Figure 2 A flowchart schematically shows a data processing method according to an embodiment of the present disclosure;

[0023] Figure 3 A flowchart schematically shows a flow chart for generating credit limit data for a user;

[0024] Figure 4 A structural block diagram schematically shows a data processing device according to an embodiment of the present disclosure; and

[0025] Figure 5 A block diagram of an electronic device suitable for implementing a data processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0026] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0027] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0028] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0029] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0030] In the technical solution of the present invention, the user information involved (including but not limited to information of enterprise users, user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0031] Enterprises in scientific and technological innovation and strategic emerging industries have high technological content, rapid development, and great difficulty in risk assessment. The credit limit data generated by the investment and financing risk limit generation method of related technologies has a relatively limited reference role in determining the risk limits of such enterprises. Specifically, the generation method of related technologies mainly uses net assets as the base to generate credit limit data. High-tech enterprises are mostly start-ups or enterprises in the R&D investment stage with relatively small assets. The traditional generation method cannot generate credit limit data in a personalized manner, resulting in a low degree of intelligence in the generated credit limit data. Moreover, the operating characteristics of high-tech enterprises are inconsistent with those of traditional industries. The generation method of related technologies does not take into account the scientific research situation, market position, etc. of high-tech enterprises, resulting in unreasonable generation results.

[0032] In view of this, the embodiments of the present disclosure provide a data processing method, device, equipment, storage medium and program product, which combine the generation concept that fits the industry characteristics and financing characteristics of high-tech enterprises, expand the scope of application of generating credit limit data, generate credit limit data in a personalized way, and improve the intelligence level of generating credit limit data. Specifically, the data processing method includes: in response to a request for obtaining the credit limit data of a user, according to the user's identification, exporting the user's initial indicator set from the database; based on the correlation value between each indicator in the initial indicator set and the credit indicator, screening out a credit feature indicator set from the initial indicator set, wherein the credit indicator includes a development potential indicator and a risk indicator, and the credit feature indicator set includes a development potential indicator subset and a risk indicator subset; based on the development potential indicator subset and the risk indicator subset, determining the user's development potential coefficient value and risk coefficient value; based on the initial indicator set, the development potential coefficient value and the risk coefficient value, generating the user's credit limit data.

[0033] It should be noted that the data processing method and device determined in the embodiments of the present disclosure can be used in the field of data processing technology or the field of financial technology, and can also be used in any field other than the field of data processing technology or the field of financial technology. The embodiments of the present disclosure do not limit the application field of the determined data processing method and device.

[0034] Figure 1 The application scenario diagram of the data processing method, apparatus, device, storage medium and program product according to the embodiments of the present disclosure is schematically shown.

[0035] like Figure 1As shown, the application scenario 100 according to this embodiment may include a first focus device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0036] The user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send a request for obtaining the user's credit limit data, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as financial applications, credit limit generation applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0037] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0038] The server 105 may be a server that provides various services, such as a background management server (only as an example) that supports the request for obtaining the user's credit limit data sent by the user using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received request and other data, and feed back the processing results (such as the credit limit data generated according to the request, the obtained or generated web page, information, or data, etc.) to the terminal device.

[0039] It should be noted that the data processing method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the data processing device provided in the embodiment of the present disclosure can generally be set in the server 105. The data processing method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the data processing device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0040] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0041] The following will be based on Figure 1 The scene described by Figure 2-Figure 3 The data processing method of the disclosed embodiment is described in detail.

[0042] Figure 2 The flowchart of the data processing method according to the embodiment of the present disclosure is schematically shown.

[0043] like Figure 2 As shown, the data processing method of this embodiment may include operations S210 to S240.

[0044] In operation S210, in response to a request for obtaining credit limit data of a user, an initial indicator set of the user is derived from a database according to an identification of the user.

[0045] In operation S220, based on the correlation value between each indicator in the initial indicator set and the credit indicator, a credit characteristic indicator set is screened out from the initial indicator set, wherein the credit indicator includes a development potential indicator and a risk indicator, and the credit characteristic indicator set includes a development potential indicator subset and a risk indicator subset.

[0046] In operation S230 , based on the development potential index subset and the risk index subset, a development potential coefficient value and a risk coefficient value of the user are determined.

[0047] In operation S240, the credit limit data of the user is generated based on the initial indicator set, the development potential coefficient value, and the risk coefficient value.

[0048] According to the embodiments of the present disclosure, users may include enterprise users. For example, high-tech enterprise users, new technology enterprise users, etc., the characteristics of such enterprise users are generally that the enterprise establishment years are less than the preset age threshold, and most of them are start-ups or enterprises in the R&D investment stage. Optionally, the data processing method provided in the embodiments of the present disclosure can also be applied to enterprise users whose enterprise establishment years are greater than the preset age threshold and whose business processing models are relatively mature.

[0049] According to an embodiment of the present disclosure, the credit limit data may be the maximum credit limit that the bank is willing and allowed to provide to the user within the user's debt tolerance and the bank's own loss tolerance. Taking a loan transaction as an example, the credit limit may be the maximum amount of funds that the bank is allowed to provide to the user.

[0050] According to an embodiment of the present disclosure, the user's identification is used to obtain the user's initial indicator set. The user's identification may include the user's name field, the user's registration serial number in the bank, and the like.

[0051] According to an embodiment of the present disclosure, the initial indicator set is used to determine the credit limit data of the user. The initial indicator set may include a business indicator subset, a capital flow indicator subset, a user's income growth indicator, a user's growth stage indicator, etc. The business indicator subset may include financial indicators, transaction indicators, the industry type to which the user belongs, the user's market level, the user's R&D situation, etc.; the capital flow indicator subset may include the user's book asset amount, the user's preset business asset flow amount, the user's non-preset business asset flow amount, etc. Preset businesses include trading business, investment business, financing business, etc.

[0052] According to an embodiment of the present disclosure, the above-mentioned initial indicator set may be stored in a database so as to be exported according to the user's identification. In another embodiment, the above-mentioned initial indicators may also exist in one or more different databases. After responding to a user's request to obtain the user's credit limit data, multiple data may be exported from the one or more different databases according to the user's identification, and the initial indicator set may be generated according to the exported multiple data.

[0053] According to an embodiment of the present disclosure, the configuration purpose of the credit indicator is to determine the credit characteristic indicator set from the initial indicator set according to the correlation value, so as to obtain the user's development potential coefficient value and risk coefficient value. The correlation value can represent the influence degree value of each indicator in the initial indicator set on the user's development potential, or the influence degree value on the user's risk. The greater the influence degree value of each indicator on the user's development potential or risk, the greater the correlation value can be.

[0054] According to an embodiment of the present disclosure, the credit index may include a development potential index and a risk index. The credit feature index set may include a development potential index subset and a risk index subset. The development potential index subset may include at least one of the following: the enterprise user's gross profit margin, asset turnover rate, asset-liability ratio, scientific research results, credibility, industry level, environmental friendliness level, etc. Among them, the user's gross profit margin, asset turnover rate, and asset-liability ratio can be used as quantitative indicators, and scientific research results, credibility, industry level, environmental friendliness level, etc. can be used as qualitative indicators. These qualitative and quantitative indicators are used to evaluate the scientific and technological research and development of high-tech enterprises.

[0055] According to an embodiment of the present disclosure, the risk indicators in the risk indicator subset include at least one of the following: the user's credit rating, the user's category rating, the user's bank-enterprise cooperation situation, etc. Based on the above indicator subset, the user's risk coefficient value can be determined, and the risk coefficient can comprehensively reflect the bank's consideration of factors such as the user's risk preference, competitive strategy, and financing peer ratio.

[0056] According to an embodiment of the present disclosure, each development potential indicator in the development potential indicator subset may have an evaluation value and a weight, and a development potential coefficient value may be obtained according to the evaluation value and weight of each development potential indicator. Each risk indicator in the risk indicator subset may have an evaluation value and a weight, and a risk coefficient value may be obtained according to the evaluation value and weight of each risk indicator.

[0057] According to an embodiment of the present disclosure, based on the above-mentioned initial indicator set, development potential coefficient value and risk coefficient value, the user's credit limit data can be generated. In the process of generating the user's credit limit data, different credit limit functions can be used, and more fine-grained generation of credit limit data can be achieved based on the user's development potential coefficient value. For example, when the development potential coefficient value is greater than or equal to a preset threshold, the credit limit data can be generated using a first credit limit function, and when the development potential coefficient value is less than the preset threshold, the credit limit data can be generated using a second credit limit function different from the first credit limit function.

[0058] According to the embodiments of the present disclosure, according to the data processing method, apparatus, device, storage medium and program product provided by the embodiments of the present disclosure, the user's initial indicator set is derived by responding to a request for obtaining credit limit data; a development potential indicator subset and a risk indicator subset are screened out from the initial indicator set according to the correlation value between each indicator and the credit indicator; based on the above two subsets, the user's development potential coefficient value and risk coefficient value are determined; and the user's credit limit data is generated according to the initial indicator set, the development potential coefficient value and the risk coefficient value. Because in the process of generating the user's limit data, the development potential indicator subset and the risk indicator subset are determined according to the user's initial indicator set, and the development potential coefficient and the risk coefficient are determined. Since the user's development potential coefficient and risk coefficient are taken into consideration, the user's credit limit data is no longer generated only based on the user's asset data, thereby improving the utilization rate of the collected data resources; and the credit limit data generated by the above method can provide a more comprehensive reference for the credit business, thereby improving the security of the credit business, at least partially overcoming the problems of low utilization rate of related technical data resources and high risk of credit business, thereby achieving the technical effect of improving the utilization rate of data resources and the security of credit business.

[0059] Figure 3 The flowchart for generating the credit limit data of a user is schematically shown.

[0060] like Figure 3 As shown, the process of generating the user's credit limit data may include operations S2401 to S2404.

[0061] In operation S2401, a credit limit base value of a user is determined according to a subset of business indicators, a development potential coefficient value, and a risk coefficient value.

[0062] In operation S2402, the credit limit verification value of the user is determined based on the fund flow indicator subset.

[0063] In operation S2403, when the user's development potential coefficient value is greater than or equal to a preset threshold, the credit limit reference value and the credit limit verification value are input into the credit limit function, and the user's credit limit data is output.

[0064] In operation S2404, when the development potential coefficient value of the user is less than a preset threshold, the credit limit reference value is set as the credit limit data of the user.

[0065] According to an embodiment of the present disclosure, the credit limit base value can represent a reference value of a user's reasonable debt level. The credit limit verification value can represent the user's cash flow that can be used for debt transactions in a future period of time. For users whose development potential coefficient value is less than a preset threshold, the user's credit limit data can be the credit limit base value; for users whose development potential coefficient value is equal to the preset threshold, the user's credit limit data can be the maximum value between the credit limit base value and the credit limit verification value. The preset threshold is used to determine the credit limit function to be called according to the user's development potential coefficient, and the preset threshold can be adaptively adjusted according to actual needs.

[0066] According to an embodiment of the present disclosure, determining a user's credit limit benchmark value based on a business indicator subset, a development potential coefficient value, and a risk coefficient value may include the following operations: extracting a first indicator queue characterizing the user's order revenue characteristics and a second indicator queue characterizing the user's financial characteristic indicators from the business indicator subset; inputting a first data queue corresponding to the first indicator queue into an order revenue function, and outputting the user's order revenue amount within a first preset time period; inputting a second data queue corresponding to the second indicator queue into a financial characteristic function, and outputting the user's financial characteristic indicator value; generating a user's credit limit benchmark value based on the user's order revenue amount, characteristic financial indicator value, development potential coefficient value, and risk coefficient value within the first preset time period.

[0067] According to an embodiment of the present disclosure, inputting the first data queue corresponding to the first indicator queue into the order revenue function, and outputting the order revenue amount of the user within the first preset time period may include the following operations: when the current order revenue amount and the order revenue conversion rate are both received, inputting the first data queue into the first order revenue function, and outputting the order revenue amount of the user within the first preset time period; when at least one of the current order revenue amount and the order revenue conversion rate cannot be received, inputting the first data queue into the second order revenue function, and outputting the order revenue amount of the user within the first preset time period.

[0068] According to an embodiment of the present disclosure, the first indicator queue may include the user's current order revenue, the user's order revenue conversion within the first preset time period, the user's order revenue in the second preset time period, the user's expected income growth, the user's actual income growth in the second preset time period, the industry average growth of the user's industry, the user's income growth indicators, and the user's development stage indicators. The first data queue corresponding to the first indicator queue may be a specific value of the first indicator queue, such as the current order revenue amount, the user's order revenue conversion rate within the first preset time period, the user's order revenue amount in the second preset time period, the user's expected income growth rate, the user's actual income growth rate in the second preset time period, the industry average growth rate of the user's industry, the user's income growth indicator evaluation value, and the user's development stage indicator evaluation value.

[0069] According to an embodiment of the present disclosure, the order revenue function includes a first order revenue function and a second order revenue function, wherein the first order revenue function is constructed based on the current order revenue amount of the user and the order revenue conversion rate of the user in the first preset time period, and the second order revenue function is constructed based on the order revenue amount of the user in the second preset time period and the expected revenue growth rate of the user. The second preset time period is earlier than the first preset time period, for example, the first preset time period may refer to a time period within the next year from the moment of processing a request for obtaining user credit limit data. The second preset time period may refer to a time period within the past year from the moment of processing a request for obtaining user credit limit data.

[0070] According to an embodiment of the present disclosure, the current order may be an order currently in hand by the user.

[0071] According to the embodiments of the present disclosure, the order revenue amount of an enterprise user cannot be fully converted into the total assets amount of the enterprise user, and a portion of the cost assets amount may need to be deducted. Therefore, the order revenue conversion rate may refer to the conversion rate of the order revenue amount into the total assets amount, etc. The order revenue conversion rate can also be adjusted according to actual needs, such as the conversion rate of the order revenue conversion rate into the profit conversion rate, etc. The order revenue conversion rate of the user within the first preset time period is generally clearly stated by the user in the agreement for signing the order, or can be reasonably determined by the user based on the signed order agreement, and generally needs to be provided by the user.

[0072] In the process of determining the order revenue of the user in the first preset time period, it can be divided into the following two situations:

[0073] When the user is able to provide the user's current orders and the order revenue conversion rate for the next year, that is, when the server is able to receive the user's current orders and order revenue conversion rate, the first order function as described in formula (1) is used to input the current order revenue amount in the first data queue and the order revenue conversion rate of the user within the first preset time period into the first order function, and output the user's order revenue amount within the first preset time period.

[0074] I e =Current order amount × order revenue conversion rate in the next year (1)

[0075] Among them, I e Used to represent the order revenue of the output user in the first preset time period.

[0076] When the user is unable to provide the user's current orders and the order revenue conversion rate for the next year, that is, when the server is unable to receive the user's current orders and order revenue conversion rate, the second order function as described in formula (2) is used to input the order revenue amount of the users in the first data queue in the second preset time period and the users' expected revenue growth rate into the second order function, and the order revenue amount of the users in the first preset time period is output.

[0077] I e =I o ×(1+g e ) (2)

[0078] Among them, I 0 It is used to represent the order income of the user in the second preset time period, g e Used to characterize the user's expected revenue growth rate.

[0079] According to an embodiment of the present disclosure, a user's expected income growth rate is constructed in the following manner: extracting the user's actual income growth rate in a second preset time period, the industry average income growth rate of the user's industry, the user's income growth indicator class evaluation value, and the user's development stage indicator class evaluation value from the first data queue; determining the user's life cycle coefficient value based on the income growth indicator class evaluation value and the development stage indicator class evaluation value; calling an expected income growth rate function from a database; inputting the user's life cycle coefficient value, actual income growth rate, and industry average income growth rate into the expected income growth rate function, and outputting the user's expected income growth rate.

[0080] According to an embodiment of the present disclosure, the user's income growth index, development stage index, and income growth index class evaluation value and development stage index class evaluation value may be as shown in Table 1.

[0081] Table 1

[0082]

[0083]

[0084] The user's life cycle coefficient value can be obtained through the process shown in formula (3):

[0085] a=income growth index evaluation value+development stage index value(3)

[0086] Wherein, a represents the user's life cycle coefficient value, and a is less than or equal to 1.

[0087] According to the embodiments of the present disclosure, the user's life cycle coefficient value can fully reflect the future growth differences of users at different development stages, thereby being more in line with the characteristics of high-tech enterprises and improving the accuracy of generating user credit limit data.

[0088] The expected income growth rate function can be shown as formula (4).

[0089] g e =a×g 0 +(1-a)×g 行业平均 (4)

[0090] Among them, g e It is used to represent the expected income growth rate of users, a represents the user's life cycle coefficient, and g 0 It is used to represent the actual income growth rate of the user in the second preset time period, g 行业平均It is used to characterize the average income growth rate of the industry in which the user is located. Specifically, if the user is a high-tech enterprise, the high-tech industry in which the user is located may include multiple high-tech enterprises. By averaging the income growth rate of each high-tech enterprise in this industry, the industry average income growth rate g can be obtained. 行业平均 .

[0091] According to the embodiments of the present disclosure, the order revenue amount of the user in the first preset time period is determined by dividing it into two situations. For users who can provide current orders and order revenue conversion rates and users who cannot provide current orders and / or order revenue conversion rates, different functions are used to determine the order revenue amount of the user in the first preset time period. This fully conforms to the characteristics of high-tech enterprises, improves the precision of generating the order revenue amount of the user in the first preset time period, and thus improves the accuracy of generating credit limit data.

[0092] According to an embodiment of the present disclosure, a second data queue corresponding to the second indicator queue is input into the financial characteristic function, and outputting the user's financial characteristic indicator value may include the following operations: retrieving the user's sub-liability asset amount and the user's total liability asset amount within a third preset time period from the business class indicator subset; when the ratio of the sub-liability asset amount to the total liability asset amount is less than or equal to the preset ratio, inputting the second data queue into the first financial characteristic function, and outputting the user's financial characteristic indicator value; when the ratio of the sub-liability asset amount to the total liability asset amount is greater than the preset ratio, inputting the second data queue into the second financial characteristic function, and outputting the user's financial characteristic indicator value.

[0093] According to an embodiment of the present disclosure, the financial characteristic function may include a first financial characteristic function and a second financial characteristic function, the first financial characteristic function being constructed based on the cost asset amount of the user, and the second financial characteristic function being constructed based on the total asset amount of the user.

[0094] According to an embodiment of the present disclosure, the second indicator queue may include the user's transaction costs, the user's taxes and surcharges, the user's sales expenses, the user's management expenses, the user's financial expenses, the user's R&D expenses, and the user's total assets. The second data queue may refer to data corresponding to the second indicator queue, such as the transaction cost amount, the user's taxes and surcharges, the user's sales expense value, the user's management expense value, the user's financial expense value, the user's R&D expense value, the user's total assets, etc.

[0095] According to an embodiment of the present disclosure, the sub-liability asset amount of the user in the third preset time period may refer to the user's long-term interest-bearing liability amount, and the user's total liability amount may refer to the sum of all the user's current interest-bearing liabilities, and the total liability amount is higher than the long-term interest-bearing liability amount. The third preset time period can be adaptively adjusted according to actual needs.

[0096] According to an embodiment of the present disclosure, the preset ratio is used to determine the financial characteristic function to be used from the first financial characteristic function and the second financial characteristic function, and the preset ratio can be adaptively adjusted according to actual needs.

[0097] In the process of determining the value of the user's financial characteristic indicator, it can be divided into the following two situations:

[0098] For users whose ratio between the sub-debt amount and the total debt amount is less than or equal to the preset ratio, or who have no interest-bearing debt, the financial characteristic indicator value of the user is determined according to the process shown in formula (5).

[0099] Financial characteristic indicator value = cost asset amount = transaction cost amount + tax and surcharge + sales expense value + management expense value + financial expense value + R&D expense value (5)

[0100] When the financial characteristic indicator value = cost asset amount, an upper limit value α can be generated to characterize That is, for After averaging, we can obtain .

[0101] According to an embodiment of the present disclosure, for users whose ratio between sub-liability amount and total liability amount is greater than a preset ratio, and for users whose cost asset amount is not suitable as a financial characteristic indicator, the user's financial characteristic indicator value can be determined according to the process shown in formula (6).

[0102] Financial characteristic index value = user's total assets (6)

[0103] When the financial characteristic indicator value = cost asset amount, an upper limit value β (β>α) can be generated to characterize The upper limit value of .

[0104] According to the embodiments of the present disclosure, the values ​​of the upper limit values ​​α and β mentioned above can be calculated by using a common artificial intelligence model based on historical user default information in the same manner as in the related art, which will not be described in detail here.

[0105] According to the embodiments of the present disclosure, the financial characteristic index values ​​of users are determined by dividing them into two situations. For users whose ratio between sub-debt amount and total debt amount is less than or equal to a preset ratio and users whose ratio is greater than the preset ratio, different functions are used to determine the financial characteristic index values ​​of users. This fully conforms to the characteristics of high-tech enterprises, improves the precision of the financial characteristic index values ​​of users, and thereby improves the accuracy of generating credit limit data.

[0106] According to the embodiments of the present disclosure, since the generation of credit limit data also needs to be based on the user's development potential coefficient value and risk coefficient value, the development potential coefficient value and the risk coefficient value are determined based on the development potential indicator subset and the risk indicator subset. The process of determining the development potential indicator subset and the risk indicator subset from the initial indicator set can be performed using a decision tree.

[0107] According to an embodiment of the present disclosure, operation S220 may include the following operations: collecting multiple historical indicators from an initial indicator set to obtain an initial historical indicator subset, wherein the historical indicators represent the user's historical business processing situation; performing data cleaning on multiple historical indicators in the initial historical indicator subset to obtain a target historical indicator subset; encoding multiple historical indicators in the target historical indicator subset to obtain a numerical historical indicator subset; inputting the numerical historical indicator subset and the numerical credit indicator into the information gain function, and outputting a correlation value representing the correlation between each historical indicator and the credit indicator; constructing a decision tree model based on the correlation value; and screening out a credit feature indicator set from the target historical indicator subset based on the number of segmentations and segmentation depth of the decision tree model.

[0108] According to the embodiment of the present disclosure, since the development potential coefficient value is a key indicator for generating the credit limit data of high-tech enterprises and the investment and financing risk limit of users, the embodiment of the present disclosure uses a decision tree method to screen the development potential indicators of users to ensure that the indicators obtained can affect the development potential of users to a large extent. The process of using a decision tree to screen indicators can be divided into the following operations.

[0109] Data collection: Collect various indicators from historical data of banks and users, such as financial indicators (such as debt-to-asset ratio), transaction indicators (such as gross profit margin), industry type, market position, R&D status, etc.

[0110] Data cleaning: Process missing values, outliers, and duplicate data to make the data set as complete and accurate as possible. For example, delete missing values, outliers, and duplicate data.

[0111] Data encoding: Convert categorical variables (such as industry type) into numerical data for use in decision tree algorithms.

[0112] Indicator selection: Select indicators related to user development potential by calculating information gain (IG), and exclude indicators with low correlation with development potential. After calculating the information gain of all indicators and the development potential indicator, select the indicator with the largest information gain for segmentation. If there are multiple indicators with the same information gain, you can select the indicator with the smallest conditional entropy, or use other feature selection methods (such as gain rate, Gini index, etc.) for comparison. In general, no matter which method is selected, the main purpose is to screen out indicators that can greatly affect user development potential. The correlation value between each indicator in the initial indicator set and the development potential indicator can be the information gain.

[0113] Decision tree construction: Build a decision tree based on the selected indicators and split the data set until the preset stopping condition is reached (when the number of samples of the child node is lower than the preset threshold, the segmentation stops).

[0114] Decision tree pruning: To avoid overfitting, you can remove unimportant branches in the decision tree through post-pruning or pre-pruning methods. Post-pruning can refer to pruning on an already generated overfit decision tree, and pre-pruning refers to stopping the growth of the decision tree in advance during the process of generating the decision tree. Compared with pre-pruning, post-pruning methods can usually obtain decision trees with stronger generalization capabilities, but the time cost is large.

[0115] Decision tree evaluation: After pruning the decision tree, the commonly used evaluation model methods in related technologies can be used to calculate evaluation indicators such as the accuracy and recall rate of the decision tree model to obtain the performance of the decision tree.

[0116] Important indicator screening: According to the information such as the number of splits and the depth of splits of each indicator in the decision tree, determine the indicators that have a greater impact on the user's development potential, and use the importance of the indicator as the indicator weight (the full score of the indicator). Use the process shown in formula (7) to determine the indicator weight of each indicator.

[0117]

[0118] Among them, I (feature) can represent the weight value of each indicator, i can represent the i-th indicator, n can represent the number of indicators, filtered_samples can represent the number of selected indicators, total_samples can represent the total number of indicators, IG (decision_node) can represent the information gain value of the decision node, and decision_node can represent the decision node.

[0119] Furthermore, the weight values ​​can be normalized so that the sum of all feature importance values ​​is 1.

[0120] Through this process, we screen out the key indicator of development potential that is suitable for banks to calculate user credit and enterprise investment and financing risk limits. Development potential indicators can include: gross profit margin, accounts receivable turnover rate, inventory turnover rate, asset-liability ratio, R&D status, scientific research results, market position, investor recognition, financing institution recognition, and green label. The above indicators are divided into quantitative indicators and qualitative indicators, and classified according to the actual meaning reflected by the indicators. The results are shown in Table 2.

[0121] Table 2

[0122]

[0123]

[0124] The same method as that used to obtain the development potential index is used to screen the initial index set, and the resulting risk index can be shown in Table 3.

[0125] Table 3

[0126]

[0127]

[0128] According to an embodiment of the present disclosure, determining the development potential coefficient value and the risk coefficient value of the user based on the development potential indicator subset and the risk indicator subset may include the following operations.

[0129] Regarding the development potential coefficient value: call the first weight function from the database; input the development potential data subset obtained after digitizing the development potential indicator subset into the first weight function to obtain multiple first initial weight values ​​corresponding to the multiple development potential indicators in the development potential indicator subset; normalize the multiple first initial weight values ​​to obtain multiple first target weight values; based on the evaluation value of each development potential indicator and the first target weight value, obtain the user's development potential coefficient value.

[0130] For the risk coefficient value: call the second weight function from the database; input the risk data subset obtained after digitizing the risk indicator subset into the second weight function to obtain multiple second initial weight values ​​corresponding to the multiple risk indicators in the risk indicator subset; normalize the multiple second initial weight values ​​to obtain multiple second target weight values; based on the evaluation value of each risk indicator and the second target weight value, obtain the user's risk coefficient value.

[0131] According to an embodiment of the present disclosure, the first weight function and the second weight function can both be functions as shown in formula (7), the difference being that the first weight function is used to determine the weight of each indicator in the development potential index, and the second weight function is used to determine the weight of each indicator in the risk index.

[0132] According to an embodiment of the present disclosure, the first initial weight value and the first target weight value are used to characterize the weight of each indicator in the development potential indicator, and the second initial weight value and the second target weight value are used to characterize the weight of each indicator in the risk indicator.

[0133] According to an embodiment of the present disclosure, the user development potential coefficient value may be the product of the evaluation value of each indicator shown in Table 2 and the weight of each indicator, and then the sum of them. For the quantitative indicators shown in Table 2, the evaluation value may be the value of the gross profit margin, accounts receivable turnover rate, inventory turnover rate, and debt-to-asset ratio itself. The evaluation value of the qualitative indicator may be an evaluation using an evaluation model, or an evaluation value obtained by manual evaluation by an expert. The user development potential coefficient value may be obtained by multiplying the evaluation value of each indicator by the weight of each indicator and then adding them together. The above process may be implemented by the computing engine of the server. The higher the development potential coefficient value, the higher the credit limit may be represented; the upper limit of the development potential coefficient value may be adjusted according to the actual business needs, for example, it may be geometrically amplified based on the initial value of 1, and raising the upper limit means that the user development potential has a greater impact on the credit limit.

[0134] According to an embodiment of the present disclosure, the process of obtaining a user risk coefficient value may be the same as the process of obtaining a user development potential coefficient value. The user risk coefficient value may be the product of the evaluation value of each indicator shown in Table 3 and the weight of each indicator and then added together. For example, each industry credit rating may correspond to a different evaluation value. When the user credit rating is the first level, the evaluation value corresponding to the first level is multiplied by the weight of the credit rating indicator within the bank to obtain a sub-risk coefficient value of the credit rating within the bank. By analogy, the user classification sub-risk coefficient value and the bank-enterprise cooperation situation sub-risk coefficient value are obtained. The level sub-risk coefficient value, the user classification sub-risk coefficient value, and the bank-enterprise cooperation situation sub-risk coefficient value are added together to obtain the user's risk coefficient value. It should be noted that the above-mentioned calculation process can be implemented using the server's computing engine.

[0135] According to the embodiments of the present disclosure, by determining the development potential coefficient, risk adjustment coefficient, and life cycle adjustment coefficient of an enterprise, the characteristics of high-tech enterprises can be fully considered, and the enterprise's scientific and technological research and development situation, the bank's risk preference for the user, competitive strategy, proportion of financing peers, future growth differences among customers at different development stages and other factors can be included in the process of generating credit limit data, so that credit limit data can be generated more accurately and reasonably.

[0136] According to an embodiment of the present disclosure, after determining the order revenue, characteristic financial indicator value, development potential coefficient value and risk coefficient value of the user in the first preset time period, a credit limit benchmark value of the user can be generated. Specifically, the following operations can be included: reading the credit limit benchmark function from the database, wherein the credit limit benchmark function includes the first credit limit benchmark function; in the case where the user's initial indicator set represents that the user's income year is greater than or equal to n full years, performing the following operations, wherein n is an integer greater than 1; executing the first preset script to obtain the user's annual average value between the characteristic financial indicator value and the annual income amount of each year of the user; executing the second preset script to obtain the first industry average value between the sub-liability value and the characteristic financial indicator value of the industry in which the user is located; inputting the order revenue, the user's annual average value, the first industry average value, the development potential coefficient value and the risk coefficient value in the first preset time period into the first credit limit benchmark function, and outputting the user's credit limit benchmark value.

[0137] According to an embodiment of the present disclosure, the first credit limit benchmark function may be as shown in formula (8).

[0138]

[0139] Among them, I e It can represent the order revenue amount of the user in the first preset time period. The user's annual average value between the characteristic financial indicator value and the annual income amount of each year obtained by executing the first preset script can be represented. The average value of the first industry obtained by executing the second preset script can be represented. For example, taking the industry including multiple high-tech computing enterprises as an example, by calculating the ratio between the total interest-bearing debt amount and the financial characteristic index of each high-tech enterprise in the industry, and then averaging the obtained multiple ratios, it can be obtained

[0140] According to an embodiment of the present disclosure, the credit limit benchmark function may also include a second credit limit benchmark function; generating a user's credit limit benchmark value based on the user's order revenue, characteristic financial indicator value, development potential coefficient value and risk coefficient value within a first preset time period may also include the following operations: when the user's initial indicator set represents that the user's income year is less than n full years, perform the following operations, where n is an integer greater than 1; extract the user's total assets from the business indicator subset; execute a third preset script to obtain a second industry average between the sub-liability value of the user's industry and the total assets associated with the industry; input the user's total assets, the second industry average, the development potential coefficient value and the risk coefficient value into the second credit limit benchmark function, and output the user's credit limit benchmark value.

[0141] According to an embodiment of the present disclosure, the second credit limit benchmark function may be as shown in formula (9).

[0142]

[0143]

[0144] in, The second industry average value obtained by executing the third preset script can be represented. The second industry average value in formula (9) can be the same as the first industry average value in formula (8), except that formula (9) is used to represent the case where the user's income year is less than n full years for the user's initial indicator set, and formula (8) is used to represent the case where the user's income year is greater than or equal to n full years for the user's initial indicator set.

[0145] According to an embodiment of the present disclosure, the first preset script is used to obtain The second preset script and the third preset script can both be used to obtain The first preset script, the second preset script and the third preset script can all be adaptively adjusted according to actual needs.

[0146] The process of determining the credit limit benchmark value in the embodiment of the present disclosure verifies the credit limit by accurately predicting the user's future income, which at least partially overcomes the problem that high-tech enterprises have fewer assets and the traditional method of using net assets as the base cannot accurately generate user credit limit data.

[0147] According to the embodiments of the present disclosure, the user's credit limit benchmark value is determined by dividing it into two situations. For users whose income year is greater than or equal to n full years and users whose income year is less than n full years, different functions are used to determine the user's credit limit benchmark value. This fully conforms to the characteristics of high-tech enterprises, improves the precision of generating user credit limit benchmark values, and thus improves the accuracy of generating credit limit data.

[0148] According to the embodiment of the present disclosure, through the above operations, the user's credit limit base value can be generated, but since the user's credit limit verification value needs to be determined in the process of determining the user's credit limit data, so that the user's credit limit data can be determined in a more fine-grained manner. Therefore, according to the subset of funds flow indicators, the process of determining the user's credit limit verification value can include the following operations: calling the limit verification function from the database; inputting the user's book asset amount, the preset business asset flow amount, and the non-preset business asset flow amount into the calling limit verification function, and outputting the user's credit limit verification value.

[0149] According to an embodiment of the present disclosure, the limit check line is the cash available for debt repayment predicted within the next year. The cash available for debt repayment includes the cash and equivalent balance at the end of the previous year and the cash flow that can be generated by operating activities, investment activities, and financing activities in the predicted year. The limit check function can be shown as formula (10).

[0150] Limit check line = X 账面资产额 +X 交易活动资产流量额 +X 投资活动资产流量额 +X 筹资活动资产流量额 +X 其他资金流入额 (10)

[0151] X 胀面资产额 At the end of the previous year, cash and cash equivalents refer to the book value of cash after deducting the restricted portion.

[0152] X 交易活动资产流量额 , the amount of asset flow from operating activities, in principle, is determined by the net asset flow generated by operating activities in the previous year. If the data of the previous year is obviously abnormal, it can be determined by the average value of the net asset flow in the N years before the forecast period (N can be less than or equal to 3).

[0153] x 投资活动资产流量额 , the amount of asset flow from investing activities refers to the realizable income from assets with strong liquidity, such as trading financial assets on the books at the end of the previous year.

[0154] X 筹资活动资产流量额 , the amount of asset flows from financing activities refers to the equity investment assets that can be received in the forecast year for which relevant evidence can be obtained.

[0155] X 其他现金流入 , other reasonable cash inflows, including science and technology subsidy funds that can be obtained.

[0156] According to an embodiment of the present disclosure, after obtaining the user's credit limit reference value and the credit limit verification value, the user's final credit limit data can be determined according to the credit limit function.

[0157] According to an embodiment of the present disclosure, the credit limit function may include a first credit limit function and a second credit limit function.

[0158] When the user's development potential coefficient value is greater than or equal to the preset threshold, the first credit limit function can be called to output the user's final credit limit data. The first credit limit function can be shown as formula (11).

[0159] Credit limit data = max{credit limit base value, credit limit verification value} (11)

[0160] Among them, when the user's development potential coefficient value is greater than or equal to a preset threshold, the user's final credit limit data can be the maximum value of the credit limit base value and the credit limit verification value.

[0161] When the user's development potential coefficient value is less than a preset threshold, the second credit limit function can be called to output the user's final credit limit data. The second credit limit function can be shown as formula (12).

[0162] Credit limit data = Credit limit benchmark value (12)

[0163] Among them, when the user's development potential coefficient value is less than a preset threshold, the user's final credit limit data may be a credit limit base value.

[0164] The preset threshold can be calculated through an artificial intelligence model based on historical high-tech customer credit data.

[0165] According to an embodiment of the present disclosure, in the process of determining the credit limit data, the credit limit verification value is added to reflect the asset flow of the user that can be used for debt repayment in the next year, so as to reflect the user's development potential.

[0166] By determining the user's credit limit data in two situations, different functions are used to determine the user's credit limit data for users whose development potential coefficient is greater than or equal to the preset threshold and users whose development potential coefficient is less than the preset threshold. This fully conforms to the characteristics of high-tech enterprises, improves the precision of generating user credit limit data, and thus improves the accuracy of generating credit limit data.

[0167] The data processing method provided by the embodiment of the present disclosure at least partially overcomes the problems in the prior art that the debt repayment situation of high-tech enterprise users cannot be correctly considered and the scientific research situation, market position, etc. of the high-tech enterprises are not considered. It provides a credit limit data generation method suitable for high-tech enterprises, assists banks in evaluating the security level of high-tech enterprises, and reasonably handles the credit business requests of enterprise users.

[0168] It should be noted that, unless it is explicitly stated that there is a sequence of execution between different operations shown in the flowchart in the embodiments of the present disclosure, or there is a sequence of execution between different operations in technical implementation, otherwise, the execution order of multiple operations may not be prioritized, and multiple operations may also be executed simultaneously.

[0169] Based on the above data processing method, the present disclosure also provides a data processing device. Figure 4 The device is described in detail.

[0170] Figure 4The structure block diagram of a data processing device according to an embodiment of the present disclosure is schematically shown.

[0171] like Figure 4 As shown, the data processing device 400 of this embodiment includes an export module 410 , a screening module 420 , a first determination module 430 and a generation module 440 .

[0172] The export module 410 is used to export the initial indicator set of the user from the database according to the user's identification in response to a request for obtaining the credit limit data of the user.

[0173] The screening module 420 is used to screen out a credit characteristic indicator set from the initial indicator set based on the correlation value between each indicator in the initial indicator set and the credit indicator, wherein the credit indicator includes a development potential indicator and a risk indicator, and the credit characteristic indicator set includes a development potential indicator subset and a risk indicator subset.

[0174] The first determination module 430 is used to determine the development potential coefficient value and the risk coefficient value of the user based on the development potential indicator subset and the risk indicator subset.

[0175] The generation module 440 is used to generate the user's credit limit data based on the initial indicator set, the development potential coefficient value and the risk coefficient value.

[0176] According to the data processing method, device, equipment, storage medium and program product provided by the embodiment of the present disclosure, the initial indicator set of the user is derived by responding to the request for obtaining the credit limit data; the development potential indicator subset and the risk indicator subset are screened out from the initial indicator set according to the correlation value between each indicator and the credit indicator; the development potential coefficient value and the risk coefficient value of the user are determined based on the above two subsets; and the credit limit data of the user is generated according to the initial indicator set, the development potential coefficient value and the risk coefficient value. Since in the process of generating the user limit data, the development potential indicator subset and the risk indicator subset are determined according to the initial indicator set of the user, and the development potential coefficient and the risk coefficient are determined. Since the development potential coefficient and the risk coefficient of the user are taken into account, the credit limit data of the user is no longer generated only according to the asset data of the user, and the utilization rate of the collected data resources is improved; and the credit limit data generated by the above method can provide a more comprehensive reference for the credit business, improve the security of the credit business, at least partially overcome the problems of low utilization rate of data resources and high risk of credit business in related technologies, and thus achieve the technical effect of improving the utilization rate of data resources and the security of credit business.

[0177] According to an embodiment of the present disclosure, the generation module may include a first determination submodule, a second determination submodule, a first input submodule, and a setting submodule.

[0178] The first determination submodule is used to determine the user's credit limit benchmark value based on the business indicator subset, the development potential coefficient value and the risk coefficient value.

[0179] The second determination submodule is used to determine the user's credit limit verification value based on the fund flow indicator subset.

[0180] The first input submodule is used to input the credit limit reference value and the credit limit verification value into the credit limit function and output the user's credit limit data when the user's development potential coefficient value is greater than or equal to a preset threshold.

[0181] The setting submodule is used to set the credit limit base value as the user's credit limit data when the user's development potential coefficient value is less than a preset threshold.

[0182] According to an embodiment of the present disclosure, the first determining submodule may include an extracting unit, a first input unit, a second input unit, and a first generating unit.

[0183] The extraction unit is used to extract a first indicator queue representing the user's order income characteristics and a second indicator queue representing the user's financial characteristic indicators from the business indicator subset.

[0184] The first input unit is used to input the first data queue corresponding to the first indicator queue into the order revenue function, and output the order revenue amount of the user within the first preset time period.

[0185] The second input unit is used to input the second data queue corresponding to the second indicator queue into the financial characteristic function, and output the financial characteristic indicator value of the user.

[0186] The first generating unit is used to generate a credit limit reference value for the user according to the order revenue amount, characteristic financial indicator value, development potential coefficient value and risk coefficient value of the user within a first preset time period.

[0187] According to an embodiment of the present disclosure, the first input unit may include a first input sub-unit and a second input sub-unit.

[0188] The first input subunit is used to input the first data queue into the first order revenue function and output the order revenue of the user within the first preset time period when both the current order revenue and the order revenue conversion rate are received.

[0189] The second input sub-unit is used to input the first data queue into the second order revenue function and output the order revenue of the user within the first preset time period when at least one of the current order revenue and the order revenue conversion rate cannot be received.

[0190] According to an embodiment of the present disclosure, the data processing device may further include an extraction module, a second determination module, a calling module, and a first input module.

[0191] The extraction module is used to extract from the first data queue the actual income growth rate of the user in the second preset time period, the industry average income growth rate of the user's industry, the user's income growth indicator evaluation value and the user's development stage indicator evaluation value.

[0192] The second determination module is used to determine the user's life cycle coefficient value based on the income growth indicator evaluation value and the development stage indicator evaluation value.

[0193] The calling module is used to call the expected income growth rate function from the database.

[0194] The first input module is used to input the user's life cycle coefficient value, actual income growth rate and industry average income growth rate into the expected income growth rate function, and output the user's expected income growth rate.

[0195] According to an embodiment of the present disclosure, the second input unit may include a retrieval subunit, a third input subunit, and a fourth input subunit.

[0196] The retrieval subunit is used to retrieve the sub-liability asset amount of the user within a third preset time period and the total liability asset amount of the user from the business indicator subset.

[0197] The third input sub-unit is used to input the second data queue into the first financial characteristic function and output the user's financial characteristic indicator value when the ratio of the sub-liability asset amount to the total liability asset amount is less than or equal to a preset ratio.

[0198] The fourth input sub-unit is used to input the second data queue into the second financial characteristic function and output the user's financial characteristic indicator value when the ratio of the sub-liability asset amount to the total liability asset amount is greater than a preset ratio.

[0199] According to an embodiment of the present disclosure, the first generating unit may include a reading subunit, a first executing subunit, a second executing subunit, and a fifth input subunit.

[0200] The reading subunit is used to read the credit limit benchmark function from the database, wherein the credit limit benchmark function includes a first credit limit benchmark function.

[0201] When the initial indicator set of the user represents that the user's income year is greater than or equal to n full years, the following operation is performed, where n is an integer greater than 1:

[0202] The first execution subunit is used to execute a first preset script to obtain the user's annual average value between the characteristic financial indicator value and the annual income amount of each year.

[0203] The second execution sub-unit is used to execute a second preset script to obtain a first industry average value between the sub-liability value and the characteristic financial indicator value of the industry in which the user is located.

[0204] The fifth input sub-unit is used to input the order revenue amount within the first preset time period, the user's annual average value, the first industry average value, the development potential coefficient value and the risk coefficient value into the first credit limit benchmark function, and output the user's credit limit benchmark value.

[0205] According to an embodiment of the present disclosure, the first generating unit may further include an extracting subunit, a third executing subunit, and a sixth inputting subunit.

[0206] In the case where the user's initial indicator set represents that the user's income year is less than n full years, the following operations are performed, where n is an integer greater than 1:

[0207] The extraction subunit is used to extract the total asset amount of the user from the business indicator subset.

[0208] The third execution subunit is used to execute a third preset script to obtain a second industry average value between the sub-liability value of the industry in which the user is located and the total asset amount associated with the industry.

[0209] The sixth input subunit is used to input the user's total assets, the second industry average value, the development potential coefficient value and the risk coefficient value into the second credit limit benchmark function, and output the user's credit limit benchmark value.

[0210] According to an embodiment of the present disclosure, the first determination module may include a first calling submodule, a second input submodule, a first processing submodule, and a first result submodule.

[0211] For the development potential coefficient value:

[0212] The first calling submodule is used to call the first weight function from the database.

[0213] The second input submodule is used to input the development potential data subset obtained by digitizing the development potential indicator subset into the first weight function to obtain multiple first initial weight values ​​corresponding to each of the multiple development potential indicators in the development potential indicator subset.

[0214] The first processing submodule is used to normalize the multiple first initial weight values ​​to obtain multiple first target weight values.

[0215] The first result submodule is used to obtain the user's development potential coefficient value based on the evaluation value of each development potential indicator and the first target weight value.

[0216] According to an embodiment of the present disclosure, the first determination module may further include a second calling submodule, a third input submodule, a second processing submodule, and a second result submodule.

[0217] For risk factor values:

[0218] The second calling submodule is used to call the second weight function from the database.

[0219] The third input submodule is used to input the risk data subset obtained by digitizing the risk indicator subset into the second weight function to obtain a plurality of second initial weight values ​​corresponding to each of the plurality of risk indicators in the risk indicator subset.

[0220] The second processing submodule is used to normalize the multiple second initial weight values ​​to obtain multiple second target weight values.

[0221] The second result submodule is used to obtain the risk coefficient value of the user based on the evaluation value of each risk indicator and the second target weight value.

[0222] According to an embodiment of the present disclosure, the second determining submodule may include a calling unit and a third input unit.

[0223] The calling unit is used to call the limit verification function from the database.

[0224] The third input unit is used to input the user's book asset amount, preset business asset flow amount and non-preset business asset flow amount into the calling limit verification function, and output the user's credit limit verification value.

[0225] According to an embodiment of the present disclosure, the screening module may include a collection submodule, a cleaning submodule, an encoding submodule, a fourth input submodule, a construction submodule, and a screening submodule.

[0226] The collection submodule is used to collect multiple historical indicators from the initial indicator set to obtain an initial historical indicator subset, wherein the historical indicators represent the historical business processing status of the user.

[0227] The cleaning submodule is used to clean the data of multiple historical indicators in the initial historical indicator subset to obtain the target historical indicator subset.

[0228] The encoding submodule is used to encode multiple historical indicators in the target historical indicator subset to obtain a numerical historical indicator subset.

[0229] The fourth input submodule is used to input the numerical historical indicator subset and the numerical credit indicator into the information gain function, and output a correlation value representing the correlation between each historical indicator and the credit indicator.

[0230] The construction submodule is used to build a decision tree model based on the correlation value.

[0231] The screening submodule screens out a credit feature indicator set from the target historical indicator subset according to the number of segmentation times and segmentation depth of the decision tree model.

[0232] According to an embodiment of the present disclosure, any multiple modules in the export module 410, the screening module 420, the first determination module 430 and the generation module 440 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the export module 410, the screening module 420, the first determination module 430 and the generation module 440 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the export module 410 , the screening module 420 , the first determination module 430 , and the generation module 440 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0233] It should be noted that the data processing device part in the embodiments of the present disclosure corresponds to the data processing method part in the embodiments of the present disclosure. The description of the data processing device part specifically refers to the data processing method part, which will not be repeated here.

[0234] Figure 5 A block diagram of an electronic device suitable for implementing a data processing method according to an embodiment of the present disclosure is schematically shown.

[0235] like Figure 5As shown, the electronic device 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include an onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0236] In RAM 503, various programs and data required for the operation of electronic device 500 are stored. Processor 501, ROM 502 and RAM 503 are connected to each other via bus 504. Processor 501 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 502 and / or RAM 503. It should be noted that the program can also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0237] According to an embodiment of the present disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to the bus 504. The electronic device 500 may further include one or more of the following components connected to the input / output (I / O) interface 505: an input portion 506 including a keyboard, a mouse, etc.; an output portion 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 508 including a hard disk, etc.; and a communication portion 509 including a network interface card such as a LAN card, a modem, etc. The communication portion 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage portion 508 as needed.

[0238] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0239] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 502 and / or RAM 503 described above and / or one or more memories other than ROM 502 and RAM 503.

[0240] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the data processing method provided by the embodiment of the present disclosure.

[0241] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 501. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0242] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 509, and / or installed from the removable medium 511. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0243] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the processor 501, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0244] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0245] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0246] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0247] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A data processing method, comprising: In response to a request for obtaining credit limit data of a user, deriving an initial indicator set of the user from a database according to an identification of the user; Based on the correlation value between each indicator in the initial indicator set and the credit indicator, a credit feature indicator set is screened out from the initial indicator set, wherein the credit indicator includes a development potential indicator and a risk indicator, and the credit feature indicator set includes a development potential indicator subset and a risk indicator subset; Determine the development potential coefficient value and the risk coefficient value of the user based on the development potential indicator subset and the risk indicator subset; Based on the initial indicator set, the development potential coefficient value and the risk coefficient value, the credit limit data of the user is generated.

2. The method according to claim 1, wherein: The initial indicator set includes a business indicator subset and a capital flow indicator subset; The generating the credit limit data of the user based on the initial indicator set, the development potential coefficient value and the risk coefficient value comprises: Determining a credit limit benchmark value for the user according to the business indicator subset, the development potential coefficient value, and the risk coefficient value; Determining the credit limit verification value of the user according to the fund flow indicator subset; In the case where the development potential coefficient value of the user is greater than or equal to a preset threshold, the credit limit reference value and the credit limit verification value are input into a credit limit function, and the credit limit data of the user is output; When the development potential coefficient value of the user is less than the preset threshold, the credit limit reference value is set as the credit limit data of the user.

3. The method according to claim 2, wherein: Determining the credit limit reference value of the user according to the business indicator subset, the development potential coefficient value and the risk coefficient value includes: Extracting a first indicator queue representing the order revenue characteristics of the user and a second indicator queue representing the financial characteristic indicators of the user from the business indicator subset; Inputting a first data queue corresponding to the first indicator queue into an order revenue function, and outputting the order revenue amount of the user within a first preset time period; Inputting a second data queue corresponding to the second indicator queue into a financial characteristic function, and outputting the financial characteristic indicator value of the user; A credit limit benchmark value for the user is generated based on the order revenue amount of the user within the first preset time period, the characteristic financial indicator value, the development potential coefficient value, and the risk coefficient value.

4. The method according to claim 3, wherein: The order revenue function includes a first order revenue function and a second order revenue function, wherein the first order revenue function is constructed based on the current order revenue amount of the user and the order revenue conversion rate of the user in the first preset time period, and the second order revenue function is constructed based on the order revenue amount of the user in the second preset time period and the expected revenue growth rate of the user, and the second preset time period is earlier than the first preset time period; The step of inputting the first data queue corresponding to the first indicator queue into the order revenue function and outputting the order revenue amount of the user in the first preset time period comprises: When the current order revenue amount and the order revenue conversion rate are both received, the first data queue is input into the first order revenue function, and the order revenue amount of the user within the first preset time period is output; When at least one of the current order revenue amount and the order revenue conversion rate cannot be received, the first data queue is input into the second order revenue function to output the order revenue amount of the user within the first preset time period.

5. The method according to claim 4, wherein: The expected income growth rate of the user is constructed as follows: Extracting from the first data queue the actual income growth rate of the user in the second preset time period, the average income growth rate of the industry to which the user belongs, the income growth indicator evaluation value of the user, and the development stage indicator evaluation value of the user; Determining the life cycle coefficient value of the user according to the income growth indicator evaluation value and the development stage indicator evaluation value; Calling the expected income growth rate function from the database; The user's life cycle coefficient value, the actual income growth rate and the industry average income growth rate are input into the expected income growth rate function, and the user's expected income growth rate is output.

6. The method according to claim 3, wherein: The financial characteristic function includes a first financial characteristic function and a second financial characteristic function, wherein the first financial characteristic function is constructed based on the cost asset amount of the user, and the second financial characteristic function is constructed based on the total asset amount of the user; The step of inputting the second data queue corresponding to the second indicator queue into the financial characteristic function and outputting the financial characteristic indicator value of the user comprises: Retrieving the sub-liability asset amount of the user within a third preset time period and the total liability asset amount of the user from the business indicator subset; In the case where the ratio of the sub-liability asset amount to the total liability asset amount is less than or equal to a preset ratio, inputting the second data queue into the first financial characteristic function, and outputting the financial characteristic index value of the user; When the ratio of the sub-liability asset amount to the total liability asset amount is greater than a preset ratio, the second data queue is input into the second financial characteristic function, and the financial characteristic index value of the user is output.

7. The method according to claim 3, wherein: The generating of the user's credit limit reference value according to the user's order revenue amount within the first preset time period, the characteristic financial indicator value, the development potential coefficient value, and the risk coefficient value comprises: Reading a credit limit benchmark function from the database, wherein the credit limit benchmark function includes a first credit limit benchmark function; In the case where the initial indicator set of the user represents that the income year of the user is greater than or equal to n full years, performing the following operation, where n is an integer greater than 1; Executing a first preset script to obtain the user's annual average value between the characteristic financial indicator value and the annual income amount of each year of the user; Execute a second preset script to obtain a first industry average value between the sub-liability value and the characteristic financial indicator value of the industry where the user is located; The order revenue amount within the first preset time period, the user's annual average value, the first industry average value, the development potential coefficient value and the risk coefficient value are input into the first credit limit benchmark function, and the credit limit benchmark value of the user is output.

8. The method according to claim 7, wherein: The credit limit benchmark function also includes a second credit limit benchmark function; The generating of the user's credit limit reference value according to the user's order revenue amount, the characteristic financial indicator value, the development potential coefficient value, and the risk coefficient value within the first preset time period further includes: In the case where the initial indicator set of the user represents that the income year of the user is less than n complete years, performing the following operation, wherein n is an integer greater than 1; Extracting the total asset amount of the user from the business indicator subset; Executing a third preset script to obtain a second industry average value between the sub-liability value of the industry to which the user belongs and the total asset amount associated with the industry; The total assets of the user, the second industry average, the development potential coefficient value and the risk coefficient value are input into the second credit limit benchmark function, and the credit limit benchmark value of the user is output.

9. The method according to claim 1, wherein: The determining of the development potential coefficient value and the risk coefficient value of the user based on the development potential indicator subset and the risk indicator subset comprises: For the development potential coefficient value: calling a first weight function from the database; Inputting the development potential data subset obtained by digitizing the development potential indicator subset into the first weight function to obtain a plurality of first initial weight values ​​corresponding to each of the plurality of development potential indicators in the development potential indicator subset; Normalizing the first initial weight values ​​to obtain a plurality of first target weight values; Based on the evaluation value of each of the development potential indicators and the first target weight value, the development potential coefficient value of the user is obtained.

10. The method according to claim 9, wherein: The step of determining the development potential coefficient value and the risk coefficient value of the user based on the development potential indicator subset and the risk indicator subset further comprises: For the risk factor values: calling a second weight function from the database; Inputting the risk data subset obtained by digitizing the risk indicator subset into the second weight function to obtain a plurality of second initial weight values ​​corresponding to each of the plurality of risk indicators in the risk indicator subset; Normalizing the plurality of second initial weight values ​​to obtain a plurality of second target weight values; Based on the evaluation value of each of the risk indicators and the second target weight value, a risk coefficient value of the user is obtained.

11. The method according to claim 2, wherein: The fund flow indicator subset includes the book asset amount of the user, the preset business asset flow amount of the user, and the non-preset business asset flow amount of the user; Determining the credit limit verification value of the user according to the fund flow indicator subset includes: Calling a limit verification function from the database; The book value of the user's assets, the preset business asset flow amount and the non-preset business asset flow amount are input into the calling limit verification function, and the credit limit verification value of the user is output.

12. The method according to claim 1, wherein: The selecting a credit feature indicator set from the initial indicator set based on the correlation value between each indicator in the initial indicator set and the credit indicator comprises: Collecting multiple historical indicators from the initial indicator set to obtain an initial historical indicator subset, wherein the historical indicators represent the historical business processing status of the user; Performing data cleaning on a plurality of the historical indicators in the initial historical indicator subset to obtain a target historical indicator subset; Performing encoding processing on a plurality of the historical indicators in the target historical indicator subset to obtain a numerical historical indicator subset; Inputting the numerical historical indicator subset and the numerical credit indicator into the information gain function, and outputting a correlation value representing the correlation between each historical indicator and the credit indicator; Constructing a decision tree model according to the correlation value; The credit feature indicator set is selected from the target historical indicator subset according to the number of segmentation times and segmentation depth of the decision tree model.

13. A data processing device, comprising: An export module, configured to export an initial indicator set of the user from a database according to an identifier of the user in response to a request for obtaining credit limit data of the user; A screening module, configured to screen out a credit feature indicator set from the initial indicator set based on the correlation value between each indicator in the initial indicator set and the credit indicator, wherein the credit indicator includes a development potential indicator and a risk indicator, and the credit feature indicator set includes a development potential indicator subset and a risk indicator subset; A first determination module, used for determining the development potential coefficient value and the risk coefficient value of the user based on the development potential indicator subset and the risk indicator subset; A generation module is used to generate the credit limit data of the user based on the initial indicator set, the development potential coefficient value and the risk coefficient value.

14. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 12.

15. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 12.

Images